Programs, information processing devices, methods, and systems

Abstract

To provide a program, an information processing device, a method, and a program for specifying optimal means for recommending reception of medical examination for a subject to whom medical examination is to be recommended.SOLUTION: In a system for studying means for recommending reception of medical examination in which a terminal device and a server are capable of communicating with each other via a network, a program that operates the server causes the server to execute: acquiring medical examination recommendation history data (S900); generating at lease one intervention pattern including at least one intervention measure which is means for recommending reception of medical examination (S903); generating, for each intervention pattern, teacher data in which results of recommendation for receiving medical examination are output for input of the intervention pattern from the medical examination recommendation history data (S904); generating a machine learning model for each intervention pattern by using the teacher data (S905); inputting the intervention pattern to the machine learning model and thereby acquiring an output for each subject which is an inference result of the machine learning model (S906); and determining the best intervention pattern for each subject on the basis of the output (S908).SELECTED DRAWING: Figure 9

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , ,

[0003] , , , , ,

[0001] This disclosure relates to a program, an information processing apparatus, a method, and a system.

Background Art

[0002] As a technique for sending a recommendation notice to a subject of a specific health check or the like, the technique disclosed in Patent Document 1 is known. The technique disclosed in Patent Document 1 relates to a method for optimizing the timing of a recommendation notice to an insured person who promotes various medical acts and health checkups performed by a medical insurance institution, and is an explanatory variable extracted from a plurality of feature amounts related to the insured person, and the optimal timing of the recommendation notice for each individual insured person is calculated using regression analysis or machine learning based on the explanatory variable, or a score indicating the magnitude of the recommendation effect for each period is calculated as the objective variable.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] [[ID=3,5]]The technique disclosed in Patent Document 1 obtains the optimization of the timing of the recommendation notice to the insured person by a machine learning model, and cannot compare a plurality of examination recommendation means and specify the optimal examination recommendation means.

[0005] Therefore, this disclosure has been made to solve the above problems, and its object is to provide a technique capable of specifying an optimal examination recommendation means for an examination recommendation target person.

Means for Solving the Problems

[0006] A program for operating a computer equipped with a processor, the program causes the processor to perform the following steps: a first step of acquiring health checkup recommendation history data which includes at least personal information of persons to be recommended for health checkups, past health checkup results of the persons, and the results of recommendations for health checkups to the persons; a second step of generating at least one intervention pattern which includes at least one intervention measure that is a means of recommending health checkups; a third step of generating training data for each intervention pattern from the health checkup recommendation history data, with the intervention pattern generated in the second step as input and the results of health checkup recommendations as output; a fourth step of generating a machine learning model for each intervention pattern using the training data generated in the third step; a fifth step of inputting the intervention pattern into the machine learning model generated in the fourth step to obtain an output which is the inference result of the machine learning model for each person; and a sixth step of finding the best intervention pattern for each person based on the output obtained in the fifth step. [Effects of the Invention]

[0007] According to this disclosure, it is possible to identify the optimal means of encouraging individuals to undergo medical examinations. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows the overall configuration of a system according to one embodiment. [Figure 2] This figure shows the functional configuration of a terminal device according to one embodiment. [Figure 3] This figure shows the functional configuration of a server according to one embodiment. [Figure 4] This figure shows the data structure of a health checkup recommendation history database according to one embodiment. [Figure 5] This figure shows an example of the data structure of an intervention strategy database according to one embodiment. [Figure 6] This figure shows an example of the data structure of an intervention pattern database according to one embodiment. [Figure 7]This figure shows an example of the data structure of an individual improvement rate database according to one embodiment. [Figure 8] This figure shows an example of the data structure of a definitive intervention pattern database according to one embodiment. [Figure 9] A flowchart showing an example of the processing flow in a system according to one embodiment. [Figure 10] This figure shows an example of an intervention measure in a system according to one embodiment. [Figure 11] This figure shows an example of a method for encouraging people to undergo health checkups in a system according to one embodiment. [Modes for carrying out the invention]

[0009] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0010] Furthermore, in the following description, "processor" refers to one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

[0011] Furthermore, at least one processor may be a broad-sense processor, such as a hardware circuit that performs some or all of the processing (e.g., an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit)).

[0012] In the following description, the expression "xxx table" may be used to describe information from which an output can be obtained for an input. However, this information may be data of any structure or a learning model such as a neural network that generates an output for an input. Therefore, "xxx table" can be referred to as "xxx information".

[0013] In the following description, the configuration of each table is an example. One table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0014] In the following description, the "program" may be used as the subject to describe a process. However, since the program is executed by a processor to perform a defined process while appropriately using a storage unit and / or an interface unit, etc., the subject of the process may be the processor (or a device such as a controller having that processor).

[0015] The program may be installed in a device such as a computer, or may be on, for example, a program distribution server or a computer-readable (e.g., non-temporary) recording medium. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0016] In the following description, an identification number is used as identification information for various objects, but other types of identification information (e.g., an identifier including letters or symbols) may be adopted.

[0017] In the following description, when describing elements of the same type without distinction, reference signs (or common signs among the reference signs) are used, and when describing elements of the same type by distinction, the identification numbers (or reference signs) of the elements may be used.

[0018] Furthermore, in the following explanation, only control lines and information lines deemed necessary for the explanation are shown, and not all control lines and information lines in the product are necessarily shown. All components may be interconnected.

[0019] <0 System Overview> The system disclosed herein seeks to provide a means of encouraging health checkups that maximizes the effectiveness of such notices when health insurance associations, local governments, etc., send notices encouraging health checkups to insured persons and dependents of health insurance associations who are eligible for health checkups (hereinafter sometimes simply referred to as "eligible persons").

[0020] The entities that encourage people to undergo health checkups (hereinafter referred to as "health insurance organizations") include health insurance associations and local governments, but the system related to this disclosure does not intend to limit the entities to these health insurance associations, etc. Similarly, the target recipients of health checkup recommendations are mainly insured persons and dependents of health insurance associations, or residents who have their domicile or residence in a local government, but the system related to this disclosure does not intend to limit the target recipients to these association members, etc. Furthermore, the health insurance covered by health insurance associations may include all health insurance included in the medical insurance system implemented in the country covered by the system related to this disclosure, such as so-called national health insurance, seamen's insurance, and mutual aid associations.

[0021] The health checkups that eligible individuals are encouraged to undergo are conducted by health insurance organizations (including cases where the organization is contracted to conduct the checkup). Generally, such health checkups are conducted repeatedly on an annual basis. Eligible individuals are encouraged to undergo health checkups within the relevant fiscal year. Health checkups that eligible individuals are encouraged to undergo include general health checkups, specific health checkups, and gynecological health checkups for women. While there are often age restrictions attached to the eligibility for these health checkups, age restrictions are not mandatory in the system related to this disclosure. Similarly, there is no intention to limit the types of health checkups in the system related to this disclosure.

[0022] For health insurance organizations that conduct (or oversee) health checkups, it is important that eligible individuals undergo health checkups to properly understand their own health status and, preferably, receive appropriate medical treatment, from the perspective of ensuring that eligible individuals pay appropriate medical expenses (which ultimately leads to the optimization of expenses incurred by the health insurance organization). From this perspective, health insurance organizations encourage eligible individuals to undergo health checkups. Therefore, health insurance organizations have an incentive to improve the health checkup participation rate. At the very least, health insurance organizations have an incentive to properly understand the rate at which eligible individuals responded to their health checkup recommendations (this includes the rate at which individuals read the recommendation notice, searched for a health checkup provider based on the recommendation notice, and even made a reservation for a health checkup at that provider), and to implement measures to improve that rate.

[0023] Therefore, the system disclosed herein acquires health checkup recommendation history data, including the results of past health checkup recommendations to the target individual, sets combinations of means for recommending health checkups to the target individual, infers the relationships between these means using a machine learning model, and finds the best combination of health checkup recommendation means from among several combinations.

[0024] In selecting the "best combination of means for encouraging medical examinations," parameters are needed to determine what constitutes the best combination. In a simplistic view, one might consider the best combination to be the one that maximizes the improvement rate in the target population's participation in health checkups. However, one could also consider a recommendation effective if it maximizes the rate of health checkup reservations, or if it maximizes the response rate to the recommendation (e.g., viewing the recommendation message). The system operator responsible for this disclosure can decide how to set these parameters, but in the following explanation, the "best combination of means for encouraging medical examinations" will be defined as the combination that maximizes the rate of health checkup reservations.

[0025] Furthermore, in the system related to this disclosure, the "best combination of means for encouraging medical examination" is determined on a case-by-case basis for each individual. Therefore, at the individual level, the combination of means for encouraging medical examination that maximizes the rate of health checkup reservations corresponds to the individual making a health checkup reservation. Alternatively, individuals may be grouped based on their characteristics (e.g., health insurance organization, place of residence), and the "best combination of means for encouraging medical examination" may be sought for each group. In this case, the combination of means for encouraging medical examination that maximizes the rate of health checkup reservations becomes the "best combination of means for encouraging medical examination."

[0026] In this specification, the means of encouraging target individuals to undergo health checkups are referred to as "interventions," and a combination of interventions that includes at least one intervention is referred to as an "intervention pattern." An example of interventions is shown in Figure 10. In the example shown in Figure 10, the interventions are classified into several categories (e.g., message content, approach methods, etc.). An intervention pattern is generated by selecting one of the interventions classified into each category. It is not necessary to select multiple interventions classified into a single category to generate an intervention pattern. For example, it is not necessary to select both direct mail and telephone as interventions classified as approach methods to generate an intervention pattern. Furthermore, an intervention pattern can be generated by selecting just one intervention from a single category; it is not necessary to individually select interventions from multiple categories to generate an intervention pattern. Moreover, an intervention pattern that does not include any interventions may also be generated as an intervention pattern in the system relating to this disclosure. This is because it is preferable to compare the best intervention pattern with the case in which no health checkup is encouraged for the target individuals.

[0027] Furthermore, the system described in this disclosure is naturally applicable not only to encouraging people to undergo health checkups, but also to diagnosing the presence or absence of specific diseases, such as cancer screenings. In this specification, the term "screening" is used to encompass both health checkups and screenings. However, unless there is a need to distinguish between health checkups and screenings such as cancer screenings, the terms "health checkup" and "screening" may be used for ease of understanding. Even in this case, it should not be interpreted that the system described in this disclosure applies only to "health checkups" and "screenings."

[0028] <One Embodiment> <1 System Configuration Diagram> Figure 1 shows the overall configuration of the medical consultation recommendation system 1 (hereinafter simply referred to as System 1) of this embodiment. As shown in Figure 1, System 1 includes a plurality of terminal devices (in Figure 1, terminal devices 10a and 10b are shown; hereinafter collectively referred to as "Terminal Device 10"), a server 20, and an external data server 30. The terminal devices 10 and the server 20 are connected to each other so as to be able to communicate with each other via a network 80. The network 80 is composed of a wired or wireless network. In this embodiment, the server 20 is a server that functions as a web server (including a cloud server) and exchanges information with the terminal devices 10 via web pages. In addition, the terminal devices 10 have a web page browser installed for viewing web pages, but a dedicated application for providing services from the server 20 may also be installed and configured to be viewable by the dedicated application.

[0029] Since the hardware configuration of terminal device 10a and terminal device 10b are the same, the explanation of the hardware configuration of terminal device 10 will be omitted by explaining the hardware configuration of terminal device 10a.

[0030] Terminal device 10 is a device operated by a user considering recommending a health checkup. Terminal device 10 can be implemented as a stationary PC (Personal Computer), laptop PC, etc. Alternatively, terminal device 10 may be a mobile device such as a tablet compatible with a mobile communication system or a smartphone.

[0031] The terminal device 10 is connected to the server 20 via the network 80 in a communicative manner. The terminal device 10 connects to the network 80 by communicating with communication equipment such as a wireless base station 81 that supports communication standards such as 4G, 5G, and LTE (Long Term Evolution), and a wireless LAN router 82 that supports wireless LAN (Local Area Network) standards such as IEEE (Institute of Electrical and Electronics Engineers) 802.11. As shown in Figure 1, the terminal device 10 includes a communication interface 12, an input device 13, an output device 14, a memory 15, a storage unit 16, and a processor 19.

[0032] The communication interface 12 is an interface for inputting and outputting signals so that the terminal device 10 can communicate with external devices. The input device 13 is an input device (for example, a keyboard, touch panel, touchpad, mouse, or other pointing device) for receiving input operations from the user. The output device 14 is an output device (display, speaker, etc.) for presenting information to the user. The memory 15 is for temporarily storing programs and data processed by programs, etc., and is a volatile memory such as DRAM (Dynamic Random Access Memory). The storage unit 16 is a storage device for saving data, such as flash memory or an HDD (Hard Disk Drive). The processor 19 is hardware for executing the instruction set written in the program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0033] Server 20 is managed by the administrator of System 1 in this embodiment, and its stored contents can be modified, added, or deleted as needed by the user of Terminal Device 10.

[0034] Server 20 is a computer connected to network 80. Server 20 includes a communication interface 22, an input / output interface 23, memory 25, storage 26, and a processor 29.

[0035] Communication IF22 is an interface for inputting and outputting signals so that the server 20 can communicate with external devices. Input / Output IF23 functions as an interface to an input device for receiving input operations from the user and an output device for presenting information to the user. Memory 25 is for temporarily storing programs and data processed by programs, etc., and is a volatile memory such as DRAM (Dynamic Random Access Memory). Storage 26 is a storage device for saving data, such as flash memory or HDD (Hard Disk Drive). Processor 29 is hardware for executing the instruction set written in the program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0036] The external data server 30 is a server that stores health checkup recommendation history data, which includes at least the personal information of individuals who are encouraged to undergo health checkups (including medical examinations), the results of past health checkups (including medical examinations) of those individuals, and the results of recommendations for health checkups (including medical examinations) to those individuals. As such a server, a combination of a server that stores so-called claims data owned by a health insurance organization and a server that stores the results of past health checkup recommendations can be considered. Typically, these servers are configured as separate entities. Therefore, the external data server 30 shown in Figure 1 may be composed of multiple servers. In addition, personal information may also be configured separately from the server that stores past health checkup results and the server that stores the results of health checkup recommendations. Furthermore, the external data server 30 is not required to provide all of the claims data and the data on the results of past health checkup recommendations to the system 1 according to this embodiment. The external data server 30 may provide the necessary data from among this data based on a request from the system 1 according to this embodiment, or it may prepare a server that stores only the necessary data and allow the system 1 according to this embodiment to access this server.

[0037] <1.1 Functional configuration of terminal device 10> Figure 2 is a block diagram showing an example of the functional configuration of the terminal device 10 shown in Figure 1. The terminal device 10 shown in Figure 2 can be implemented, for example, by a PC, a mobile terminal, or a wearable terminal. As shown in Figure 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. Each block included in the terminal device 10 is electrically connected, for example, by a bus.

[0038] The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and transmits it to an external source (for example, the server 20). The communication unit 120 performs reception processing on the signal received from an external source and outputs it to the control unit 190.

[0039] The input device 13 is a device for a user operating the terminal device 10 to input instructions or information. The input device 13 may be implemented as, for example, a keyboard, mouse, reader, etc. If the terminal device 10 is a mobile terminal, it may be implemented as a touch-sensitive device 131, etc., to which instructions are input by touching the operating surface. The input device 13 converts the instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that accepts electrical signals input from an external input device.

[0040] The output device 14 is a device for presenting information to the user operating the terminal device 10. The output device 14 is implemented, for example, by a display 141. The display 141 displays data according to the control of the control unit 190. The display 141 is implemented, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0041] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of the audio signal. The audio processing unit 17 converts the signal received from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is implemented, for example, by an audio processing processor. The microphone 171 receives an audio input and provides the audio signal corresponding to that audio input to the audio processing unit 17. The speaker 172 converts the audio signal received from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0042] The storage unit 180 is implemented by, for example, memory 15 and storage unit 16, and stores data and programs used by the terminal device 10.

[0043] The control unit 190 is realized when the processor 19 reads the application program 181 stored in the storage unit 180 and executes the instructions contained in the application program 181. The control unit 190 controls the operation of the terminal device 10. By operating according to the application program 181 stored in the storage unit 180, the control unit 190 performs the functions of an operation reception unit 191, a transmission / reception unit 192, a data processing unit 193, and a presentation control unit 194.

[0044] The operation reception unit 191 processes instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 receives information based on instructions input from a keyboard, mouse, etc.

[0045] Furthermore, the operation reception unit 191 receives voice instructions input from the microphone 171. Specifically, for example, the operation reception unit 191 receives voice signals input from the microphone 171 and converted into digital signals by the voice processing unit 17. The operation reception unit 191 obtains instructions from the user by, for example, analyzing the received voice signals and extracting predetermined nouns.

[0046] The transmitting / receiving unit 192 performs processing to enable the terminal device 10 to send and receive data with external devices such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 transmits the business content entered by the user to the server 20. The transmitting / receiving unit 192 also receives information about the user from the server 20.

[0047] The data processing unit 193 performs calculations on the data received as input by the terminal device 10 according to the application program 181 and outputs the calculation results to the memory 15 or the like.

[0048] The presentation control unit 194 controls the output device 14 in order to present information provided by the server 20 to the user. Specifically, for example, the presentation control unit 194 displays the information transmitted from the server 20 on the display 141. The presentation control unit 194 also outputs the information transmitted from the server 20 through the speaker 172.

[0049] <1.2 Functional Configuration of Server 20> Figure 3 shows an example of the functional configuration of server 20. As shown in Figure 3, server 20 functions as a communication unit 201, a storage unit 202, and a control unit 203.

[0050] The communications unit 201 performs processing to enable the server 20 to communicate with external devices.

[0051] The memory unit 202 includes, for example, a health checkup recommendation history DB (DataBase) 2022, an intervention strategy DB 2023, an intervention pattern DB 2024, an individual improvement rate DB 2025, a confirmed intervention pattern DB 2026, training data 2027, a learning model 2028, and the like.

[0052] The Health Checkup Recommendation History DB2022 is a database that stores health checkup recommendation history data acquired from the external data server 30. As already explained, the health checkup recommendation history data includes at least the personal information of individuals who are recommended to undergo health checkups (including medical examinations), the results of past health checkups (including medical examinations) of those individuals, and the results of recommendations for health checkups (including medical examinations) to those individuals, but it may also include other data. For example, if the external data server 30 includes a server that stores data related to medical claims, the data that constitutes the medical claims data may be stored in the Health Checkup Recommendation History DB2022 as health checkup recommendation history data. The health checkup recommendation history data stored in the Health Checkup Recommendation History DB2022 is stored by the Health Checkup Recommendation History Acquisition Module 2033, which will be described later, and is added, deleted, and updated as needed. Details will be described later.

[0053] The intervention plan DB2023 is a database containing intervention plans that can be implemented for a target individual in System 1 according to this embodiment. It is preferable that the data stored in the intervention plan DB2023 is pre-stored by the operator of System 1 according to this embodiment, and that additions, deletions, and updates are made as needed. Further details will be described later.

[0054] The types of interventions to be stored in the Intervention DB2023 are also related to whether the intervention patterns described later will lead to effective recommendations for medical consultation. One possible approach is to first set the categories shown in Figure 10 as interventions, and then set detailed interventions for the categories that will lead to effective recommendations for medical consultation.

[0055] The intervention pattern DB2024 is a database containing intervention patterns to be considered for implementation for a target individual in System 1 according to this embodiment. The data stored in the intervention pattern DB2024 is generated and stored by the intervention pattern generation module 2035, which will be described later, and is added, deleted, and updated as needed. Details will be described later.

[0056] The Individual Improvement Rate DB2025 is a database that stores the improvement rate of parameters related to health checkup attendance, which is estimated (inferred by the learning model 2028) as a result of adopting each intervention pattern. The parameters related to health checkup attendance may be determined as appropriate by the operator of System 1 according to this embodiment, but in System 1 according to this embodiment, the parameters related to health checkup attendance are mainly the rate of booking health checkups (including health examinations), as described above. The data stored in the Individual Improvement Rate DB2025 is calculated and stored by the Individual Improvement Rate Calculation Module 2037, which will be described later, and is added, deleted, and updated as appropriate. Here, the Individual Improvement Rate Calculation Module 2037 calculates the individual improvement rate for each target person. Details will be described later.

[0057] The Confirmed Intervention Pattern DB2026 is a database that stores information indicating the intervention patterns that have been confirmed to be implemented for each individual, based on the calculated individual improvement rate. The Confirmed Intervention Pattern DB2026 is determined (confirmed) and stored by the Intervention Pattern Confirmation Module 2038, described later, and is added, deleted, and updated as needed.

[0058] Training data 2027 is training data that takes intervention patterns stored in intervention pattern DB2024 as input and outputs the results of recommendations for receiving health checkups (including medical examinations). Training data 2027 is generated for each target person by the learning model generation module 2036, which will be described later, and is added, deleted, and updated as needed.

[0059] The learning model 2028 is obtained by performing machine learning according to the model learning program (not shown in the diagram) based on the training data 2027 described above. When a specific intervention pattern is input to this learning model 2028, the inference result provides a recommendation to undergo a health checkup (including a medical examination). The learning model 2028 is generated for each individual by the learning model generation module 2036, which will be described later, and is added, deleted, and updated as needed. Therefore, the output of the learning model 2028 is also an output for each individual.

[0060] The learning model 2028 according to this embodiment is, for example, a parameterized composite function composed of multiple functions. A parameterized composite function is defined by a combination of multiple tunable functions and parameters. The prediction model according to this embodiment may be any parameterized composite function that satisfies the above requirements, but is assumed to be a multi-layer network model (hereinafter referred to as a multi-layer network). A prediction model using a multi-layer network has an input layer, an output layer, and at least one intermediate or hidden layer between the input and output layers. The prediction model is intended to be used as a program module that is part of artificial intelligence software.

[0061] As the multilayer network according to this embodiment, for example, a deep neural network (DNN), which is a multilayer neural network targeted by deep learning, may be used. As the DNN, for example, a convolutional neural network (CNN) that targets images may be used.

[0062] Furthermore, the above is merely an example of a predictive model, and a predictive model may have other configurations. For example, the predictive model may be a rule-based model in which intervention patterns and the results of health checkup recommendations are variables, and each variable is described by a function to which coefficients derived from past performance are attached.

[0063] The control unit 203 is realized when the processor 29 reads the application program 2021 stored in the memory unit 202 and executes the instructions contained in the application program 2021. By operating according to the application program 2021, the control unit 203 performs the functions shown as a reception control module 2031, a transmission control module 2032, a health checkup recommendation history acquisition module 2033, an intervention measure selection module 2034, an intervention pattern generation module 2035, a learning model generation module 2036, an individual improvement rate calculation module 2037, an intervention pattern confirmation module 2038, and a health checkup recommendation implementation module 2039.

[0064] The receive control module 2031 controls the process by which the server 20 receives signals from external devices according to a communication protocol.

[0065] The transmission control module 2032 controls the process by which the server 20 transmits signals to external devices according to a communication protocol.

[0066] The health check recommendation history acquisition module 2033 acquires health check recommendation history data from, for example, an external data server 30. The health check recommendation history data includes at least the personal information of the person who is recommended to undergo a health check, the person's past health check results, and the results of the recommendation to undergo the health check for that person. The health check recommendation history acquisition module 2033 does not need to acquire all the data stored in the external data server 30, but only needs to acquire the data necessary to determine the best intervention pattern for each person, as described later. In addition, since the data stored in the external data server 30 may include personal information (e.g., name, address), it is preferable for the health check recommendation history acquisition module 2033 to replace such personal information with identification information and store it in the health check recommendation history DB 2022.

[0067] Since the data stored in the external data server 30 is likely to be updated as needed, it is preferable for the health checkup recommendation history acquisition module 2033 to periodically access the external data server 30 and acquire health checkup recommendation history data. The health checkup recommendation history acquisition module 2033 stores the acquired health checkup recommendation history data in the health checkup recommendation history DB 2022, and also adds, deletes, and updates the contents of the health checkup recommendation history DB 2022 as needed.

[0068] The intervention selection module 2034 extracts intervention measures from the intervention DB 2023 that will serve as the basis for the intervention patterns generated by the intervention pattern generation module 2035 (described later), and provides the extracted intervention measures to the intervention pattern generation module 2035. The intervention measures selected by the intervention selection module 2034 may be single or multiple.

[0069] There are no particular restrictions on the method by which the intervention selection module 2034 selects interventions from the intervention database 2023. When providing interventions to the intervention pattern generation module 2035, possible methods include initially providing a single intervention, and then subsequently providing the intervention pattern generation module 2035 with multiple interventions, including an intervention that leads to effective referral to medical consultation. Alternatively, it is possible to have the intervention pattern generation module 2035 generate an intervention pattern that has a certain meaning by combining multiple interventions.

[0070] The intervention pattern generation module 2035 generates intervention patterns that include at least one intervention based on the interventions provided by the intervention selection module 2034. Preferably, the intervention pattern generation module 2035 also generates intervention patterns that do not include any interventions, i.e., no recommendation for medical consultation. The intervention pattern generation module 2035 stores the generated intervention patterns in the intervention pattern DB 2024.

[0071] Similar to the interventions selected by the intervention selection module 2034, the intervention patterns generated by the intervention pattern generation module 2035 are important for effective encouragement of medical examinations. There are no particular limitations on the intervention pattern generation method used by the intervention pattern generation module 2035, but one example is a trial-and-error method in which intervention patterns are generated by first generating an intervention pattern with a single intervention, and then, when the medical examination encouragement history data is updated, interventions are appropriately added to intervention patterns that show a large improvement rate in the parameters related to medical examination participation calculated by the individual improvement rate calculation module 2037 (i.e., the effectiveness of encouraging medical examinations).

[0072] From the perspective of conducting trial and error, it is preferable that the intervention selection module 2034 and the intervention pattern generation module 2035 periodically select interventions and generate intervention patterns. In particular, since the screening recommendation history acquisition module 2033 periodically acquires and updates screening recommendation history data, it is preferable to select interventions and generate intervention patterns in accordance with the timing of the screening recommendation history data update.

[0073] The learning model generation module 2036 takes the intervention patterns generated by the intervention pattern generation module 2035 as input and generates training data for each subject, using the results of health checkup recommendations included in the health checkup recommendation history data as output, and stores this training data 2027 in the memory unit 202. Next, the learning model generation module 2036 generates a learning model for each subject by performing machine learning using the generated training data 2027, and stores this learning model 2028 in the memory unit 202. Preferably, the learning model generation module 2036 recreates the training data 2027 in accordance with the timing of the health checkup recommendation history data update and retrains the learning model 2028.

[0074] The Individual Improvement Rate Calculation Module 2037 inputs intervention patterns into the learning model 2028 generated by the learning model generation module 2036, thereby obtaining the results of the learning model 2028's inference, which are recommendations for receiving health checkups (including medical examinations), for each individual. Then, based on the results of the health checkup recommendations output from the learning model 2028, the Individual Improvement Rate Calculation Module 2037 calculates the improvement rate of parameters related to receiving health checkups and stores the calculated results in the Individual Improvement Rate DB 2025. It is preferable that the Individual Improvement Rate Calculation Module 2037 also performs the improvement rate calculation work in conjunction with the retraining of the learning model 2028 by the learning model generation module 2036, and updates the Individual Improvement Rate DB 2025 accordingly.

[0075] The intervention pattern determination module 2038 determines the best intervention pattern for each individual based on the improvement rate calculated by the individual improvement rate calculation module 2037. The "best intervention pattern" here refers, for example, to the pattern that maximizes the number of appointments for health checkups (including medical examinations) resulting from recommendations for health checkups (including medical examinations) as a result of implementing the intervention pattern.

[0076] The screening recommendation implementation module 2039 recommends that individuals undergo screenings (including health checkups) based on the best intervention pattern for each individual determined by the intervention pattern determination module 2038.

[0077] An example of a health checkup recommendation implemented by the health checkup recommendation module 2039 will be explained with reference to Figure 11.

[0078] The health check recommendation implementation module 2039 refers to the personal information of the target person included in the health check recommendation history data, and if necessary, obtains detailed personal information of the target person from the external data server 30, and sends a postcard 1101 to the target person's address or sends an SMS (short message) 1102 to the target person's mobile terminal. The postcard 1101 displays a two-dimensional barcode 1103 containing identification information (ID) that can identify the target person and link information for accessing the system 1 according to this embodiment. Similarly, the SMS 1102 contains identification information (ID) that can identify the target person and link information 1104 for accessing the system 1 according to this embodiment. The postcard 1101 and SMS 1102 are also examples of the intervention measures and intervention patterns described above. Individuals who have received postcard 1101 or SMS 1102 access System 1 according to this embodiment by using a two-dimensional barcode 1103 or by accessing it based on link information 1104. Upon receiving the access, the health checkup recommendation module 2039 displays a screen 1105 on the individual's mobile device or other device to transition to the questionnaire page. The content displayed on this screen 1105 is also an example of the intervention measures and intervention patterns described above. Next, the subject performs an operation input by touching or otherwise using the button 1106 displayed at the bottom of screen 1105. The operation input from button 1106 is also incorporated as part of the health checkup recommendation history data and can be used as data to determine the best intervention pattern.

[0079] <2 Data Structure> Figures 4 to 8 show the data structure of the database stored by server 20. Note that Figures 4 to 8 are examples and do not exclude any data not shown.

[0080] The databases shown in Figures 4 to 8 refer to relational databases, which are data sets called tables, structurally defined by rows and columns, and are used to manage and relate these tables to each other. In databases, tables are called tables, the columns of tables are called columns, and the rows of tables are called records. In relational databases, relationships can be established and linked between tables.

[0081] Typically, each table has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit 203 of the server 20 can instruct the processor 29 to add, delete, or update records in specific tables stored in the storage unit 202, according to various programs.

[0082] Figure 4 shows the data structure of the health checkup recommendation history DB2022. As shown in Figure 4, each record in the health checkup recommendation history DB2022 includes, for example, the fields "Target Person ID", "Insurance Organization ID", "City / Town / Village ID", "Age", "Gender", "Type of Health Checkup Recommendation", "Past Health Checkup Results", "Health Checkup Recommendation Message ID", "Approach Method", "Approach Date and Time", "Reward", "Health Checkup Recommendation Input", and "Health Checkup Received". Each field in the health checkup recommendation history DB2022 is entered by the health checkup recommendation history acquisition module 2033 when it acquires health checkup recommendation history data from the external data server 30. The information stored in the health checkup recommendation history DB2022 can be changed and updated as needed.

[0083] The item "Person ID" is an ID used to identify persons who are eligible to receive health checkups by System 1 (especially Server 20) according to this embodiment. The item "Insurance Organization ID" is an ID used to identify the health insurance organization (insurance organization) that is the entity operating the health checkup and is the entity that utilizes the best intervention pattern for each person identified by System 1 according to this embodiment. The item "Municipality ID" is the municipality to which the address or residence of the person identified by the Person ID belongs, and is an ID used to identify the municipality that is under the jurisdiction of the health insurance organization identified by the insurance agent. The item "Age" is information indicating the age of the person identified by the Person ID. The item "Gender" is information indicating the gender of the person identified by the Person ID. The item "Type of Health Checkup Recommendation" is information indicating the type of health checkup recommended to the person identified by the Person ID. The item "Past Health Checkup Results" is information indicating the results of health checkups recommended to the person identified by the Person ID. The item "Medical Examination Recommendation Message ID" is an ID used to identify the message included in a medical examination recommendation sent to a person identified by the person ID. The item "Method of Approach" is information indicating the method of recommendation used when a medical examination recommendation was sent to a person identified by the person ID. The item "Date and Time of Approach" is information indicating the date and time when a medical examination recommendation was sent to a person identified by the person ID. The item "Reward" is information indicating whether or not a reward was given to a person identified by the person ID when a medical examination recommendation was sent to them. The item "Whether or Not a Health Examination Was Taken" is information indicating whether or not a person identified by the person ID underwent a health examination as a result of the recommendation.

[0084] Figure 5 shows the data structure of the intervention plan DB2023. As shown in Figure 5, each record in the intervention plan DB2023 includes, for example, the fields "Intervention Plan ID", "Intervention Plan", "Intervention Plan Content ID", and "Intervention Plan". Each field in the intervention plan DB2023 is entered in advance by the operator of system 1 according to this embodiment. The information stored in the intervention plan DB2023 can be changed and updated as needed.

[0085] The item "Intervention ID" is an ID used to identify the category of intervention measures that can be implemented in System 1 according to this embodiment (see Figure 10). The item "Intervention" is information indicating the name of the category of intervention measures identified by the Intervention ID. The item "Intervention Content ID" is an ID used to identify the specific intervention measure belonging to the category of intervention measures identified by the Intervention ID. The item "Intervention Content" is information indicating the name of the specific intervention measure identified by the Intervention Content ID.

[0086] In Figure 5, "-" indicates that there is no information. As shown in Figure 5, the intervention DB2023 also includes cases where there is no intervention, i.e., no recommendation for screening is made, as indicated by intervention ID "I0004".

[0087] Figure 6 shows the data structure of the intervention pattern DB2024. As shown in Figure 6, each record in the intervention pattern DB2024 includes, for example, the fields "Intervention Pattern ID", "Intervention Measure ID", and "Intervention Measure Content ID". Each field in the intervention pattern DB2024 is entered by the intervention pattern generation module 2035 when the module generates an intervention pattern. The information stored in the intervention pattern DB2024 can be changed and updated as needed.

[0088] The item "Intervention Pattern ID" is an ID used to identify an intervention pattern, which is a combination of means of encouraging a target person to seek medical attention in System 1 according to this embodiment. The item "Intervention Measure ID" is an ID used to identify a category of intervention measures that can be implemented in System 1 according to this embodiment, and is the same as the item "Intervention Measure ID" in the Intervention Measure DB2023 shown in Figure 5. The item "Intervention Measure Content ID" is an ID used to identify a specific intervention measure that belongs to the category of intervention measures identified by the Intervention Measure ID, and is the same as the item "Intervention Measure Content ID" in the Intervention Measure DB2023 shown in Figure 5.

[0089] Figure 7 shows the data structure of the Individual Improvement Rate DB2025. As shown in Figure 7, each record in the Individual Improvement Rate DB2025 includes, for example, the fields "Subject ID", "Intervention Pattern ID", and "Improvement Rate". Each field in the Individual Improvement Rate DB2025 is entered by the Individual Improvement Rate Calculation Module 2037 when it calculates the improvement rate of parameters related to receiving health checkups for each intervention pattern for each subject. The information stored in the Individual Improvement Rate DB2025 can be changed and updated as needed.

[0090] The item "Target Person ID" is an ID used to identify the person who is eligible to receive a health checkup by System 1 according to this embodiment, and is the same as the item "Target Person ID" in the health checkup recommendation history DB2022 shown in Figure 4. The item "Intervention Pattern ID" is an ID used to identify the intervention pattern, which is a combination of means of encouraging a health checkup to be performed on the target person in System 1 according to this embodiment, and is the same as the item "Intervention Pattern ID" in the confirmed intervention pattern DB2026 shown in Figure 7. The item "Improvement Rate" is information regarding the improvement rate of parameters related to health checkup participation calculated by the individual improvement rate calculation module 2037.

[0091] Figure 8 shows the data structure of the Definitive Intervention Pattern DB2026. As shown in Figure 8, each record in the Definitive Intervention Pattern DB2026 includes, for example, the fields "Subject ID", "Intervention Pattern ID", and "Date of Definition". Each field in the Definitive Intervention Pattern DB2026 is entered by the Individual Improvement Rate Calculation Module 2037 when the Intervention Pattern Definition Module 2038 determines the intervention pattern to be performed for each subject, in other words, the best intervention pattern for each subject. The information stored in the Definitive Intervention Pattern DB2026 can be changed and updated as needed.

[0092] The item "Target Person ID" is an ID used to identify the person who is eligible to undergo a health checkup by System 1 according to this embodiment, and is the same as the item "Target Person ID" in the health checkup recommendation history DB2022 shown in Figure 4. The item "Intervention Pattern ID" is an ID used to identify the intervention pattern, which is a combination of means of encouraging a health checkup to be performed on the target person in System 1 according to this embodiment, and is the same as the item "Intervention Pattern ID" in the confirmed intervention pattern DB2026 shown in Figure 7. The item "Confirmation Date" is information indicating the date on which the intervention pattern confirmation module 2038 determined (confirmed) that the intervention pattern identified by the item "Intervention Pattern ID" is the best for the target person identified by the item "Target Person ID".

[0093] <3 Examples of Operation> The following describes an example of how Server 20 operates.

[0094] Figure 9 is a flowchart illustrating an example of the main operation of server 20.

[0095] In step S900, the control unit 203 acquires health checkup recommendation history data from the external data server 30. Specifically, for example, the control unit 203 acquires health checkup recommendation history data necessary for the operation of system 1 according to this embodiment from the external data server 30 using the receiving control module 2031 and the health checkup recommendation history acquisition module 2033.

[0096] Next, in step S901, the control unit 203 selects an intervention from the intervention DB 2023 for generating an intervention pattern. Specifically, for example, the control unit 203 uses the intervention selection module 2034 to select an intervention from the intervention DB 2023 for generating an intervention pattern.

[0097] In step S902, the control unit 203 generates an intervention pattern using the intervention measures selected in step S901. Specifically, for example, the control unit 203 generates an intervention pattern using the intervention pattern generation module 2035, which is selected in step S901. The generated intervention pattern is stored in the intervention pattern DB 2024.

[0098] In step S903, the control unit 203 determines the result of the health check recommendation, which will be the output of the training data 2027 and the learning model 2028 generated in step S904 and beyond. Specifically, for example, the control unit 203 uses the learning model generation module 2036 to determine the result of the health check recommendation, which will be the output of the training data 2027 and the learning model 2028 generated in step S904 and beyond.

[0099] In step S904, the control unit 203 generates training data 2027, which takes the result of the recommendation to undergo a health checkup determined in step S903 as an output and the intervention pattern generated in step S902 as an input. Specifically, for example, the control unit 203 generates training data 2027 using the learning model generation module 2036, which takes the result of the recommendation to undergo a health checkup determined in step S903 as an output and the intervention pattern generated in step S902 as an input. The generated training data 2027 is stored in the storage unit 202 of the server 20.

[0100] In step S905, the control unit 203 performs machine learning using the training data 2027 generated in step S904 to generate a learning model 2028. Specifically, for example, the control unit 203 uses the learning model generation module 2036 to perform machine learning using the training data 2027 generated in step S904 to generate a learning model 2028. The generated learning model 2028 is stored in the storage unit 202 of the server 20.

[0101] In step S906, the control unit 203 selects an intervention pattern from the intervention pattern DB 2024 and a learning model 2028 stored in the memory unit 202. By inputting this intervention pattern into the selected learning model 2028, the control unit 203 obtains the result of a health checkup recommendation, which is the inference result of the learning model 2028. Specifically, for example, the control unit 203 uses the individual improvement rate calculation module 2037 to select an intervention pattern from the intervention pattern DB 2024 and a learning model 2028 stored in the memory unit 202. By inputting this intervention pattern into the selected learning model 2028, the control unit 203 obtains the result of a health checkup recommendation, which is the inference result of the learning model 2028. The obtained output is temporarily stored in the memory unit 202. The output acquisition operation in step S906 is repeatedly performed for each subject by changing the intervention pattern and learning model 2028 in various ways.

[0102] In step S907, the control unit 203 calculates the improvement rate of parameters related to health checkup participation based on the output, which is the inference result obtained in step S906. Specifically, for example, the control unit 203 uses the individual improvement rate calculation module 2037 to calculate the improvement rate of parameters related to health checkup participation based on the output, which is the inference result obtained in step S906. The calculated improvement rate is stored in the individual improvement rate DB 2025. The improvement rate calculation operation in step S907 is performed for each individual.

[0103] In step S908, the control unit 203 determines the best intervention pattern to be implemented for each individual based on the improvement rate calculated in step S907. Specifically, for example, the control unit 203 uses the intervention pattern determination module 2038 to determine the best intervention pattern to be implemented for each individual based on the improvement rate calculated in step S907. The determined best intervention pattern for each individual is stored in the determined intervention pattern DB 2026.

[0104] Although not shown in the diagrams below, the control unit 203, for example, using the health checkup recommendation implementation module 2039, recommends that the subject undergo a health checkup based on the best intervention pattern determined in step S908.

[0105] <5 Effects of one embodiment> As described in detail above, according to the system 1 of this embodiment, it is possible to identify the optimal means of encouraging individuals to undergo medical examinations.

[0106] The technology disclosed in Patent Document 1, mentioned above, predicts the probability of undergoing a health check after a health check recommendation. However, this technology does not predict the effectiveness of the health check recommendation.

[0107] On the other hand, System 1 according to this embodiment predicts the increase in the probability of receiving a health checkup due to health checkup recommendations. Furthermore, System 1 according to this embodiment predicts the increase in health checkup recommendations (improvement rate) for each health checkup recommendation pattern (intervention pattern) for each target person, identifies the pattern with the largest increase, and determines this intervention pattern as the best intervention pattern for each target person.

[0108] Therefore, according to the system 1 of this embodiment, the improvement rate of multiple intervention patterns is compared for each subject, and the best intervention pattern for each subject is determined as a result of the comparison, so that the optimal means of encouraging people to undergo medical examinations can be identified.

[0109] <6. Addendum> The embodiments described above are detailed explanations of the configuration in order to make this disclosure easier to understand, and are not necessarily limited to those comprising all the configurations described. Furthermore, some of the configurations of each embodiment can be added to, deleted from, or replaced with other configurations.

[0110] As an example, in the system 1 according to the embodiment described above, training data 2027 and learning model 2028 were uniformly generated for the health checkup recommendation history data acquired by the system 1. However, these training data 2027 and learning model 2028 may be generated for each health insurance organization and for each area of ​​residence of the target person, and the training data 2027 and learning model 2028 may be selected according to the health insurance organization to which the target person belongs and the area in which the target person resides.

[0111] Furthermore, in the system 1 according to the above embodiment, the best intervention pattern was sought for each individual subject. However, subjects may be grouped based on their characteristics (e.g., their residential area), and training data 2027 and learning models 2028 may be generated for each group, and the best intervention pattern may be sought for each group. Alternatively, subjects may be grouped, and then the best intervention pattern may be sought for each group using common training data 2027 and learning models 2028.

[0112] Furthermore, various parameters can be selected for the output of the learning model 2028 in the system 1 according to the above embodiment, as a result of the health check recommendation. One example is whether or not a health check appointment has been made, but other parameters such as whether the recommendation message has been read or not, transition to the appointment booking page, and the health check attendance rate can also be selected.

[0113] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.

[0114] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, and Java (registered trademark).

[0115] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.

[0116] The details described in each of the above embodiments are noted below.

[0117] (Note 1) A program (2021) for operating a computer (20) equipped with a processor (29), wherein the program (2021) includes a first step (S900) of acquiring screening recommendation history data which includes at least personal information of persons to be recommended for screening, past screening results of the persons, and the results of recommendations for screening to the persons; a second step (S902) of generating at least one intervention pattern which includes at least one intervention measure that is a means of recommending screening; and a program which takes the intervention pattern generated in the second step (S902) as input and outputs the results of recommendations for screening. A program (2021) that executes the following steps: a third step (S904) to generate training data from health checkup recommendation history data for each intervention pattern; a fourth step (S905) to generate a machine learning model for each intervention pattern using the training data generated in the third step (S904); a fifth step (S906) to obtain an output, which is the inference result of the machine learning model, for each subject by inputting the intervention pattern into the machine learning model generated in the fourth step (S905); and a sixth step (S908) to find the best intervention pattern for each subject based on the output obtained in the fifth step (S906). (Note 2) The intervention patterns include those that do not include intervention measures, as described in Appendix 1 (2021). (Note 3) The best intervention pattern for each target group is the program described in Appendix 1 or 2 (2021), which includes the intervention pattern that results in the maximum number of appointments for health checkups. (Note 4) Program (2021) is a program (2021) described in any of the appendices 1 to 3, which causes the processor (29) to execute the first step (S900) and the third step (S904) at predetermined timings, thereby causing the program (2021) to retrain a machine learning model for each intervention pattern using the training data generated in the third step (S904). (Note 5) A program (2021) described in any of the appendices 1 to 4, which in the third step (S904) generates training data for at least one of the health insurance organizations to which the subject belongs and the subject's place of residence, and in the fourth step (S905) generates a machine learning model for at least one of the health insurance organizations to which the subject belongs and the subject's place of residence. (Note 6) In the third step (S904), the program (2021) described in any of the appendices 1 to 5 classifies subjects into multiple groups based on the characteristics of subjects included in the health check recommendation history data, generates training data for each of these groups, and in the fourth step (S905), generates a machine learning model for each of these groups. (Note 7) Program (2021) is Program (2021) as described in any of the appendices 1 to 6, which further causes the processor (29) to perform Step 7, which involves encouraging the subjects to undergo screening based on the best intervention pattern determined in Step 6 (S908). (Note 8) In Step 7, the program described in Appendix 7 (2021) implements the recommendation to seek medical attention by mailing a document to the target person displaying a barcode containing a link with identification information for that person, or by sending a message containing a link with identification information to the target person's mobile device. (Note 9) The program (2021) further executes an eighth step in which the processor (29) obtains whether the subject has accessed the link based on the identification information, and in the first step (S900), the program (2021) includes whether the subject has accessed the data as health check recommendation history data, as described in Appendix 8. (Note 10) An information processing device equipped with a processor (29) wherein the processor (29) performs the following steps: a first step (S900) of acquiring health check recommendation history data which includes at least personal information of persons to be recommended for health checkups, past health checkup results of the persons, and the results of recommendations for health checkups to the persons; a second step (S902) of generating at least one intervention pattern which includes at least one intervention measure that is a means of recommending health checkups; and testing training data which takes the intervention pattern generated in the second step (S902) as input and the results of health checkup recommendations as output for each intervention pattern. An information processing device that performs the following steps: a third step (S904) which generates data from medical recommendation history data; a fourth step (S905) which generates a machine learning model for each intervention pattern using the training data generated in the third step (S904); a fifth step (S906) which inputs the intervention pattern into the machine learning model generated in the fourth step (S905) to obtain the output, which is the inference result of the machine learning model, for each subject; and a sixth step (S908) which determines the best intervention pattern for each subject based on the output obtained in the fifth step (S906). (Note 11) A method performed by a computer (20) equipped with a processor (29), wherein the processor (29) performs the following steps: a first step (S900) of acquiring screening recommendation history data which includes at least personal information of persons to be recommended for screening, past screening results of the persons, and the results of recommendations for screening to the persons; a second step (S902) of generating at least one intervention pattern which includes at least one intervention measure that is a means of recommending screening; and training data which takes the intervention pattern generated in the second step (S902) as input and the results of recommendations for screening as output. A method comprising: a third step (S904) generating data from health check recommendation history data for each intervention pattern; a fourth step (S905) generating a machine learning model for each intervention pattern using the training data generated in the third step (S904); a fifth step (S906) obtaining an output, which is the inference result of the machine learning model, for each subject by inputting the intervention pattern into the machine learning model generated in the fourth step (S905); and a sixth step (S908) determining the best intervention pattern for each subject based on the output obtained in the fifth step (S906). (Note 12) A system comprising: means (2033) for acquiring health check recommendation history data which includes at least personal information of persons who are encouraged to undergo health checks, the results of past health checks of the persons, and the results of encouragement to undergo health checks of the persons; means (2035) for generating at least one intervention pattern which includes at least one intervention measure that is a means of encouraging health checks; means (2036) for generating training data for each intervention pattern from health check recommendation history data, with the intervention pattern generated by means (2035) as input and the results of encouragement to undergo health checks as output; means (2036) for generating a machine learning model for each intervention pattern using the training data generated by means (2036); means (2037) for acquiring an output which is the inference result of the machine learning model for each person by inputting the intervention pattern into the machine learning model generated by means (2036); and means (2038) for determining the best intervention pattern for each person based on the output acquired by means (2037). [Explanation of Symbols]

[0118] 1…System for considering means of encouraging medical examinations 10…Terminal device 20…Server 25…Memory 26…Storage 29…Processor 30…External data server 202…Storage unit 203…Control unit 2021…Application program 2022…Medical examination recommendation history DB 2023…Intervention measures DB 2024…Intervention pattern DB 2025…Individual improvement rate DB 2026…Confirmed intervention pattern DB 2027…Training data 2028…Learning model 2031…Receive control module 2032…Transmit control module 2033…Medical examination recommendation history acquisition module 2034…Intervention measures selection module 2035…Intervention pattern generation module 2036…Learning model generation module 2037…Individual improvement rate calculation module 2038…Intervention pattern confirmation module 2039…Medical examination recommendation implementation module

Claims

1. A program for operating a computer equipped with a processor and memory, The program is provided to the processor: The first step is to obtain health check recommendation history data which includes at least the personal information of individuals who are recommended to undergo health checks, selected from among individuals belonging to an organization that conducts health checks according to predetermined conditions including the year, the past health check results of the said individuals, and the results of past health check recommendation efforts, including intervention measures that are means of recommending the said individuals to undergo health checks. A second step involves selecting at least one intervention from a group of interventions that are means of encouraging people to undergo health checkups, thereby generating at least one intervention pattern which is a combination of interventions including the selected intervention, and storing it in the memory. A third step involves generating training data for each subject from the aforementioned health check recommendation history data, with the aforementioned intervention measures as input and the results of past health check recommendation recommendations included in the health check recommendation history data as output. A fourth step involves generating a machine learning model for each subject using the training data generated in the third step, The fifth step involves inputting the intervention measures into the machine learning model generated in the fourth step, thereby obtaining the results of the recommendation to seek medical attention, which are the inference results of the machine learning model, for each of the target individuals. A program that performs a sixth step, based on the results of the recommendation to seek medical attention obtained in the fifth step, to determine the best intervention pattern for each subject that maximizes the rate of appointment for the medical examination or the increase in the recommendation to seek medical attention.

2. The program according to claim 1, wherein the intervention pattern includes one that does not include the intervention measure.

3. The best intervention pattern for each subject includes the intervention pattern that results in the maximum number of appointments for the medical examinations under that intervention pattern, according to claim 1.

4. The program according to claim 1, wherein the program causes the processor to execute the first step and the third step at predetermined timings, thereby causing the program to retrain the machine learning model for each intervention using the training data generated in the third step.

5. In the third step, the training data is generated for at least one of the health insurance organizations to which the subject belongs and the subject's place of residence. The program according to claim 1, wherein in the fourth step, the program generates the machine learning model for at least one of the health insurance organization to which the subject belongs and the subject's place of residence.

6. In the third step, the subjects are classified into multiple groups based on the characteristics of the subjects included in the health check recommendation history data, and training data is generated for each of these groups. The program according to claim 1, wherein in the fourth step, the machine learning model is also generated for each of the groups.

7. The program further provides the processor with: The program according to claim 1, which causes the program to perform a seventh step of encouraging the subject to undergo the health checkup based on the best intervention pattern determined in the sixth step.

8. The program according to claim 7, wherein in the seventh step, the recommendation to seek medical attention is made by mailing the person a piece of mail displaying a barcode containing a link containing identification information for each person, or by sending a message containing a link containing identification information to a mobile device owned by the person.

9. The program further provides the processor with: Using the aforementioned identification information, an eighth step is performed to determine whether the subject has accessed the link. The program according to claim 8, wherein in the first step, the presence or absence of the access of the subject is included as the health check recommendation history data.

10. An information processing device comprising a processor and memory, The aforementioned processor, The first step is to obtain health check recommendation history data which includes at least the personal information of individuals who are recommended to undergo health checks, selected from among individuals belonging to an organization that conducts health checks according to predetermined conditions including the year, the past health check results of the said individuals, and the results of past health check recommendation efforts, including intervention measures that are means of recommending the said individuals to undergo health checks. A second step involves selecting at least one intervention from a group of interventions that are means of encouraging people to undergo health checkups, thereby generating at least one intervention pattern which is a combination of interventions including the selected intervention, and storing it in the memory. A third step involves generating training data for each subject from the aforementioned health check recommendation history data, with the aforementioned intervention measures as input and the results of past health check recommendation recommendations included in the health check recommendation history data as output. A fourth step involves generating a machine learning model for each subject using the training data generated in the third step, The fifth step involves inputting the intervention measures into the machine learning model generated in the fourth step, thereby obtaining the results of the recommendation to seek medical attention, which are the inference results of the machine learning model, for each of the target individuals. An information processing device that performs a sixth step of determining the best intervention pattern for each subject that maximizes the rate of appointments for the medical examination or the increase in the recommendation for medical examination, based on the results of the recommendation for medical examination obtained in the fifth step.

11. A method performed by a computer having a processor and memory, The aforementioned processor, The first step is to obtain health check recommendation history data which includes at least the personal information of individuals who are recommended to undergo health checks, selected from among individuals belonging to an organization that conducts health checks according to predetermined conditions including the year, the past health check results of the said individuals, and the results of past health check recommendation efforts, including intervention measures that are means of recommending the said individuals to undergo health checks. A second step involves selecting at least one intervention from a group of interventions that are means of encouraging people to undergo health checkups, thereby generating at least one intervention pattern which is a combination of interventions including the selected intervention, and storing it in the memory. A third step involves generating training data for each subject from the aforementioned health check recommendation history data, with the aforementioned intervention measures as input and the results of past health check recommendation recommendations included in the health check recommendation history data as output. A fourth step involves generating a machine learning model for each subject using the training data generated in the third step, The fifth step involves inputting the intervention measures into the machine learning model generated in the fourth step, thereby obtaining the results of the recommendation to seek medical attention, which are the inference results of the machine learning model, for each of the target individuals. A method comprising: a sixth step of determining the best intervention pattern for each subject that maximizes the rate of appointments for the health checkup or the increase in the number of health checkup recommendations, based on the results of the recommendation to seek medical attention obtained in the fifth step.

12. A means for acquiring screening recommendation history data which includes at least the personal information of individuals who are recommended to undergo screening based on predetermined conditions including the year, selected from among individuals belonging to an organization that conducts screenings; the past screening results of the said individuals; and the results of past screening recommendations, including intervention measures that are means of recommending the said individuals to undergo screenings. A means for selecting at least one intervention from multiple interventions that are means of encouraging people to undergo health checkups, thereby generating at least one intervention pattern which is a combination of interventions including the selected intervention, and storing it in memory; A means for generating training data for each subject from the aforementioned health check recommendation history data, with the aforementioned intervention measures as input and the results of past health check recommendation history data included in the health check recommendation history data as output, A means for generating training data generates a machine learning model for each target person using the training data generated by the means for generating training data, A means for generating the machine learning model inputs the intervention measures into the machine learning model generated by the means for generating the machine learning model, thereby obtaining the results of the recommendation to seek medical attention, which are the inference results of the machine learning model, for each of the target persons. A system comprising: means for obtaining the results of the recommendation to seek medical attention, and based on the output obtained by means for obtaining the results of the recommendation to seek medical attention, means for determining the best intervention pattern for each subject that maximizes the rate of appointments for the medical examination or the increase in the recommendation to seek medical attention.

Images