WO2023162829A1

WO2023162829A1 - Information processing device, information processing method, and recording medium

Info

Publication number: WO2023162829A1
Application number: PCT/JP2023/005304
Authority: WO
Inventors: 陽介瀧本
Original assignee: 株式会社ヘルスケアシステムズ
Priority date: 2022-02-22
Filing date: 2023-02-15
Publication date: 2023-08-31
Also published as: JP2023121986A

Abstract

[Problem] Conventionally, when an intervention with respect to the result of an inspection is to be proposed, the reason for the proposal could not have been presented. [Solution] The above problem can be solved by an information processing device 1 provided with: a user information reception unit 121 for receiving user information including result information that specifies an inspection result of a user; an intervention determination unit 133 for acquiring learning information based on two or more training data items that are associated with an intervention identifier for identifying an intervention made by the user and that include first result information that specifies an inspection result before making the intervention and second result information that specifies an inspection result after making the intervention, and acquiring the intervention identifier corresponding to the result information included in the user information by using the learning information and the received user information; a reason information acquisition unit 134 for, by using the received user information and one or more training data items corresponding to the acquired intervention identifier, acquiring the reason information concerning the reason why the intervention is recommended; and an information output unit 141 for outputting the intervention identifier and the reason information.

Description

Information processing device, information processing method, and recording medium

The present invention relates to an information processing device and the like that proposes a course of action according to the user's biopsy results.

In the prior art, there is a technology that outputs information indicating recommended health foods according to test results and information indicating recommended lifestyle habits according to test results (see Patent Document 1).

JP 2021-148507 A

However, in the prior art, when proposing measures to deal with test results, it was not possible to present the grounds for the proposal.

The information processing apparatus of the first invention includes a user information reception unit that receives user information having one or more user attribute values including result information that specifies the test results related to the biological body of one user, and a user's countermeasure. Two or more training data associated with the identified treatment identifier, including first result information specifying inspection results before handling and second result information specifying inspection results as a result of handling Acquiring learning information from a learning information storage unit storing learning information based on two or more teacher data having two or more user attribute values, and using the learning information and the user information received by the user information receiving unit a countermeasure determination unit that acquires a countermeasure identifier that identifies a countermeasure corresponding to the result information contained in the user information; one or more teacher data corresponding to the countermeasure identifier that the countermeasure determination unit acquires; and a grounds information acquisition unit for acquiring grounds information relating to grounds for recommending the handling identified by the handling identifier acquired by the handling determination unit, and the grounds acquired by the handling identifier acquired by the handling determination unit and the grounds information acquisition unit using and an information output unit that outputs information.

With this configuration, when proposing measures to deal with inspection results, the grounds for the proposal can be presented.

Further, in the information processing apparatus of the second invention, in contrast to the first invention, the basis information acquisition unit receives one or more teacher data corresponding to the handling identifier acquired by the handling determination unit and the user information reception unit accepts information indicating the level of grounds for recommending a course of action, and the reason for recommending the course of action, using the user information obtained by the user, and information indicating the reason for recommending the course of action. An information processing apparatus that acquires basis information including one or more types of information among reason information that is information including satisfaction level information related to satisfaction level after performing a.

With this configuration, when proposing measures to deal with inspection results, it is possible to present appropriate grounds for the proposal.

Further, in the information processing apparatus of the third invention, in contrast to the first or second invention, if the basis information acquisition unit fails to acquire the basis information, the basis information that is information to the effect that there is no basis is an information processing device that acquires

With this configuration, when proposing measures to deal with inspection results, it is possible to clearly indicate that there is no basis for the proposal.

Further, the information processing device of the fourth invention is information specifying a reward for recommending the user to take action against any one of the first to third inventions, and corresponds to the basis information. The information processing apparatus further includes a remuneration information acquisition unit that acquires remuneration information as information, and the information output unit also outputs the remuneration information acquired by the remuneration information acquisition unit.

With this configuration, it is possible to provide the user with an incentive to take action when proposing a course of action for the inspection results.

Further, in the information processing device of the fifth invention, in the information processing apparatus of the fourth invention, the remuneration information acquisition unit acquires remuneration information specifying remuneration according to the basis level included in the basis information. It is a device.

Further, the information processing apparatus of the sixth invention is obtained by using the second result information possessed by each of the two or more teacher data for each treatment identifier for any one of the first to fifth inventions. A classification unit that classifies two or more teacher data into two or more classes using effect information that is information and is information about the effect of coping, and associates each of the two or more teacher data with a class identifier that identifies the class. and the handling determining unit determines a class to which the user information belongs for each of the two or more handling identifiers using the user information received by the user information accepting unit and learning information based on the two or more teacher data. Further, the information processing apparatus distinguishes and acquires a measure identifier corresponding to a class having a large difference between the first result information and the second result information and a measure identifier corresponding to a class having a small difference.

With such a configuration, it is possible to determine an appropriate course of action for the inspection results.

Further, in the information processing apparatus of the seventh invention, in contrast to the sixth invention, the teacher data also has the user's degree of satisfaction as a result of taking action, and the classifying unit includes two points for each action identifier. Information processing for classifying two or more teacher data into two or more classes using the effect information and satisfaction level for each of the above teacher data, and associating each of the two or more teacher data with a class identifier that identifies the class. It is a device.

With such a configuration, it is possible to determine a more appropriate response to the inspection results.

Further, in the information processing apparatus of the eighth invention, in contrast to the sixth invention, each of the two or more classes classified by the classification unit is associated with a basis level based on effect information for teacher data corresponding to the class. The basis information acquisition unit acquires the basis level corresponding to the class, and is information acquired using the second result information of the teacher data corresponding to the class determined by the handling determination unit, and the effect of handling 7. The information processing apparatus according to claim 6, wherein effectiveness information is obtained using effect information that is related information, and basis information that includes a basis level and reason information that is information containing effectiveness information is obtained.

Further, in the information processing apparatus of the ninth invention, in contrast to the eighth invention, the teacher data also has the user's satisfaction level of the result of taking the countermeasure, and the classification unit includes two Using the effect information and satisfaction level for each of the above teaching data, two or more teaching data are classified into two or more classes, each of the two or more teaching data is associated with a class identifier that identifies the class, and the basis is The information acquisition unit is an information processing device that acquires satisfaction level information using the satisfaction level of the teacher data corresponding to the class to which the user information belongs, and acquires basis information including reason information including the satisfaction level information.

With this configuration, it is possible to present a more appropriate basis for the proposal when proposing measures to deal with the results of the inspection.

Further, the information processing apparatus of the tenth invention satisfies the similarity condition with one or more user attribute values included in the user information received by the user information receiving unit, in relation to any one of the first to ninth inventions. The learning information acquisition unit acquires learning information using two or more teacher data having one or more user attribute values, and the learning information storage unit of the learning information storage unit stores the learning acquired by the learning information acquisition unit. It is an information processing device that is information.

Further, the information processing apparatus of the eleventh invention is, for any one of the first to tenth inventions, the countermeasure is to provide a challenge or service to ingest the product for a certain period or more in order to improve the test result. is a challenge to enjoy a certain period of time or longer, or a challenge to perform an action for a certain period of time or longer, and the teacher data is an information processing device that includes the degree of effort for the challenge, which is answer information to a questionnaire about the challenge.

According to the information processing apparatus of the present invention, when proposing measures to deal with test results, the grounds for the proposal can be presented.

Conceptual diagram of information system A in Embodiment 1 Block diagram of the same information system A Flowchart for explaining an operation example of the information processing device 1 Flowchart for explaining the first example of the learning information creation process Flowchart for explaining an example of same classification processing Flowchart explaining an example of the same learning process Flowchart for explaining a second example of the same learning information creation processing Flowchart for explaining a third example of the same learning information creation processing Flowchart for explaining a fourth example of the same learning information creation processing Flowchart for explaining an example of the same output information acquisition process Flowchart for explaining an example of countermeasure information acquisition processing Flowchart for explaining an example of countermeasure information acquisition processing Flowchart for explaining an example of countermeasure information acquisition processing Flowchart for explaining an example of countermeasure information acquisition processing Flowchart explaining an example of the same basis information processing Flowchart explaining an example of reward information processing Diagram showing the same teacher data management table Diagram showing the basis level judgment table Diagram showing the concept of classification of the same training data Diagram showing the same output example Overview of the computer system Block diagram of the same computer system

Hereinafter, embodiments of an information processing device, etc. will be described with reference to the drawings. It should be noted that, since components denoted by the same reference numerals in the embodiments perform similar operations, repetitive description may be omitted.

(Embodiment 1)
In the present embodiment, an information processing apparatus that receives inspection results of a user, acquires and outputs countermeasures (for example, products) according to the inspection results and grounds information on grounds for recommending the countermeasures using learning information. will be explained.

Also, in the present embodiment, an information processing apparatus that acquires and outputs remuneration information using basis information will be described.

Furthermore, in the present embodiment, after the user has taken action, information for acquiring and outputting information on the basis information on the basis for recommending the action and the action according to the inspection result using the answer information of the questionnaire for the action. A processing device will be described.

In the present embodiment, the fact that the information X is associated with the information Y means that the information Y can be obtained from the information X or the information X can be obtained from the information Y, and the method of the association does not matter. . Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, and information Y may be included in information X. etc. is fine.

FIG. 1 is a conceptual diagram of the information system A according to this embodiment. An information system A includes an information processing device 1 , one, or two or more terminal devices 2 .

The information processing device 1 is a device that outputs countermeasures and basis information according to the user's test results. The information processing device 1 is a so-called server, for example, a cloud server or an ASP server, but the type of server does not matter. Note that the information processing device 1 may be a stand-alone device.

The terminal device 2 is a device used by the user. The terminal device 2 is, for example, a so-called personal computer, a multifunctional mobile phone such as a smart phone, a mobile phone, or a tablet terminal, but the type of the terminal device 2 is not limited. A user is a person who uses the information processing device 1 or an administrator of the information processing device 1 .

The information processing device 1 and one or more terminal devices 2 can communicate via a network such as the Internet or a LAN.

FIG. 2 is a block diagram of the information system A according to this embodiment. The information processing device 1 includes a storage unit 11 , a reception unit 12 , a processing unit 13 and an output unit 14 . The storage unit 11 includes a teacher data storage unit 111 and a learning information storage unit 112 . The reception unit 12 has a user information reception unit 121 . The processing unit 13 includes a classification unit 131 , a learning information acquisition unit 132 , a coping determination unit 133 , a basis information acquisition unit 134 and a remuneration information acquisition unit 135 . The output unit 14 has an information output unit 141 .

The terminal device 2 includes a terminal storage section 21 , a terminal reception section 22 , a terminal processing section 23 , a terminal transmission section 24 , a terminal reception section 25 and a terminal output section 26 .

Various types of information are stored in the storage unit 11 that constitutes the information processing device 1 . The various types of information are, for example, teacher data to be described later, learning information to be described later, questionnaire information to be described later, answer information to be described later, and various conditions to be described later. Various conditions are, for example, an effect condition described later, a satisfaction condition described later, an acquisition condition described later, a remuneration condition described later, and information that associates a class identifier with a basis level.

The teacher data storage unit 111 stores one or more teacher data. Teacher data is information that is the source of learning information. The training data is associated with an action identifier that identifies the action taken by the user (which may also be referred to as a "subject"). Teacher data has two or more user attribute values. The two or more user attribute values include first result information and second result information. User attribute values of 2 or more are, for example, user gender, user age, user height, user weight, activity information, lifestyle information, goals, and goal achievement rate (to-be realization rate). , including satisfaction. The training data may be obtained directly from the user himself/herself, or may be obtained indirectly from an academic paper, an academic journal, or the like.　

It is preferable that the training data include effect information. The effect information is information about the effect of countermeasures. Effect information is usually information obtained using the second result information. The effect information is, for example, information regarding the difference between the first result information and the second result information. The effect information is, for example, information indicating the degree of improvement, which is the difference between the first result information and the second result information, or the ratio of the difference between the first result information and the second result information to the first result information. . The effect information is, for example, information regarding the difference between the second result information and the target. The effect information is, for example, the difference between the second result information and the target, the information indicating the degree of improvement which is the ratio of the difference between the second result information and the target and the target, or the degree of achievement of the target. If the teacher data includes effect information, the teacher data may not include the first result information and the second result information. Effect information is information related to the effect of the user's action. The effect information is information related to the difference between the first result information and the second result information. Improvement rate of xyl sulfate measurement value, number of increases in intestinal health, rate of increase in intestinal health, amount of weight loss (increase), amount of improvement in body composition, and amount of change in height.

　Treatment is information about the user's behavior according to the test results. The action is, for example, a product ingested by the user, a service provided to the user, an action performed by the user, or a challenge performed by the user. The challenges made by the user are, for example, that the user ingests a product in a predetermined period (for example, eats a meal using the low-salt product A for two weeks), that the user enjoys the service provided in a predetermined period, that the user in a given period of time (e.g., walked for 30 minutes for 1 month, ran for 1 hour continuously for 2 weeks, stopped or restricted smoking or drinking for 1 month) , etc.). It should be noted that the products, services, actions, etc. ingested by the user are, for example, products for improving test results.

The first result information is information that specifies the inspection result before taking the action identified by the action identifier. The second result information is information specifying the inspection result after taking the treatment identified by the treatment identifier. The first result information and second result information are, for example, blood sugar level, blood pressure, measured value of indoxyl sulfate, health level of intestinal environment, weight, body composition, and height. The body composition is, for example, muscle mass (percentage), body fat mass (percentage), visceral fat mass (percentage), subcutaneous fat mass (percentage), bone density, BMI, body age, and the like.

It should be noted that the inspection is an inspection of the user's living body. A test is performed here, for example, using a sample. A specimen is a biological or ex vivo sample. Biological samples are, for example, urine, stool, blood, intraoral cells, saliva, hair, body hair, sebum, nails, skin pieces, semen, tears, sweat, breast milk, runny nose, sputum, tartar, and tongue coating. Ex vivo samples are, for example, subject's photographic data, subject's video data, subject's audio data, and house dust of the subject's residence. Further, the inspection includes, for example, an inspection using a test kit, but is not limited to this. The examination may be, for example, an examination using a physical examination instrument such as a weight scale, a body composition meter, or a stature meter. The test may be, for example, a subjective stress degree check or discomfort check by questionnaire, or a cognitive function test. Such tests are, for example, the Mini-Mental State Examination (MMSE) test that evaluates cognitive status (see URL: http://www.shizuokamind.org/wp-content/uploads/2013/10/MMSE.pdf) , the Kupperman climacteric index (KKSI) test (see URL: https://ohana-clinic-kinoshitacho.com/wp-content/themes/ohana/download/kuppaman.pdf) to assess menopausal symptoms.

A test kit is, for example, an article for testing using substances emitted from the subject's body. Substances emitted from the living body are, for example, urine, blood, stool, and other body fluids. A test kit is an article for testing, eg, to obtain an indoxyl sulfate measurement. Test kits include, for example, an equol test kit, a urine test that measures whether equol is produced from soy isoflavones, and an intestinal environment test kit, a urine test that measures the health of the intestinal environment based on the amount of putrefactive substances derived from intestinal bacteria. kit, oxidative stress test kit that measures DNA (8-OHdG) damaged by active oxygen, urinalysis test kit that measures salt intake per day, low-salt test kit, stomach cancer It is a urine test kit that measures the presence or absence of antibodies to Helicobacter pylori, which increases the risk.

The test kit may be, for example, information for testing using information about the subject (for example, rights information). The information about the subject is, for example, voice data of the subject and image data of the subject, and the image data is a still image or moving image. Items other than articles may be information including both image data and audio data. Information about the health condition of the subject can be obtained as the test result from the voice data of the subject and the image data of the subject. The information about the health condition is, for example, the degree of frailty, the degree of depression, etc., but the content of the information does not matter.

Effort information is information about the status of the user's efforts toward the challenge. Effort information is, for example, the degree of effort for the user's challenge. The action information is, for example, the completion rate and the number of days the action was taken. The completion rate is, for example, the rate of days on which measures were taken during a predetermined period. The effort information may include not only information about direct efforts to the challenge, but also information about incidental efforts. Ancillary efforts are health-related actions that the user engages in outside of the challenge. The information about the incidental efforts may be actions that are known to lead to improvement in test results or actions that are not known to lead to improvement in test results. Information related to accompanying efforts includes, for example, information indicating that snacking has been stopped, information indicating that sleep time has been increased, information specifying sleep time, for the challenge program effort (e.g., yogurt intake), Information indicating increased exercise time, information specifying exercise time, information indicating quitting smoking, information specifying the number of cigarettes smoked, information indicating quitting drinking, information specifying the amount of alcohol consumed, etc. be.

　Lifestyle information is information related to the user's lifestyle. The lifestyle information includes, for example, whether or not the person smokes, whether or not he/she drinks alcohol, the amount of smoking per day, the frequency of drinking alcohol, the amount of drinking alcohol, the presence/absence of exercise habits, and the exercise time for a predetermined period (for example, one day).

A goal is a user's goal, usually a goal related to test results. A goal is, for example, a goal for which there is a basis. A goal indicates an ideal state based on, for example, papers or statistical results. A goal may be, for example, a value between the ideal value and the current user's value. The target is, for example, a blood pressure target value and a weight target value. The target may also be a target value corresponding to the first result information and the second result information. good too.

The To-Be realization rate is the degree of achievement from the user's current state (As-Is) to the ideal state (To-Be). ).

"Satisfaction" is the degree of satisfaction after taking action. Satisfaction is usually the degree of satisfaction with the treatment. Satisfaction is, for example, a numerical value from 1 to 5, an evaluation value in one of three stages of "satisfied", "normal", and "not satisfied", and a continuous value such as VAS (Visual Analog Scale). .

User attribute values other than the first result information and the second result information included in the training data are, for example, answer information corresponding to questionnaires for users. The answer information includes, for example, the user's gender, user's age, user's height, user's weight, effort information, lifestyle information, goal, To-Be realization rate, and satisfaction level.

The learning information storage unit 112 stores learning information based on two or more teacher data. The learning information storage unit 112 is, for example, a learning device to be described later, a correspondence table to be described later, and a teacher data set. The processing of creating learning information in the learning information storage unit 112 may be performed by the learning information acquisition unit 132 described later, or may be performed by an external learning device (not shown). Note that a teacher data set is a set of two or more teacher data.

A learning device is, for example, data created by machine learning learning processing using two or more teacher data. Such a learning process may be performed by the learning information acquisition unit 132, which will be described later, or may be performed by an external learning device (not shown). If an external learning device performs the learning process, the teacher data storage unit 111 is unnecessary. Note that the learning device may also be called a classifier, a predictor, a learning model, a model, or the like.

The correspondence table has two or more pieces of correspondence information. Correspondence information is, for example, information indicating correspondence between one or more user attribute values and action identifiers. Correspondence information is, for example, information indicating correspondence between one or more user attribute values and class identifiers. Class identifiers will be described later.

The reception unit 12 receives various information and instructions. Various information and instructions are, for example, user information described later.

Here, "acceptance" usually means reception of information transmitted from the terminal device 2 via a wired or wireless communication line. However, reception may be a concept that includes reception of information input from input devices such as keyboards, mice, and touch panels, and reception of information read from recording media such as optical disks, magnetic disks, and semiconductor memories. .

The user information reception unit 121 receives user information of one user. User information has one or more user attribute values. User attribute values include result information. The result information is information specifying the result of an examination on the living body of one user. The result information is, for example, blood sugar level, blood pressure, measured value of indoxyl sulfate, health level of intestinal environment. The reason why the user information receiving unit 121 receives user information is usually to obtain a countermeasure identifier and ground information. The result information included in the user information received by the user information receiving unit 121 is information on the inspection result before taking action.

The processing unit 13 performs various types of processing. Various types of processing are processing performed by the classification unit 131, the learning information acquisition unit 132, the coping determination unit 133, the ground information acquisition unit 134, and the remuneration information acquisition unit 135, for example.

The processing unit 13 may use the basis information acquired by the basis information acquisition unit 134 to construct the output information. The processing unit 13 may configure the output information using the basis information acquired by the basis information acquisition unit 134 and the remuneration information acquired by the remuneration information acquisition unit 135 . Output information is information to be output.

The classification unit 131 classifies two or more teacher data in the teacher data storage unit 111 into two or more classes, and associates each of the two or more teacher data with a class identifier. A class identifier is information for identifying a class. The class identifier is, for example, one of "class 1", "class 2", "class 3", and "class 4".

The classification unit 131 classifies two or more teacher data into two or more classes using effect information for each action identifier, and associates each of the two or more teacher data with a class identifier.

The classification unit 131, for example, acquires effect information regarding the difference between the first result information and the second result information possessed by each of the two or more pieces of teacher data for each treatment identifier. Next, the classification unit 131 classifies the effect information corresponding to each of the two or more pieces of teacher data into two or more classes, and classifies the two or more pieces of teacher data into two or more classes according to the classification of the effect information. , corresponding to each of the two or more teacher data with a class identifier. For example, the classification unit 131 classifies the teacher data of “effect information <= threshold 1” into “class 1”, the teacher data of “threshold 1 < effect information <= threshold 2” into “class 2”, and classifies the teacher data of “threshold 2 < effect information” into “class 1”. ” is classified into “class 3”, and two or more pieces of teacher data are classified into three classes. The number of classes does not matter.

For example, the classification unit 131 classifies the two or more teacher data into two or more classes using the effect information and the satisfaction level of each of the two or more teacher data for each coping identifier, and classifies the two or more teacher data. corresponds to a class identifier that identifies a class for

For example, the classification unit 131 classifies teacher data of "effect information <= threshold 1 and satisfaction level <= threshold a" as "class 1", and classifies teacher data of "effect information <= threshold 1 and threshold a < satisfaction level" as "class 1". class 2", "threshold 1 < effect information and satisfaction level <= threshold a" as "class 3", and "threshold 1 < effect information and threshold a < satisfaction level" as "class 4", Two or more teacher data are classified into four classes. The number of classes does not matter.

Also, the classification unit 131 may classify, for example, two or more pieces of teacher data into two or more classes using a known cluster analysis algorithm. Known cluster analysis algorithms include hierarchical methods such as the k-means method, the shortest distance method (nearest neighbor method), the shortest distance method (nearest neighbor method), the centroid method, and the group average method, the k-means method, and hypervolume A non-hierarchical method such as a method may also be used. Note that classifying two or more pieces of teacher data into two or more classes means associating each of the two or more pieces of teacher data with a class identifier.

The learning information acquisition unit 132 acquires learning information using two or more pieces of teacher data in the teacher data storage unit 111. It is preferable that the learning information acquisition unit 132 acquires learning information using the result of the classification performed by the classification unit 131 . The learning information is information used to acquire the action identifier. The learning information may be information that acquires the class identifier of the class to which the user belongs before acquiring the action identifier. Also, the learning information is, for example, a learning device and a correspondence table.

The learning information acquiring unit 132 uses two or more teacher data having one or more user attribute values that satisfy a similarity condition with one or more user attribute values included in the user information received by the user information receiving unit 121, and obtains learning information. It is preferable to obtain The similarity condition is, for example, that the degree of similarity is equal to or greater than a threshold, and that the degree of similarity is greater than the threshold. Note that the degree of similarity is calculated using a vector whose elements are one or more user attribute values included in the user information received by the user information receiving unit 121, and a vector whose elements are one or more user attribute values included in the teacher data. is the similarity of The algorithm for calculating the degree of similarity between two vectors is a well-known technique, so the explanation is omitted.

A specific example of an algorithm for acquiring learning information will be described below.
(1) Learning information for acquiring a class identifier (1-1) When learning information is a learning device (1-1-1) For a learning device to output one class identifier among class identifier candidates If the learner (e.g., multivalued classification) of

The learning information acquisition unit 132 acquires two or more pieces of teacher data stored in the teacher data storage unit 111 for each action identifier. Next, the learning information acquisition unit 132 uses one or more user attribute values possessed by each of two or more teacher data as an explanatory variable for each action identifier, and sets the class identifier corresponding to each of two or more teacher data as an objective variable. , a learning process of machine learning is performed, a learning device is acquired, and it is stored in the learning information storage unit 112 in association with the countermeasure identifier. Note that the class identifier of the training data is information acquired by the classification unit 131 .

It should be noted that deep learning, decision trees, random forests, SVR, etc. can be used as algorithms for machine learning learning processing, but it does not matter. It should be noted that an algorithm for performing prediction processing of machine learning, which will be described later, may be deep learning, decision tree, random forest, SVR, or the like, but it does not matter. For machine learning, for example, various machine learning functions such as TensorFlow library, fastText, tinySVM, R language random forest module, and various existing libraries can be used. Note that the module may also be called a program, software, function, method, or the like.

Note that the learning information acquisition unit 132 does not need to use all the user attribute values that make up the teacher data when creating a learning device, and may use a part of the user attribute values.
(1-1-2) When the learner is a binary classification learner

The learning information acquisition unit 132 acquires two or more pieces of teacher data stored in the teacher data storage unit 111 for each action identifier. Next, the learning information acquisition unit 132 sets the teacher data corresponding to the class identifier of interest as a positive example and the teacher data not corresponding to the class identifier as a negative example for each action identifier and each class identifier, and performs machine learning. A learning process is performed, a learning device is acquired, the action identifier and the class identifier are associated with each other, and stored in the learning information storage unit 112 .

The learning information acquisition unit 132 uses one or more user attribute values possessed by each of two or more teacher data as an explanatory variable, and uses a class identifier corresponding to each of two or more teacher data as an objective variable for machine learning learning. Execute processing and acquire a binary classification learner.
(1-2) When learning information is a correspondence table (1-2-1) When one correspondence information corresponds to one teacher data

The learning information acquisition unit 132 acquires two or more pieces of teacher data stored in the teacher data storage unit 111 for each action identifier. Next, the learning information acquisition unit 132 constructs a vector whose elements are one or more user attribute values of two or more pieces of teacher data for each action identifier. Then, the learning information acquisition unit 132 constructs a correspondence table having two or more pieces of correspondence information having class identifiers corresponding to the vector and the teacher data for each countermeasure identifier, and associates the correspondence table with the countermeasure identifier. and stored in the learning information storage unit 112 .
(1-2-2) When one correspondence information corresponds to one class identifier

The learning information acquisition unit 132 acquires two or more pieces of teacher data stored in the teacher data storage unit 111 for each action identifier. Next, the learning information acquiring unit 132 constructs a vector whose elements are one or more user attribute values of one or two or more pieces of teacher data for each action identifier and each class identifier. Next, the learning information acquisition unit 132 acquires a representative vector representing one or more vectors for each handling identifier and each class identifier. Next, the learning information acquisition unit 132 constructs a correspondence table having two or more pieces of correspondence information having representative vectors and class identifiers for each handling identifier and each class identifier, and associates the correspondence table with the handling identifier. and stored in the learning information storage unit 112 .
(2) Learning information for acquiring action identifiers

If the learning information is information for acquiring a countermeasure identifier, there is no need to classify the teacher data, and the classifying unit 131 is unnecessary.
(2-1) When learning information is a learner (2-1-1) When using effect information

The learning information acquisition unit 132 acquires effect information corresponding to each piece of teacher data from two or more pieces of each piece of teacher data held by the teacher data storage unit 111 . Next, the learning information acquisition unit 132 acquires one or more teacher data whose effect information satisfies predetermined effect conditions. Next, the learning information acquisition unit 132 uses one or more user identifiers of each of the one or more acquired teacher data as explanatory variables, and uses the action identifier corresponding to each of the one or more teacher data as objective variables, and performs machine learning. A learning process is performed, a learning device is acquired, and stored in the learning information storage unit 112 .

The effect condition is a condition for judging that the effect information is equal to or greater than a predetermined effect. The effect condition is, for example, if the effect information is greater than or equal to a threshold (eg, "decrease in blood glucose level by 10 or more", "decrease in systolic blood pressure by 20 or more", "target achievement level of 80% or more") or greater than a threshold (eg, " Blood glucose reduction greater than 10, systolic blood pressure reduction greater than 20, goal achievement greater than 70%, or a specific value (eg, effective, great improvement).
(2-1-2) When using effect information and satisfaction

The learning information acquisition unit 132 acquires the effect information for each teacher data and the degree of satisfaction possessed by each teacher data from two or more each of the teacher data stored in the teacher data storage unit 111 . Next, the learning information acquisition unit 132 acquires one or more teacher data whose effect information satisfies a predetermined effect condition and whose degree of satisfaction satisfies a predetermined satisfaction condition. Next, the learning information acquisition unit 132 uses one or more user identifiers of each of the one or more acquired teacher data as explanatory variables, and uses the action identifier corresponding to each of the one or more teacher data as objective variables, and performs machine learning. A learning process is performed, a learning device is acquired, and stored in the learning information storage unit 112 .

Note that the effect information for the teacher data is effect information acquired from information possessed by the teacher data or effect information possessed by the teacher data. The satisfaction level condition is a condition for determining that the satisfaction level is high, and is, for example, that the satisfaction level is equal to or greater than a threshold or larger than the threshold (satisfied).
(2-2) When learning information is a correspondence table (2-2-1) When effect information is used (2-2-1-1) When one correspondence information corresponds to one teacher data

The learning information acquisition unit 132 acquires effect information corresponding to each piece of teacher data from two or more pieces of teacher data stored in the teacher data storage unit 111 . Next, the learning information acquisition unit 132 acquires one or more teacher data whose effect information satisfies predetermined effect conditions. Next, the learning information acquiring unit 132 constructs a vector whose elements are the one or more user identifiers of the acquired one or more teacher data. Then, the learning information acquisition unit 132 constructs a correspondence table having two or more pieces of correspondence information having the vector and the handling identifier corresponding to the training data, and accumulates the correspondence table in the learning information storage unit 112 .
(2-2-1-2) When one correspondence information corresponds to one handling identifier

The learning information acquisition unit 132 acquires effect information corresponding to each piece of teacher data from two or more pieces of teacher data stored in the teacher data storage unit 111 . Next, the learning information acquisition unit 132 acquires one or more teacher data whose effect information satisfies predetermined effect conditions. Next, the learning information acquisition unit 132 constructs a vector whose elements are one or more user attribute values included in one or more pieces of teacher data for each action identifier. Next, the learning information acquisition unit 132 acquires a representative vector representing one or more vectors for each countermeasure identifier. Next, learning information acquisition section 132 constructs a correspondence table having two or more pieces of correspondence information each having a representative vector and a countermeasure identifier, and accumulates the correspondence table in learning information storage section 112 .
(2-2-2) When effect information and satisfaction level are used (2-2-2-1) When one correspondence information corresponds to one teacher data

The learning information acquisition unit 132 acquires the effect information and the degree of satisfaction corresponding to each piece of teacher data from two or more pieces of teacher data held by the teacher data storage unit 111 . Next, the learning information acquisition unit 132 acquires one or more teacher data whose effect information satisfies a predetermined effect condition and whose degree of satisfaction satisfies a predetermined satisfaction condition. Next, the learning information acquiring unit 132 constructs a vector whose elements are the one or more user identifiers of the acquired one or more teacher data. Then, the learning information acquisition unit 132 constructs a correspondence table having two or more pieces of correspondence information having the vector and the handling identifier corresponding to the training data, and accumulates the correspondence table in the learning information storage unit 112 .
(2-2-2-2) When one correspondence information corresponds to one handling identifier

The learning information acquisition unit 132 acquires effect information and satisfaction level corresponding to each teacher data from two or more each of the teacher data stored in the teacher data storage unit 111 . Next, the learning information acquisition unit 132 acquires one or more teacher data whose effect information satisfies a predetermined effect condition and whose degree of satisfaction satisfies a predetermined satisfaction condition. Next, the learning information acquisition unit 132 constructs a vector whose elements are one or more user attribute values included in one or more pieces of teacher data for each action identifier. Next, the learning information acquisition unit 132 acquires a representative vector representing one or more vectors for each countermeasure identifier. Next, learning information acquisition section 132 constructs a correspondence table having two or more pieces of correspondence information each having a representative vector and a countermeasure identifier, and accumulates the correspondence table in learning information storage section 112 .

The handling determining unit 133 acquires learning information, and uses the learning information and the user information received by the user information receiving unit 121 to identify one or more measures according to the result information of the user information. Get an identifier.

For example, using the user information and learning information received by the user information receiving unit 121, the handling determination unit 133 determines the class to which the user information belongs for each of two or more handling identifiers, and determines the class to which the user information belongs. A countermeasure identifier corresponding to a class having a large difference from the second result information (a class having a large countermeasure effect) and a countermeasure identifier corresponding to a class having a small difference (a class having a small countermeasure effect) are acquired separately. Acquiring them separately means, for example, sorting the action identifiers in descending order of difference, or acquiring only the action identifiers corresponding to the differences that satisfy the effect condition.

The handling determination unit 133 acquires a handling identifier by, for example, machine learning prediction processing. The handling determination unit 133 acquires a handling identifier using, for example, a correspondence table. An example of the processing of the handling determination unit 133 will be described below.
When the learning information is a learner (1-1) When the learner is a learner that acquires a class identifier (1-1-1) When there is one learner

The handling determining unit 133 acquires one or more attribute values of the user information accepted by the user information accepting unit 121 for each handling identifier. Next, the handling determining unit 133 constructs a vector whose elements are the one or more attribute values. Further, the handling determination unit 133 acquires a learning device corresponding to the handling identifier from the learning information storage unit 112 . Next, the handling determining unit 133 provides the vector and the learning device for each handling identifier to a module that performs prediction processing of machine learning, executes the module, and acquires a class identifier.

Next, the handling determination unit 133 associates the acquired class identifier with the handling identifier, and stores them in a buffer (not shown). Note that the handling determination unit 133 may acquire one or more handling identifiers corresponding to a class identifier that satisfies an acquisition condition (for example, an identifier of a class that has a large effect and a high level of satisfaction), and accumulate them in a buffer (not shown). . Acquisition conditions are conditions for acquiring a countermeasure identifier. Acquisition conditions are effect conditions based on effect information. Acquisition conditions may be effect conditions and satisfaction conditions. The effect condition is, for example, that the effect information is greater than or equal to a threshold. A satisfaction condition is a condition based on satisfaction, for example, satisfaction is greater than or equal to a threshold. Acquisition conditions are, for example, that the effect indicated by the effect information is the highest and the degree of satisfaction is the highest.
(1-1-2) When the learner is a binary classification learner with two or more

The handling determining unit 133 acquires one or more attribute values of the user information accepted by the user information accepting unit 121 for each handling identifier. Next, the handling determining unit 133 constructs a vector whose elements are the one or more attribute values. Further, the handling determination unit 133 acquires the learning device corresponding to the handling identifier and each class identifier from the learning information storage unit 112 . Next, the handling determination unit 133 supplies the configured vector and the acquired learning device to a module that performs prediction processing of machine learning for each handling identifier and each class identifier, executes the module, and identifies with the class identifier. Get a prediction result that indicates whether the class belongs to Note that the prediction result may include a score.

Next, the handling determination unit 133 acquires one or more class identifiers corresponding to the prediction result including the information "belongs to class".

Next, the handling determining unit 133 associates each handling identifier with the acquired class identifier and stores them in a buffer (not shown). Note that the handling determination unit 133 may acquire one or more handling identifiers corresponding to class identifiers that satisfy acquisition conditions, and store them in a buffer (not shown). The acquisition condition is, for example, that the effect information corresponding to the class identifier is information equal to or greater than a threshold (has a large effect).
(1-2) When the learning device is a learning device that acquires an action identifier (1-2-1) When there is one learning device

The handling determining unit 133 acquires one or more attribute values of the user information received by the user information receiving unit 121 for each handling identifier. Next, the handling determining unit 133 constructs a vector whose elements are the one or more attribute values. Also, the handling determination unit 133 acquires a learning device from the learning information storage unit 112 . Next, the countermeasure determination unit 133 provides the vector and the learning device to a module that performs prediction processing of machine learning, executes the module, and acquires a countermeasure identifier.
(1-2-2) When the learner is a binary classification learner with two or more

The handling determining unit 133 acquires one or more attribute values of the user information received by the user information receiving unit 121 for each handling identifier. Next, the handling determining unit 133 constructs a vector whose elements are the one or more attribute values. Further, the handling determination unit 133 acquires a learning device from the learning information storage unit 112 for each handling identifier. Next, for each countermeasure identifier, the countermeasure determination unit 133 provides the vector and the learning device to a module that performs machine learning prediction processing, executes the module, and determines whether the module belongs to the countermeasure identified by the countermeasure identifier. Obtain a prediction result that includes information indicating whether or not Then, the countermeasure determination unit 133 acquires the countermeasure identifier corresponding to the prediction result including the information indicating that "it belongs to the countermeasure identified by the countermeasure identifier".
(2) When the learning information is a correspondence table (2-1) When the correspondence table is a correspondence table for acquiring class identifiers

The handling determining unit 133 acquires one or more attribute values of the user information accepted by the user information accepting unit 121 for each handling identifier. Next, the handling determining unit 133 constructs a vector whose elements are the one or more attribute values. Next, the handling determination unit 133 determines correspondence information having a vector that is most similar to the vector, and acquires the class identifier of the correspondence information.

Next, the handling determination unit 133 associates the acquired class identifier with the handling identifier, and stores them in a buffer (not shown). Note that the handling determination unit 133 may acquire one or more handling identifiers corresponding to class identifiers that satisfy acquisition conditions, and store them in a buffer (not shown). Note that the acquisition condition is, for example, that the effect information corresponding to the class identifier is information equal to or greater than a threshold value (has a large effect).
(2-2) When the correspondence table is a correspondence table for obtaining a countermeasure identifier

The handling determining unit 133 acquires one or more attribute values of the user information accepted by the user information accepting unit 121 for each handling identifier. Next, the handling determining unit 133 constructs a vector whose elements are the one or more attribute values. Next, the handling determination unit 133 determines correspondence information having a vector that is most similar to the vector, and acquires a handling identifier included in the correspondence information.

Note that the handling determination unit 133 may acquire from the storage unit 11 the handling identifiers of all two or more candidate measures.

The basis information acquisition unit 134 uses one or more training data corresponding to each of the one or more countermeasure identifiers acquired by the countermeasure determination unit 133 and the user information received by the user information reception unit 121 to obtain the basis information. Get information. The basis information is information relating to the basis for recommending the countermeasure identified by the countermeasure identifier acquired by the countermeasure determination unit 133 .

The basis information acquisition unit 134 acquires, for example, the basis level corresponding to the class identifier associated by the classification unit 131. The grounds information acquisition unit 134 acquires effectiveness information using, for example, effect information for teacher data corresponding to the class identifier associated by the classification unit 131, and obtains information including the grounds level and the effectiveness information. Get information. It is preferable for the basis information acquisition unit 134 to acquire basis information including, for example, one or more types of information among basis level and reason information.

It is preferable that the grounds information acquisition unit 134 acquires satisfaction level information using the satisfaction level of the teacher data corresponding to the class to which the user information belongs, and acquires grounds information including reason information including the satisfaction level information. be.

You can call it evidence. Basis information can be called evidence information. The basis information has, for example, one or more information among basis level and reason information. Reason information has one or more information of effectiveness information and satisfaction information.

The rationale level is information that specifies the strength of the rationale for recommending a course of action. The basis level is, for example, one of "1", "2", "3", "4", and "5", but it is sufficient if it is sequential information such as "A", "B", and "C". .

The reason information is information about the reason for recommending the action. Effectiveness information is information about the effectiveness of countermeasures. Effectiveness information includes, for example, the average value of effectiveness when taking action, the percentage of users whose effectiveness is above the threshold when taking action (percentage of teacher data), and the effectiveness when taking action. It is the number of users above the threshold. Satisfaction level information is information related to the satisfaction level after taking action. Satisfaction information includes the average satisfaction after taking action, the ratio of users whose satisfaction is above the threshold after taking action (teaching data is also acceptable), and the satisfaction after taking action is above the threshold. is the number of users of

For example, for each of the one or more handling identifiers acquired by the handling determining unit 133, the basis information acquiring unit 134 uses one or more teacher data corresponding to the handling identifier and the user information received by the user information accepting unit 121. , to get the rationale level. The basis information acquisition unit 134 acquires, for example, a class identifier paired with one or more teacher data corresponding to the handling identifier acquired by the handling determination unit 133 . Next, the basis information acquisition unit 134 acquires, for example, the basis level corresponding to the class identifier. In this case, it is assumed that the class identifier is associated with the basis level and stored in the storage unit 11 .

The basis information acquisition unit 134 acquires effectiveness information, for example, for each measure identifier using one or more training data corresponding to the measure identifier acquired by the measure determination unit 133 . The basis information acquisition unit 134 acquires, for example, effect information corresponding to one or more pieces of teacher data corresponding to each coping identifier acquired by the coping determination unit 133 . Next, the basis information acquisition unit 134 acquires, for example, the effective number of persons, which is the number of effect information that satisfies the effect conditions, among the acquired effect information for each countermeasure identifier. Next, the basis information acquisition unit 134 acquires effectiveness information, which is a ratio of effectiveness, using, for example, the number of all teaching data items corresponding to the action identifier and the number of persons who are effective. Note that the effectiveness information may be the number of persons who are effective. The effect condition is information indicating that the effect information is highly effective, and for example, the effect information is equal to or greater than the threshold, the effect information is greater than the threshold, and the effect information is "effective".

The basis information acquisition unit 134 acquires satisfaction level information, for example, for each measure identifier using one or more teacher data corresponding to the measure identifier acquired by the measure determination unit 133 . The basis information acquisition unit 134 acquires, for example, satisfaction levels of one or more pieces of teacher data corresponding to each handling identifier acquired by the handling determination unit 133 . Next, the basis information acquisition unit 134 acquires, for example, the number of people who were satisfied, which is the number of degrees of satisfaction that satisfy the satisfaction level condition, among the acquired degrees of satisfaction, for each measure identifier. Next, the basis information acquisition unit 134 acquires satisfaction level information, which is the rate of satisfaction, using, for example, the number of all teacher data corresponding to the handling identifier and the number of people who were satisfied. The satisfaction level information may be the number of people who were satisfied.

The basis information acquisition unit 134 acquires effectiveness information and satisfaction level information, for example, for each measure identifier using one or more teacher data corresponding to the measure identifier acquired by the measure determination unit 133 . Then, it is preferable that the basis information acquisition unit 134 configure reason information having, for example, the acquired effectiveness information and the acquired satisfaction level information.

It is preferable for the basis information acquisition unit 134 to acquire recommended information for strongly recommending a measure identifier that satisfies the goal achievement condition. The goal achievement condition is that the degree of goal achievement is greater than or equal to a threshold. The goal achievement rate is the degree of achievement with respect to a goal, which is a user attribute value. The degree of goal achievement is, for example, one or more representative values (eg, average value, median value) of goal achievement rates, the number of users who have achieved their goals, and the percentage of users who have achieved their goals.

It is preferable for the basis information acquisition unit 134 to acquire basis information that is information indicating that there is no basis for the action identifier for which basis information could not be acquired.

Note that the basis information acquisition unit 134 usually associates the acquired basis information with the corresponding action identifier and temporarily stores it in a buffer (not shown).

The remuneration information acquisition unit 135 acquires remuneration information, which is information specifying a remuneration for recommending the user to take action, and is information corresponding to the basis information. The remuneration information is, for example, information recommending purchase of goods or services corresponding to the countermeasure. The remuneration information is, for example, information indicating the discount rate of the product or service corresponding to the handling.

The remuneration information acquisition unit 135 acquires remuneration information that specifies remuneration according to the basis level included in the basis information. The remuneration information acquisition unit 135 acquires, for example, remuneration information specifying a higher remuneration as the ground level included in the ground information is lower. The reward indicated by the reward information in such a case is the reward for the user's efforts to adopt the low basis level. Further, the remuneration information acquisition unit 135 acquires remuneration information specifying a higher remuneration, for example, as the ground level included in the ground information is higher. In such a case, it is a case where we want the user to take action with a high level of grounds. An administrator of the information processing device 1 may set such a relationship between the basis level and the remuneration information.

For example, the remuneration information acquisition unit 135 acquires remuneration information associated with the acquired basis level from the storage unit 11.

The output unit 14 outputs various information. Various types of information are, for example, a countermeasure identifier, basis information, and remuneration information.

Here, the output is usually transmission to the terminal device 2, but display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, other processing devices or other The concept may include delivery of the processing result to a program or the like.

The information output unit 141 outputs the countermeasure identifier acquired by the countermeasure determination unit 133 and the basis information acquired by the basis information acquisition unit 134 . It is preferable that the information output unit 141 also output the remuneration information acquired by the remuneration information acquisition unit 135 .

Various types of information are stored in the terminal storage unit 21 that constitutes the terminal device 2 . Various information is, for example, a user identifier. The user identifier may be the ID of the terminal device 2 or the like.

The terminal reception unit 22 receives various information and instructions. Various information and instructions are, for example, user information. Input means for various information and instructions may be anything, such as a microphone, a touch panel, a keyboard, a mouse, or a menu screen.

The terminal processing unit 23 performs various types of processing. Various types of processing are, for example, processing for creating a data structure for transmitting instructions and information received by the terminal receiving unit 22 . Further, various kinds of processing are, for example, processing to make a data structure for outputting information received by the terminal reception unit 25 .

The terminal transmission unit 24 transmits various information and instructions to the information processing device 1 . Various information and instructions are, for example, user information.

The terminal reception unit 25 receives various types of information from the information processing device 1 . Various types of information are, for example, a countermeasure identifier, basis information, and remuneration information.

The terminal output unit 26 outputs various information. Various types of information are, for example, a countermeasure identifier, basis information, and remuneration information.

The storage unit 11, the teacher data storage unit 111, the learning information storage unit 112, and the terminal storage unit 21 are preferably non-volatile recording media, but can also be realized with volatile recording media.

The process by which information is stored in the storage unit 11 or the like does not matter. For example, information may be stored in the storage unit 11 or the like via a recording medium, or information transmitted via a communication line or the like may be stored in the storage unit 11 or the like. Alternatively, information input via an input device may be stored in the storage unit 11 or the like.

The reception unit 12 and the user information reception unit 121 are preferably realized by wireless or wired communication means, but device drivers for input means such as means for receiving broadcasts, touch panels and keyboards, and menu screen It may be realized by control software or the like.

The processing unit 13, the learning information acquisition unit 132, the classification unit 131, the coping determination unit 133, the basis information acquisition unit 134, the remuneration information acquisition unit 135, and the terminal processing unit 23 can usually be implemented by a processor, memory, or the like. The processing procedure of the processing unit 13 and the like is normally realized by software, and the software is recorded in a recording medium such as a ROM. However, the processing unit 13 and the like may be realized by hardware (dedicated circuit). Note that the processor may be a CPU, MPU, GPU, or the like, and may be of any type.

The output unit 14, the information output unit 141, and the terminal transmission unit 24 are usually realized by wireless or wired communication means, but may be realized by broadcasting means.

The terminal reception unit 22 can be realized by device drivers for input means such as touch panels and keyboards, control software for menu screens, and the like.

The terminal receiving unit 25 is usually realized by wireless or wired communication means, but may be realized by means for receiving broadcast.

The terminal output unit 26 may or may not include output devices such as displays and speakers. The terminal output unit 26 can be realized by output device driver software, or by output device driver software and an output device.

Next, an operation example of information system A will be described. First, an operation example of the information processing apparatus 1 will be described with reference to the flowchart of FIG.

(Step S301) The reception unit 12 determines whether or not one or more teaching data has been received. If one or more teacher data is received, the process goes to step S302. If no teacher data is received, the process goes to step S303. It should be noted that the reception here is reception from the terminal device 2, for example.

(Step S302) The processing unit 13 accumulates the one or more teacher data accepted in step S301 in the teacher data storage unit 111. Return to step S301.

(Step S303) The processing unit 13 determines whether or not to create learning information. If it is determined to create learning information, the process goes to step S304, and if it is not determined to create learning information, the process goes to step S305. Note that the processing unit 13 determines to create learning information, for example, when the receiving unit 12 receives a learning information creation instruction. Also, the processing unit 13 determines to create the learning information, for example, when a predetermined time has come. Also, the processing unit 13 determines to create learning information, for example, when the number of training data items accumulated in the training data storage unit 111 is equal to or greater than a threshold. However, the condition for judging that the processing unit 13 creates learning information does not matter.

(Step S304) The learning information acquisition unit 132 performs learning information creation processing. Return to step S301. An example of learning information creation processing will be described with reference to the flowcharts of FIGS. 4, 7, 8, and 9. FIG.

(Step S305) The user information reception unit 121 determines whether user information has been received. If the user information has been received, the process goes to step S306, and if the user information has not been received, the process returns to step S301. It should be noted that the reception here is reception from the terminal device 2, for example.

(Step S306) The processing unit 13 performs output information acquisition processing. An example of output information acquisition processing will be described with reference to the flowchart of FIG.

(Step S307) The information output unit 141 outputs the output information acquired in step S306. Return to step S301. Note that the output here is transmission to the terminal device 2, for example.

In addition, in the flowchart of FIG. 3, the process ends when the power is turned off or an interrupt to end the process occurs.

Next, a first example of the learning information creation process in step S304 will be described using the flowchart of FIG. A first example of learning information creation processing is an example of acquiring a learning device for acquiring a class identifier.

(Step S401) The processing unit 13 substitutes 1 for the counter i.

(Step S402) The processing unit 13 determines whether or not the i-th action identifier exists. If the i-th action identifier exists, go to step S403, and if the i-th action identifier does not exist, return to the upper process.

(Step S403) The classification unit 131 classifies two or more teacher data corresponding to the i-th action identifier. An example of such classification processing will be described with reference to the flowchart of FIG.

(Step S404) The learning information acquisition unit 132 performs learning processing using the result of the classification processing in step S403, and acquires a learning device. An example of learning processing will be described with reference to the flowchart of FIG.

(Step S405) The learning information acquisition unit 132 stores the learning device acquired in step S404 in the learning information storage unit 112 in association with the i-th action identifier.

(Step S406) The processing unit 13 increments the counter i by 1. Return to step S402.

Next, an example of the classification processing in step S403 will be described using the flowchart of FIG.

(Step S501) The classification unit 131 acquires from the teacher data storage unit 111 all training data corresponding to the action identifier of interest (the i-th action identifier in S402).

(Step S502) The classification unit 131 substitutes 1 for the counter i.

(Step S503) The classification unit 131 determines whether or not i-th teacher data exists in the teacher data acquired in step S501. If the i-th teacher data exists, the process goes to step S504, and if the i-th teacher data does not exist, the process returns to the upper process.

(Step S504) The classification unit 131 acquires effect information for the i-th teacher data. For example, the classification unit 131 acquires the first result information and the second result information included in the i-th teacher data, and acquires the effect information regarding the difference between the first result information and the second result information. The classification unit 131 acquires, for example, effect information of i-th teacher data.

(Step S505) The classification unit 131 acquires the satisfaction level of the i-th teacher data.

(Step S506) Using the effect information acquired in step S504 and the satisfaction level acquired in step S505, the classification unit 131 acquires a class identifier corresponding to the effect information and the satisfaction level.

(Step S507) The classification unit 131 associates the i-th teacher data with the class identifier acquired in step S506.

(Step S508) The classification unit 131 increments the counter i by 1. Return to step S503.

In addition, in the flowchart of FIG. 5, the classification unit 131 determines the class of the training data using the effect information and the degree of satisfaction. However, the classification unit 131 may use one of the effect information and the degree of satisfaction to determine the class of the teacher data.

In addition, in the flowchart of FIG. 5, the classification unit 131 may classify two or more pieces of teacher data using the known cluster analysis algorithm described above.

Next, an example of the learning process in step S404 will be described using the flowchart of FIG.

(Step S601) The learning information acquisition unit 132 substitutes 1 for the counter i.

(Step S602) The learning information acquisition unit 132 determines whether the class identifier of the i-th class classified by the classification unit 131 in step S403 exists. If the i-th class identifier exists, go to step S603; otherwise, return to the upper process.

(Step S603) The learning information acquisition unit 132 acquires one or more positive examples. A positive example is teacher data associated with the i-th class identifier.

(Step S604) The learning information acquisition unit 132 acquires one or more negative examples. A negative example is teacher data that is not associated with the i-th class identifier. Teacher data not associated with the i-th class identifier is usually teacher data associated with a class identifier other than the i-th class identifier.

(Step S605) The learning information acquisition unit 132 performs machine learning learning processing using the one or more positive examples acquired in step S603 and the one or more negative examples acquired in step S604, and acquires a learning device. do. This learning device is a learning device for determining whether or not it belongs to the i-th class, and is a learning device that performs binary classification.

(Step S606) The learning information acquisition unit 132 stores the learning device acquired in step S605 in the learning information storage unit 112 in association with the action identifier of interest and the i-th class identifier.

(Step S607) The learning information acquisition unit 132 increments the counter i by 1. Return to step S602.

Note that in the flowchart of FIG. 6, the learning information acquisition unit 132 uses two or more teacher data corresponding to the action identifier of interest, uses one or more user attribute values possessed by each teacher data as explanatory variables, and class identifiers as explanatory variables. A machine learning learning process may be performed to obtain a learning device using an objective variable, and the obtained learning device may be stored in the learning information storage unit 112 in association with the action identifier of interest. In this case, one learner corresponds to one action identifier. Such a learner is a learner for predicting any of the class identifiers.

Next, a second example of the learning information creation process in step S304 will be described using the flowchart of FIG. A second example of learning information creation processing is an example of acquiring a learning device for acquiring a countermeasure identifier. Also, the learning device acquired in the second example is a learning device for determining whether or not to take the action identified by the corresponding action identifier, and is acquired for each action. Such a learner is a learner that performs binary classification.

(Step S701) The learning information acquisition unit 132 substitutes 1 for the counter i.

(Step S702) The learning information acquisition unit 132 determines whether or not the i-th action identifier exists. If the i-th countermeasure identifier exists, go to step S703; otherwise, return to the upper process.

(Step S703) The learning information acquisition unit 132 acquires two or more teacher data corresponding to the i-th action identifier from the teacher data storage unit 111.

(Step S704) The learning information acquisition unit 132 acquires one or more positive examples from the two or more teacher data acquired in step S703. A positive example is teacher data that meets the positive example condition.

It should be noted that the positive case condition is a condition for determining that action should be taken. A positive example condition may be one or two of satisfying an effect condition and satisfying a satisfaction condition. A positive example condition is, for example, a condition based on one or more types of information among effect information and satisfaction. Positive example conditions include, for example, "effect information is greater than or equal to the threshold value", "satisfaction is greater than or equal to the threshold value", "effect information is greater than or equal to the threshold value and satisfaction is greater than the threshold value greater than or equal to a threshold”.

(Step S705) The learning information acquisition unit 132 acquires one or more negative examples from the two or more teacher data acquired in step S703. Negative examples are training data that do not meet the positive example conditions.

(Step S706) The learning information acquisition unit 132 acquires a learning device by performing machine learning learning processing using the one or more positive examples acquired in step S704 and the one or more negative examples acquired in step S705. .

(Step S707) The learning information acquisition unit 132 stores the learning device acquired in step S706 in the learning information storage unit 112 in association with the action identifier of interest.

(Step S708) The learning information acquisition unit 132 increments the counter i by 1. Return to step S702.

Next, a third example of the learning information creation process in step S304 will be described using the flowchart of FIG. A third example of the learning information creation process is an example of acquiring one learning device for acquiring a countermeasure identifier. Note that such a learning device is usually a learning device for performing multilevel classification.

(Step S801) The learning information acquiring unit 132 acquires from the teaching data storage unit 111 one or more teacher data that match the positive case condition.

(Step S802) The learning information acquisition unit 132 gives the one or more teacher data acquired in step S801 to the learning module for machine learning, and acquires a learning device.

(Step S803) The learning information acquisition unit 132 accumulates the learners learned in step S802 in the learning information storage unit 112. Return to upper process.

Next, a fourth example of the learning information creation process in step S304 will be described using the flowchart of FIG. A fourth example of learning information creation processing creates a correspondence table for each countermeasure identifier. In the flow chart of FIG. 9, the description of the same steps as in the flow chart of FIG. 4 will be omitted.

(Step S901) The learning information acquisition unit 132 substitutes 1 for the counter j.

(Step S902) The learning information acquisition unit 132 determines whether or not the j-th class identifier corresponding to the i-th action identifier exists. If the j-th class identifier exists, go to step S903, otherwise go to step S907.

(Step S903) The learning information acquisition unit 132 acquires one or more teacher data corresponding to the i-th action identifier and the j-th class identifier.

(Step S904) The learning information acquisition unit 132 acquires a representative vector of vectors composed of one or more teacher data.

(Step S905) The learning information acquisition unit 132 temporarily accumulates the representative vector acquired in step S904 in association with the j-th class identifier.

(Step S906) The learning information acquisition unit 132 increments the counter j by 1. Return to step S902.

(Step S907) The learning information acquisition unit 132 constructs a correspondence table having two or more pieces of correspondence information having the representative vectors and class identifiers acquired in step S905, associates the i-th measure identifier with the correspondence table are stored in the learning information storage unit 112 .

(Step S908) The learning information acquisition unit 132 increments the counter i by 1. Return to step S402.

Next, an example of the output information acquisition process in step S306 will be described using the flowchart of FIG.

(Step S1001) The handling determining unit 133 acquires handling information. An example of handling information acquisition processing will be described with reference to flowcharts of FIGS. 11, 12, 13, and 14. FIG.

(Step S1002) The basis information acquisition unit 134 acquires basis information. An example of basis information processing will be described with reference to the flowchart of FIG. 15 .

(Step S1003) The remuneration information acquisition unit 135 acquires remuneration information. An example of reward information processing will be described using the flowchart of FIG. 16 .

(Step S1004) The processing unit 13 forms output information using the countermeasure information, ground information, and remuneration information. Return to upper process.

Next, an example of the countermeasure information acquisition process in step S1001 will be described using the flowchart of FIG. In addition, in the flowchart of FIG. 11, a learner is used for each measure and for each class.

(Step S1101) The handling determination unit 133 acquires one or more user attribute values included in the received user information.

(Step S1102) The handling determination unit 133 substitutes 1 for the counter i.

(Step S1103) The handling determination unit 133 determines whether or not the i-th handling identifier exists. If the i-th countermeasure identifier exists, go to step S1104; otherwise, return to the upper process.

(Step S1104) The handling determination unit 133 substitutes 1 for the counter j.

(Step S1105) The handling determination unit 133 determines whether or not the j-th class identifier exists. If the j-th class identifier exists, go to step S1106; if not, go to step S1111.

(Step S1106) The handling determination unit 133 acquires from the learning information storage unit 112 the learner corresponding to the i-th handling identifier and the j-th class identifier.

(Step S1107) The handling determination unit 133 uses the learner acquired in step S1106 and one or more user attribute values acquired in step S1101 to perform machine learning prediction processing and acquire a prediction result. Note that the prediction result includes information as to whether or not it belongs to the class identified by the j-th class identifier. Prediction results preferably include scores.

(Step S1108) If the prediction result obtained in step S1107 is a prediction result that "belongs to the class identified by the j-th class identifier", the handling determination unit 133 goes to step S1109, does not belong to the class identified by the class identifier", go to step S1110.

(Step S1109) The handling determination unit 133 temporarily stores the j-th class identifier in a buffer (not shown) in association with the i-th handling identifier.

(Step S1110) The handling determination unit 133 increments the counter j by 1. Return to step S1105.

(Step S1111) The handling determination unit 133 increments the counter i by 1. Return to step S1103.

It should be noted that in the flowchart of FIG. 11, the class identifier was determined for each countermeasure identifier. Then, the handling determination unit 133 may store only the handling identifier corresponding to the determined class identifier in the storage unit 11 only when the determined class identifier satisfies the acquisition condition.

Next, an example of the countermeasure information acquisition process in step S1001 will be described using the flowchart of FIG. In the flowchart of FIG. 12, description of the same steps as in the flowchart of FIG. 11 will be omitted. In addition, in the flowchart of FIG. 12, the learning device is for determining whether or not to take action, and a learning device for each action is used.

(Step S<b>1201 ) The handling determination unit 133 acquires the learning device corresponding to the i-th handling identifier from the learning information storage unit 112 .

(Step S1202) The handling determination unit 133 uses the learner acquired in step S1201 and one or more user attribute values acquired in step S1101 to perform machine learning prediction processing and acquire a prediction result. Note that the prediction result includes information as to whether the countermeasure identified by the j-th countermeasure identifier is effective (satisfied). Prediction results preferably include scores.

(Step S1203) If the prediction result in step S1202 includes "satisfy" (eg, "1"), the handling determination unit 133 proceeds to step S1204; Go to step S1207. Note that "satisfied" in the prediction result indicates that the action identified by the action identifier should be taken.

(Step S1204) The handling determination unit 133 acquires the score of the prediction process in step S1202.

(Step S1205) The handling determination unit 133 determines whether the score obtained in step S1204 satisfies the conditions. If the condition is satisfied, go to step S1206, otherwise go to step S1207. The condition is that the score is high, for example, "the score is greater than or equal to the threshold" and "the score is greater than the threshold".

(Step S1206) The handling determination unit 133 accumulates the j-th handling identifier in the storage unit 11. FIG. It is preferable that the handling determination unit 133 also accumulates the scores acquired in step S1204.

(Step S1207) The handling determination unit 133 increments the counter i by 1. Return to step S1105.

Next, an example of the countermeasure information acquisition process in step S1001 will be described using the flowchart of FIG. In the flowchart of FIG. 13, the description of the same steps as in the flowchart of FIG. 11 will be omitted. Note that in the flowchart of FIG. 13, a learning device that outputs a countermeasure identifier is used.

(Step S<b>1301 ) The handling determination unit 133 acquires a learning device from the learning information storage unit 112 .

(Step S1302) The handling determination unit 133 uses the learner acquired in step S1301 and one or more user attribute values acquired in step S1101 to perform machine learning prediction processing and acquire a prediction result. Note that the prediction result includes a countermeasure identifier. Prediction results preferably include scores.

(Step S1303) The handling determination unit 133 accumulates the handling identifier acquired in step S1302. Return to upper process. Here, it is preferable that the handling determination unit 133 also accumulates scores.

Next, an example of the countermeasure information acquisition process in step S1001 will be described using the flowchart of FIG. In the flowchart of FIG. 14, description of the same steps as in the flowchart of FIG. 11 will be omitted. In addition, in the flowchart of FIG. 14, a correspondence table for acquiring class identifiers is used.

(Step S1401) The handling determination unit 133 constructs a vector whose elements are one or more user attribute values acquired in step S1101. Next, the countermeasure determining unit 133 determines correspondence information having a vector that is most similar to the vector from the correspondence table of the learning information storage unit 112 that is paired with the i-th countermeasure identifier.

(Step S1402) The handling determination unit 133 acquires the class identifier included in the correspondence information determined in step S1401.

(Step S1403) The handling determination unit 133 determines whether the class identifier acquired in step S1402 satisfies the conditions. If the condition is satisfied, go to step S1404, otherwise go to step S1405. The condition here is that the class identifier is one of one or more predetermined class identifiers (for example, an identifier of a class that satisfies the effect condition).

(Step S1404) The handling determining unit 133 stores the class identifier acquired in step S1402 and the i-th handling identifier as a pair.

(Step S1405) The handling determination unit 133 increments the counter i by 1. Return to step S1103.

In addition, in the flowchart of FIG. 14, a correspondence table for acquiring the countermeasure identifier may be used. In such a case, in step S1402, the handling determination unit 133 acquires and accumulates the handling identifier included in the correspondence information determined in step S1401. Also, in such a case, steps S1403 and S1404 are unnecessary.

Next, an example of the basis information processing in step S1002 will be described using the flowchart of FIG.

(Step S1501) The basis information acquisition unit 134 substitutes 1 for the counter i.

(Step S1502) The basis information acquisition unit 134 determines whether or not the i-th measure identifier exists among the measure identifiers acquired in step S1002. If the i-th countermeasure identifier exists, go to step S1503; otherwise, return to the upper process.

(Step S1503) The basis information acquisition unit 134 acquires original information. Note that the original information is information used when acquiring the basis level. The original information is, for example, a class identifier corresponding to the handling identifier and a score corresponding to the handling identifier.

(Step S1504) The basis information acquisition unit 134 acquires the basis level corresponding to the original information acquired in step S1503.

Note that the basis information acquisition unit 134 acquires, for example, the basis level corresponding to the class identifier acquired in step S1503. In such a case, the storage unit 11 stores two or more class identifiers and evidence levels paired with each class identifier.

Also, the basis information acquisition unit 134 acquires, for example, the basis level corresponding to the score acquired in step S1503. In such a case, the storage unit 11 stores the ground level paired with each condition of two or more scores. The score condition is usually information indicating the score range. Note that the score is a score obtained in prediction processing of machine learning.

(Step S1505) The basis information acquisition unit 134 acquires one or more teacher data from which the i-th measure identifier is acquired.

(Step S1506) The basis information acquisition unit 134 acquires effect information corresponding to each teacher data using one or more of each teacher data acquired in step S1505. Next, the basis information acquisition unit 134 acquires effectiveness information using one or more effect information, associates it with the i-th countermeasure identifier, and stores it in a buffer (not shown).

(Step S1507) The basis information acquisition unit 134 acquires the degree of satisfaction from each of the one or more teacher data acquired in step S1505.

(Step S1508) The basis information acquisition unit 134 acquires satisfaction level information using one or more satisfaction levels acquired in step S1507, associates it with the i-th measure identifier, and stores it in a buffer (not shown).

(Step S1509) The basis information acquisition unit 134 increments the counter i by 1. Return to step S1502.

Although the basis level, effect information, and satisfaction level information are acquired in the flowchart of FIG. 15, only one or two types of information may be acquired.

Next, an example of the reward information processing in step S1003 will be described using the flowchart of FIG.

(Step S1601) The remuneration information acquisition unit 135 substitutes 1 for the counter i.

(Step S1602) The remuneration information acquisition unit 135 determines whether or not the i-th action identifier exists. If the i-th countermeasure identifier exists, go to step S1603; otherwise, return to the upper process.

(Step S1603) The remuneration information acquisition unit 135 determines whether or not the i-th action identifier matches the remuneration conditions. If the remuneration conditions are met, the process goes to step S1604, and if the remuneration conditions are not met, the process goes to step S1606.

For example, the remuneration information acquisition unit 135 uses one or more of the i-th coping identifier, the basis level associated with the i-th coping identifier, the effect information, and the satisfaction level information to determine whether the i-th coping identifier is the remuneration condition. It is determined whether or not the

It should be noted that the remuneration conditions are the conditions for obtaining remuneration information. The remuneration conditions are, for example, ``that the remuneration information associated with the i-th action identifier is stored in the storage unit 11'', and ``the grounds level associated with the i-th action identifier indicates that there is no grounds. information", "the ground level associated with the i-th action identifier is equal to or less than the threshold value or smaller than the threshold value", "the effect indicated by the effect information associated with the i-th action identifier is low enough to satisfy the conditions "that the degree of satisfaction indicated by the satisfaction level information associated with the i-th measure identifier is so low as to satisfy the condition".

(Step S1604) The remuneration information acquisition unit 135 acquires remuneration information from the storage unit 11. The remuneration information acquisition unit 135 acquires remuneration information associated with the i-th action identifier from the storage unit 11, for example. The remuneration information acquisition unit 135 acquires, for example, remuneration information associated with remuneration conditions from the storage unit 11 .

(Step S1605) The remuneration information acquisition unit 135 temporarily stores the remuneration information acquired in step S1604 as remuneration information to be output in a buffer (not shown) in association with the i-th action identifier.

(Step S1606) The remuneration information acquisition unit 135 increments the counter i by 1. Return to step S1602.

Next, an operation example of the terminal device 2 will be described. The terminal reception unit 22 of the terminal device 2 receives user information. Next, the terminal processing unit 23 configures user information to be transmitted using the user information. The terminal transmission unit 24 transmits the user information to the information processing device 1 . Next, the terminal reception unit 25 receives output information from the information processing device 1 in response to transmission of the user information. Next, the terminal processing unit 23 configures information to be output using the output information. The terminal output unit 26 outputs the configured information. The output information includes, for example, a countermeasure identifier, basis information, and remuneration information.

Also, the terminal reception unit 22 of the terminal device 2 may receive teacher data. In such a case, the terminal processing unit 23 uses the teacher data to compose the teacher data to be transmitted. Next, the terminal transmission unit 24 transmits the teacher data to the information processing device 1 .

A specific operation example of the information system A in this embodiment will be described below.

Assume that the teacher data storage unit 111 of the information processing device 1 stores a teacher data management table having two or more pieces of teacher data transmitted from the terminal device 2 . The teacher data is information about a user who has taken some kind of action, and has first result information and second result information. This teaching data management table is shown in FIG. The training data management table manages two or more records having "ID", "treatment identifier", "first result information", "second result information", "gender", "age", "height", "weight", and "response information". It is "Answer information" is an answer to a questionnaire for the user, and has "effort information", "lifestyle information", "goals", and "satisfaction" here. Also, the "first result information" is the inspection result before the treatment identified by the treatment identifier is performed. "Second result information" is the inspection result after taking the treatment identified by the treatment identifier. The test result here is the systolic blood pressure. "Target" is the systolic blood pressure that the user aims for. The “satisfaction level” is the user's degree of satisfaction with the action identified by the action identifier.

It is also assumed that the storage unit 11 of the information processing device 1 stores countermeasure identifiers "product A (reduced salt soy sauce)", "product B (reduced salt miso)" and "product C (yogurt)". Further, here, the action corresponding to "product A" is a program (program A) in which product A is used continuously for one month, and the action corresponding to "product B" is to continue using product B for one month. It is assumed that the program (program B) is a program (program B) that uses product C continuously for two months, and that the measure corresponding to "product C" is a program (program C) that uses product C continuously for two months. The program refers to continuous ingestion of products, services, etc., and is also called a challenge program.

Further, the storage unit 11 stores the basis level "3" associated with the class identifier "class A", the basis level "2" associated with the class identifiers "class B" and "class D", the class identifier " Assume that a basis level determination table is stored that has a basis level "1" associated with class C" and a basis level "0" associated with the class identifier "none".

It should be noted that the basis level determination table may be a table for judging the basis level using one or more information among the effectiveness information and the satisfaction level information, as shown in FIG. The basis level judgment table has "basis level" and "judgment condition". The "judgment condition" is a condition for determining the basis level. That is, the basis information acquisition unit 134 may acquire the basis level using one or more of the effectiveness information and the satisfaction level information. Also, it is assumed that the judgment condition of "foundation level = 1 to 3" is applied, for example, when the number of training data is equal to or greater than a threshold (for example, 100) or more than the threshold. In addition, it is assumed that "ground level = 1 to 3" in Fig. 18 is applied in the order of "ground level = 3", "ground level = 2", and "ground level = 1".

It is also assumed that the storage unit 11 stores the target achievement condition "target achievement rate >= 80%". Then, it is assumed that the basis information acquisition unit 134 acquires recommendation information for strongly recommending a measure identifier that satisfies the target achievement condition. It is assumed here that the recommended information is "required" (for example, "1"). Note that "necessary" means that it is necessary to take the action identified by the action identifier in order to achieve the goal. Further, it is assumed that the basis information acquisition unit 134 acquires recommended information “unnecessary” (for example, “0”) for a measure identifier that does not satisfy the goal achievement condition.

It is also assumed that the storage unit 11 stores a remuneration condition "base level = 0" and remuneration information "30% OFF" corresponding to the remuneration condition. In other words, 30% off remuneration information (information indicating that the product can be purchased with a 30% discount) is presented for the product corresponding to "ground level=0".

In this situation, the classification unit 131 of the information processing device 1 acquires the first result information, the second result information, the goal, and the degree of satisfaction of each teacher data in FIG. 17 for each action identifier. Next, the classification unit 131 acquires effect information using the first result information, the second result information, and the goal for each treatment identifier and each training data. The effect information is the target achievement rate here. The target achievement rate is calculated by, for example, "(first result information-second result information)/(first result information-target)*100(%)".

Next, the classification unit 131 classifies the training data using the effect information and the degree of satisfaction for each treatment identifier. Here, for each measure identifier, the classification unit 131 sets the class identifier of teacher data whose effect information is 60% or more and whose satisfaction level is “4 or 5” to “class A”, and the effect information is 60%. The class identifier of the teacher data whose satisfaction level is "4 or 5" is "class B", the effect information is less than 60%, and the satisfaction level is "1 or 2 or 3". Assume that the teacher data is classified with the identifier as "class C" and the class identifier of the teacher data whose effect information is 60% or more and the degree of satisfaction is "1, 2 or 3" as "class D". FIG. 19 is a diagram showing the concept of such teacher data classification.

Next, the learning information acquisition unit 132 retrieves “first result information”, “gender”, “age”, “height”, “weight”, “lifestyle information”, “goal” from the training data management table of FIG. 17 for each coping identifier. is obtained for each training data, and the "first result information", "gender", "age", "height", "weight", "lifestyle information", and "goal" are used as explanatory variables, and a vector is constructed with the class identifier as the objective variable. do.

Next, the learning information acquisition unit 132 performs machine learning learning processing using two or more vectors for each handling identifier, configures a learning device for each handling identifier, and constructs a learning device for each handling identifier, It is stored in the learning information storage unit 112 in association with the countermeasure identifier. This learning device is a learning device for predicting a class identifier using a vector having "first result information", "gender", "age", "height", "weight", "lifestyle information", and "goal". be.

In the above situation, user A sends "<first result information> 183 <sex> male <age> 68 <height> 175 <weight> 88 <lifestyle information> smoking <goal> 140" to the terminal device 2. It is assumed that the user information that has Next, the terminal device 2 receives the user information and transmits the user information to the information processing device 1 .

Next, the user information reception unit 121 of the information processing device 1 receives the user information from the terminal device 2 of the user A.

Next, the processing unit 13 performs output information acquisition processing as follows. That is, first, the handling determination unit 133 determines a class identifier for each of the handling identifiers “product A (low-salt soy sauce),” “product B (low-salt miso),” and “product C (yogurt).” That is, first, the countermeasure determination unit 133 acquires from the learning information storage unit 112 a learning device paired with the countermeasure identifier “Product A (low-salt soy sauce)”. Next, the handling determination unit 133 determines the user attribute value "<first result information> 183 <sex> male <age> 68 <height> 175 <weight> 88 <lifestyle information> smoking <goal> 140 ” and the obtained learner are given to a prediction module that performs prediction processing of machine learning, the prediction module is executed, and the class identifier “class A” is obtained. Similarly, the countermeasure determination unit 133 acquires from the learning information storage unit 112 a learning device paired with the countermeasure identifier “product B (low-salt miso)”. Next, the handling determination unit 133 gives the two or more user attribute values included in the user information and the acquired learner to a prediction module that performs machine learning prediction processing, executes the prediction module, and uses the class identifier “class D" is acquired. It is assumed that the handling determination unit 133 has failed to acquire a learning device paired with the handling identifier “product C (yogurt)” from the learning information storage unit 112 .

Next, the basis information acquisition unit 134 acquires from the storage unit 11 the basis level "3" paired with the class identifier "class A" corresponding to the countermeasure identifier "product A (reduced salt soy sauce)". Further, the basis information acquisition unit 134 acquires from the storage unit 11 the basis level “2” paired with the class identifier “class D” corresponding to the countermeasure identifier “product B (low-salt miso)”. Furthermore, the basis information acquisition unit 134 acquires from the storage unit 11 the basis level “0” paired with the handling identifier “product C (yogurt)” for which the class could not be determined.

Next, the basis information acquisition unit 134 acquires one or more training data corresponding to each handling identifier from which the class identifier has been acquired and the handling identifier and the class identifier. Then, the basis information acquisition unit 134 acquires effect information of each teacher data using the acquired one or more teacher data. Next, the basis information acquisition unit 134 acquires “effectiveness information” that is the average of the effect information of each teacher data. Assume that the basis information acquisition unit 134 acquires the effectiveness information “80%” from one or more training data corresponding to the measure identifier “product A (reduced salt soy sauce)” and the class identifier “class A”. . Further, the basis information acquisition unit 134 acquires the degree of satisfaction of each of the acquired one or more teacher data. Next, it is assumed that the basis information acquisition unit 134 acquires satisfaction level information “60%”, which is the ratio of teacher data having a satisfaction level of “4” or “5” in the same class.

Similarly, the basis information acquisition unit 134 acquires one or more training data corresponding to the class identifier "class D" corresponding to the handling identifier "product B (low-salt miso)", and uses the training data to obtain valid Assume that sex information "80%" and satisfaction level information "30%" have been acquired.

Also, the basis information acquisition unit 134 acquires the goal achievement condition "goal achievement rate >= 80%" from the storage unit 11. Next, the basis information acquiring unit 134 acquires, for each measure identifier, the measure identifier “product A (reduced salt soy sauce)” that satisfies the target achievement condition by averaging the target achievement rate of the one or more teacher data for the class identifier corresponding to the measure identifier. )”. Next, the basis information acquisition unit 134 acquires the recommendation information "required" in association with the countermeasure identifier "product A (low-salt soy sauce)". Further, the basis information acquiring unit 134 acquires the recommendation information “unnecessary” in association with the countermeasure identifiers “product B (low-salt miso)” and “product C (yogurt)” that do not satisfy the goal achievement condition.

Also, the basis information acquisition unit 134 could not acquire the effectiveness information and satisfaction level information corresponding to the measure identifier "product C (yogurt)". This is because the basis level is "0".

Next, the remuneration information acquisition unit 135 refers to the remuneration condition “basis level=0” in the storage unit 11, and determines that the handling identifier “product C (yogurt)” corresponding to the “basis level=0” Acquire OFF reward information.

Next, the processing unit 13 configures output information using the acquired coping information, basis information, recommended information, and remuneration information. Next, the information output unit 141 transmits the acquired output information to the terminal device 2 .

Next, the terminal device 2 receives and outputs the output information. An example of such an output is shown in FIG. In FIG. 20, 2001 is the basis level, which is called "evidence level" here. Further, 2002 is evidence information having effectiveness information and satisfaction level information, and is given a label of "Reason". 2003 is recommended information with a label of "to achieve ToBe". Further, 2004 is remuneration information, labeled as "incentive".

As described above, according to the present embodiment, it is possible to determine an appropriate course of action for the inspection result.

Also, according to the present embodiment, when proposing measures to deal with test results, the grounds for the proposal can be presented.

In addition, according to the present embodiment, when proposing measures to deal with test results, it is possible to clearly indicate that there is no basis for the proposal.

Furthermore, according to the present embodiment, it is possible to provide the user with an incentive to take action when proposing a course of action for the inspection result.

Also, the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Also, this software may be recorded on a recording medium such as a CD-ROM and distributed. Note that this also applies to other embodiments in this specification. The software that implements the information processing apparatus according to the present embodiment is the following program. In other words, the program identifies a computer as a user information reception unit that receives user information having one or more user attribute values including result information that specifies the test results related to the living body of one user, and a countermeasure taken by the user. Two or more training data associated with a handling identifier, including first result information specifying the test result before the handling and second result information specifying the inspection result of the handling Acquiring learning information from a learning information storage unit storing learning information based on two or more teacher data having two or more user attribute values, and acquiring the learning information and the user information received by the user information receiving unit. , a handling determination unit that acquires a handling identifier that identifies a handling corresponding to the result information contained in the user information, and one or more teacher data corresponding to the handling identifier acquired by the handling determination unit and the user information a grounds information acquisition unit for acquiring grounds information relating to grounds for recommending the handling identified by the handling identifier acquired by the handling determination unit, using the user information received by the reception unit; A program for functioning as an information output unit that outputs the countermeasure identifier and the basis information acquired by the basis information acquisition unit.

Also, FIG. 21 shows the appearance of a computer that executes the programs described in this specification and implements the information processing apparatus 1 and the like of the various embodiments described above. The embodiments described above may be implemented in computer hardware and computer programs running thereon. FIG. 21 is an overview diagram of this computer system 300, and FIG. 22 is a block diagram of the system 300. As shown in FIG.

In FIG. 21, computer system 300 includes computer 301 including a CD-ROM drive, keyboard 302 , mouse 303 and monitor 304 .

22, a computer 301 includes a CD-ROM drive 3012, an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, a ROM 3015 for storing programs such as a boot-up program, It includes a RAM 3016 connected and for temporarily storing application program instructions and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs and data. Although not shown here, computer 301 may also include a network card that provides connection to a LAN.

A program that causes the computer system 300 to execute the functions of the information processing apparatus 1 of the embodiment described above may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. . Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored in hard disk 3017 . Programs are loaded into RAM 3016 during execution. The program may be loaded directly from CD-ROM 3101 or network.

The program does not necessarily include an operating system (OS) that causes the computer 301 to execute the functions of the information processing apparatus 1 of the embodiment described above, or a third-party program. A program need only contain those parts of instructions that call the appropriate functions (modules) in a controlled manner to produce the desired result. How the computer system 300 operates is well known and will not be described in detail.

In the above program, the step of transmitting information, the step of receiving information, etc. are performed by hardware. processing) are not included.

Also, the computer that executes the above program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

In addition, in each of the above embodiments, it goes without saying that two or more communication means existing in one device may be physically realized in one medium.

Also, in each of the above embodiments, each process may be implemented by centralized processing by a single device, or may be implemented by distributed processing by a plurality of devices.

It goes without saying that the present invention is not limited to the above embodiments, and that various modifications are possible and are also included within the scope of the present invention.

As described above, the information processing apparatus according to the present invention has the effect of being able to present the grounds for the proposal when proposing a countermeasure for the result of an examination. It is useful as a server or the like that outputs .

Claims

a user information reception unit that receives user information having one or more user attribute values including result information specifying test results related to the living body of one user;
Two or more teaching data associated with a handling identifier that identifies a handling performed by a user, and specifies first result information that specifies inspection results before the handling and inspection results as a result of carrying out the handling. Acquiring learning information from a learning information storage unit storing learning information based on two or more teacher data having two or more user attribute values including second result information, and receiving the learning information and the user information a countermeasure determination unit that acquires a countermeasure identifier that identifies a countermeasure corresponding to the result information included in the user information, using the user information received by the unit;
A countermeasure identified by the countermeasure identifier acquired by the countermeasure determination unit using one or more teacher data corresponding to the countermeasure identifier acquired by the countermeasure determination unit and the user information received by the user information reception unit a grounds information acquisition unit that acquires grounds information on the grounds for recommending
An information processing apparatus comprising: an information output unit that outputs the countermeasure identifier acquired by the countermeasure determination unit and the basis information acquired by the basis information acquisition unit.
The basis information acquisition unit
Grounds for specifying the degree of strength of grounds for recommending the countermeasures using one or more training data corresponding to the countermeasure identifiers acquired by the countermeasure determination unit and the user information received by the user information reception unit Reason information, which is information indicating the level and the reason for recommending the above-mentioned countermeasure, and is information including effectiveness information about the effectiveness when the countermeasure is performed or satisfaction information about the degree of satisfaction after performing the countermeasure 2. The information processing apparatus according to claim 1, which acquires basis information including one or more types of information among them.
The basis information acquisition unit
3. The information processing apparatus according to claim 1, wherein when the basis information cannot be acquired, the basis information that is information indicating that there is no basis is acquired.
further comprising a remuneration information acquiring unit that acquires remuneration information that is information specifying a remuneration for recommending the user to take the action and that is information corresponding to the basis information;
The information output unit
2. The information processing apparatus according to claim 1, wherein said remuneration information acquired by said remuneration information acquisition unit is also output.
The remuneration information acquisition unit
5. The information processing apparatus according to claim 4, wherein remuneration information specifying a remuneration according to a basis level included in said basis information is acquired.
For each action identifier, the two or more teacher data are divided into two by using effect information, which is information obtained using the second result information possessed by each of the two or more teacher data, and is information relating to the effect of the action. Classifying into the above classes, further comprising a classifying unit that associates each of the two or more teacher data with a class identifier that identifies the class,
The handling determination unit
determining a class to which the user information belongs for each of the two or more action identifiers using the user information received by the user information receiving unit and the learning information based on the two or more teacher data; 2. The information processing apparatus according to claim 1, wherein said handling identifier corresponding to a class having a large difference between said result information and said second result information and said handling identifier corresponding to said class having a small difference are acquired separately.
The training data also includes user satisfaction as a result of taking the action,
The classification unit
Classify the two or more teacher data into two or more classes using the effect information and the satisfaction level for each of the two or more teacher data for each coping identifier, and classify the two or more teacher data into two or more classes. 7. The information processing apparatus according to claim 6, associated with a class identifier that identifies said class.
Each of the two or more classes classified by the classification unit is associated with a basis level based on effect information for the teacher data corresponding to the class,
The basis information acquisition unit
Effect, which is information obtained by obtaining the basis level corresponding to the class and using the second result information included in the teacher data corresponding to the class determined by the handling determination unit, and is information relating to the effect of handling. 7. The information processing apparatus according to claim 6, wherein validity information is obtained using information, and base information including the base level and reason information that is information including the validity information is obtained.
The training data also includes user satisfaction as a result of taking the action,
The classification unit
Classify the two or more teacher data into two or more classes using the effect information and the satisfaction level for each of the two or more teacher data for each coping identifier, and classify the two or more teacher data into two or more classes. associated with a class identifier that identifies the class;
The basis information acquisition unit
9. The information processing apparatus according to claim 8, wherein satisfaction level information is obtained using the satisfaction level of teacher data corresponding to said class to which said user information belongs, and base information including reason information including said satisfaction level information is obtained. .
Learning information for acquiring learning information using two or more teacher data having one or more user attribute values satisfying a similarity condition with the one or more user attribute values contained in the user information received by the user information receiving unit. further comprising an acquisition unit;
2. The information processing apparatus according to claim 1, wherein the learning information stored in said learning information storage unit is learning information acquired by said learning information acquisition unit.
The countermeasure is a challenge of taking a product for a certain period of time or longer, a challenge of receiving a service for a certain period of time or longer, or a challenge of performing an action for a certain period of time or longer in order to improve test results. 2. The information processing apparatus according to claim 1, further comprising a level of effort for the challenge, which is the answer information for the challenge.
An information processing method realized by a user information reception unit, a handling determination unit, a basis information acquisition unit, and an information output unit,
a user information reception step in which the user information reception unit receives user information having one or more user attribute values including result information specifying test results related to the living body of one user;
The handling determination unit has one or more user attribute values including first result information specifying inspection results before handling and second result information specifying inspection results as a result of taking the handling Acquiring learning information from a learning information storage unit that stores learning information based on two or more teaching data, and using the learning information and the user information received by the user information receiving unit, the user information has a countermeasure determination step of acquiring a countermeasure identifier that identifies a countermeasure according to the result information;
The countermeasure determination unit obtains the basis information acquisition unit using one or more teacher data corresponding to the countermeasure identifier obtained in the countermeasure determination step and the user information received by the user information reception unit a grounds information acquisition step of acquiring grounds information relating to grounds for recommending the handling identified by the handling identifier;
and an information output step in which the information output unit outputs the countermeasure identifier acquired in the countermeasure determination step and the basis information acquired in the basis information acquisition step.
Two or more teacher data having one or more user attribute values including first result information specifying inspection results before taking action and second result information specifying inspection results as a result of taking the action A computer that can access a learning information storage unit that stores learning information based on
a user information reception unit that receives user information having one or more user attribute values including result information specifying test results related to the living body of one user;
Acquiring the learned information from the learned information storage unit, and using the learned information and the user information received by the user information receiving unit, a countermeasure identifier that identifies a countermeasure corresponding to the result information of the user information a handling determination unit that acquires
A countermeasure identified by the countermeasure identifier acquired by the countermeasure determination unit using one or more teacher data corresponding to the countermeasure identifier acquired by the countermeasure determination unit and the user information received by the user information reception unit a grounds information acquisition unit that acquires grounds information on the grounds for recommending
A recording medium recording a program for functioning as an information output unit that outputs the countermeasure identifier acquired by the countermeasure determination unit and the basis information acquired by the basis information acquisition unit.