KR101573118B1 - Smart terminal for point of care - Google Patents

Abstract

The present invention relates to a smart terminal for receiving a living body signal from a sensor attached to a human body and transmitting a living body signal to a related medical center through the Internet, comprising: a central processing unit (CPU) for controlling the overall operation of the smart terminal; (EN) There is provided an image processing apparatus that receives biometric signal data from two or more GPU (Graphics Processing Unit) cores for processing image information or processing a screen output and at least one sensor for collecting biometric signals, and divides the biometric signal data, And a task scheduler that generates a processing task by fragmenting the fragmented processing task and allocates the fragmented processing task to the at least two GPU cores. According to the present invention, barriers to entry into mobile healthcare can be eliminated by extending functions of smart terminals such as smart phones and tablet PCs.

Description

[0001] Smart terminal for on-site medical diagnosis [

The present invention relates to a smart terminal such as a smart phone, and more particularly to a smart terminal used for on-site medical diagnosis.

Generally, as the development of mobile communication technology, the function of a mobile phone is developing as a multimedia phone which transmits a simple call function, data communication as well as moving image.

In addition, as the living standard increases from the social point of view, the average life expectancy increases and the aging population increases. As interest in the well-being lifestyle that pursues a happy life increases, interest in the individual's health and safety is increasing. to be.

In response to this tendency, technologies for providing health-related services using mobile terminals (e.g., mobile phones) have been gradually developed and Korean Patent Registration No. 10-0374979 has been proposed as "a health management service system for wireless communication network and / Method "has been registered.

In the related art, a mobile phone has a vibration sensor unit and a low-frequency sensor unit to detect the number of walking and heart rate of a user and transmit the detected number to the server through a communication network, and the server analyzes the information to provide individual health- have.

However, such conventional health-related service providing technologies detect only a small part of the user's biometric information and provide health related information, so that health related information is not accurate and service contents are extremely limited.

In addition, vehicles such as automobiles (automobiles, electric trains, trains), ships, aircraft and the like have been applied to human-use transportation means such as an integrated safety management system linked to a mobile communication terminal of Korean Patent Registration No. 10-0397756. , A ship, an aircraft, and so on, the safety and management system that links the mobile body and the mobile communication terminal is implemented in order to achieve safety and management, and the mobile body and the mobile communication terminal are linked. In addition, The control of the vehicle, the control of the vehicle, the provision of traffic information, and other information related to the information and safety and management of the vehicle are introduced.

However, such a technology restricts the objects to be managed to safety devices for ships, aircraft, heavy equipment, and important facilities, and there is a limitation in object setting, and the communication connection is cut off or the reaction speed is slow and the economical problem of the communication fee is obstructed in commercialization There was a problem.

On the other hand, the development of the communication network is called the sea of information that conveys the information of every part of the world at an unspectacular time. The international computer network Internet is very important and useful to all human beings and it is a technology that broadens the choice for all the members of society.

The IT technology history of electronic information communication using this is that when the calling number is taken by wireless communication, the order number is taken on the other device, and after passing through the simple pager of the analog function which called by calling the calling number, Former vice president of Motorola (1973) who made cellular phone (voice function) After Martin Kofer's simple voice mobile phone technology era, feature phone technology that transmits characters and images in real time is generalized.

The feature phone, which combines the Internet technology, IT technology, and satellite communication network technology to transmit and receive voice, text, and image, is an innovative IT technology compared to a pager and a cellular phone.

However, recently, Apple's iPhone (iphone), Samsung's Galaxy S smartphone (smartphone), etc., can not be used as a personal computer Operating systems and implementation functions, such as providing interfaces and platforms for software execution, are destroying the feature phone monopoly market.

Web browser for launching Mosaic browser with successful commercial network Web browser for accessing world wide page by using Microsoft's Internet Explorer, Mozilla's Firefox, etc. Feature phone, Connect to Mobilis Facebook, which allows smartphones to create and download applications that feature phones can not use, such as listening to music, getting directions, scheduling, viewing e-books, and implementing augmented reality. And SNS (Mobile Social Networking Service), which is represented by Twitter, provide a PC-like interface and platform, and the SNS service improvement function to increase the search share from the users, , Web, homepage, etc., Development of competition is fierce.

In the service technology market of the feature phone and the smartphone, a tablet PC called a small PC is equipped with an operating system (OS) of Microsoft (MS) Windows 7, a webcam and an SD card slot, a micro HDMI terminal and another Wi- (Wi-LAN) In addition to Bluetooth, Tablet PC, which is different from iPad that can connect to WiMAX, is in the initial stage of commercialization. It is an IT device of internet communication network that Internet technology and IT technology are used in combination with satellite communication network technology. The next generation PC device that connects to smartphone, smartphone, tablet PC phone, desktop PC, and notebook PC after the feature phone connects to the Internet network and the Internet network and connects IT devices connected to the Internet network , The result of service quality and amount of service varies greatly according to the result of the viewpoint decision of the service entity managing and operating the service after connection.

In recent years, there has been a system for implementing a communication network that combines Internet technology, IT device technology, and satellite communication network technology, and a next-generation PC device that includes smart phones, tablet PCs, desktop PCs, The mobile CPU (human brain) and GPU (multi-monitor) technologies are evolving to make intelligent decisions and roles that make data analysis more sophisticated, mathematical, intelligent and emotional.

In the mobile device, the execution speed is also increased to 1 GHz, providing various possibilities oriented functions such as Internet search and multimedia reproduction, and the competition among the companies is intensifying.

Recently, many attempts have been made for personalized medical services. In this trend, much attention is focused on the development of new sensors, where the main subject is intermittent monitoring of biological signals, alarms based on thresholds, and data uploading.

There are many cases in which a separate monitoring terminal is used for such medical service, which increases the cost.

In addition, when smart terminals such as smart phones and tablet PCs are used, most of them are used for simple display purposes.

In addition, energy-efficient continuous bio-signal processing is required, and there are many advantages when first-order local processing is performed using a highly-smart smart terminal. For example, it can request early risk diagnosis and telemedicine in similar cases, utilize various communication interfaces, and can be extended to use as an economical point-of-care (POC) testing device.

However, there is a problem that such an application example using the smart terminal is difficult to manage power consumption compared with a dedicated terminal, and various user applications coexist and are difficult to be generalized, and large power consumption is large due to use of a large display and a high performance CPU.

Korean Patent Registration No. 10-0374979 Korean Patent Registration No. 10-0397756

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and it is an object of the present invention to provide energy efficient processing of bio-signal processing of a smart terminal for on-site medical diagnosis.

For this purpose, there is another purpose of collecting sensing data in a smart terminal, designing an algorithm, and designing a mobile GPU based bio-signal local processing algorithm.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, the present invention provides a smart terminal for receiving a living body signal from a sensor attached to a human body and transmitting a living body signal to an associated medical center through the Internet, Processing unit), two or more GPU (Graphics Processing Unit) cores for processing image information of a smart terminal or processing a screen output, and biometric signal data from at least one sensor for collecting bio-signals, And a task scheduler for fragmenting the bio-signal data to generate a processing task and allocating a fragmented processing task to the two or more GPU cores.

The task scheduler may buffer the bio-signal so that the GPU core is activated for a minimum amount of time.

The task scheduler may fragment the bio-signal data by the number of GPU cores.

When receiving a bio-signal from two or more sensors, the task scheduler can buffer the processing of each bio-signal to be assigned to different time slots if the processing time difference for each bio-signal is greater than a predetermined reference.

The smart terminal includes a CPU processing algorithm for providing load information according to the CPU processing to the task scheduler and a GPU processing algorithm for providing load information according to the GPU processing to the task scheduler algorithm).

The task scheduler quantifies the power consumption characteristics of each of the CPU and the GPU according to the load, DB (Database) tables them, predicts a load due to the CPU processing and a load according to the GPU processing according to the input load of the bio- The energy efficiency of the processing and the optimal load distribution can be determined based on the load according to the current CPU processing received from the CPU processing algorithm and the load according to the current GPU processing received from the GPU processing algorithm.

Wherein the smart terminal further comprises a battery management system for managing a battery, the task scheduler calculating an energy cost in conjunction with the battery management system, and based on the calculated energy cost, the CPU and the GPU Can be scheduled.

The task scheduler may schedule a task between the CPU and the GPU in a direction that minimizes a processing delay when the remaining amount of the battery is equal to or greater than a predetermined value.

According to the present invention, barriers to entry into mobile healthcare can be eliminated by extending functions of smart terminals such as smart phones and tablet PCs.

In addition, energy can be efficiently used when a smart terminal uses a mobile healthcare application.

1 is a block diagram of a field medical diagnosis system according to an embodiment of the present invention.
FIG. 2 is a diagram for explaining a fragmentation of a bio-signal and an operation allocation method in a GPU core according to an embodiment of the present invention.
3 is a block diagram illustrating a configuration of a mobile terminal according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted in an ideal or overly formal sense unless expressly defined in the present application Do not.

In the following description of the present invention with reference to the accompanying drawings, the same components are denoted by the same reference numerals regardless of the reference numerals, and redundant explanations thereof will be omitted. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail.

1 is a block diagram of a field medical diagnosis system according to an embodiment of the present invention.

Referring to FIG. 1, the smart terminal 100 is a concept of a mobile communication terminal including a smart phone, a tablet PC, and the like.

The smart terminal 100 receives a biometric signal from a sensor attached to a human body such as a wireless body sensor, and transmits the biometric signal to the related medical center via the Internet.

In the present invention, the bio-signal processing energy efficiency of a smart terminal for point-of-care (POC) is sought, and a data processing technique for GPU processing of multiple bio-signals, a processing load and an energy consumption prediction And assigning and switching tasks between the GPU and the CPU.

FIG. 2 is a diagram for explaining a fragmentation of a bio-signal and an operation allocation method in a GPU core according to an embodiment of the present invention.

A GPU is an operation processing unit that processes image information of a computer or outputs a screen image. The GPU is designed to facilitate the graphic processing of a central processing unit. The GPU is included in a graphics card or a motherboard. Quot; refers to a semiconductor chip that processes an operation. A GPU is also called a graphics processor or simply a graphics processing unit (GPU).

The GPU was created to address bottlenecks caused by the graphics work of a central processing unit (CPU) and can process 2D or 3D graphics faster than CPU processing. Because of this graphics acceleration, the graphics card is also called a graphics accelerator, and the performance of the graphics card depends on the graphics processing unit (GPU) and video RAM (RAM).

Referring to FIG. 2, the smart terminal performs fragmentation of a serial type bio signal input from a sensor, and then assigns a processing task to a plurality of GPU cores.

3 is a block diagram illustrating a configuration of a mobile terminal according to an embodiment of the present invention.

3, the mobile terminal of the present invention includes a task scheduler 310, a central processing unit (CPU), a graphics processing unit (GPU) core, a GPU processing algorithm 320, A processing algorithm 330, and a battery management system 340.

The CPU controls the overall operation of the smart terminal.

The GPU core plays a role of processing image information of the smart terminal or processing the screen output, and is provided in a plurality of two or more.

The task scheduler 310 receives bio-signal data from at least one sensor for collecting bio-signals, and generates a processing task by fragmenting the bio-signal data in serial form , And assigning fragmented processing tasks to more than one GPU core.

In one embodiment of the present invention, the task scheduler 310 may buffer the biometric signal such that the GPU core is activated for a minimum amount of time.

In an embodiment of the present invention, the task scheduler 310 may fragment the bio-signal data by the number of GPU cores.

In the case of receiving biometric signals from two or more sensors, the task scheduler 310 may buffer the processing of each bio-signal to be assigned to different time slots if the processing time difference for each biometric signal is equal to or greater than a predetermined reference.

The CPU processing algorithm 320 serves to provide the task scheduler 310 with load information according to CPU processing.

The GPU processing algorithm 330 serves to provide the task scheduler 310 with load information according to GPU processing.

The task scheduler 310 quantifies the power consumption characteristics of each CPU and the GPU according to the load, DB (Database) tables them, predicts the load according to the CPU processing and the load according to the GPU processing according to the input load of the bio- Determines the energy efficiency and optimal load distribution of the processing based on the load according to the current CPU processing received from the CPU processing algorithm and the load according to the current GPU processing received from the GPU processing algorithm.

The battery management system 340 serves to manage the battery.

In an embodiment of the present invention, the task scheduler 310 may calculate the energy cost in conjunction with the battery management system 340, and may schedule tasks between the CPU and the GPU based on the calculated energy cost. Here, the task scheduler 310 can schedule tasks between the CPU and the GPU in a direction that minimizes processing delay when the remaining amount of the battery is equal to or greater than a predetermined value.

In the present invention, the task scheduler 310 quantifies the power consumption characteristics of the CPU and the GPU according to the load, and DB-tables them. To this end, the task scheduler 310 hard-codes real-time measurements or pre-measurement data.

p_cpu (load) is the power consumption function according to the CPU load, and p_gpu (load) is the power consumption function according to the GPU load.

The task scheduler 310 predicts the CPU processing load and the GPU processing load according to the input load of the bio-signal.

load_cpu (a × load) is a CPU load conversion function according to an allocation signal load, and load_gpu ((1 - a) × load) is a CPU load conversion function according to an allocation signal load.

a (0? a? 1) is a load dispersion factor.

The task scheduler 310 predicts the energy efficiency of processing based on each current load and determines the optimal load distribution. The total energy consumption expressed as follows is obtained by applying the minimum value to the load dispersion factor a between the CPU and the GPU.

Load (1-a) load) nT_gpu ((1-a) load) clp_cpu (cl_cpu + load_cpu (a x load) nt_cpu (a x load) + p_gpu (cload_gpu +

Here, E (a) is a function of a as a total energy consumption, cload_cpu is an authorization load of a conventional CPU, cload_gpu is an authorization load of an existing GPU, and nT_cpu (a x load) , And nT_gpu ((1 - a) × load) is the time required for the operation of the GPU for processing the bio signal.

In the present invention, the task scheduler 310 calculates the energy cost through interworking with the battery management system 340.

The task scheduler 310 operates in a different strategy according to the current remaining battery level, and operates in the direction of minimizing the processing delay when the remaining amount is large. A, which minimizes the cost due to the energy consumption expressed as follows according to the load dispersion factor, is applied.

Cost (a) = e_price (cbattery) x E (a)

Here, e_price (cbattery) is the cost of energy consumption according to the current battery charge (cbattery).

While the present invention has been described with reference to several preferred embodiments, these embodiments are illustrative and not restrictive. It will be understood by those skilled in the art that various changes and modifications may be made therein without departing from the spirit of the invention and the scope of the appended claims.

100 Smart Terminal 310 Task Scheduler
320 GPU processing algorithm 330 CPU processing algorithm
340 Battery management system

Claims (8)

1. A smart terminal for receiving a living body signal from a sensor attached to a human body and transmitting a living body signal to an associated medical center via the Internet,
A central processing unit (CPU) for controlling the overall operation of the smart terminal;
At least two graphics processing unit (GPU) cores for processing image information of a smart terminal or for processing a screen output; And
A method for processing a bio-signal, comprising: receiving bio-signal data from at least one sensor for collecting a bio-signal; generating a processing task by fragmenting the bio-signal data in serial; And a task scheduler that allocates the task scheduler to the two or more GPU cores,
Wherein the task scheduler buffers the bio-signals so that the GPU core is activated only for a minimum amount of time.
delete The method according to claim 1,
Wherein the task scheduler segments the bio-signal data by the number of GPU cores.
The method according to claim 1,
Wherein the task scheduler buffers the processing of each of the bio-signals so that the processing time of each of the bio-signals is allocated to different time slots if the processing time difference of each of the bio-signals is equal to or greater than a predetermined reference value. .
The method according to claim 1,
The smart terminal includes:
A CPU processing algorithm for providing the task scheduler with load information according to the CPU processing; And
Further comprising a GPU processing algorithm for providing the task scheduler with load information according to the GPU processing.
The method of claim 5,
The task scheduler quantifies the power consumption characteristics of each of the CPU and the GPU according to the load, DB (Database) tables them, predicts a load due to the CPU processing and a load according to the GPU processing according to the input load of the bio- And determines the energy efficiency and optimal load distribution of processing based on the load according to the current CPU processing received from the CPU processing algorithm and the load according to the current GPU processing received from the GPU processing algorithm.
The method of claim 6,
The smart terminal further includes a battery management system for managing a battery,
Wherein the task scheduler calculates an energy cost in cooperation with the battery management system and schedules a task between the CPU and the GPU based on the calculated energy cost.
The method of claim 7,
Wherein the task scheduler schedules a task between the CPU and the GPU in a direction that minimizes a processing delay when the remaining amount of the battery is equal to or greater than a predetermined value.

Images