Determination system

The determination system addresses the issue of obsolete judgment standards by allowing users to select and weight risk data, dynamically evaluating service provision risks, thus increasing subscribers and reducing losses for service providers through a clear and participatory process.

WO2024228261A1PCT designated stage expired Publication Date: 2024-11-07NT T INC
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2023/017165
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-02
Publication Date
2024-11-07

AI Technical Summary

Technical Problem

Existing judgment systems in services like life insurance often rely on single standards, which become obsolete due to changing historical backgrounds, leading to incorrect subscription denials and a decrease in subscribers, as they fail to adapt to dynamic risk assessments.

Method used

A determination system that includes a user terminal and a connected device, allowing users to select and weight risk determination data, with a variable selection unit that chooses variables for each time step width to determine service provision risks, enabling a dynamic and multi-criteria evaluation for subscription decisions.

Benefits of technology

This approach allows for appropriate subscription decisions based on evolving risk assessments, increasing the number of subscribers while minimizing losses for service providers by presenting a clear and participatory process for users, thereby enhancing data provision and reducing psychological barriers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2023017165_07112024_PF_FP_ABST
    Figure JP2023017165_07112024_PF_FP_ABST
Patent Text Reader

Abstract

In the present invention, a user terminal: receives, from a user, the input of risk determination data accompanying service provision; displays a selection screen for selecting data to be used for risk determination, from among the input risk determination data; receives a selection of data to be used for the risk determination from the user; and displays the result of a determination as to subscribing to a target service of the user. A determination device includes: a variable selection unit that selects, for each time step width, a variable used for risk determination corresponding to the time step width from among variables included in the selected data to be used for the risk determination; and a determination unit that, for each time step width, uses the selected variable to determine a risk related to the provision of the target service, and makes a determination as to subscription to the target service of the user on the basis of a result of the risk determination for each time step width.
Need to check novelty before this filing date? Find Prior Art

Description

Judgment System

[0001] The disclosed technology relates to a determination system.

[0002] In businesses that provide subscriber services such as insurance payments in response to events such as the contraction of an illness or hospitalization of a subscriber, such as life insurance, certain standards are set to limit losses to the service provider due to the occurrence of an event, and applicants may be denied membership if they do not meet those standards.

[0003] In addition, AI technology has been proposed to automate loan screening (Non-Patent Document 1).

[0004] Mitsubishi Research Institute, "Starts Providing AI Screening Service," Internet search <URL: https: / / www.mri.co.jp / news / press / 20201203.html>

[0005] However, the method described in Non-Patent Document 1 makes a judgment based on a single criterion, and if the judgment method becomes outdated due to changes in the times, there is a risk that the application of a subscriber who is unlikely to experience an event will be mistakenly denied, leading to a decrease in the number of subscribers.

[0006] The disclosed technology has been made in consideration of the above points, and aims to provide a determination system that can appropriately determine whether or not to subscribe to a target service.

[0007] A first aspect of the present disclosure is a determination system including a user terminal and a determination device connected via a network, wherein the user terminal accepts input of risk assessment data associated with service provision from a user, displays a selection screen for selecting data to be used for risk assessment from the input risk assessment data, accepts a selection of data to be used for the risk assessment from the user, and displays the results of the user's subscription determination for the target service, and the determination device includes: a variable selection unit that selects, for each time step width, from variables included in the selected data to be used for the risk assessment that corresponds to the time step width; and a determination unit that uses the selected variables for each time step width to determine the risk associated with the provision of the target service, and makes a determination of the user's subscription to the target service based on the results of the risk assessment for each time step width.

[0008] According to the disclosed technology, it is possible to appropriately determine whether or not to subscribe to a target service.

[0009] 1 is a schematic block diagram of a determination system of this embodiment. FIG. 1 is a schematic block diagram of an example of a computer that functions as a user terminal and a determination device of this embodiment. FIG. 2 is a block diagram showing the configuration of the determination device of this embodiment. FIG. 3 is a flowchart showing a determination processing routine of the determination device of this embodiment. FIG. 4 is a diagram for explaining the processing of a determination unit of this example. FIG. 5 is a diagram showing a table used to determine service provision conditions. FIG. 6 is a diagram showing a table used to determine service provision conditions. FIG. 7 is a diagram for explaining a method for determining service provision conditions. FIG. 8 is a diagram for explaining a method for determining service provision conditions. FIG. 9 is a diagram showing an example of the results of a health check. FIG. 10 is a diagram showing an example of the results of a health check. FIG. 11 is a diagram showing an example of a selection screen. FIG. 12 is a diagram showing another example of a selection screen.

[0010] An example of an embodiment of the disclosed technology will be described below with reference to the drawings. Note that the same or equivalent components and parts in each drawing are given the same reference numerals. Also, the dimensional proportions in the drawings are exaggerated for the convenience of explanation and may differ from the actual proportions.

[0011] <Outline of this embodiment> In this embodiment, by determining whether to provide a target service to a user who wishes to join and the conditions for providing the target service based on multiple criteria, the number of subscribers, which could not be increased using a single criterion because it would be expected that the service provider would incur large losses, can be increased while minimizing losses. Furthermore, by accepting from the user the selection of data to be used for risk assessment, the number of subscribers can be further increased while minimizing losses.

[0012] <Configuration of the determination system according to this embodiment> As shown in FIG. 1, the determination system 100 according to this embodiment of the present invention comprises a determination device 10 installed on the service provider side and a user terminal 20 installed on the user side who wishes to subscribe.

[0013] The determination device 10 and the user terminal 20 are connected via a network 26 such as the Internet.

[0014] The user terminal 20 is a mobile terminal, a computer terminal, or the like. Here, the mobile terminal includes a smartphone terminal, a mobile phone, and a PDA (Personal Digital Assistant) terminal. The computer terminal includes a notebook computer terminal and a desktop computer terminal.

[0015] FIG. 2 is a block diagram showing the hardware configuration of the determination device 10 and the user terminal 20 of this embodiment.

[0016] 2 , the determination device 10 and the user terminal 20 include a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each component is connected to each other via a bus 19 so as to be able to communicate with each other.

[0017] The CPU 11 is a central processing unit that executes various programs and controls each component. That is, the CPU 11 reads programs from the ROM 12 or the storage 14 and executes the programs using the RAM 13 as a work area. The CPU 11 controls the above components and performs various arithmetic processing in accordance with the programs stored in the ROM 12 or the storage 14. In this embodiment, the ROM 12 or the storage 14 stores programs for performing various processing.

[0018] The ROM 12 stores various programs and various data. The RAM 13 temporarily stores programs or data as a working area. The storage 14 is configured with an HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs including the operating system and various data.

[0019] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to input various types of information.

[0020] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may be a touch panel type and function as the input unit 15.

[0021] The communication interface 17 is an interface for communicating with other devices, and uses standards such as Ethernet (registered trademark), FDDI, and Wi-Fi (registered trademark).

[0022] Next, a description will be given of the functional configuration of the determination device 10. Fig. 3 is a block diagram showing an example of the functional configuration of the determination device 10.

[0023] As shown in FIG. 3, the determination device 10 functionally comprises a receiving unit 30, a variable selecting unit 32, a determining unit 34, and an output unit 36.

[0024] The reception unit 30 receives input of risk assessment data associated with the provision of a service from the user terminal 20 .

[0025] Specifically, the user terminal 20 displays an input screen for inputting risk assessment data, including a message requesting data provision, and the user inputs the risk assessment data. The reception unit 30 of the determination device 10 then receives the input of the risk assessment data.

[0026] At this time, the user terminal 20 may further display a ranking screen showing the ranking of the types of risk assessment data provided by other users.

[0027] The receiving unit 30 also receives a selection of data to be used for risk assessment from the risk assessment data input from the user terminal 20 .

[0028] Specifically, the user terminal 20 displays a selection screen for selecting data to be used for risk assessment from the input risk assessment data, and the user inputs the selection of data to be used for risk assessment. Then, the reception unit 30 of the determination device 10 receives the selection of data to be used for risk assessment.

[0029] At this time, the user terminal 20 may present a selection screen including options regarding the weighting of the data used for risk assessment, and may accept the selection of the data to be used for risk assessment by the user selecting an option. Here, the weighting of the data to be used for risk assessment is calculated based on the reliability of the data to be provided and the length of the data (the length of the period of provision).

[0030] Furthermore, the user terminal 20 may further display a change screen for changing the selection of data to be used for risk assessment by the user, and may accept changes to the selection of data to be used for risk assessment from the user.

[0031] The variable selection unit 32 selects, for each time step width, variables to be used for risk assessment corresponding to the selected time step width from among the variables included in the data to be used for risk assessment.

[0032] Specifically, for each time step width, if a variable that changes with that time step width and is included in a set of variables to be used for a predetermined risk assessment is included in the data to be used for the selected risk assessment, that variable is selected as the variable to be used for the risk assessment corresponding to that time step width.

[0033] The judgment unit 34 uses the selected variables to judge the risk associated with the provision of the target service for each time step width, and based on the results of the risk judgment for each time step width, judges whether the user should subscribe to the target service and also judges the service provision conditions when providing the target service to the user.

[0034] Specifically, for each time step width, the selected variables are input to a risk determiner that is predetermined corresponding to that time step width to determine the risk associated with the provision of the target service. Then, based on the risk determined by the determiner for each time step width, a subscription decision is made as to whether or not to provide the target service to the user, and the service provision conditions for providing the target service to the user are determined. For example, the service provision conditions are information that determines the level of the service to be provided, and as an example, a discount rate related to the level of the service is determined.

[0035] The output unit 36 ​​causes the display unit 16 to display the result of the user's subscription decision to the target service and the conditions for providing the service.

[0036] <Operation of Determination System According to This Embodiment> Next, the operation of the determination system 100 will be described.

[0037] When an instruction to start a subscription application for the target service is received from the user terminal 20, the CPU 11 in the determination device 10 reads a determination program from the ROM 12 or the storage 14, expands it into the RAM 13, and executes it, thereby performing the determination process shown in Figure 4.

[0038] In step S100, the CPU 11, functioning as the reception unit 30, causes an input screen for inputting risk assessment data, including a message representing a data provision request, to be displayed on the user terminal 20. Then, when the user operates the user terminal 20 to input risk assessment data, the CPU 11, functioning as the reception unit 30, accepts the input of the risk assessment data from the user terminal 20.

[0039] In step S102, the CPU 11, functioning as the reception unit 30, causes the user terminal 20 to display a selection screen for selecting data to be used for risk assessment from the input risk assessment data. Then, when the user operates the user terminal 20 to select data to be used for risk assessment, the CPU 11, functioning as the reception unit 30, receives the selection of data to be used for risk assessment from the user terminal 20.

[0040] In step S104, the CPU 11 functions as the variable selection unit 32 to select, for each time step width, a variable to be used for risk assessment corresponding to the time step width from among the variables included in the data to be used for the selected risk assessment.

[0041] In step S106, the CPU 11 functions as the determination unit 34 to determine the risk associated with the provision of the target service for each time step width using the selected variables.

[0042] In step S108, the CPU 11, as the determination unit 34, determines whether the user should subscribe to the target service based on the result of the risk determination for each time step width, and determines the service provision conditions when the target service is provided to the user.

[0043] In step S110, the CPU 11 causes the display unit 16 as the output unit 36 ​​to display the result of the subscription determination for the user to the target service and the service provision conditions.

[0044] As described above, the determination system according to this embodiment accepts, from a user terminal, input of risk assessment data associated with the provision of a service, displays a selection screen for selecting data to be used for risk assessment from the input risk assessment data, and accepts from the user a selection of data to be used for risk assessment. The determination device selects, for each time step width, variables to be used for risk assessment corresponding to the selected time step width from variables included in the selected data to be used for risk assessment, determines, for each time step width, the risk associated with the provision of the target service using the selected variables, and determines whether the user should subscribe to the target service based on the results of the risk assessment for each time step width. This allows appropriate determination of subscription to the target service.

[0045] In addition, the risk assessment data is provided by the user. In particular, the user can be involved in the process of deciding whether to enroll by selecting the risk assessment data and weighting.

[0046] The result of the subscription decision is also presented to the user, who can participate in the subscription decision process through the user terminal.

[0047] In addition, risk assessment data provided by other users is presented to the user as a ranking. This allows the types of data provided by other users to be presented, encouraging users to provide data and reducing the psychological anxiety users may feel when providing data. This makes it easier to obtain consent from users for data provision and use, which was previously difficult to obtain.

[0048] <Example> In this example, insurance is the target service, and a user is a prospective insurer seeking insurance. The following describes an example of determining whether to enroll in insurance. Here, a "target service" refers to a service provided to a subscriber. A "subscriber" refers to a person receiving the subscription service. A "subscription candidate" refers to a person who is about to receive the subscription service or who is about to become a subscriber. An "event" refers to an incident that triggers the provision of the target service. A "service provider" refers to a person providing the target service. "Risk assessment data" refers to a value input to a determinator, such as a health check result. A "determinator" refers to a device that receives data as input and outputs a judgment value. A "judgment value" refers to an output containing information necessary for determining whether to enroll. A "judgment criterion" refers to a criterion for determining whether to enroll based on the judgment value. A "judgment result" refers to the result obtained by applying the judgment value to the judgment criterion. A "service provision condition" refers to a condition specified when there are restrictions on the provision of the target service to a subscriber.

[0049] First, the prospective subscriber provides the insurance company, which is the service provider, with risk assessment data by inputting the data into the user terminal 10. Here, risk assessment data refers to information such as the results of a health checkup, which is related to the occurrence of events that pose a risk to the service provider, such as contracting a disease or being hospitalized.

[0050] Next, as shown in Fig. 5, the determination unit 34 of the determination device 10 inputs the risk determination data submitted by the applicant to determiners 1 to N that perform risk determination, and receives determination values ​​1 to N from the respective determiners, where N is an integer of 2 or greater.

[0051] Here, the determinator is a device that performs a certain calculation on input risk determination data and returns a determination value as a numerical value representing the risk. Details of the determinator and its calculation will be described later.

[0052] The judgment unit 34 receives judgment values ​​1 to N, and compares them with judgment criteria 1 to N to obtain judgment result 1 to N. Here, a judgment result is the result of determining whether a judgment value is greater than or equal to the judgment criteria, or less than the judgment criteria. In the following examples, for all judgment values ​​and criteria, if a judgment value exceeds the judgment criteria, it means that the applicant will not be considered a subscriber when determining whether to accept the applicant as a subscriber based on a single judgment criterion. In other words, the judgment result can be one of two results: "Subscription permitted" or "Subscription not permitted."

[0053] The determination unit 34 determines the service provision conditions for the applicant from the N determination results based on a correspondence table such as that shown in Fig. 6, which is prepared in advance by the service provider. For example, in Fig. 6, if the proportion of applicants who are permitted to join is less than 50% of the N determination results, the service provision conditions are 0; if the proportion of applicants who are permitted to join is 50% or more but less than 70%, the service provision conditions are 0.5; if the proportion of applicants who are permitted to join is 70% or more but less than 90%, the service provision conditions are 0.9; and if the proportion of applicants who are permitted to join is 90% or more, the service provision conditions are 1.0. The proportion of applicants who are permitted to join can be set between 0% and 100%, and the correspondence with the service provision conditions can be set by the service provider anywhere between 0 and 1. In other words, the service provider can set the weighting of insurance claim recipients and the sharing of the burden.

[0054] Here, the service provision condition is information that determines the level of the target service provided by the service provider to the subscriber when an event occurs to the subscriber. If the value is 1.0, the maximum possible target service is provided, and if not, the target service is provided at a discount from the maximum target service. This service provision condition is specified as a continuous value, and the value corresponds to the discount rate. For example, in the example of insurance subscription, if the service provision condition for the payment of the target service, which is the insurance payment, is 0.5, it means that the insurance company will pay the subscriber an amount equal to 0.5 multiplied by the full insurance payment.

[0055] Here, an example using multiple determiners has been described, but even if only one determiner is used, for example, with N=1, it is possible to determine the service provision conditions if the degree of acceptance risk can be evaluated as shown in Figure 7. For example, when a risk score distribution is obtained as shown in Figure 8, if the cumulative sum is taken by adding up the risk scores in descending order, a curve like the graph on the right of Figure 8 is obtained. The left end of this curve represents service provision condition 0, and the right end represents service provision condition 1. In this way, even with a single determiner, it is possible to determine the service provision conditions from the distribution of risk scores.

[0056] Furthermore, when using multiple classifiers that output a distribution of risk scores, the final service provision conditions are determined from the curve of the service provision conditions obtained by the multiple classifiers, as shown in Figure 9. At this time, the conditions may be expressed as the sum of the cumulative sums of the multiple classifiers, or a weighted average may be taken. When taking a weighted average, the service provider sets a weight for each classifier. The weight is increased for classifiers that are desired to be emphasized, and decreased for classifiers that are not.

[0057] As a result, the service provider can aim to increase the number of subscribers while accepting the risks associated with the occurrence of events among subscribers.

[0058] Here, a specific example of a classifier is shown. To create a classifier, a user ID, the year of medical examination, and the results of the health checkup for that year, as shown in FIG. 10, and the year of medical examination for a user corresponding to the user in FIG. 10 and whether or not the user developed a disease in that year, as shown in FIG. 11, are prepared in advance as learning data. Here, the development of a disease is an event that poses a risk to the service provider. The learning data is a combination of risk assessment data and whether or not a risk event has occurred.

[0059] The results of a certain year's health check 1 , x 2 , x 3 , ... and then determine whether or not the next year will develop disease α by y α It can be expressed by the following formula:

[0060] (1)

[0061] w 0 , w 1 , w 2 , ... can be obtained by solving equation (1) by the least squares method. That is, E(w 0 , w 1 , w 2 , …) to minimize w 0 , w 1 , w 2 ,... is required.

[0062] (2)

[0063] Here, M is the number of users used for learning.

[0064] The results of the applicant's health check as risk assessment data are then used to 1 , x 2 , x 3 , . . . are substituted into equation (1), the diagnosis value for disease α can be obtained.

[0065] The above is an example of a classifier for disease α, and y α By replacing with the onset of disease β, it is possible to create a classifier for disease β.

[0066] In addition, in the above, the occurrence of the disease in the following year is calculated by y α However, the presence or absence of onset at any time from the year following the year of the health checkup in question can be included in the survey.

[0067] Another method for creating a classifier is shown below. For example, a table like that shown in FIG. 12 is created from a table like that shown in FIG. 11. ID1 and ID2 in FIG. 12 are arbitrary IDs selected from the user IDs in FIG. 11. Diseases α, β, ... in FIG. 12 are calculated by comparing the period from a certain year until first onset for diseases α, β, ... in FIG. 11. If the period for ID2 is shorter than the period for ID1, the value is 1; otherwise, the value is 0. For example, looking at disease α in FIG. 11, when 2000 is used as the base year, the user with ID "0001" first developed the disease three years later in 2003, while the user with ID "0002" developed the disease one year later in 2001. In FIG. 12, the period until first onset for user ID "0002" (ID2) is not shorter than that for user ID "0001" (ID1), so the value of disease α is 0.

[0068] On the other hand, looking at disease β in FIG. 11, when the year 2000 is used as the base year, the user with ID "0001" first developed the disease one year later in the year 2001, while the user with ID "0002" did not develop the disease. If the user did not develop the disease, the period until the onset is calculated as being longer than any period included in the table in FIG. 11. In FIG. 12, the user with ID "0002" (ID2) took a shorter period to first develop the disease than the user with ID "0001" (ID1), so the value of disease β is 1.

[0069] The value of disease α in FIG. 12 is calculated by y α The difference between the results of the health checkups for ID “0001” and ID “0002” in the reference year (2000 in this case) in FIG. 11 is expressed as x 1 , x 2 , x 3 , ..., and by minimizing the function shown in equation (2), w 0 , w 1 , w 2 ,... can be obtained.

[0070] The results of the applicant's health check as risk assessment data are then used to 1 , x 2 , x 3 , . . . are substituted into equation (1), the diagnosis value for disease α can be obtained.

[0071] This concludes the second method for creating a determinator.

[0072] Specifically, when two or more decision devices are used, if one of the decision devices is used for conventional decision making, by using the other decision devices in addition, it becomes possible to admit more people who wish to join than at least the number of people who were judged to join using the conventional method.

[0073] The above examples show methods of making judgments based on the results of health checkups, but the data that prospective members provide to service providers can also include other information, such as "personal information such as age, gender, and address," "personal health records (PHR) such as step counts and weight," "genomic information," and "electronic health records (EHR) information regarding medical history and treatment history."

[0074] The prospective subscriber can select which of these pieces of information to provide as risk assessment data on an input screen such as that shown in FIG. 13. The example in FIG. 13 shows that the results of last year's health checkup and genome information are provided to the service provider as risk assessment data. In this way, the prospective subscriber can select the data to provide to the service provider from a selection of options. In other words, the user can input or select the type of additional information to provide, allowing them to select the classifier and the risk assessment data required for it. It is also possible to set the combination and weighting of the data to be used for risk assessment.

[0075] The service provider prepares a classifier corresponding to the risk assessment data provided, i.e., separate classifiers are prepared that input the results of the health check, genome information, PHR, and EHR, respectively.

[0076] The determination unit 34 inputs the risk assessment data provided by the prospective subscriber into the corresponding determiner and obtains the assessment result. For example, in the example of FIG. 13 , the determination unit 34 inputs the results of last year's health checkup into a determiner that determines subscription based on the health checkup results, and inputs the genomic information into a determiner that determines subscription based on the genomic information, resulting in the determination unit 34 obtaining two assessment results. As a result, even if a user has a genetic risk of disease, by setting the service provision conditions based on the health checkup results, it is possible to increase the number of subscribers while reducing the risk faced by the service provider. Because the assessment result and the associated subscription conditions are presented based on information provided by the user themselves, the process leading up to the assessment is clearer for the user, and the assessment result is more acceptable to the user.

[0077] While Fig. 13 illustrates an example in which the prospective subscriber makes a selection based on the risk assessment data to be provided, it is also possible for the prospective subscriber to make a selection based on the assessor, as shown in Fig. 14. For example, in a determination that emphasizes PHR, N assessors are used to obtain N assessment results, each of which inputs a combination of data that necessarily includes PHR, such as a combination of PHR and EHR, a combination of PHR and health checkup, or a combination of PHR and genomic information. This allows the prospective subscriber to request a assessment based on their own condition and obtain service provision conditions that are desirable for them.

[0078] The method for classifying the classifiers according to the type of variables has been described above, but next we will describe a method for automatically classifying the variables to be input to the classifiers according to the time step width at which the variables change. This is the process performed by the variable selection unit 32.

[0079] The variable selection unit 32 determines a set of variables to be used for risk assessment in advance by the following method. First, for the data shown in FIG. 10, the following equation is used to select D m (S) is found. m (S) indicates the ease of change of the variable m when the time step width is S.

[0080]

[0081] By changing S from 1 to N, the variable D m (S) is calculated. Then, for each time step width S, m The top P variables with the largest (S) are adopted, and for each time step width S, a variable set consisting of P variables to be input to the decision unit for that time step width S is created. Here, P is an arbitrary constant that can be set by the service provider.

[0082] The determinator 1 receives as input a variable whose evaluation becomes high when the change step size S is 1, and the determinator N receives as input a variable whose evaluation becomes high when the change step size S is N. In other words, the determinator 1 evaluates short-term risks more effectively than the determinator N.

[0083] At the time of subscription determination, the variable selection unit 32 selects, for each time step width, a variable set to be used for risk determination corresponding to the time step width from among the variables included in the risk determination data selected by the user. The variable set selected for the time step width is input to the determiner corresponding to the time step width.

[0084] <Modifications> The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the gist of the present invention.

[0085] For example, various processes executed by the CPU after reading software (programs) in the above embodiments may be executed by various processors other than the CPU. Examples of processors in this case include dedicated electrical circuits, such as programmable logic devices (PLDs) (such as field-programmable gate arrays (FPGAs)) whose circuit configuration can be changed after manufacture, and application-specific integrated circuits (ASICs) that are processors having circuit configurations designed specifically for executing specific processes. Furthermore, the determination process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, the hardware structure of these various processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor elements.

[0086] In addition, in each of the above embodiments, the determination program is pre-stored (installed) in the storage 14, but this is not limiting. The program may be provided in a form stored in a non-transitory storage medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The program may also be downloaded from an external device via a network.

[0087] The following additional notes are provided regarding the above-described embodiments.

[0088] (Supplementary Item 1) A determination system including a user terminal and a determination device connected via a network, wherein the user terminal: accepts input of risk assessment data associated with service provision from a user; displays a selection screen for selecting data to be used for risk assessment from the input risk assessment data, and accepts a selection of data to be used for the risk assessment from the user; displays a result of the user's determination of subscription to the target service; the determination device: includes a memory; and at least one processor connected to the memory; the processor: for each time step width, selects, from variables included in the selected data to be used for the risk assessment, variables to be used for the risk assessment corresponding to the time step width; for each time step width, uses the selected variables to determine the risk associated with the provision of the target service; and makes a determination of the user's subscription to the target service based on the result of the risk assessment for each time step width.

[0089] REFERENCE SIGNS LIST 10 Determination device 11 CPU 14 Storage 15 Input unit 16 Display unit 20 User terminal 26 Network 30 Reception unit 32 Variable selection unit 34 Determination unit 36 ​​Output unit 100 Determination system

Claims

1. A determination system including a user terminal and a determination device connected via a network, wherein the user terminal: accepts input of risk assessment data associated with service provision from a user; displays a selection screen for selecting data to be used for risk assessment from the input risk assessment data, and accepts a selection of data to be used for the risk assessment from the user; and displays a result of the user's subscription determination for a target service; and the determination device: a variable selection unit: for each time step width, selects a variable to be used for risk assessment corresponding to the time step width from among variables included in the selected data to be used for the risk assessment; and a determination unit: for each time step width, uses the selected variable to determine the risk associated with the provision of the target service, and makes a determination of the user's subscription to the target service based on the result of the risk assessment for each time step width.

2. A determination system as described in claim 1, wherein the determination unit further determines the service provision conditions when providing the target service to the user based on the result of the risk determination for each time step width.

3. The judgment system according to claim 1, wherein the user terminal displays an input screen including a message representing a request for data provision and for inputting the risk assessment data, and accepts input of the risk assessment data from a user.

4. The judgment system of claim 1, wherein the user terminal presents as the selection screen a screen including options regarding the weighting of data to be used in risk assessment, and accepts the selection of data to be used in the risk assessment by the user selecting one of the options.

5. The user terminal further displays a change screen for changing the selection of data to be used in the risk assessment by the user, and accepts a change to the selection of data to be used in the risk assessment from the user, and the variable selection unit of the judgment device selects, for each time step width, variables to be used in the risk assessment corresponding to the time step width from among the variables contained in the changed data to be used in the risk assessment.

6. The determination system according to claim 1, wherein the user terminal further displays a ranking screen showing a ranking of types of risk determination data provided by other users.

Citation Information

Patent Citations

  • Insurance design support system and insurance design support method

    JP2019012493A

  • Medical assessment support device, medical assessment support method and medical assessment support program

    JP2022007687A

  • Disease risk prediction system and disease risk prediction method

    JP2022182316A

  • Systems and methods for providing personalized prognostic profiles

    US20170177822A1

  • Skew-mitigated evolving prediction model

    US20210342757A1