KR102190822B1 - Method for processing biological signals based on parallel processing and apparatus for the same - Google Patents

Abstract

Disclosed are a method and apparatus for processing biosignals based on parallel processing. Here, the parallel processing-based biosignal processing method includes the steps of obtaining new biosignal data of a first sample size by measuring a biosignal of a user, and old biosignal data of a second sample size measured in advance immediately before the new biometric data. Obtaining from a data buffer, generating data to be analyzed by combining the obtained old biological signal data and the new biological signal data, extracting the most recent biological signal data of the second sample size from the data to be analyzed And storing the data in the data buffer, analyzing biometric information for the data to be analyzed, and re-performing from the step of acquiring the new biosignal data in parallel with the analysis.

Description

Bio-signal processing method based on parallel processing and its device {METHOD FOR PROCESSING BIOLOGICAL SIGNALS BASED ON PARALLEL PROCESSING AND APPARATUS FOR THE SAME}

The present invention relates to a bio-signal processing method and apparatus thereof based on parallel processing, and more particularly, by processing bio-signal collection and analysis in parallel, the memory required for storing bio-signals is minimized, and optimal It relates to technology for securing biometric data.

Due to the recent technological evolution, demand for reliable health prediction technology based on real life using various sensor technologies is increasing. In particular, the reliability of the service is reinforced by providing user-customized healthcare contents through bio-signal information that has been widely used in medical environments. In general, as a biological signal for healthcare services, there are heart rate variability (HRV) using an electrocardiogram (ECG), and various studies using this have been attempted.

Conventionally, in order to utilize the biosignal, a biosignal is first measured, and then features extraction and analysis of the measured biosignal are performed. However, in this case, a lot of memory space is required to accumulate and store the measured biosignals, and if the accumulated biosignal data is insufficient, the reliability of the analysis result is lowered or a high-performance analysis system is built according to the performance of the analysis device There is a problem to be done.

In addition, depending on actual use cases, it is impossible to extract and analyze features of the bio-signal until the measurement of the bio-signal is completed, and thus it is impossible to process an exception for error occurrence. Therefore, when an error occurs, there is a problem that the biosignal must be measured again from the beginning.

Korean Patent Publication 10-2018-0000936 (Applicant: Dr. Skin Korea Co., Ltd.)

An object of the present invention for solving the above problems is to provide a biosignal processing method based on parallel processing.

Another object of the present invention for solving the above problems is to provide a biosignal processing apparatus based on parallel processing.

Another object of the present invention for solving the above problems is to provide a method for collecting bio signals for parallel processing.

An aspect of the present invention for achieving the above object is to provide a biosignal processing method based on parallel processing.

Here, the parallel processing-based biosignal processing method includes the steps of obtaining new biosignal data of a first sample size by measuring a biosignal of a user, and old biosignal data of a second sample size measured in advance immediately before the new biometric data. Obtaining from a data buffer, generating data to be analyzed by combining the obtained old biological signal data and the new biological signal data, extracting the most recent biological signal data of the second sample size from the data to be analyzed And storing the data in the data buffer, analyzing biometric information for the data to be analyzed, and re-performing from the step of acquiring the new biosignal data in parallel with the analysis.

Here, the first sample size may be set smaller than the second sample size.

The obtaining of the new biosignal data includes transmitting a request message for requesting a biosignal to a wearable device attached to the user, and receiving the biosignal of the user from the wearable device. It may include the step of.

Herein, the user's biosignal may include at least one of blood pressure, body fat percentage, oxygen saturation, heart rate, pulse, electrocardiography (ECG), and photoplethysmography (PPG).

Here, the re-performing may include performing an exception handling for the error when an error occurs during re-execution.

Here, the performing of the exception processing may include re-adjusting the size of the data buffer based on a difference value between a time point when the analysis target data is generated and a time point at which the analysis is completed.

In the step of re-adjusting the size of the data buffer, the size of the data buffer may be readjusted based on the size of the first sample size and the second sample size.

Here, the step of re-adjusting the size of the data buffer may include increasing the first sample size than a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include.

Here, the step of re-adjusting the size of the data buffer may include reducing the second sample size from a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include.

Another aspect of the present invention for achieving the above object is to provide a biosignal processing apparatus based on parallel processing.

Here, the biosignal processing apparatus based on parallel processing may include at least one processor and a memory storing instructions instructing the at least one processor to perform at least one step. have.

Here, the at least one step may include obtaining new biosignal data of a first sample size by measuring a user's biosignal, and storing old biosignal data of a second sample size measured in advance immediately before the new biometric data into a data buffer. Obtaining from, combining the obtained old biosignal data and the new biosignal data to generate analysis target data, extracting the most recent biosignal data of the second sample size from the analysis target data It may include storing in a buffer and analyzing the biometric information for the data to be analyzed, and re-performing from the step of acquiring the new biosignal data in parallel with the analysis.

Here, the first sample size may be set smaller than the second sample size.

The obtaining of the new biosignal data includes transmitting a request message for requesting a biosignal to a wearable device attached to the user, and receiving the biosignal of the user from the wearable device. It may include the step of.

Herein, the user's biosignal may include at least one of blood pressure, body fat percentage, oxygen saturation, heart rate, pulse, electrocardiography (ECG), and photoplethysmography (PPG).

Here, the re-performing may include performing an exception handling for the error when an error occurs during re-execution.

Here, the performing of the exception processing may include re-adjusting the size of the data buffer based on a difference value between a time point when the analysis target data is generated and a time point at which the analysis is completed.

In the step of re-adjusting the size of the data buffer, the size of the data buffer may be readjusted based on the size of the first sample size and the second sample size.

Here, the step of re-adjusting the size of the data buffer may include increasing the first sample size than a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include.

Here, the step of re-adjusting the size of the data buffer may include reducing the second sample size from a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include.

Another aspect of the present invention for achieving the above object is to provide a method for collecting biometric signals for parallel processing.

Here, the biosignal collection method for parallel processing includes the steps of obtaining new biosignal data of a first sample size by measuring a biosignal of a user, and collecting old biosignal data of a second sample size measured in advance immediately before the new biometric data. Acquiring from a data buffer, generating analysis target data by combining the acquired old biological signal data and the new biological signal data, and extracting the most recent biological signal data of the second sample size from the analysis target data It may include storing in the data buffer.

Here, the first sample size may be set smaller than the second sample size.

In the case of using the bio-signal processing method and the apparatus based on parallel processing according to the present invention as described above, the memory required for storing the bio-signal is minimized by processing the measurement and analysis of the bio-signal in parallel. Biosignal data can be secured.

In addition, there is an advantage in that it is easy to handle exceptions for errors that occur when measuring biometric signals, and that unnecessary time consumption due to re-measurement can be reduced.

1 is a conceptual diagram functionally showing a biosignal processing apparatus based on parallel processing according to an embodiment of the present invention.
2 is an exemplary view of configuring a biosignal data buffer applied to parallel processing according to an embodiment of the present invention.
3 is a flowchart of a method for processing a biosignal based on parallel processing according to an embodiment of the present invention.
4 is an implementation example of a method for measuring a biosignal based on parallel processing according to an embodiment of the present invention.
5A to 5B are implementation examples of a biosignal processing method based on parallel processing according to an embodiment of the present invention.
6 is an example implementation of exception processing according to an error occurrence in a biosignal processing method based on parallel processing according to an embodiment of the present invention.
7 is a block diagram of a biosignal processing apparatus based on parallel processing according to an embodiment of the present invention.

In the present invention, various modifications may be made and various embodiments may be provided, and specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, it is to be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. In describing each drawing, similar reference numerals have been used for similar elements.

Terms such as first, second, A, and B may be used to describe various elements, but the elements should not be limited by the terms. These terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

Unless otherwise defined, 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 the present invention belongs. Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this application. Does not.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a conceptual diagram functionally showing a biosignal processing apparatus based on parallel processing according to an embodiment of the present invention.

Referring to FIG. 1, a biosignal processing apparatus 100 based on parallel processing according to an embodiment of the present invention includes a signal measurement unit 110, a buffer 120, a signal analysis unit 130, and a parallel processing control unit. (140) and/or an exception processing unit 150 may be included.

The signal measurement unit 110 periodically receives a bio-signal from a wearable device worn or attached to a user's body (eg, wrist, arm, etc.) through an external interface according to a preset sampling rate. And may store the obtained signal in the buffer 120. Here, the biological signal may be blood pressure, body fat percentage, oxygen saturation, heart rate, pulse, electrocardiography (ECG), photoplethysmography (PPG), and the like. In addition, in the drawing, the signal measurement unit 110 is shown to receive a biometric signal from a biometric device attached to the user, but the signal measurement unit 110 or the biosignal processing apparatus 100 based on parallel processing is combined with the wearable device. It can also be implemented integrally.

The signal analysis unit 130 may analyze biosignal data stored in the buffer 120 by the signal measurement unit 110 and generate analysis result data. For example, the signal analysis unit 130 may perform frequency analysis, filtering, and the like on the biosignal data stored in the buffer 120.

Here, the operation of the signal measurement unit 110 and the signal analysis unit 130 may operate in parallel with each other. For example, while measuring and collecting biosignal data through the signal measuring unit 110, the signal analyzing unit 130 may analyze the biosignal data stored in the buffer 120.

The parallel processing control unit 140 controls the operation of both the signal measurement unit 110 and the signal analysis unit 130, and the amount of biosignal data collected and stored in the buffer 120 by the signal measurement unit and the signal analysis unit 130 The amount of biosignal data processed by can be adjusted. Accordingly, the parallel processing control unit 140 may adjust the delay between data collection and analysis to be minimized or prevented even if the signal measurement unit 110 and the signal analysis unit 130 operate in parallel.

The exception processing unit 150 may perform an operation of handling an exception with respect to an error occurring during parallel processing. For example, the exception processing unit 150 may perform events such as system reset of the biosignal processing device based on parallel processing, re-execution of the signal measurement unit 110 and the signal analysis unit 130, and readjusting the size of the buffer 120. Can generate signals.

Meanwhile, although not shown in the drawings, the biosignal processing apparatus 100 based on parallel processing includes a communication module that transmits the analysis result data generated by the signal analysis unit 130 at a preset time or in real time to an external user terminal. It may contain more. In this case, the communication module may transmit and receive data through a wired network or a wireless network.

2 is an exemplary view of configuring a biosignal data buffer applied to parallel processing according to an embodiment of the present invention.

2, a data buffer for analyzing a biosignal in a biosignal processing method and apparatus based on parallel processing according to an embodiment of the present invention performs a process of measuring and analyzing a biosignal in one step (Stage, stage (Referred to as), it may be reconstructed for each of the first step 20a, the second step 20b, and the third step 20c.

At this time, the data buffer configured in each stage is composed of old biosignal data (RAW DATA OLD) and M+N sample data (M+N samples) consisting of N samples data predefined in a moving window method. It can be composed of composed new biosignal data (RAW DATA NEW). For example, the analysis target data 23 for biosignal analysis in the first stage 20a may be configured by combining the old biosignal data 22 and the new biosignal data 21.

Here, the old biosignal data (RAW DATA OLD) may be biosignal data used for biosignal analysis of a stage immediately preceding the current stage where biosignal is measured. For example, the old biosignal data 26 used in the second stage 20b is the most among the data 23 configured in the data buffer of the first stage 20a that was configured immediately before the second stage 20b. It may be the latest N number of sample data 24. Specifically, in the second stage 20b, the most recent N sample data 24 among the analysis target data 23 stored in the data buffer of the first stage 20a are the data to be analyzed in the second stage 20b ( 27), and M+N sample data (25) obtained through measurement and collection of additional bio-signal data are used as new bio-signal data (RAW DATA NEW) and later data of the analysis target data (27). Can be used. Accordingly, among the data 27 stored in the data buffer configured in the second stage 20b, the most recent N number of sample data 28 are also updated with data for biosignal analysis according to the third stage 20c.

As described above, in the present invention, a sufficient amount of data for biosignal analysis can be secured by using some of the data used for biosignal analysis in the previous stage for the next biosignal analysis. In addition, by using the old biosignal data, biosignal measurement/collection and biosignal analysis can be performed in parallel.

In the drawing, the first stage 20a to the third stage 20c are illustrated, but the data buffer may be repeatedly configured for a predetermined time or number of times. In addition, here, M and N samples mean biosignal data collected according to the sampling period. Further, M and N may be set in advance and may be readjusted to an optimized value of parallel processing according to the measurement and analysis of the biosignal. However, since some of the new biosignal data (RAW DATA NEW) is used as the old biosignal data (RAW DATA OLD), the number of samples of the new biosignal data (RAW DATA NEW) is the old biosignal data (RAW DATA OLD). ) May be smaller than the number of samples.

3 is a flowchart of a method for processing a biosignal based on parallel processing according to an embodiment of the present invention.

Referring to FIG. 3, in the parallel processing-based biosignal processing method, the step of obtaining new biosignal data of a first sample size by measuring a biosignal of a user (S100), 2 Obtaining old biosignal data of a sample size from a data buffer (S110), combining the obtained old biosignal data and the new biosignal data to generate data to be analyzed (S120), from the data to be analyzed Extracting the most recent biosignal data of the second sample size and storing it in the data buffer (S130), analyzing biometric information for the data to be analyzed, and the new biosignal data in parallel with the analysis It may include a step (S140) of re-performing from the step of acquiring.

Here, the first sample size may be set smaller than the second sample size.

Here, the step of acquiring the new biosignal data (S100) includes transmitting a request message for requesting a biosignal to a wearable device attached to the user, and the user's biometrics from the wearable device. It may include receiving a signal.

Herein, the user's biosignal may include at least one of blood pressure, body fat percentage, oxygen saturation, heart rate, pulse, electrocardiography (ECG), and photoplethysmography (PPG).

Here, the re-performing step S140 may include performing exception handling for the error when an error occurs during re-execution.

Here, the performing of the exception processing may include re-adjusting the size of the data buffer based on a difference value between a time point when the analysis target data is generated and a time point at which the analysis is completed.

In the step of re-adjusting the size of the data buffer, the size of the data buffer may be readjusted based on the size of the first sample size and the second sample size.

Here, the step of re-adjusting the size of the data buffer may include increasing the first sample size than a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include. That is, since the amount of new data to be collected is increased by increasing the first sample size, it is possible to adjust the time point at which the analysis target data is generated and the time point at which the analysis is completed are adjacent.

Here, the step of re-adjusting the size of the data buffer may include reducing the second sample size from a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include. That is, since the amount of old data is reduced by reducing the second sample size, the time required for analysis may be reduced.

Also, a process of increasing the first sample size and decreasing the second sample size may be performed simultaneously.

In addition, in the biosignal processing method for parallel processing according to an embodiment of the present invention, only the biosignal collection method may be separately performed.

In this case, the biosignal collection method for parallel processing according to an embodiment of the present invention includes the steps of obtaining new biosignal data of a first sample size by measuring a biosignal of a user, measured in advance immediately before the new biometric data. Acquiring old biosignal data of a second sample size from a data buffer, generating analysis target data by combining the obtained old biosignal data and the new biosignal data, and the latest generation of the analysis target data 2 extracting biosignal data of a sample size and storing it in the data buffer.

In addition, a description of the biosignal collection method may be included throughout the specification of the present invention, and detailed descriptions will be omitted to prevent redundant descriptions.

4 is an implementation example of a method for collecting biosignals based on parallel processing according to an embodiment of the present invention.

Referring to FIG. 4, an implementation example of collecting a biosignal in a biosignal processing method based on parallel processing according to an embodiment of the present invention can be confirmed.

Specifically, first, a system initialization for collecting a biometric signal may be performed (S200). Here, the system initialization may include initialization of a data buffer, setting a sample size of old biosignal data and new biosignal data, and the like.

Next, after setting the time to measure and collect bio-signals according to the user's input (S210), set the maximum number of repetitions (MAX_ITER) corresponding to the set time, and start measuring and collecting bio-signals (S220) can do. If the variable (Iteration) representing the number of repetitions is 1 (S230), initial N biosignal data may be collected to fill the first data buffer to generate the old biosignal data RAW_DATA_OLD (S240). Next, M+N biosignal data may be collected to generate new biosignal data RAW_DATA_NEW (S250). When the old biosignal data (RAW_DATA_OLD) and the new biosignal data (RAW_DATA_NEW) are generated, a data buffer is created by combining the old biosignal data (RAW_DATA_OLD) and the new biosignal data (RAW_DATA_NEW) (S260), and the created data buffer The old biosignal data RAW_DATA_OLD may be updated by extracting the most recent N samples in step S270. When the data buffer is ready, the flag is set (S280), and the module that processes the signal analysis checks whether the flag is set, starts the analysis of the biosignal stored in the data buffer, and repeats the variable for the number of repetitions (Iteration) is 1 each time it is repeated. It can be increased incrementally (S285).

On the other hand, if the variable for the number of repetitions (Iteration) reaches the previously set maximum number of repetitions (MAX_ITER) (S290), the procedure for measuring/collection of biosignals is terminated, otherwise, new biosignal data is generated. It can be restarted from the process (S250).

5A to 5B are implementation examples of a biosignal processing method based on parallel processing according to an embodiment of the present invention.

Referring to FIGS. 5A to 5B, an implementation example of a biosignal processing method based on parallel processing according to an embodiment of the present invention can be confirmed.

Referring to FIG. 5A, the biosignal collection module (Signal Measurement Module, which may correspond to the signal measurement unit of FIG. 1) is periodically used according to a sampling rate preset by a user. Can be measured and collected. For periodic measurement and collection of bio signals, an interrupt is generated according to a sampling rate and an interrupt service routine (ISR) is executed (S300). The ISR measures and collects one biosignal sample (S310), stores it in new biosignal data (RAW_DATA_NEW), increases the CNT variable (S320), and increases the size (M+N) of the new biosignal data (RAW_DATA_NEW) previously set. You can store it over and over again until it reaches.

When the biosignal sample is stored up to the size (M+N) of the new biosignal data (RAW_DATA_NEW) (S330), the biosignal collection module (Signal Measurement Module) is a signal processing module (Signal Processing Module) in FIG. The flag indicating to start the analysis) is set to 1, the CNT variable is initialized to 0 (S340), and the ISR may be terminated (S350).

On the other hand, when it is confirmed that the flag is set to 1, the Signal Processing Module may perform signal analysis on a data buffer composed of new biosignal data RAW_DATA_NEW and old biosignal data RAW_DATA_OLD (S360). ).

However, at this time, the signal analysis of the signal processing module may be performed during an interval time during which the biosignal collection module measures and collects the biosignal sample through the ISR. That is, as shown in reference numerals 50 and 51 of FIGS. 5A and 5B, the measurement and collection of the biosignal may be processed in parallel with the analysis of the biosignal.

Referring to FIG. 5B, when signal analysis is finished, the signal processing module may store a signal analysis result and set a flag for the previously set analysis start to 0 (S390).

6 is an example implementation of exception processing according to an error occurrence in a biosignal processing method based on parallel processing according to an embodiment of the present invention.

Referring to FIG. 6, in order to process the collection and analysis of the bio-signal in parallel, the exception processing for the case in which the analysis of the bio-signal is not completed or is not completed due to an error while measuring a bio-signal sample through ISR I can.

First, as shown in FIG. 5A, the Signal Measurement Module may repeatedly measure and collect one biological signal sample through ISR (S410). When the collected biosignal sample reaches the predefined size (M+N) of the defined new biosignal data (RAW_DATA_NEW) (S420, CNT is a variable that counts the number of collected samples), signal analysis is complete and It can be checked whether the flag indicating the start of analysis is set to 0 (S430). If the flag instructing the start of analysis is still 1, the analysis of the biosignal (S400) is still in progress, so the exception_flag is set to 1 (S440) and the exception handling module sets the exception handler. It can be executed (S450). The exception handler may perform operations such as system reset, re-performing bio-signal collection and analysis, and data buffer size adjustment according to an actual use example.

7 is a block diagram of a biosignal processing apparatus based on parallel processing according to an embodiment of the present invention.

Referring to FIG. 7, the biosignal processing apparatus 200 based on parallel processing includes at least one processor 210 and instructions instructing the at least one processor to perform at least one step. It may include a memory (memory, 220) to store.

In addition, the biosignal processing apparatus 200 based on parallel processing may include a transceiver 230 that communicates with a base station through a wired or wireless network. In addition, the communication node 200 may further include an input interface device 240, an output interface device 250, and a storage device 260. Each of the components included in the communication node 200 may be connected by a bus 270 to perform communication with each other.

Here, the processor 210 may refer to a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor in which methods according to embodiments of the present invention are performed. Each of the memory 220 and the storage device 260 may be configured with at least one of a volatile storage medium and a nonvolatile storage medium. For example, the memory 220 may be formed of at least one of a read only memory (ROM) and a random access memory (RAM).

Here, the at least one step may include obtaining new biosignal data of a first sample size by measuring a user's biosignal, and storing old biosignal data of a second sample size measured in advance immediately before the new biometric data into a data buffer. Obtaining from, combining the obtained old biosignal data and the new biosignal data to generate analysis target data, extracting the most recent biosignal data of the second sample size from the analysis target data It may include storing in a buffer and analyzing the biometric information for the data to be analyzed, and re-performing from the step of acquiring the new biosignal data in parallel with the analysis.

Here, the first sample size may be set smaller than the second sample size.

The obtaining of the new biosignal data includes transmitting a request message for requesting a biosignal to a wearable device attached to the user, and receiving the biosignal of the user from the wearable device. It may include the step of.

Herein, the user's biosignal may include at least one of blood pressure, body fat percentage, oxygen saturation, heart rate, pulse, electrocardiography (ECG), and photoplethysmography (PPG).

Here, the re-performing may include performing an exception handling for the error when an error occurs during re-execution.

Here, the performing of the exception processing may include re-adjusting the size of the data buffer based on a difference value between a time point when the analysis target data is generated and a time point at which the analysis is completed.

In the step of re-adjusting the size of the data buffer, the size of the data buffer may be readjusted based on the size of the first sample size and the second sample size.

Here, the step of re-adjusting the size of the data buffer may include increasing the first sample size than a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include.

Here, the step of re-adjusting the size of the data buffer may include reducing the second sample size from a currently set value when the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed. Can include.

Examples of the biosignal processing device 200 based on parallel processing, for example, a communication capable desktop computer, a laptop computer, a notebook, a smart phone, and a tablet PC , Mobile phone, smart watch, smart glass, e-book reader, portable multimedia player (PMP), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant) Etc.

The methods according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the computer-readable medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in computer software.

Examples of computer-readable media may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine language codes such as those created by a compiler. The above-described hardware device may be configured to operate as at least one software module to perform the operation of the present invention, and vice versa.

In addition, the above-described method or apparatus may be implemented by combining all or part of its configuration or function, or may be implemented separately.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the following claims. You will understand that you can do it.

Claims (20)

Measuring a user's bio-signal to obtain new bio-signal data of a first sample size;
Acquiring, from a data buffer, old biosignal data of a second sample size measured in advance immediately before the new biometric data;
Generating data to be analyzed by combining the obtained old biosignal data and the new biosignal data;
Extracting the most recent biosignal data of the second sample size from the analysis target data and storing it in the data buffer; And
Analyzing biometric information for the data to be analyzed, and re-performing from the step of acquiring the new biosignal data in parallel with the analysis. In claim 1,
The first sample size is,
The biosignal processing method based on parallel processing, which is set smaller than the second sample size. In claim 1,
Acquiring the new bio-signal data,
Transmitting a request message for requesting a bio-signal to a wearable device attached to the user; And
And receiving a biosignal of the user from the wearable device. In claim 3,
The user's biosignal is,
Blood pressure, body fat percentage, oxygen saturation, heart rate, pulse, electrocardiography (ECG, Electrocardiography), including at least one of photo-volume pulse wave (PPG, Photoplethysmography), parallel processing-based bio-signal processing method. In claim 1,
The re-performing step,
When an error occurs during re-execution, the method of processing biosignals based on parallel processing comprising the step of performing exception handling for the error. In claim 5,
The step of performing the exception processing,
And re-adjusting the size of the data buffer based on a difference value between a time point when the analysis target data is generated and a time point at which the analysis is completed. In claim 6,
Re-adjusting the size of the data buffer,
The biosignal processing method based on parallel processing, wherein the size of the data buffer is readjusted based on the size of the first sample size and the second sample size. In claim 7,
Re-adjusting the size of the data buffer,
When the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed,
And increasing the first sample size from a currently set value. In claim 7,
Re-adjusting the size of the data buffer,
When the time point at which the analysis target data is generated is earlier than a preset threshold value than the time point at which the analysis is completed,
And reducing the second sample size from a currently set value. As a biosignal processing device based on parallel processing,
At least one processor;
Including a memory (memory) for storing instructions (instructions) instructing the at least one processor to perform at least one step,
The at least one step,
Measuring a user's bio-signal to obtain new bio-signal data of a first sample size;
Acquiring, from a data buffer, old biometric signal data of a second sample size measured in advance immediately before the new biometric data;
Generating data to be analyzed by combining the obtained old biosignal data and the new biosignal data;
Extracting the most recent biosignal data of the second sample size from the analysis target data and storing it in the data buffer; And
Analyzing biometric information for the data to be analyzed, and re-performing from the step of acquiring the new biosignal data in parallel with the analysis. delete delete delete delete delete delete delete delete delete delete

Images