JP2022157470A - Learning device, estimation device, learning method, estimation method, and computer program - Google Patents

Abstract

To estimate information on a human cognitive ability more accurately while suppressing a load on an estimation object person.SOLUTION: A learning device includes: a learning data generation unit for generating learning data by dividing biological information into a plurality of sections according to time of sleep and wake-up on teacher data having unit teacher data that associates biological information related to the sleep of a person with information on the cognitive ability of that person for a plurality of persons; a learning unit for acquiring a learned model for outputting information on the cognitive ability of the estimation object person by inputting information on the biological information on the estimation object person by executing learning processing using the learning data; and an output control unit for outputting data on the learned model.SELECTED DRAWING: Figure 1

Description

The present invention relates to technology for estimating information about human cognitive ability.

In recent years, with the aging of society as a whole, suppression of deterioration in cognitive ability has become a social issue. In order to suppress the deterioration of cognitive ability, it is important to discover the tendency of deterioration of cognitive ability as early as possible. Therefore, techniques have been proposed for estimating whether or not a subject has dementia by performing learning processing (see, for example, Patent Literature 1).

JP 2020-149234 A

However, in the prior art, in order to perform accurate estimation, it was necessary to attach sensors such as a monitoring device to the user's body. However, having to consciously wear sensors such as a monitoring device may impose a mental and physical burden on the user. In addition, there were cases where the estimation could not be performed correctly due to forgetting to attach the sensors. On the other hand, if a simpler sensor were used, there was a problem that the accuracy of estimation would be greatly reduced in the first place.

In view of the above circumstances, an object of the present invention is to provide a technology capable of estimating information on human cognitive ability with higher accuracy while reducing the burden on the subject of estimation.

According to one aspect of the present invention, for teacher data having unit teacher data relating to a plurality of people in which biometric information related to sleep of a person and information related to cognitive ability of the person are associated, and a learning data generation unit that generates learning data by dividing into a plurality of intervals according to bedtime, and by performing learning processing using the learning data, inputting information related to the biometric information of the subject to be estimated. and an output control unit for outputting data of the learned model.

An aspect of the present invention is the learning device described above, wherein the plurality of sections are sections determined based on biometric information obtained from the estimation target person.

According to one aspect of the present invention, an estimation process is performed using an information acquisition unit that acquires biometric information of an estimation target, a trained model generated by the learning device, and the biometric information of the estimation target. and an estimating device.

According to one aspect of the present invention, for teacher data having unit teacher data relating to a plurality of people in which biometric information related to sleep of a person and information related to cognitive ability of the person are associated, Information about the biometric information of the subject to be estimated is input by performing a learning data generation step of generating learning data by dividing into a plurality of intervals according to the bed time and the learning data, and performing a learning process using the learning data. and a learning step of acquiring a trained model that outputs information about the cognitive ability of the person to be estimated, and an output control step of outputting data of the trained model.

An aspect of the present invention performs an estimation process using an information acquisition step of acquiring biometric information of an estimation target, a trained model generated by the learning device, and the biometric information of the estimation target. and an estimation step.

One aspect of the present invention is a computer program for causing a computer to function as the learning device.

One aspect of the present invention is a computer program for causing a computer to function as the above estimation device.

ADVANTAGE OF THE INVENTION By this invention, it becomes possible to estimate the information regarding a person's cognitive ability with higher precision, suppressing the burden on the subject of an estimation.

1 is a schematic block diagram showing the system configuration of an estimation system 100 of the present invention; FIG. 1 is a schematic block diagram showing the functional configuration of a learning device 10 of the present invention; FIG. FIG. 10 is a diagram showing a specific example of how to divide a unified fixed type; FIG. 10 is a diagram showing a specific example of how to divide individual fixed type. It is a figure which shows the specific example of how to divide a flow type|mold. 3 is a schematic block diagram showing the functional configuration of an estimating device 30 of the present invention; FIG. 4 is a flowchart showing a specific example of the flow of processing of the learning device 10; 4 is a flow chart showing a specific example of the flow of processing of the estimation device 30. FIG.

Hereinafter, specific configuration examples of the present invention will be described with reference to the drawings.
FIG. 1 is a schematic block diagram showing the system configuration of an estimation system 100 of the present invention. The estimation system 100 is a system for estimating information (hereinafter referred to as "cognitive information") regarding the cognitive ability of a user (estimation target). The estimation system 100 includes an information acquisition device 20 , an estimation device 30 and a user terminal 40 . The estimation system 100 may use a trained model generated by learning processing by the learning device 10 . The estimation device 30 and the user terminal 40 are communicably connected via a network 90 . Information acquisition device 20 communicates with estimation device 30 via network 90 . For example, the information acquisition device 20 may be directly connected to the network 90 using a communication device provided in the device itself, or may communicate with the user terminal 40 to connect to the network via the user terminal 40. 90 may be connected. The network 90 may be a network using wireless communication or a network using wired communication. Network 90 may be configured by combining a plurality of networks.

The learning device 10 executes learning processing based on information obtained in advance to generate a trained model. The trained model generated by learning device 10 is used by estimating device 30 . The information acquisition device 20 acquires the user's biometric information and transmits it to the estimation device 30 via the network 90 . The estimation device 30 estimates information about the user's cognitive ability based on the biometric information received from the information acquisition device 20 . The estimation device 30 outputs information about the estimation result to an information processing device such as the user terminal 40 . The user terminal 40 is a terminal device used by a person (hereinafter referred to as “user”) who uses the information acquisition device 20 to transmit his/her biological information to the estimation device 30 .

FIG. 2 is a schematic block diagram showing the functional configuration of the learning device 10 of the present invention. The learning device 10 performs learning processing using teacher data including biometric information obtained from a plurality of persons. The learning device 10 generates a trained model for estimating information (cognitive information) about the cognitive ability of the estimation subject by executing the learning process. The learning device 10 is configured using an information processing device such as a personal computer or a server device. The learning device 10 includes an input unit 11 , an output unit 12 , a storage unit 13 and a control unit 14 .

The input unit 11 inputs teacher data to the learning device 10 . The input unit 11 may read teacher data recorded in a recording medium such as a CD-ROM or USB memory (Universal Serial Bus Memory) from the recording medium. Also, the input unit 11 may receive teacher data from another device via a network. The input unit 11 may be configured in a different manner as long as it is configured to receive input of teacher data.

The teacher data includes a plurality of unit teacher data obtained from individual persons. That is, the teacher data includes unit teacher data obtained by a plurality of persons. The unit training data consists of values of multiple data items and information on the cognitive ability of the person from whom the value of the data item was obtained (for example, classification as to whether it belongs to "healthy", "MCI", or "dementia"). (information indicating ) and information in association with each other. At least one of the data items included in the unit teaching data indicates information about a living body (hereinafter referred to as "biological information"). It is desirable that information regarding each person's cognitive ability be obtained based on the judgment of a physician.

A specific example of the data item of the biological information is information about sleep (hereinafter referred to as "sleep information"). The sleep information may be any information as long as it relates to sleep. For example, biological information in a period from going to bed to waking up (hereinafter referred to as "bedtime period") may be used as sleep information. More specifically, the sum of sleep time from going to bed to waking up, the number of awakenings from going to bed to waking up (hereinafter referred to as "mid-awakening"), each time of mid-awakening, total time of mid-awakening, Time-series information of heartbeat during sleep, time-series information of breathing frequency during sleep, time-series information of blood pressure during sleep, information on body movement during sleep, breathing interruption (number, time, interval) during sleep Specific examples of sleep information include time-series information.

Not limited to sleep information, biometric information (breathing rate, heart rate, brain waves, etc.) acquired during the period when the user is active, activity information (action history [eating, drinking, toileting, bathing, going out, etc.], location information, etc.) ) may be used as biometric information. Biometric information may be acquired by any means. For example, biometric information may be generated using a device such as a sensor that acquires sleep information from a person.

The output unit 12 outputs information from the learning device 10 to the outside. The output unit 12 may record data of the learned model on a recording medium such as a CD-ROM or USB memory. Also, the output unit 12 may transmit data of the learned model to another device via the network. The output unit 12 may be configured in a different manner as long as it is configured to output the data of the trained model.

The storage unit 13 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 13 stores data used by the control unit 14 and data generated by the control unit 14 . For example, the storage unit 13 may function as a teacher data storage unit 131 , a learning data storage unit 132 and a learned model storage unit 133 .

The teacher data storage unit 131 stores teacher data input from the input unit 11 . The learning data storage unit 132 stores learning data generated based on teacher data by processing of the control unit 14 . Learning data is data containing a plurality of feature values used in learning processing. The feature amount may be obtained, for example, as statistical values of teacher data. The learned model storage unit 133 stores data of a learned model obtained by learning processing using learning data.

The control unit 14 is configured using a processor such as a CPU (Central Processing Unit) and a memory. The control unit 14 functions as an information acquisition unit 141, a learning data generation unit 142, a learning unit 143, and an output control unit 144 by the processor executing programs. All or part of each function of the control unit 14 may be implemented using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, semiconductor storage devices (such as SSD: Solid State Drives), hard disks and semiconductor storage built into computer systems. It is a storage device such as a device. The above program may be transmitted via telecommunication lines.

The information acquisition unit 141 acquires teacher data via the input unit 11 . The information acquisition unit 141 records the acquired teacher data in the teacher data storage unit 131 .

The learning data generation unit 142 generates learning data having a plurality of feature amounts by performing predetermined processing on the teacher data recorded in the teacher data storage unit 131 . The learning data generation unit 142 records the generated learning data in the learning data storage unit 132 .

The learning data generation unit 142, for example, acquires statistical values for time-series values of biometric data obtained as each unit teacher data, and generates learning data by using the acquired statistical values as feature amounts. good too. Examples of such statistics include values such as mean, standard deviation, variance, minimum, maximum, first quartile, third quartile, and interquartile range. For example, the learning data generation unit 142 may divide the sleep information into a plurality of intervals according to sleep and bedtime, and obtain statistical values for each interval. Several specific examples of how to divide the time series of sleep information into a plurality of sections (hereinafter referred to as "section division processing") will be described.

For example, there are "unified fixed type", "individual fixed type", and "fluid type" in how to divide sleep information. In the following description, the sleeping period will be described as an example of sleep information to be segmented. 3 to 5 are diagrams showing the concept of specific examples of how to divide the bedtime. In FIGS. 3 to 5, the horizontal axes of (A) to (C) indicate time, and "going to bed" and "waking up" defined on each of the horizontal axes indicate the bedtime of users A to C. It shows the time and wake-up time. 3 to 5, each section dividing the bedtime period has the same length, but each section may be defined to have a different length. 3 to 5, the number of sections dividing the bed period is four, but the number may be three or less or five or more.

FIG. 3 is a diagram showing a specific example of the uniform fixed type segmentation method. In the unified fixed type, multiple intervals dividing the sleeping time are applied to all users in a predetermined group that includes multiple users (for example, users nationwide, all users at a certain facility, etc.) Commonly fixedly determined. For example, in the example shown in FIG. 3, it is defined that sleep time is evenly divided into four intervals. That is, the start time and end time of each of the four sections (first section to fourth section) are fixed and common to all users. Therefore, in reality, the bedtime and the start time of the first section (first section) do not always match, and the wake-up time and the end time of the last section (fourth section) do not always match. However, in the unified fixed type, the deviation may be appropriately adjusted according to a predetermined rule. For example, if the bedtime is later than the start time of the first section, the section may be determined by replacing the start time of the section in which the bedtime is located with the bedtime. For example, if the wake-up time is earlier than the end time of the fourth segment, the segment may be determined by replacing the end time of the segment in which the wake-up time is located with the wake-up time.

FIG. 4 is a diagram showing a specific example of the individual-fixed division method. In the individual fixed type, a plurality of intervals for dividing sleep time are independently and fixedly determined for each user. For example, in the example shown in FIG. 4, it is defined that the sleep time is evenly divided into four intervals for each user. That is, the start time and end time of each of the four sections (first section to fourth section) are fixedly determined for each individual. The start time and end time of each section in the individual fixed type may be determined, for example, based on sleep information (for example, sleep period) of the user during a predetermined period. For example, a statistical value of the bedtime actually acquired for the user during a predetermined period (for example, for a predetermined number of days after starting to use the information acquisition device 20, for a predetermined number of days including the previous day, etc.) Each individual-fixed section may be determined using the statistical value of time. Even with the individual fixed type, the bedtime and the start time of the first section (first section) do not always match, and the wake-up time and the end time of the last section (fourth section) do not always match. do not have. However, even in the individual fixed type, the value may be appropriately adjusted according to a predetermined rule for this deviation. For example, if the bedtime is later than the start time of the first section, the section may be determined by replacing the start time of the section in which the bedtime is located with the bedtime. For example, if the wake-up time is earlier than the end time of the fourth segment, the segment may be determined by replacing the end time of the segment in which the wake-up time is located with the wake-up time.

FIG. 5 is a diagram showing a specific example of how to divide the flow type. In the fluid type, a plurality of intervals dividing the sleep time are determined according to the sleep time to be processed each time. For example, in the example shown in FIG. 5, it is defined that the sleep time is evenly divided into four intervals, but the start time and end time of each interval are not predetermined. In the fluid type, the bedtime in the sleep period that is actually the target of segmentation is defined as the start time of the first segment (first segment), and the wake-up time is defined as the end time of the last segment (fourth segment). be.

The learning unit 143 uses learning data generated by the learning data generation unit 142 (including learning data recorded in the learning data storage unit 132) to execute learning processing according to a predetermined learning model. A learning model used by the learning unit 143 is determined in advance. The learning model used by the learning unit 143 may be, for example, a decision tree, a support vector machine, or other algorithms. By the learning unit 143 performing the learning process, the input data obtained by performing the same process as the learning data generation process performed by the learning data generation unit 142 is used to obtain the input data. A trained model is generated for estimating information about the person's cognitive abilities. The learning unit 143 records the generated trained model in the trained model storage unit 133 .

The output control unit 144 outputs the learned model generated by the learning unit 143 (including the learned model stored in the learned model storage unit 133 ) through the output unit 12 . The trained model output by the output control unit 144 is used by the estimation device 30, which will be described later.

The information acquisition device 20 is configured using one or more sensors and a communication device. A sensor of the information acquisition device 20 acquires the user's biometric information. A specific example of the acquired biometric information is information about sleep of the user (sleep information). The information acquisition device 20 transmits the acquired biological information as estimation target data to the estimation device 30 via the network 90 .

FIG. 6 is a schematic block diagram showing the functional configuration of the estimation device 30 of the present invention. The estimation device 30 performs estimation processing using estimation target data including biometric information obtained from an estimation target person. The estimating device 30 estimates information (cognitive information) about the cognitive ability of the person to be presumed by executing the estimating process. The estimation device 30 is configured using an information processing device such as a personal computer or a server device. The estimation device 30 includes an input unit 31 , an output unit 32 , a storage unit 33 and a control unit 34 .

The input unit 31 inputs the estimation target data to the estimation device 30 . The input unit 31 may read the estimation target data recorded in a recording medium such as a CD-ROM or a USB memory from the recording medium. Also, the input unit 31 may be configured as a communication device that receives estimation target data from another device (for example, the information acquisition device 20 ) via the network 90 . The input unit 31 may be configured in a different manner as long as it is configured to receive input of estimation target data.

The estimation target data has values of data items similar to the teacher data used in the learning data. When the estimation target data includes sleep information, for example, the estimation target data may be configured using data obtained during sleep of the estimation target by the information acquisition device 20 used by the estimation target.

The output unit 32 outputs information from the estimation device 30 to the outside. The output unit 32 may record data indicating the estimation result on a recording medium such as a CD-ROM or a USB memory. Also, the output unit 32 may transmit data indicating the estimation result to another device (for example, the user terminal 40) via the network 90. FIG. The output unit 32 may be configured in a different manner as long as it is configured to output data indicating the estimation result.

The storage unit 33 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 33 stores data used by the control unit 34 and data generated by the control unit 34 . For example, the storage unit 33 may function as a trained model storage unit 331 , an estimation target data storage unit 332 , an estimated data storage unit 333 and an estimation result data storage unit 334 .

The trained model storage unit 331 stores data of trained models. The learned model data is, for example, the learned model data generated by the learning device 10 . The learned model data may be recorded in advance in the learned model storage unit 331 or may be input from the input unit 31 . The estimation target data storage unit 332 stores the estimation target data input from the input unit 31 . The estimated data storage unit 333 stores estimated data generated based on the estimation target data by the processing of the control unit 34 . Estimation data is data containing a plurality of feature values used in estimation processing. The feature amount included in the estimated data is obtained by subjecting the estimation target data to the same processing as the feature amount used for the learning data in the learning device 10 . The estimation result data storage unit 334 stores data indicating estimation results obtained by estimation processing using estimation data.

The control unit 34 is configured using a processor such as a CPU and a memory. The control unit 34 functions as an information acquiring unit 341, an estimated data generating unit 342, an estimating unit 343, and an output control unit 344 by the processor executing programs. All or part of each function of the control unit 34 may be realized using hardware such as ASIC, PLD, FPGA, or the like. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, semiconductor storage devices (such as SSD), and storage devices such as hard disks and semiconductor storage devices built into computer systems. It is a device. The above program may be transmitted via telecommunication lines.

The information acquisition unit 341 acquires estimation target data via the input unit 31 . For example, the information acquisition unit 341 may acquire the estimation target data by receiving the biometric information (including sleep information) of the estimation target person from the information acquisition device 20 via the input unit 31 . The information acquisition unit 341 records the acquired estimation target data in the estimation target data storage unit 332 . When acquiring data of a learned model via the input unit 31 , the information acquisition unit 341 records the acquired data of the learned model in the learned model storage unit 331 .

The estimated data generator 342 generates estimated data by performing the same processing as the learning data generator 142 of the learning device 10 on the estimation target data. Therefore, the generated estimation data has the same configuration as the learning data. That is, the number of data items (number of dimensions) and the type of each data item (acquisition method) included in the estimated data match the number of data items and the type of each data item in the learning data. For example, if a common pattern is used in generating training data, the same common pattern is used in generating estimated data. The estimated data generation unit 342 records the generated estimated data in the estimated data storage unit 333 .

The estimation unit 343 performs estimation processing by using the estimated data generated by the estimated data generation unit 342 (including the estimated data stored in the estimated data storage unit 333) as input values for the trained model. The estimation unit 343 acquires information about the cognitive ability of the person to be estimated by executing the estimation process. For example, the estimation unit 343 determines which of the predetermined classifications (for example, the classification of MCI and dementia and others, the classification of MCI, dementia, or healthy, etc.) to which the estimation subject may fall. You may acquire the estimation result which shows. The estimation unit 343 records data indicating the acquired estimation result in the estimation result data storage unit 334 .

The output control unit 344 outputs data indicating the estimation result obtained by the estimation unit 343 (including data stored in the estimation result data storage unit 334 ) via the output unit 32 . The output control unit 344 may transmit the estimation result data to, for example, the terminal device (user terminal 40) used by the person to be estimated.

FIG. 7 is a flowchart showing a specific example of the processing flow of the learning device 10. As shown in FIG. The learning data generation unit 142 generates learning data by executing section division processing on the acquired teacher data (step S101). The learning unit 143 executes learning processing using the learning data (step S102). The learning unit 143 records the data of the learned model obtained by executing the learning process in the learned model storage unit 133 (step S103). The output control unit 144 outputs data of the trained model (step S104).

FIG. 8 is a flowchart showing a specific example of the processing flow of the estimation device 30. As shown in FIG. The estimated data generating unit 342 generates estimated data by performing a section dividing process on the acquired estimation target data (step S201). The estimation unit 343 executes estimation processing using the estimation data (step S202). The estimation unit 343 records the data of the estimation result obtained by executing the estimation process in the estimation result data storage unit 334 (step S203). The output control unit 344 outputs data of the estimation result (step S204).

With the learning device 10 and the estimation device 30 configured in this manner, it is possible to estimate information on human cognitive ability with higher accuracy while reducing the burden on the subject of estimation.

For example, in the learning device 10, the learning process may be performed by dividing the time series of sleep information into a plurality of intervals, and a learned model may be generated. By dividing the time series of sleep information into a plurality of sections, characteristic biometric information in each section, such as a section immediately after going to bed and a section immediately before waking up, is expressed. It is generally known that sleep-related behavior and biological information are correlated with cognitive ability. On the other hand, the time series of sleep information in this embodiment is biological information during sleep and can be realized using a relatively simple sensor. Therefore, by using such a new feature value related to sleep, it is possible to estimate information on human cognitive ability with higher accuracy while reducing the burden on the user with a simpler device. Become.

Although the embodiment of the present invention has been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design and the like are included within the scope of the gist of the present invention.

DESCRIPTION OF SYMBOLS 10... Learning apparatus, 11... Input part, 12... Output part, 13... Storage part, 131... Teacher data storage part, 132... Learning data storage part, 133... Trained model storage part, 14... Control part, 141... Information Acquisition unit 142 Learning data generation unit 143 Learning unit 144 Output control unit 30 Estimation device 31 Input unit 32 Output unit 33 Storage unit 331 Learned model storage unit 332 Estimated data storage unit 333 Estimated data storage unit 334 Estimation result data storage unit 34 Control unit 341 Information acquisition unit 342 Estimated data generation unit 343 Estimation unit 344 Output control unit

Claims (7)

With respect to teacher data having unit teacher data relating to a plurality of people in which biometric information relating to sleep of a person and information relating to cognitive ability of the person are associated, the biometric information is obtained according to sleep and bedtime. a learning data generation unit that generates learning data by dividing into a plurality of intervals;
a learning unit that acquires a trained model that outputs information about the cognitive ability of the subject by inputting information about the biometric information of the subject of estimation by performing learning processing using the learning data;
an output control unit that outputs data of the trained model;
A learning device with 2. The learning device according to claim 1, wherein the plurality of sections are sections determined based on biometric information obtained from the person to be presumed. an information acquisition unit that acquires biometric information of an estimation target;
An estimating unit that performs an estimating process using a trained model generated by the learning device according to claim 1 or 2 and the biometric information of the person to be estimated;
An estimating device comprising: With respect to teacher data having unit teacher data relating to a plurality of people in which biometric information relating to sleep of a person and information relating to cognitive ability of the person are associated, the biometric information is obtained according to sleep and bedtime. a learning data generating step for generating learning data by dividing into a plurality of intervals;
A learning step of acquiring a trained model that outputs information about the cognitive ability of the subject by inputting information about the biometric information of the subject by performing a learning process using the learning data;
an output control step of outputting data of the trained model;
A learning method with an information acquisition step of acquiring the biometric information of the presumed subject;
an estimation step of performing an estimation process using a trained model generated by the learning device according to claim 1 or 2 and the biometric information of the estimation target;
An estimation method with A computer program for causing a computer to function as the learning device according to claim 1 or 2. A computer program for causing a computer to function as the estimation device according to claim 3.

Images