JP7323883B2 - Cognitive function improvement solution estimation system, cognitive function improvement solution estimation method and program - Google Patents

Description

The present invention relates to a cognitive function improvement solution estimation system, a cognitive function improvement solution estimation method, and a program.

Today, reducing the anxiety and burden of elderly people with cognitive decline and their families is recognized as a social issue. For this reason, there is growing interest in solutions for cognitive decline. In the academic field, four solutions of studying, eating, exercising, and communication are pointed out to be effective in enhancing or improving cognitive functions.

Hayato Nagatomo, 3 others, ``Intervention effect of short-term intensive rehabilitation in improving cognitive function in elderly with dementia'', Aichi Physical Therapy Association, December 2011, Vol. 23, No. 2, pp. 51-55 Masaru Mimura, "Evidence-based non-drug therapy for dementia," Higher Brain Function Research, 2012, Vol. 32, No. 3, pp. 454-460 Ryuta Kawashima, "Aiming to prevent and improve dementia with learning therapy", [online], July 23, 2009, [searched on October 11, 2021], <URL: http://homesweethome. jp/files/libs/126/20180420112850351.pdf＞

However, the four proposed solutions only mention general effects, and it is not known which of the four solutions is effective in enhancing or improving the cognitive functions of specific individuals. In other words, there are individual differences between the four solutions and their effectiveness, and it is difficult to judge the degree of effectiveness.

An object of the present invention is to provide a service for estimating, for each user, a combination of one or more solutions that are expected to improve cognitive function.

The invention according to claim 1 includes a proposal unit that proposes one or more solutions to the user for the purpose of improving cognitive function, and an evaluation of the subject's cognitive function before implementation of the one or more solutions. a first acquisition unit that acquires first information; a second acquisition unit that acquires second information representing an evaluation of the subject's cognitive function after implementation of the one or more solutions; and a determination unit that determines a change in the subject's cognitive function evaluation that occurred before and after implementation of the one or more solutions based on the information of and the second information, and the proposal unit, A cognitive function improvement solution estimation system for estimating one or a plurality of newly proposed solutions based on a history of solutions proposed in the past and results of determination by the determination unit.
The invention according to claim 2 is the cognitive function improvement solution estimation system according to claim 1, wherein the first information and the second information are given as a result of analyzing measurement data measured in different periods. is.
The invention according to claim 3 is the cognitive function improvement solution estimation system according to claim 1, wherein the first information and the second information are given as a result of a test regarding the subject's cognitive function.
The invention according to claim 4 is the cognitive function improvement solution estimation system according to claim 1, wherein the proposal unit proposes one or more recommended solutions for the subject's attribute data.
The invention according to claim 5 is the cognitive function improvement solution estimation system according to claim 4, wherein the proposing unit proposes one or more recommended solutions for the classification to which the attribute data belongs.
The invention according to claim 6 is the cognitive function improvement solution estimation system according to claim 4, wherein the proposal unit proposes one or more recommended solutions for other subjects to whom the attribute data belongs. .
The invention according to claim 7, wherein the proposing unit estimates one or a plurality of newly proposed solutions based on the determination result of the determining unit and the attribute data. 2. A cognitive function improvement solution estimation system according to item 1.
The invention according to claim 8 further comprises a correction unit that corrects the attribute data according to the opinion on the one or more solutions obtained from the subject after the implementation of the one or more solutions, according to claim 7. It is a cognitive function improvement solution estimation system.
The invention according to claim 9, wherein the proposal unit estimates, for each subject, one or more new solutions that improve the evaluation of the subject's cognitive function by a Bayesian optimization method. The described cognitive function improvement solution estimation system.
The invention according to claim 10 is a cognitive function improvement solution estimation method realized through execution of a program by a computer, and is a process of proposing one or more solutions for each subject for the purpose of improving cognitive function. , a process of obtaining first information representing an evaluation of the subject's cognitive function before implementation of the one or more solutions, and a third representing an evaluation of the subject's cognitive function after implementation of the one or more solutions A process of acquiring the information of 2, and a process of determining a change in the evaluation of the subject's cognitive function that occurred before and after the implementation of the one or more solutions based on the first information and the second information. and a process of estimating one or more newly proposed solutions based on the history of solutions proposed in the past and the result of the determination.
In the invention according to claim 11, the computer has a function of acquiring first information representing an evaluation of the cognitive function of the subject before implementation of one or more solutions, and after implementation of the one or more solutions Ability to obtain second information representing an assessment of the subject's cognitive function, and the subject's experience before and after implementation of the one or more solutions based on the first information and the second information A program for realizing a function of determining changes in evaluation of cognitive function and a function of estimating one or more newly proposed solutions based on the history of solutions proposed in the past and the result of the determination. is.

According to the present invention, it is possible to provide a service for estimating, for each user, a combination of one or a plurality of solutions that are expected to improve cognitive function.

1 is a diagram showing a conceptual configuration example of a system that provides a cloud service assumed in Embodiment 1; FIG. 2 is a diagram illustrating a configuration example of a cloud server used in Embodiment 1; FIG. 4 is a diagram illustrating an example data structure of a DB stored in a storage device; FIG. (A) shows an example data structure of an attribute data DB, and (B) shows an example data structure of a measurement data DB. FIG. 7 is a diagram illustrating another data structure example of another DB stored in the storage device; (A) shows an example data structure of an execution history DB, and (B) shows an example data structure of an evaluation result DB. 4 is a flowchart for explaining an example of processing operations performed by a cloud server assumed in Embodiment 1; It is a figure explaining the change of the evaluation of a cognitive function by execution of the proposed solution. (A) is an example of change in cognitive function when a solution is proposed by the experience of the proposer, (B) is an example of change in cognitive function when a solution is proposed by this service, and (C) is This is an example of change in cognitive function when a solution is proposed in consideration of preferences. FIG. 10 is a diagram illustrating a configuration example of a cloud server used in Embodiment 2; FIG. FIG. 11 is a flowchart for explaining an example of processing operations performed by a cloud server assumed in Embodiment 2; FIG. FIG. 13 is a diagram for explaining a method of proposing a solution according to Embodiment 4; FIG. (A) shows distribution of attribute data and classifications G1 to G8 corresponding to each subject, and (B) shows an example of corresponding classifications and solutions. FIG. 13 is a diagram for explaining a method of proposing a solution according to Embodiment 5;

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings.
<Embodiment 1>
<Term>
In this embodiment, a service that provides a solution that is expected to be effective in improving the cognitive function of the subject will be described. Below, the service provided in the present embodiment is also referred to as "this service".
Here, "probable" is used in the sense of probability or high possibility of obtaining the effect of improving cognitive function.

“Target” includes not only those who have been diagnosed with dementia, but also those who are suspected of having dementia, those who want or desire prevention of dementia, and those who are concerned about the decline in cognitive function. use in meaning. In this embodiment, all persons who use this service for the purpose of improving cognitive function are included in the target persons.
On the other hand, users of this service include, for example, the target person, the target person's family and relatives, the person in charge of the business operator who supports the target person's life, and the doctor and staff of the medical institution.

<System configuration>
FIG. 1 is a diagram showing a conceptual configuration example of a system (hereinafter referred to as “cloud system”) 1 that provides cloud services assumed in Embodiment 1. As shown in FIG.
The cloud system 1 shown in FIG. 1 includes a network 10, an information terminal 20 used for uploading recorded data and measured data about a subject, and a solution expected to improve the cognitive function of each subject. It is composed of a cloud server 30 for estimation and an information terminal 40 that receives solutions provided by the cloud server 30 .

The network 10 in this embodiment is, for example, the Internet, a mobile communication system such as 4G or 5G.
However, the network 10 may be a LAN (=Local Area Network) depending on the form of provision of this service. Also, when data is exchanged off-line, a semiconductor memory or an optical disk may be used instead of the network 10 .

The information terminal 20 is, for example, an information terminal 20A installed in a private home where the subject resides or worn by the subject, an information terminal installed in a nursing facility where the subject resides or worn by the subject. 20B. Private homes and nursing homes are examples of a subject's living base.
The information terminals 20A and 20B are, for example, notebook computers, desktop computers, tablet computers, smart phones, and wearable computers.

Various data necessary for providing this service are uploaded from the information terminals 20A and 20B to the cloud server 30 in real time or periodically. For example, data is automatically uploaded at predetermined intervals, such as once a week or once a month. However, if the target person or the user of the service instructs the upload, the data will be uploaded at an arbitrary timing.
Various data necessary for the provision of services include, for example, information on the subject's body and medical history, information on the medical history of family members and relatives, information on the subject's preferences, measurement data on the subject's sleep and behavior, proposals Contains execution history data about the solution that was created.

The body information of the target person includes, for example, sex, age, height, weight, eyesight, and physical disability.
The information about the medical history of the subject includes, for example, the diagnosis result of dementia, hospital visit history, and nursing care certification.
The information about the subject's taste includes, for example, a movie lover, a fish lover, a mystery novel lover, a karaoke lover, and a conversation lover.
The measurement data includes sleep data and action data, for example.
Sleep data is biological data acquired during sleep, and includes data on pulse, respiration rate, rolling over and other body movements. Sleep data also includes sleep time and sleep cycles that can be acquired from data on body movement.

To acquire sleep data, we use, for example, a mat-type sensor that can measure data related to the subject's body movement without contact, a microwave Doppler radar, and an acceleration sensor built into a smartphone.
Sleep data need not be the entire period during which the subject is asleep. For example, only the biometric data of the time period when the characteristics of sleep are likely to appear may be used. For example, a time period immediately after falling asleep, a time period between the first REM sleep and non-REM sleep, and a time period immediately before waking up may be used as the time period in which the characteristics of sleep are likely to appear.

The behavior data is biometric data acquired while waking up, and output data of a sensor that detects the operation of equipment caused by the behavior of the subject and the behavior of the subject.
The biological data acquired during waking up includes data related to heartbeat, pulse, respiration rate, blood pressure, blood flow, number of steps, and other body movements. A sensor worn on the wrist, for example, can be used to acquire these biometric data.
Sensors that detect the operation of equipment and the behavior of the subject due to the behavior of the subject include, for example, a human sensor installed in the bathroom, a sensor that detects the opening and closing of the bathroom door, the operating state of the water heater, Sensors that detect hot water temperature, bath water level, and other data, controllers installed in bathrooms and kitchens, sensors that detect cooker operation, sensors that detect TV and video operations, and sensors that detect air conditioner operations. There is

The cloud server 30 is a server for the information terminal 20 and the information terminal 40, and for each subject, the type of proposed solution, the period during which the solution was implemented, the history of solution execution, and the measurement data collected during the same period. , information representing the evaluation of cognitive function, etc. are recorded. In the present embodiment, based on the timing of proposing a new solution, information representing the evaluation of the subject's cognitive function before executing the solution is called "first information", and after executing the proposed solution The information representing the evaluation of the subject's cognitive function in 1 is referred to as "second information".

In addition, the cloud server 30 estimates a solution that is expected to improve the cognitive function of each subject based on the subject's attribute data and collected information, and transmits the estimated solution to the information terminal 40. .
The information terminal 40 is, for example, a notebook computer, desktop computer, tablet computer, smart phone, or wearable computer. The example of FIG. 1 represents a case where the information terminal 40 is a smart phone.
In the example of FIG. 1, it is assumed that the information terminal 40 is different from the information terminal 20, but the information terminal 40 and the information terminal 20 may be the same terminal.

<Cloud server configuration>
FIG. 2 is a diagram illustrating a configuration example of the cloud server 30 used in the first embodiment. The cloud server 30 is an example of a cognitive function improvement solution estimation system.
The cloud server 30 includes an arithmetic device 301 that executes programs, a storage device 302 that stores various data, a communication unit 303 that is used for communication with the network 10 (see FIG. 1), and a bus that connects them. of wiring 304 .

The arithmetic unit 301 includes a CPU (=Central Processing Unit), a ROM (=Read Only Memory) storing BIOS (=Basic Input Output System), etc., and a RAM (=Random Access Memory) used as a work area. have.
In the case of this embodiment, the arithmetic unit 301 realizes the functions of a solution proposal unit 311, evaluation information acquisition units 312 and 313, and a determination unit 314 through execution of programs by the CPU.

The solution proposing unit 311 in this embodiment also has a sub-function for estimating a solution optimized for each subject.
The solution estimation sub-function is used at least during the second and subsequent proposals of the solution. The sub-function here estimates the next proposed solution depending on whether the cognitive function of the subject who executed the previously proposed solution improved, remained unchanged, or deteriorated due to execution of the solution.

In the case of this embodiment, four types of solutions are proposed. Specifically, there are four types: diet, exercise, communication, and learning. However, these four types are representative examples of solutions, and other types may be proposed as solutions. Also, the number of types of solutions to be proposed is not limited to four, and may be two, three, or five or more.
Solution proposal unit 311 in the present embodiment proposes any one of these four types.

The solution proposing unit 311 in the present embodiment changes the method of estimating the solution between when the solution is proposed for the first time and when the solution is proposed for the second and subsequent times.
At the time of the first proposal, the solution proposal unit 311 proposes a solution individually determined by, for example, the doctor who examined the subject or the advisor in charge of the subject.
However, in the initial proposal, a pre-determined solution may be proposed without specifying the target audience. In addition, the solution proposal part 311 may presume a solution based on a subject's attribute data at the time of an initial proposal. For example, priority may be given to solutions related to subject matter that the subject likes.

At the second and subsequent proposals, there is at least one solution executed by the subject, and there is also at least one information regarding the quality of execution, etc., and information regarding changes in evaluation of cognitive function before and after execution. Performance quality is given, for example, in the content and intensity performed by the subject.
The solution proposal unit 311 in the present embodiment, at the time of the second and subsequent proposals, includes the history of the solution proposed immediately before and the plurality of solutions proposed until the previous time, and the cognitive function before and after the execution of the solution by the subject. A new proposed solution is estimated based on the results of determining the change in the evaluation of .

For example, when the effect of improvement is confirmed, the solution proposal unit 311 presumes the same solution as the previous time as a newly proposed solution.
On the other hand, if the effect of improvement is not confirmed, the solution proposal unit 311 presumes a different type from the previous time as a new solution.
The solution proposing unit 311 proposes one of the types that have not been proposed in the past as a solution until all four types of proposals are circulated. At this time, the solution proposing unit 311 refers to information about the preferences of the subject, and gives priority to solutions that the subject is likely to be interested in.

After one round of suggestions, preference is given to types estimated to be more likely to improve the subject's cognitive function. For example, priority is given to types that have been recognized to have improved effects in the past.
However, even for types that have been shown to have an improvement effect in the past, if the same type of stimulation continues, the improvement effect may not be obtained as expected. It may be different from the point at which improvement is observed.

In some cases, the subject's current practice may be the reason why the improvement effect is not observed or is low. For example, if the quality of execution of the solution is poor.
Therefore, in the second and subsequent rounds, even a solution that did not have an improvement effect or had a low improvement effect at the time of past proposals is included in the subject of re-proposal.
On the other hand, after a predetermined number of proposals have been made, or after a predetermined number of rounds (for example, two times), the provision of this service may be terminated once.

The evaluation information acquisition unit 312 acquires information regarding the evaluation of the subject's cognitive function before executing the solution being executed. The evaluation information acquisition unit 312 is an example of a first acquisition unit in the claims.
In the case of the present embodiment, the information regarding the evaluation of cognitive function represents, for example, the degree of normality of cognitive function. Information about the evaluation of cognitive function is given by, for example, several grades of indexes or numerical values.

It should be noted that if the solution being implemented is the first solution proposed for the subject, the information relating to the evaluation of cognitive function may be, for example, the results of a test or diagnosis of cognitive function.
In addition, if there is available measurement data for the subject, the result of processing the measurement data by a known method may be acquired as information on the evaluation of cognitive function.

The evaluation information acquisition unit 313 acquires information regarding the evaluation of the subject's cognitive function after executing the solution being executed. The evaluation information acquisition unit 313 is an example of a second acquisition unit in the claims.
Since it is after execution of the solution by the subject, the evaluation information acquisition unit 313 acquires an evaluation of cognitive function based on measurement data and execution history data acquired for the subject.

However, the evaluation information acquisition unit 313 may acquire the results of examinations and diagnoses performed on the subject after execution of the solution as information that evaluates the cognitive function. Basically, priority is given to the results of diagnosis by a doctor. However, in addition to the results of diagnosis by a doctor, measurement data and the like during execution of the solution may also be acquired.
Note that before and after execution of a solution are determined relative to a specific solution as a reference, so after execution of a certain solution corresponds to before execution of the next solution. Therefore, the information representing the cognitive function evaluation obtained after executing a solution is used as the information representing the cognitive function evaluation obtained before executing the next solution.

The determination unit 314 compares the information acquired by the evaluation information acquisition unit 312 and the information acquired by the evaluation information acquisition unit 313, and determines the degree of improvement in cognitive function as a result of executing the solution.
The judgment by the judging unit 314 may be a binary judgment result of "cognitive function improved" and "cognitive function decreased", or a three-value judgment result of "no change in cognitive function" added to these. may be used as the result of determination.
Further, the determination by the determination unit 314 may be performed using the amount of change in the numerical value representing the evaluation of the cognitive function as the determination result.

In this embodiment, the storage device 302 is, for example, a hard disk device. However, the storage device 302 may be a large-capacity semiconductor memory. Also, the storage device 302 may be a storage server connected to the network 10 (see FIG. 1) separately from the cloud server 30 instead of being an auxiliary storage device of the cloud server 30 .

In the case of this embodiment, the storage device 302 stores an attribute data DB 321 , a measurement data DB 322 , an execution history DB 323 and an evaluation result DB 324 .
The attribute data DB 321 stores attribute data relating to the target person of this service.
The measurement data DB 322 stores measurement data regarding the target person of this service.
The execution history DB 323 stores the types and contents of solutions executed by the target person of this service.
The evaluation result DB 324 stores the proposed solution and the result of determination for evaluation of cognitive function after execution of the solution.

<DB data structure>
FIG. 3 is a diagram illustrating an example data structure of a DB stored in the storage device 302 (see FIG. 2). (A) shows a data structure example of the attribute data DB 321, and (B) shows a data structure example of the measurement data DB 322. FIG.
In the case of FIG. 3A, the attribute data DB 321 is composed of gender, age, medical history, physical disability, preference, attribute classification, and the like for each subject. Items other than attribute classification are examples of attribute data.

Note that preferences are acquired, for example, by answering questionnaires. Preferences may be content directly related to the solution or content not directly related to the solution. Dietary preferences, for example, are directly related to solutions. On the other hand, clothing preferences and hobbies are not directly related to solutions.
The attribute classification is information specifying a group of subjects with similar attribute data. A set used as a classification is given for one item of attribute data or a combination of a plurality of items in the case of this embodiment.
In the case of FIG. 3B, the measurement data DB 322 is composed of sleep data, action data, and the like for each subject.

FIG. 4 is a diagram illustrating an example of the data structure of another DB stored in the storage device 302 (see FIG. 2). (A) shows a data structure example of the execution history DB 323, and (B) shows a data structure example of the evaluation result DB 324. FIG. The data structure examples shown in FIGS. 4A and 4B correspond to the subject A. FIG.
In the case of FIG. 4A, the execution history DB 323 is composed of, for each subject, the date on which the solution was executed, the type of solution, the content of the execution, and the like.
The content of the execution also includes information on the strength at the time of execution. Intensity includes, for example, the number of times and execution time.

For example, as for "meal", the content, number of items, calorie, number of times, etc. of the meal are stored. Such information is input by the subject person or the user of the service. Note that the content and number of meals may be registered by image recognition or the like from a photograph of the meal.
For example, for "exercise", the contents of the exercise, the duration of the exercise, the number and intensity of the exercise, and the like are stored.
For example, for "communication", the number of times of conversation, the number of people, the time of conversation, etc. are stored.
For example, for "learning", the number of characters written, the type and difficulty of the book read, the number of pages read, the number of characters read, the number and difficulty of calculated questions, the percentage of correct answers, etc. are stored.

In the case of FIG. 4B, the evaluation result DB 324 is composed of the execution period, solution type, determination result, etc. for each subject.
In the example of FIG. 4B, a new solution is proposed on a two-month basis. However, the same solution is proposed for the next period as well, if the solution is found to be improved as a result of the judgment. In the example of FIG. 4B, learning is proposed twice in succession.

<Processing operation example>
FIG. 5 is a flowchart for explaining an example of processing operations performed by the cloud server 30 assumed in the first embodiment. Note that the symbol S shown in the figure means a step. The processing method shown in FIG. 5 is an example of a cognitive function improvement solution estimation method.
When providing the service, the cloud server 30 acquires information representing the evaluation of the subject's cognitive function (step 101). As the information representing the evaluation of the subject's cognitive function, for example, the result of a cognitive function test or the result of a diagnosis by a doctor is used. The information here is an example of the first information in the scope of claims.

Next, the cloud server 30 acquires the subject's attribute data (step 102).
Next, the cloud server 30 proposes a solution that is expected to improve the cognitive function of the subject (step 103). Note that the proposed solution may be extrapolated based on the subject's attribute data.
After proposing the solution, the cloud server 30 acquires the subject's execution history and measurement data for the proposed solution (step 104). These data are notified to the cloud server 30 from the information terminal 20 (see FIG. 1).

When the execution period of the solution ends, the cloud server 30 acquires information representing the evaluation of the subject's cognitive function after execution of the solution (step 105). The information acquired in step 105 corresponds to an example of the second information in the scope of claims for the executed latest solution. However, this information is an example of the first information in the claims from the point of view of the new solution estimated in step 107 .

Next, cloud server 30 determines changes in cognitive function ratings due to execution of the solution (step 106).
Cloud server 30 then estimates and proposes a new solution based on the result of the determination (step 107).
After that, the cloud server 30 proposes a new solution from the next time onwards using steps 103 to 107 as one cycle, and judges the improvement of the cognitive function by the proposed solution.

FIG. 6 is a diagram explaining changes in evaluation of cognitive function due to execution of the proposed solution. (A) is an example of change in cognitive function when a solution is proposed by the experience of the proposer, (B) is an example of change in cognitive function when a solution is proposed by this service, and (C) is This is an example of change in cognitive function when a solution is proposed in consideration of preferences.

In FIGS. 6A to 6C, the vertical axis is the score in the test of cognitive function, and the horizontal axis is time. A higher score indicates better cognitive function.
As shown in FIG. 6A, when a solution is proposed based on experience, it depends on the past experience of the proposer, and compatibility between the target person and the solution is neglected.
In addition, even when the proposed solution is determined programmatically, it is easy to simply apply the statistically effective solution in order, and many proposals are required to arrive at the highly effective solution for the target person.

On the other hand, as shown in Fig. 6(B), when proposing a solution using this service, the score fluctuates until the proposed solution is circulated, but an effective solution was found for each target person. After that, we can continuously propose highly effective solutions, so that cognitive improvement starts early.
Furthermore, as shown in FIG. 6(C), when a solution is proposed in consideration of the subject's preference, further improvement in cognitive function can be expected. A solution that everyone likes or is interested in is easier to stick with than a solution that everyone dislikes or is not interested in, and the quality of execution is likely to be higher. For this reason, it becomes easier to discover solutions that are expected to have an improvement effect from an early stage.

<Summary>
As mentioned above, by repeating the loop of proposing a new solution, collecting execution history and measurement data, and judging the improvement of cognitive function, it is possible to propose a solution according to the target person, that is, personalization, in a small number of times. be.
In addition, by preferentially proposing solutions that the subject likes or is interested in, the possibility of improvement in cognitive function can be increased.

In addition, by estimating a new solution in step 107 (see FIG. 5), including the execution history and measurement data of the solution by the subject acquired in step 104 (see FIG. 5), the accuracy of the proposed solution is evaluated. can be increased. For example, since the content and strength of solutions executed can be obtained from the execution history, it is possible to analyze the reasons why cognitive functions did not improve or improved, and to increase the accuracy of estimating newly proposed solutions. become. For example, even if the same solution is used, it is possible to include a change in the content to be executed or a change in strength in the proposal. Such a proposal is an effect that cannot be realized by focusing only on the type of solution (major classification).

In addition, in the description of the present embodiment, solutions are executed in units of four types (major classifications), but it is also possible to propose solutions in units of middle classifications and small classifications, which are lower layers of each type. For example, instead of meals, a solution may be proposed based on a classification such as Japanese food or Western food, or a solution may be proposed based on a classification such as meat dishes or fish dishes. For exercise, communication, and learning, a middle class or a small class may be used as a unit of proposal.

When solutions are proposed in units of middle class or small class, the number of solutions that can be proposed increases, and in brute-force proposals, it takes time to find a solution that has an improvement effect on the target person.
However, the method described in this embodiment does not only compare information representing the evaluation of cognitive function before and after solution execution, but also considers attribute data including subject preferences, history of solution execution, and measurement data. Therefore, efficient narrowing of the solution becomes possible.

<Embodiment 2>
In this embodiment, before estimating a new solution, a case will be described in which a function is added to acquire the target person's impressions and likes/dislikes of the executed solution, and to correct the attribute data. Responses about impressions or likes and dislikes here are examples of subject's opinions in the scope of claims.
The configuration of the cloud system 1 (see FIG. 1) assumed in this embodiment is the same as in the first embodiment.

FIG. 7 is a diagram illustrating a configuration example of the cloud server 30 used in the second embodiment. In FIG. 7, parts corresponding to those in FIG. 2 are shown with reference numerals corresponding thereto.
The cloud server 30 shown in FIG. 7 differs from the cloud server 30 shown in FIG. 2 in that an attribute data correction unit 315 is added.
The attribute data correction unit 315 has a function of correcting the attribute data of the target person stored in the attribute data DB 321 when the result of a questionnaire or the like conducted on the target person who has executed the solution is acquired from the information terminal 20. offer. For example, the attribute data correction unit 315 corrects the content of preferences in the attribute data DB 321 shown in FIG. 3(A).

In the column of preferences, in addition to likes and dislikes for the types of solutions that have been executed, likes and dislikes for middle class and small class level solutions are added or modified.
Addition is performed in case of unregistered information. Modifications are performed on registered information.
For example, something that didn't interest me the last time I ran it may find it interesting this time. In addition, the impression of the same event may change depending on the physical condition at the time of execution and the accumulation of experience. For example, the same solution in a row can lose interest.
In this way, preferences are information with a relatively high possibility of change, and reflecting the latest information of the subject when estimating a solution is also required to enhance the effect of improving cognitive function.

FIG. 8 is a flowchart for explaining an example of processing operations performed by the cloud server 30 assumed in the second embodiment. In FIG. 8, parts corresponding to those in FIG. 5 are shown with reference numerals corresponding thereto. The processing method shown in FIG. 8 is also an example of a cognitive function improvement solution estimation method.
In the case of FIG. 8, the cloud server 30 acquires the subject's impression of the executed solution and corrects the attribute data between steps 104 and 105 (step 201). As mentioned above, the modified attribute data is used when estimating new solutions in step 107 .

Correction of attribute data is not limited to impressions. For example, the addition or reduction of the inconvenient part of the limb may be corrected. Also, if the date of birth is not registered, the age is also subject to correction.
In the case of this embodiment, it is ensured that the information about the impressions of the implemented solution is reflected in the attribute data of the subject. For this reason, it becomes easier for the subject to select a solution that the subject likes or is interested in as a newly proposed solution, and it is possible to increase the possibility of improving the cognitive function.

<Embodiment 3>
In the above-described embodiment, a method of proposing one of four types of solutions prepared in advance or one of a plurality of solutions belonging to a lower layer thereof for each subject has been described.
However, the cloud server 30 may propose a combination of multiple solutions. For example, the subject A may be suggested learning and exercise as solutions, and the subject B may be suggested exercise, communication, and diet as solutions.

By performing a combination of multiple solutions that are of high interest to the subject, the likelihood of cognitive improvement is greater than when performing a single solution alone. It should be noted that the combination that provides an improvement effect is not limited to the combination of solutions that have a high improvement effect alone. For example, even if the improvement effect is low when executed alone, a high improvement effect may be obtained by executing them in combination.

However, the combination of multiple solutions increases the number of solutions that can be proposed compared to the first embodiment. For example, even if there are four types of solutions prepared in advance, there are 15 solutions in total: one of them, a combination of two of them, a combination of three of them, and all four of them.

For this reason, it is required to efficiently find and propose a combination with a high improvement effect in order to improve the cognitive function of the subject. Since the solution is estimated by taking into account the content and strength of the executed solution and the measurement data at the time of execution, it is possible to combine solutions with a high improvement effect more efficiently or with fewer trials than when relying on empirical rules. can find out. As a result, it becomes possible to enhance the effect of improving the subject's cognitive function.

In this embodiment, Bayesian optimization aiming at optimizing a black-box function is adopted for estimating a combination of solutions with a high improvement effect. In the case of this embodiment, as inputs, the proposed solution, execution history, measurement data, subject attribute data, information representing the evaluation of cognitive function before executing the proposed solution, The information represents the evaluation of cognitive function, and the output is a combination of newly proposed solutions. The attribute data also includes subject's preferences.
Note that Bayesian optimization is an example of an estimation algorithm, and other methods can also be adopted.
Bayesian optimization can also be used for solution estimation in the first and second embodiments.

<Embodiment 4>
In the first embodiment, a solution to be proposed to a target person is estimated by basically considering the history of four types of solutions that can be proposed, the target person's preferences, and the like. The cloud server 30 in preferentially proposes, as a new solution, a solution whose improvement effect has been proven for the classification to which the subject's attribute data belongs.

FIG. 9 is a diagram for explaining a method of proposing a solution according to the fourth embodiment. (A) shows distribution of attribute data and classifications G1 to G8 corresponding to each subject, and (B) shows an example of corresponding classifications and solutions.
In addition, the circle mark of FIG. 9(A) corresponds to each subject. Also, the distribution of circles represents the positional relationship when the attribute data are mapped on the attribute space.
In this embodiment, as shown in FIG. 9B, recommended solutions are defined for each classification.

For example, a combination of learning and exercise is recommended for subjects belonging to class G1.
A diet is recommended for subjects belonging to category G2, and a combination of exercise, communication, and diet is recommended for subjects belonging to category G3.
FIG. 9B shows classifications G2, G6, G7, and G8 to which only one solution is assigned, classifications G1, G4, and G5 to which a combination of two solutions is assigned, and classification G3 to which a combination of three solutions is assigned. It is shown.
By preferentially proposing a solution that has had an improvement effect on other subjects with similar attribute data, it is possible to increase the possibility of improving the subject's cognitive function by executing the proposed solution.

<Embodiment 5>
In the first embodiment, a case has been described in which a solution that has a track record for the classification to which the subject's attribute data belongs is preferentially proposed as a new solution for the subject.
However, while the proposal based on classification is expected to improve statistically, the difference with the subject's attribute data becomes large depending on the granularity of the classification.
Therefore, the cloud server 30 (see FIG. 1) in the present embodiment will explain a method of preferentially proposing a solution that has an improvement effect for other subjects whose attribute data are close to each other in the same classification. .

FIG. 10 is a diagram for explaining a method of proposing a solution according to the fifth embodiment.
The circles in FIG. 10 correspond to each subject. Also, the distribution of circles represents the positional relationship when the attribute data are mapped on the attribute space. The closer the circles are, the higher the matching degree of the attribute data is, and the farther the circles are, the lower the matching degree of the attribute data is.
In the case of FIG. 10, the target person of this service belongs to either the classification G1 or the classification G2. Subject A, subject B, and subject C belong to category G1. It can be seen that the distance between the attribute data of the subjects A and B is short, but the distance between the attribute data of the subjects A and C is long even within the same classification.

A solution that uses classification as a unit is a solution that has an improvement effect on the target person as a representative value using classification as a unit. For this reason, in the case of a subject whose attribute data is mapped near the outer edge, although the subject belongs to the category G1, the distance from the representative value is large.
Therefore, as in the present embodiment, by adopting a method of proposing a solution that had an improvement effect on the subject B to the subject A, there is a high possibility that the cognitive function of the subject A will also improve. Become.
As a result, it is possible to increase the possibility of proposing a solution or a combination of solutions having an improvement effect with a small number of trials.

<Other embodiments>
(1) Although the embodiments of the present invention have been described above, the technical scope of the present invention is not limited to the scope described in the above-described embodiments. It is clear from the scope of claims that the technical scope of the present invention includes various modifications and improvements to the above-described embodiment.

(2) In the above-described Embodiments 1 to 5, when proposing the second and subsequent solutions, the attribute data of the subject is referred to and the solution to be preferentially applied is estimated. At the time of proposing , by referring to the attribute data of the subject and determining the solution to be proposed, it is possible to propose a solution with a high improvement effect from the beginning.

(3) In the first to fifth embodiments described above, the solution proposed by the cloud server 30 is estimated and proposed to the service user. You may In other words, a solution may be estimated through execution of a program installed in the information terminal 20 or the information terminal 40 rather than as a cloud service. The information terminal 20 and the information terminal 40 in this case are an example of a cognitive function improvement solution estimation system.

Moreover, the processing functions corresponding to the cloud server 30 may be executed by cooperation between the cloud server 30 and the information terminals 20 and 40 . In other words, the corresponding processing functionality may be distributed over multiple terminals. In this case, multiple terminals involved in realizing the processing function correspond to the cognitive function improvement solution estimation system.

DESCRIPTION OF SYMBOLS 1... Cloud system, 10... Network, 20, 20A, 20B, 40... Information terminal, 301... Arithmetic unit, 311... Solution proposal part, 312, 313... Evaluation information acquisition part, 314... Judgment part, 321... Attribute data DB , 322... Measurement data DB, 323... Execution history DB, 324... Evaluation result DB

Claims (11)

a proposal unit that proposes one or more solutions to the user for the purpose of improving cognitive function;
a first acquisition unit that acquires first information representing an assessment of the subject's cognitive function prior to implementation of the one or more solutions;
a second acquisition unit that acquires second information representing an assessment of the subject's cognitive function after implementation of the one or more solutions;
a determination unit that determines a change in the subject's cognitive function evaluation that occurred before and after implementation of the one or more solutions based on the first information and the second information;
has
The proposing unit estimates one or more newly proposed solutions based on the history of solutions proposed in the past and the results of determination by the determining unit.
Cognitive function improvement solution estimation system. The first information and the second information are given as a result of analyzing measurement data measured during different periods;
The cognitive function improvement solution estimation system according to claim 1. The first information and the second information are given as a result of a test on the subject's cognitive function,
The cognitive function improvement solution estimation system according to claim 1. The proposal unit proposes one or more recommended solutions for the subject's attribute data;
The cognitive function improvement solution estimation system according to claim 1. the proposal unit proposes one or more recommended solutions for the classification to which the attribute data belongs;
Cognitive function improvement solution estimation system according to claim 4. The proposal unit proposes one or more recommended solutions for other subjects to whom the attribute data belongs;
Cognitive function improvement solution estimation system according to claim 4. The proposing unit estimates one or more newly proposed solutions based on the determination result of the determining unit and the attribute data.
Cognitive function improvement solution estimation system according to any one of claims 4 to 6. 8. The cognitive function improvement solution estimation system according to claim 7, further comprising a correction unit that corrects the attribute data according to an opinion on the one or more solutions obtained from the subject after the implementation of the one or more solutions. The proposal unit estimates, for each subject, one or more new solutions that improve the evaluation of the subject's cognitive function by a Bayesian optimization technique.
The cognitive function improvement solution estimation system according to claim 1. A cognitive function improvement solution estimation method realized through execution of a program by a computer,
A process of proposing one or more solutions for each subject for the purpose of improving cognitive function;
obtaining first information representing an assessment of the subject's cognitive function prior to implementation of the one or more solutions;
obtaining second information representing an assessment of the subject's cognitive function after implementation of the one or more solutions;
Based on the first information and the second information, a process of determining a change in the evaluation of the subject's cognitive function that occurred before and after implementation of the one or more solutions;
A process of estimating one or more newly proposed solutions based on the history of solutions proposed in the past and the result of the determination;
Cognitive function improvement solution estimation method having to the computer,
the ability to obtain first information representing an assessment of the subject's cognitive function prior to implementation of one or more solutions;
the ability to obtain second information representing an assessment of the subject's cognitive function after implementation of the one or more solutions;
the ability to determine a change in the subject's assessment of cognitive function that occurred before and after implementation of the one or more solutions based on the first information and the second information;
A function of estimating one or more newly proposed solutions based on the history of solutions proposed in the past and the result of the determination;
program to make it happen.