JP2024092356A - Information processing device, test method, information processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the problem of conventional information processing devices that it is difficult to obtain information relating to placebo effects per user.

SOLUTION: It is possible to easily obtain information relating to placebo effects of individual users by an information processing device 100 that comprises: a learning information acquisition unit 141 that acquires learning information constituted using two or more pieces of teaching data that pertain to two or more users and that respectively have two or more biological attribute values of one user and subjective information change information relating to the health of users before and after placebo ingestion; an input information acquisition unit 143 that acquires input information including the two or more biological attribute values pertaining to one subject user; a change information acquisition unit 145 that acquires change information regarding the subject user on the basis of the learning information and the input information; and a change information output unit 147 that outputs the change information.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2024,JPO&INPIT

Description

The present invention relates to an information processing device, a testing method, an information processing method, and a program that use information relating to changes in subjective health-related information.

Changes in human health before and after ingestion of a test substance may be evaluated using information on changes in the subjective information of the target users who ingested the test substance.

For example, the following Patent Document 1 discloses the configuration of a medication effect prediction system that predicts the effects of a drug on a patient using subjective information about the patient's past subjective opinions.

JP 2014-071592 A

However, evaluation results based on individual users' subjective information and changes in that information can be influenced by the user's tendencies regarding their perceptions. For users who experience the so-called placebo effect, it can be difficult to determine whether changes in subjective information before and after taking the test substance are due to the placebo effect or to the taking of the test substance.

The present invention therefore aims to provide an information processing device, a testing method, an information processing method, and a program that can easily obtain information regarding the placebo effect of individual users.

The information processing device of the first invention is an information processing device that includes a learning information acquisition unit that acquires learning information configured using two or more teacher data related to two or more users, each of which has two or more types of bio-attribute values of one user and change information of the user's subjective information related to health before and after taking a placebo, an input information acquisition unit that acquires input information including two or more types of bio-attribute values related to one target user, a change information acquisition unit that acquires change information about the target user based on the learning information and the input information, and a change information output unit that outputs the change information.

This configuration makes it easy to obtain information about the placebo effect of individual users.

The information processing device of the second invention is an information processing device in which, compared to the first invention, the learning information acquisition unit has a learning unit that configures the learning information using two or more teacher data, and acquires the learning information configured by the learning unit.

With this configuration, it is possible to construct learning information for obtaining information about the placebo effect.

The information processing device of the third invention is an information processing device in which, compared to the second invention, the learning information acquisition unit has an adoption condition determination unit that determines whether data that is a candidate for teacher data satisfies an adoption condition related to subjective information before taking a placebo, and the learning unit uses two or more pieces of data that are determined by the adoption condition determination unit to satisfy the adoption condition as two or more pieces of teacher data to construct learning information.

This configuration makes it possible to construct learning information that can effectively obtain information about the placebo effect for individual users.

The information processing device of the fourth invention is an information processing device according to any one of the first to third inventions, in which the learning information is a prediction model constructed by a machine learning learning process, and the change information acquisition unit acquires the change information by a machine learning prediction process using the learning information.

This configuration makes it possible to obtain highly accurate information about the placebo effect of individual users.

The information processing device of the fifth invention is an information processing device according to any one of the first to third inventions, in which the learning information is a correspondence table including two or more pieces of correspondence information having vectors each having two or more types of biometric attribute values as elements and change information, and the change information acquisition unit identifies one or more pieces of change information corresponding to vectors each having two or more types of biometric attribute values as elements of the input information that satisfy a predetermined similarity condition, and acquires the change information based on the identification result.

This configuration makes it easier to obtain information about the placebo effect of individual users.

The information processing device of the sixth invention is an information processing device according to any one of the first to fifth inventions, comprising an appropriateness information acquisition unit that uses change information of the target user acquired by the change information acquisition unit to acquire appropriateness information regarding the suitability of the target user as a subject for a test measuring the effect of the use of a test substance, including an evaluation index related to subjective information, and an appropriateness information output unit that outputs the appropriateness information.

This configuration allows for the selection of appropriate subjects.

The information processing device of the seventh invention is an information processing device according to any one of the first to sixth inventions, comprising a recommendation information acquisition unit that acquires recommendation information regarding the activity of the target user using the change information of the target user acquired by the change information acquisition unit, and a recommendation information output unit that outputs the recommendation information.

This configuration makes it possible to output recommendation information regarding the activities of the target user.

The testing method of the eighth invention includes the steps of acquiring two or more bioattribute values for each of two or more candidate users, acquiring output information for each of the two or more candidate users output by an information processing device according to any one of the first to seventh inventions using the acquired two or more bioattribute values, selecting one or more candidate users as subjects from the two or more candidate users based on the output information for each candidate user, and measuring the effectiveness of the use of a test substance including an evaluation index related to subjective information for the selected subjects.

This configuration allows the effectiveness of the test substance to be measured with high accuracy.

The testing method of the ninth invention includes the steps of acquiring two or more biometric attribute values for each of three or more candidate users, acquiring output information for each of the three or more candidate users by an information processing device according to any one of the first to seventh inventions using the acquired two or more biometric attribute values, selecting one or more candidate users as subjects from the three or more candidate users based on the output information of each candidate user, and dividing the two or more selected subjects into a control group and a treatment group to conduct a placebo-controlled test including an evaluation index related to subjective information.

This configuration allows placebo-controlled trials to be conducted with high accuracy.

The information processing device according to the present invention makes it easy to obtain information regarding the placebo effect of individual users.

FIG. 1 is a block diagram of an information processing system using an information processing device according to a first embodiment of the present invention; Block diagram of the information processing device FIG. 13 is a diagram illustrating an example of training data used in the information processing device. A flowchart illustrating an example of an operation flow when the information processing device performs a learning process. A flowchart illustrating an example of an operation flow when the information processing device outputs selection information as output information. A flowchart illustrating an example of the flow of an appropriateness information acquisition process performed in the information processing device. A flowchart illustrating an example of a usage example of the information processing device. A flowchart illustrating another example of the use of the information processing device. A graph showing an example of a placebo-controlled study conducted on subjects selected using the information processing device. Graph showing comparative examples of placebo-controlled studies 1 is a block diagram of an information processing device according to a second embodiment of the present invention; FIG. 13 is a diagram showing an example of recommendation information used in the information processing device; A flowchart illustrating an example of an operation flow when the information processing device outputs recommendation information as output information. FIG. 13 is a diagram illustrating an example of an information transmission screen for transmitting information to the information processing apparatus. FIG. 13 is a diagram illustrating a specific example of a display screen of recommended information by the information processing apparatus. Overview of the computer system according to the above embodiment. Block diagram of the computer system

Embodiments of an information processing device and the like will be described below with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore may not be described again.

The terms used below are generally defined as follows. The meanings of these terms should not always be interpreted as shown here, but for example, when they are explained individually below, they should be interpreted taking into account that explanation.

An identifier for a certain item is a character or code that uniquely identifies that item. An identifier can be, for example, an ID, but any type of information can be used as long as it can identify the corresponding item. In other words, an identifier can be the name of the thing it represents, or a combination of codes that uniquely identify the thing.

Acquiring may include acquiring items input by a user, etc., or may include acquiring information stored in one's own device or another device (which may be information stored in advance or information generated by information processing performed on the device). Acquiring information stored in another device may include acquiring information stored in the other device via an API, etc., or may include acquiring the contents of a document file provided by the other device (including the contents of a web page, etc.). It may also include acquiring information in a format different from that of the original information, such as acquiring information by performing optical character reading on an image file.

In addition, the so-called machine learning technique may be used to acquire information. The machine learning technique can be used, for example, as follows. That is, a learning device (learning information) that receives a specific type of input information as an input and outputs a type of output information to be acquired is configured using the machine learning technique. For example, two or more pairs of input information and output information are prepared in advance, and the two or more pairs of information are provided to a module for configuring a machine learning learning device to configure a learning device, and the configured learning device is stored in a storage unit. The learning device can also be called a classifier. Note that machine learning techniques can be, for example, deep learning, random forest, SVM, etc. In addition, for machine learning, functions in various machine learning frameworks such as scikit-learn, TensorFlow, PyTorch, and various existing libraries can be used. Acquiring information using such a learning device is sometimes called acquisition by machine learning.

The learning device is not limited to one obtained by machine learning. The learning device may be, for example, a table (correspondence table) showing the correspondence between an input vector based on input information, etc. and output information. In this case, output information corresponding to a feature vector based on input information may be obtained from the table, or a vector approximating a feature vector based on input information may be generated using two or more input vectors in the table and parameters for weighting each input vector, and final output information may be obtained using output information and parameters corresponding to each input vector used in the generation. Obtaining information using such a learning device may be referred to as obtaining using a correspondence relationship or obtaining using a correspondence table. The learning device may be, for example, a function that represents the relationship between an input vector based on input information, etc. and information for generating output information. In this case, for example, information corresponding to a feature vector based on input information may be obtained by a function, and output information may be obtained using the obtained information. Obtaining information using such a learning device may be referred to as obtaining using a function.

The concept of outputting information includes displaying on a display, projecting using a projector, printing on a printer, outputting sound, sending to an external device, storing on a recording medium, and passing the processing results to other processing devices or other programs. Specifically, it includes, for example, making it possible to display information on a web page, sending it as e-mail, and outputting information for printing.

The concept of accepting information includes the acceptance of information entered from input devices such as a keyboard, mouse, or touch panel, the reception of information transmitted from other devices via wired or wireless communication lines, and the acceptance of information read from recording media such as optical disks, magnetic disks, and semiconductor memories.

Regarding various types of information stored in information processing devices, etc., the concept of updating includes not only changing the stored information, but also adding new information to the stored information and deleting part or all of the stored information.

(Embodiment 1)

In this embodiment, the information processing device is configured to acquire and output change information of a target user using learning information configured to use two or more types of biometric attribute values of a user (person) as input information and change information of the user's subjective information regarding health before and after taking a placebo as output information. An information processing system using an information processing device configured in this manner is described below.

Figure 1 is a block diagram of an information processing system 1 using an information processing device 100 in embodiment 1 of the present invention.

The information processing system 1 includes an information processing device 100 and a terminal device 600. In the information processing system 1, the information processing device 100 is generally configured to acquire change information using information transmitted from the terminal device 600. Note that the information processing device 100 may be configured to be usable independently without using the terminal device 600.

In the information processing system 1, the information processing device 100 can communicate with devices such as the terminal device 600 via a network such as the Internet. Note that the network is not limited to this and may be a LAN or other communication network. Note that the connection mode and communication method between the information processing device 100 and the terminal device 600 are not limited to this.

In this embodiment, the terminal device 600 is a device that can be a destination of output information from the information processing device 100. In this embodiment, for example, a device such as a terminal used by an administrator or user of the information processing device 100 can be the terminal device 600. Note that a device other than these may also be used as the terminal device 600.

The electronic calculator used in the terminal device 600 may be a variety of devices, such as a personal computer, a mobile information terminal device such as a smartphone, or a tablet-type information terminal device. In the following examples, the electronic calculator used in the terminal device 600 may be a smartphone, but is not limited to this.

Figure 2 is a block diagram of the information processing device 100.

The information processing device 100 includes a storage unit 110, a receiving unit 120, an acceptance unit 130, a processing unit 140, and a transmission unit 170. The information processing device 100 is, for example, a server device, but may also be a personal computer or other information terminal device.

The storage unit 110 includes a learning information storage unit 111, a user information storage unit 115, and a teacher data storage unit 119.

The storage unit 110 is preferably a non-volatile recording medium, but can also be a volatile recording medium. Each part of the storage unit 110 stores information acquired by the receiving unit 120 or the processing unit 140, for example, but the process by which information is stored in each part of the storage unit 110 is not limited to this. For example, information may be stored in the storage unit 110 via a recording medium, information transmitted via a communication line or the like may be stored in the storage unit 110, or information inputted via an input device may be stored in the storage unit 110.

The learning information storage unit 111 stores learning information. The learning information may be called a learner, a classifier, a predictive model, or a trained model. In this embodiment, the learning information is, for example, configured by the learning unit 165 as described below. The learning information may be obtained by an external device. In other words, the learning information may be acquired by the information processing device 100 from an external device and stored in the learning information storage unit 111. Details of the learning information and its use will be described later.

The user information storage unit 115 stores user information. In this embodiment, the user information is information in which a user identifier, which is an identifier that identifies a target user from which change information is to be acquired in the information processing device 100, is associated with information about the target user. The user information may include various information. For example, the user information may include information transmitted from the terminal device 600 used by the target user, the terminal device 600 used by a user (for convenience, referred to as an operator, who may be the same as or different from the target user) who is to obtain output information, or other external devices. The user information may also include information directly input by the target user or the operator to the information processing device 100. The user information may also include information about the target user acquired by the information processing device 100 as described below.

In this embodiment, the user information includes two or more types of biometric attribute values of the user. Examples of biometric attribute values include, but are not limited to, BMI, uric acid level (UA), and blood pressure values such as diastolic blood pressure (DBP) and systolic blood pressure (SBP). For example, attribute values of the user's height, weight, and test values obtained by biochemical tests (e.g., at least one of RBC, Hb, Ht, WBC, PL, TP, ALB, CK, GOT, GPT, LDH, ALP, GGT, Cre, BUN, BG, TG, T_CHO, and T_BIL) may be included.

The user information may include attribute values other than the biometric attribute values. For example, attribute values such as the user's age and sex may be included. Attribute values related to lifestyle habits may be included. Attribute values related to lifestyle habits may include, but are not limited to, whether or not the user smokes, and how often the user smokes, whether or not the user drinks alcohol, the amount of alcohol consumed, and the amount and number of meals eaten. The user information may also include attribute values related to subjective information related to health, as described below. Specific examples of attribute values related to subjective information include values related to aspects such as mood state (POMS2), QOL (SF-36), and fatigue (VAS). The attribute values related to subjective information here are those before a specific behavior (such as taking a placebo), as described below. Among the user information, such biometric attribute values, attribute values such as age and sex, attribute values related to lifestyle habits, and attribute values related to subjective information before a specific behavior may be particularly called user health-related attribute values. The user health-related attribute values are information related to the user's health condition among the user information.

The teacher data storage unit 119 stores teacher data used to construct the learning information. The teacher data stored in the teacher data storage unit 119 may be candidate data that can be a candidate for teacher data used when actually constructing the learning information. In this embodiment, two or more teacher data related to two or more users are stored. Each teacher data has two or more types of biometric attribute values of one user and information related to the subjective information of the user. In other words, each teacher data is information in which two or more biometric attribute values and information related to the subjective information are associated with each other for one user.

The two or more types of biometric attribute values included in the training data are attribute values for two or more of the attributes of the biometric attribute values stored as user information as described above. The biometric attribute values stored as user information may include attributes different from the attributes of the biometric attribute values included in the training data. Note that it is preferable to select two or more types of biometric attribute values, i.e., explanatory variables, used as training data that have a relatively high contribution to the change information, which is the objective variable. The selection of attributes with a high contribution can be performed, for example, using the results of determining the contribution of each attribute using a known analysis method such as a machine learning library.

In addition, information related to subjective information is information on changes in subjective information related to health before and after the user performs a specified action. Subjective information related to health is information that represents the user's subjective evaluation of himself/herself from a specified perspective regarding health. Examples of specified perspectives include, but are not limited to, fatigue, degree of gastrointestinal discomfort, how well one wakes up, how well one falls asleep, whether one slept soundly, the presence or absence and severity of a headache, drowsiness, feeling of rest after sleep, impressions about QOL, happiness level, mood, etc.

The subjective information is, for example, a value that quantitatively represents the user's evaluation result for a specific viewpoint. The subjective information is, for example, a numerical value obtained by using a specific method to represent the degree to which the user felt about a specific viewpoint. As the specific method, for example, a visual analog scale (VAS) may be used, but a numerical rating scale (NRS) or other methods may also be used. The subjective information may also be a value that is expressed qualitatively, or information that expresses a state in language. For example, the subjective information may be information that indicates whether or not the user is in a state related to a specific viewpoint, or information that indicates the result of the user's selection from options that represent a state prepared in advance. The subjective information may also be information that is expressed using a verbal rating scale (VRS). The subjective information may also be, for example, the result of a mood profile test such as POMS or POMS2 regarding a state related to vitality or fatigue.

The change information is information that indicates how the subjective information after a predetermined behavior has changed from the subjective information before the predetermined behavior. The change information may be qualitative or quantitative. The change information may be information that indicates the result of comparing the subjective information before the predetermined behavior with the subjective information after the predetermined behavior. For example, the change information may be information that indicates whether the user's evaluation result has become better for a predetermined viewpoint. Also, for example, the change information may be the amount of change in a value that is the subjective information for a predetermined viewpoint. Note that, for example, the change information may be information that indicates whether the user's evaluation result for a predetermined viewpoint has changed. After a predetermined behavior is, for example, a point in time when a predetermined period (for example, a predetermined number of days, a predetermined week, etc.) has passed since the predetermined behavior, but is not limited thereto, and may be any point in time after the predetermined behavior or within a predetermined period.

For example, in the case where fatigue is expressed as subjective information by a VAS score (the higher the fatigue, the higher the score), and the score after a specified action has decreased from the score before the specified action, information indicating that the condition has improved (fatigue has decreased) can be used as change information. In this case, the value (amount of change) obtained by subtracting the score before the specified action from the score after the specified action may be used as change information.

In this embodiment, the predetermined behavior related to the change information is, for example, taking a placebo. In other words, each training data set includes, for one user, multiple bio-attribute values and information on changes in subjective information before and after taking a placebo.

Figure 3 is a diagram illustrating an example of training data used in the information processing device 100.

In FIG. 3, it is shown that the teacher data of each user identified by a user identifier is associated with the user identifier. That is, the teacher data of each user includes biometric attribute values such as BMI, uric acid level, and blood pressure value, and change information indicating whether the VAS score indicating fatigue has improved with "yes" or "no." In addition, in the example shown in the figure, the teacher data includes the initial value of the VAS score indicating fatigue (the value before the specified action).

Note that a user identifier may not be associated with the teacher data. In other words, it may be impossible to identify which user each teacher data belongs to. Furthermore, each teacher data may include attribute values related to other users of the biometric attribute values, in which case it is not necessary to include two or more biometric attribute values. For example, each teacher data may include attribute values of subjective information related to the user's health before a specified action (e.g., before taking a placebo). Furthermore, for example, each teacher data may include attribute values related to the user's lifestyle habits. In other words, each teacher data may include two or more types of user health-related attribute values.

Returning to FIG. 2, the receiving unit 120 receives information transmitted from another device. The receiving unit 120 stores the received information, for example, in the storage unit 110. The receiving unit 120 is typically realized by a wireless or wired communication means, but may also be realized by a means for receiving broadcasts.

The reception unit 130 receives various input operations performed by the user on the information processing device 100. The reception unit 130 receives, for example, information input using an input means (not shown) connected to the information processing device 100, or information input by an input operation (including, for example, information read by a device) performed using a reading device (e.g., a code reader) (not shown) connected to the information processing device 100. The reception unit 130 may receive information related to the input operation, etc., transmitted via another device connected via a network, etc. The received information is stored in the storage unit 110, for example.

The input means that can be used to input information that can be accepted by the acceptance unit 130 may be anything, such as a numeric keypad, keyboard, mouse, or menu screen. The acceptance unit 130 may be realized by a device driver for an input means such as a numeric keypad or keyboard, or control software for a menu screen.

The processing unit 140 includes a learning information acquisition unit 141, an input information acquisition unit 143, a change information acquisition unit 145, a change information output unit 147, an aptitude information acquisition unit 151, an aptitude information output unit 153, a subject selection unit 155, a selection information output unit 157, a learning unit 165, and an employment condition determination unit 167.

The processing unit 140 performs various processes, such as the processes performed by each part of the processing unit 140 as follows. The processing unit 140 can usually be realized by an MPU (including a CPU and/or GPU), memory, etc. The processing procedure of the processing unit 140 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may also be realized by hardware (dedicated circuitry).

The learning information acquisition unit 141 acquires learning information used to acquire change information as described below. The learning information acquisition unit 141 acquires learning information stored in the learning information storage unit 111. That is, the learning information acquisition unit 141 acquires learning information that is two or more teacher data related to two or more users, each of which has two or more types of biological attribute values of one user and change information of the user's subjective information related to health before and after taking a placebo. In addition, when learning information is prepared for each predetermined attribute value of the target user (for example, age, generation, etc., but is not limited to this), the learning information acquisition unit may be configured to acquire learning information corresponding to the attribute value of the target user to acquire change information with higher accuracy.

The learning information acquisition unit 141 may be configured to acquire learning information stored in another device other than the information processing device 100 from that device. For example, if learning information stored in another device is always used, the information processing device 100 does not need to be provided with the learning information storage unit 111.

The input information acquisition unit 143 acquires input information including two or more types of biometric attribute values related to one target user. The input information is information used to acquire change information of the target user. As the input information, two or more predetermined types of biometric attribute values of the target user are acquired. The two or more predetermined types of biometric attribute values correspond to the attributes of the two or more types of biometric attribute values included in the teacher data. The input information acquisition unit 143 can acquire two or more predetermined types of biometric attribute values from the user information storage unit 115 of the target user, but the acquisition method is not limited to this. It should be noted that the input information may be two or more predetermined types of user health-related attribute values of the target user. In this case, the two or more predetermined types of user health-related attribute values may correspond to the attributes of the two or more user health-related attribute values included in the teacher data.

In this embodiment, the learning information is configured to output the following change information for the following input information, for example. The input information is, for example, the biological attribute values of the target user, such as BMI, uric acid, diastolic blood pressure, and systolic blood pressure. The change information is, for example, information indicating whether the target user's VAS score, which indicates fatigue, has improved before and after taking a placebo.

The change information acquisition unit 145 acquires change information about the target user based on the learning information and the input information. The change information acquisition unit 145 stores the acquired change information in the user information storage unit 115 in association with a user identifier that identifies the target user.

In this embodiment, the change information is configured to be acquired by machine learning as described above. That is, the learning information is a prediction model configured by a machine learning learning process. The change information acquisition unit 145 is configured to acquire the change information by a machine learning prediction process using the learning information. In this embodiment, for example, classification or clustering using a random forest can be suitably used as a machine learning algorithm. Note that the algorithm is not limited to this and may be other algorithms.

The change information may be acquired using a correspondence table as described above or a function as described above. That is, the learning information is not limited to a machine learning prediction model. For example, the learning information may be a correspondence table including two or more pieces of correspondence information having vectors whose elements are two or more predetermined biometric attribute values included in the input information and change information. In this case, the change information acquisition unit 145 may be configured to identify one or more pieces of change information corresponding to a vector that satisfies a predetermined similarity condition for a vector whose elements are two or more biometric attribute values of the input information, and acquire the change information based on the identification result.

The change information output unit 147 outputs the change information. In this embodiment, the change information output unit 147 outputs the change information by passing the change information to the next process performed by the appropriateness information acquisition unit 151.

The suitability information acquisition unit 151 acquires suitability information of the target user using the change information of the target user acquired by the change information acquisition unit 145. The suitability information acquisition unit 151 stores the acquired suitability information in the user information storage unit 115 in association with a user identifier that identifies the target user.

The suitability information is information regarding the suitability of a subject as a subject for a test to measure the effect of using a test substance, including an evaluation index related to subjective information. A test substance is a substance that is not a placebo and is the subject of a test to measure the effect. Examples of test substances include, but are not limited to, drugs, supplements, and other food ingredients. The suitability information may be, for example, information indicating whether or not a subject is suitable as a subject, or may be a score indicating the suitability of a subject. Use of a test substance includes, for example, but is not limited to, ingestion into the body.

In this embodiment, the suitability information acquisition unit 151 is configured to output suitability information based on, for example, a result of a judgment as to whether or not the change information satisfies a predetermined suitability judgment condition. The suitability judgment condition is, for example, a condition as to whether or not the change information matches a predetermined value, or a condition as to whether or not the amount of change is greater than a predetermined threshold, but is not limited thereto. The suitability information acquisition unit 151 is configured to acquire suitability information indicating suitability as a subject when, for example, the change information indicates that the change in subjective information is small before and after taking the placebo (such as when the amount of change is smaller than a predetermined threshold). That is, when the target user can be evaluated as a placebo non-responder based on the change information, the suitability information acquisition unit 151 is configured to acquire suitability information indicating suitability as a subject, or to acquire a high score as a score indicating the suitability as a subject acquired as suitability information.

In this embodiment, the suitability judgment condition may be, for example, change information indicating that the fatigue VAS score has not improved, but is not limited to this. The suitability judgment condition may be, for example, a condition based on change information acquired for each of two or more users including the target user. More specifically, for example, the suitability judgment condition may relate to the comparison result between the change information of one or more other users and the change information of the target user (for example, the change information is equal to or greater than the average value of the change information of all users, the change information is within a predetermined proportion of high (or low) change information among all users, the change information falls within a range of a predetermined number of users in order of high (or low) change information, etc., but various conditions can be set).

The suitability information output unit 153 outputs suitability information. In this embodiment, the suitability information output unit 153 outputs the suitability information by passing the suitability information to the next process performed by the subject selection unit 155.

The subject selection unit 155 uses the suitability information of the target user output by the suitability information output unit 153 to select subjects for a test to measure the effect of using the test substance. The subject selection unit 155 acquires, for example, selection information related to the selection result. The selection information is, but is not limited to, the user identifier of the user selected as the subject of the test to measure the effect of using the test substance. When two or more users are selected, a list of user identifiers may be acquired as the selection information.

In this embodiment, the subject selection unit 155 selects subjects based on, for example, the results of suitability information acquired for two or more target users. For example, the subject selection unit 155 selects subjects according to predetermined selection conditions. Specifically, for example, among the two or more target users, all target users whose suitability information is predetermined (for example, being suitable as a subject) or who satisfy a predetermined criterion (such as a score indicating suitability as a subject being equal to or greater than a predetermined value) may be selected as subjects. Also, for example, a predetermined number of target users who are at the top of a hierarchy of two or more target users based on suitability information may be selected as subjects.

The subject selection unit 155 may be configured to select subjects using the change information of the target users output by the change information output unit 147. For example, among two or more target users, all target users whose change information is of a predetermined content (e.g., the subjective information score does not change) or whose change information satisfies a predetermined criterion (e.g., the amount of change in the subjective information is equal to or less than a predetermined value) may be selected as subjects.

The selection information output unit 157 outputs the selection information. In this embodiment, the selection information output unit 157 is configured to output the selection information as output information by transmitting it to another device using the transmitting unit 170 or the like, or by displaying it on, for example, a display device provided in the information processing device 100. This allows the operator of the information processing device 100 to obtain the subject selection results.

The change information or suitability information may be output information output from the information processing device 100. For example, the change information output unit 147 or the suitability information output unit 153 may output the output information by transmitting the output information, which is the change information or suitability information, to another device using the transmission unit 170 or the like, or may output the output information by displaying the output information on a display device provided in the information processing device 100, for example.

In addition, in the information processing device 100, the change information output unit 147 may be configured to transmit or display the change information as output information to another device, and not to acquire or output suitability information. In this case, the suitability information acquisition unit 151, the suitability information output unit 153, the subject selection unit 155, and the selection information output unit 157 may not be provided.

In addition, the information processing device 100 may be configured such that the suitability information acquisition unit 151 transmits or displays the suitability information as output information to another device, and selection information is not acquired or output. In this case, the subject selection unit 155 and the selection information output unit 157 may not be provided.

The change information output unit 147, the appropriateness information output unit 153, and the selection information output unit 157 may or may not include an output device such as a display or a speaker. The change information output unit 147, the appropriateness information output unit 153, and the selection information output unit 157 may be realized by driver software for an output device, or driver software for an output device and an output device, etc.

In this embodiment, the learning unit 165 executes a learning process that constructs learning information using two or more pieces of teacher data stored in the teacher data storage unit 119. The learning unit 165 constructs learning information that is a predictive model by a machine learning technique, for example, as described above. The learning process can be performed by a known method.

In this embodiment, the learning unit 165 is configured to construct learning information using two or more pieces of teacher data that satisfy a predetermined adoption condition based on the judgment result of the adoption condition judgment unit 167. In this case, for example, the teacher data stored in the teacher data storage unit 119 may be said to be candidate data that is a candidate for teacher data to be used in the learning process.

The use of teacher data that satisfies such adoption conditions may be performed, for example, as follows. That is, in this embodiment, the adoption condition determination unit 167 determines whether or not the candidate data stored in the teacher data storage unit 119 satisfies a predetermined adoption condition. Then, the learning unit 165 uses two or more pieces of candidate data that are determined by the adoption condition determination unit 167 to satisfy the adoption condition as two or more pieces of teacher data to construct learning information.

As an adoption condition, for example, a condition related to the subjective information before taking the placebo can be used. For example, the subjective information being greater than (or smaller than) a predetermined value, or the subjective information corresponding to (or not corresponding to) a predetermined value, etc., can be used as an adoption condition. This makes it possible to configure the learning information so that change information can be output with greater accuracy.

The adoption conditions can be set so that, for example, the presence or absence of an effect of taking a placebo on the change information can be effectively confirmed. For example, when a VAS score indicating fatigue is used as subjective information, the adoption condition can be that the VAS score before taking the placebo is greater than a predetermined threshold (e.g., the score indicates a relatively large sense of fatigue). If the score before taking the placebo is smaller than the predetermined threshold, the presence or absence of an effect of taking the placebo on the change information is less likely to appear in the change information. For teacher data in which the score before taking the placebo is greater than the predetermined threshold, if the effect of taking the placebo causing the score to decrease appears, the effect will be easily reflected in the change information. By using such adoption conditions, it is possible to configure learning information that can acquire change information that can effectively confirm the presence or absence of an effect of taking a placebo on the change information.

In addition to the above, the hiring conditions may be, for example, that the candidate data contains an attribute value indicating that the user belongs to a user group having a specified attribute value. For example, being in a specified age group, having a BMI within a specified range, being of a specified gender, etc. can be used as hiring conditions. In particular, when sufficient teacher data satisfying the hiring conditions is obtained, learning information that can acquire change information with higher accuracy for target users belonging to the user group can be configured for each user group. The learning information configured in this way for each user group can be used to acquire change information for target users that can be said to correspond to the respective user groups.

The transmitting unit 170 transmits information to other devices with which it can communicate via a network. For example, the transmitting unit 170 transmits the selection information output by the selection information output unit 157 as output information. The transmitting unit 170 is typically realized by a wireless or wired communication means, but may also be realized by a broadcasting means.

Next, the flow of operations of the information processing device 100 will be described. The information processing device 100 performs various operations, for example, as follows. These operations are performed by the processing unit 140 executing control operations and the like using each unit.

Figure 4 is a flowchart that explains an example of the operational flow when the information processing device 100 performs a learning process.

The learning process is carried out, for example, as follows:

(Step S21) That is, the processing unit 140 acquires pairs of input information including biometric attribute values and change information for each of two or more users as candidate data for teacher data. The candidate data is accumulated in the teacher data storage unit 119.

Next, learning information is constructed using the candidate data stored in the teacher data storage unit 119.

(Step S22) The processing unit 140 sets counter i to 1.

(Step S23) The processing unit 140 judges whether the i-th candidate data among the candidate data stored in the teacher data storage unit 119 satisfies the adoption conditions. If it is judged that the adoption conditions are satisfied, the process proceeds to step S24, and if not, the process proceeds to step S25. Note that if it is not judged that the adoption conditions are satisfied, the processing unit 140 may discard the i-th candidate data.

(Step S24) The processing unit 140 sets (adopts) the i-th candidate data as one of the teacher data to be used in generating the current learning information. For example, the processing unit 140 sets a flag indicating that the candidate data is teacher data in association with the candidate data, or stores only the teacher data in a distinguishable state.

(Step S25) The processing unit 140 increments the counter i by 1.

(Step S26) The processing unit 140 determines whether the i-th candidate data exists. If it is determined that the i-th candidate data exists, the process returns to step S23. If not, the process proceeds to step S27.

(Step S27) The processing unit 140 uses the set teacher data to construct learning information.

(Step S28) The processing unit 140 stores the constructed learning information in the learning information storage unit 111. Then, the processing ends.

Such processing is started when a specific start condition is met. For example, the start condition may be, but is not limited to, the arrival of a specific time or the receipt of a specific instruction from an operator or the like.

In addition, the selection of candidate data using the adoption conditions as described above may not be performed, in which case it may be interpreted that all candidate data is set as teacher data. It may also be interpreted that pairs of input information and change information acquired by the processing unit 140 are stored as teacher data in the teacher data storage unit 119, and that the processing from step S27 onwards is performed using the teacher data.

Next, we will explain the flow of operations when the information processing device 100 outputs output information about a target user.

Figure 5 is a flowchart illustrating an example of the operational flow when the information processing device 100 outputs selection information as output information.

(Step S41) The processing unit 140 acquires the input information of the target user.

(Step S42) The processing unit 140 acquires the learning information to be used to acquire the change information from the learning information storage unit 111.

(Step S43) The processing unit 140 acquires change information for the target user by applying the input information to the learning information. The acquired change information may be stored in the user information storage unit 115 in association with a user identifier that identifies the target user.

(Step S44) The processing unit 140 uses the acquired change information to acquire suitability information. The process for acquiring suitability information will be described later.

(Step S45) The processing unit 140 selects subjects based on the acquired information and acquires selection information. The processing unit 140 outputs the selection information as output information. Then, the series of processes ends.

In this way, subjects for a test to measure the effect of using a test substance are selected using the suitability information of the target user, and the selection information is output, allowing a user of the information processing device 100 to easily identify subjects for a test to measure the effect of using a test substance.

When step S44 is completed, the processing unit 140 may determine whether or not to execute the processing of step S45. For example, the processing unit 140 may be configured to execute the processing of step S45 when a predetermined condition is satisfied, such as that suitability information has been acquired for a predetermined number of target users, that a predetermined instruction has been given by an operator, etc.

When the processing unit 140 acquires input information of the target user, the processing unit 140 may use the input information to determine whether or not to output change information. For example, the adoption condition determination unit 167 may determine whether or not the adoption conditions are satisfied for the input information, and if the adoption conditions are satisfied, the processing from step S42 onwards may be performed. In this case, if it is not determined that the adoption conditions are satisfied, the change information may not be output, or predetermined information (for example, information that the subjective information does not change) may be output as the change information. If it is not determined that the adoption conditions are satisfied, suitability information indicating that the subject is not suitable to be a test subject may be output.

Figure 6 is a flowchart illustrating an example of the flow of the appropriateness information acquisition process performed in the information processing device 100.

(Step S61) The processing unit 140 determines whether or not a predetermined suitability determination condition is satisfied for the change information of the target user. If it is determined that the condition is satisfied, the process proceeds to step S62; if not, the process proceeds to step S63.

(Step S62) The processing unit 140 acquires suitability information indicating that the target user is suitable as a test subject.

(Step S63) The processing unit 140 obtains suitability information indicating that the target user is not suitable as a test subject.

When the processing of step S62 or step S63 is completed, the process returns to the upper level.

When the information processing device 100 is configured to output suitability information for the target user as output information, the information processing device 100 may be operated, for example, as follows. That is, in the flowchart shown in FIG. 5, instead of step S45, the processing unit 140 may be configured to output the suitability information acquired in step S44 as output information. Using the suitability information output in this manner, a target user who is suitable as a subject for a test to measure the effect of using a test substance may be selected.

As described above, in this embodiment, the information processing device 100 can use the input information and the learning information to acquire information on changes in subjective health information of the target user before and after taking a placebo. Therefore, information on the placebo effect of each individual user can be easily obtained. In this embodiment, the learning information is obtained by machine learning using teacher data, and by using such learning information, highly accurate information on the placebo effect of each individual user can be acquired.

Next, we will explain examples of how the information processing device 100 can be used.

In this embodiment, the information processing device 100 can be used, for example, when measuring the effectiveness of the use of a test substance that includes an evaluation index related to subjective information with the cooperation of a subject. That is, the information processing device 100 executes processing including output of change information for each of the candidate users who are subjects. Then, based on the output information of the information processing device 100, subjects can be selected and a test can be conducted. Such a usage mode can be carried out by a user, for example, specifically as follows.

Figure 7 is a flowchart illustrating an example of how the information processing device 100 can be used.

(Step S801) First, the user acquires two or more types of biometric attribute values for each of two or more candidate users. The user himself/herself may acquire the information of each candidate user, or the information of each candidate user may be acquired by the information processing device 100 used by the user.

(Step S802) The user obtains output information output by the information processing device 100 using the two or more types of biometric attribute values obtained for each of the two or more candidate users. In other words, the information processing device 100 outputs output information for each of the two or more candidate users. The output information obtained here is, for example, suitability information, but may also be selection information or change information.

(Step S803) The user selects one or more candidate users as subjects from two or more candidate users based on the output information of each candidate user. For example, the user can preferentially select as subjects a candidate user for whom change information indicating that subjective information is unlikely to change has been obtained, or a candidate user for whom suitability information indicating that the candidate user is suitable as a subject has been obtained. Note that, when selection information is output by the information processing device 100, subjects may be selected according to the selection information. In this case, the process of step S803 may be understood to be executed by the information processing device 100.

(Step S804) The user measures the effectiveness of the use of the test substance, including evaluation indicators related to subjective information, on the selected subjects.

According to the above-described test method, the output information of the information processing device 100 can be used to test the effects of the use of a test substance on subjects who are relatively unlikely to exhibit a placebo effect (i.e., placebo non-responders). Therefore, it is possible to obtain highly accurate results of measuring the effects of the use of a test substance.

In this embodiment, the information processing device 100 can be used, for example, when conducting a placebo-controlled test including an evaluation index related to subjective information with the cooperation of subjects. That is, the information processing device 100 executes processing including output of change information for each of the candidate users who are subjects. Then, based on the output information of the information processing device 100, two or more subjects are selected. Then, the two or more subjects can be divided into a control group and a treatment group to conduct a placebo-controlled test. Such a usage mode can be carried out by a user, for example, specifically as follows.

Figure 8 is a flowchart illustrating another example of use of the information processing device 100.

Steps S811 to S813 are the same as steps S801 to S803 described above. In this example, input information and output information are acquired for three or more candidate users. Then, two or more of the three or more candidate users are selected as subjects.

(Step S814) The user divides the two or more selected subjects into a control group and a treatment group.

(Step S815) The user conducts a placebo-controlled study including evaluation indices related to subjective information for subjects in both the control and treatment groups.

In this way, according to the above-described test method, a placebo-controlled test can be conducted using the output information of the information processing device 100 on subjects who are relatively unlikely to exhibit a placebo effect (i.e., placebo non-responders). Therefore, the results of the placebo-controlled test can be obtained with high accuracy.

Figure 9 is a graph showing an example of a placebo-controlled study conducted on subjects selected using the information processing device 100. Figure 10 is a graph showing a comparative example of a placebo-controlled study.

In each of the graphs in Figures 9 and 10, the horizontal axis indicates the test period, and the vertical axis indicates the VAS value indicating fatigue (hereinafter simply referred to as VAS). Each graph shows the progress of the VAS of the treatment group taking the test substance (test substance group) and the progress of the VAS of the control group taking a placebo (placebo group). In Figure 9, the number of cases in the treatment group is 14, and the number of cases in the control group is 13. Also, in Figure 10, the number of cases in the treatment group is 24, and the number of cases in the control group is 24.

As shown in FIG. 9, when subjects were selected using the information processing device 100, the VAS of the control group hardly changed over time. On the other hand, as shown in FIG. 10, in the comparative example in which subjects were not specially selected, the VAS of the control group decreased over time. That is, it is considered that the comparative example included a relatively large number of placebo responders among the subjects. Therefore, it is considered that the change in the VAS of the treatment group shows the effect of the test substance with higher accuracy when subjects were selected using the information processing device 100 than in the comparative example. Therefore, by selecting subjects using the information processing device 100, a placebo-controlled study can be easily performed with high accuracy.

The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as an optical disk and distributed. The software for realizing the information processing device 100 in this embodiment is a program as follows. That is, this program is executed by the computer of the information processing device 100, and causes the computer of the information processing device 100 to function as a learning information acquisition unit that acquires learning information composed of two or more teacher data related to two or more users, each of which has two or more types of bio-attribute values of one user and change information of the subjective information related to the health of the user before and after taking a placebo, an input information acquisition unit that acquires input information including two or more types of bio-attribute values related to one target user, a change information acquisition unit that acquires change information about the target user based on the learning information and the input information, and a change information output unit that outputs the change information.

(Embodiment 2)

The outline of the second embodiment will be described below with respect to the differences from the first embodiment described above. The second embodiment differs from the first embodiment in that recommendation information for the target user is obtained using change information. Also, in the second embodiment, learning information is not configured in the information processing device.

Figure 11 is a block diagram of an information processing device 200 according to embodiment 2 of the present invention.

In this embodiment, the information processing system 1 has an information processing device 200 instead of the information processing device 100 according to embodiment 1. The information processing device 200 differs from the information processing device 100 according to embodiment 1 in that it does not have the teacher data storage unit 119, the aptitude information acquisition unit 151, the aptitude information output unit 153, the subject selection unit 155, the selection information output unit 157, and the learning unit 165. Furthermore, in the information processing device 200, the storage unit 110 has a recommendation information storage unit 217, and the processing unit 140 has a recommendation information acquisition unit 255 and a recommendation information output unit 257. The other block configurations of the information processing device 200 are similar to those of the information processing device 100.

In this embodiment, the learning information storage unit 111 stores, for example, learning information that has been configured in advance by another device. Note that, even in this embodiment, the information processing device 200 may be provided with a teacher data storage unit 119 and a learning unit 165, and the information processing device 200 itself may be able to configure the learning information.

The recommendation information storage unit 217 stores recommendation information. In this embodiment, the recommendation information is information indicating matters that may be recommended to the user regarding the user's activities. The recommendation information indicates, for example, actions or behaviors that the user should undertake, and the state that should be achieved as a result of undertaking those actions. The recommendation information may indicate, for example, information regarding knowledge that the user should be aware of. The recommendation information may be, for example, information regarding exercise, diet, or lifestyle habits such as diet, exercise, and sleep. More specifically, the recommendation information may include, for example, a dietary diversity evaluation program, a fatigue improvement exercise program, or a sleep habit diagnosis program to enhance daytime activities, or the contents of each program (for example, information specifically explaining what the user should do) may be included in the recommendation information.

Figure 12 shows an example of recommendation information used in the information processing device 200.

In FIG. 12, three types of recommendation information are shown diagrammatically. Each piece of recommendation information includes, for example, an identifier (ID) that identifies the recommendation information, hyperlink information indicating the location of an information resource for showing the content of the recommendation information to the user (for example, information indicating the location of a video or audio, a link to a web page, etc.), and title information (display title) for explaining the recommendation information. Note that the present invention is not limited to this form, and the content of the recommendation information may also be recorded.

The three types of recommendation information can be, for example, first recommendation information, second recommendation information, and general advice information (third recommendation information). The first recommendation information is information that is considered to be recommended to a user whose subjective information changes relatively greatly before and after taking a placebo. The second recommendation information is information that is considered to be recommended to a user whose subjective information changes moderately before and after taking a placebo (for example, a user whose subjective information changes less than the user to whom the first recommendation information is recommended). The first recommendation information and the second recommendation information can be various predetermined information, such as an exercise program (exercise menu) that is expected to have an effect of improving fatigue, or meal menu information or food intake recommendations that may have an effect on improving fatigue. The general advice information is information aimed at a user whose subjective information changes relatively little before and after taking a placebo. The general advice information can be, for example, advice that is considered to be useful to a wide range of users regardless of whether or not there is a change in subjective information. It should be noted that the general advice information may not be included in the recommendation information.

Returning to FIG. 11, the recommendation information acquisition unit 255 acquires recommendation information related to the activity of the target user by using the change information of the target user acquired by the change information acquisition unit 145. The recommendation information acquisition unit 255 stores the acquired recommendation information in the user information storage unit 115 in association with a user identifier that identifies the target user.

In this embodiment, the recommendation information acquisition unit 255 is configured to acquire recommendation information based on, for example, a result of a determination as to whether or not the change information satisfies a predetermined recommendation condition. The recommendation condition is, for example, a condition related to whether or not the amount of change is greater than a predetermined threshold, but is not limited thereto. In this embodiment, the recommendation information acquisition unit 255 is configured to acquire first recommendation information when it is determined that the change information is large enough to satisfy a predetermined first recommendation condition, and to acquire second recommendation information when it is determined that the change information does not satisfy the predetermined first recommendation condition but is large enough to satisfy a predetermined second recommendation condition. In addition, the recommendation information acquisition unit 255 is configured to acquire general advice information when neither the first recommendation condition nor the second recommendation condition is satisfied. When neither the first recommendation condition nor the second recommendation condition is satisfied, neither information may be acquired.

The recommendation information output unit 257 outputs the recommendation information acquired by the recommendation information acquisition unit 255. In this embodiment, the recommendation information output unit 257 is configured to output the recommendation information by transmitting it as output information to the terminal device 600 of the target user using the transmission unit 170 or the like, or by displaying it on a display device provided in the information processing device 100, for example. This allows the target user or the operator of the information processing device 100 to confirm the contents of the recommendation information.

Next, we will explain the flow of operations when the information processing device 200 outputs output information about a target user.

Figure 13 is a flowchart illustrating an example of the operation flow when the information processing device 200 outputs recommendation information as output information.

Steps S241 to S243 are the same as steps S41 to S43 in the above-described first embodiment. Note that in this embodiment, in step S241, the target user transmits input information to the information processing device 200 using the terminal device 600 or the like, and the processing unit 140 acquires the information, but this is not limited thereto.

(Step S244) The processing unit 140 determines whether a predetermined first recommendation condition is satisfied for the change information of the target user. If it is determined that the condition is satisfied, the process proceeds to step S246, and if not, the process proceeds to step S245.

(Step S245) The processing unit 140 determines whether a predetermined second recommendation condition is satisfied for the change information of the target user. If it is determined that the condition is satisfied, the process proceeds to step S247, and if not, the process proceeds to step S248.

(Step S246) The processing unit 140 acquires the first recommendation information from the recommendation information storage unit 217 as output information for the target user.

(Step S247) The processing unit 140 acquires the second recommendation information from the recommendation information storage unit 217 as output information for the target user.

(Step S248) The processing unit 140 obtains general advice information from the recommendation information storage unit 217 as output information for the target user.

(Step S249) The processing unit 140 outputs the output information. Then, the series of processes ends.

In this embodiment, for example, the target user can obtain output information by using the terminal device 600 to transmit and receive information to and from the information processing device 200. In this case, for example, various operation screens and information display screens are displayed on the display unit 661, such as a touch panel, of the terminal device 600. The terminal device 600 can display information, for example, by using information transmitted from the information processing device 200 or by running a specified application on the terminal device 600. Such an example will be described below.

Figure 14 is a diagram illustrating an example of an information transmission screen for transmitting information to the information processing device 200.

As shown in FIG. 14, the target user can display the information transmission screen 1010 on the display unit 661 and perform a predetermined operation to transmit input information for causing the information processing device 200 to acquire change information. For example, the information transmission screen 1010 includes a display requesting permission to transmit the user's own information to the information processing device 200 in order to make a judgment regarding the placebo effect, and an instruction button 1015. For example, when the target user operates the instruction button 1015, input information including two or more biometric attribute values related to the user stored in the terminal device 600 is configured to be transmitted to the information processing device 200.

As a result, when input information is sent to the information processing device 200, the information processing device 200 acquires change information and recommendation information, and the recommendation information can be transmitted to the terminal device 600 as output information.

Figure 15 is a diagram illustrating a specific example of a display screen for recommendation information by the information processing device 200.

In FIG. 15, an example of a state in which recommendation information is displayed on the display unit 661 of the terminal device 600 is shown. The recommendation information may be displayed as an information display screen 1020 by a client application of an instant messaging service, for example, or the recommendation information may be transmitted by email, for example, as the email body or an attachment.

As shown in the figure, the information display screen 1020 includes, for example, a character string that provides information about the recommended information, and a display button 1025 for displaying more detailed content of the recommended information. The target user can use the information display screen 1020 to check the content of the recommended information. In this specific example, the display button 1025 displayed on the information display screen 1020 is displayed so as to function as a hyperlink to a web page or the like for providing more detailed information. This makes it possible to reduce the volume of information on the information display screen 1020 so that the target user can easily grasp the overview, while also making it possible to provide the target user with more information in accordance with the target user's wishes.

As described above, in the second embodiment, recommendation information is output to the target user in accordance with the change information of the target user. Therefore, the target user can know recommendation information related to activities that are effective for him/her. For example, by outputting recommendation information related to activities for improving fatigue to a user who is predicted to be a placebo responder, the user who engages in the activity is more likely to be able to subjectively feel the effects of the activity. Therefore, it can be said that recommendation information that can increase the user's satisfaction can be output.

(others)

Figure 16 is an overview of the computer system 800 in the above embodiment. Figure 17 is a block diagram of the same computer system 800.

These figures show examples of computer configurations that execute the programs described in this specification to realize the information processing devices and the like of the above-mentioned embodiments. The above-mentioned embodiments can be realized by computer hardware and computer programs executed thereon.

The computer system 800 includes a computer 801 including an optical disk drive, a keyboard 802, a mouse 803, and a monitor 804.

In addition to an optical disk drive (ODD) 8012, the computer 801 includes an MPU 8013, a bus 8014 connected to the optical disk drive 8012 etc., a ROM 8015 for storing programs such as a boot-up program, a RAM 8016 connected to the MPU 8013 for temporarily storing instructions for application programs and providing temporary storage space, and a hard disk (HDD) 8017 for storing application programs, system programs, and data. Although not shown here, the computer 801 may further include a network card providing a connection to a LAN.

A program that causes the computer system 800 to execute the functions of the information processing device of the above-mentioned embodiment may be stored on an optical disk 8101, inserted into the optical disk drive 8012, and then transferred to the hard disk 8017. Alternatively, the program may be transmitted to the computer 801 via a network (not shown) and stored on the hard disk 8017. The program is loaded into the RAM 8016 when executed. The program may be loaded directly from the optical disk 8101 or the network.

The program does not necessarily have to include an operating system (OS) or a third-party program that causes the computer 801 to execute the functions of the information processing device of the above-described embodiment. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner to obtain the desired results. How the computer system 800 operates is well known, and a detailed description will be omitted.

In the above program, the transmission step of transmitting information and the reception step of receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that is performed only by hardware).

The computer that executes the above program may be a single computer or multiple computers. In other words, it may perform centralized processing or distributed processing.

Furthermore, in the above embodiment, two or more components present in one device may be physically realized on one medium.

In addition, in the above embodiments, each process (each function) may be realized by centralized processing in a single device (system), or may be realized by distributed processing by multiple devices (in this case, the entire system consisting of multiple devices performing distributed processing can be considered as a single "device").

In addition, in the above embodiment, the transfer of information between components may be performed, for example, by one component outputting information and the other component receiving information if the two components transferring the information are physically different, or, if the two components transferring the information are physically the same, by shifting from a processing phase corresponding to one component to a processing phase corresponding to the other component.

In addition, in the above embodiment, information related to the processing executed by each component, such as information accepted, acquired, selected, generated, transmitted, or received by each component, and information such as thresholds, formulas, and addresses used by each component in processing, may be temporarily or long-term stored in a recording medium (not shown) even if not specified in the above description. Furthermore, each component or a storage unit (not shown) may store information in the recording medium (not shown). Furthermore, each component or a reading unit (not shown) may read information from the recording medium (not shown).

In the above embodiment, if the information used by each component, such as the thresholds, addresses, and various setting values used by each component in processing, may be changed by the user, the user may or may not be able to change the information as appropriate, even if not specified in the above description. If the information is changeable by the user, the change may be realized, for example, by a reception unit (not shown) that receives a change instruction from the user, and a change unit (not shown) that changes the information in response to the change instruction. The reception unit (not shown) may receive the change instruction from an input device, may receive information transmitted via a communication line, or may receive information read from a specified recording medium.

The present invention is not limited to the above embodiment, and various modifications are possible, and these are also included within the scope of the present invention.

An embodiment may be constructed by appropriately combining the above-described multiple embodiments. For example, it is not limited to the configurations of the above-described embodiments themselves, and each component of the above-described embodiments may be replaced or combined with a component of another embodiment as appropriate. Also, some components or functions of the above-described embodiments may be omitted.

As described above, the information processing device of the present invention has the effect of easily obtaining information regarding the placebo effect of individual users, and is useful as an information processing device, etc.

1 Information processing system 100, 200 Information processing device 110 Storage unit 111 Learning information storage unit 115 User information storage unit 119 Teacher data storage unit 120 Receiving unit 130 Accepting unit 140 Processing unit 141 Learning information acquisition unit 143 Input information acquisition unit 145 Change information acquisition unit 147 Change information output unit 151 Suitability information acquisition unit 153 Suitability information output unit 155 Subject selection unit 165 Learning unit 167 Recruitment condition determination unit 170 Transmission unit 217 Recommendation information storage unit 255 Recommendation information acquisition unit 257 Recommendation information output unit 600 Terminal device 661 Display unit

Claims (11)

a learning information acquisition unit that acquires learning information configured using two or more pieces of teacher data related to two or more users, each of which has two or more types of biometric attribute values of one user and information on changes in subjective information related to health of the user before and after taking a placebo;
an input information acquisition unit that acquires input information including the two or more types of biometric attribute values related to one target user;
a change information acquisition unit that acquires the change information about the target user based on the learning information and the input information;
and a change information output unit that outputs the change information. The learning information acquisition unit
A learning unit that configures the learning information using the two or more pieces of teacher data,
The information processing apparatus according to claim 1 , further comprising: a learning unit configured to obtain the learning information; The learning information acquisition unit has an adoption condition determination unit that determines whether or not the candidate data for the teacher data satisfies an adoption condition regarding the subjective information before taking a placebo,
The information processing apparatus according to claim 2 , wherein the learning unit uses two or more pieces of data determined by the adoption condition determination unit to satisfy the adoption condition as the two or more pieces of teacher data to configure the learning information. The learning information is a prediction model configured by a machine learning learning process,
The information processing device according to claim 1 , wherein the change information acquisition unit acquires the change information by a machine learning prediction process using the learning information. the learning information is a correspondence table including two or more pieces of correspondence information having vectors each having the two or more types of biometric attribute values as elements and the change information,
The information processing device according to claim 1 , wherein the change information acquisition unit identifies one or more pieces of change information corresponding to a vector that satisfies a predetermined similarity condition for a vector having elements of each of the two or more types of biometric attribute values of the input information, and acquires the change information based on the identification result. an appropriateness information acquisition unit that acquires appropriateness information regarding the appropriateness of the target user as a subject of a test for measuring the effect of use of a test substance, the appropriateness information including an evaluation index regarding the subjective information, using the change information of the target user acquired by the change information acquisition unit;
The information processing apparatus according to claim 1 , further comprising: an appropriateness information output unit that outputs the appropriateness information. a recommendation information acquisition unit that acquires recommendation information regarding an activity of the target user by using the change information of the target user acquired by the change information acquisition unit;
The information processing device according to claim 1 , further comprising: a recommendation information output unit that outputs the recommendation information. acquiring two or more types of biometric attribute values of two or more candidate users;
acquiring output information for each of the two or more candidate users by using the acquired two or more types of biometric attribute values, the output information being output by the information processing device according to any one of claims 1 to 7;
selecting one or more candidate users as subjects from the two or more candidate users based on the output information of each candidate user;
and measuring the effect of use of a test substance, including an evaluation index relating to subjective information, on selected subjects. acquiring two or more types of biometric attribute values of each of three or more candidate users;
acquiring output information for each of the three or more candidate users by using the acquired two or more types of biometric attribute values, the output information being output by the information processing device according to any one of claims 1 to 7;
selecting two or more candidate users as subjects from the three or more candidate users based on the output information of each candidate user;
and dividing the two or more selected subjects into a control group and a treatment group, and conducting a placebo-controlled study including evaluation indicators related to subjective information. An information processing method performed by using a learning information acquisition unit, an input information acquisition unit, a change information acquisition unit, and a change information output unit,
a learning information acquisition step in which the learning information acquisition unit acquires learning information configured using two or more pieces of teacher data related to two or more users, each of which has two or more types of biometric attribute values of one user and information on changes in subjective information related to health of the user before and after taking a placebo;
an input information acquisition step in which the input information acquisition unit acquires input information including the two or more types of biometric attribute values related to one target user;
a change information acquisition step in which the change information acquisition unit acquires the change information about the target user based on the learning information and the input information;
The information processing method includes a change information output step in which the change information output unit outputs the change information. Computer,
a learning information acquisition unit that acquires learning information configured using two or more pieces of teacher data related to two or more users, each of which has two or more types of bioattribute values of one user and information on changes in subjective information related to health of the user before and after taking a placebo;
an input information acquisition unit that acquires input information including the two or more types of biometric attribute values related to one target user;
a change information acquisition unit that acquires the change information about the target user based on the learning information and the input information;
a change information output unit that outputs the change information.

Images