KR102749035B1 - Customized alarm method and system through rehabilitation perofrmance pattern analysis - Google Patents

Abstract

The present invention discloses a customized alarm method and system through analysis of rehabilitation performance patterns.
The customized alarm system through analysis of the rehabilitation performance pattern of the present invention includes: a patient terminal for collecting rehabilitation performance data of a patient performing a spinal disease rehabilitation program; a server for analyzing the patient's rehabilitation performance pattern based on the rehabilitation performance data, extracting a rehabilitation performance index (index) from the patient's rehabilitation performance pattern, and notifying the patient terminal of an alarm notifying the performance of the spinal disease rehabilitation program according to the rehabilitation performance index; and a doctor terminal for establishing or modifying a rehabilitation policy of the spinal disease rehabilitation program or changing the configuration of the spinal disease rehabilitation program according to the rehabilitation performance index.
According to the customized alarm method and system through analysis of the rehabilitation performance pattern of the present invention, there is an effect in which the alarm cycle that can encourage the patient's rehabilitation performance can be automatically adjusted according to the patient's rehabilitation performance status.

Description

{CUSTOMIZED ALARM METHOD AND SYSTEM THROUGH REHABILITATION PEROFRMANCE PATTERN ANALYSIS}

The present invention relates to the field of rehabilitation of patients with spinal diseases, and more specifically, to a customized alarm method and system capable of monitoring the rehabilitation status of a patient with spinal diseases, analyzing the patient's movement status patterns, etc., and customizing an alarm cycle for notifying the patient of rehabilitation performance.

In recent years, the number of patients with scoliosis has rapidly increased due to increased sitting time caused by long-term computer use, long-term smartphone use, lack of exercise, and lack of awareness of physical imbalances, and scoliosis has emerged as a serious health problem.

Scoliosis is a condition in which the spine is bent or twisted like a 'C' or 'S', causing the body to tilt or turn to the left or right. It can cause back pain and, if the curvature angle is over 70 to 80°, it can affect lung function, if it is over 90 to 100°, it can affect breathing, and if it is over 120°, it can cause cor pulmonale due to decreased lung capacity. Depending on the cause, scoliosis is classified into functional scoliosis and structural scoliosis, and posture correction is very important for the treatment of scoliosis without neurological symptoms.

However, patients have to visit the hospital continuously for rehabilitation treatment, which is very difficult. They have to go to the hospital to receive rehabilitation treatment or physical therapy, and because there are many patients, the waiting time is long and they have to return home after treatment. If you add up all of this time, it takes more than 5 hours on average for large hospitals and more than 3 hours for small and medium-sized hospitals, so it is practically impossible for patients to visit the hospital every day with their sick bodies.

Also, if you can do rehabilitation or physical therapy at home, it is good because it saves time and money, but it is very difficult for patients to continue the treatment on their own. In particular, rehabilitation therapy is difficult, repetitive, and boring, so it is difficult to continue the treatment for a long time unless someone is constantly coaching you. Therefore, an exercise therapy system that patients can enjoy and continue to treat at home is urgently needed.

Meanwhile, the background technology described above is technical information that the inventor possessed for deriving the present invention or acquired during the process of deriving the present invention, and cannot necessarily be considered as publicly known technology disclosed to the general public prior to the application of the present invention.

Patent Publication No. 10-2551402 (2023.06.29)

The present invention relates to a customized alarm method and system capable of setting an alarm cycle customized according to the rehabilitation pattern of a patient undergoing a spinal disease rehabilitation program.

The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below.

A customized alarm system through analysis of rehabilitation performance patterns according to one embodiment of the present invention is

A patient terminal that collects rehabilitation performance data from patients undergoing a spinal disease rehabilitation program;

A server that analyzes the patient's rehabilitation performance pattern based on the rehabilitation performance data, extracts a rehabilitation performance index from the patient's rehabilitation performance pattern, and notifies the patient terminal of an alarm indicating the performance of the spinal disease rehabilitation program according to the rehabilitation performance index;

It includes a terminal for use by a physician who establishes or modifies a rehabilitation policy of the above spinal disease rehabilitation program or changes the composition of the above spinal disease rehabilitation program according to the above rehabilitation performance indicator.

Preferably,

The above server,

A rehabilitation performance pattern analysis unit that analyzes the patient's rehabilitation performance pattern by obtaining at least one piece of information from the rehabilitation performance data, including a rehabilitation date, a rehabilitation time, a rehabilitation movement sequence, and a number of rehabilitation repetitions;

A rehabilitation performance index extraction unit that extracts the rehabilitation performance index by comparing the rehabilitation schedule included in the rehabilitation policy of the above spinal disease rehabilitation program with the rehabilitation performance pattern of the patient;

An alarm notification unit that notifies the patient terminal of an alarm indicating the performance of the spinal disease rehabilitation program; and

It includes an alarm notification cycle control unit that automatically controls the notification cycle of the alarm based on the above rehabilitation performance indicator.

Preferably,

The above rehabilitation performance indicator includes the patient's faithfulness in performing the spinal disease rehabilitation program, and the faithfulness in performing the spinal disease rehabilitation program is determined based on how regularly the patient performs the spinal disease rehabilitation program in accordance with the rehabilitation schedule time, rehabilitation schedule date, rehabilitation schedule movement order, and rehabilitation schedule number of times included in the rehabilitation policy of the spinal disease rehabilitation program.

The above rehabilitation date and rehabilitation time are extracted from the date and time the above rehabilitation performance data was collected,

The above rehabilitation movement sequence is estimated from the type and location of the muscle from which the rehabilitation performance data is collected.

The above number of rehabilitation repetitions is characterized in that it is estimated from the number of repetitions in which the same rehabilitation performance data is collected.

Preferably,

The above rehabilitation performance data includes at least one of a motion image of the patient performing a predetermined motion when performing the spinal disease rehabilitation program and measurement data measuring the patient's condition measured by a sensor when performing the motion.

The above rehabilitation performance pattern analysis unit classifies the rehabilitation performance data by movement, and extracts rehabilitation performance data exceeding a predetermined threshold for each movement.

The above rehabilitation performance index extraction unit is characterized by being configured to extract the rehabilitation performance index based on rehabilitation performance data exceeding the threshold value.

Preferably,

The extraction of rehabilitation performance data exceeding a predetermined threshold by the above rehabilitation performance index extraction unit is performed by extracting image similarity by comparing an image of the patient performing a predetermined movement with a reference image of the predetermined movement by artificial intelligence.

The extraction of rehabilitation performance data exceeding a predetermined threshold by the above rehabilitation performance index extraction unit is characterized in that it is performed by comparing the measurement data measured by the sensor worn by the patient when performing the above-determined movement with predetermined muscle-related characteristic data.

Preferably,

The above muscle-related characteristic data includes at least one of muscle tension, muscle stiffness, muscle elasticity, and muscle strain.

Preferably,

Changing the composition of the above spinal disease rehabilitation program includes at least one of changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed.

Preferably,

The above alarm notification cycle control unit is characterized by reducing the cycle of the alarm when the rehabilitation performance index is lower than the comparative rehabilitation performance index of another patient undergoing rehabilitation with the same spinal disease rehabilitation program.

Preferably,

The above rehabilitation performance indicator extraction unit is configured to extract rehabilitation performance indicators in predetermined rehabilitation period units,

The above alarm notification cycle control unit is characterized by reducing the cycle of the alarm when a rehabilitation performance index lower than the minimum rehabilitation performance index extracted from a past rehabilitation period unit is obtained.

A customized alarm method through analysis of rehabilitation performance patterns according to another embodiment of the present invention is as follows:

A rehabilitation performance data receiving step for receiving rehabilitation performance data of a patient performing a spinal disease rehabilitation program;

A rehabilitation performance pattern analysis step for analyzing the patient's rehabilitation performance pattern by obtaining at least one piece of information from the rehabilitation performance data, including a rehabilitation date, a rehabilitation time, a rehabilitation movement sequence, and a rehabilitation repetition number;

A rehabilitation performance index extraction step for extracting the rehabilitation performance index by comparing the rehabilitation schedule included in the rehabilitation policy of the above spinal disease rehabilitation program with the rehabilitation performance pattern of the patient; and

It includes an alarm notification step for notifying the patient terminal of an alarm notifying the performance of the spinal disease rehabilitation program based on the rehabilitation performance indicator.

Preferably,

An alarm notification cycle adjustment step for automatically adjusting the notification cycle of the alarm based on the above rehabilitation performance indicator; and

It further includes a step of changing the composition of the spinal disease rehabilitation program according to the above rehabilitation performance indicators.

Preferably,

The above rehabilitation performance indicator includes the patient's faithfulness in performing the spinal disease rehabilitation program, and the faithfulness in performing the spinal disease rehabilitation program is determined based on how regularly the patient performs the spinal disease rehabilitation program in accordance with the rehabilitation schedule time, rehabilitation schedule date, rehabilitation schedule movement order, and rehabilitation schedule number of times included in the rehabilitation policy of the spinal disease rehabilitation program.

The above rehabilitation date and rehabilitation time are extracted from the date and time the above rehabilitation performance data was collected,

The above rehabilitation movement sequence is estimated from the type and location of the muscle from which the rehabilitation performance data is collected.

The above number of rehabilitation repetitions is characterized in that it is estimated from the number of repetitions in which the same rehabilitation performance data is collected.

Preferably,

The above rehabilitation performance data includes at least one of a motion image of the patient performing a predetermined motion when performing the spinal disease rehabilitation program and measurement data measuring the patient's condition measured by a sensor when performing the motion.

The above rehabilitation performance pattern analysis step includes classifying the rehabilitation performance data by movement and extracting rehabilitation performance data exceeding a predetermined threshold for each movement.

The above rehabilitation performance indicator extraction step includes extracting the rehabilitation performance indicator based on rehabilitation performance data exceeding the threshold.

Preferably,

In the above rehabilitation performance index extraction step, the extraction of rehabilitation performance data exceeding a predetermined threshold is performed by extracting image similarity by comparing the motion image of the patient performing the determined motion with the reference image of the determined motion by artificial intelligence.

The extraction of rehabilitation performance data exceeding a predetermined threshold in the above rehabilitation performance index extraction step is characterized by being performed by comparing the measurement data measured by the sensor worn by the patient when performing the above-determined movement with predetermined muscle-related characteristic data.

Preferably,

The above muscle-related characteristic data includes at least one of muscle tension, muscle stiffness, muscle elasticity, and muscle strain.

Preferably,

The step of changing the composition of the spinal disease rehabilitation program includes at least one of changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed.

Preferably,

The above alarm notification cycle adjustment step includes reducing the cycle of the alarm when the rehabilitation performance index is lower than the comparative rehabilitation performance index of other patients undergoing rehabilitation with the same spinal disease rehabilitation program.

Preferably,

The above rehabilitation performance indicator extraction step includes extracting rehabilitation performance indicators by predetermined rehabilitation period units,

The above alarm notification cycle adjustment step includes reducing the cycle of the alarm when a rehabilitation performance index lower than a minimum rehabilitation performance index extracted from a past rehabilitation period unit is obtained.

Specific details of other embodiments are included in the detailed description and drawings.

According to the customized alarm method and system through analysis of rehabilitation performance patterns of the present invention, the patient's spinal disease rehabilitation status can be monitored, and an alarm cycle for notifying the patient of rehabilitation performance can be set in a customized manner by analyzing the patient's movement status patterns, etc.

According to the customized alarm method and system through analysis of the rehabilitation performance pattern of the present invention, there is an effect in which the alarm cycle that can encourage the patient's rehabilitation performance can be automatically adjusted according to the patient's rehabilitation performance status.

However, the effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

FIG. 1 is a diagram schematically illustrating the configuration of a spinal disease patient rehabilitation monitoring and feature motion extraction system according to one embodiment of the present invention.
FIG. 2 is a diagram schematically illustrating an image processing process for performing rehabilitation motion recognition using artificial intelligence according to one embodiment of the present invention.
FIG. 3 is a diagram conceptually explaining an image similarity comparison process using artificial intelligence according to one embodiment of the present invention.
FIG. 4 is a diagram schematically illustrating a preprocessing process of an image processing unit of a patient terminal according to one embodiment of the present invention.
FIG. 5 is a diagram illustrating an example of a method for quantitatively calculating the effect of rehabilitation treatment according to one embodiment of the present invention.
FIG. 6 is a diagram illustrating a flow chart of a method for monitoring rehabilitation of a spinal disease patient and extracting feature motions according to the present invention.
FIG. 7 is a diagram schematically illustrating the configuration of a server of a customized alarm system through analysis of a rehabilitation performance pattern according to one embodiment of the present invention.
FIG. 8 is a flowchart illustrating a customized alarm method through analysis of a rehabilitation performance pattern according to one embodiment of the present invention.
FIG. 9 is a diagram illustrating an exemplary computing device that may implement devices and/or systems according to various embodiments of the present invention.

The advantages and features of the present invention, and the methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and the present embodiments are provided only to make the disclosure of the present invention complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

The embodiments described herein will be described with reference to cross-sectional and/or plan views, which are ideal illustrations of the present invention. In the drawings, the thicknesses of the components are exaggerated for the purpose of effectively explaining the technical contents. Accordingly, the components illustrated in the drawings have a schematic nature, and the shapes of the components illustrated in the drawings are intended to illustrate specific forms of the components and are not intended to limit the scope of the invention. Although the terms first, second, third, etc. have been used to describe various components in various embodiments of the present specification, these components should not be limited by these terms. These terms are only used to distinguish one component from another. The embodiments described and illustrated herein also include complementary embodiments thereof.

The terminology used herein is for the purpose of describing embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless the context clearly dictates otherwise. The terms "comprises" and/or "comprising" as used herein do not exclude the presence or addition of one or more other components, steps, operations, and/or elements to the mentioned components, steps, operations, and/or elements.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with a meaning that can be commonly understood by a person of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries shall not be ideally or excessively interpreted unless explicitly specifically defined.

Hereinafter, with reference to the drawings, the concept of the present invention and embodiments thereof will be described in detail.

FIG. 1 is a diagram schematically illustrating the configuration of a spinal disease patient rehabilitation monitoring and feature motion extraction system according to one embodiment of the present invention.

A spinal disease patient rehabilitation monitoring and feature motion extraction system (1000) according to one embodiment of the present invention includes a patient terminal (110), a server (120), and a doctor terminal (130).

The patient terminal (110), server (120), and doctor terminal (130) are connected to each other via a network and can exchange data.

The patient terminal (110) collects multiple rehabilitation performance data of a patient undergoing a spinal disease rehabilitation program. As an example, the patient terminal (110) may be a smartphone equipped with a camera capable of photographing the patient's rehabilitation movements.

The spinal disease rehabilitation program of the present invention can be provided in the form of a game-based application. The patient can perform rehabilitation by executing the spinal disease rehabilitation program in the form of a game-based application installed on the patient terminal (110). The patient does not need to visit the hospital in person for rehabilitation. The spinal disease rehabilitation program of the present invention is provided in the form of a game-based application, so that rehabilitation can be performed anywhere, at any time, without any special location restrictions.

In the present invention, rehabilitation performance data includes at least one of a motion image of a patient performing a predetermined motion when performing a spinal disease rehabilitation program and measurement data measuring the patient's condition by a sensor when performing the motion.

The patient terminal (110) transmits the collected rehabilitation performance data to the server (120).

The server (120) classifies multiple rehabilitation performance data by movement, extracts rehabilitation performance data exceeding a predetermined threshold for each movement, and calculates the patient's faithfulness in performing the spinal disease rehabilitation program.

As illustrated in Fig. 1, the server (120) transmits the patient's rehabilitation performance data to a doctor's terminal (130), thereby enabling the doctor to continuously monitor the patient's rehabilitation status.

When rehabilitation performance data is a motion image, extraction of rehabilitation performance data exceeding a predetermined threshold by the artificial intelligence of the server (120) is performed by comparing the motion image with a reference image of a determined motion.

In the present invention, the reference image of the rehabilitation movement may be an image that can be a sample of a specific rehabilitation movement and may be a filmed image of a rehabilitation movement performed by a rehabilitation therapist or doctor.

The motion images extracted in this way that are above the threshold value mean that the patient performs rehabilitation movements similarly to the reference images. The higher the similarity, the better the patient is judged to be performing the rehabilitation movements.

When rehabilitation performance data is measurement data, extraction of rehabilitation performance data exceeding a predetermined threshold by the artificial intelligence of the server (120) is performed by comparing measurement data measured by a sensor worn by the patient when performing a predetermined movement with predetermined muscle-related characteristic data.

In one embodiment, the muscle-related characteristic data includes muscle tension, muscle stiffness, muscle elasticity, and muscle strain.

The resonant frequency [Hz], which indicates muscle tension, represents the vibration inherent in the muscle that exists even in the absence of voluntary muscle contraction (EMG Zero level). In general, the level of muscle contraction and tension are positively correlated. That is, as the muscle contraction force increases, that is, as the force is exerted more strongly, the muscle tension also increases.

Muscle stiffness refers to the resistance of muscle tissue to external force in the initial muscle state. In other words, it refers to the magnitude of force required to cause displacement of muscle fiber tissue by muscle contraction.

Muscle elasticity is a biomechanical property of muscle that allows it to recover to its initial muscle shape after a decrease or removal of an external force. Elasticity is inversely proportional to the damping ratio, and theoretically, a damping ratio of 0 represents absolute elasticity.

Muscle strain is determined by the ratio of the time from the start of the deformation to the time from the end of the deformation to the recovery time. Recovery time is the time it takes for the muscle to return to normal after the muscle contraction or external stress is removed. In other words, it is the rate at which the muscle returns from its initial state of relaxation to the deformation and back again.

In one embodiment, muscle-related characteristic data can be measured using a portable muscle diagnostic device. The measurement principle is performed by calculating the natural frequency of physiological properties of body skin and muscles.

As an example, when a patient performs a rehabilitation movement that outputs muscle strain above a threshold, the patient may be judged to be performing that rehabilitation movement well.

In one embodiment, extraction of rehabilitation performance data above a predetermined threshold may be performed by considering both motion images and measurement data.

That is, when performing a specific rehabilitation movement, a motion image and measurement data measuring the patient's muscles when performing the rehabilitation movement are collected, the motion image is compared with a reference image for similarity, and the measurement data is compared with muscle-related characteristic data having a predetermined threshold, so that rehabilitation performance data exceeding a predetermined threshold can be extracted.

In the present invention, the patient's faithfulness in performing the spinal disease rehabilitation program is a quantitative expression of how well and regularly the patient performs the spinal disease rehabilitation program according to a specified time and date.

The server (120) transmits rehabilitation performance data exceeding the threshold for each movement and the patient's faithfulness in performing the spinal disease rehabilitation program to the doctor's terminal (130).

The medical terminal (130) can change the composition of the spinal disease rehabilitation program based on the rehabilitation performance data exceeding the threshold for each movement and the patient's faithfulness in performing the spinal disease rehabilitation program.

Changes in the composition of the spinal disease rehabilitation program can be performed based on input signals from a physician or by a processor.

For example, by combining motion images above a threshold value to construct a modified rehabilitation program, the patient can be made to perform only rehabilitation movements that are similar to the baseline movements.

As an example, the medical terminal (130) can change a spinal disease rehabilitation program by increasing the number of rehabilitation operations of a motion image having a high similarity to a reference motion and decreasing the number of rehabilitation operations of a motion image having a low similarity to a reference motion.

As an example, the medical terminal (130) can change a spinal disease rehabilitation program by replacing rehabilitation motions of motion images having low similarity to the reference motion with simplified rehabilitation motions.

The medical terminal (130) can output a spinal disease rehabilitation program with a changed configuration to a server (120) or a patient terminal (110).

When a spinal disease rehabilitation program with a changed configuration is transmitted to the server (120), the server (120) updates the spinal disease rehabilitation program to the latest version.

The server (120) transmits a spinal disease rehabilitation program with a changed configuration to the patient terminal (110).

In one embodiment, changing the composition of the spinal disease rehabilitation program includes changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed.

In one embodiment, the server (120) determines how regularly the patient performs the spinal disease rehabilitation program in accordance with the prescribed time, date, sequence of motions, and number of times to perform the spinal disease rehabilitation program.

For example, if a doctor prescribes rehabilitation treatment three times a week for one hour each time, and the patient consistently performs the spinal disease rehabilitation program between 8:00 and 9:00 a.m. on Mondays, Wednesdays, and Fridays, this can be considered good adherence.

The more irregular the dates or times of performing a spinal disease rehabilitation program are, and the more difficult it is to meet the set number of dates and times, the lower the level of fidelity may be judged.

In one embodiment, the server (120) can extract time and date information for performing a spinal disease rehabilitation program from the time and date when rehabilitation performance data was collected.

In one embodiment, the server (120) can estimate the sequence of movements for performing a spinal disease rehabilitation program from the types and locations of muscles from which measurement data is collected.

In one embodiment, the server (120) can estimate the number of times a spinal disease rehabilitation program is performed from the number of repetitions in which the same measurement data is collected.

FIG. 2 is a diagram schematically illustrating an image processing process for performing rehabilitation motion recognition using artificial intelligence according to one embodiment of the present invention.

Based on artificial intelligence, gesture recognition technology relies on input data.

Each input data has its own strengths and weaknesses in identifying actions, depending on its format. For example, RGB images are good at recognizing actions by extracting the color appearance of people in a video. However, they do not provide clues about the 3D structure of the image and are sensitive to lighting changes.

In this way, using a single modality in human gesture recognition does not guarantee optimal recognition because most of them have limited fields of view, cannot overcome occlusion, and are sensitive to illumination changes.

Therefore, the present invention uses a multi-mode motion recognition technology that combines an RGB image (210), a depth image (220), and a skeleton image (230).

Multi-mode gesture recognition technology provides more powerful gesture recognition, is insensitive to changes in lighting, and ensures good recognition in various environments.

First, the artificial intelligence combines the RGB image (210) with the depth image (220) and the skeleton image (230) to create an image in real time and stores it over time (240).

After preprocessing the input data, artificial intelligence performs cropping of the subject based on feature expression and motion classification (250). In this process, the shape of the human skeleton can be utilized and the subject can be cropped efficiently from the image using 2D skeletal coordinates.

Artificial intelligence extracts features for each motion image using a unique convolutional neural network (CNN) and converts them to create a final image (260).

Each RGB image, depth image, and skeleton image has its own unique format differences, so combining them can greatly improve recognition performance.

Motion recognition is based on CNN (Convolution Neural Network) and vector values of input image data. is defined as , where n represents the number of input samples.

The output image of each convolution layer is as shown in Equation (1).

Equation (1)

은 계층의 인덱스에 해당하고,

는 시그모이드 활성화 함수이다.

는

번째 특징에 해당하는 편향이고,

은 필터 크기이다.

은

번째 특징 맵과

번째 필터 인덱스에 대한 가중치를 나타낸다.Here,

corresponds to the index of the silver layer,

is the sigmoid activation function.

Is

The bias corresponding to the th feature,

is the filter size.

silver

The second feature map and

Indicates the weight for the th filter index.

FIG. 3 is a diagram conceptually explaining an image similarity comparison process using artificial intelligence according to one embodiment of the present invention.

Image similarity comparison by artificial intelligence according to one embodiment of the present invention is performed by extracting image similarity by comparing an action image (320) of a patient performing a predetermined action with a reference image (310) of the predetermined action by artificial intelligence.

Referring to FIG. 3, the motion image (320) may be composed of a plurality of similar motion image frames. This is because one rehabilitation motion may be repeated several times over a set period of time.

The similarity between scenes is calculated (321) for multiple motion images (320). The similarity between scenes is calculated, and images with a similarity lower than a threshold are removed.

Then, the artificial intelligence extracts feature vectors (322) of motion images with similarity greater than a threshold.

Artificial intelligence automatically extracts high-quality image features by applying deep learning technology. Image features are data that digitize high-level information contained in an image. Image features are also expressed in the form of a fixed-size vector. By comparing the similarity of these image feature vectors, the similarity of two images can be calculated.

In one embodiment, extraction of a feature vector (322) of a motion image can be performed by taking an average of the feature vectors.

In one embodiment, extraction of a feature vector (322) of a motion image can be performed by taking the median of the feature vector.

Feature vectors for multiple reference images (310) are stored in advance in a database (310). Artificial intelligence extracts feature vectors for each reference image and stores them in the database (310).

The artificial intelligence performs a similarity comparison between the feature vector (322) of the motion image and the feature vector for the reference image (310) in the vector space (330).

After extracting the feature vector (322) of the motion image, the feature vector of the reference image (310) that is most similar to the feature vector (322) of the motion image is searched.

In one embodiment, the artificial intelligence may use cosine similarity, which uses the angle between two vectors to calculate the similarity between feature vectors.

In one embodiment, the artificial intelligence may use the k-Nearest Neighbor (KNN) algorithm to compute the similarity between feature vectors.

In one embodiment, the artificial intelligence may use an Approximate Nearest Neighbor (ANN) algorithm based on the open source Non-Metric Space Library (NMSLIB) to compute similarity between feature vectors.

FIG. 4 is a diagram schematically illustrating a preprocessing process of an image processing unit of a patient terminal according to one embodiment of the present invention.

The patient terminal (110) of the present invention includes an image processing unit.

The image processing unit receives real-time images from the camera, performs image preprocessing, and generates RGB images, depth images, and skeleton images to be used in artificial intelligence.

The human body is a three-dimensional structure, but the real-time images coming from the camera are two-dimensional images that must be converted into three-dimensional images for artificial intelligence to perform rehabilitation movement recognition.

To accurately recognize body parts, the user must be recognized in three dimensions.

Therefore, the image processing unit of the present invention converts a real-time user image into a virtual 3D object by using a back-projection matrix algorithm that changes a 2D image of a camera into a 3D image.

In order to change a 2D image into a 3D image, you basically need to know the relationship between the 2D image and the 3D space. This can be obtained by using a camera backprojection matrix consisting of several camera parameters (e.g., internal parameters and external parameters), and by using this, you can obtain the information necessary to backproject a point in a 2D image into a 3D space. In this way, the camera backprojection matrix plays a key role in the task of obtaining 3D information.

The backprojection matrix converts the rehabilitation motion images from real-time images input from the camera into virtual three-dimensional images.

The virtual 3D user image generated by the image processing unit is transferred to the artificial intelligence so that the artificial intelligence can recognize the user's rehabilitation movements.

FIG. 5 is a diagram illustrating an example of a method for quantitatively calculating the effect of rehabilitation treatment according to one embodiment of the present invention.

According to the spinal disease patient rehabilitation monitoring and feature motion extraction system of the present invention, the effectiveness of rehabilitation treatment can be quantitatively estimated by collecting muscle-related measurement data when a patient performs rehabilitation motions.

As illustrated in FIG. 5, the muscles involved in a specific rehabilitation movement (510) may be multiple muscles.

Muscle-related measurement data collected by the sensor during rehabilitation movement (510) may include muscle strain of the first muscle, muscle strain of the second muscle, and muscle strain of the third muscle.

The server (120) can assign a predetermined weight to each muscle for muscle-related measurement data collected by the sensor during rehabilitation movement (510).

In rehabilitation movements (510), a relatively high weight is given to muscles that need to receive a lot of stimulation, and a relatively low weight is given to muscles that need to receive less stimulation.

The server (120) can assign a first weight (520) to the muscle strain of the first muscle, a second weight (521) to the muscle strain of the second muscle, and a third weight (522) to the muscle strain of the third muscle.

Then, the server (120) can quantitatively express the rehabilitation effect for the corresponding rehabilitation movement (510) by adding up multiple weighted muscle strains and calculating an average.

By using the average of muscle strain, the patient can more clearly and quantitatively determine the effect on multiple muscles involved in the rehabilitation movement (510).

FIG. 6 is a diagram illustrating a flow chart of a method for monitoring rehabilitation of a spinal disease patient and extracting feature motions according to the present invention.

A method for monitoring rehabilitation of a spinal disease patient and extracting feature motions according to another embodiment of the present invention is performed by a server (120).

A method for monitoring rehabilitation of a patient with spinal disease and extracting feature motions according to another embodiment of the present invention includes a step (S610) of receiving multiple rehabilitation performance data of a patient performing a spinal disease rehabilitation program from a patient terminal (110).

In S620, the server (120) classifies a plurality of rehabilitation performance data by movement, extracts rehabilitation performance data exceeding a predetermined threshold for each movement, and calculates the patient's faithfulness in performing the spinal disease rehabilitation program.

In S630, the server (120) transmits rehabilitation performance data exceeding the threshold for each movement and the patient's faithfulness in performing the spinal disease rehabilitation program to the doctor terminal (130).

In S640, the server (120) receives and manages a changed spinal disease rehabilitation program from a doctor terminal (130) based on rehabilitation performance data exceeding a threshold for each movement and the patient's faithfulness in performing the spinal disease rehabilitation program.

In one embodiment, the rehabilitation performance data includes at least one of a motion image of a patient performing a predetermined motion during a spinal disease rehabilitation program and measurement data measuring the patient's condition measured by a sensor while performing the motion.

In one embodiment, the step of extracting rehabilitation performance data exceeding a predetermined threshold includes the step of extracting image similarity by comparing an image of a patient performing a predetermined movement with a reference image of the predetermined movement by artificial intelligence of the server.

In one embodiment, the step of extracting rehabilitation performance data above a predetermined threshold includes the step of comparing measurement data measured by sensors worn by the patient when performing a predetermined movement with predetermined muscle-related characteristic data.

In one embodiment, the muscle-related characteristic data includes at least one of muscle tension, muscle stiffness, muscle elasticity, and muscle strain.

In one embodiment, the modified spinal disease rehabilitation program includes at least one of changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed.

In one embodiment, the patient's adherence to the spinal disease rehabilitation program is determined based on how regularly the patient performs the spinal disease rehabilitation program in accordance with the prescribed times, dates, sequence of movements, and number of times to perform the spinal disease rehabilitation program.

In one embodiment, the time and date information for performing the spinal disease rehabilitation program is extracted from the time and date the rehabilitation performance data was collected.

In one embodiment, the sequence of movements for performing a spinal disorder rehabilitation program is inferred from the types and locations of muscles from which measurement data is collected.

In one embodiment, the number of times the spinal disorder rehabilitation program is performed is estimated from the number of repetitions over which the same measurement data is collected.

FIG. 7 is a diagram schematically illustrating the configuration of a server of a customized alarm system through analysis of a rehabilitation performance pattern according to one embodiment of the present invention.

A customized alarm system through analysis of a rehabilitation performance pattern according to one embodiment of the present invention is configured to include a patient terminal (110), a server (120), and a doctor terminal (130) in FIG. 1.

The patient terminal (110) collects rehabilitation performance data of a patient undergoing a spinal disease rehabilitation program.

The server (120) analyzes the patient's rehabilitation performance pattern based on the rehabilitation performance data, extracts a rehabilitation performance index from the patient's rehabilitation performance pattern, and notifies the patient terminal of an alarm indicating the performance of a spinal disease rehabilitation program according to the rehabilitation performance index.

The medical terminal (130) establishes or modifies the rehabilitation policy of the spinal disease rehabilitation program or changes the composition of the spinal disease rehabilitation program according to the rehabilitation performance indicators.

The server (120) of the present invention is characterized by analyzing a patient's rehabilitation performance pattern based on rehabilitation performance data and automatically notifying an alarm to a patient terminal.

Separately, the patient can set an alarm on his/her patient terminal (110) to notify him/her of the performance of the spinal disease rehabilitation program to achieve the goals he/she has set for himself/herself.

As illustrated in FIG. 7, in order to implement a customized alarm system through rehabilitation performance pattern analysis according to one embodiment of the present invention, the server (120) includes a rehabilitation performance pattern analysis unit (710), a rehabilitation performance index extraction unit (720), an alarm notification unit (730), and an alarm notification cycle adjustment unit (740).

The rehabilitation performance pattern analysis unit (710) analyzes the patient's rehabilitation performance pattern by obtaining at least one piece of information from the rehabilitation performance data: rehabilitation date, rehabilitation time, rehabilitation movement sequence, and number of rehabilitation repetitions.

The rehabilitation performance index extraction unit (720) extracts a rehabilitation performance index by comparing the rehabilitation schedule included in the rehabilitation policy of the spinal disease rehabilitation program with the patient's rehabilitation performance pattern.

Rehabilitation performance indicators can be expressed as specific numbers or as grades such as A, B, C, etc.

The closer the rehabilitation date, rehabilitation time, rehabilitation movement sequence, and rehabilitation repetition count from the rehabilitation performance data are to the rehabilitation schedule time, rehabilitation schedule date, rehabilitation schedule movement sequence, and rehabilitation schedule count included in the rehabilitation policy of the spinal disease rehabilitation program, the higher the rehabilitation performance index will be.

As a specific example, if the rehabilitation time matches the rehabilitation schedule time from the rehabilitation performance data, the rehabilitation performance index can be given 10 points. The rehabilitation performance index can be lowered as the rehabilitation time is later than the rehabilitation schedule time.

The rehabilitation performance index values given for each of the rehabilitation date, rehabilitation time, rehabilitation movement sequence, and rehabilitation repetition number can be preset in the rehabilitation policy of the spinal disease rehabilitation program.

The rehabilitation performance index value can be given differently for the rehabilitation date, rehabilitation time, rehabilitation movement order, and number of rehabilitation repetitions. That is, if the rehabilitation movement order is considered most important and the rehabilitation movement order matches the rehabilitation schedule movement order, 100 points can be given to the rehabilitation performance index.

The rehabilitation performance index extraction unit (720) can determine the average value of rehabilitation performance indexes of rehabilitation date, rehabilitation time, rehabilitation movement sequence, and number of rehabilitation repetitions as the final rehabilitation performance index.

The alarm notification unit (730) notifies the patient terminal (110) of an alarm notifying the performance of a spinal disease rehabilitation program.

The alarm notification cycle control unit (740) automatically controls the alarm notification cycle based on the rehabilitation performance indicator.

In one embodiment, the rehabilitation performance indicator includes the patient's faithfulness in performing the spinal disease rehabilitation program, and the faithfulness in performing the spinal disease rehabilitation program is determined based on how regularly the patient performs the spinal disease rehabilitation program in accordance with the rehabilitation schedule time, rehabilitation schedule date, rehabilitation schedule motion sequence, and rehabilitation schedule number of times included in the rehabilitation policy of the spinal disease rehabilitation program.

When extracting the fidelity of performing a spinal disease rehabilitation program, the rehabilitation date and rehabilitation time are extracted from the date and time when the rehabilitation performance data is collected, the rehabilitation movement order is estimated from the type and location of the muscle from which the rehabilitation performance data is collected, and the number of rehabilitation repetitions is estimated from the number of repetitions in which the same rehabilitation performance data is collected.

In one embodiment, the rehabilitation performance data may include at least one of a motion image of a patient performing a predetermined motion during a spinal disease rehabilitation program and measurement data measuring the patient's condition measured by a sensor while performing the motion.

In one embodiment, the rehabilitation performance pattern analysis unit (710) may be configured to classify rehabilitation performance data by movement and extract rehabilitation performance data exceeding a predetermined threshold for each movement.

In one embodiment, the rehabilitation performance index extraction unit (720) may be configured to extract a rehabilitation performance index based on rehabilitation performance data greater than or equal to a threshold. By extracting a rehabilitation performance index based on rehabilitation performance data greater than or equal to a threshold, a rehabilitation movement by a patient can be utilized as a rehabilitation performance index only when it is performed correctly compared to a reference movement.

Rehabilitation movements performed below a threshold compared to the baseline movement are not counted in the rehabilitation performance index, so they can be ignored as not being performed.

Extraction of rehabilitation performance data exceeding a predetermined threshold by the rehabilitation performance index extraction unit (720) is performed by extracting image similarity by comparing an image of a patient performing a predetermined movement with a reference image of the predetermined movement using artificial intelligence.

Extraction of rehabilitation performance data exceeding a predetermined threshold by the rehabilitation performance index extraction unit (720) is performed by comparing measurement data measured by a sensor worn by the patient when performing a predetermined movement with predetermined muscle-related characteristic data.

In one embodiment, the muscle-related characteristic data includes at least one of muscle tension, muscle stiffness, muscle elasticity, and muscle strain.

In one embodiment, changing the composition of the spinal disease rehabilitation program includes at least one of changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed.

In one embodiment, the alarm notification cycle control unit (740) may be configured to reduce the cycle of the alarm when the rehabilitation performance index is lower than the comparative rehabilitation performance index of another patient undergoing rehabilitation with the same spinal disease rehabilitation program.

The purpose is to encourage more active rehabilitation through comparison with other patients undergoing rehabilitation with the same spinal disease rehabilitation program.

In one embodiment, the rehabilitation performance indicator extraction unit (720) may be configured to extract rehabilitation performance indicators in predetermined rehabilitation period units.

In one embodiment, the alarm notification cycle control unit (740) may be configured to reduce the cycle of the alarm when a rehabilitation performance index lower than the minimum rehabilitation performance index extracted from a past rehabilitation period unit is obtained.

FIG. 8 is a flowchart illustrating a customized alarm method through analysis of a rehabilitation performance pattern according to one embodiment of the present invention.

A customized alarm method through analysis of a rehabilitation performance pattern according to another embodiment of the present invention includes a rehabilitation performance data reception step (S810) for receiving rehabilitation performance data of a patient performing a spinal disease rehabilitation program, a rehabilitation performance pattern analysis step (S820) for analyzing a patient's rehabilitation performance pattern by obtaining at least one piece of information from the rehabilitation performance data among a rehabilitation date, a rehabilitation time, a rehabilitation movement sequence, and a number of rehabilitation repetitions, a rehabilitation performance index extraction step (S830) for extracting a rehabilitation performance index by comparing the patient's rehabilitation performance pattern with a rehabilitation schedule included in a rehabilitation policy of the spinal disease rehabilitation program, and an alarm notification step (S840) for notifying an alarm notifying the performance of the spinal disease rehabilitation program to a patient terminal based on the rehabilitation performance index.

A customized alarm method through analysis of a rehabilitation performance pattern according to another embodiment of the present invention may further include an alarm notification cycle adjustment step for automatically adjusting an alarm notification cycle based on a rehabilitation performance index, and a spinal disease rehabilitation program configuration change step for changing the configuration of a spinal disease rehabilitation program based on the rehabilitation performance index.

In one embodiment, the rehabilitation performance indicator includes the patient's faithfulness in performing the spinal disease rehabilitation program, and the faithfulness in performing the spinal disease rehabilitation program is determined based on how regularly the patient performs the spinal disease rehabilitation program in accordance with the rehabilitation schedule time, rehabilitation schedule date, rehabilitation schedule motion sequence, and rehabilitation schedule number of times included in the rehabilitation policy of the spinal disease rehabilitation program.

In one embodiment, the rehabilitation date and rehabilitation time are extracted from the date and time when the rehabilitation performance data is collected, the rehabilitation motion sequence is estimated from the type and location of the muscle from which the rehabilitation performance data is collected, and the number of rehabilitation repetitions is estimated from the number of repetitions for which the same rehabilitation performance data is collected.

In one embodiment, the rehabilitation performance data includes at least one of a motion image of a patient performing a predetermined motion during a spinal disease rehabilitation program and measurement data measuring the patient's condition measured by a sensor while performing the motion.

In one embodiment, the rehabilitation performance pattern analysis step (S820) includes classifying rehabilitation performance data by movement and extracting rehabilitation performance data exceeding a predetermined threshold for each movement.

In one embodiment, the rehabilitation performance indicator extraction step (S830) includes extracting a rehabilitation performance indicator based on rehabilitation performance data greater than or equal to a threshold.

In one embodiment, the extraction of rehabilitation performance data exceeding a predetermined threshold in the rehabilitation performance index extraction step is performed by extracting image similarity by comparing an image of a patient performing a predetermined movement with a reference image of the predetermined movement by artificial intelligence.

In one embodiment, the extraction of rehabilitation performance data exceeding a predetermined threshold in the rehabilitation performance index extraction step is characterized in that it is performed by comparing measurement data measured by the sensor worn by the patient when performing a predetermined movement with predetermined muscle-related characteristic data.

In one embodiment, the muscle-related characteristic data includes at least one of muscle tension, muscle stiffness, muscle elasticity, and muscle strain.

In one embodiment, the step of changing the composition of the spinal disease rehabilitation program includes at least one of changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed.

In one embodiment, the alarm notification frequency adjustment step includes reducing the frequency of the alarm when the rehabilitation performance indicator is lower than a comparative rehabilitation performance indicator of another patient undergoing rehabilitation with the same spinal disease rehabilitation program.

In one embodiment, the rehabilitation performance indicator extraction step (S830) includes extracting the rehabilitation performance indicator in predetermined rehabilitation period units.

In one embodiment, the alarm notification cycle adjustment step comprises decreasing the cycle of the alarm when a rehabilitation performance index lower than a minimum rehabilitation performance index extracted from a past rehabilitation period unit is obtained.

FIG. 9 is a diagram illustrating an exemplary computing device that may implement devices and/or systems according to various embodiments of the present invention.

An exemplary computing device (900) that can implement devices according to some embodiments of the present disclosure will now be described in more detail with reference to FIG. 9.

A computing device (900) may include one or more processors (910), a bus (950), a communication interface (970), a memory (930) for loading a computer program (991) executed by the processor (910), and a storage (990) for storing the computer program (991). However, only components related to the embodiment of the present disclosure are illustrated in FIG. 9.

Accordingly, a person skilled in the art will appreciate that the present disclosure may further include general components other than those illustrated in FIG. 9.

The processor (910) controls the overall operation of each component of the computing device (900). The processor (910) may be configured to include a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphics Processing Unit), or any other form of processor (910) well known in the technical field of the present disclosure. In addition, the processor (910) may perform operations for at least one application or program for executing a method according to embodiments of the present disclosure. The computing device (900) may have one or more processors (910). The computing device (900) may refer to artificial intelligence (AI).

The memory (930) stores various data, commands, and/or information. The memory (930) can load one or more programs (991) from the storage (990) to execute a method according to embodiments of the present disclosure. The memory (930) may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

The bus (950) provides communication between components of the computing device (900). The bus (950) may be implemented as various types of buses such as an address bus, a data bus, and a control bus.

The communication interface (970) supports wired and wireless Internet communication of the computing device (900). In addition, the communication interface (970) may support various communication methods other than Internet communication. To this end, the communication interface (970) may be configured to include a communication module well known in the technical field of the present disclosure.

According to some embodiments, the communication interface (970) may be omitted.

Storage (990) can non-temporarily store one or more programs (991) and various data.

Storage (990) may be configured to include non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present disclosure pertains.

The computer program (991) may include one or more instructions that cause the processor (910) to perform methods/operations according to various embodiments of the present disclosure when loaded into the memory (930). That is, the processor (910) may perform methods/operations according to various embodiments of the present disclosure by executing the one or more instructions.

Although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications may be made by those skilled in the art without departing from the gist of the present invention as claimed in the claims. Furthermore, such modifications should not be understood individually from the technical idea or prospect of the present invention.

Claims (18)

A patient terminal that collects rehabilitation performance data from patients undergoing a spinal disease rehabilitation program;
A server that analyzes the patient's rehabilitation performance pattern based on the rehabilitation performance data, extracts a rehabilitation performance index from the patient's rehabilitation performance pattern, and notifies the patient terminal of an alarm indicating the performance of the spinal disease rehabilitation program according to the rehabilitation performance index;
Including a terminal for use by a physician to establish or modify the rehabilitation policy of the above spinal disease rehabilitation program or to change the composition of the above spinal disease rehabilitation program according to the above rehabilitation performance indicators;
The above server,
A rehabilitation performance pattern analysis unit that analyzes the patient's rehabilitation performance pattern by obtaining at least one piece of information from the rehabilitation performance data, including a rehabilitation date, a rehabilitation time, a rehabilitation movement sequence, and a number of rehabilitation repetitions;
A rehabilitation performance index extraction unit that extracts the rehabilitation performance index by comparing the rehabilitation schedule included in the rehabilitation policy of the above spinal disease rehabilitation program with the rehabilitation performance pattern of the patient;
An alarm notification unit that notifies the patient terminal of an alarm indicating the performance of the spinal disease rehabilitation program; and
An alarm notification cycle control unit that automatically controls the notification cycle of the alarm based on the rehabilitation performance indicator;
The above rehabilitation performance indicator includes the patient's faithfulness in performing the spinal disease rehabilitation program, and the faithfulness in performing the spinal disease rehabilitation program is determined based on how regularly the patient performs the spinal disease rehabilitation program in accordance with the rehabilitation schedule time, rehabilitation schedule date, rehabilitation schedule movement order, and rehabilitation schedule number of times included in the rehabilitation policy of the spinal disease rehabilitation program.
The above rehabilitation date and rehabilitation time are extracted from the date and time the above rehabilitation performance data was collected,
The above rehabilitation movement sequence is estimated from the type and location of the muscle from which the rehabilitation performance data is collected.
A customized alarm system through analysis of rehabilitation performance patterns, characterized in that the number of rehabilitation repetitions is estimated from the number of repetitions in which the same rehabilitation performance data is collected. delete delete In claim 1,
The above rehabilitation performance data includes at least one of a motion image of the patient performing a predetermined motion when performing the spinal disease rehabilitation program and measurement data measuring the patient's condition measured by a sensor when performing the motion.
The above rehabilitation performance pattern analysis unit classifies the rehabilitation performance data by movement, and extracts rehabilitation performance data exceeding a predetermined threshold for each movement.
A customized alarm system through rehabilitation performance pattern analysis, characterized in that the rehabilitation performance index extraction unit is configured to extract the rehabilitation performance index based on rehabilitation performance data exceeding the threshold value. In claim 4,
The extraction of rehabilitation performance data exceeding a predetermined threshold by the above rehabilitation performance index extraction unit is performed by extracting image similarity by comparing an image of the patient performing a predetermined movement with a reference image of the predetermined movement by artificial intelligence.
A customized alarm system through analysis of a rehabilitation performance pattern, characterized in that the extraction of rehabilitation performance data exceeding a predetermined threshold by the rehabilitation performance index extraction unit is performed by comparing the measurement data measured by the sensor worn by the patient when performing the determined movement with predetermined muscle-related characteristic data. In claim 5,
A customized alarm system through analysis of rehabilitation performance patterns, wherein the muscle-related characteristic data includes at least one of muscle tension, muscle stiffness, muscle elasticity, and muscle strain. In claim 1,
A customized alarm system through analysis of a rehabilitation performance pattern, wherein changing the composition of the spinal disease rehabilitation program includes at least one of changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed. In claim 1,
A customized alarm system through analysis of rehabilitation performance patterns, characterized in that the alarm notification cycle control unit reduces the cycle of the alarm when the rehabilitation performance index is lower than the comparative rehabilitation performance index of other patients undergoing rehabilitation with the same spinal disease rehabilitation program. In claim 1,
The above rehabilitation performance indicator extraction unit is configured to extract rehabilitation performance indicators in predetermined rehabilitation period units,
A customized alarm system through analysis of rehabilitation performance patterns, characterized in that the alarm notification cycle control unit reduces the cycle of the alarm when a rehabilitation performance index lower than the minimum rehabilitation performance index extracted from a past rehabilitation period unit is obtained. A rehabilitation performance data receiving step for receiving rehabilitation performance data of a patient performing a spinal disease rehabilitation program;
A rehabilitation performance pattern analysis step for analyzing the patient's rehabilitation performance pattern by obtaining at least one piece of information from the rehabilitation performance data, including a rehabilitation date, a rehabilitation time, a rehabilitation movement sequence, and a rehabilitation repetition number;
A rehabilitation performance index extraction step for extracting a rehabilitation performance index by comparing the rehabilitation schedule included in the rehabilitation policy of the above spinal disease rehabilitation program with the rehabilitation performance pattern of the patient;
An alarm notification step for notifying a patient terminal of the performance of the spinal disease rehabilitation program based on the rehabilitation performance indicator;
An alarm notification cycle adjustment step for automatically adjusting the notification cycle of the alarm based on the above rehabilitation performance indicator; and
A step of changing the composition of the spinal disease rehabilitation program according to the above rehabilitation performance indicators; including,
The above rehabilitation performance indicator includes the patient's faithfulness in performing the spinal disease rehabilitation program, and the faithfulness in performing the spinal disease rehabilitation program is determined based on how regularly the patient performs the spinal disease rehabilitation program in accordance with the rehabilitation schedule time, rehabilitation schedule date, rehabilitation schedule movement order, and rehabilitation schedule number of times included in the rehabilitation policy of the spinal disease rehabilitation program.
The above rehabilitation date and rehabilitation time are extracted from the date and time the above rehabilitation performance data was collected,
The above rehabilitation movement sequence is estimated from the type and location of the muscle from which the rehabilitation performance data is collected.
A customized alarm method through analysis of rehabilitation performance patterns, characterized in that the number of rehabilitation repetitions is estimated from the number of repetitions in which the same rehabilitation performance data is collected. delete delete In claim 10,
The above rehabilitation performance data includes at least one of a motion image of the patient performing a predetermined motion when performing the spinal disease rehabilitation program and measurement data measuring the patient's condition measured by a sensor when performing the motion.
The above rehabilitation performance pattern analysis step includes classifying the rehabilitation performance data by movement and extracting rehabilitation performance data exceeding a predetermined threshold for each movement.
A customized alarm method through rehabilitation performance pattern analysis, wherein the above rehabilitation performance index extraction step includes extracting the rehabilitation performance index based on rehabilitation performance data exceeding the threshold value. In claim 13,
In the above rehabilitation performance index extraction step, the extraction of rehabilitation performance data exceeding a predetermined threshold is performed by extracting image similarity by comparing the motion image of the patient performing the determined motion with the reference image of the determined motion by artificial intelligence.
A customized alarm method through analysis of a rehabilitation performance pattern, characterized in that the extraction of rehabilitation performance data exceeding a predetermined threshold in the above rehabilitation performance index extraction step is performed by comparing the measurement data measured by the sensor worn by the patient when performing the above-determined movement with predetermined muscle-related characteristic data. In claim 14,
A customized alarm method through analysis of rehabilitation performance patterns, wherein the muscle-related characteristic data includes at least one of muscle tension, muscle stiffness, muscle elasticity, and muscle strain. In claim 10,
A customized alarm method through analysis of a rehabilitation performance pattern, wherein the step of changing the composition of the spinal disease rehabilitation program includes at least one of changing the order of movements constituting the spinal disease rehabilitation program, adjusting the duration of performance of movements constituting the spinal disease rehabilitation program, and adjusting the number of times the movements constituting the spinal disease rehabilitation program are performed. In claim 10,
A customized alarm method through analysis of rehabilitation performance patterns, wherein the alarm notification cycle adjustment step includes reducing the cycle of the alarm when the rehabilitation performance index is lower than the comparative rehabilitation performance index of other patients undergoing rehabilitation with the same spinal disease rehabilitation program. In claim 10,
The above rehabilitation performance indicator extraction step includes extracting rehabilitation performance indicators by predetermined rehabilitation period units,
A customized alarm method through analysis of a rehabilitation performance pattern, wherein the alarm notification cycle adjustment step includes reducing the cycle of the alarm when a rehabilitation performance index lower than the minimum rehabilitation performance index extracted from a past rehabilitation period unit is obtained.

Images