Program, information processing device, and information processing method

Abstract

To provide a program capable of supporting change in action of a target person for the purpose of constitution improvement of the target person, an information processing device, and an information processing method.SOLUTION: A program causes a computer to implement a classification function and a presentation function. The classification function classifies first target persons into any of one or more target groups composed of one or more second target persons per purpose using a classification model including a plurality of purpose-classified models corresponding to each constitution improvement purpose on the basis of target person data containing measurement results of biological bodies of the first target persons. The presentation function presents one or more action plan candidates for improving constitution for the first target persons to a user on the basis of action history information indicative of a history of each action of one or more second target persons belonging to a classified target person group and improvement history information indicative of a history of improvements in each constitution of one or more second target persons by action.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a program, an information processing device, and an information processing method. [Background technology]

[0002] Conventionally, there are technologies for improving the physical constitution of a subject by changing the subject's behavior, such as lifestyle habits. Patent Document 1 below discloses a lifestyle improvement support system that extracts a first participant who meets basic conditions, including the age and gender, of a second participant, and calculates the similarity between the extracted first participant and the second participant in terms of lifestyle information related to the living environment and lifestyle habits, and physical constitution information related to the physical constitution. In this lifestyle improvement support system, when providing insurance guidance to the second participant, the first participant for whom insurance guidance has been completed and successful is displayed in order of, for example, the degree of similarity in lifestyle information and physical constitution information, based on history information indicating whether the insurance guidance for the first participant has been completed and whether the insurance guidance was successful, according to the calculated similarity. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-164670 Summary of the Invention [Problem to be solved by the invention]

[0004] Here, even if subjects have similar ages, sexes, living environments, constitutions, etc., it is conceivable that the purpose of improving their constitutions may differ, for example, the purpose may be to improve inflammatory diseases in general, or the purpose may be to rehabilitate CVA (cerebral vascular accident). However, with the technology described in Patent Document 1, it is difficult to provide support for changing behaviors in consideration of such differences in purpose.

[0005] Therefore, some aspects of the present invention aim to provide a program, an information processing device, and an information processing method that can assist a subject in changing their behavior based on the goal of improving their physical condition. [Means for solving the problem]

[0006] A program according to one embodiment of the present invention causes a computer to implement a classification function that classifies a first subject into one or more subject groups consisting of one or more second subjects for each purpose, based on subject data including results of measuring the first subject's biological characteristics, using a classification model including multiple purpose-specific models corresponding to each purpose of improving physical condition; and a presentation function that presents to a user one or more candidate action plans for improving the physical condition of the first subject, based on behavioral history information that indicates the behavioral history of each of the one or more second subjects belonging to the classified subject group, and improvement history information that indicates the history of improvements in the physical condition of each of the one or more second subjects through behavior.

[0007] An information processing device according to one embodiment of the present invention includes a classification unit that classifies the first subject into one or more subject groups consisting of one or more second subjects based on subject data indicating the results of measuring the first subject's biological characteristics, using a classification model including a plurality of purpose-specific models corresponding to each purpose of improving physical constitution, and a presentation unit that presents to a user one or more candidate action plans for improving the physical constitution of the first subject based on behavioral history information indicating the behavioral history of each of the one or more second subjects belonging to the classified subject group, and improvement history information indicating the history of improvements in the physical constitution of each of the one or more second subjects through behavior.

[0008] In an information processing method according to one embodiment of the present invention, a computer classifies a first subject into one or more subject groups consisting of one or more second subjects for each purpose, based on subject data indicating the results of measuring the first subject's biological characteristics, using a classification model including a plurality of purpose-specific models corresponding to each purpose of improving physical constitution, and presents to a user one or more candidate action plans for improving the physical constitution of the first subject based on behavioral history information indicating the behavioral history of each of the one or more second subjects belonging to the classified subject group, and improvement history information indicating the history of improvements in the physical constitution of each of the one or more second subjects through behavior. [Effects of the Invention]

[0009] According to some aspects of the present invention, it is possible to support a subject in changing his or her behavior based on the subject's goal of improving his or her physical condition. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of the system configuration of a healthcare system according to an embodiment of the present invention. [Figure 2] FIG. 1 is a diagram illustrating an example of an overview of a healthcare system according to an embodiment of the present invention. [Figure 3] FIG. 1 is a diagram illustrating an example of an overview of a healthcare system according to an embodiment of the present invention. [Figure 4] FIG. 2 is a diagram illustrating an example of a functional configuration of a server device according to the present embodiment. [Figure 5] FIG. 10 is a diagram showing an example of a screen of the healthcare system according to the present embodiment. [Figure 6] FIG. 10 is a diagram showing an example of a screen of the healthcare system according to the present embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of the operation of the server device according to the embodiment. [Figure 8] FIG. 2 is a diagram illustrating an example of a hardware configuration of a server device according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] A preferred embodiment of the present invention (hereinafter referred to as "the present embodiment") will be described with reference to the accompanying drawings. In the drawings, components with the same reference numerals have the same or similar configurations.

[0012] In this invention, the terms "unit," "means," "device," and "system" do not simply mean physical means, but also include cases where the functions of the "unit," "means," "device," and "system" are realized by software. Furthermore, the functions of one "unit," "means," "device," or "system" may be realized by two or more physical means or devices, and the functions of two or more "units," "means," "device," or "system" may be realized by one physical means or device.

[0013] <1. System configuration> An example of the system configuration of a healthcare system 1 according to this embodiment will be described with reference to FIG.

[0014] The healthcare system 1 is a system for providing healthcare to a first subject and supporting the improvement of the first subject's physical condition. For example, the healthcare system 1 analyzes data showing the results of measurements of the first subject (hereinafter also referred to as "measurement data") and, based on the results of this analysis, proposes an action plan for improving the first subject's physical condition to the first subject, the first subject's family, and / or therapists who care for the first subject (hereinafter also referred to as "stakeholders"). The first subject can then improve their physical condition by reviewing their lifestyle habits and other behaviors based on this action plan. Furthermore, if the first subject has, for example, impaired cognitive function or dementia, the first subject can also recover their cognitive function by improving their physical condition using the healthcare system 1. Note that the first subject and a second subject (described later) are collectively referred to as "subjects" unless there is a need to distinguish between them.

[0015] The measurement data may include, for example, first data obtained by mechanically measuring the first subject's body and second data obtained by measuring the first subject's body by each of multiple measurers. In other words, the first data is objective data, and the second data is subjective data obtained by the measurers. The measurers may be, for example, therapists, caregivers, and / or medical professionals in charge of the first subject. The measurement data is one type of subject data. Subjective parameters and objective parameters are described, for example, in Funabashi, M. "Citizen Science and Topology of Mind: Complexity, Computation and Criticality in Data-Driven Exploration of Open Complex Systems," Entropy 2017, 19, 181. (https: / / www.mdpi.com / 1099-4300 / 19 / 4 / 181).

[0016] Subject data is data related to a subject. In addition to measurement data, the subject data may include, for example, personal information of the subject, such as name, age, sex, and / or address. The subject data may also include, for example, treatment history information indicating the subject's treatment history and / or current illness history information indicating the subject's current illness history. The subject data may include, for example, multiple types of data. In other words, the subject data may be multivariate data consisting of values ​​of multiple variables.

[0017] The first data may include, for example, data indicating test results of the first subject through a heavy metal test that measures harmful heavy metals accumulated in the body, a mineral test that measures minerals in hair, nails, the body, etc., a vitamin test that measures vitamins in the blood, etc., a blood test, a urine test, and / or a metabolic test, etc. The first data may also be, for example, data obtained by sensing the subject's living body, such as data obtained by measuring the subject's sleep state, excretion state, pulse state, breathing state, blood pressure state, weight state, and / or body temperature state using a measuring device (not shown) such as a sensor.

[0018] The second data may include, for example, data indicating various records (e.g., nursing care records and / or medical examination records) recorded by the measurer. The second data may be, for example, quantitative data or qualitative data such as text (character strings). Furthermore, the second data may include, for example, data recorded by the subject or related parties indicating the subject's family relationships, level of enthusiasm for improving their constitution or lifestyle habits, level of stress, state of eating habits, etc.

[0019] The subject data may include, for example, the degree of commonality between a plurality of second data. The plurality of second data may be, for example, two or more pieces of data indicating the results of measurements taken by a plurality of examiners. The degree of commonality may be, for example, the degree of agreement between the plurality of quantified second data obtained by quantifying the second data using a VAS (Visual Analogue Scale) method.

[0020] According to the above configuration, by using the degree of commonality among a plurality of second data, the second data that is dependent on the measurer and may change due to the subjective thinking (especially fluctuations thereof) of each measurer can be used in a converged form, thereby enabling the use of second data with improved accuracy.

[0021] 1, the healthcare system 1 includes a server device 100 and a user device 200 used by a first subject or a user such as a care staff member or therapist who cares for the first subject. The server device 100 and the user device 200 are connected to each other via a network N so as to be able to communicate with each other.

[0022] The network N is composed of a wireless network or a wired network. Examples of the network include a mobile phone network, a PHS (Personal Handy-phone System) network, a wireless LAN (a local area network, including communication conforming to IEEE802.11 (so-called Wi-Fi (registered trademark))), 3G (3rd Generation), LTE (Long Term Evolution), 4G (4th Generation), 5G (5th Generation), WiMax (registered trademark), infrared communication, visible light communication, Bluetooth (registered trademark), a wired LAN, a telephone line, a power line communication network, a network conforming to IEEE1394, etc.

[0023] The server device 100 is an information processing device for providing a service to support improvement of the physical constitution of a subject. By executing a predetermined program, the server device 100 acquires measurement data from a measurement device or a user device 200, analyzes the acquired measurement data as subject data, and classifies the first subject into one or more subject groups based on the analysis results (in other words, clusters the first subject).

[0024] The user device 200 is an information processing device used by a user, such as a terminal such as a smartphone or laptop. By executing a predetermined program, the user device 200 cooperates with the server device 100 to send and receive information about a screen for outputting the analysis results and an action plan (hereinafter also referred to as "output information"), display this screen, and accept input from the user for selecting an action plan.

[0025] <2. Overview> An example of an overview of the healthcare system 1 will be described with reference to Fig. 2. As shown in Fig. 2, in the healthcare system 1, the server device 100 stores, as a plurality of purpose-specific models, (A) a general inflammatory disease model for all inflammatory diseases, (B) a CVA-specific model specialized for subjects with CVA (cerebral vascular accident), and (C) a stress-specific model specialized for subjects with symptoms due to stress (for example, adrenal fatigue, etc.).

[0026] The purpose-specific model is a model corresponding to each purpose of improving physical constitution (hereinafter also referred to as "improvement purpose"). The general inflammatory disease model may be, for example, a model intended to present an optimal improvement plan for a subject with an inflammatory disease. The CVA-specific model may be, for example, a model intended to improve CVA rehabilitation. The stress-specific model may be, for example, a model intended to improve stress-related symptoms by cause, such as whether the cause is alcohol or family relationships. The purpose-specific model and the metabolic feature-specific model described below may be, for example, a model using AI technology, specifically, a model trained by machine learning using training data.

[0027] (1) In the healthcare system 1, measurement data obtained by measuring the first subject through various tests and observation by the measurer is acquired, and this measurement data is input into each of a plurality of purpose-specific models stored in the server device 100.

[0028] The subject data input to the purpose-specific models may be different data depending on the model. Specifically, the input data for the CVA-specific model may include measurement data measuring the state of physical paralysis (in other words, the state of physical stiffness, etc.) of the first subject, while the input data for the inflammatory disease general model may not include this measurement data.

[0029] (2) The server device 100 inputs the subject data into a purpose-specific model and classifies the first subject into one of one or more subject groups for each improvement purpose. A subject group is a group (in other words, a cluster) made up of one or more second subjects. For example, the server device 100 may input the measurement data indicating the state of paralysis into a CVA-specialized model and use the CVA-specialized model to classify the first subject into a subject group made up of second subjects who have a similar paralysis state to the first subject. In this example, the first subject is classified into subject group Gp-A1 (a group in which glucotoxicity is estimated to be the main cause of inflammation (in other words, glucotoxicity is the greatest health issue)) among subject groups Gp-A1 to A3 in the general inflammatory disease model.

[0030] (3) The server device 100 presents candidate action plans for the first subject to the user device 200 based on the behavior history information and improvement history information of the second subject who belongs to the subject group classified in (2) above. The server device 100 identifies candidate action plans for the first subject, for example, based on the behavior history information and improvement history information of the second subject who belongs to the subject group GP-A1 classified in (2) above and whose primary cause of illness is glucotoxicity, similar to the first subject. The behavior history information is information indicating the subject's behavior history within a predetermined period. The improvement history information is information indicating the subject's improvement history of their respective constitutions within a predetermined period. The behavior history information and / or the improvement history information may be associated with each other and stored in the storage unit 130, for example. The server device 100 may associate these history information when, for example, the degree of correlation between the behavior history and the improvement history exceeds a predetermined threshold. The behavior history information and / or the improvement history information may be included in the subject data, for example.

[0031] For example, if the second subject has a behavioral history of refraining from consuming foods high in glucose, such as sweet bread, and the improvement history associated with this behavioral history indicates that glucotoxicity has been alleviated, the server device 100 may identify refraining from foods high in glucose as a candidate action plan (also referred to as "candidate plan A") and present it to a user such as a therapist. In this example, the candidate action plan identified by the subject group classified by the CVA-specialized model is called candidate plan B, and the candidate action plan identified by the subject group classified by the stress-specialized model is called candidate plan C.

[0032] (4) A user such as a therapist selects one of the candidate plans A to C presented on user device 200 to be adopted as the action plan for the first subject.

[0033] (5) The server device 100 acquires the result of the action plan selection in (4) above from the user device 200 as feedback from the user. If the objective-specific model is a model trained using training data, the server device 100 reflects the acquired selection of the action plan in the training data of the objective-specific model.

[0034] An example of the flow of processing from examination of a first subject to proposal of action plan candidates in the healthcare system 1 will be described with reference to FIG.

[0035] 1) Inspection 3, the healthcare system 1 uses a measurement device to perform a test to measure the biological characteristics of a first subject. This test may be, for example, a heavy metal test, a vitamin test, a mineral test, and / or a blood test.

[0036] 2) Analysis of characteristics In the healthcare system 1, an estimation unit 112b (described later) of the server device 100 estimates causal characteristics (hereinafter simply referred to as "causal characteristics") of a symptom such as dementia in a first subject based on subject data including first data indicating the results of the measurement in 1) above. A classification unit 112 (described later) of the server device 100 classifies the first subject into one or more subject groups to which second subjects having causal characteristics identical or similar to the estimated causal characteristics belong.

[0037] The causal characteristic may include, for example, inflammatory, glucotoxicity, stress, atrophy, toxic, vascular, and / or traumatic. Furthermore, the type of causal characteristic may be set according to, for example, the type of symptom or disease. Specifically, when the first subject has mild cognitive impairment or a neurodegenerative disease, the estimation unit 112b may estimate at least one of five types of causal characteristics of the first subject: inflammatory, glucotoxicity, stress, atrophy, and toxic. Furthermore, when the first subject has a cerebrovascular disease, the estimation unit 112b may estimate at least one of seven types of causal characteristics of the first subject: inflammatory, glucotoxicity, stress, atrophy, toxic, vascular, and traumatic.

[0038] 3) Proposing an action plan In the healthcare system 1, the presentation unit 113 of the server device 100, which will be described later, may propose an action plan to a user based on behavioral history information and improvement history information of a second subject belonging to the same group as the subject group classified based on the analysis results of the above 2). Specifically, the presentation unit 113 refers to the behavioral history information and improvement history information of the second subject belonging to the same subject group, and extracts relevant histories regarding what actions a person with the same or similar causal characteristics has taken in the past and how their constitution has improved as a result. The presentation unit 113 identifies candidate action plans based on the extracted histories. The presentation unit 113 presents the identified candidate action plans to a user, such as a medical staff member or a care staff member, as a proposed action plan. Specifically, the presentation unit 113 may output the test results of the above 1), the analysis results of the causal characteristics of the above 2), and the proposed action plan together on a screen or in a file as an examination report, such as the one shown in the examples of FIGS. 5 and 6, which will be described later.

[0039] 4) User evaluation of the proposal In the healthcare system 1, the user evaluates the proposed action plan in 3) above, such as whether it was actually effective in improving the constitution of the first subject. A receiving unit 114 of the server device 100, which will be described later, receives the evaluation of this proposal. This evaluation may be, for example, a binary evaluation (e.g., "0: good" or "1: bad"), a rating based on multiple levels (e.g., a five-level rating from 1 to 5), and / or a qualitative evaluation using text. A reflecting unit 115 of the server device 100, which will be described later, reflects this evaluation in the training data for the classification model, the selection conditions for the classification model, etc.

[0040] With the above configuration, the healthcare system 1 can classify a first subject into one or more subject groups using a model based on the purpose of physical condition improvement. Then, an action plan can be proposed based on the behavior of a second subject who belongs to the classified subject group and whose physical condition has improved in the past. Therefore, the healthcare system 1 can support the subject in changing his or her behavior based on the subject's purpose of improving his or her physical condition.

[0041] With the above configuration, the healthcare system 1 can improve the classification model by receiving feedback from the user regarding the proposed action plan, thereby providing the first subject and related parties with a service that supports more accurate physical improvement.

[0042] <3. Functional configuration> The functional configuration of the server device 100 according to this embodiment will be described with reference to Fig. 4. As shown in Fig. 4, the server device 100 includes a control unit 110, a communication unit 120, and a storage unit .

[0043] [Control Unit] The control unit 110 includes an acquisition unit 111, a classification unit 112, and a presentation unit 113. The control unit 110 may also include a reception unit 114 and / or a reflection unit 115, for example.

[0044] [Acquisition Department] The acquiring unit 111 acquires subject data from the user device 200, a measuring device that measures the living body of the first subject, a device of a third-party system, etc. The acquiring unit 111 stores the acquired subject data in the storage unit 130.

[0045] [Classification Department] The classification unit 112 refers to the model memory unit 131 and the data memory unit 132, and uses a classification model based on one or more subject data of the first subject to classify the first subject into one or more subject groups for each improvement purpose.

[0046] The classification model is a model for classifying first subjects into one or more subject groups. The subject groups are groups made up of one or more second subjects. The classification model includes multiple objective-specific models corresponding to respective improvement objectives. Furthermore, the classification model may be, for example, a model trained by a machine learning technique using training data.

[0047] The classification model may be, for example, a model using multivariate analysis in which the subject data of the first subject is used as an explanatory variable and classification into one of one or more subject groups is used as a response variable.

[0048] The classification unit 112 may standardize, for example, first data indicating the results of measurements such as blood tests, urine tests, and heavy metal tests, second data indicating the results of measurements by the subject such as stress level, exercise frequency, and / or dietary quality, and / or the degree of commonality among multiple second data. Next, if the classification model is a model based on principal component analysis and cluster analysis techniques, the classification unit 112 may use this classification model to perform principal component analysis based on the standardized first data, second data, and / or the degree of commonality. Then, the classification unit 112 may use this classification model to perform cluster analysis based on the results of the principal component analysis, thereby classifying the first subject into one or more subject groups.

[0049] The classification unit 112 may, for example, convert the second data into a numerical value by the VAS method as the degree of commonality between the plurality of second data, and calculate the degree of agreement between the plurality of digitized second data.

[0050] According to the above configuration, it is possible to comprehensively summarize subject data consisting of multiple types of related data (in other words, multivariate data) obtained from the first subject, and to clarify the relationships between the multiple types of data (in other words, between variables).

[0051] The classification unit 112 may include, for example, a learning unit 112a. The learning unit 112a may train a classification model using, for example, subject data. The learning unit 112a may use, for example, techniques such as principal component analysis, generative adversarial networks, and / or cluster analysis (in other words, clustering) as unsupervised learning. The learning unit 112a may use, for example, techniques such as random forest, SVM (Support Vector Machine), logistic regression, reinforcement learning, and / or deep reinforcement learning as supervised learning.

[0052] The classification unit 112 may select a classification model to be applied to the first subject based on, for example, selection conditions for selecting each of one or more classification models. The selection conditions may be conditions according to the improvement goal and / or metabolic characteristics of the first subject. For example, if the selection conditions for the CVA-specialized model include the condition "the improvement goal is CVA rehabilitation," and if the improvement goal of the first subject is CVA rehabilitation, the classification unit 112 may select the CVA-specialized model as the model to be applied to the first subject.

[0053] The learning unit 112a may, for example, train the classification model using training data in which the subject data is input data and the user's selection of one or more action plan candidates is used as correct answer data.

[0054] The classification model may include, for example, a plurality of metabolic feature models. A metabolic feature model is a model corresponding to each metabolic feature of a living organism (hereinafter simply referred to as a "metabolic feature"). The classification unit 112 may use a plurality of metabolic feature models to classify a first subject into one or more subject groups for each metabolic feature. Specifically, when the first subject has the causal characteristic "stress" estimated by the estimation unit 112b as a metabolic feature, the classification unit 112 may use a stress-specific model to classify the first subject into a subject group consisting of second subjects who have had stress in the past. With this configuration, it is possible to support the subject in changing their behavior based on their metabolic features.

[0055] For example, the classification unit 112 may calculate a confidence level for each subject group into which the first subject is classified for each classification model. The classification unit 112 may use the calculated confidence level as a recommendation level for the candidate action plan identified based on each subject group.

[0056] The learning unit 112a may apply a different learning method to each of the purpose-specific models or metabolic feature-specific models. In other words, the learning unit 112a may change the learning method to be applied to each of the purpose-specific models or metabolic feature-specific models.

[0057] For example, as preprocessing, the learning unit 112a may process and / or weight the learning data for each objective model and / or metabolic feature model. The learning unit 112a may weight the subject data for each improvement objective and / or metabolic feature. For example, if the improvement objective is CVA rehabilitation, data related to CVA may be weighted.

[0058] The classification unit 112 includes an estimation unit 112b. The estimation unit 112b estimates one or more causal characteristics of the symptoms related to the improvement objective in the first subject based on the subject data of the first subject. The classification unit 112 may, for example, extract cause data related to each of the one or more estimated cause characteristics from the subject data of the first subject. The classification unit 112 may classify the first subject into one or more subject groups based on the extracted cause data.

[0059] For example, when the value of homocysteine ​​or the value of CRP (C-reactive protein) in the blood, which are inflammatory markers indicated by the first data, exceed a predetermined threshold, the estimation unit 112b may estimate the causal characteristic to be inflammatory based on such homocysteine ​​value and / or CRP in the blood.Furthermore, when the value of TSH (thyroid stimulating hormone) or testosterone, which indicate the tendency of hormones secreted from the adrenal gland and are indicated by the first data, exceed a predetermined threshold, the estimation unit 112b may estimate the causal characteristic to be stress-related.

[0060] According to the above configuration, the subject data can be narrowed down to cause data corresponding to the causal characteristics of the first subject and input to the classification model. For example, if the classification model is a CVA-specialized model, the subject data may include data that is almost unrelated to CVA. Therefore, cause data that is causally related to CVA can be extracted and classification can be performed based on this extracted data so as to exclude data that is unrelated to CVA. Therefore, the first subject can be accurately and efficiently classified into one or more subject groups.

[0061] The estimation unit 112b may, for example, estimate the degree and / or proportion of one or more causal characteristics. The estimation unit 112b may, for example, estimate the degree of one or more causal characteristics based on the weighting of each of one or more subject data (in other words, may calculate the degree of one or more causal characteristics). For example, when a points system is adopted, the estimation unit 112b may assign 5 points to the degree of stress when the TSH value indicated by the first data exceeds a predetermined threshold. Furthermore, the estimation unit 112b may add 5 points to the degree of stress when the second data indicates that the first subject's stress level is "high" in addition to the first data, to give a total of 6 points as the degree of the causal characteristics.

[0062] The estimation unit 112b may estimate the metabolic characteristics based on the degree and / or proportion of one or more estimated causal characteristics. For example, if the degree of stress sensitivity exceeds a predetermined threshold, the estimation unit 112b may estimate that there is a metabolic problem in stress sensitivity. Based on the result of this estimation, for example, the classification unit 112 may classify the first subject into one or more subject groups using the stress sensitivity specialization model shown in the example of FIG. 2.

[0063] [Presentation part] The presentation unit 113 presents various information and data to the user. The presentation unit 113 may present the various information in any manner, for example, it may generate output information for outputting action plan candidates to a screen or a file, and transmit this output information to the user device 200 used by the user to whom the output information is to be presented.

[0064] The presentation unit 113 presents to the user one or more candidate action plans for improving the constitution of the first subject, for example, based on the behavioral history information and improvement history information of one or more second subjects. The presentation unit 113 identifies the second subject whose constitution can be considered to have improved, for example, based on the improvement history information. Next, the presentation unit 113 identifies past behaviors of the second subject that have a predetermined correlation with the improvement of the constitution, based on the behavioral history information of the identified second subject. Then, the presentation unit 113 may identify the identified past behaviors as candidate action plans.

[0065] According to the above configuration, the presentation unit 113 can present an action plan based on the behavior of a second subject whose constitution has been improved in the past and who belongs to a subject group classified using a model for improving physical constitutions according to the subject's purpose. Therefore, it is possible to support the subject in changing his or her behavior based on the subject's purpose for improving his or her physical constitution.

[0066] 5 and 6, examples of screen or file output by the presentation unit 113 will be described. As shown in FIG. 5, the report screen A1 output by the presentation unit 113 may include a test result area a11 showing measurement results from various tests as the first data of the first subject. Furthermore, the test result area a11 may include, for example, an area a11a showing the results of a heavy metal test, an area a11b showing the results of a vitamin and mineral test, and an area a11c showing the results of a blood test.

[0067] 6, the report screen A1 may include, in addition to the areas shown in FIG. 5, an analysis result area a12 showing the results of the estimation of the causal characteristics and a proposal area a13 showing a proposal of an action plan. The proposal area a13 includes, for example, an area a13a showing a list of candidate action plans and an area a13b showing, in text, the action plans corresponding to each of the estimated causal characteristics. For example, in the area a13a, the presentation unit 113 may output a list including three candidate action plans No. 1 to No. 3 (denoted as "care plans" in FIG. 5) and the recommendation level of each candidate.

[0068] [Reception] Continuing the explanation, returning to Fig. 4, the accepting unit 114 accepts a selection of an action plan to be used for the first target person from among one or more candidate action plans presented by the presenting unit 113 from the user.

[0069] The receiving unit 114 may receive, for example, an evaluation of one or more action plans from a user. The evaluation from the user may be, for example, an evaluation using the Functional Independence Measure (FIM), which is an index of activities of daily living, or the PGC Moral Scale, which is an index of QOL. Furthermore, the evaluation from the user may be, for example, answers to questions set for evaluating the condition of each subject, which are set for each subject.

[0070] [Reflection section] The reflecting unit 115 reflects the selection of the action plan accepted by the accepting unit 114 in the learning data. Furthermore, the reflecting unit 115 may, for example, reflect the selection of the action plan accepted by the accepting unit 114 and / or the selected action plan, and in turn, the user's evaluation of the classification model on which the action plan is based, in the selection conditions for the classification model. For example, when a statistical value of user evaluations over a predetermined period of time for action plans presented using a classification model of cluster analysis exceeds a predetermined threshold, the reflecting unit 115 may determine that the performance of the cluster analysis algorithm is good and change the selection conditions to select this classification model.

[0071] According to the above configuration, the user's selection and evaluation of the action plan can be fed back to the selection of the classification model, thereby enabling the first subject to be classified into one or more subject groups with high accuracy.

[0072] [Communications Department] The communication unit 120 transmits and receives various information including subject data and output information to and from the user device 200, the measurement device, and the like via the network N.

[0073] [Storage] The storage unit 130 stores the classification model, subject data, output information, etc. The storage unit 130 may store each piece of information using a database management system (DBMS), or may store each piece of information using a file system. When using a DBMS, a table may be provided for each piece of information, and each piece of information may be managed by associating these tables.

[0074] The storage unit 130 may include, for example, a model storage unit 131. The model storage unit 131 stores the classification model. The storage unit 130 may also include, for example, a data storage unit 132. The data storage unit 132 stores subject data.

[0075] <4. Example of operation> An example of the operation of the server device 100 according to this embodiment will be described with reference to Fig. 7. Note that the order of processing in the flow chart shown below is an example and may be changed as appropriate.

[0076] 7, the receiving unit 114 of the server device 100 receives a request to present a report including candidate action plans from a user via the user device 200 (step S10). Next, the acquiring unit 111 of the server device 100 acquires subject data of a first subject (step S11).

[0077] Next, the classification unit 112 of the server device 100 classifies the first subject into one or more subject groups for each improvement purpose using a classification model including multiple purpose-specific models (step S12). Next, the presentation unit 113 extracts behavior history information and improvement history information of the second subject belonging to the one or more classified subject groups (step S13). Next, the presentation unit 113 identifies one or more candidate action plans based on the extracted behavior history information and improvement history information (step S14). Next, the presentation unit 113 presents the identified one or more candidate action plans to the user (step S15).

[0078] The receiving unit 114 receives from the user a selection of an action plan to be used for the first subject from among the one or more presented action plan candidates (step S16). The reflecting unit 115 reflects the selected action plan in the learning data of the classification model (step S17).

[0079] <5. Hardware Configuration> 8, an example of a hardware configuration in which the above-described server device 100 is realized by a computer 800 will be described. Note that the functions of each device can also be realized by dividing them into multiple devices.

[0080] As shown in FIG. 8, the computer 800 includes a processor 801, a memory 803, a storage device 805, an input I / F unit 807, a data I / F unit 809, a communication I / F unit 811, and a display device 813.

[0081] The processor 801 controls various processes in the computer 800 by executing programs stored in the memory 803. For example, each functional unit included in the control unit 110 of the server device 100 can be realized by the processor 801 executing a program temporarily stored in the memory 803.

[0082] The memory 803 is a storage medium such as a RAM (Random Access Memory), etc. The memory 803 temporarily stores the program code of the program executed by the processor 801 and data required when the program is executed.

[0083] The storage device 805 is a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 805 stores an operating system and various models and programs for realizing the above-mentioned configurations. In addition, the storage device 805 can also store a table for registering subject data and a DB for managing this table. Such programs and data are loaded into the memory 803 as needed and referenced by the processor 801.

[0084] The input I / F unit 807 is a device for receiving input from a user. Specific examples of the input I / F unit 807 include a keyboard, a mouse, a touch panel, various sensors, and a wearable device. The input I / F unit 807 may be connected to the computer 800 via an interface such as a USB (Universal Serial Bus).

[0085] The data I / F unit 809 is a device for inputting data from outside the computer 800. A specific example of the data I / F unit 809 is a drive device for reading data stored in various storage media. The data I / F unit 809 may be provided outside the computer 800. In this case, the data I / F unit 809 is connected to the computer 800 via an interface such as a USB.

[0086] The communication I / F unit 811 is a device for performing data communication via the Internet N, either wired or wirelessly, with devices external to the computer 800. The communication I / F unit 811 may be provided outside the computer 800. In this case, the communication I / F unit 811 is connected to the computer 800 via an interface such as a USB.

[0087] The display device 813 is a device for displaying various types of information. Specific examples of the display device 813 include a liquid crystal display, an organic EL (Electro-Luminescence) display, and a display of a wearable device. The display device 813 may be provided outside the computer 800. In this case, the display device 813 is connected to the computer 800 via, for example, a display cable. Furthermore, when a touch panel is adopted as the input I / F unit 807, the display device 813 can be configured as an integral part of the input I / F unit 807.

[0088] The above-described embodiments are merely examples for explaining the present invention, and are not intended to limit the present invention to these embodiments. Furthermore, the present invention can be modified in various ways without departing from the spirit of the invention. Furthermore, those skilled in the art can adopt embodiments in which the above-described elements are replaced with equivalents, and such embodiments are also within the scope of the present invention.

[0089] The components of the server device described in the above embodiment are assumed to realize predetermined processing in cooperation with other hardware by the processor 801 executing a program stored in the storage device 805. In other words, these components are assumed to be software or firmware, as well as corresponding hardware, and in both of these concepts, they are also referred to as "functions," "means," "parts," "processing circuits," "units," or "modules," and can be interpreted as such.

[0090] [Variations] Although the present invention has been described based on the above embodiment, the following cases are also included in the present invention.

[0091] [Variation 1] At least some of the components of the server device 100 according to the above embodiment may be included in the user device 200. For example, the function of the presentation unit 113 of the control unit 110 in the server device 100 may be implemented in the user device 200. Specifically, the user device 200 may implement these components by, for example, installing an application program dedicated to the healthcare system 1 and executing this program.

[0092] [Variation 2] In the above embodiment, an example has been described in which the storage unit 130 of the server device 100 includes the model storage unit 131 as a location for storing the classification model, but the location where the classification model is stored is not limited to this. The classification model may be stored in a storage unit of an external device, for example. The classification unit 112 of the server device 100 may, for example, instruct an API provided by the external device for using the functions of the classification model to classify the first subject into one or more subject groups using the classification model. In response to this instruction, the classification unit 112 may obtain classification information indicating the classification result (e.g., indicating which subject group the first subject belongs to) from the external device via the communication unit 120.

[0093] [Variation 3] In the above embodiment, an example has been described in which the control unit 110 of the server device 100 includes the learning unit 112a that trains the classification model. However, the learning unit according to the present invention is not limited to this. For example, the learning unit according to the present invention may be included in a device different from the device that includes the classification unit that classifies the first subject into one or more subject groups using the classification model. This different device may be, for example, an external device in a third-party system different from the healthcare system 1. For example, the acquisition unit 111 included in the control unit 110 of the server device 100 may acquire a trained classification model (in other words, a trained classification model) from an external device and store the acquired classification model in the model storage unit 131. [Explanation of symbols]

[0094] 1...healthcare system, 100...server device, 110...control unit, 111...acquisition unit, 112...classification unit, 113...presentation unit, 114...reception unit, 115...reflection unit, 120...communication unit, 130...storage unit, 200...user device, 800...computer, 801...processor, 803...memory, 805...storage device, 807...input I / F unit, 809...data I / F unit, 811...communication I / F unit, 813...display device.

Claims

1. On the computer, a classification function for classifying the first subject into one or more subject groups each consisting of one or more second subjects for each purpose, using a classification model including a plurality of purpose-specific models corresponding to each purpose of constitution improvement, based on subject data including the results of measuring the living body of the first subject; a presentation function of presenting to a user one or more action plan candidates for improving the constitution of the first subject based on behavior history information indicating the behavior history of each of the one or more second subjects belonging to the classified subject group and improvement history information indicating the history of improvement in the constitution of each of the one or more second subjects due to the behavior, the subject data includes first data which is objective data of the first subject and second data which is subjective data of the first subject, the first data includes at least data indicating a test result of the first subject or data obtained by sensing a living body of the first subject; The second data includes at least data indicating various records recorded by a person other than the first subject. program.

2. The classification model includes a plurality of metabolic feature models corresponding to respective metabolic features of the living organism; The classification function classifies the first subject into one of the one or more subject groups for each of the metabolic characteristics. The program according to claim 1.

3. The computer, a learning function that uses learning data in which the subject data is input data and a user's selection of the one or more action plan candidates is used as correct answer data to learn the classification model; a reception function for receiving, from the user, a selection of an action plan to be used for the first target person from the presented one or more candidate action plans; a reflection function of reflecting the selected action plan in the learning data; The program according to claim 1 or 2.

4. The subject data includes multiple types of data, The classification model is a model using multivariate analysis with the subject data as an explanatory variable and the classification into one of the one or more subject groups as a response variable. The program according to claim 1 or 2.

5. The subject data includes a degree of commonality between a plurality of the second data. The program according to claim 1 or 2.

6. The subject data includes multiple types of data, the classification function comprises an estimation function; The estimation function estimates characteristics of one or more causes of the symptom of interest in the first subject based on the subject data; the classification function extracts cause data relating to each of the characteristics of the one or more estimated causes from the plurality of types of data, and classifies the first subject into one of the one or more subject groups based on the extracted cause data. The program according to claim 1 or 2.

7. a classification unit that classifies the first subject into one or more subject groups each composed of one or more second subjects, using a classification model including a plurality of purpose-specific models corresponding to each purpose of constitution improvement, based on subject data indicating the results of measuring the living body of the first subject; a presentation unit that presents to a user one or more candidate action plans for improving the constitution of the first subject based on behavior history information indicating the behavioral history of each of the one or more second subjects belonging to the classified subject group and improvement history information indicating the history of improvement in the constitution of each of the one or more second subjects due to the behavior; An information processing device comprising: the subject data includes first data which is objective data of the first subject and second data which is subjective data of the first subject, the first data includes at least data indicating a test result of the first subject or data obtained by sensing a living body of the first subject; The second data includes at least data indicating various records recorded by a person other than the first subject. Information processing device.

8. The computer Based on subject data indicating the results of measuring the living body of the first subject, using a classification model including a plurality of purpose-specific models corresponding to each purpose of constitution improvement, classifying the first subject into one or more subject groups composed of one or more second subjects for each purpose; presenting to the user one or more candidate action plans for improving the constitution of the first subject based on behavior history information indicating the behavioral history of each of the one or more second subjects belonging to the classified subject group and improvement history information indicating the history of improvement in the constitution of each of the one or more second subjects due to the behavior; An information processing method, comprising: the subject data includes first data which is objective data of the first subject and second data which is subjective data of the first subject, the first data includes at least data indicating a test result of the first subject or data obtained by sensing a living body of the first subject; The second data includes at least data indicating various records recorded by a person other than the first subject. Information processing methods.

Images