CN108633249B - Physiological signal quality judgment method and device - Google Patents

Abstract

A physiological signal quality judgment method and device relate to the field of wearable devices, which can improve the accuracy of the physiological signal quality judgment result and reduce the calculation amount in the physiological signal quality judgment process. The specific scheme is: S301, collecting physiological signals, which are periodic signals or quasi-periodic signals; S302, extracting feature points of the physiological signals, the feature points including feature points used to indicate the period of the physiological signals; S303, according to the physiological signals The characteristic point of , divides the period to the physiological signal; S304, judges the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set; Wherein, the signal template set includes N signals Template, N signal templates are obtained according to the physiological signal before the signal of the ith cycle, N is greater than or equal to 2, and i is greater than N. The method and device are used in the process of judging the quality of the physiological signal before obtaining the physiological information of the human body according to the physiological signal of the human body.

Description

A kind of physiological signal quality judgment method and device

This application claims the priority of the Chinese patent application filed on January 25, 2017 with the application number 201710061354.0 and the invention titled "Method and System for Real-time Physiological Signal Quality Judgment with Extremely Low Resource Consumption", the entire contents of which are approved by Reference is incorporated in this application.

technical field

Embodiments of the present invention relate to the field of wearable devices, and in particular, to a method and device for judging the quality of a physiological signal.

Background technique

In recent years, wearable devices have been gradually applied to the physiological monitoring of the human body due to their non-invasive, simple and flexible characteristics. Wearable devices can provide patients with low-load, non-contact, long-term continuous physiological monitoring, such as monitoring the human body's electrocardiogram (ECG), pulse wave (Photoplethsmogram, PPG), respiration, blood pressure and other physiological signals. Among them, the pulse wave is the abbreviation of the electrical plethysmography information. At present, wearable devices obtain physiological signals of the human body through wearable sensors, and wearable sensors are easily interfered by noise and motion artifacts, which make the obtained physiological signals and human physiological information obtained based on them deviate from the real situation. Therefore, before using the physiological signal to obtain the physiological information of the human body, the signal quality of the physiological signal must be judged. Specifically, it is determined whether the above-mentioned physiological signal is a normal physiological signal or an abnormal physiological signal interfered by noise and motion artifacts.

In the prior art, before judging the quality of the obtained physiological signals such as human electrocardiogram, pulse wave, respiration, blood pressure, etc., it is usually necessary to preset a signal template for judging the quality of the above-mentioned physiological signals; and, in the process of obtaining the above-mentioned physiological signals. , it is usually necessary to accurately obtain a large number of characteristic values of the physiological signal, that is, to accurately extract a large number of characteristic points of the physiological signal; thus, the quality of the physiological signal is judged according to the above-mentioned preset signal template and the above-mentioned large number of accurate characteristic values.

The problem is that the above preset signal templates are usually obtained from a large number of offline physiological signals using machine learning algorithms or prior knowledge, and there is a certain deviation between offline physiological signals and real-time physiological signals. The accuracy of the physiological signal quality judgment result obtained from the preset signal template needs to be improved. In addition, since the current wearable sensors are usually relatively simple, some features of physiological signals, such as the peaks of dichotomous waves, may not be extracted, that is, the above-mentioned large number of accurate feature values may not be obtained; in this way, according to the above-mentioned large number of The accuracy of the physiological signal quality judgment result obtained by the precise eigenvalues needs to be improved, and the calculation amount in the process of judging the physiological signal quality is relatively large.

SUMMARY OF THE INVENTION

The present application provides a method and device for judging the quality of physiological signals, which can improve the accuracy of the results of judging the quality of physiological signals and reduce the amount of calculation in the process of judging the quality of physiological signals.

To achieve the above object, the application adopts the following technical solutions:

In a first aspect, a method for judging the quality of a physiological signal is provided, the method for judging the quality of a physiological signal includes: collecting a physiological signal, where the physiological signal is a periodic signal or a quasi-periodic signal; The characteristic point of the physiological signal cycle; according to the characteristic point of the physiological signal, the physiological signal is divided into cycles; according to the similarity between the signal of the ith cycle and the current signal template set, the signal quality of the signal of the ith cycle is judged; Wherein, the above-mentioned signal template set includes N signal templates, the N signal templates are obtained according to the physiological signal before the signal of the ith cycle, N is greater than or equal to 2, and i is greater than N. Generally speaking, each signal template of the N signal templates in the current signal template set is a physiological signal of better quality. Therefore, if the similarity between the signal of the ith cycle and the current signal template set is higher, it means that the signal quality of the signal of the ith cycle is better; the difference between the signal of the ith cycle and the current signal template set is better. The lower the similarity, the worse the signal quality of the i-th cycle signal.

It should be noted that, in the physiological signal quality judgment method provided by this application, the current signal template set for judging the physiological signal quality is obtained according to the physiological signal acquired in real time, rather than using machine learning algorithms or prior knowledge to determine the quality of physiological signals from a large number of Therefore, the current signal template provided by the present application is more in line with the physiological signal acquired in real time, so that the accuracy of the physiological signal quality judgment result obtained according to the above-mentioned current signal template set is higher.

In a possible implementation manner, the signal quality of the signal in the ith cycle can be judged by judging whether the signal in the ith cycle reaches the standard of a normal physiological signal, that is, whether the signal in the ith cycle is a normal physiological signal or an abnormal physiological signal Signal. Specifically, the above-mentioned judging the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the signal template set may include: determining the similarity result of the signal of the ith cycle, the signal of the ith cycle The similarity result of the signal is used to indicate the similarity between the signal of the ith cycle and the current signal template set; if the similarity result of the signal of the ith cycle satisfies the preset similarity condition, the signal of the ith cycle is judged to be normal For physiological signals, the preset similarity conditions are preset; if the similarity results of the signals in the ith cycle do not meet the preset similarity conditions, the signals in the ith cycle are determined to be abnormal physiological signals.

Wherein, the similarity between the signal of the i-th cycle and the current signal template set can be represented by similarity parameters such as the correlation coefficient and mean square error between the sample sequence of the signal of the i-th cycle and the sample sequence of the signal template. For example, when the similarity parameter of the signal in the ith cycle is the correlation coefficient, the greater the similarity parameter of the signal in the ith cycle, the higher the similarity and the better the signal quality. The smaller the similarity parameter of the signal in the ith cycle, the lower the similarity and the worse the signal quality.

In a possible implementation manner, when it is determined that the similarity result of the signal of the ith cycle is better than the similar result of at least one signal template in the N signal templates, the above method may further include: according to the signal of the ith cycle Signal updates the current set of signal templates. That is to say, if the signal quality of the signal of the ith cycle is higher than that of at least one signal template in the N signal templates in the current signal template set, the above method can replace the signal according to the signal of the ith cycle template to update the current set of signal templates above. Wherein, the similar result of one signal template among the above N signal templates is obtained according to the physiological signal before the signal of the ith cycle.

It should be noted that the above-mentioned current signal template set is continuously updated according to the physiological signals acquired in real time. Wherein, a signal template with relatively poor signal quality is replaced according to a signal of a period with better signal quality to update the current signal template set, so that the signal quality of the signal templates in the current signal template set is improved in real time. In this way, the accuracy of the physiological signal quality judgment result obtained according to the current signal template set updated in real time is relatively high.

In a possible implementation manner, since the signal quality of the signal in the i-th cycle is related to the similar result of the signal in the i-th cycle, the current signal template set can be updated according to the similar result of the signal in the i-th cycle. Specifically, the above-mentioned updating of the current signal template set according to the signal of the ith cycle may include: when it is determined that the similar result of the signal of the ith cycle is better than the similar result of at least one signal template in the N signal templates: using the ith cycle The signal of i cycles replaces the signal template with the worst similar result in the current signal template set.

Optionally, the above "use the signal of the i-th cycle to replace the signal template with the worst similar result in the current signal template set" can be replaced with the signal of the i-th cycle to replace any signal template with a poor similar result in the current signal template set. Signal template. Wherein, the similarity result of any of the above-mentioned signal templates with poor similarity results is worse than the similarity result of the signal of the ith cycle.

In a possible implementation manner, before judging the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set, the above method may further include: according to the ith cycle The physiological signal before the signal gets the current signal template set.

Wherein, the above-mentioned current signal template set may be an updated signal template set, for example, the current signal template set may be a signal template set updated according to the signal of the i-1th cycle. Alternatively, the above-mentioned current signal template set may be a signal template set that has not been updated.

In a possible implementation manner, obtaining the current signal template set according to the physiological signal before the signal of the ith cycle may include: obtaining an initial signal template set according to the signals of the first N+a cycles; according to the initial signal template set and The physiological signal between the signal of the N+a th cycle and the signal of the ith cycle obtains the current signal template set. Wherein, the above-mentioned initial signal template set is a signal template set that has not been updated.

It should be noted that the N signal templates in the above initial signal template set are not necessarily all normal physiological signals with good signal quality, but the above physiological signal quality judgment method can be executed as long as the initial signal template set includes N signal templates. Wherein, while the above method obtains the current signal template set according to the initial signal template set and the physiological signal between the signal of the N+ath cycle and the signal of the ith cycle, it can also obtain the current signal template set according to the signal of the N+ath cycle. Similar results of the signals of each cycle between the signals of the ith cycle determine the signal quality of the signal of each cycle.

In a possible implementation manner, obtaining the initial signal template set according to the signals of the first N+a cycles may include: determining a similar result of the signals of each cycle in the signals of the first N+a cycles; a is greater than or equal to Integer of 0, N+a is less than i; where the similar result of the signal of one cycle in the signal of the first N+a cycles is determined by the signal of the cycle and the signal of the previous N+a cycles except the signal of the cycle It is composed of the similarity between the signals of other cycles; the signals of the first N cycles with the best similarity result among the signals of the first N+a cycles are determined as the initial signal template set.

Wherein, when a is equal to 0, the N signal templates in the above-mentioned initial signal template set are the signals of the first N cycles. When a is greater than 0, the signals of the first N+a periods have a period of signals that are not the signal templates in the initial signal template set. It should be noted that after determining the similarity of the signals of each cycle in the signals of the first N+a cycles, the signal quality of the signals of each cycle of the signals of the first N+a cycles can also be judged.

In a possible implementation manner, after extracting the characteristic points of the physiological signal, the method may further include: obtaining the characteristic value of the signal of the i-th cycle according to the characteristic point of the physiological signal; determining that the characteristic value of the signal of the i-th cycle is not It is within the current preset threshold range, and it is judged that the signal of the ith cycle is an abnormal physiological signal, and the current preset threshold range is determined according to the signal of the cycle before the signal of the ith cycle; Before judging the signal quality of the signal in the ith cycle based on similarity between template sets, the above method may further include: determining that the characteristic value of the signal in the ith cycle is within the current preset threshold range.

It should be noted that, since the above-mentioned current preset threshold value range is obtained according to the signals of all cycles in the physiological signal acquired in real time, that is, the current preset threshold value range is obtained according to the global variable; therefore, the above-mentioned current preset threshold value range conforms to the real-time acquisition. physiological signals. Therefore, the method for judging the quality of the physiological signal provided by the present application can further improve the accuracy of the judgment result of the quality of the physiological signal.

In a possible implementation manner, in the case that the extracted characteristic points of the physiological signal include a vertex and a bottom point, the characteristic value of the signal in the i-th cycle includes: the period value of the signal in the i-th cycle and/or The height value of the signal for the ith cycle. Therefore, the current preset threshold value range may include: the current preset period range and/or the current preset height range. Specifically, the characteristic value of the signal of the ith cycle is not within the current preset threshold range may include: the period value of the signal of the ith cycle is not within the current preset cycle range, and/or the height of the signal of the ith cycle The value is not within the current preset altitude range. The characteristic value of the signal in the ith cycle being in the current preset threshold range may include: the cycle value of the signal in the ith cycle is in the current preset cycle range and the height value of the signal in the ith cycle is in the current preset height range.

It should be noted that the method provided in this application can determine the signal quality of the signal of each cycle in the physiological signal by extracting the apex and the bottom point in the characteristic value of the physiological signal, which can reduce the process of judging the quality of the physiological signal to a certain extent. the amount of computation in .

In a possible implementation manner, before obtaining the characteristic value of the signal of the i-th cycle according to the characteristic point of the physiological signal, the above method may further include: determining the current signal according to the signal of the cycle before the signal of the i-th cycle. Preset threshold range; after acquiring the characteristic value of the signal in the i-th cycle according to the characteristic point of the physiological signal, the method further includes: updating the current preset threshold range according to the characteristic value of the signal in the i-th cycle.

Wherein, since the above-mentioned current preset threshold value range is continuously updated according to the physiological signal acquired in real time; therefore, the above-mentioned current preset threshold value range is consistent with the physiological signal acquired in real time. Therefore, the method for judging the quality of the physiological signal provided by the present application can further improve the accuracy of the judgment result of the quality of the physiological signal.

In a possible implementation manner, the above method may further include: outputting a signal quality judgment result, where the signal quality judgment result includes that the signal in the ith cycle is a normal physiological signal or the signal in the ith cycle is an abnormal physiological signal, and The signal of each cycle before the signal of the ith cycle is a normal physiological signal or the signal of each cycle is an abnormal physiological signal. Among them, if the similar result of the signal of a cycle before the signal of the ith cycle satisfies the preset similarity condition, the signal of this cycle is a normal physiological signal; if the similar result of the signal of a cycle before the signal of the ith cycle If the preset similar conditions are not met, the signal of this period is an abnormal physiological signal.

It should be noted that the method for judging the quality of physiological signals provided by the present application can judge the signal quality of the collected physiological signals in real time and cycle by cycle, and more accurately distinguish whether the signal of any cycle in the physiological signal is a normal physiological signal or a cycle-by-cycle signal. Abnormal physiological signals. In this way, more accurate human physiological information can be obtained according to the normal physiological signal obtained by the judgment. Moreover, the output signal quality judgment result enables the result to be more intuitively displayed to the user or the related technical personnel, so as to improve the user experience or meet the requirements of the related technical personnel.

In a second aspect, a device for judging the quality of a physiological signal is provided, including a collection module, an extraction module, a division module and a judgment module. Among them, the acquisition module is used to collect physiological signals, and the physiological signals are periodic signals or quasi-periodic signals. The extraction module is used for extracting the characteristic points of the physiological signal collected by the collection module, and the characteristic points include characteristic points used to indicate the period of the physiological signal. The dividing module is used for dividing the period of the physiological signal according to the characteristic points of the physiological signal extracted by the extraction module. The judgment module is used to judge the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set; wherein, the signal template set includes N signal templates, and the N signal templates are based on For the acquisition of the physiological signal before the signal of the ith cycle collected by the acquisition module, N is greater than or equal to 2, and i is greater than N.

In a possible implementation manner, the above apparatus may further include: a determining module. Wherein, the determining module is used to determine the similarity result of the signal of the ith cycle divided by the dividing module, and the similarity result of the signal of the ith cycle is used to indicate the similarity between the signal of the ith cycle and the current signal template set sex. The above judgment module is specifically configured to judge that the signal of the ith cycle is a normal physiological signal if the similarity result of the signal of the ith cycle satisfies the preset similarity condition, and the preset similarity condition is preset; If the similarity result of the signal does not meet the preset similarity condition, it is determined that the signal of the i-th cycle is an abnormal physiological signal.

In a possible implementation manner, the above apparatus may further include: an update module. Wherein, the updating module is configured to update the current signal template set according to the signal of the ith cycle under the condition that the similar result of the signal of the ith cycle is determined to be better than the similar result of at least one signal template in the N signal templates, wherein , the similarity of one signal template among the N signal templates is obtained according to the physiological signal before the signal of the ith cycle.

In a possible implementation manner, the above updating module is specifically configured to replace the signal template with the worst similar result in the current signal template set with the signal of the ith cycle.

In a possible implementation manner, the above apparatus may further include: an acquisition module. Wherein, the acquisition module is configured to, before the judgment module judges the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set, according to the signal quality of the ith cycle The current signal template set is obtained from the physiological signal before the signal.

In a possible implementation manner, the above-mentioned obtaining module is specifically configured to obtain the initial signal template set according to the signals of the first N+a cycles; The physiological signal between the signals gets the current signal template set.

In a possible implementation manner, the above determination module can also be used to determine the similarity of the signals of each cycle in the signals of the first N+a cycles; a is an integer greater than or equal to 0, and N+a is less than i; Among them, the similarity result of the signal of one cycle in the signal of the first N+a cycles is determined by the similarity between the signal of the cycle and the signals of other cycles except the signal of the cycle in the signal of the previous N+a cycles consist of. The above obtaining module is specifically configured to determine, among the signals of the first N+a cycles determined by the above determining module, the signals of the first N cycles with the best similarity result as the initial signal template set.

In a possible implementation manner, the above obtaining module may be further configured to obtain the characteristic value of the signal of the ith cycle according to the characteristic point of the physiological signal after the extraction module extracts the characteristic point of the physiological signal. The above judgment module can also be used to determine that the characteristic value of the signal in the ith cycle is not within the current preset threshold range, and determine that the signal in the ith cycle is an abnormal physiological signal, and the current preset threshold range is based on the ith cycle. Before judging the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set, determine that the eigenvalue of the signal of the ith cycle is in the The current preset threshold range.

In a possible implementation manner, the characteristic value of the signal in the i-th cycle includes: a period value of the signal in the i-th cycle and/or a height value of the signal in the i-th cycle. The current preset threshold value range may include: the current preset period range and/or the current preset height range. The characteristic value of the signal in the i-th cycle is not in the current preset threshold range may include: the cycle value of the signal in the i-th cycle is not in the current preset cycle range, and/or the height value of the signal in the i-th cycle is not in the range The current preset altitude range. The characteristic value of the signal in the ith cycle being in the current preset threshold range may include: the cycle value of the signal in the ith cycle is in the current preset cycle range, and the height value of the signal in the ith cycle is in the current preset height range .

In a possible implementation manner, the above-mentioned determining module may also be used to obtain the characteristic value of the signal of the i-th cycle according to the characteristic point of the physiological signal by the obtaining module, according to the cycle before the signal of the i-th cycle The signal determines the current preset threshold range. The above updating module can also be used to update the current preset threshold range according to the characteristic value of the signal in the i-th cycle after the acquisition module obtains the characteristic value of the signal in the i-th cycle according to the characteristic point of the physiological signal.

In a possible implementation manner, the above apparatus may further include: an output module. The output module is used for outputting the signal quality judgment result, and the signal quality judgment result includes that the signal of the i-th cycle obtained by the judgment module is a normal physiological signal or the signal of the i-th cycle is an abnormal physiological signal, and the signal of the i-th cycle is an abnormal physiological signal. The signal of each cycle before the signal is a normal physiological signal or the signal of each cycle is an abnormal physiological signal. Wherein, if the similarity result of the signal of a cycle before the signal of the ith cycle satisfies the preset similarity condition, the signal of the cycle is judged to be a normal physiological signal; if the signal of a cycle before the signal of the ith cycle is similar If the result does not satisfy the preset similarity condition, it is determined that the signal of the period is an abnormal physiological signal.

In a third aspect, a physiological signal quality judging device may include a processor, a memory, a display, an input device and a bus; the memory is used to store the at least one instruction, the processor, the memory, the The display and the input device are connected through the bus, and when the device is running, the processor executes at least one instruction stored in the memory, so that the device performs the physiological signal quality judgment in the first aspect and various optional manners of the first aspect method.

In a fourth aspect, a computer storage medium is provided, and at least one instruction is stored in the computer storage medium; when the at least one instruction is executed on a computer, the computer is made to execute various optional manners such as the first aspect and the first aspect. Physiological signal quality judgment method in .

In a fifth aspect, a computer program is provided, and at least one instruction is stored in the computing program product; when the at least one instruction is executed on a computer, the computer is made to execute the first aspect and various optional manners of the first aspect. Physiological signal quality judgment method.

It should be noted that the processor in the third aspect of the present application may be an integration of functional modules such as an extraction module, a division module, a judgment module, a determination module, an update module, and an acquisition module in the second aspect, and the processor may implement the first The second aspect is the functions of the above-mentioned functional modules. For detailed descriptions and analysis of beneficial effects of the modules in the second aspect and the third aspect, reference may be made to the corresponding descriptions and technical effects in the first aspect and various possible implementations thereof, which will not be repeated here.

Description of drawings

FIG. 1 is a schematic structural diagram of a wearable device according to an embodiment of the present invention;

FIG. 2 is a schematic waveform diagram of a physiological signal provided by an embodiment of the present invention;

3 is a schematic flowchart of a method for judging the quality of a physiological signal provided by an embodiment of the present invention;

FIG. 4 is a schematic waveform diagram of another physiological signal provided by an embodiment of the present invention;

FIG. 5 is a schematic waveform diagram of another physiological signal provided by an embodiment of the present invention;

6 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

7 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

8 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

9 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

10 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

11 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

12 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

13 is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention;

14 is a schematic flowchart of another method for determining the quality of a physiological signal provided by an embodiment of the present invention;

15 is a schematic diagram of a possible composition of the apparatus for determining the quality of a physiological signal provided by an embodiment of the present invention;

FIG. 16 is a schematic diagram of another possible composition of the apparatus for determining the quality of a physiological signal provided by an embodiment of the present invention;

FIG. 17 is another possible schematic diagram of the composition of the apparatus for judging the quality of a physiological signal provided by an embodiment of the present invention;

18 is a schematic diagram of another possible composition of the apparatus for determining the quality of a physiological signal provided by an embodiment of the present invention;

FIG. 19 is a schematic diagram of another possible composition of the apparatus for determining the quality of a physiological signal provided by an embodiment of the present invention;

FIG. 20 is a schematic diagram of another possible composition of the apparatus for determining the quality of a physiological signal provided by an embodiment of the present invention.

Detailed ways

Embodiments of the present invention provide a method and device for judging the quality of a physiological signal, which are applied in the process of obtaining physiological information of the human body according to the physiological signal of the human body, and are specifically applied to the process of judging the quality of the physiological signal before obtaining the physiological information of the human body according to the physiological signal of the human body. In the process, the accuracy of the result of judging the quality of the physiological signal can be improved, and the amount of calculation in the process of judging the quality of the physiological signal can be reduced.

The technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

In the method for judging the quality of a physiological signal provided by the embodiment of the present invention, the involved physiological signal may be a periodic or quasi-periodic physiological signal, such as a human body's electrocardiogram, pulse wave, respiration, blood pressure and other periodic physiological signals. The above physiological signals all contain a large amount of physiological information of the human body. For example, the pulse wave signal of the human body may contain physiological information such as the heart rate, the respiratory rate, and the blood oxygen of the human body.

It should be noted that, in the method for judging the quality of physiological signals provided by the embodiments of the present invention, in addition to judging the signal quality of the above-mentioned physiological signals, the quality of other signals having periodicity or quasi-periodic signals can also be judged, such as in the pedometer algorithm. The acceleration signal is not limited in this embodiment of the present invention.

The apparatus for determining the quality of a physiological signal provided by the embodiment of the present invention may be a wearable device capable of acquiring a physiological signal of a human body. Among them, wearable devices are portable devices that are directly worn on the user's body or integrated into the user's clothes or accessories, and most wearable devices have built-in intelligent systems that can be connected to mobile phones and various terminals. It has one or more of the above functions such as taking pictures, GPS positioning, family calls, intelligent anti-lost, monitoring sleep, monitoring heart rate, and running steps. Common wearable devices include wrist-supported smart bracelets, smart watches and other products, foot-supported smart shoes, socks or other leg-wearing products, and head-supported smart glasses, helmets, and headbands and other products, as well as various forms of products such as smart body temperature stickers, heart rate belts, smart clothing, school bags, crutches, accessories, etc.

Exemplarily, FIG. 1 is a schematic structural diagram of a wearable device provided by an embodiment of the present invention. Referring to FIG. 1 , the wearable device 10 may include one or more of the following components: a sensor component 101, a memory 102, a processing component 103, A multimedia component 104 , an audio component 105 , an input/output (I/O) interface 106 , a power supply component 107 , and a communication component 108 .

Wherein, the sensor assembly 101 includes one or more sensors for providing the wearable device 10 with state assessment in various aspects. The state changes in various aspects provided by the above-mentioned wearable device 10 may be caused by the operation of the user who uses the wearable device 10, or caused by changes in the physiological information of the user.

Exemplarily, the sensor assembly 101 can detect the open/closed state of the wearable device 10 and the relative positioning of the assembly. The sensor assembly 101 may also detect changes in the position of the wearable device 10 or one of its components, the orientation or acceleration/deceleration of the wearable device 10 and the temperature change of the wearable device 10 . Sensor assembly 101 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. Specifically, the sensor assembly 101 may include a pulse sensor, such as an infrared pulse sensor, a heart rate pulse sensor, a photoelectric pulse sensor, a wrist pulse sensor, or a digital pulse sensor, etc., for detecting the user's pulse wave, so that the human body's heart rate and other physiological parameters can be obtained. information. Among them, the commonly used pulse sensor may be a PPG sensor. The sensor assembly 101 may include a blood pressure sensor for detecting the blood pressure of the human body. In some embodiments, sensor assembly 101 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. For example, the above-mentioned CMOS or CCD image sensor can be used to acquire video signals of exposed skin parts such as the face and hands of the human body. Wherein, the above-mentioned video signal may include multiple frames, each frame is a two-dimensional image, and the two-dimensional image is a red, green, and blue RGB image, and the RGB image can be divided into three channels: R-channel image, G-channel image and B-channel image image, these three-way images can be used to extract the pulse wave signal of the human body. In other embodiments, the sensor assembly 101 may further include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

The memory 102 is configured to store various types of data to support the operation of the wearable device 10 . Examples of such data include instructions for any application or method operating on the wearable device 10, contact data, phonebook data, messages, pictures, videos, and data such as human physiological information. Memory 102 may be implemented by any type of volatile or non-volatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

The processing component 103 generally controls the overall operation of the wearable device 10, such as operations associated with display, phone calls, data communications, camera operations, and recording operations, as well as processing signals or data acquired by sensors. Specifically, after the sensor component 101 detects and acquires the physiological signal, the processing component 103 can judge the quality of the physiological signal, and obtain that the physiological signal is a normal physiological signal or the physiological signal is an abnormal physiological signal; thus, the human body can be obtained according to the normal physiological signal physiological information. Among others, the processing component 103 may include one or more processors 1031 to execute the instructions. Additionally, processing component 103 may include one or more modules to facilitate interaction between processing component 103 and other components. For example, processing component 103 may include a multimedia module to facilitate interaction between multimedia component 104 and processing component 103 .

Multimedia component 104 includes a screen that provides an output interface between wearable device 10 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The above-mentioned touch sensor may not only sense the boundary of the touch or swipe action, but also detect the duration and pressure associated with the above-mentioned touch or swipe action. In some embodiments, the multimedia component 104 includes a camera. When the wearable device 10 is in an operation mode, such as a shooting mode or a video mode, the camera can receive external multimedia data. Each camera can be a fixed optical lens system or have focal length and optical zoom capability. Of course, in addition to the above-mentioned video signals obtained by the above-mentioned sensors such as the CMOS or CCD image sensor, the above-mentioned video signals for the exposed parts of the skin such as the face and hands of the human body can also be obtained by the camera in the multimedia component 104, and the embodiment of the present invention is not limited to this. Not limited.

Audio component 105 is configured to output and/or input audio signals. For example, audio component 105 includes a microphone (MC) that is configured to receive external audio signals when wearable device 10 is in operating modes, such as calling mode, recording mode, and voice recognition mode. The received audio signal may be further stored in memory 102 or transmitted via communication component 108 . In some examples, the audio component 105 also includes a speaker for outputting audio signals. Specifically, in the implementation of the present invention, the audio component 105 can be used to output the quality judgment result of the physiological signal obtained by the above-mentioned processing component 103, and output the detailed physiological information of the human body obtained according to the physiological signal, for example, the heart rate of the human body is 65 beats/min ( beats per minute, bpm).

The I/O interface 106 provides an interface between the processing component 102 and a peripheral interface module, which may be a click wheel, a button, or the like. These buttons may include, but are not limited to: a home button, a start button, and a lock button. Specifically, in the implementation of the present invention, the home button in the I/O interface 106 may also be used to instruct the processing component 103 to start processing the physiological signals obtained by the above-mentioned sensor component 101 .

Power component 107 provides power to various components of wearable device 10 . Power components 107 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to wearable device 10 .

Communication component 108 may support wired or wireless communications between wearable device 10 and other devices, such that wearable device 10 may access wireless networks based on communication standards, such as WF, 2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 108 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 108 described above also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFD) technology, infrared data association (rDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies. Specifically, in this embodiment of the present invention, the communication component 108 may be configured to send the quality judgment result of the physiological signal obtained by the processing component 103 to other devices, or send the physiological information of the human body obtained according to the physiological signal, for example, the heart rate of the human body is 65bpm.

In an exemplary embodiment, the wearable device may be implemented by one or more application specific integrated circuits (ASCs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable Programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation.

In an exemplary embodiment, there is also provided a non-transitory computer-readable storage medium including instructions, such as a memory 102 including instructions, which are executable by the processor 103 of the wearable device. For example, the above-mentioned non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

It should be noted that, in addition to the above-mentioned wearable device, the physiological signal determination device provided in the embodiment of the present invention may also be a mobile phone, a personal computer (PC), a tablet computer, etc. that can obtain the physiological signals of the human body. Terminal Equipment. Embodiments of the present invention The following only takes the above-mentioned physiological signal quality judgment apparatus as a wearable device as an example to describe the physiological signal quality judgment method provided by the embodiments of the present invention.

Specifically, in the embodiments of the present invention, the following only takes the physiological signal as a pulse wave signal as an example to describe the method for judging the quality of a physiological signal provided by the embodiment of the present invention.

As shown in FIG. 2 , it is a schematic diagram of a waveform of a physiological signal provided by an embodiment of the present invention. The waveform of the physiological signal shown in FIG. 2 is a pulse wave signal under ideal conditions. For an ideal pulse wave signal, each cycle of the signal can have the same features and feature points. For example, the signal of each cycle in the pulse wave signal includes characteristics such as ascending branch, main wave peak, dichotomous wave, descending branch, etc., as well as characteristic points such as apex and bottom point.

Specifically, the variable of the abscissa t(s) in FIG. 2 is time t, and the unit of time t is seconds (s); the variable of the ordinate A (mv) is the amplitude A, and the unit of the amplitude A is millivolts (mv). Points B ₁ , B ₂ and B ₃ are three base points, and points C ₁ and C ₂ are two vertices. The waveform between adjacent bottom points can be a one-period signal. Of course, the feature points that distinguish the period of the pulse wave signal in FIG. 2 may be other feature points, such as apex, in addition to the bottom point. Exemplarily, the waveform between the bottom point B ₁ and the bottom point B ₂ in FIG. 2 is a signal of one cycle (denoted as signal period 1 ); the period value of signal period 1 may be denoted as T ₁ . The waveform between the bottom point B ₂ and the bottom point B ₃ is a signal of another period (denoted as signal period 2 ); the period value of signal period 2 can be denoted as T ₂ . Generally speaking, the period value of the normal pulse wave signal corresponds to the normal range of the human heart rate in the range of 40bpm to 180bpm. In Fig. ₂ , the waveform between the bottom point B1 and the F1 point is the main wave of the signal period ₁ , and the waveform between the F1 point and the bottom point B2 is the _dipulsive wave of the signal period ₁ .

The bottom point B ₁ is the starting point of signal cycle 1. The waveform between the bottom point B ₁ and the vertex C ₁ is the ascending branch of the main wave of the signal period 1, and its height value can be recorded as H _1-1 , and its width value can be recorded as T _1-1 . The waveform between the vertex C ₁ and the point F ₁ is the descending branch of the main wave of the signal period 1, and its height value can be denoted as H _1-2 , and its width value can be denoted as T _1-2 . The waveform between point F ₁ and point G ₁ is the ascending branch of the dichotomous wave of signal cycle 1, and its height value can be recorded as H _1-3 , and its width value can be recorded as T _1-3 . The peak at point G ₁ is the peak of the dicrotic wave in signal cycle 1. The waveform between the point G ₁ and the bottom point B ₂ is the descending branch of the dichotomous wave of the signal period 1, and its height value can be recorded as H _1-4 , and its width value can be recorded as T _1-4 . The bottom point B ₂ is the end point of signal period 1. Wherein, the period value of signal period 1 is T ₁ =T _1-1 +T _1-2 +T _1-3 +T _1-4 . The rising branch of the main wave from the bottom point B ₁ to the vertex C ₁ in the above signal period 1 can also be called the systolic wave of the signal period 1; the waveform from the vertex C ₁ to the point B ₂ can also be called the signal period 1. Diastolic wave. Therefore, the height value of the systolic wave in the signal period 1 is H _1-1 , and the height value of the diastolic wave in the signal period 1 can be recorded as H _1-5 .

Similarly, the characteristics and characteristic points of signals of other periods (eg, signal period 2 ) in the above-mentioned pulse wave signal are similar to those of signal period 1 , and details are not described herein again in this embodiment of the present invention.

In addition, the area of the graph formed by the waveform from the bottom point B2 to _E2 and the coordinate axis t(s) in the signal period ₂ can be recorded as _Sa ; the waveform between the _E2 point and the bottom point _B3 and the coordinate axis t( The area of the graph formed by s) can be denoted as S _b ; the area of the graph formed by the waveform of the signal cycle 2 and the coordinate axis t(s) can be denoted as S, that is, the waveform between the bottom point B ₂ and the bottom point B ₃ and The area of the figure formed by the coordinate axis t(s) can be recorded as S. where S=S _a +S _b . Similarly, for the description of the area of the graph formed by the waveform of the pulse wave signal or other signal periods and the coordinate axis, reference may be made to the above description of the signal period 2, which will not be repeated here.

It should be noted that, because the current wearable sensors are relatively simple and most of them acquire wrist signals, the pulse wave signals obtained by the current wearable sensors often cannot see features such as diploid waves and the peaks of diploid waves. feature points. However, current wearable sensors can generally obtain the bottom and top of the pulse wave signal. Similarly, current wearable sensors can generally also acquire the apex and nadir of other physiological signals other than the pulse wave signal, which will not be repeated here. Embodiments of the Present Invention Hereinafter, the method for judging the quality of a physiological signal provided by the embodiment of the present invention is described by taking only the characteristic points of the physiological signal as the vertex and the bottom as an example.

In order to make the purposes, technical solutions, and advantages of the embodiments of the present invention clearer, the following describes the physiological signals provided by the embodiments of the present invention through the flowchart of the physiological signal quality determination method shown in FIG. 3 in conjunction with the wearable device 10 shown in FIG. 1 . The quality judgment method is described in detail. Referring to FIG. 3 , the method for judging the quality of a physiological signal provided here in this embodiment of the present invention may include S301-S304:

S301. The wearable device collects a physiological signal, where the physiological signal is a periodic signal or a periodic signal.

Wherein, step 301 may be performed by the sensor component 101 in the wearable device 10 shown in FIG. 1 , such as a PPG sensor.

Exemplarily, the above sensor assembly 101 may collect physiological signals at a certain sampling frequency and for a fixed period of time (eg, 3s), and the obtained physiological signals are a set of discrete samples.

The sampling frequency does not affect the realization of the purpose of the present application, and the embodiment of the present invention does not limit the sampling frequency, for example, it may be 25-100 Hz.

It should be noted that, after the wearable device obtains the physiological signal, the physiological signal may be preprocessed, such as filtering, to obtain the pulse wave signal, as shown in FIG. 4 , which is the preprocessed pulse wave signal. The preprocessing process may be performed by a processor in the wearable device, or may be performed by a separate filtering component in the wearable device, and the filtering component may be a filter implemented by hardware, which is not limited in this embodiment of the present invention.

S302. The wearable device extracts a feature point of the physiological signal, where the feature point includes a feature point used to indicate the period of the physiological signal.

Wherein, the above-mentioned characteristic points used to indicate the period of the physiological signal may be the apex and the nadir of the physiological signal.

Optionally, the above-mentioned feature points may also be other feature points in the physiological signal except the bottom point and the apex, such as the feature points where the peaks of the pulse wave signals are located.

Because in the physiological signal (such as pulse wave physiological signal) extracted by the above wearable device, the waveform between adjacent bottom points can be a cycle, or the waveform between adjacent vertices can be a cycle; and the wearable device is a The signal quality of the physiological signal is judged cycle by cycle, so the method provided by the embodiment of the present invention may further include S303:

S303. The wearable device divides the physiological signal into cycles according to the characteristic points of the physiological signal.

Exemplarily, as shown in FIG. 5 , it is a schematic diagram of a waveform of a physiological signal provided by an embodiment of the present invention. FIG. 5 shows the bottom point and the top point extracted by the wearable device from the pulse wave signal shown in FIG. 4 through the wearable sensor. Then, the wearable device can divide the waveform between adjacent bottom points as shown in Figure 5, and record the signal of each cycle in time sequence, that is, record the sample sequence of the signal of each cycle.

Wherein, the sample sequence of the signal of the first cycle acquired by the wearable device can be recorded as x ₁ ={x _{1_1} , x _{1_2} ,...x _{1_j} ,...,x _{1_n} }, j∈{1,2,...,n }, the sample sequence x ₁ of the signal of the first cycle may include n samples, where n is a positive integer; x _{1_j} is the jth sample in the sample sequence x ₁ of the signal of the first cycle. Similarly, when the wearable device acquires the signal of any period after the first period of the signal, it can also record the sample sequence of the signal of the period, and the sample sequence of the signal of the period can also include n samples.

It should be noted that, when the sampling frequency provided in the embodiment of the present invention is 100 Hz, the time interval between two samples in the sample sequence of the signal of each cycle acquired by the wearable device may be 0.01s. Combining the schematic diagrams of the physiological signal waveforms shown in Fig. 3 and Fig. 5, the time T1 of the signal in the first cycle shown in Fig. ₅ can be 0.3s, then the waveform of the signal in the first cycle can include 30 points , that is, the sample sequence of the signal of the first cycle may include 30 samples.

S304. The wearable device judges the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set.

Wherein, the above steps 302-304 may all be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

The above-mentioned current signal template set includes N signal templates, the N signal templates can be obtained according to the physiological signal before the signal of the ith cycle, N is greater than or equal to 2, and i is greater than N. That is to say, the above N signal templates may be N cycles of signals from the first cycle signal to the i-1th cycle signal, and the N signal templates are acquired by the wearable device in real time. The similarity between the signal of the i-th cycle and the current signal template set is composed of the similarity between the signal of the i-th cycle and each of the N signal templates included in the current signal template set.

Wherein, there is similarity between the signals of every two cycles among the periodic signals acquired by the wearable device. The similarity between the signals of the two periods can be used to indicate how similar the waveforms of the two periods of signals are. For example, the higher the similarity between the signals of two cycles, the higher the similarity of the waveforms of the signals of the two cycles; the lower the similarity between the signals of the two cycles, the higher the similarity of the signals of the two cycles The less similar the waveforms are. That is to say, the higher the similarity between the signal of the i-th cycle and any signal template, the higher the degree of similarity between the waveform of the signal of the i-th cycle and the waveform of the signal template; furthermore, the above-mentioned i-th cycle The higher the similarity between the signal and the current signal template set. The lower the similarity between the signal of the i-th cycle and any signal template, the lower the degree of similarity between the waveform of the signal of the i-th cycle and the waveform of the signal template; furthermore, the signal of the i-th cycle and the current The lower the similarity between the signal template sets.

Generally speaking, each signal template of the N signal templates in the current signal template set is a physiological signal of better quality. Therefore, if the similarity between the signal of the ith cycle and the current signal template set is higher, it means that the signal quality of the signal of the ith cycle is better; the difference between the signal of the ith cycle and the current signal template set is better. The lower the similarity, the worse the signal quality of the i-th cycle signal.

Wherein, the wearable device can record the sample sequence of the signal of the ith cycle while acquiring the signal of the ith cycle. For example, the sample sequence of the signal of the ith cycle can be recorded as x _i ={x _{i_1} , x _{i_2} , ... x _{i_j} , ..., x _{i_n} }, j∈{1, 2, ..., n}. At this time, the signal of the i-th cycle may also be simply referred to as _xi . Wherein, the sample sequence xi of the signal of the _ith cycle includes n samples, and _{xi_j} is the jth sample in the sample sequence _xi of the signal of the ith cycle. Of course, before the wearable device acquires the signal of the i-th cycle, the wearable device may have recorded a sample sequence of the signal of each cycle in the first i-1 cycle of the signal. For example, the wearable device can record the sample sequence of the i-1th cycle signal as x _i-1 ={x _{i-1_1} , x _i -1_2 ,...x _{i-1_j} ,..., _{xi-1_n} }, The sample sequence _xi-1 of the signal of the i-1 th cycle may also include n samples, and _{xi-1_j} is the j th sample in the sample sequence _xi-1 of the signal of the i-1 th cycle.

It should be noted that, in the method for judging the quality of physiological signals provided by the embodiments of the present invention, the current signal template set used for judging the quality of physiological signals is obtained by the wearable device according to the physiological signals acquired in real time, rather than using machine learning algorithms or prioritization. Therefore, the current signal template provided by the embodiment of the present invention is more in line with the physiological signal obtained by the wearable device in real time, so that the quality judgment result of the physiological signal obtained according to the above-mentioned current signal template set is more accurate. High accuracy. Moreover, since the embodiment of the present invention obtains the physiological signal, the wearable device can extract the apex and the nadir in the physiological signal to support the wearable device to judge the quality of the physiological signal, and it is not necessary to extract the apex and the nadir in the physiological signal. In addition, a large number of other feature points can be used to support the wearable device in judging the quality of the physiological signal; therefore, the calculation amount in the process of judging the quality of the physiological signal by the wearable device can be reduced, and the accuracy of the judgment result of the quality of the physiological signal can be further improved.

Specifically, in a possible implementation manner, the wearable device judges the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set, and can determine the signal quality of the ith cycle Whether the signal is a normal physiological signal or an abnormal physiological signal. S304 in the method for judging the quality of a physiological signal provided by the embodiment of the present invention may include S601-S603 or S601, S602, and S604. Exemplarily, as shown in FIG. 6 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. In FIG. 6, S304 shown in FIG. 3 may include S601-S603 or S601, S602, and S604:

S601. The wearable device determines the similarity result of the signal of the ith cycle, where the similarity result of the signal of the ith cycle is used to indicate the similarity between the signal of the ith cycle and the current signal template set.

Among them, the similarity between the signals of every two cycles in the periodic signals obtained by the wearable device can be represented by similar parameters such as the correlation coefficient or the mean square error of the sample sequences of the signals of the two cycles. That is to say, the similarity between the signal of the i-th cycle and the current signal template set can be determined by the correlation coefficient, mean square error and other similar parameters of the sample sequence of the signal of the i-th cycle and the sample sequence of a signal template composition. Therefore, the similarity between the signal of the i-th cycle and the current signal template set can be represented by the similarity parameter of the signal of the i-th cycle. In this way, the similar results of the signal of the i-th cycle above may be similar parameters of the signal of the i-th cycle. Among them, the similar parameter of the signal of the ith cycle can be the sum of the similar parameters of the signal of the ith cycle and each signal template in the current N signal templates, or the signal of the ith cycle and the current N signals The mean between similar parameters for each signal template in the template.

The wearable device can record the current signal template set as y={y ₁ , y ₂ ,...y _t ,...,y _N-1 ,y _N },t∈{1,2,...,N}, The y _t is the sample sequence of the t-th signal template in the current N signal templates. At the same time, the wearable device can record the sample sequence y _t of the t-th signal template as y _t ={y _{t_1} , y _{t_2} ,...y _{t_j} ,...,y _{t_n} },j∈{1,2,...,n }. The sample sequence y _t of the t-th signal template may also include n samples, and y _{t_j} is the j-th sample in the sample sequence y _t of the t-th signal template. Subsequently, the wearable device may record the similar parameters of the signal of the i-th cycle and the t-th signal template in the current N signal templates as r _{i_t} . Thus, the similar parameter r _{i_t} of the i-th cycle signal can be recorded as:

或者，

or,

It should be noted that, any signal template in the above-mentioned current signal template set y is a signal of one cycle, for example, the first signal template y ₁ may be the signal x ₁ of the first cycle. For the convenience of description in the embodiments of the present invention, a signal template and a period signal corresponding to the signal template are respectively represented by different characters.

Exemplarily, in the case where the similarity between the signals of two cycles is represented by the correlation coefficients of the sample sequences of the signals of the two cycles: the signal of the i-th cycle and the signal of the t-th signal in the current N signal templates The similarity parameter r _{i_t} of the template is the correlation coefficient between the sample sequence xi of the _i -th cycle signal and the sample sequence y _t of the t-th signal template in the current N signal templates.

Specifically, the similar parameter r _{i_t} between the signal of the i-th cycle and the t-th signal template in the current N signal templates may be:

为第i个周期的信号的样本序列x_i中n个样本的均值，且

为第t个信号模板的样本序列y_t中n个样本的均值，且

in,

is the mean of n samples in the sample sequence x _i of the signal of the ith cycle, and

is the mean of n samples in the sample sequence y _t of the t-th signal template, and

带入(1)式中，第i个周期的信号与当前N个信号模板中第t个信号模板的相似参数r_{i_t}还可以为：Further, will

Bringing into formula (1), the similar parameter r _{i_t} of the signal of the i-th cycle and the t-th signal template of the current N signal templates can also be:

It should be noted that, if the correlation coefficient of the sample sequences of the two periods of signals is larger, the similarity between the two periods of signals is higher; otherwise, the similarity between the two periods of signals is lower. . Therefore, if the similarity parameter r _{i_t} is larger, the similarity between the signal of the i-th cycle and the t-th signal template in the current N signal templates is higher; further, the i-th cycle obtained according to the similarity parameter r _{i_t} The greater the similarity parameter r _i of the signal of , the better the similarity result of the signal of the ith cycle, and the better the signal quality of the signal of the ith cycle. If the similarity parameter r _{i_t} is smaller, the similarity between the signal of the i-th cycle and the t-th signal template in the current N signal templates is lower; further, the signal of the i-th cycle obtained according to the similarity parameter r _{i_t} The smaller the similarity parameter r _i of , the worse the similarity result of the signal in the ith cycle, and the worse the signal quality of the signal in the ith cycle.

In another example, in the case where the similarity between the signals of two cycles is represented by the mean square error of the sample sequence of the signals of the two cycles: the signal of the ith cycle is compared with the current N signal templates in the The similarity parameter r _{i_t} of the t-th signal template is the mean square error of the sample sequence x _i of the signal of the i-th cycle and the sample sequence y _t of the t-th signal template in the current N signal templates.

Specifically, the mean square error mse _{i_t} (that is, the similarity parameter r _{i_t} ) between the signal of the i-th cycle and the t-th signal template in the current N signal templates may be:

Among them, a _{i_j} is the jth sample of the sample sequence a _i obtained by normalizing the sample sequence x _i of the i-th cycle signal, and b _{i_j} is the sample sequence y _t of the t-th signal template obtained by normalizing The jth sample of the sample sequence b _t .

Among them, unlike the correlation coefficient, if the mean square error of the sample sequence of the two-period signal is smaller, the similarity between the two-period signals is higher; the lower the similarity. Therefore, in the case where the similarity parameter r _{i_t} is the mean square error mse _{i_t} , if the similarity parameter r _{i_t} is smaller, the similarity between the signal of the i-th cycle and the t-th signal template in the current N signal templates is higher. Furthermore, the smaller the similarity parameter r _i of the signal of the ith cycle obtained according to the similarity parameter r _{i_t} , the better the similarity result of the signal of the ith cycle, and the better the signal quality of the signal of the ith cycle . If the similarity parameter r _{i_t} is larger, the similarity between the signal of the i-th cycle and the t-th signal template in the current N signal templates is lower; further, the signal of the i-th cycle obtained according to the similarity parameter r _{i_t} The larger the similarity parameter r _i of , the worse the similarity result of the signal in the ith cycle, and the worse the signal quality of the signal in the ith cycle.

It should be noted that, in the following embodiments of the present invention, only the similarity between two cycles of signals is represented by the correlation coefficients of the signal sample sequences of the two cycles to describe the method for judging the quality of physiological signals provided by the embodiments of the present invention.

Further, the above-mentioned wearable device judges the signal quality of the signal of the ith cycle according to the similar result of the signal of the ith cycle, specifically, the wearable device can judge whether the signal of the ith cycle is a normal physiological signal or an abnormal physiological signal.

S602. The wearable device determines whether the similarity result of the signal in the i-th cycle satisfies a preset similarity condition.

The above preset similar conditions may be preset by the wearable device before executing S602, and the preset similar conditions may be used to indicate whether the signals of each cycle in the physiological signals obtained by the wearable device are normal physiological signals.

It should be noted that when the similarity between the two-period signals is represented by the correlation coefficients of the sample sequences of the two-period signals, the value range of the similarity parameters of the two-period signals can be [0, 1]. Generally speaking, if the similarity parameter of the two-period signals is greater than or equal to 0.8, it means that the similarity between the two-period signals is high; if the similarity parameters of the two-period signals are less than 0.8, it means that The similarity between the signals of these two periods is low. If the similarity parameter of the signals of the two periods is equal to 0, it means that there is no similarity between the signals of the two periods. If the similarity parameter of the signals of the two periods is equal to 1, it means that the signals of the two periods are completely similar.

Wherein, if the similarity parameter of the signal of the i-th cycle is the sum of the similarity parameter of the signal of the i-th cycle and each signal template in the current N signal templates, then the above-mentioned "Is the phase result of the signal of the i-th cycle? “Meet the preset similarity condition” can be whether the similarity parameter of the signal of the i-th cycle is greater than or equal to 0.8×N. If the similarity parameter of the signal of the i-th cycle is the average value between the signal of the i-th cycle and the similarity parameters of each signal template in the current N signal templates, then the above "Is the similarity result of the signal of the i-th cycle? "Meet the preset similarity condition" can be whether the similarity parameter of the signal of the ith cycle is greater than or equal to 0.8.

S603. If the similarity result of the signal of the ith cycle satisfies the preset similarity condition, the wearable device determines that the signal of the ith cycle is a normal physiological signal.

Wherein, if the similarity result of the signal of the ith cycle satisfies the preset similarity condition, it means that the signal quality of the signal of the ith cycle reaches the standard of normal physiological signal, that is, the signal of the ith cycle is a normal physiological signal. Then, the wearable device can mark the signal of the ith cycle as a normal physiological signal, and obtain the physiological information of the human body according to the signal of the ith cycle.

S604. If the similarity result of the signal in the i-th cycle does not meet the preset similarity condition, the wearable device determines that the signal in the i-th cycle is an abnormal physiological signal.

Wherein, if the similarity result of the signal in the i-th cycle does not meet the preset similarity conditions, it means that the signal quality of the signal in the i-th cycle does not meet the standard of normal physiological signals, that is, the signal in the i-th cycle is an abnormal physiological signal . Subsequently, the wearable device can mark the signal of the ith cycle as an abnormal physiological signal, and not use the signal of the ith cycle in the process of determining the physiological information of the human body.

Further, in the case that the wearable device determines that the similarity result of the signal in the ith cycle is better than the similarity result of at least one signal template in the current N signal templates, the wearable device can update the current signal template set. As after the above S603 or S604, the above method may further include S701. Exemplarily, as shown in FIG. 7 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. In FIG. 7, after S603 shown in FIG. 6, the above method may further include S701:

S701. The wearable device updates the current signal template set according to the signal of the ith cycle.

The above step 701 may be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

Wherein, if the signal quality of the signal in the i-th cycle is higher than the signal quality of at least one signal template in the N signal templates in the current signal template set, the wearable device can update the current signal according to the signal in the i-th cycle Template collection.

It should be noted that the above-mentioned current signal template set is continuously updated by the wearable device according to the physiological signals acquired in real time. Wherein, since the wearable device updates the current signal template set by replacing the signal template with relatively poor signal quality according to the periodic signal with good signal quality, the signal quality of the signal template in the current signal template set is improved in real time. In this way, the accuracy of the physiological signal quality judgment result obtained according to the current signal template set updated in real time is relatively high.

Generally speaking, the signal for one cycle of updating the current signal template set is a normal physiological signal with better signal quality; of course, it may also be an abnormal physiological signal with better signal quality. Among them, the situation of updating the current signal template by the abnormal physiological signal usually occurs in several update processes after the wearable device obtains the unupdated signal template set.

Since the signal quality of the signal of the ith cycle is related to the similar result of the signal of the ith cycle in the embodiment of the present invention, the wearable device can update the current signal template set according to the similar result of the signal of the ith cycle. In another possible implementation manner, in the method for judging the quality of a physiological signal provided by the embodiment of the present invention, the foregoing S701 may specifically include S801-S802. Exemplarily, as shown in FIG. 8 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. In FIG. 8, S701 in FIG. 7 may specifically include S801-S802:

S801. The wearable device determines that the similarity result of the signal of the ith cycle is better than the similarity result of at least one signal template in the current N signal templates.

At this time, the signal quality of the signal in the ith cycle is higher than the signal quality of at least one signal template in the current N signal templates.

S802, the wearable device replaces the signal template with the worst similar result in the current signal template set with the signal of the i-th cycle.

Among them, the wearable device uses the signal of the ith cycle to replace the signal template with the worst similar result in the current signal template set, that is, the wearable device deletes the signal template with the worst similar result from the current signal template set, and uses a similar signal template with the worst result. The signal of the ith cycle with a better result is used as a new signal template to update the current signal template set. Similar results for one signal template among the N signal templates in the current signal template set can be obtained according to the physiological signal before the signal of the ith cycle.

Optionally, the above "wearable device uses the signal of the i-th cycle to replace the signal template with the worst similar result in the current signal template set" can be replaced with the wearable device using the signal of the i-th cycle to replace any signal template in the current signal template set. A similar signal template with poorer results. Wherein, the similarity result of any of the above-mentioned signal templates with poor similarity results is worse than the similarity result of the signal of the ith cycle.

It should be noted that the wearable device may also acquire the current signal template before judging the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set. Specifically, in another possible implementation manner, the method for judging the quality of a physiological signal provided by the embodiment of the present invention may further include S901 before the foregoing S304 or S601. Exemplarily, as shown in FIG. 9 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. In FIG. 9, S901 may also be included before S601 shown in FIG. 8:

S901. The wearable device acquires the current signal template set according to the physiological signal before the signal of the ith cycle.

The above step 901 may be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

The current signal template set may be the signal template set that has been updated by the wearable device, for example, the current signal template set may be the signal template set that has been updated by the wearable device according to the signal of the i-1th cycle. Alternatively, the current signal template set may be a signal template set that has not been updated by the wearable device, and in this case, the current signal template set is the initial signal template set obtained by the wearable device.

Specifically, in another possible implementation manner, before obtaining the current signal template set according to the physiological signal before the i-th cycle signal, the wearable device may also obtain an unupdated initial signal template set. Exemplarily, as shown in FIG. 10 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. In Fig. 10, the method shown in Fig. 9 may further include S1001 before S901:

S1001. The wearable device obtains an initial signal template set according to the signals of the first N+a cycles.

The above step 1001 may be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

Wherein, the above N+a is less than i, for example, N+a is less than or equal to i-1. The above a is an integer equal to or greater than 0.

Specifically, the wearable device obtains the initial signal template set according to the signals of the first N+a cycles, which may be obtained according to the similarity of the signals of each cycle in the signals of the first N+a cycles. Therefore, in another possible implementation manner, S1001 in the above method may specifically include S1101-S1102. Exemplarily, as shown in FIG. 11 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. In FIG. 11, S1001 in the method shown in FIG. 10 may specifically include S1101-S1102:

S1101. The wearable device determines the similarity of the signals of each cycle in the signals of the first N+a cycles.

Wherein, the similarity result of the signal of one cycle among the signals of the preceding N+a cycles is the similarity between the signal of the cycle and the signals of other cycles except the signal of the cycle among the signals of the previous N+a cycles made up of sex. Wherein, the similarity between the signals of two cycles in the signals of the first N+a cycles can also be represented by the similar parameters of the signals of the two cycles, and the similarity parameter can also be the samples of the signals of the two cycles Correlation coefficient between series. Thus, a similar result of a signal of one cycle among the signals of the first N+a cycles can be represented by a similar parameter of the signal of that cycle.

Referring to the above embodiment, the wearable device may also record a sample sequence of the signal of each cycle in the first N+a cycles of the signal. For example, the wearable device can record the signal of the second cycle as x ₂ ={x _{2_1} , x _{2_2} ,...x _{2_j} ,...,x _{2_n} }, j∈{1,2,...,n}; The signal of 3 cycles is recorded as x ₃ ={x _{3_1} , x _{3_2} ,...x _{3_j} ,...,x _{3_n} }; the signal of the N+a-1th cycle is recorded as x _N+a-1 ={x _{N +a-1_1} , x _N+ a-1_2 ,...x _{N+a-1_j} ,...,x _{N+a-1_n} }; record the signal of the N+ath cycle as x _N+a ={x _{N+ a_1} , x _{N+a_2} , …x _{N+a_j} , …, x _{N+a_n} }.

Exemplarily, taking the similar result of the signal of the first cycle obtained by the wearable device as an example, the similar result of the signal of one cycle among the signals of the first N+a cycles above is described: the similar result of the signal of the first cycle , which can be represented by similar parameters of the first cycle signal. The wearable device can record a similar parameter of the 1st cycle signal as r ₁ .

At the same time, the wearable device can record the similar parameters of the first cycle signal and the second cycle signal as r _{1_2} , and the similar parameter r _{1_2} can be the sample sequence x ₁ of the first cycle signal and the second cycle signal The correlation coefficient of the sample sequence of the signal x ₂ . The wearable device can record the similar parameters of the signal of the 1st cycle and the signal of the 3rd cycle as r _{1_3} , and the similar parameter r _{1_3} can be the sample sequence x ₁ of the signal of the 1st cycle and the signal of the 3rd cycle The correlation coefficient of the sample sequence x ₃ . The wearable device can record the similar parameters of the signal of the 1st cycle and the signal of the N+a-1th cycle as r _{1_N+a-1} , and the similar parameter r _{1_N+a-1} can be the signal of the 1st cycle The correlation coefficient between the sample sequence x ₁ of and the sample sequence x _N +a-1 of the signal of the N+a-1th cycle. The wearable device can record the similar parameters of the signal of the 1st cycle and the signal of the N+ath cycle as r _{1_N+a} , and the similar parameter r _{1_N+a} can be the sample sequence of the signal of the 1st cycle x ₁ and The correlation coefficient of the sample sequence x _N+a of the signal of the N+ath cycle.

Therefore, when a is equal to 1: the similar parameter r ₁ of the signal of the first cycle can be the signal of the first cycle and the signal of the previous N+1 cycles except the signal of the first cycle. The sum of the similar parameters of the signals of other cycles; or, the similar parameters of the signals of the first cycle, can also be the signal of the first cycle and the signals of the previous N+1 cycles except the signal of the first cycle The mean between similar parameters of signals of other periods. That is, the similar parameters of the signal of the first cycle can be r ₁ =r _{1_2} +r _{1_3} +...+r _{1_N} +r _{1_N+1} , or,

In the case where a is not equal to 1: the similar parameters of the signal of the first cycle can be the signal of the first cycle and the signals of the previous N+a cycles except the signal of the first cycle. The mean between similar parameters of a signal. That is, the similar parameters of the signal of the first cycle can be

Exemplarily, the similar parameter r _{1_2} of the signal of the first cycle and the signal of the second cycle may be

为第1个周期的信号的样本序列x₁中n个样本的均值，且

为第2个周期的信号的样本序列x₂中n个样本的均值，且

in,

is the mean of n samples in the sample sequence x ₁ of the signal of the first cycle, and

is the mean of n samples in the sample sequence x ₂ of the signal of the second cycle, and

带入(3)式中，第1个周期的信号与第2个周期的信号的相似参数r_{1_2}还可以为：Further, will

Bringing into formula (3), the similar parameter r _{1_2} of the signal of the first cycle and the signal of the second cycle can also be:

Similarly, for the specific description of the similar parameter r _{1_3} , the similar parameter r _{1_N+a-1} , the similar parameter r _{1_N+a} and other similar parameters of the signal of the first cycle, reference may be made to the detailed description of the similar parameter r _{1_2} . The embodiments of the invention will not be described repeatedly.

It should be noted that, after the wearable device determines the similar results of the signals of each cycle in the signals of the first N+a cycles, that is, after obtaining the similar parameters of the signals of each cycle in the signals of the first N+a cycles, it will The signal quality of the signal of each cycle among the signals of the first N+a cycles can be judged. Specifically, for the signals of each cycle in the signals of the first N+a cycles: if the similar results of the signals of the cycle meet the preset similarity conditions, the wearable device determines that the signal of the cycle is a normal physiological signal; If the similar result of the signal does not meet the preset similarity condition, the wearable device determines that the signal of this period is an abnormal physiological signal.

Further, while judging and obtaining the signal quality of the signal of each cycle in the signals of the first N+a cycles, the wearable device can also obtain an initial signal template including N signal templates from the signals of the first N+a cycles. gather. Specifically, in another possible implementation manner, the above method further includes S1102 after S1101:

S1102. The wearable device determines the first N cycles of signals with the best similarity results among the signals of the first N+a cycles as the initial signal template set.

The above step 1102 may be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

Wherein, when a is equal to 0, the N signal templates in the above-mentioned initial signal template set are the signals of the first N cycles acquired by the wearable device. When a is greater than 0, the signals of the first N+a periods acquired by the wearable device have a period of signals that are not the signal templates in the initial signal template set.

It should be noted that after the wearable device obtains the initial signal template set according to the signals of the first N+a cycles, it can also determine the current signal template set when receiving the signal of each cycle after the signal of the N+ath cycle. . The current signal template set may be an initial signal template set that has not been updated by the wearable device, or the current signal template set may be a signal template set obtained after the wearable device updates the initial signal template set.

Correspondingly, in another possible implementation manner, in the method shown in FIG. 10 or FIG. 11 , S901 may be replaced by S1002:

S1002 , the wearable device acquires the current signal template set according to the initial signal template set and the physiological signal between the signal of the N+a th cycle and the signal of the ith cycle.

Correspondingly, the above step 1002 can also be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

Specifically, when N+a is equal to i-1, the current signal template set when the wearable device acquires the signal of the ith cycle is the above-mentioned initial signal template set that has not been updated by the wearable device.

When N+a is less than i-1, when the wearable device acquires the signal of the i-th cycle, the current signal template set is the above-mentioned initial signal template set that has not been updated by the wearable device; or, the current signal template set is The wearable device updates the signal template set obtained by updating the above-mentioned initial signal template set according to the physiological signal between the signal of the N+a th cycle and the signal of the ith cycle.

Exemplarily, in the case that N+a is less than i-1, if i-1 is equal to N+a+1, and the similar result of the signal of the i-1th cycle is better than the N included in the above initial signal template set Similar results of at least one signal template in the signal template, the wearable device uses the signal of the i-1th cycle to replace the signal template with the worst similar result in the above-mentioned initial signal template set. Subsequently, when the wearable device acquires the signal of the ith cycle, the current signal template set is the signal template set obtained by replacing the signal template with the worst similar result in the initial signal template set with the signal of the ith-1th cycle.

Optionally, the above-mentioned "wearable device uses the signal of the i-1th cycle to replace the signal template with the worst similar result in the above-mentioned initial signal template set" can be replaced with the wearable device using the signal of the i-1th cycle to replace the above-mentioned signal template. Any signal template with poor similar results in the initial set of signal templates. Wherein, the similarity result of any one of the above-mentioned signal templates with poor similarity results is worse than the similarity result of the signal of the i-1th cycle.

For example, when N is equal to 5, a is equal to 1, i-1 is equal to 7, and i is equal to 8, the wearable device obtains the initial set of signal templates from the signals of the first 6 cycles. Assuming that the similarity parameter r1 of the signal in the _1st cycle is equal to 0.7, the similarity parameter r2 of the signal of the _2nd cycle is equal to 0.75, the similarity parameter r3 of the signal of the _3rd cycle is equal to 0.8, and the similarity parameter of the signal of the 4th cycle is equal to 0.8. The similarity parameter r ₄ is equal to 0.85, the similarity parameter r ₅ of the 5th cycle signal is equal to 0.85, and the similarity parameter r ₆ of the 6th cycle signal is equal to 0.9. At this time, the 5 signal templates in the initial signal template set obtained by the wearable device can be the signal of the second cycle, the signal of the third cycle, the signal of the fourth cycle, the signal of the fifth cycle and the signal of the first cycle 6 cycle signal. The wearable device may record the initial signal template set as y={x ₂ , x ₃ , x ₄ , x ₅ , x ₆ }.

Subsequently, if the similarity parameter r ₇ of the signal of the seventh cycle is equal to 0.6, the wearable device will not update the above-mentioned initial signal template set. Therefore, when the wearable device acquires the signal of the 8th cycle, the current signal template set is the above-mentioned initial signal template set. That is to say, the 5 signal templates included in the current signal template set are still the signals of the 2nd-6th cycle; the wearable device can record the current signal template set as y={x ₂ , x ₃ , x ₄ , x ₅ , x ₆ }.

If the similarity parameter r ₇ of the signal of the seventh cycle is equal to 0.95, the wearable device uses the signal of the seventh cycle to replace the signal of the second cycle with the worst similarity result in the above initial signal template set. Therefore, when the wearable device acquires the signal of the 8th cycle, the current signal template set is the signal template set obtained by updating the above-mentioned initial signal template set. That is to say, the 5 signal templates included in the current signal template set are signals of the 2-7th cycle; the wearable device can record the current signal template set as y={x ₇ , x ₃ , x ₄ , x ₅ , x ₆ }.

The N signal templates in the initial signal template set obtained by the wearable device are not necessarily normal physiological signals with better signal quality, but as long as the initial signal template set includes N signal templates, the wearable device can be supported to implement the present invention The embodiment provides a method for judging the quality of a physiological signal. As the number of cycles in the physiological signal acquired by the wearable device increases, the current signal template set can be continuously updated, so that the signal quality of any signal template in the current signal template set can be improved. That is, the N signal templates in the current signal template set updated by the wearable device are usually normal physiological signals with better signal quality. Therefore, the accuracy of the physiological signal quality judgment result obtained by the wearable device according to the above-mentioned current signal template set is high.

It should be noted that, when the wearable device obtains the current signal template set according to the initial signal template set and the signal of the period between the signal of the N+a th cycle and the signal of the ith cycle, it can also determine the N+a th signal template set. Similar results for the signal of each cycle between the signal of the ith cycle to the signal of the ith cycle. That is, the wearable device can obtain the similar parameters of the signal of each cycle between the signal of the N+a-th cycle to the signal of the i-th cycle, so as to judge the signal of the N+a-th cycle to the signal of the i-th cycle The signal quality of the signal between each cycle. Specifically, the signal of each cycle between the signal of the N+a th cycle and the signal of the ith cycle: if the similarity result of the cycle signal satisfies the preset similarity condition, the wearable device judges the signal of the cycle It is a normal physiological signal; if the similar result of the periodic signal does not meet the preset similarity condition, the wearable device determines that the periodic signal is an abnormal physiological signal.

Further, the signals of each cycle in the physiological signals obtained by the wearable device may have the same feature points. Therefore, the wearable device can also judge the signal quality of the physiological signal according to the characteristic value corresponding to the characteristic point of the physiological signal. Specifically, in another possible implementation manner, in the method for judging the quality of a physiological signal provided by the embodiment of the present invention, S1201, S1202, and S1203 may be further included after the above S303. Exemplarily, as shown in FIG. 12 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. In Fig. 12, S1201, S1202 and S1203 may be further included after S303 in Fig. 3:

S1201. The wearable device acquires the characteristic value of the signal of the ith cycle according to the characteristic point of the physiological signal.

Wherein, the wearable device can obtain the period value of the signal of each period and the height value of the signal of each period according to the peak and bottom point of the signal of each period in the physiological signal. Therefore, the characteristic value of the signal in the i-th cycle includes: the period value of the signal in the i-th cycle and/or the height value of the signal in the i-th cycle. Wherein, the height value of the signal of the ith cycle may include the height value of the left branch of the signal of the ith cycle and the height value of the right branch of the signal of the ith cycle. Specifically, the period value of the signal of each period may be the time interval between two adjacent bottom points in the signal of the period; the height value of the signal of each period may be the peak to the two bottom points of the signal of the period The magnitude of each bottom point in the point.

Specifically, the wearable device can obtain a physiological signal every 3s to obtain a waveform of a physiological signal. The wearable device may record the period value of the i-th period signal as T _i . The wearable device can obtain the period value of the signal of each period according to the number of points included in the signal of each period and the time interval between two points in the physiological signal, such as obtaining the period value T _i of the signal of the ith period. For example, when the sampling frequency is 100 Hz, the time interval between every two discrete ones in the physiological signal waveform shown in FIG. 5 may be 0.01s. At this time, the waveform of the signal of the first cycle shown in FIG. 5 may include 30 points, and the period value T1 of the signal of the _first cycle may be 0.3s.

则当前预设周期值范围可以为

Wherein, the wearable device may determine the current preset threshold range according to the signal of the period before the signal of the ith period. Specifically, the wearable device may obtain the initial preset threshold range according to the mean value of the characteristic values of the signals of all periods in a set of physiological signals acquired for the first time. Subsequently, the wearable device can update the initial preset threshold value range according to the characteristic values of the physiological signals of all cycles acquired subsequently, so as to obtain the current preset cycle value range. Exemplarily, the average of the current period values is

Then the current preset period value range can be

当前的右支高度值的均值可以记为

可穿戴设备获取的生理信号的当前预设左支高度值范围可以为

当前预设左支高度值范围可以为

Similarly, the average value of the current left branch height of the physiological signals obtained by the wearable device can be recorded as

The mean value of the current right branch height can be recorded as

The current preset left branch height value range of the physiological signal obtained by the wearable device can be

The current preset left branch height value range can be

It should be noted that, in the embodiment of the present invention, the preset threshold range obtained by the wearable device according to the average value of the acquired characteristic values of the physiological signal is not unique, and can be adjusted by the relevant technical personnel according to the actual situation.

S1202. The wearable device determines that the characteristic value of the signal in the ith cycle is not within the current preset threshold range, and determines that the signal in the ith cycle is an abnormal physiological signal.

时，第i个周期的信号为异常生理信号。Specifically, the characteristic value of the signal of the ith cycle is not within the current preset threshold range, including: the period value of the signal of the ith cycle is not within the current preset cycle range, and/or the height of the signal of the ith cycle The value is not within the current preset altitude range. For example, the value range of the period value T _i of the signal of the ith period is not in

, the signal of the i-th cycle is an abnormal physiological signal.

Correspondingly, before judging the signal quality of the signal of the ith cycle according to the similarity between the signal of the ith cycle and the current signal template set, the wearable device can also judge the eigenvalue of the signal of the ith cycle. The signal of one cycle may be a normal physiological signal. Specifically, before S304, the above method may further include S1203:

S1203. The wearable device determines that the characteristic value of the signal of the i-th cycle is within the current preset threshold range.

Wherein, the above steps 1201-1203 can all be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

内、第i个周期的信号的左支高度值在

内，且第i个周期的信号的右支高度值在

内，则第i个周期的信号可能为正常生理信号。Specifically, the characteristic value of the signal in the ith cycle is in the current preset threshold range, including: the cycle value of the signal in the ith cycle is in the current preset cycle range and the height value of the signal in the ith cycle is in the current preset range. height range. For example, the period value T _i of the signal of the i-th period is

The height value of the left branch of the signal in the i-th cycle is

, and the height value of the right branch of the signal in the i-th cycle is

within, the signal of the i-th cycle may be a normal physiological signal.

It should be noted that, in the method for judging the quality of a physiological signal provided by the embodiment of the present invention, the wearable device can judge the signal quality of the signal of each cycle in the physiological signal according to the period value and the height value in the characteristic value of the physiological signal. That is, the characteristic points of the physiological signal are extracted by the wearable device, and the signal quality of the signal of each cycle in the physiological signal can be judged, which can reduce the amount of calculation in the process of judging the quality of the physiological signal to a certain extent.

Further, the wearable device may determine the current preset threshold range according to the physiological signal before the signal of the ith cycle. Specifically, the wearable device may obtain the initial preset threshold range according to the mean value of the characteristic values of the signals of all periods in a set of physiological signals acquired for the first time. Subsequently, the wearable device may update the initial preset threshold range according to the characteristic values of signals of all cycles in the subsequently acquired physiological signals, so as to obtain the current preset threshold range. Therefore, in another possible implementation manner, the method provided by the embodiment of the present invention may further include S1301 and S1302 after S303. Exemplarily, as shown in FIG. 13 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. S1301 and S1302 may also be included after S303 in FIG. 13 :

S1301. The wearable device determines the current preset threshold range according to the physiological signal before the signal of the ith cycle.

Wherein, the wearable device may determine the current preset threshold range according to the signal of the period before the signal of the ith period. Specifically, the wearable device may obtain the initial preset period value range according to the average value of the period values of the signals of all periods in a group of physiological signals acquired for the first time. Exemplarily, the wearable device may obtain the initial preset period value range according to the average value of the period values of all periods of the physiological signals acquired in the first 3 s. Subsequently, the wearable device can update the initial preset period value range according to the period value of the physiological signal obtained every 3s time interval before the signal of the ith cycle to obtain the current preset period value range.

Similarly, the wearable device can obtain the initial preset left branch height value range and the initial preset left branch height value range according to the mean value of the height values of the signals of all periods in a set of physiological signals acquired for the first time. Subsequently, the wearable device can update the preset left branch height value range and the initial preset left branch height value range according to the height value of the subsequently acquired physiological signal, so as to obtain the current preset left branch height value range and the current preset left branch height value value range.

Exemplarily, the wearable device may obtain an initial preset left branch value range and an initial right branch height value range according to the mean value of the height values of all cycles of the physiological signals acquired in the first 3 s. Subsequently, the wearable device can update the initial preset left branch value range and the initial right branch height value range according to the height values of the signals of all cycles in the physiological signal obtained every 3s time interval before the signal of the i-th cycle, to obtain the preset period value range of the current preset left branch value range and the current preset right branch height value range.

It should be noted that the wearable device can update the current preset period value range according to the period values of the signals of all periods in the physiological signal obtained every 3s time interval after the signal of the i-th period, so as to obtain a new current preset period. value range. Correspondingly, the above method may further include S1302 after S1203:

S1302, the wearable device updates the current preset threshold range according to the characteristic value of the signal of the i-th cycle.

Wherein, the above steps 1301-1302 can all be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 .

It should be noted that, in the method for judging the quality of a physiological signal provided by the embodiment of the present invention, the above-mentioned current preset threshold range is continuously updated according to the physiological signal obtained in real time; and the current preset threshold range is the wearable device according to the obtained physiological signal. That is, the current preset threshold range is obtained according to global variables; therefore, the above current preset threshold range is in line with the physiological signals acquired by the wearable device in real time. Therefore, the method for judging the quality of the physiological signal provided by the embodiment of the present invention can further improve the accuracy of the judgment result of the quality of the physiological signal.

Further, after judging and obtaining the signal quality of the signal of each cycle in the physiological signal, the wearable device may use the judged normal physiological signal to obtain the physiological information of the human body. Specifically, in another possible implementation manner, after the foregoing S304 or S603 or S604, the foregoing method may further include S1401. Exemplarily, as shown in FIG. 14 , it is a schematic flowchart of another method for judging the quality of a physiological signal provided by an embodiment of the present invention. S1401 may also be included after S304 in FIG. 14 :

S1401. The wearable device outputs a signal quality judgment result.

The above step 1401 may be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 through the multimedia component 104 .

The above signal quality judgment result includes that the signal in the ith cycle is a normal physiological signal or an abnormal physiological signal, and the signal in each cycle before the signal in the ith cycle is a normal physiological signal or an abnormal physiological signal. Specifically, the wearable device can mark normal physiological signals and abnormal physiological signals differently, and can also output the ratio of normal physiological signals in all periodic signals in the acquired physiological signals, which is not limited in this embodiment of the present invention . In this way, the judgment result of the physiological signal quality obtained by the wearable device can be more intuitively displayed to the user or related technical personnel, so that the user experience is better.

It should be noted that, in the method for judging the quality of a physiological signal provided by the embodiment of the present invention, the wearable device can judge the signal quality of the collected physiological signal in real time and cycle by cycle, and more accurately distinguish the physiological signal of any cycle. Whether the signal is a normal physiological signal or an abnormal physiological signal. In this way, the wearable device can obtain relatively accurate human physiological information according to the normal physiological signal obtained by the judgment.

The foregoing mainly introduces the solutions provided by the embodiments of the present invention from the perspective of the wearable device in the apparatus for judging the quality of the physiological signal. It can be understood that, in order to realize the above-mentioned functions, the apparatus for judging the quality of physiological signals includes corresponding hardware structures and/or software modules for executing each function. Those skilled in the art should easily realize that the present invention can be implemented in hardware or a combination of hardware and computer software in conjunction with the algorithm steps of the examples described in the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

In the embodiment of the present invention, the physiological signal quality judgment apparatus may be divided into functional modules according to the above method examples. For example, each functional module may be divided according to each function, or two or more functions may be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. It should be noted that, the division of modules in the embodiment of the present invention is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

In the case where each functional module is divided according to each function, FIG. 15 shows a possible schematic diagram of the composition of the physiological signal quality judging device provided in the above embodiment. As shown in FIG. 15 , the physiological signal quality judging device 15 may It includes: a collection module 151 , an extraction module 152 , a division module 153 and a judgment module 154 . Among them, the acquisition module 151 is used to support the physiological signal quality judgment apparatus 15 to perform S301 in the above-mentioned embodiment, and/or other processes used in the technology described herein. The extraction module 152 is used to support the physiological signal quality determination apparatus 15 to perform S302 in the above-mentioned embodiments, and/or other processes for the techniques described herein. The division module 153 is used to support the physiological signal quality judgment apparatus 15 to perform S303 in the above-mentioned embodiment, and/or other processes for the techniques described herein. The judgment module 154 is used to support the physiological signal quality judgment apparatus 15 to perform S304, S602, S603, S604 and S1202 in the above embodiments, and/or other processes for the techniques described herein.

Further, FIG. 16 shows another possible composition diagram of the physiological signal quality judging apparatus provided in the above embodiment. As shown in FIG. 16 , the physiological signal quality judging apparatus 15 may further include: a determining module 155 . The determination module 155 is used to support the physiological signal quality determination apparatus 15 to perform S601 and S1301 in the above-mentioned embodiments, and/or other processes for the techniques described herein.

Further, FIG. 17 shows another possible composition diagram of the physiological signal quality judging apparatus provided in the above embodiment. As shown in FIG. 17 , the physiological signal quality judging apparatus 15 may further include: an update module 156 . The update module 156 is used to support the physiological signal quality determination apparatus 15 to perform S701, S801, S802 and S1302 in the above embodiments, and/or other processes for the techniques described herein.

Further, FIG. 18 shows another possible composition diagram of the physiological signal quality judging apparatus provided in the above embodiment. As shown in FIG. 18 , the physiological signal quality judging apparatus 15 may further include: an acquisition module 157 . The acquisition module 157 is used to support the physiological signal quality determination device 15 to perform S901, S1001, S1002, S1102, S1102, S1201 and S1202 and S1203 in the above embodiments, and/or other processes for the techniques described herein.

Further, FIG. 19 shows another possible composition diagram of the physiological signal quality judging apparatus provided in the above embodiment. As shown in FIG. 19 , the physiological signal quality judging apparatus 15 may further include: an output module 158 . The output module 158 is used to support the physiological signal quality determination apparatus 15 to perform S1401 in the above-mentioned embodiment, and/or other processes for the techniques described herein.

It should be noted that, all relevant contents of the steps involved in the above method embodiments can be cited in the functional description of the corresponding functional module, which will not be repeated here.

The apparatus for judging the quality of a physiological signal provided by the embodiment of the present invention is used to execute the above-mentioned method for judging the quality of a physiological signal, and thus can achieve the same effect as the above-mentioned method for judging the quality of a physiological signal.

In the case of using an integrated unit, the above-mentioned extracting module 152 , dividing module 153 , judging module 154 , determining module 155 , updating module 156 , obtaining module 157 , etc. can be integrated into one processing module. The above-mentioned processing module may be a processor or a controller, for example, a CPU, a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC), a field programmable gate array ( Field Programmable Gate Array, FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various illustrative logical blocks, modules and circuits described in connection with the present disclosure. The above-mentioned processing unit may also be a combination for realizing computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The storage module may be a memory. The above-mentioned acquisition module 151 may be implemented by an input device. The above-mentioned output module 158 may be implemented by a display.

When the above-mentioned processing module is a processor and the storage module is a memory, an embodiment of the present invention provides a physiological signal quality judgment apparatus 20 as shown in FIG. 20 . As shown in FIG. 20 , the apparatus 20 for determining the quality of physiological signals includes: a processor 201 , a memory 222 , a display 203 , an input device 204 and a bus 205 . Among them, the processor 201 , the memory 202 , the display 203 and the input device 204 are connected to each other through the bus 205 . The bus 205 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus or the like. The above-mentioned bus 205 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is shown in FIG. 20, but it does not mean that there is only one bus or one type of bus.

Exemplarily, the above-mentioned input device 204 may include a camera, a wearable sensor, etc., such as the sensor component 101 in the wearable device 10 . The above-mentioned display 203 may be the multimedia component 104 or the audio component 105 in the wearable device 10 .

For the detailed description of each module in the physiological signal quality determination apparatus 20 provided by the embodiment of the present invention and the technical effect brought by each module after performing the relevant method steps in the above-mentioned embodiment, reference may be made to the relevant description in the method embodiment of the present invention , and will not be repeated here.

From the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and brevity of the description, only the division of the above functional modules is used as an example for illustration. In practical applications, the above functions can be allocated as required. It is completed by different functional modules, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. For the specific working process of the system, apparatus and unit described above, reference may be made to the corresponding process in the foregoing method embodiments, and details are not described herein again.

In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be Incorporation may either be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units. The integrated units, if implemented in the form of software functional units and sold or used as stand-alone computer program products, may be stored in a computer-readable storage medium.

When the technical solutions of the present application are implemented using software, they may be implemented in the form of computer program products in whole or in part. The computer program product includes at least one instruction. When the instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer may be through a computer, special purpose computer, computer network, or other programmable device. The instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, from a website site, computer, server, or data center via the same computer. Transmission to another website site, computer, server or data center by wired means such as coaxial cable, optical fiber, digital subscriber line (DSL), or wireless means such as infrared, wireless, microwave, etc. The computer-readable medium can be any available medium that can be accessed by a computer, or a data storage device such as a server, data center, etc., that includes an integration of one or more available media. The usable medium may be a magnetic medium such as a floppy disk, a hard disk, and a magnetic tape, or a semiconductor medium such as a solid state disk (Solid State Disk, SSD).

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited to this, and any changes or substitutions within the technical scope disclosed in the present application should be covered within the protection scope of the present application. . Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims (10)

1. A method for judging the quality of a physiological signal, comprising:

acquiring a physiological signal, wherein the physiological signal is a periodic signal or a quasi-periodic signal;

extracting feature points of the physiological signal, wherein the feature points comprise feature points used for indicating the period of the physiological signal;

dividing the physiological signal into cycles according to the characteristic points of the physiological signal;

determining a similarity result of the signal of the ith period, wherein the similarity result of the signal of the ith period is used for indicating the similarity between the signal of the ith period and a signal template set, wherein the signal template set comprises N signal templates, the N signal templates are obtained according to signals of 1-i-1 periods before the signal of the ith period, N is greater than or equal to 2, and i is greater than N;

judging the signal quality of the signal of the ith period according to the similar result of the signal of the ith period;

acquiring a characteristic value of the signal of the ith period according to the characteristic point of the physiological signal; if the characteristic value of the signal of the ith period is within the range of the current preset threshold value, judging that the signal of the ith period is a normal physiological signal;

if the characteristic value of the signal of the ith period is not within the range of the current preset threshold value, judging that the signal of the ith period is an abnormal physiological signal;

wherein the current preset threshold range is determined according to the signals of the 1 st to i-1 st periods;

if the similarity result of the signal of the ith period is better than the similarity result of at least one signal template in the N signal templates, the method further comprises:

replacing the signal template with the signal of the ith period having the worst similar result in the set of signal templates;

the duration of the cycle is 0.3 seconds.

2. The method of claim 1, wherein the characteristic value of the signal of the i-th cycle comprises: a period value of the i-th period signal and/or a height value of the i-th period signal.

3. The method according to claim 1 or 2, wherein after the obtaining the characteristic value of the signal of the i-th cycle according to the characteristic point of the physiological signal, the method further comprises:

and updating the current preset threshold range according to the characteristic value of the signal of the ith period.

4. The method according to any one of claims 1-2, further comprising:

outputting a signal quality judgment result, wherein the signal quality judgment result comprises that the signal of the ith period is a normal physiological signal or the signal of the ith period is an abnormal physiological signal, and the signal of the 1 st to i-1 st periods is a normal physiological signal or the signal of the 1 st to i-1 st periods is an abnormal physiological signal.

5. A physiological signal quality judging device, comprising:

the acquisition module is used for acquiring physiological signals, and the physiological signals are periodic signals or quasi-periodic signals;

the extraction module is used for extracting the feature points of the physiological signals acquired by the acquisition module, wherein the feature points comprise feature points used for indicating the period of the physiological signals;

the dividing module is used for dividing the physiological signal into cycles according to the characteristic points of the physiological signal extracted by the extracting module;

a determining module, configured to determine a similarity result of an ith periodic signal, where the similarity result of the ith periodic signal is used to indicate similarity between the ith periodic signal and a signal template set, where the signal template set includes N signal templates, the N signal templates are obtained according to signals of 1 to i-1 periods before the ith periodic signal, where N is greater than or equal to 2, and i is greater than N;

the judging module is used for judging the signal quality of the signal of the ith period according to the similar result of the signal of the ith period;

an updating module, configured to determine whether a similarity result of the signal in the ith period is better than a similarity result of at least one signal template of the N signal templates; the updating module is specifically configured to replace the signal template with the lowest similarity in the signal template set with the signal of the ith period;

the acquisition module is further used for acquiring a characteristic value of the signal of the ith period according to the characteristic point of the physiological signal;

the judging module is further configured to judge that the signal of the ith cycle is a normal physiological signal if the characteristic value of the signal of the ith cycle is within a current preset threshold range; if the characteristic value of the signal of the ith period is not in the current preset threshold range, judging the signal of the ith period as an abnormal physiological signal, wherein the current preset threshold range is determined according to the signals of the 1 st to i-1 st periods;

the duration of the cycle is 0.3 seconds.

6. The apparatus of claim 5, wherein the characteristic value of the signal of the i-th cycle comprises: a period value of the i-th period signal and/or a height value of the i-th period signal.

7. The apparatus according to claim 5 or 6, wherein the updating module is further configured to update the current preset threshold range according to the characteristic value of the signal of the ith cycle after the obtaining module obtains the characteristic value of the signal of the ith cycle according to the characteristic point of the physiological signal.

8. The apparatus of any of claims 5-6, further comprising:

an output module, configured to output a signal quality determination result, where the signal quality determination result includes that the signal in the ith cycle determined by the determination module is a normal physiological signal or the signal in the ith cycle is an abnormal physiological signal, and the signal in the 1 st to i-1 st cycles is a normal physiological signal or the signal in the 1 st to i-1 st cycles is an abnormal physiological signal.

9. A physiological signal quality judging device, comprising: a processor, a memory, a display, an input device and a bus;

the memory is used for storing at least one instruction, the processor, the memory, the display and the input device are connected through the bus, when the device runs, the processor executes the at least one instruction stored in the memory, so that the device executes the physiological signal quality judging method according to any one of claims 1-4.

10. A computer storage medium, comprising: at least one instruction;

when the at least one instruction is executed on a computer, the computer is caused to perform the physiological signal quality determination method of any one of claims 1-4.

Images