JP7819896B2 - Biological information processing system, biological information processing device, biological information processing program, and biological information processing method - Google Patents

Description

The present invention relates to a biometric information processing system, a biometric information processing device, a biometric information processing program, and a biometric information processing method for acquiring a user's biometric information.

In recent years, technology has become widespread that uses wearable devices attached to any part of the user's body to acquire a user's biometric information, such as pulse, blood pressure, body temperature, or heart rate, and then processes and analyzes the acquired biometric information.

Patent Document 1 discloses a technology in which biometric information acquired by a wearable device attached to any part of the user's body is transmitted to an electronic terminal connected to the wearable device, and analysis is performed based on the biometric information.

JP 2015-126804 A

However, with this type of technology, the accuracy of the acquired biometric information can sometimes be reduced due to factors such as different users wearing the wearable device in different ways, the wearable device being displaced from the area where it is worn due to the user's movements, or the presence of pigmentation or wrinkles on the area where it is worn.

If the accuracy of the acquired biometric information decreases, there is a concern that it will become impossible to perform analysis or processing using that biometric information with high accuracy.

The present invention was made in consideration of the above circumstances, and aims to provide a biometric information processing system, a biometric information processing device, a biometric information processing program, and a biometric information processing method that can acquire highly accurate biometric information.

To achieve the above-mentioned objective, the biometric information processing system of the present invention comprises a first biometric information acquisition device that is worn on any part of the user's body to acquire first biometric information of the user; a second biometric information acquisition device that is worn on any part of the user different from the first biometric information acquisition device to acquire second biometric information of the user that is more accurate than the first biometric information; and a biometric information processing device having correction means that compares the second biometric information acquired by the second biometric information acquisition device with the first biometric information acquired by the first biometric information acquisition device and corrects the first biometric information acquired by the first biometric information acquisition device.

This allows the first biometric information acquisition device to acquire highly accurate first biometric information by correcting the first biometric information by matching it with second biometric information that is more accurate than the first biometric information.

This biometric information processing system includes a user terminal that is held by a user and connects the first and second biometric information acquisition devices to the biometric information processing device.

The biometric information processing device of this biometric information processing system has a generation means that generates learned parameters based on the results of correcting the first biometric information by matching the first biometric information acquired by the first biometric information acquisition device with the second biometric information acquired by the second biometric information acquisition device, and a correction means autonomously corrects the first biometric information based on the learned parameters generated by the generation means.

Furthermore, the first biometric information acquisition device of this biometric information processing system has a display unit that displays the time and the first biometric information, and the second biometric information acquisition device has a display unit that displays the acquired second biometric information, and image data captured simultaneously of the time and first biometric information displayed on the display unit of the first biometric information acquisition device worn by the user and the second biometric information displayed on the display unit of the second biometric information acquisition device worn by the user are added to the first biometric information and the second biometric information, respectively.

The first biometric information acquisition device of this biometric information processing system irradiates LED light onto any part of the user's body, receives the reflected LED light, measures the amount of LED light, and acquires the measured amount of light as first biometric information. The second biometric information acquisition device irradiates LED light onto any part of the user's body, receives the LED light that has passed through the part, measures the amount of LED light, and acquires the measured amount of light as second biometric information.

To achieve the above-mentioned objective, the biometric information processing device of the present invention comprises a first biometric information receiving means for receiving first biometric information of a user acquired by a first biometric information acquisition device worn on any part of the user's body, a second biometric information receiving means for receiving second biometric information of the user that is more accurate than the first biometric information acquired by a second biometric information acquisition device worn on any part of the user different from the first biometric information acquisition device, and a correction means for correcting the first biometric information received by the first biometric information receiving means by comparing the second biometric information received by the second biometric information receiving means with the first biometric information received by the first biometric information receiving means.

To achieve the above-mentioned objective, the biometric information processing program of the present invention comprises a first biometric information receiving means for receiving first biometric information of a user acquired by a first biometric information acquisition device worn on any part of the user's body, a second biometric information receiving means for receiving second biometric information of the user that is more accurate than the first biometric information acquired by a second biometric information acquisition device worn on any part of the user different from the first biometric information acquisition device, and a correction means for correcting the first biometric information received by the first biometric information receiving means by comparing the second biometric information received by the second biometric information receiving means with the first biometric information received by the first biometric information receiving means.

To achieve the above-mentioned objective, the biometric information processing method of the present invention comprises a first process of receiving first biometric information of a user acquired by a first biometric information acquisition device worn on any part of the user's body; a second process of receiving second biometric information of the user that is more accurate than the first biometric information acquired by a second biometric information acquisition device worn on any part of the user different from the first biometric information acquisition device; and a third process of correcting the first biometric information by matching the second biometric information received in the second process with the first biometric information received in the first process.

This invention enables the biometric information acquisition device to acquire highly accurate biometric information.

1 is a block diagram illustrating an outline of the configuration of a biological information processing system according to an embodiment of the present invention. 1 is a block diagram illustrating an outline of the configuration of a first biometric information acquisition device of the biometric information processing system according to the present embodiment. FIG. 10 is a block diagram illustrating an outline of the configuration of a second biometric information acquisition device of the biometric information processing system according to the present embodiment. FIG. FIG. 10 is a block diagram illustrating an outline of the configuration of a user terminal of the biological information processing system according to the present embodiment. FIG. 10 is a block diagram illustrating an outline of the configuration of a server in the biological information processing system according to the present embodiment. FIG. 10 is a block diagram illustrating an outline of the configuration of the storage of the server of the biological information processing system according to the present embodiment. 10 is a diagram for explaining an outline of the process of the correction means of the biological information processing system according to the present embodiment. FIG. FIG. 10 is a block diagram for explaining an outline of the processing of the generating means of the biometric information processing system according to the present embodiment. 10 is a diagram for explaining an outline of image data processed by the biometric information processing system according to the present embodiment. FIG. 10 is a flowchart outlining a method for operating the biological information processing system according to the present embodiment.

Next, a biometric information processing system according to an embodiment of the present invention will be described with reference to Figures 1 to 10.

In this embodiment, we will explain an example in which percutaneous arterial oxygen saturation (SpO2) is calculated based on biological information acquired by the biological information processing system.

Figure 1 is a block diagram illustrating the general configuration of a biometric information processing system according to this embodiment. As shown, the biometric information processing system 10 includes a wearable device 20, which is a first biometric information acquisition device, a pulse oximeter 30, which is a second biometric information acquisition device, a user terminal 40, and a server 50, which is a biometric information processing device.

In this embodiment, the wearable device 20, pulse oximeter 30, and user terminal 40 are connected to each other via a network so that they can access each other, and the user terminal 40 and server 50 are connected to each other via a network so that they can access each other.

The wearable device 20 and pulse oximeter 30 are worn on the body of user 1, the user terminal 40 is owned by user 1, and the server 50 is deployed at business operator 2 that provides services using the biometric information processing system 10.

Figure 2 is a block diagram illustrating the general configuration of wearable device 20. Wearable device 20 is a wristwatch-type device worn on any part of the body of user 1, in this embodiment on the wrist of user 1, and as shown in the figure, is primarily composed of a control unit 21, a display 22, a biometric sensor 23, and an acceleration/direction sensor 24.

In this embodiment, the control unit 21 controls each part of the wearable device 20, such as the display 22, which serves as a display unit, the biosensor 23, the acceleration/orientation sensor 24, etc., and is composed of, for example, a processor, memory, storage, a transceiver, etc.

This control unit 21 stores various applications that run on the wearable device 20, and in this embodiment, stores an application that manages the first biometric information D1 (described below) and a time management application that manages the time.

In this embodiment, the display 22 displays the screen interfaces of various applications executed on the wearable device 20, such as an application that manages the first biometric information D1 and a time management application.

This display 22 is a so-called touch panel that accepts information input by touching the display surface, and is implemented using various technologies such as resistive film and capacitive touch.

The biosensor 22 is a sensor that includes an LED that emits LED light toward the wrist of the user 1 and a light receiving unit implemented with a phototransistor that receives the LED light. The LED emits LED light toward the wrist and the light receiving unit receives the reflected LED light.

This biosensor 22 uses the characteristics that infrared light from the LED light is easily absorbed by oxygenated hemoglobin (HbO2), a component of blood, and red light from the LED light is easily absorbed by reduced hemoglobin (Hb), a component of blood, to acquire the amount of LED light that is not absorbed by the blood components but is reflected and received by the light receiving unit as first biometric information D1.

It is anticipated that the first biometric information D1 acquired by the biometric sensor 23 mounted on a wristwatch-type wearable device 20 such as that of this embodiment may have low accuracy or variations in accuracy due to differences in the way the wearable device 20 is worn by each user 1, the wearable device 20 being displaced from its worn position due to the movements of user 1, or wrinkles or pigmentation on the user 1's wrist.

In this embodiment, the acceleration/orientation sensor 24 is a sensor that detects the acceleration of the wearable device 20 when it moves in accordance with the movement of the user 1, the orientation in which the wearable device 20 is facing, etc.

Figure 3 is a block diagram illustrating the general configuration of pulse oximeter 30. Pulse oximeter 30 is a device approved as a medical device on the condition that it is worn on any part of the body of user 1, in this embodiment, by clamping the fingertip of user 1. As shown in the figure, its main components are a control unit 31, a display 32, and a biosensor 33.

In this embodiment, the control unit 31 controls each part of the pulse oximeter 30, such as the display 32 and the biosensor 33, and is composed of, for example, a processor, memory, a transmission/reception interface, etc.

The display 32 is, for example, a liquid crystal display implemented using a liquid crystal panel, and in this embodiment, the second biometric information D2 is displayed as numerical data.

The biosensor 33 is a sensor that includes an LED that emits LED light toward the fingertip of the user 1 and a light-receiving unit implemented with a phototransistor that receives the LED light. The LED emits LED light toward the fingertip and the light-receiving unit receives the transmitted LED light.

This biosensor 33 uses the characteristics that infrared light from the LED light is easily absorbed by oxygenated hemoglobin (HbO2), a component of blood, and red light from the LED light is easily absorbed by reduced hemoglobin (Hb), a component of blood, to obtain the amount of LED light that is not absorbed by the blood components but is transmitted and received by the light receiving unit as second biometric information D2.

The second biometric information D2 acquired by the biometric sensor 33 mounted on the pulse oximeter 30 that holds the fingertip as in this embodiment is expected to be more accurate than the first biometric information D1 acquired by the wearable device 20, since the method of wearing the pulse oximeter 30 does not vary significantly between users 1, the wearing position does not shift due to fingertip movements, and there are almost no wrinkles or pigmentation on the fingertips.

Figure 4 is a block diagram illustrating the general configuration of the user terminal 40. In this embodiment, the user terminal 40 is a portable information terminal such as a smartphone or tablet computer, and as shown in the figure, is primarily composed of a control unit 41, a display 42, and a camera 43.

In this embodiment, the control unit 41 controls each part of the user terminal 40, such as the display 42 and camera 43, and is composed of, for example, a processor, memory, storage, a transceiver, etc.

This control unit 21 stores various applications that run on the user terminal 40, and in this embodiment, stores applications that manage the first biometric information D1 and the second biometric information D2, etc.

In this embodiment, the display 42 displays the screen interface of an application executed on the user terminal 40, such as an application that manages the first biometric information D1 and the second biometric information D2.

This display 42 is a so-called touch panel that accepts information input by touching the display surface, and is implemented using various technologies such as resistive film and capacitive touch.

The camera 43 is an imaging means that captures images or videos of any object, and in this embodiment, it captures an image of the hand of the user 1 wearing the wearable device 20 and pulse oximeter 30.

Figure 5 is a block diagram illustrating the general configuration of server 50.

As shown in the figure, the server 50 mainly comprises a processor 51, memory 52, storage 53, a transceiver 54, and an input/output unit 55, which are electrically connected to each other via a bus 56.

The processor 51 is a computing device that controls the operation of the server 50, controls the sending and receiving of data between each element, and performs processing necessary to execute application programs.

In this embodiment, this processor 51 is, for example, a CPU (Central Processing Unit), and executes application programs stored in storage 53 (described below) and deployed in memory 52 to perform various processes.

Memory 52 is implemented as a main memory device consisting of a volatile memory device such as DRAM (Dynamic Random Access Memory).

This memory 52 is used as a working area for the processor 51, and also stores the BIOS (Basic Input/Output System) that runs when the server 50 starts up, as well as various setting information.

Storage 53 stores application programs and data used for various processes.

The transmission/reception unit 54 connects the server 50 to a network, and in this embodiment, it is connected to the user terminal 40 via the network via the transmission/reception unit 54 so that they can communicate with each other.

This transceiver unit 54 may be equipped with a short-range communication interface such as Bluetooth (registered trademark) or BLE (Bluetooth Low Energy).

If necessary, information input devices such as a keyboard and mouse, and output devices such as a display, are connected to the input/output unit 55. In this embodiment, a keyboard, mouse, and display are connected.

The bus 56 transmits, for example, address signals, data signals, and various control signals between the connected processor 51, memory 52, storage 53, transceiver unit 54, and input/output unit 55.

Figure 6 is a block diagram illustrating the general configuration of the storage 53 of the server 50. As shown, the storage 53 includes a biometric information processing program 60, a first storage area 61, and a second storage area 62.

The biological information processing program 60 is a program that processes the first biological information D1 acquired by the wearable device 20 and the second biological information D2 acquired by the pulse oximeter 30, and is implemented by a screen interface that allows the server 50 to input and output information.

In this embodiment, this biometric information processing program 60 includes a first biometric information receiving unit 60a, which is a first biometric information receiving means, a second biometric information receiving unit 60b, which is a second biometric information receiving means, a correction unit 60c, which is a correction means, a generation unit 60d, which is a generation means, and an information processing unit 60e.

In this embodiment, the first biological information receiving unit 60a is a module that receives first biological information D1 acquired by the wearable device 20, and the second biological information receiving unit 60b is a module that receives second biological information D2 acquired by the pulse oximeter 30.

In this embodiment, the correction unit 60c is a module that compares the first biometric information D1 with the second biometric information D2 and corrects the first biometric information D1 based on the comparison results.

Figure 7 is a diagram outlining the processing performed by the correction unit 60c. As shown in the figure, the correction unit 60c compares the amount of light captured as the first biometric information D1 with the amount of light captured as the second biometric information D2 to determine the difference, and then corrects the first biometric information D1 based on that difference, using the second biometric information D2 as a reference.

Furthermore, the correction unit 60c autonomously corrects the first biometric information D1 based on the learned parameters generated by the generation unit 60d, which will be described next.

Specifically, the generated learned parameters are compared with the acquired first biometric information D1, the actual light intensity (true value) ascertained from the acquired first biometric information D1 is estimated, and the first biometric information D1 is autonomously corrected to match the estimated true value.

In this embodiment, the generation unit 60d shown in FIG. 6 is a module that generates learned parameters based on the results of the correction unit 60c comparing the first biometric information D1 with the second biometric information D2 and correcting the first biometric information D1.

Figure 8 is a block diagram outlining the processing of the generation unit 60d. As shown in the figure, the generation unit 60d uses the first biometric information D1 as learning data and the second biometric information D2 as training data, compares the first biometric information D1 with the second biometric information D2, corrects the first biometric information D1, and performs machine learning on the results to generate a learned parameter P.

Furthermore, in this embodiment, when image data D3 described below is added to the first biometric information D1, the generation unit 60d also uses the image data D3 added to the first biometric information D1 as learning data, and when image data D3 is added to the second biometric information D2, the generation unit 60d also uses the image data D3 added to the second biometric information D2 as training data to generate the learned parameter P.

Various algorithms, such as neural networks, random forests, and SVMs (Support Vector Machines), are used as appropriate for machine learning techniques.

In this embodiment, the information processing unit 60e shown in Figure 6 is a module that executes various processes executed by the biometric information processing program 60.

In this embodiment, image data D3 is added to the first biometric information D1 and the second biometric information D2 via user 1's user terminal 40, so that the image data D3 added to the first biometric information D1 constitutes learning data together with the first biometric information D1, and the image data D3 added to the second biometric information D2 constitutes training data together with the second biometric information D2.

Figure 9 is a diagram illustrating an overview of image data D3. As shown in the figure, image data D3 is data obtained by simultaneously capturing the time and first biological information D displayed on the display 22 of the wearable device 20 worn by user 1, and second biological information D2 displayed on the display 32 of the pulse oximeter 30 worn by user 1.

In this embodiment, this image data D3 is captured and acquired by the camera 43 of the user terminal 40 and transmitted to the server 50. The image data D3 transmitted to the server 50 is added to the first biometric information D1 and the second biometric information D2 by the information processing unit 60e.

In this embodiment, the first storage area 61 and second storage area 62 shown in Figure 6 are realized by the storage area of storage 53.

The first storage area 61 stores the first biometric information D1 and the second biometric information D2, and the second storage area 62 stores the learned parameters P.

Next, we will explain how to operate the biometric information processing system 10.

Figure 10 is a flowchart outlining the operation method of the biometric information processing system 10. First, the user 1 wears the wearable device 20 and the pulse oximeter 30 on predetermined body parts.

Next, as shown in the figure, in step S1, the wearable device 20 acquires first biometric information D1. The acquired first biometric information D1 is transmitted to the server 50 via the user terminal 40 and received by the first biometric information receiving unit 60a of the biometric information processing program 60 of the server 20 (first process).

Meanwhile, in step S2, around the same time as step S1, the pulse oximeter 30 acquires second biological information D2. The acquired second biological information D2 is transmitted to the server 50 via the user terminal 40 and received by the second biological information receiving unit 60b of the biological information processing program 60 of the server 20 (second processing).

At this time, in this embodiment, the user 1 simultaneously captures the time and first biological information D displayed on the display 22 of the wearable device 20 and the second biological information D2 displayed on the display 32 of the pulse oximeter 30, and obtains image data D3.

The acquired image data D3 is sent to the server 50 via the user terminal 40 and added to the first biometric information D1 and the second biometric information D2, respectively.

Furthermore, in step S3, the first biometric information D1 and the second biometric information D2 are compared, and the first biometric information D1 is corrected (third process).

Then, in step S4, the first biometric information D1 is used as learning data, the second biometric information D2 is used as training data, and machine learning is performed on the results of comparing the first biometric information D1 and the second biometric information D2 and correcting the first biometric information D1.

Since machine learning requires a relatively large amount of first biometric information D1, it may take a long time to acquire a sufficient amount of first biometric information D1 to complete the machine learning.

On the other hand, as the acquisition of first biometric information D1 progresses over a long period of time, the first biometric information D1 is accumulated and machine learning progresses, and the previously acquired and accumulated first biometric information D1 is used as new learning data for machine learning, thereby improving the accuracy of learning.

In the following step S5, a sufficient amount of first biometric information D1 is acquired to complete the machine learning and generate learned parameters P. In step S6, the first biometric information D1 is corrected using the learned parameters P.

The wearable device 20 calculates the percutaneous arterial oxygen saturation (SpO2) based on the corrected first biological information D1.

On the other hand, in step S5, if machine learning is not yet complete and the learned parameter P has not yet been generated, the first biometric information D1 is corrected by comparing the first biometric information D1 with the second biometric information D2, and machine learning is continued on the corrected result.

In this way, by comparing the first biometric information D1 with the second biometric information D2, which is more accurate than the first biometric information D1, and correcting the first biometric information D1, it is possible to obtain highly accurate first biometric information D1 in the wearable device 20.

In particular, in this embodiment, highly accurate first biometric information D1 can be obtained using a wristwatch-type wearable device 20 that is expected to be worn at all times during the day, thereby improving convenience for user 1.

Furthermore, in this embodiment, learned parameters P are generated by machine learning, and the first biometric information D1 is autonomously corrected based on the learned parameters P, further improving the accuracy of the first biometric information D1.

If the accuracy of the first biological information D1 can be improved by correction based on the learned parameter P, the convenience for user 1 will be further improved, as there will be no need to wear a pulse oximeter 30 and compare the first biological information D1 with the second biological information D2.

The present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the spirit of the invention.

In the above embodiment, the wearable device 20 and pulse oximeter 30 are connected to a user terminal 40 that is connected to a server 50. However, the wearable device 20 and pulse oximeter 30 may also be configured to be connected to the server 50 without the intervention of the user terminal 40.

In the above embodiment, the first biometric information acquisition device was described as a wristwatch-type wearable device 20, but various other devices, such as eyeglass-type wearable devices, may be used as long as they can be worn on any part of the user 1's body.

In the above embodiment, we have described a case where percutaneous arterial blood oxygen saturation is calculated based on first biological information D1 or second biological information D2, but various types of biological information, such as respiratory rate and heart rate, may also be acquired as first biological information D1 and second biological information D2.

In this case, any device can be used as the second biometric information acquisition device depending on the second biometric information D2 to be acquired. For example, if heart rate is to be acquired as the second biometric information D2, it is preferable that the second biometric information acquisition device be a heart rate monitor.

In the above embodiment, the second biological information acquisition device was described as a pulse oximeter 30 having a biological sensor 33 that emits LED light. However, in addition to the pulse oximeter 30, any second biological information acquisition device equipped with a biological sensor that acquires second biological information D2 using electrodes, for example, can also be used.

In this way, by acquiring the second biometric information D2 using multiple different biometric sensors, the accuracy of correction of the first biometric information D1 can be improved.

In the above embodiment, the server 50 is deployed at the business operator 2, but the server 50 may also be implemented in a cloud environment.

1 User 2 Business 10 Biometric information processing system 20 Wearable device (first biological information acquisition device)
22 Display (display unit)
23 Biometric sensor 30 Pulse oximeter (second biological information acquisition device)
32 Display (display unit)
33 Biometric sensor 40 User terminal 50 Server (biometric information processing device)
60 Biometric information processing program 60a First biological information receiving unit (first biological information receiving means)
60b Second biological information receiving unit (second biological information receiving means)
60c Correction section (correction means)
60d Generation unit (generation means)
D1 First biometric information D2 Second biometric information D3 Image data P Learned parameters

Claims (6)

a first biometric information acquisition device that is worn on an arbitrary part of a user's body to acquire first biometric information of the user and has a display unit that displays the acquired first biometric information and a time;
a second biometric information acquisition device that is worn on an arbitrary part of the user different from the first biometric information acquisition device, acquires second biometric information of the user that is more accurate than the first biometric information, and has a display unit that displays the acquired second biometric information;
a biometric information processing device including a correction means for correcting the first biometric information acquired by the first biometric information acquisition device by comparing the second biometric information acquired by the second biometric information acquisition device with the first biometric information acquired by the first biometric information acquisition device, and a generation means for generating learned parameters based on a result of correction by the correction means;
a user terminal that is held by the user and connects the first biometric information acquisition device and the second biometric information acquisition device to the biometric information processing device, and image data that is simultaneously captured of the time and the first biometric information displayed on the display unit of the first biometric information acquisition device worn by the user and the second biometric information displayed on the display unit of the second biometric information acquisition device worn by the user is added to the first biometric information and the second biometric information, respectively, by the biometric information processing device;
The image data added to the first biometric information constitutes learning data together with the first biometric information, and the image data added to the second biometric information constitutes teacher data together with the second biometric information,
the first biometric information of the image data included in the learning data and the time at which the first biometric information was acquired are compared with the second biometric information of the image data included in the teacher data at that time, and machine learning is performed assuming that the first biometric information at that time is the second biometric information, thereby generating the learned parameters;
Biometric information processing system. The biometric information processing device includes:
the correction means autonomously corrects the first biological information based on the learned parameters generated by the generation means.
The biological information processing system according to claim 1 . the first biological information acquisition device,
irradiating an LED light onto the arbitrary part of the user and receiving the reflected LED light to measure the amount of the LED light, and acquiring the measured amount of light as the first biological information;
the second biological information acquisition device,
irradiating an arbitrary part of the user with LED light and receiving the LED light that has passed through the part to measure the amount of light of the LED light, and acquiring the measured amount of light as the second biological information;
The biological information processing system according to claim 1 or 2. a first biometric information receiving means for receiving the first biometric information of the user acquired by a first biometric information acquisition device that is worn on an arbitrary part of the user's body and has a display unit that displays the acquired first biometric information and a time;
a second biometric information receiving means for receiving the second biometric information of the user, the second biometric information being attached to an arbitrary part of the user different from the first biometric information acquiring device, the second biometric information acquiring means having a display unit for displaying the acquired second biometric information, and the second biometric information being acquired by the second biometric information acquiring means having a display unit for displaying the acquired second biometric information;
a correction means for correcting the first biometric information received by the first biometric information receiving means by comparing the second biometric information received by the second biometric information receiving means with the first biometric information received by the first biometric information receiving means, and a generation means for generating learned parameters based on a result of the correction by the correction means,
a user terminal that is held by the user and connects the first biometric information acquisition device and the second biometric information acquisition device adds, to the first biometric information and the second biometric information, respectively, the time displayed on the display unit of the first biometric information acquisition device worn by the user and image data obtained by simultaneously capturing the first biometric information and the second biometric information displayed on the display unit of the second biometric information acquisition device worn by the user;
The image data added to the first biometric information constitutes learning data together with the first biometric information, and the image data added to the second biometric information constitutes teacher data together with the second biometric information.
the first biometric information of the image data included in the learning data and the time at which the first biometric information was acquired are compared with the second biometric information of the image data included in the teacher data at that time, and machine learning is performed assuming that the first biometric information at that time is the second biometric information, thereby generating the learned parameters;
Biometric information processing device. A biometric information processing device
a first biometric information receiving means for receiving the first biometric information of the user acquired by a first biometric information acquisition device that is worn on an arbitrary part of the user's body and has a display unit that displays the acquired first biometric information and a time;
a second biometric information receiving means for receiving the second biometric information of the user, the second biometric information being attached to an arbitrary part of the user different from the first biometric information acquiring device, the second biometric information acquiring means having a display unit for displaying the acquired second biometric information, and the second biometric information being acquired by the second biometric information acquiring means having a display unit for displaying the acquired second biometric information;
a correction means for correcting the first biometric information received by the first biometric information receiving means by comparing the second biometric information received by the second biometric information receiving means with the first biometric information received by the first biometric information receiving means, and a generation means for generating learned parameters based on the correction result by the correction means;
a user terminal that is held by the user and connects the first biometric information acquisition device and the second biometric information acquisition device to the biometric information processing device, and image data that is simultaneously captured of the time and the first biometric information displayed on the display unit of the first biometric information acquisition device worn by the user and the second biometric information displayed on the display unit of the second biometric information acquisition device worn by the user is added to the first biometric information and the second biometric information, respectively, by the biometric information processing device;
The image data added to the first biometric information constitutes learning data together with the first biometric information, and the image data added to the second biometric information constitutes teacher data together with the second biometric information,
the first biometric information of the image data included in the learning data and the time at which the first biometric information was acquired are compared with the second biometric information of the image data included in the teacher data at that time, and machine learning is performed assuming that the first biometric information at that time is the second biometric information, thereby generating the learned parameters;
Biometric information processing program. A biometric information processing device
a first process of receiving the first biometric information of the user acquired by a first biometric information acquisition device that is worn on an arbitrary part of the user's body and has a display unit that displays the acquired first biometric information and a time;
a second process of receiving the second biometric information of the user, the second biometric information being attached to an arbitrary part of the user different from the first biometric information acquisition device, the second biometric information being acquired by a second biometric information acquisition device having a display unit on which the acquired second biometric information is displayed, the second biometric information being acquired by a second biometric information acquisition device having a display unit on which the acquired second biometric information is displayed;
a third process of correcting the first biometric information by comparing the second biometric information received in the second process with the first biometric information received in the first process;
generating means for generating a learned parameter based on the result of the correction in the third process;
a user terminal that is held by the user and connects the first biometric information acquisition device and the second biometric information acquisition device to the biometric information processing device, and image data that is simultaneously captured of the time and the first biometric information displayed on the display unit of the first biometric information acquisition device worn by the user and the second biometric information displayed on the display unit of the second biometric information acquisition device worn by the user is added to the first biometric information and the second biometric information, respectively, by the biometric information processing device;
The image data added to the first biometric information constitutes learning data together with the first biometric information, and the image data added to the second biometric information constitutes teacher data together with the second biometric information,
the first biometric information of the image data included in the learning data and the time at which the first biometric information was acquired are compared with the second biometric information of the image data included in the teacher data at that time, and machine learning is performed assuming that the first biometric information at that time is the second biometric information, thereby generating the learned parameters;
Biometric information processing method.