Output program, output method, and information processing device

Abstract

This output program causes a computer to perform a process for: receiving information about a measure; using the received information about the measure to identify a measure model comprising a plurality of components that define content about the measure in a hierarchical structure; generating a measure model by changing one or more components of the plurality of components of the identified measure model that correspond to the information about the measure; and outputting the generated measure model.

Description

Output program, output method, and information processing device

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

[0002] One type of workflow is the policy flow graph, which diagrams the process of assigning policy target objects, such as people, to services to achieve the policy's objectives in various fields such as medical care, nursing care, and administration.

[0003] For example, to generate a flow graph of a measure, an AI (Artificial Intelligence) chat service realized by a large-scale language model such as Transformer, so-called LLM (Large Language Models), can be used.

[0004] Some of these AI chat services take text as input and output a flowchart. For example, by providing prompts to set roles such as an interviewer with prerequisites and detailed conditions defined, the service can output a flow through an interview format.

[0005] Japanese Patent Application Laid-Open No. 2003-228647

[0006] However, the AI ​​chat service described above has the drawback of making it difficult to generate a flow graph of a measure that is suited to the actual situation where the measure will be applied. For example, the AI ​​chat service described above may output a flow graph of a measure that is missing components such as services or conditions that are essential in the actual situation, or that includes components such as services or conditional branches that do not comply with standards such as laws, regulations, or guidelines.

[0007] Note that the above issues are not limited to policy models that are realized in flow format, such as policy flow graphs, but are issues that arise in general with policy models that are realized in the form of social concepts, organizational charts, guidelines, etc.

[0008] In one aspect, an object of the present invention is to provide an output program, an output method, and an information processing device that can realize the generation of a policy model suited to the site where the policy is to be applied.

[0009] One embodiment of the output program causes a computer to execute a process that receives information regarding a policy, uses the received information regarding the policy to identify a policy model composed of multiple components that define the content related to the policy in a hierarchical structure, generates a policy model in which one or more components corresponding to the information regarding the policy are modified from the multiple components contained in the identified policy model, and outputs the generated policy model.

[0010] According to one embodiment, it is possible to generate a policy model that is suited to the site where the policy is to be applied.

[0011] FIG. 1 is a block diagram illustrating an example of the functional configuration of a server device. FIG. 2 is a diagram illustrating an example of a flow graph of a policy. FIG. 3 is a diagram illustrating a specific example of a flow graph of a policy. FIG. 4 is a diagram illustrating an example of question collection data. FIG. 5 is a diagram illustrating an example of flow collection data. FIG. 6 is a schematic diagram illustrating an example of association information. FIG. 7 is a diagram (1) illustrating an example of a question window. FIG. 8 is a diagram (2) illustrating an example of a question window. FIG. 9 is a diagram (3) illustrating an example of a question window. FIG. 10 is a diagram (4) illustrating an example of a question window. FIG. 11 is a diagram (5) illustrating an example of a question window. FIG. 12 is a diagram illustrating an example of an answer confirmation window. FIG. 13 is a diagram illustrating an example of the result of generating a policy flow. FIG. 14 is a flowchart showing the steps of a model output process. FIG. 15 is a block diagram illustrating an example of the functional configuration of a server device related to an application example. FIG. 16 is a diagram (1) illustrating an example of a chatbot screen. FIG. 17 is a diagram (2) illustrating an example of a chatbot screen. FIG. 18 is a diagram illustrating an example of a hardware configuration.

[0012] Hereinafter, embodiments of the output program, output method, and information processing device according to the present application will be described with reference to the accompanying drawings. Each embodiment is merely an example, and does not limit the configuration, structure, functions, numerical values ​​used to specify these, or usage scenarios. Each embodiment can be adaptively combined within the scope of not causing contradictions in the processing content.

[0013] <First Embodiment> <System Configuration> Fig. 1 is a block diagram showing an example of the functional configuration of a server device 10. The server device 10 shown in Fig. 1 provides a model output function that outputs a policy model in which the design concept of the policy, i.e., a scenario, is digitized, in order to support the planning of the policy.

[0014] The server device 10 can provide the above model output function as a cloud service by executing PaaS (Platform as a Service) type middleware or SaaS (Software as a Service) type application.

[0015] As shown in Fig. 1, the server device 10 can be communicatively connected to a client terminal 30 via a network NW. For example, the network NW may be any type of communication network, whether wired or wireless, such as the Internet or a local area network (LAN). Note that Fig. 1 shows an example in which one client terminal 30 is connected to one server device 10, but any number of client terminals 30 may be connected.

[0016] The client terminal 30 is a terminal device that receives the model output function. For example, the client terminal 30 may be used by a customer such as a policy planner as an entity that implements a policy, such as a local government or other related party. The client terminal 30 may be realized by any computer, such as a personal computer, a smartphone, a tablet terminal, or a wearable terminal.

[0017] Although the above example illustrates a case in which the model output function is provided as a cloud service, the present invention is not limited to this. For example, the above model output function may be provided on-premise. Furthermore, the above example illustrates a case in which the model output function is provided in a client-server system, but the present invention is not limited to this. For example, the above model output function may be provided standalone by causing an application running on the client terminal 30 to cause the client terminal 30 to execute processing corresponding to the above model output function.

[0018] <Policy model> Here, the term "policy model" includes a diagram consisting of multiple components that define the contents of a policy in a hierarchical structure. For example, a policy model can be realized as a policy flow graph, a social concept, an organizational chart, a medical guideline, etc.

[0019] The following description will be given using a policy flow graph as an example of one policy model. FIG. 2 is a diagram illustrating a policy flow graph. Z1, Z2, Z3, and Z4 in FIG. 2 indicate, for example, services that an administrator provides to a user. These may also be referred to as "service implementation components." Specific examples of services include, in the medical field, "interventions" to which the policy target object, such as a resident, is assigned, such as undergoing a health checkup or being examined by a specialist, as well as "no intervention" such as follow-up observation, but are not limited to policies in the medical field.

[0020] H1 and H2 indicate, for example, conditional branches including conditions. These may also be referred to as "conditional branch components." Specific examples of conditions, in the medical field, include an estimated glomerular filtration rate (eGFR) below a threshold, a hemoglobin A1c value (HbA1c) below a threshold, and a urinary protein value equal to or greater than a threshold, but are not limited to conditions in the medical field.

[0021] Z1, Z2, Z3, Z4, H1, and H2 may each be referred to as a "component." From the perspective of graph data, such a "component" may correspond to an example of a "node." Furthermore, the connection between nodes may correspond to an example of an "edge," including a "directed edge."

[0022] In this embodiment, policy planning in the medical field will be described as an example, but the use case of the model output function described above is not limited to this. For example, the model output function described above may be applied to various policy planning in the transportation field such as road pricing, the energy field such as decarbonization and power supply, as well as work, testing, questionnaires, etc. In such cases, the same effects as when applied to policy planning in the medical field can be obtained.

[0023] Figure 3 shows a specific example of a policy flow graph. As shown in Figure 3, a policy is modeled as a workflow consisting of a combination of components such as conditional branching and service implementation. Then, the number of people receiving each service is output from a model that has been trained by accumulating information and parameters on the flow of people based on the actual values ​​when each conditional branching component is used.

[0024] In the example shown in FIG. 3 , the number of people N=1000 is input at S0. At S1, component #1 as service execution component A is set to "health check." At S2, component #2 as conditional branch component B is set to "eGFR<α." If "eGFR<α" is not satisfied (see the NO route at S2), it is determined that "no intervention" by a specialist is required for the citizen, as shown at S5.

[0025] On the other hand, if "eGFR<α" is satisfied (see the YES route at S2), then component #3 as conditional branch component C is set to "HbA1c<β" as shown at S3. If "HbA1c<β" is satisfied (see the YES route at S3), then component #4 as conditional branch component D is set to "nephrologist" as shown at S6, and it is determined that the citizen requires intervention by a "nephrologist." On the other hand, if "HbA1c<β" is not satisfied (see the NO route at S3), then it is determined that the citizen requires intervention by a "diabetes specialist" as shown at S7.

[0026] In the example shown in Figure 3, the number of people who will flow through part #1, part #2, part #3, and part #4 in that order is predicted, as indicated by the arrows. For example, in the policy flow graph shown in Figure 3, the results of assigning the number of people N = 1000 to interventions Z2 to Z4 are as follows: 50 people are assigned to intervention Z2. 150 people are assigned to intervention Z3. Furthermore, 800 people are assigned to intervention Z4.

[0027] Hereinafter, the flow graph of a policy may be abbreviated as "policy flow." Policy flows may be shared in any framework. As just one example, policy flows can be shared among organizations around the world, such as public organizations such as local governments, through a data-based platform that allows policy flows to be shared, cross-referenced, and updated.

[0028] Such a data infrastructure platform may be provided by the business that provides the model output function described above, or by another business. For example, a policy planner can refer to the policy flows from around the world collected in the data infrastructure via a client terminal 30. In this case, by incorporating all or part of the policy flows collected in the data infrastructure, the existing policy flows can be updated to support the planning of original policy flows.

[0029] In addition to sharing policy flows, the data infrastructure can also provide the following back-end functions. For example, it can run simulations that mimic the flow of objects targeted by services on existing and proposed policy flows. It can also evaluate indicators of existing and proposed policy flows, such as effectiveness and cost, and compare existing and proposed policy flows, or compare policy flows across multiple proposals.

[0030] <Configuration of Server Device 10> Next, the functional configuration of the server device 10 that provides the above-mentioned model output function will be described. Fig. 1 schematically shows blocks related to the model output function of the server device 10. As shown in Fig. 1, the server device 10 has a communication control unit 11, a storage unit 13, and a control unit 15. Note that Fig. 1 only shows a selection of functional units related to the above-mentioned model output function, and the server device 10 may also be provided with functional units other than those shown.

[0031] The communication control unit 11 is a functional unit that controls communications with other devices such as the client terminal 30. As just one example, the communication control unit 11 can be realized by a network interface card such as a LAN card. In one aspect, the communication control unit 11 receives a request to generate a policy flow from the client terminal 30, or outputs a policy flow to the client terminal 30.

[0032] The storage unit 13 is a functional unit that stores various types of data. As merely an example, the storage unit 13 may be realized by internal, external, or auxiliary storage of the server device 10. For example, the storage unit 13 stores question collection data 13A, flow collection data 13B, and association information 13C. Note that the question collection data 13A, flow collection data 13B, and association information 13C are merely examples, and data other than these may be stored in the storage unit 13.

[0033] The questionnaire data 13A may be a set of question templates in which questions about policies are categorized. Such question templates may include questions that accept the specification of the policy type to be planned, among a set of flow templates in which the basic form of a policy flow is categorized for each policy type. Additionally, the question templates may include questions that customize a part of the flow template.

[0034] Fig. 4 is a diagram showing an example of the question collection data 13A. As shown in Fig. 4, the question collection data 13A may be data in which items such as "major items," "questions," and "options or example answers" are associated with each other.

[0035] Here, "major items" refer to items that divide question categories. "Questions" refer to questions or text that corresponds to the definition of a question. "Choices or sample answers" refer to options or sample answers to questions. Note that "choices or sample answers" are illustrated for the sake of convenience, but they do not necessarily have to be used to present questions or obtain answers.

[0036] For example, Fig. 4 shows an excerpt from a collection of question templates related to medical function reorganization, merely as an example of a policy type. Details will be described later using Figs. 7 to 12, but by presenting questions based on the question templates shown in Fig. 4 to the client terminal 30, it is possible to receive, as answers, designations such as a policy type that identifies the type of policy to be planned and content for customizing the flow template.

[0037] The flow collection data 13B may be a collection of flow templates in which the basic form of a policy flow is stylized. FIG. 5 is a diagram showing an example of the flow collection data 13B. FIG. 5 shows an excerpt of flow template f1, which is a stylized version of the policy flow for the policy type "Medical Function Reorganization," as just one example of a flow template. As shown in FIG. 5, flow template f1 describes, in Business Process Model and Notation (BPMN), a procedure for allocating objects such as residents to service components corresponding to each medical function in the order of highly acute, acute, and recovery phases.

[0038] The association information 13C is information that defines the association between a question template and a flow template. As just one example, the association information 13C may describe the association between a question template and a target element of the flow template that is customized according to the answer corresponding to the question template, such as a component such as a service or a conditional branch, or a parameter of the component. As just one example, such association may be described in any format, such as JSON (Java (registered trademark) Script Object Notation) or a markup language.

[0039] Fig. 6 is a schematic diagram illustrating an example of the association information 13C. In Fig. 6, related elements #0 to #6 that are related to the question templates included in the question collection data 13A shown in Fig. 4 out of the flow template f1 shown in Fig. 5 are indicated by bold frames.

[0040] The association information 13C may include related elements #0 to #6 shown in Fig. 6. Furthermore, related elements #0 to #6 may be linked to information on modification patterns that customize parts of the flow template depending on answers corresponding to question templates. Such modification patterns may include, by way of example only, the following four modification patterns P1 to P4.

[0041] As one aspect, the related elements #1 to #4 are linked to a modification pattern P1 that customizes the service components arranged in parallel on the flow template or the parameters of the components.

[0042] For example, in the case of flow template f1, acute care institutions and recovery care institutions are given as examples of service components that are arranged in parallel on flow template f1. In this flow template f1, two components n4 and n5 are given as examples of acute care institutions, and two components n4 and n5 are given as examples of recovery care institutions, but the number of these medical institutions can be changed according to modification pattern P1.

[0043] Specifically, in the example of related element #1, the number of acute care medical institutions arranged in parallel in flow template f1 is changed depending on the answer corresponding to the question template of related element #1. Also, in the example of related element #2, the number of convalescent care medical institutions arranged in parallel in flow template f1 is changed depending on the answer corresponding to the question template of related element #2.

[0044] In the example of flow template f1, the parameters of the service components arranged in parallel on flow template f1 include the name of the medical institution and medical functions. These parameters can also be changed according to modification pattern P1.

[0045] Specifically, in the example of related element #3, the names of medical institutions n4 and n5 for the acute phase or the names of medical institutions n8 and n9 for the recovery phase are set according to the answer corresponding to the question template of related element #3. Also, in the example of related element #4, the medical functions of medical institutions n4, n5, n8, and n9, i.e., acute phase or recovery phase, are selected according to the answer corresponding to the question template of related element #4.

[0046] In another aspect, related element #5 is linked to modification pattern P2, which changes meta information of service components included in the flow template. For example, in the case of related element #5, the number of hospital beds is set as an example of detailed information for medical institutions n4, n5, n8, and n9, depending on the answer corresponding to the question template for related element #5. Note that the number of hospital beds is merely one example of an item included as detailed information for a medical institution, and other items such as the number of doctors may also be used.

[0047] As a further aspect, related element #6 is linked to modification pattern P3, which modifies the parameters of the conditional branch components included in the flow template. For example, in the case of related element #6, the threshold value of the bed occupancy rate used in the determination of conditional branch components n3 and n7 is set according to the answer corresponding to the question template of related element #6.

[0048] In another aspect, related element #0 is linked to modification pattern P4, which deletes a conditional branch component included in the flow template, or a conditional branch component included in the flow template and a service component connected to that component. For example, in the case of related element #0, conditional branch component n1 and the service connected to conditional branch component n1, i.e., tertiary emergency component n2, are set according to the answer corresponding to the question template of related element #0.

[0049] Thus, in the example shown in Figure 6, the association information 13C may include related element #0 (modification pattern P4), related elements #1 to #4 (modification pattern 1), related element #5 (modification pattern P2), and related element #6 (modification pattern P3).

[0050] The control unit 15 is a functional unit that performs overall control of the server device 10. As just one example, the control unit 15 may be realized by a hardware processor. Alternatively, the control unit 15 may be realized by hardwired logic. As shown in FIG. 1 , the control unit 15 includes a receiving unit 15A, an identifying unit 15B, a changing unit 15C, and an output unit 15D.

[0051] The reception unit 15A is a processing unit that receives various types of information from the client terminal 30. As just one example, the reception unit 15A can receive a request to generate a policy flow from the client terminal 30. When such a request to generate a policy flow is received, the reception unit 15A can receive various types of information related to the policy to be planned.

[0052] In one aspect, the reception unit 15A presents a flow template, a question requiring an answer of a so-called flow type, to the client terminal 30.

[0053] 7 is a diagram (1) showing an example of a question window. Fig. 7 shows a question window 200 generated according to a question template belonging to the major category "Questions for determining the basic form of a policy flow" in the question collection data 13A shown in Fig. 4.

[0054] 7, the question window 200 includes pull-down menus 201, 202, and 206. These pull-down menus 201, 202, and 206 correspond to the major categories of policy types: "Mobility," "Well-being," and "Education / Human Resources."

[0055] At this time, when an operation is performed on any of the pull-down menus 201, 202, and 206, an item button corresponding to the pull-down menu on which the operation was performed is displayed.

[0056] 7 shows an example in which the pull-down menu 202 is selected. In this case, item buttons 202B and 202C corresponding to the pull-down menu are displayed. These item buttons 202B and 202C correspond to the sub-categories of the policy type, "Regional Medical Reorganization" and "Health Insurance Policy." By accepting an operation on either of these item buttons 202B and 202C, it is possible to accept the designation of the policy type.

[0057] In another aspect, the reception unit 15A presents to the client terminal 30 a question requiring an answer regarding customization of the flow template designated by the client terminal 30 and received from the client terminal 30 .

[0058] 8 is a diagram (2) showing an example of a question window. Fig. 8 shows a question window 210 generated according to a question template belonging to the major category "Questions for refining the policy flow" in the question collection data 13A shown in Fig. 4.

[0059] As an example only, the question window 210 may be transitioned from the question window 200 when an operation is performed on the item button 202B of the policy type "regional medical reorganization" in the question window 200.

[0060] As shown in FIG. 8, the question window 210 displays question display fields 211 to 213 containing questions about customization related to acute care hospitals, in other words, processing and editing.

[0061] Of these, the question display field 211 is generated based on the question template "What is the name of the hospital?" in the question collection data 13A shown in Fig. 4. Furthermore, the question display field 211 includes a text box 211A. The answer of the name of the acute care hospital can be received by inputting text into such text box 211A.

[0062] The question display field 212 is generated based on the question template "Which diseases can you treat (multiple answers allowed)?" from the question collection data 13A shown in Fig. 4. The question display field 212 further includes four check boxes 212A to 212D. By selecting one of these check boxes 212A to 212D, answers regarding one or more types of diseases that the acute care hospital can treat can be received.

[0063] Furthermore, the question display field 213 is generated based on the question template "How many hospital beds does it have?" in the question collection data 13A shown in Fig. 4. Furthermore, the question display field 213 includes a text box 213A for accepting a numerical input, a spin button 213B for accepting an increase in the numerical value, and a spin button 213C for accepting an decrease in the numerical value. The answer regarding the number of hospital beds in the acute care hospital can be accepted via the spin box including the text box 213A, the spin button 213B, and the spin button 213C.

[0064] When answers to these question display fields 211 to 213 are entered and an operation is performed on the "Add hospital" GUI button 214, a request is accepted to add the acute care hospital corresponding to the answers to the question display fields 211 to 213 as a target for customization of the flow template.

[0065] 8 shows an example in which "FJ Hospital" and "KW Hospital" have been added as examples of flow template customization targets. When the "Next" GUI button 215A is operated with the flow template customization targets registered in this manner, the display transitions to the presentation of the next window. When the "Back" GUI button 215B is operated, the display returns to the presentation of the previous window.

[0066] 9 is a diagram (3) showing an example of a question window. Fig. 9 shows a question window 220 generated according to a question template belonging to the major category "Questions for refining the policy flow" in the question collection data 13A shown in Fig. 4.

[0067] As shown in FIG. 9, the question window 220 displays question display fields 221 to 223 containing questions about customization related to the convalescent hospital, in other words, processing and editing.

[0068] Of these, the question display field 221 is generated based on the question template "What is the name of the hospital?" in the question collection data 13A shown in Fig. 4. Furthermore, the question display field 221 includes a text box 221A. The answer of the name of the convalescent hospital can be received by inputting text into such text box 221A.

[0069] The question display field 222 is generated based on the question template "Which diseases can you treat (multiple answers allowed)?" from the question collection data 13A shown in Fig. 4. The question display field 222 further includes four check boxes 222A to 222D. By selecting one of these check boxes 222A to 222D, it is possible to receive answers about one or more types of diseases that the convalescent hospital can treat.

[0070] Furthermore, the question display field 223 is generated based on the question template "How many hospital beds does the hospital have?" in the question collection data 13A shown in Fig. 4. Furthermore, the question display field 223 includes a text box 223A for accepting a numerical input, a spin button 223B for accepting an increase in the numerical value, and a spin button 223C for accepting an decrease in the numerical value. The answer regarding the number of hospital beds in the convalescent hospital can be accepted via the spin box including the text box 223A, the spin button 223B, and the spin button 223C.

[0071] When answers to these question display fields 221 to 223 are entered and an operation is performed on the "Add hospital" GUI button 224, a request is accepted to add the convalescent hospital corresponding to the answers to the question display fields 221 to 223 as a target for customization of the flow template.

[0072] 9 shows an example in which "FJUv Hospital" and "FJ Clinic" have been added as examples of flow template customization targets. When the "Next" GUI button 225A is operated with the flow template customization targets registered in this manner, the display transitions to the presentation of the next window. When the "Back" GUI button 225B is operated, the display returns to the presentation of the previous window.

[0073] 10 is a diagram (4) showing an example of a question window. Fig. 10 also shows a question window 230 generated according to a question template belonging to the major category "Questions for refining the policy flow" in the question collection data 13A shown in Fig. 4.

[0074] As an example only, the question window 230 may be transitioned from the question window 220 when an operation is performed on the "Next" GUI button 225A of the question window 220.

[0075] 10, a question window 230 displays a question display field 231 including a question requiring an answer about the bed occupancy rate at which new patients can be admitted at each medical institution, such as an acute care hospital or a convalescent care hospital. Such a question display field 231 is generated based on the question template "What is the maximum bed occupancy rate that can be admitted?" in the question collection data 13A shown in FIG.

[0076] Furthermore, the question display field 231 includes a text box 231A for accepting a numerical value input, a spin button 231B for accepting an increase in the numerical value, and a spin button 231C for accepting an decrease in the numerical value.

[0077] An answer regarding the bed occupancy rate for accepting new patients can be received via the spin box including the text box 231A, spin button 231B, and spin button 231C.

[0078] When the "Next" GUI button 232A is operated after an answer has been entered in the question display field 231, the next window is displayed. When the "Back" GUI button 232B is operated, the previous window is displayed.

[0079] 10 illustrates an example in which a bed utilization rate for new patients can be received in common for both acute care hospitals and convalescent care hospitals, but the present invention is not limited to this. For example, a bed utilization rate for new patients can be received separately for acute care hospitals and a bed utilization rate for new patients can be received separately for convalescent care hospitals.

[0080] 11 is a diagram (5) showing an example of a question window. Fig. 11 shows a question window 240 generated according to a question template belonging to the major category "Questions for determining the basic form of a policy flow" in the question collection data 13A shown in Fig. 4.

[0081] As an example, the question window 240 may be transitioned from the question window 230 when an operation is performed on the "Next" GUI button 232A of the question window 230. This is merely an example, and the order in which the question window 240 is displayed is not limited to being next to the question window 230, and the question window 240 may be transitioned to be next to the question window 200.

[0082] 11, a question window 240 displays a question display field 241 including a question asking whether or not tertiary emergency care should be included in the policy. Such a question display field 241 is generated based on the question template "What are the stakeholders and their roles?" in the question collection data 13A shown in FIG.

[0083] Furthermore, the question display field 241 includes a check box 241A. Depending on whether or not such a check box 241A is checked, an answer as to whether or not the part n2 of the service "Tertiary Emergency" and the part n1 of the conditional branch that allocates an object to the part n2 of the service "Tertiary Emergency" are necessary can be received.

[0084] When the "Next" GUI button 242A is operated, the display transitions to the next window. When the "Back" GUI button 242B is operated, the display returns to the previous window.

[0085] 12 is a diagram showing an example of an answer confirmation window 250. As shown in Fig. 12, an answer confirmation window 250 displays confirmation of the answer input results in the question windows 200 to 240 shown in Figs.

[0086] According to this response confirmation window 250, a confirmation display is displayed indicating that responses to add "FJ Hospital" and "KW Hospital" as targets for customizing acute care hospitals are being accepted. Furthermore, as examples of detailed information about the acute care hospital "FJ Hospital," responses of the types of illnesses that can be treated, "pneumonia" and "stroke," as well as a confirmation display indicating that a response of the number of hospital beds, "100," is being accepted. Furthermore, as examples of detailed information about the acute care hospital "KW Hospital," responses of the types of illnesses that can be treated, "pneumonia" and "stroke," as well as a confirmation display indicating that a response of the number of hospital beds, "110," is being accepted.

[0087] Furthermore, the response confirmation window 250 displays a confirmation message indicating that responses to add "FJUv Hospital" and "FJ Clinic" as targets for customizing the convalescent hospital are being accepted. Furthermore, as examples of detailed information about the convalescent hospital "FJUv Hospital," responses to the types of illnesses that can be treated, "acute myocardial infarction," "pneumonia," "stroke," and "femur fracture," as well as a confirmation message indicating that a response to the number of hospital beds, "60," is being accepted. Furthermore, as examples of detailed information about the acute care hospital "FJ Clinic," responses to the types of illnesses that can be treated, "acute myocardial infarction," "pneumonia," "stroke," and "femur fracture," as well as a confirmation message indicating that a response to the number of hospital beds, "40," is being accepted.

[0088] Furthermore, the answer confirmation window 250 displays a confirmation message indicating that the answer accepted for customizing the conditional branch parameters is a bed occupancy rate of "95%" that can accept new patients and is common to both the acute care hospital and the convalescent care hospital.

[0089] Furthermore, the answer confirmation window 250 displays a confirmation message indicating that the answer "true" has been accepted as a customization target for the stakeholder regarding the necessity of considering tertiary emergency care.

[0090] Here, when an operation is performed on the "Confirm Answer" GUI button 251A, customization of the flow template is started. Note that when an operation is performed on the "Download Answer" GUI button 251B, a file, such as a JSON file, in which the answer input results displayed for confirmation in the answer confirmation window 250 are written is output to the client terminal 30.

[0091] Returning to the explanation of FIG. 1 , the identification unit 15B is a processing unit that uses information about the measures received by the receiving unit 15A to identify a flow template to be planned and target elements to be customized on the flow template. For example, the identification unit 15B receives information about the measures and uses the received information about the measures to identify a policy model composed of multiple components that define the content related to the measures in a hierarchical structure. More specifically, for example, the identification unit 15B uses the received information about the measures to identify a policy model that includes a diagram composed of multiple components that define the content related to the measures in a hierarchical structure.

[0092] In one aspect, the identification unit 15B identifies a flow template corresponding to the policy type whose designation has been accepted by the accepting unit 15A from the flow collection data 13B. As an example, the identification unit 15B acquires the policy type whose designation has been accepted via the question window 200 shown in FIG. 7 . For example, consider a case where the item button 202B for the policy type "regional medical reorganization" is selected in the question window 200 shown in FIG. 7 . In this case, the identification unit 15B identifies, from among the flow templates included in the flow collection data 13B, a flow template f1 (see FIG. 5 ) in which the basic form of the policy flow for the policy type "medical function reorganization" has been stylized.

[0093] In another aspect, for each answer to a question presented by the receiving unit 15A, the identifying unit 15B identifies a target element of the specified flow template to be customized according to the answer, such as a component such as a service or a conditional branch, or a parameter of the component. When identifying the target element in this way, a related element in the association information 13C stored in the storage unit 13, which describes the association of the question template corresponding to the answer, is referenced.

[0094] The modification unit 15C is a processing unit that modifies the target elements identified by the identification unit 15B according to a modification pattern corresponding to each answer to the question presented by the reception unit 15A. For example, the modification unit 15C generates a policy model in which one or more parts corresponding to information about the policy have been modified from among the multiple parts included in the identified policy model. More specifically, for example, the modification unit 15C identifies one or more parts corresponding to information about the policy from among the multiple parts included in the identified policy model. Then, the modification unit 15C generates a policy model including a diagram in which the one or more identified parts have been modified based on the received information about the policy.

[0095] The change unit 15C may generate a policy model in which one or more components have been changed using an answer to a question displayed on the chat screen. For example, the reception unit 15A receives a chat start instruction from the terminal 30 and displays a question asking about customizing the identified policy model on the chat screen that has received the chat start instruction from the terminal 30. The reception unit 15A then receives from the terminal 30 an answer to the question displayed on the chat screen. At this time, the change unit 15C changes one or more components corresponding to information about the policy from among the multiple components included in the identified policy model, based on the answer to the question. The change unit 15C then generates a policy model including a diagram in which one or more components have been changed.

[0096] 13 is a diagram showing an example of the generated policy flow F1, which is generated by customizing the flow template f1 in accordance with the input results of the answers exemplified in the answer confirmation window 250 shown in FIG.

[0097] For example, according to the answer confirmation window 250 shown in Fig. 12, answers for two acute care hospitals, "FJ Hospital" and "KW Hospital," are obtained as answers to the question template "How many acute care hospitals are there?" shown in Fig. 4. In this case, related element #1, which describes the association of the question template "How many acute care hospitals are there?", is referenced, and therefore parts n4 and n5 corresponding to the service "acute care hospitals" in flow template f1 are identified as target elements. Furthermore, related element #1 corresponds to modification pattern P1, and therefore the number of acute care hospitals arranged in parallel in flow template f1 is customized to two.

[0098] 12, the answer confirmation window 250 acquires the answers of two convalescent hospitals, "FJUv Hospital" and "FJ Clinic," as the answer to the question template "How many convalescent hospitals are there?" shown in FIG. 4. In this case, the related element #2, which describes the association of the question template "How many convalescent hospitals are there?", is referenced, and therefore, the parts n8 and n9 corresponding to the service "convalescent hospitals" in the flow template f1 are identified as the target elements. Furthermore, the related element #2 corresponds to the modification pattern P1, and therefore the number of convalescent hospitals arranged in parallel in the flow template f1 is customized to two.

[0099] Furthermore, according to the answer confirmation window 250 shown in FIG. 12 , the hospital name “FJ Hospital” and the medical function “acute phase,” the hospital name “KW Hospital” and the medical function “acute phase,” the hospital name “FJUv Hospital” and the medical function “convalescence phase,” and the hospital name “FJ Clinic” and the medical function “convalescence phase” are acquired as answers to the question template “What is the name of the hospital?” shown in FIG. 4 and the question template “Which medical function?” shown in FIG. 4 . Since related elements #3 and #4, which describe the association of these question templates, are referenced, parts n4 and n5 corresponding to the service “acute phase hospital” and parts n8 and n9 corresponding to the service “convalescence phase hospital” are identified as target elements in the flow template f1. Furthermore, related elements #3 and #4 correspond to the modification pattern P1. Therefore, the hospital names of parts n4 and n5 corresponding to the medical function "acute phase" are changed to "FJ Hospital" and "KW Hospital", respectively, and the hospital names of parts n8 and n9 corresponding to the medical function "recovery phase" are changed to "FJUv Hospital" and "FJ Clinic", respectively.

[0100] 12, the answer confirmation window 250 acquires the following answers to the question template "How many beds does this hospital have?" shown in FIG. 4: "100" for the number of beds at FJ Hospital, "110" for KW Hospital, "60" for FJUv Hospital, and "40" for FJ Clinic. Since the related element #5, which describes the association of this question template, is referenced, the meta information of the part n4 corresponding to FJ Hospital, the meta information of the part n5 corresponding to KW Hospital, the meta information of the part n8 corresponding to FJUv Hospital, and the meta information of the part n9 corresponding to FJ Clinic in the flow template f1 are identified as target elements. Furthermore, the related element #5 corresponds to the modification pattern P2. Therefore, the number of beds included in the meta information of the part n4 corresponding to FJ Hospital is changed to "100." Furthermore, the number of beds included in the meta information of the part n5 corresponding to KW Hospital is changed to "110." Furthermore, the number of hospital beds included in the meta information of part n8 corresponding to FJUv Hospital is changed to "60." Furthermore, the number of hospital beds included in the meta information of part n9 corresponding to FJ Clinic is changed to "40."

[0101] Furthermore, according to the answer confirmation window 250 shown in FIG. 12 , a bed occupancy rate of "95%" is acquired as the answer to the question template shown in FIG. 4 , "What is the maximum bed occupancy rate for hospitalizations?" Since the related element #6, which describes the association of this question template, is referenced, the bed occupancy rate parameter of the conditional branch component n3 and the bed occupancy rate parameter of the conditional branch component n7 in the flow template f1 are identified as target elements. Furthermore, the related element #6 corresponds to the modification pattern P3. Therefore, the bed occupancy rate parameter of the conditional branch component n3 is changed to "95%," and the bed occupancy rate parameter of the conditional branch component n7 is also changed to "95%."

[0102] 12, the answer confirmation window 250 acquires "true" as the answer to the question generated from the question template "What are the stakeholders and their respective roles?" shown in FIG. 4 regarding the necessity of considering tertiary emergency care. Since the related element #0 describing the association of this question template is referenced, the component n2 of the service "tertiary emergency care" and the component n1 of the conditional branch that allocates an object to the component n2 of the service "tertiary emergency care" in the flow template f1 are identified as target elements. Furthermore, the related element #0 corresponds to the modification pattern P4. Therefore, the component n2 of the service "tertiary emergency care" and the component n1 of the conditional branch are left untouched and remain in the flow template f1. Note that, while an example in which "true" is acquired regarding the necessity of considering tertiary emergency care is given here, if "false" is acquired as the necessity of considering tertiary emergency care, the component n2 of the service "tertiary emergency care" and the component n1 of the conditional branch that are identified as target elements are deleted from the flow template f1.

[0103] By executing a series of customizations on the flow template f1 in this way, the policy flow F1 shown in FIG. 13 is generated.

[0104] Returning to the description of FIG. 1 , the output unit 15D executes various output controls. As an example, the output unit 15D can display, on the client terminal 30, a policy flow generated by customizing the flow template by the modification unit 15C. The policy flow displayed on the client terminal 30 can be arbitrarily edited using a graph editing tool or the like. The output destination of the policy flow is not limited to the client terminal 30. For example, the output unit 15D can also output the policy flow generated by customizing the flow template by the modification unit 15C to a back-end function, service, application, or the like that operates on the data platform. For example, the output unit 15D displays a diagram of the policy model generated by the modification unit 15C on a chat screen that receives a chat start instruction from the terminal 30.

[0105] 14 is a flowchart showing the steps of the model output process. This process is merely an example and can be started when a request to generate a policy flow is received from the client terminal 30.

[0106] 14, the reception unit 15A presents a question for accepting the designation of a policy type to be planned to the client terminal 30 (Step S101). Subsequently, the reception unit 15A acquires an answer regarding the policy type to the question presented in Step S101 (Step S102).

[0107] Thereafter, the reception unit 15A executes a loop process 1 in which steps S103 and S104 described below are repeated a number of times corresponding to the number K of questions asking about the content of customizing the flow template corresponding to the policy type answered in step S102. It goes without saying that steps S103 and S104 can be executed in parallel for a plurality of questions.

[0108] That is, the reception unit 15A presents the k-th question to the client terminal 30 based on the question template related to the policy type answered in step S102 from the questionnaire data 13A (step S103). Subsequently, the reception unit 15A acquires the answer to the k-th question presented in step S103 (step S104).

[0109] By repeating this loop process 1, answers to each of the K questions are obtained.

[0110] Then, the identifying unit 15B acquires a flow template corresponding to the measure type answered in step S102 from among the flow templates included in the flow collection data 13B (step S105).

[0111] Thereafter, loop process 2 is executed, which repeats steps S106 and S107 described below a number of times corresponding to the number K of answers obtained in loop process 1. It goes without saying that steps S106 and S107 can be executed in parallel for a plurality of answers.

[0112] That is, the specifying unit 15B specifies a target element to be customized with the m-th answer from the flow template acquired in step S105 (step S106). Then, the changing unit 15C customizes the target element specified in step S106 according to the modification pattern corresponding to the m-th answer (step S107).

[0113] By repeating this loop process 2, customization corresponding to each of the M responses is performed on the flow template, thereby generating a policy flow from the flow template.

[0114] Then, the output unit 15D outputs the policy flow generated as a result of the loop process 2 to an arbitrary output destination, for example, the client terminal 30 (step S108), and ends the process.

[0115] <One aspect of the effect> As described above, the server device 10 according to this embodiment presents questions for customizing a flow pattern in which the basic form of a policy flow has been stylized, and customizes part of the flow pattern based on the answers to the questions. This makes it possible to generate a policy flow that is in compliance with laws and regulations without missing any components that are essential in the field. Therefore, the server device 10 according to this embodiment makes it possible to generate a policy model that is suited to the field where the policy will be applied.

[0116] Although the embodiments of the disclosed device have been described above, the present invention may be embodied in various different forms other than the above-described embodiments. Therefore, other embodiments included in the present invention will be described below.

[0117] <Chat APP> In the first embodiment, an example has been given in which questions are generated based on the question collection data 13A and presented to the client terminal 30, but the question does not necessarily have to be generated using the question collection data 13A.

[0118] Fig. 15 is a block diagram showing an example of the functional configuration of a server device 20 according to an application example. The server device 20 shown in Fig. 15 differs from the server device 10 shown in Fig. 1 in that part of the functional configuration of the control unit 21 is different and the question collection data 13A does not need to be stored in the storage unit 13. In Fig. 2, functional units that perform the same functions as those of the server device 10 are assigned the same reference numerals.

[0119] As shown in Figure 15, the control unit 21 has a chat APP (APPlication) execution unit 23 that performs the same functions as the reception unit 15A, identification unit 15B, and change unit 15C that the control unit 15 of the server device 10 shown in Figure 1 has.

[0120] Such a chat APP execution unit 23 can be realized by executing an AI chat application program realized by a large-scale language model such as Transformer, a so-called LLM.

[0121] In this case, the chat APP execution unit 23 can provide the chat APP with a prompt for the association information 13C, thereby presenting questions equivalent to those presented by the reception unit 15A shown in Figure 1 to the client terminal 30 even without the question collection data 13A.

[0122] 16 and 17 are diagrams (1) and (2) showing examples of chatbot screens. Chatbot screens 260 and 270 generated by a chat APP are shown in FIGS. 16 and 17. For example, it is clear that the chatbot screen 260 shown in FIG. 16 can present questions equivalent to those in the question window 200 shown in FIG. 7. Furthermore, it is clear that the chatbot screen 270 shown in FIG. 17 can present questions similar to those in the question window 210 shown in FIG. 8. Although not described here, chatbot screens capable of presenting questions equivalent to those in the question windows 220 to 250 shown in FIGS. 9 to 11 can also be generated.

[0123] In this way, by providing a prompt for the association information 13C to the chat APP, the question collection data 13A can be made unnecessary.

[0124] <Distribution and Integration> Furthermore, the components of each device shown in the figure do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of the devices can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. For example, the reception unit 15A, the identification unit 15B, the change unit 15C, or the output unit 15D may be connected via a network as an external device to the server device 10 or the server device 20. Furthermore, the reception unit 15A, the identification unit 15B, the change unit 15C, or the output unit 15D may be included in a separate device, and the functions of the server device 10 or the server device 20 may be realized by the devices being connected to a network and operating together.

[0125] <Hardware Configuration> The various processes described in the above embodiments can be realized by executing a prepared program on a computer such as a personal computer, a workstation, etc. Therefore, an example of a computer that executes a model output program having the same functions as those in the first and second embodiments will be described below with reference to FIG.

[0126] Fig. 18 is a diagram showing an example of a hardware configuration. As shown in Fig. 18, a computer 100 has an operation unit 110a, a speaker 110b, a camera 110c, a display 120, and a communication unit 130. The computer 100 also has a CPU 150, a ROM 160, an HDD 170, and a RAM 180. These units 110 to 180 are connected via a bus 140.

[0127] 18, the HDD 170 stores a model output program 170a that performs the same functions as the receiving unit 15A, identifying unit 15B, changing unit 15C, and output unit 15D shown in the first embodiment. This model output program 170a may be integrated or separated, similar to the components of the receiving unit 15A, identifying unit 15B, changing unit 15C, and output unit 15D shown in FIG. 1. In other words, the HDD 170 does not necessarily have to store all of the data shown in the first embodiment, as long as the data used for processing is stored in the HDD 170.

[0128] Under such an environment, the CPU 150 reads the model output program 170a from the HDD 170 and loads it into the RAM 180. As a result, the model output program 170a functions as a model output process 180a, as shown in FIG. 18 . This model output process 180a loads various data read from the HDD 170 into an area of ​​the storage area of ​​the RAM 180 allocated to the model output process 180a, and executes various processes using the loaded data. For example, examples of processes executed by the model output process 180a include the processes shown in FIG. 14 . Note that the CPU 150 does not necessarily need to operate all of the processing units shown in the first embodiment above; it is sufficient that the processing units corresponding to the processes to be executed are virtually implemented.

[0129] The model output program 170a does not necessarily have to be stored in the HDD 170 or the ROM 160 from the beginning. For example, each program may be stored on a "portable physical medium" such as a flexible disk, a so-called FD, a CD-ROM, a DVD disk, a magneto-optical disk, or an IC card that is inserted into the computer 100. The computer 100 may then acquire and execute each program from such a portable physical medium. Alternatively, each program may be stored in another computer or server device connected to the computer 100 via a public line, the Internet, a LAN, a WAN, or the like, and the computer 100 may acquire and execute each program from such a computer or server device.

[0130] REFERENCE SIGNS LIST 10 Server device 11 Communication control unit 13 Storage unit 13A Question collection data 13B Flow collection data 13C Association information 15 Control unit 15A Reception unit 15B Identification unit 15C Change unit 15D Output unit 30 Client terminal

Claims

1. An output program that causes a computer to execute the following processes: accept information related to a policy; use the accepted information related to the policy to identify a policy model composed of a plurality of components that define the content related to the policy in a hierarchical structure; generate a policy model in which one or more components corresponding to the information related to the policy are changed from among the plurality of components contained in the identified policy model; and output the generated policy model.

2. The output program of claim 1, characterized in that the process of identifying the policy model identifies a policy model including a diagram composed of a plurality of parts that define the contents related to the policy in a hierarchical structure, the process of generating identifies one or more parts corresponding to information related to the policy from among the plurality of parts contained in the identified policy model, and generates a policy model including the diagram in which the identified one or more parts have been changed based on the received information related to the policy, and the process of outputting displays the generated diagram of the policy model on a screen.

3. The output program according to claim 1, characterized in that the identified policy model is a policy model including a diagram composed of the multiple parts, the receiving process includes a process of receiving an instruction to start a chat from a terminal and displaying a question asking about the content of customizing the identified policy model on a chat screen that has received the instruction to start a chat from the terminal, and receiving an answer to the displayed question from the terminal, the generating process includes a process of generating a policy model including the diagram in which one or more parts have been changed based on the answer to the question, and the output process includes a process of displaying the generated diagram of the policy model on the chat screen that has received the instruction to start a chat from the terminal.

4. The output program according to claim 1, characterized in that the receiving process includes a process of presenting a question based on a pre-arranged question template and obtaining an answer to the question, the identifying process includes a process of identifying a flow template from pre-prepared flow templates that corresponds to the obtained answer, the generating process includes a process of identifying one or more parts that correspond to the obtained answer from among multiple parts of the identified flow template based on the identified flow template and association information associating the question template and the flow template, and generating a flow graph of a policy in which the one or more parts of the identified flow template are modified based on the obtained answer, and the output process includes a process of displaying the generated flow graph of the policy flow.

5. The output program according to claim 4, further causing the computer to execute a process of accepting changes to the flow graph of the displayed action flow.

6. The output program according to claim 4, characterized in that the generating process includes a process for changing service components arranged in parallel on the flow template or parameters of the components.

7. The output program according to claim 4, wherein the generating process includes a process for changing meta-information of a service component included in the flow template.

8. The output program according to claim 4, wherein the generating process includes a process for changing a parameter of a conditional branch part included in the flow template.

9. An output program as described in claim 4, characterized in that the generating process includes a process of deleting a conditional branch component included in the flow template, or a conditional branch component included in the flow template and a service component connected to said component.

10. An output method characterized in that a computer executes the following processes: accept information related to a policy; use the accepted information related to the policy to identify a policy model composed of a plurality of parts that define the content related to the policy in a hierarchical structure; generate a policy model in which one or more parts corresponding to the information related to the policy are changed from among the plurality of parts contained in the identified policy model; and output the generated policy model.

11. An information processing device having a control unit that executes the following processes: accepts information related to a policy; uses the accepted information related to the policy to identify a policy model composed of a plurality of components that define the content related to the policy in a hierarchical structure; generates a policy model in which one or more components corresponding to the information related to the policy are changed from among the plurality of components contained in the identified policy model; and outputs the generated policy model.

Images