Business support system, its control method, and program

Abstract

This enables supporters who provide support services to improve their work efficiency or the quality of their work. [Solution] A business support system that analyzes cases in support work has a reception unit that receives case information including psychological test results of the person being supported and information indicating the situation of the person being supported, a collection unit that collects information for analysis from a predetermined knowledge database, a generation unit that uses the case information and the information collected by the collection unit as input for a large-scale language model to generate information as analysis results including an evaluation of the situation of the person being supported and the basis for that evaluation, and an output unit that outputs the generated analysis results.

Description

[Technical Field]

[0001] The present invention relates to a business support system, a control method thereof, and a program. [Background technology]

[0002] In recent years, community support services have begun to use systems that provide support to recipients based on their individual circumstances. Community support must take into account a wide range of recipients and circumstances, including child support, abuse response, child injury and accident response, maternal and child health, domestic violence (DV), sexual violence, delinquency and crime response, developmental disabilities, elderly welfare, welfare for people with disabilities, delinquency and crime investigation, and harassment.

[0003] For example, community support services require appropriate support after analyzing the ever-changing circumstances of the recipients and their surrounding environments. Furthermore, when providing such support, a basis for determining the content of support is required. Such analysis and presentation of the basis must be based on specialized knowledge, such as legal and medical knowledge, institutional knowledge, past cases, and evidence. Therefore, this type of work can be quite difficult for inexperienced supporters.

[0004] For example, Patent Document 1 discloses a system that analyzes conversation histories regarding child-rearing problems and consultations, and provides support to users suspected of abuse based on the results of the analysis. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2025-048168 Summary of the Invention [Problem to be solved by the invention]

[0006] Recently, AI-related technologies such as machine learning and generative AI (artificial intelligence) have been developed and are being used in a variety of fields. Each of these AI-related technologies has its own unique characteristics, and by utilizing these characteristics, they can be useful in solving the above-mentioned issues that must be considered in support services.

[0007] In view of the above problems, the present invention aims to provide functions for improving the work efficiency of supporters who provide support services and the quality of their work. [Means for solving the problem]

[0008] In order to solve the above problems, one aspect of the present invention has the following configuration: A business support system that analyzes cases in support work, a reception unit that receives case information including psychological test results of the support recipient and information indicating the situation of the support recipient; a collection unit that collects information for analysis from a predetermined knowledge database; a generation unit that generates, as an analysis result, information including an evaluation of the situation of the support recipient and the basis for the evaluation, by using the case information and the information collected by the collection unit as inputs of a large-scale language model; an output unit that outputs the generated analysis result; It has.

[0009] Another aspect of the present invention has the following configuration: A business support system for a support business for a support recipient, comprising: a reception unit that receives case information including information indicating the status of the support recipient; a collection unit that collects information related to a predetermined field from a predetermined knowledge database; a generation unit that generates, as an analysis result, information including an assessment of the situation of the support recipient and a response plan based on information in the predetermined field for the assessment, by using the case information and the information collected by the collection unit as inputs to a large-scale language model; an output unit that outputs the generated analysis results as a report in a predetermined format; It has.

[0010] Another aspect of the present invention has the following configuration: That is, a control method of a business support system that analyzes cases in support business, comprising: a receiving step of receiving case information including the results of a psychological test on the support recipient and information indicating the situation of the support recipient; a collection step of collecting information for analysis from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an evaluation of the situation of the support recipient and the basis for the evaluation, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis result; It has.

[0011] Another aspect of the present invention has the following configuration: That is, a control method of a business support system for a support business for a support recipient, comprising: a receiving step of receiving case information including information indicating the status of the support recipient; a collection step of collecting information related to a predetermined field from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an assessment of the situation of the support recipient and a response plan based on information in the predetermined field for the assessment, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis results as a report configured in a predetermined format; It has.

[0012] Another aspect of the present invention has the following configuration: a program comprising: On the computer, a receiving step of receiving case information including the results of a psychological test on the support recipient and information indicating the situation of the support recipient; a collection step of collecting information for analysis from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an evaluation of the situation of the support recipient and the basis for the evaluation, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis result; Execute the following.

[0013] Another aspect of the present invention has the following configuration: a program comprising: On the computer, a receiving step of receiving case information including information indicating the status of the support recipient; a collection step of collecting information related to a predetermined field from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an assessment of the situation of the support recipient and a response plan based on information in the predetermined field for the assessment, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis results as a report configured in a predetermined format; Execute the following. [Effects of the Invention]

[0014] According to the present invention, it is possible to provide a function for improving the work efficiency of supporters who provide support services and the quality of their work. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 is a configuration diagram showing an example of the configuration of a business support system according to a first embodiment of the present invention. [Figure 2] FIG. 1 is a functional block diagram showing a server terminal according to a first embodiment of the present invention; [Figure 3] FIG. 1 is a functional block diagram showing a user terminal according to a first embodiment of the present invention; [Figure 4]FIG. 1 is a schematic diagram illustrating a data flow in a system according to a first embodiment of the present invention. [Figure 5A] FIG. 1 is an example illustrating input and output data of a generative model according to a first embodiment of the present invention; [Figure 5B] FIG. 1 is an example showing an example of output data of a generative model according to the first embodiment of the present invention; [Figure 5C] FIG. 1 is an example of form data according to the first embodiment of the present invention; [Figure 6] 1 is a flowchart of a process according to a first embodiment of the present invention; [Figure 7A] FIG. 10 is an example for explaining input and output data of a generative model according to a second embodiment of the present invention; [Figure 7B] FIG. 10 is an example showing an example of input data for a generative model according to a second embodiment of the present invention; [Figure 7C] FIG. 10 is an example showing an example of output data of a generative model according to a second embodiment of the present invention; [Figure 7D] FIG. 10 is an example of form data according to a second embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that the embodiment described below is one embodiment for explaining the present invention and is not intended to be interpreted as limiting the present invention. Furthermore, not all configurations described in each embodiment are necessarily essential configurations for solving the problems of the present invention. Furthermore, in each drawing, the same components are assigned the same reference numerals to indicate their correspondence. Note that to avoid unnecessary redundancy and to facilitate understanding by those skilled in the art, some of the description may be omitted or simplified. For example, detailed descriptions of already well-known matters or redundant descriptions of substantially identical configurations may be omitted.

[0017] First, in the embodiment of the present invention, a description will be given assuming a child support service, which is a type of administrative service. Note that some or all of the functions and components of the embodiments described below are not limited to application only to child support services, but may be applied to various fields and services. Furthermore, modifications, adjustments, extensions, etc. may be made as appropriate depending on the field or service to which they are applied.

[0018] Furthermore, the term "personal information" used in the following description may include data collected directly from an individual or not, and may include data consisting of one or more items. If other information is generated or derived based on personal information including PII (Personally Identifiable Information), such other information may also be treated as personal information. Personal information is generally managed under strict restrictions on its handling as sensitive data (hereinafter collectively referred to as "sensitive data"). In the following embodiment of the present invention, child support services provided by government agencies and other organizations are assumed to be provided under management based on such restrictions.

[0019] Furthermore, the configuration according to the present invention assumes the use of sensitive data such as personal information that requires careful handling, and therefore assumes a network in which access by users is restricted. Note that the method of access restriction here is not particularly limited, but one example is the use of a closed network that is not connected to the Internet. Furthermore, it is assumed that the data that these users can access, the scope of that data, and how it is handled are specified based on the tasks and authority assigned to them.

[0020] In this embodiment, a generating AI is used that is generated by performing a predetermined learning process based on machine learning technology. The learning algorithm, learning method, and learning data for generating the generating AI are not particularly limited, and may be adjusted or combined as appropriate to provide the functions described below.

[0021] Large language models (LLMs) in generative AI are built based on large-scale data and are capable of outputting data that takes into account the context of the input data. Examples of well-known LLMs include ChatGPT, Copilot, Gemini, Claude, Llama, and OpenELM.

[0022] First Embodiment In a first embodiment of the present invention, support for child abuse will be described as an example of child support services provided by government agencies, etc. In particular, for each case of child abuse, analysis of risks and countermeasures for those risks, and organization and presentation of information that serves as the basis for that analysis are envisioned.

[0023] More specifically, supporters, such as staff at child consultation centers, are required to comprehensively collect information, objectively assess risks, develop evidence-based intervention plans, accurately understand the impact on children, and make future forecasts while dealing with complex and diverse child abuse cases. These tasks require a high level of expertise and considerable effort, placing a heavy burden on individual staff members. Conventionally, there has been a lack of comprehensive support for such multifaceted analysis and structured report creation, particularly the ability to organize and present information that serves as the basis for judgment. Therefore, this embodiment provides a work support function that reduces the workload of the above-mentioned tasks and enables more appropriate support to be provided to support recipients.

[0024] [System Configuration] FIG. 1 is a schematic diagram illustrating an example of the configuration of a business support system (information processing system) according to a first embodiment of the present invention. The business support system 1 may be, for example, a system whose primary function is to support communication with users and decision-making. It allows for the input, viewing, and sharing of records both within and outside the organization where the business is performed, and may also be a system that allows chat communication between supporters, registration and sharing of photos of support recipients, or simulation of past support trends. Here, a child consultation center that provides child support services is used as an example of an institution to which the system can be applied, but the present invention is not limited to this. The system may be applied to or configured to cooperate with systems of organizations such as city / ward / town / village offices, maternal and child health centers, schools, kindergartens, daycare centers, medical institutions, police, prosecutors, fire departments, child welfare organizations, and non-profit organizations (NPOs), as well as private companies that cooperate with these organizations. The business support system 1 includes a server device 100, multiple user terminals 200, and a linkage system 300. Each device constituting the business support system 1 is configured to be able to communicate via a network NW.

[0025] The server device 100 is a device for providing various functions provided by the business support system 1 to the user terminals 200. The server device 100 provides applications for supporting business efficiency improvement to each of the user terminals 200 and manages information registered via each of the user terminals 200. Note that some or all of the functions described below may be provided by the user terminals 200 or by a linkage system 300 that can link via a network NW. The server device 100 may be configured on-premise using a general-purpose computer such as a workstation or a personal computer, or may be logically realized by cloud computing (e.g., SaaS (Software as a Service)). In this embodiment, for convenience of explanation, one server device 100 is illustrated as an example, but the present invention is not limited to this. Multiple server devices 100 may be used, and servers with different roles, such as an authentication server and a database server, may also be included.

[0026] The user terminal 200 is an operation terminal used by users such as staff of a child consultation center. The user terminal 200 may be configured, for example, by an information processing device such as a personal computer, a tablet terminal, a smartphone, or a POS terminal. The user terminal 200 provides users with web services provided by the server device 100 and the functions of applications installed and running on the user terminal 200. In the example of FIG. 1, two user terminals 200a and 200b are shown, but more user terminals may be used. The configurations of the multiple user terminals 200 may be different from each other or may be the same. Furthermore, the available functions may differ depending on the role and authority of the user using the user terminal 200. For convenience, the user terminals will be collectively described as the user terminal 200. Note that when it is necessary to explain each individual user terminal separately, suffixes (a, b, ...) will be added.

[0027] The linkage system 300 is an external system that functions in cooperation with the server device 100 via a network NW. The linkage system 300 may be configured, for example, as a child consultation record system, and its primary functions may be recording child consultations and issuing administrative documents. The child consultation record system performs tasks such as issuing child ID numbers and reception numbers related to children, issuing consultation tickets and temporary protection decision notices, managing family information and fees linked to administrative information, and managing the progress of procedures. The configuration of the linkage system 300 is not particularly limited, and it may be configured to provide, for example, various functions related to business support. While only one linkage system 300 is shown, this configuration is not limited, and the linkage system 300 may be configured with one or more devices depending on the functions and services.

[0028] The network NW may be configured by the Internet, an intranet, a wireless LAN (Local Area Network), a WAN (Wide Area Network), etc. Note that there are no particular limitations on the communication standards or wired / wireless nature of the network NW, and the network NW may be configured by combining multiple communication standards. As mentioned above, in consideration of the confidentiality of the information handled, the network NW may be configured as a closed network accessible only to specified users, rather than a public network such as the Internet.

[0029] 2 is a block diagram showing an example of the functional configuration of the server device 100 according to this embodiment. The server device 100 includes a control unit 110, a communication unit 130, and a storage unit 140. These units are configured to be able to communicate with each other via an internal bus or the like.

[0030] The control unit 110 controls the operation of the server device 100. The control unit 110 is composed of, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an NPU (Neural network Processing Unit), etc., and provides various functions by reading and executing various programs and data stored in the storage unit 140. The control unit 110 functions as, for example, a data collection unit 111, a data management unit 112, a data generation unit 113, a prompt control unit 114, an output data generation unit 115, a RAG data collection unit 116, a RAG data generation unit 117, a knowledge data update unit 118, a display control unit 119, and a communication control unit 120.

[0031] The data collection unit 111 collects data from various databases (hereinafter referred to as "DB") configured in the storage unit 140 based on user instructions. Note that the data collected by the data collection unit 111 is not limited to data stored in the storage unit 140, and may be collected by inquiring externally (for example, the linked system 300).

[0032] The data management unit 112 manages the recording, reference, updating, etc. of data in the various DBs configured in the storage unit 140. Examples of data managed in each DB will be described later.

[0033] The data generation unit 113 inputs various data and prompts to a large-scale language model (LLM) obtained by learning processing, and outputs desired generated data. Details of input and output to the generation model as a large-scale language model according to this embodiment will be described later.

[0034] The prompt control unit 114 controls and selects prompts to be used in the generative model according to this embodiment, based on user instructions. The prompts used vary depending on the type and content of the generated data output by the generative model. In this embodiment, prompts may be selected based on information such as the purpose of the interview and the interviewee indicated by the user's instructions. Predefined prompts may also be used in combination. In this embodiment, Retrieval-Augmented Generation (RAG) technology is used when generating prompts to input into the generative model. An example of using the RAG technology according to this embodiment will be described later. Note that the RAG technology is just one example, and other technologies may be used as long as they can implement the functions to be realized in this embodiment.

[0035] The output data generation unit 115 generates output data converted into an output format using the data generated by the data generation unit 113. For example, the output data may be in a file format or a display screen for displaying on a browser or the like. More specifically, the output data may be report data in a predetermined format.

[0036] The RAG data collection unit 116 collects various information (hereinafter referred to as "RAG data") to be input to the generative model along with the prompt from a knowledge database (hereinafter referred to as "knowledge DB"). The collected information items may vary depending on the content expected as output data. Specific examples will be described later.

[0037] The RAG data generation unit 117 converts the RAG data collected by the RAG data collection unit 116 into a configuration for inputting the RAG data together with prompts into a generative model. The RAG data is used, for example, in combination with pre-registered prompt data to improve the accuracy of the output of the generative model. The information items included in the RAG data may be determined according to the configuration of the generative model, or may be determined according to information specified by the user as interview information.

[0038] The knowledge data update unit 118 updates the knowledge DB in response to changes in laws, the occurrence of new cases, the addition of evidence, etc. The update here may include addition, deletion, editing, etc.

[0039] The display control unit 119 controls the display of the display screen generated by the output data generation unit 115, forms (described later), and the like on the screen. The display control unit 119 also displays a screen for receiving various instructions from the user. For example, the display control unit 119 may provide data of a UI (User Interface) screen for display to the user terminal 200.

[0040] The communication control unit 120 controls communication with external devices (e.g., the user terminal 200 and the linkage system 300) and transmits and receives data. The communication control here may be performed according to, for example, the configuration of the closed network and access restrictions.

[0041] The communication unit 130 is a communication interface for communicating with external devices via the network NW. The communication unit 130 may be configured to be compatible with multiple communication standards depending on the configuration of the network NW.

[0042] The storage unit 140 is a storage device for storing programs, data, etc. for executing various control processes and functions within the control unit 110. The storage unit 140 is configured from volatile / non-volatile storage devices such as a RAM (Random Access Memory), a ROM (Read Only Memory), an HDD (Hard Disk Drive), and a flash memory. The storage unit 140 includes a DB for managing data corresponding to the functions described below.

[0043] The business data DB 141 manages various business data related to the support business. For example, it may manage information on children who are support recipients and information on those involved. It may also manage information on supporters such as staff at child consultation centers.

[0044] The generative model DB 142 manages generative models as LLMs used when the data generation process is performed by the data generation unit 113. The generative models are models that have undergone a certain level of learning so that the process according to this embodiment can be executed. Furthermore, learning processes may be performed periodically.

[0045] The prompt DB 143 manages prompt data for configuring prompts used when the data generation unit 113 performs data generation processing. Prompts correspond to commands or instructions used as input to a generative model, and are used differently depending on the content to be output. For example, a prompt format that assumes output data, which will be described later, may be predefined as prompt data. The prompt data registered in the prompt DB 143 may be configured so that it can be input directly to a generative model, or may be adjusted or selected based on instructions from a user.

[0046] The RAG DB 144 is configured as a knowledge DB and manages information that is the source of the RAG data input to the generative model. The RAG DB 144 may be configured to include, for example, the following data. Note that the following configurations and names are examples, and only some of the data may be included, or more data may be included.

[0047] (1) Case database Case records of children who are the target of support at actual child consultation centers are managed. These records may include a wide range of information required for generating reports, such as characteristics of parents, characteristics of children (including psychological test results), home environment, utilization of social resources, and past intervention history.

[0048] (2) Evidence database Information extracted and structured from a wide range of academic papers, specialist books, statistical data, and case studies on risk factors and protective factors for child abuse, the impact of abuse on children and families, the effectiveness and application conditions of various intervention methods, characteristics of perpetrators, child development indicators, knowledge regarding the interpretation of various psychological tests, relevant laws and regulations, ethical guidelines, etc., as well as information specific to the region (local information) including administrative manuals and guidelines from various government agencies and regions, and response manuals.

[0049] (3) Psychological assessment tool information database Overview of various psychological tests (intelligence tests, developmental tests, personality tests, trauma checklists, etc.) and standardized behavioral observation rating scales, including methods of administration and scoring, standard interpretation guidelines, age-specific norms, clinical significance, and information on the psychological characteristics and difficulties that the results may directly or indirectly suggest.

[0050] The form format DB 145 holds a form format when the generated data obtained as a result of the data generation process by the data generation unit 113 is output as form data.

[0051] The output data DB 146 stores, as output data, the results of generation by the data generation unit 113 and form data configured based on the format stored in the form format DB 145. The output data is configured to be output to a user or the like on a UI screen or in a predetermined file format. Note that the output data DB 146 may store the results of generation by the data generation unit 113 in association with prompts and various data used during generation.

[0052] 3 is a block diagram showing an example of the functional configuration of a user terminal 200 according to this embodiment. The user terminal 200 includes a control unit 210, a storage unit 220, a communication unit 230, an operation unit 240, a display unit 250, and an external IF (Interface) 260.

[0053] The control unit 210 controls the operation of the user terminal 200. The control unit 210 is composed of, for example, a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit), and provides various functions by reading and executing various programs and data stored in the storage unit 220.

[0054] The storage unit 220 is a storage device for storing programs, data, etc. for executing various control processes and functions of the control unit 210. The storage unit 220 is configured from volatile / non-volatile storage devices such as a RAM (Random Access Memory), a ROM (Read Only Memory), an HDD (Hard Disk Drive), and a flash memory.

[0055] The communication unit 230 is a communication interface for communicating with external devices via the network NW. The communication unit 230 may be configured to be compatible with a plurality of communication standards depending on the configuration of the network NW.

[0056] The operation unit 240 is an interface for receiving operations from the user of the user terminal 200. The operation unit 240 may be composed of a mouse, a keyboard, etc. The display unit 250 is an interface for displaying various screens and is composed of a display, etc. A touch panel display integrating the operation unit 240 and the display unit 250 may be used. The external IF 260 is an interface for connecting to various devices, and may be, for example, a connection interface with an imaging unit (not shown) for capturing images, sensors for acquiring predetermined information, etc.

[0057] [Data flow] 4 is a schematic diagram for explaining the flow of data in the business support system 1 according to this embodiment. The flow here is implemented in the server device 100, and is shown focusing on parts related to this embodiment. Therefore, the data flow is not limited to this, and further data flows (such as data input by a user) may be added as necessary.

[0058] A supporter such as a staff member of a child consultation center specifies information about the support recipient and information about the current situation (user-specified data 401). The user-specified data 401 may be pre-registered as business data, or may be input individually by the supporter.

[0059] The system prepares knowledge data and prompts based on user-specified data 401. The knowledge data is collected from a knowledge DB using RAG technology from already registered information and prepared as RAG data (knowledge data 402). Furthermore, a prompt to be used is set and selected from a plurality of predefined prompts (prompt 403). The knowledge data 402 may be referenced from the knowledge DB according to the contents of the predefined prompt 403.

[0060] Then, by inputting user-specified data 401, knowledge data 402, and prompt 403 into the generative model 404, generated data 405 is output. In this embodiment, the generated data 405 is information on the analysis of individual cases of child abuse and the basis for the analysis.

[0061] [Example of input / output data] 5A to 5C show examples of input and output data according to this embodiment. In FIG. 5A, input data 500 is a specific example of case information included in user-specified data 401. Here, specific information about abuse and information about the family of the support recipient are shown as examples. The input data 500 may be acquired, for example, by a supporter user inputting character string information via the user terminal 200. The input data 500 is input to the generative model 404. At this time, knowledge data 402 and prompts 403 are selected based on further user-specified data 401 specified by the user, and are input to the generative model 404 together with the input data 500.

[0062] In this example, the following information items may be included as specific information items to be input as input data 500. Note that each information item is not a required input item, and the user may input any item (for example, an item that has already been investigated).

[0063] Case summary - Information on the perpetrator (results of investigations by relevant organizations, etc.) Perpetrator's claims Child psychological test results and medical diagnoses

[0064] Output data 501 shows specific example items of the generated data 405 output from the generative model 404. In this example, information is generated about the risk of abuse in the family and the response of supporters (e.g., child welfare workers) in the case. More specifically, the following items may be included:

[0065] 1. Risks of abuse and strengths (protective factors) in this household: Major risk factors for abuse (listing the main factors that increase the risk of abuse, such as the perpetrator, the child, and the family / upbringing environment), strengths and protective factors (listing factors that reduce the risk of abuse) 2. Specific support policies for each risk of abuse: Abuse risk level, specific support content, support measures, methods, procedures, and points to note for each specific risk factor, measures to ensure child safety, child care policy, intervention policy and methods for parents, collaboration with related organizations (major collaborators and roles, including division of roles) 3. The impact of child abuse and psychological test results: Current impacts (psychological or behavioral impacts directly or indirectly suggested by observed facts, future impacts of concern, and particularly important risks based on professional knowledge), and the child's condition as determined by the results of psychological testing 4. On-site response process and legal risk management: What should be done in the initial response and investigation (major actions such as safety confirmation, safety measures, information gathering, and legal action considerations), legal risks and countermeasures (major expected lawsuits, and avoidance / mitigation measures) 5. Prospects for conclusion, further investigation, and future specific response policy: Prospects for completion (intervention, status of follow-up regarding abuse risks, status of cooperation with related organizations), additional investigation items (each item's "purpose," "specific means," and "basis of necessity"), specific future response policy steps (each step's "content and procedure" and its legal basis, roles and cooperation policies of related organizations, follow-up)

[0066] Fig. 5B shows output data 510 illustrating specific examples of each item in output data 501 in Fig. 5A. Fig. 5C shows an example of report data 520 that is output based on input data 500 shown in Fig. 5A and output data 510 shown in Fig. 5C. Report data 520 may be configured as a report that includes analysis results and the grounds for the results based on case information and a knowledge database.

[0067] [Example of analysis processing configuration] In this embodiment, the analysis process is defined using a prompt for the generation AI. Note that part of the analysis process may be defined and implemented as a process separate from the generation AI. In order to obtain the items shown in the output data 501 in FIG. 5A, the analysis process according to this embodiment may be defined using a prompt or the like in the following configuration. It may also be configured as part of the process for generating RAG data. Note that the following processing steps are only an example, and some or all of them may be omitted, or additional processing steps may be included.

[0068] (Abuse Risk Assessment) Extract information related to parental factors, child factors, environmental factors, support factors, and protective factors from the case information of the person being supported, and compare it with risk factors and protective factors in the evidence database. -Evaluate the contribution of each factor and determine the abuse risk (recurrence risk) level (e.g., category or number) as an individual and overall assessment. - As the basis for the assessment, the identified risk and protective factors are presented in relation to specific descriptions in the case information.

[0069] (Proposed response policy) Generate an outline of an intervention plan based on the results of the abuse risk assessment module, identified risk factors, and child safety needs. Propose response policies such as measures to ensure children's safety (whether temporary protection is necessary, specific plans for in-home support, etc.), direct care and support for children (specialized evaluation and treatment considerations, developmental support, support for building safe relationships, etc.), intervention and support for parents (specific follow-up proposals in response to risk factors), and measures to strengthen collaboration with related organizations, by referring to recommended intervention methods and collaboration models in the evidence database.

[0070] (Child Impact Assessment) -Analyze the child's specific words and actions, emotional state, behavioral characteristics, developmental status, and psychological test results in the case information. · Refer to the evidence database (particularly knowledge from psychiatry, psychology, and behavioral science) to identify psychological influences that are highly likely to be suggested by the observed behaviors. Psychological influences may be, for example, traumatic reactions, attachment problems, difficulty regulating emotions, etc. These may also be presented together with academic variables. Furthermore, describe the identified psychological influences in relation to specific behaviors of the child that support them.

[0071] (Evaluation of expected completion) Conduct a comprehensive assessment of the current case situation, identified risk and protective factors, responsiveness to intervention, and available social resources. This paper presents factors that make termination difficult, positive factors for termination, specific goals and conditions for reaching termination, and the current time horizon, while also referring to findings on prognosis prediction in the evidence database.

[0072] (Proposal for additional research items) Based on the results of the analysis so far, we will identify areas where information is lacking or where further detailed assessment is necessary in order to improve the accuracy of risk assessment and individually optimize support plans. For each survey item, present its purpose, examples of specific survey and assessment methods, and the reasons for its necessity.

[0073] (Preparation of psychological diagnostic findings) Conduct a detailed analysis of the specific words and actions, emotional state, behavioral characteristics, and developmental status of the child in the case information, as well as the results of psychological tests of the child obtained from the case database. By referring to the evidence database and psychological assessment tool information database, the psychological state, developmental challenges, and impact of abuse that are highly likely to be suggested by observed behaviors and test results are identified. Examples of impacts include developmental characteristics, personality traits, trauma responses, attachment issues, emotional regulation difficulties, cognitive distortions, and biases in intellectual functioning. These may also be presented together with academic variables. Furthermore, the identified content is organized in relation to the specific behaviors and test indicators that serve as the basis for the identified content, and described as a "summary of psychological findings," which is important when child welfare officers collaborate with psychological diagnostic experts (such as psychological assessors) or when formulating care plans. For example, this corresponds to the section regarding the impact on children in item 3 of output data 501.

[0074] [Processing flow] 6 is a flowchart showing the overall processing flow for the business according to this embodiment. This processing flow is realized, for example, by the control unit 110 of the server device 100 reading and executing programs and various data stored in the storage unit 140. Here, for simplicity of explanation, the processing entity will be described as the server device 100.

[0075] Before this processing flow starts, various information is registered and configured to be referable in each DB of the server device 100. In addition, the server device 100 is in a state where various information managed in each DB can be added, edited, and deleted.

[0076] In step S601, the server device 100 accepts input of case information related to child abuse from the user. The case information here includes information about the support recipient, such as personal information, and information about the support recipient's current situation. The case information may be used based on the information entered by the user, with reference to information recorded in the business data DB 141, etc. Also, the server device 100 may accept selection of desired analysis content for each item included in the output data 501 of FIG. 5A.

[0077] In step S602, the server device 100 collects knowledge data based on the case information and constructs RAG data. Note that the construction of RAG data based on the knowledge database may be performed at any timing during processing. For example, new RAG data may be constructed by referring to the knowledge database during processing by the generation AI.

[0078] In step S603, the server device 100 determines prompts to be used as inputs to the generative model based on the case information. The prompts may be adjusted using the RAG data configured in step S602.

[0079] In step S604, the server device 100 inputs the various data obtained in the processes of steps S601 to S603 into the generative model to generate information about the analysis content and its basis. The information input here may be adjusted based on the case information received in step S601.

[0080] In step S605, server device 100 outputs the generated data generated in step S604. For example, output data 510 in FIG. 5B may be displayed. Alternatively, server device 100 may perform control so that the generated data is stored in a predetermined storage unit.

[0081] In step S606, the server device 100 determines whether or not it is necessary to output the generated data in a form. For example, an output instruction may be received from the user via a UI screen (not shown), or an instruction to output a form may be received in step S601. If it is determined that output in form is to be performed (step S606: YES), the processing of the server device 100 proceeds to step S607. On the other hand, if it is determined that output in form is not to be performed (step S606: NO), this processing flow ends.

[0082] In step S607, server device 100 generates form data using the generated data generated in step S604 and the form format stored in form format DB 145. The form format used here may be specified by a user or may be selected depending on the configuration of the generated data generated in step S604.

[0083] In step S608, the server device 100 outputs the form data generated in step S607. The output here may be displayed on the screen, stored in a predetermined storage area, or printed out. Then, this processing flow ends.

[0084] As described above, this embodiment makes it possible to improve the work efficiency and quality of supporters who provide support services. In particular, supporters can present a situation analysis of child abuse and the information that supports it. Furthermore, these can be output as a report in a specified format. Furthermore, for example, child welfare officers can gain multifaceted and deep insights into individual cases, and efficiently obtain organized, evidence-based information that is essential for improving the quality of judgment, standardizing and streamlining work, facilitating information sharing within teams, and providing effective support.

[0085] Second Embodiment In a second embodiment of the present invention, support for child abuse will be described as an example of child support services provided by administrative agencies, etc. In particular, for each case of child abuse, psychological analysis of the child and organization and presentation of information that serves as the basis for that analysis are envisioned.

[0086] More specifically, in cases of child abuse, it is extremely important to accurately grasp the impact on the child and determine appropriate psychological care and treatment policies. Psychological assessors (child psychologists) must comprehensively evaluate a wide range of information, including interview records, investigation records, and psychological test results, which requires a high level of expertise and a significant amount of time. Objectivity in judgment, clarification of the basis, and reflection of the latest academic findings are also constantly required. Currently, comprehensive functionality that efficiently integrates this information and supports the creation of structured, high-quality psychological diagnostic findings reports is lacking. Therefore, this embodiment provides a work support function that reduces the workload of the above-mentioned tasks and enables more appropriate support to be provided to support recipients.

[0087] In the following description of this embodiment, the description of the same or similar parts as those in the first embodiment will be omitted, and the description will focus on the parts unique to this embodiment. The system configuration and processing flow may be the same as those in the first embodiment.

[0088] [Knowledge Database] As in the first embodiment, the RAG DB 144 is configured as a knowledge DB. The knowledge DB according to this embodiment may have a configuration that includes, for example, the following data. Note that the configuration and names below are examples, and only a portion of the data may be included, or more data may be included.

[0089] (1) Evidence database This information is extracted from academic papers, specialist books, diagnostic criteria (e.g., DSM (Diagnostic and Statistical Manual of Mental Disorders), ICD (International Statistical Classification of Diseases and Related Health Problems)), treatment guidelines, etc. related to "general crime, abuse perpetration, abuse victims, effects of abuse, psychiatry, psychology, and behavioral science," and structurally or semantically associates specific abuse situations, child characteristics, and behavioral patterns with their associated psychological impacts (e.g., trauma reactions, attachment problems, difficulty regulating emotions, cognitive distortions), impact on development, prognostic predictors, effective intervention methods (psychotherapy, parent training, etc.), and support approaches. (2) Psychological test information database Overview of various psychological tests (e.g., intelligence tests such as the WISC (Wechsler Intelligence Scale for Children), personality tests such as the PF Study, other developmental tests, and trauma-related tests such as the TSCC (Trauma Symptom Checklist for Children)), administration and scoring methods, standard interpretation guidelines, age-specific normative values, interpretation of clinically significant deviations and patterns, and information on the psychological characteristics and difficulties suggested by each indicator.

[0090] [Example of input / output data] 7A to 7D show examples of input / output data according to this embodiment. In FIG. 7A, input data 700 is a specific example of case information included in user-specified data 401. Here, information about an abused child who is a support recipient is shown as an example. The input data 700 may be acquired, for example, by a user who is a supporter inputting character string information via the user terminal 200. The input data 700 is input to the generative model 404. At this time, knowledge data 402 and a prompt 403 are selected based on further user-specified data 401 specified by the user, and are input to the generative model 404 together with the input data 700.

[0091] In this example, the following information items may be included as specific information items about abused children that are input as input data 700. Note that each information item is not a required input item, and the user may input any item (for example, an item that has already been investigated).

[0092] 1. Psychological test results: Various psychological tests such as WISC, PF Study, TSCC, etc. and their results 2. Life history: Developmental history from birth to the present, family structure, and changes in living environment 3. History of contact (history of involvement): The history of contact and support with the child and family by the child welfare agency and related organizations. 4. Abuse situation: type of abuse, frequency, duration, perpetrator, specific episodes 5. Interpersonal relationships: Relationships and communication with parents and children, siblings, friends, teachers, etc. 6. Learning situation: School attendance status, academic performance, learning attitude, strengths and weaknesses 7. Emotional state: emotional expression and stability, self-evaluation, and stress response 8. Behavioral characteristics: characteristic patterns of behavior, habits, and quirks observed in daily life 9. Adaptive behavior: Behavior that responds constructively to environmental and social demands. 10. Maladaptive behavior: Problem behaviors or expressions of psychological difficulties that are inappropriate for the child's age or situation.

[0093] Output data 701 shows specific example items of generated data 405 output from the generative model 404. In this example, information on psychological diagnostic findings is generated for a case. More specifically, the following items may be included:

[0094] 1. Chief complaint and abuse situation: Objective facts such as the details of the report, type, frequency, and duration of abuse 2. Findings of psychological test results: Summary and evaluation of intellectual ability, cognitive characteristics, and psychological state suggested by the test results 3. Children's behavioral characteristics: Characteristic interpersonal behavior and lifestyle attitudes observed through interviews and behavioral observations 4. Children's psychological and cognitive characteristics: Children's emotions, ways of thinking, self-awareness, stress responses, and other internal characteristics 5. Mechanisms and causes of maladaptive behavior: The relationship between the psychological mechanisms behind problem behavior and experiences of abuse 6. Effects of abuse and prognosis: The developmental and psychological impact of abuse and future prospects 7. Strengths: The strengths and positive resources of the child, family, and environment 8. Care plan: A plan for specific psychological support and environmental adjustments based on the diagnostic results 9. Conclusion and treatment plan: Summarizing the diagnostic results, and making recommendations to future treatment and related institutions

[0095] 7B shows input data 710 showing specific examples of each item in the input data 700 in FIG. 7A. In this example, only some of the items shown in the input data 700 in FIG. 7A are shown. The item numbers are just an example and may be arbitrarily adjusted.

[0096] Fig. 7C shows output data 720 showing specific examples of each item of output data 701 in Fig. 7A. Output data 720 shows specific examples of psychological diagnostic findings output based on input data 710 shown in Fig. 7B and the knowledge database. Fig. 7D shows an example of form data 730 output based on input data 710 shown in Fig. 7B and output data 720 shown in Fig. 7C. Form data 730 may be configured as a report including psychological diagnostic results and their grounds based on case information and the knowledge database.

[0097] [Example of psychological diagnosis processing configuration] In this embodiment, the psychological diagnosis process is defined using prompts for the generation AI. Note that part of the psychological diagnosis process may be defined and implemented as a process separate from the generation AI. In order to obtain the items shown in the output data 701 of FIG. 7A, the psychological diagnosis process according to this embodiment may be defined using prompts or the like in the following configuration. It may also be configured as part of the process for generating RAG data. Note that the following processing steps are only an example, and some or all of them may be omitted, or additional processing steps may be included.

[0098] (Input data integration and interpretation) -Integrates data items related to the entered case information, psychological test results, and information on the condition of the child who is the target of support. Each piece of information may be extracted from the information registered in each database as specified by the user (for example, interview and survey records). The psychological test results are compared with standard data by referring to the psychological test information database, and initial interpretation information is generated by extracting indicators with significant differences and characteristic profile patterns. The results of this processing may be used as basic information for the output item "2. Findings of psychological test results" included in the output data 701, for example.

[0099] (state image and behavioral characteristics analysis) The information processed through input data integration and interpretation, especially each item of information about the child's condition (upbringing history, abuse situation, interpersonal relationships, learning situation, emotional state, behavioral characteristics, adaptive and maladaptive behavior) and specific episodes in the interview records are analyzed in detail. -Referring to the evidence database, the specific behaviors observed (e.g., unguarded approaches, unempathetic responses, harm to others, self-harm, avoidance of specific stimuli, etc.) are classified and organized from a psychological and behavioral science perspective, and the psychological and cognitive characteristics that may be behind them are estimated. The results of this processing may be used as basic information for the output items "3. Behavioral characteristics of children" and "4. Psychological and cognitive characteristics of children" included in the output data 701, for example.

[0100] (Mechanisms of Maladaptive Behavior and Causal Inference) - For behaviors identified as "maladaptive behaviors" shown in the information on the child's condition, information on the "abuse situation," "upbringing history," "emotional state," "psychological and cognitive characteristics," and interpretation information on psychological test results will be integrated. By comparing findings from the evidence database on the effects of abuse, developmental psychology, attachment theory, behavioral theory, and the like, the mechanisms by which the maladaptive behavior is acquired and maintained, as well as its underlying causes, are inferred and described from multiple perspectives. This may serve as basic information for output item "5. Mechanisms and causes of maladaptive behavior" included in output data 701, for example. Examples of the mechanisms inferred include inappropriate learning from caregivers, acting out as a traumatic response, immature communication skills, and cognitive distortions. Furthermore, examples of the underlying causes inferred include the prevention of stable attachment formation, lack of empathic interaction, and repression due to fear.

[0101] (Abuse impact assessment and prognosis prediction) -Integrate research findings on the type, duration, frequency, and severity of abuse (based on information on the child's state profile), the child's developmental stage, current psychological and behavioral characteristics (results of the state profile and behavioral characteristics analysis), psychological test findings, and the effects of abuse in the evidence database. Identify and list multiple specific effects of the abuse that are currently occurring. Specific effects of the abuse may include, for example, specific traumatic symptoms, distorted interpersonal patterns, difficulty regulating emotions, and distorted self-perception. - Predict, based on evidence, the potential impacts of not implementing appropriate interventions in the future, such as chronic mental illness, delinquency, poor academic performance, and social isolation. The above various information is integrated to generate the output item “6. Impact and prognosis of abuse” included in the output data 701.

[0102] (Strength Identification) From case information, information on the child's condition (especially "adaptive behavior"), and psychological test results, the child's own positive aspects, abilities, interests, and ability to cope with difficult situations (resilience factors) as well as protective factors in the family and surrounding environment are extracted, identified, and listed. Protective factors here may include, for example, supportive relatives, school teachers, and the child's own intellectual curiosity. The results of this processing may be used as basic information for output item "7. Strengths" included in output data 701, for example.

[0103] (Care plan and treatment plan generation) Comprehensively organize the effects of abuse, mechanisms of maladaptive behavior, prognosis, and strengths assessed and identified through each of the above processes. · Reference information on effective or suitable psychological treatments, support programs, and environmental adjustment strategies in evidence databases. Psychological value therapies include, for example, trauma-focused cognitive behavioral therapy, play therapy, and attachment repair programs. Support programs include, for example, parent training and SST (Social Skills Training). - Taking into consideration the child's age, developmental stage, personality characteristics, trauma status, available resources, family situation, etc., the system presents or prioritizes the most effective and feasible specific care plans. The care plans presented here may include, for example, the goals, type, frequency, and policy of psychological treatment, suggestions for environmental adjustments, and collaboration measures with related organizations. The results of this processing may be used as the basic information for output item "8. Care Plan" included in the output data 701, for example. All analysis results are combined to compile a comprehensive conclusion for the case and specific treatment proposals. Proposals here may include, for example, continuing home guidance and introducing specialized psychotherapy, providing intensive care under temporary custody, or providing psychological support in conjunction with foster care placement. The results of this processing may be used as the basic information for the output item "9. Conclusions and Treatment Proposals" included in the output data 701.

[0104] (Provide evidence) For each item of the psychological diagnostic findings generated by each of the above processes, the main grounds for the judgment, evaluation, inference, or proposal are output in clear association with the relevant part of the input case information, specific items of the child's condition, findings from the referenced evidence database (e.g., specific research results or theories), specific indicators of the psychological test results, etc.

[0105] As described above, this embodiment makes it possible to improve the work efficiency and quality of supporters who provide support services. In particular, supporters can present a psychological analysis of a child affected by child abuse and the information that supports it. Furthermore, supporters, such as professionals at child consultation centers, can efficiently organize and analyze complex information and quickly create evidence-based, objective, and high-quality psychological diagnostic findings. As a result, it is expected that this will contribute to the determination of appropriate support and treatment policies that contribute to the best interests of children.

[0106] Third Embodiment In a third embodiment, which is one embodiment of the present invention, support for child abuse will be described as an example of child support services provided by administrative agencies, etc. In particular, for each case of child abuse, analysis of litigation and organization and presentation of information that serves as the basis for that analysis are envisioned.

[0107] More specifically, in cases where child abuse is suspected, child consultation center staff (e.g., child welfare officers) must prioritize ensuring the safety of the child while quickly taking appropriate legal action. This includes accurately identifying the abuse situation, understanding relevant laws and regulations, assessing potential legal risks, planning specific response procedures, and collaborating with relevant organizations. However, these tasks are highly specialized and complex, requiring significant time and effort. In particular, they must consider the risk of lawsuits from parents, make decisions based on objective evidence, and properly record the process. However, it is not easy for on-site staff to consistently and comprehensively and efficiently organize and analyze this information and formulate practical response plans. Therefore, this embodiment provides a work support function that reduces the workload of the above-mentioned tasks and enables more appropriate support to be provided to support recipients.

[0108] In the following description of this embodiment, the description of the same or similar parts as those in the first embodiment will be omitted, and the description will focus on the parts unique to this embodiment. The system configuration and processing flow may be the same as those in the first embodiment.

[0109] [Knowledge Database] As in the first embodiment, the RAG DB 144 is configured as a knowledge DB. The knowledge DB according to this embodiment may have a configuration that includes, for example, the following data. Note that the configuration and names below are examples, and only a portion of the data may be included, or more data may be included.

[0110] (1) Legal and Guidance Database: Provisions of relevant laws and regulations related to child welfare, such as the Child Welfare Act, Child Abuse Prevention Act, Criminal Code, Civil Code, Administrative Litigation Act, and State Compensation Act, as well as related administrative manuals, guidelines for responding to sexual abuse at child consultation centers, other child abuse-related guidelines, child abuse response guides, child consultation center operating guidelines, and various notifications related to child abuse. (2) Database of legal precedents and past cases Past court cases related to child abuse (especially those in which the intervention of child consultation centers was contested), and past cases of responses accumulated within child consultation centers (summary of the case, issues at stake, content of intervention, intervention methods, results, legal issues, etc.). (3) Abuse Risk and Impact Database Evidence based on academic papers and specialist books on risk factors and protective factors for various types of abuse, as well as the psychological, physical and developmental impact on children. (4) Intervention and collaboration method database Information on effective intervention strategies (motivational interviewing, parent training, etc.), how to collaborate with relevant organizations, and various social resources.

[0111] [Example of input / output data] Examples of input and output data according to this embodiment are shown below. The input data according to this embodiment may include the following information items. ·Case summary ·Investigation records, etc. Specific text information and structured data related to the case, such as the contents of the notification, the contents of the assessment sheet, records of interviews with the relevant parties (child, guardian, notifier, school officials, etc.), records of observations of the child's behavior, psychological test results (if any), and records of information provided by relevant institutions. ·Perpetrator information Detailed information about the parent or cohabitant alleged to have committed the abuse (basic information, life history, work history, mental state, awareness of the abuse, attitude during interviews, past history of consultations and interventions, risk factors such as violence and addiction, etc.).

[0112] The output data according to this embodiment may include the following items: 1.Assessment of the abusive situation 2. Specific steps in on-site response and legal risks 3. Future response policy, including additional investigation

[0113] A practical response report based on legal grounds, including the above items and taking into consideration litigation responses, may be output as a report.

[0114] [Example of analysis processing configuration] In this embodiment, the analysis process is defined using a prompt for the generation AI. Note that part of the analysis process may be defined and implemented as a process separate from the generation AI. To achieve the above items, the analysis process according to this embodiment may be defined using prompts or the like in the following configuration. Note that the following processing steps are only an example, and some or all of them may be omitted, or additional processing steps may be included.

[0115] (Input information analysis) From the various information entered, the system extracts and analyzes the key information required to generate a report, such as the circumstances of the abuse, characteristics of those involved, risk factors, strength factors, etc. Each piece of information may be extracted from the information registered in each database as specified by the user.

[0116] (Abuse Situation Assessment) Based on the analyzed information and knowledge database, the type, frequency, severity, and special notes (such as disclosure status of abuse) of abuse are evaluated, the underlying recorded facts are identified, and the above information item "1. Evaluation of the abuse situation" is generated.

[0117] (On-site response flow and legal risk analysis) Based on the analyzed information and knowledge base, specific initial response procedures for each case after a report is received, specific investigation content and points to note, and items to consider when formulating an assistance plan are proposed. Specific initial response procedures may include, for example, confirming the child's safety, face-to-face meetings, after-hours and holiday response, on-site investigations, and determining whether temporary protection is necessary, as well as the requirements and procedures. Specific investigation content may include, for example, understanding the child's physical and psychological condition, understanding their living environment and family relationships, promptness, explaining and interviewing the parents, and collecting evidence. Items to consider when formulating an assistance plan may include, for example, the perspective of a comprehensive diagnosis, the content of the assistance policy, and items to be confirmed at individual case review meetings. Analyze and present the legal measures and their rationale that may be envisaged in proceeding with the above measures, as well as the related legal risks (such as lawsuits against parents for revocation, lawsuits seeking compensation from the state, etc.) and how to avoid or mitigate them, and generate the information item above, "2. Specific steps and legal risks in on-site responses."

[0118] (Future response policy and additional investigation proposals) Based on the analyzed information, the results of the abuse situation assessment and on-site response flow, the legal risk analysis, and the knowledge database, specific future response steps will be proposed that take into consideration the safety and best interests of the child. Specific future response steps could include, for example, the content and procedures of each step, the legal basis, the division of roles and specific collaboration methods of related organizations, matters to be considered, confirmation of the child's wishes, explanations to and consensus building with parents, and key points for recording. Identify matters that are difficult to judge based on current information alone, and additional research items that are considered essential for more appropriate policy decisions, and clearly state the "purpose of the research," "specific methods," and "reason for necessity" for each item. -Integrate each piece of information and generate the information item above, "3. Future response policy, including additional investigation."

[0119] As described above, this embodiment makes it possible to improve the work efficiency and quality of supporters who provide support services. In particular, supporters such as child consultation center staff can quickly plan and implement more specific and legally appropriate response policies that are objectively based on the results of AI's integration and analysis of complex case information and expert knowledge. As a result, it is expected to contribute to improving the quality of work, standardizing judgment, strengthening risk management, and protecting the best interests of children.

[0120] <Other embodiments> In the above embodiments, child abuse has been described as an example of a support service, but the present invention is not limited to this. The functions of the present invention can be applied to various fields and services in terms of analysis and the presentation of information that serves as the basis for the analysis. For example, the functions may be applied to analysis of child injuries and accidents, maternal and child health, domestic violence (DV), sexual violence, delinquency and crime, developmental disabilities, elderly welfare, welfare for people with disabilities, delinquency and crime investigations, harassment, and the like. Furthermore, the present invention is not limited to government services, and may also be applied to services used by private companies or individuals.

[0121] Furthermore, the above-described embodiments are not mutually exclusive and may be configured in appropriate combinations. Therefore, the DB configuration, generative model, and prompt corresponding to the functions described in each embodiment may be configured in one server device and provided based on a user's instruction. Alternatively, the functions described in each embodiment may be configured in separate server devices, and the user may switch the server device to access depending on the function to be used.

[0122] In addition, in the present invention, a program or application for realizing the functions of one or more of the above-mentioned embodiments can be supplied to a system or device using a network or a storage medium, etc., and one or more processors in the computer of the system or device can read and execute the program.

[0123] Alternatively, it may be realized by a circuit that realizes one or more functions (for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array)).

[0124] In this specification, for convenience, expressions such as "first" and "second" are used. These are not intended to be interpreted restrictively as referring to a specific configuration, and may be interpreted as appropriate depending on the components and aspects.

[0125] Although various embodiments have been described above with reference to the drawings, it goes without saying that the present disclosure is not limited to these examples. It is clear to those skilled in the art that various modifications, alterations, substitutions, additions, deletions, and equivalents may be made within the scope of the claims, and it is understood that these also fall within the technical scope of the present disclosure. Furthermore, the components of the various embodiments described above may be combined in any manner without departing from the spirit of the invention.

[0126] As such, the present invention is not limited to the above-described embodiments, and the present invention also contemplates the mutual combination of the various components of the embodiments, as well as modifications and applications by those skilled in the art based on the description in the specification and well-known techniques, and these modifications and applications are included in the scope of protection sought.

[0127] As described above, the present specification discloses the following:

[0128] (Technology 1) A business support system that analyzes cases in support work, a reception unit that receives case information including psychological test results of the support recipient and information indicating the situation of the support recipient; a collection unit that collects information for analysis from a predetermined knowledge database; a generation unit that generates, as an analysis result, information including an evaluation of the situation of the support recipient and the basis for the evaluation, by using the case information and the information collected by the collection unit as inputs of a large-scale language model; an output unit that outputs the generated analysis result; A business support system with the above.

[0129] (Technology 2) The support services are support related to abuse of the support recipients, The predetermined knowledge database includes: a first database containing information on risk factors for abuse, protective factors, the effects of abuse, intervention methods, knowledge on perpetrator characteristics, relevant psychiatric, psychological, and behavioral science knowledge, and / or region-specific information; a second database containing information relating to psychological test interpretations; The business support system according to technology 1 is configured to include at least one of the above.

[0130] (Technology 3) The generation unit an abuse risk assessment that assesses the level of abuse risk in the case as indicated by the case information and the basis for that abuse risk; A response policy proposal that generates a response policy proposal based on the results of the abuse risk assessment, including measures to ensure the safety of children, care policies for children, intervention policies for parents, and policies for collaboration with related organizations; A psychological assessment to evaluate the psychological impact of abuse and the current psychological state of the person receiving support, based on the results of psychological testing and behavioral observations of the person receiving support, and the basis for such findings; A closure likelihood assessment that assesses the case information's outlook for closure, the factors that may challenge closure, and the goals and conditions for closure; and Proposal of additional investigation items, proposing the items, purposes, and methods for which additional information collection or assessment is recommended in the analysis of the case information; The business support system according to technology 2 generates at least one of the above information as the analysis result.

[0131] (Technology 4) The business support system described in technology 3, wherein the abuse risk assessment includes individual assessments of parental factors, child factors, environmental factors, support factors, and protective factors, as well as a comprehensive assessment that integrates each individual assessment.

[0132] (Technology 5) The business support system described in Technology 3 or Technology 4, wherein the response policy proposal includes a follow-up proposal corresponding to the risk factors of abuse risk identified by the abuse risk assessment.

[0133] (Technology 6) The business support system according to any one of Technology 3 to Technology 5, wherein the psychological state assessment derives information on at least one of the intellectual function, developmental characteristics, personality characteristics, and trauma response of the support recipient based on the psychological test results.

[0134] (Technology 7) The support services are support related to abuse of the support recipients, The predetermined knowledge database includes: a third database containing information on the effects of abuse, psychological treatments, psychiatric findings, psychological findings, behavioral findings, and / or region-specific information; a fourth database containing information relating to the interpretation of psychological tests; The business support system according to technology 1 is configured to include at least one of the above.

[0135] (Technology 8) The generation unit The main complaint and circumstances of abuse in the case as indicated in the case information; Findings directly suggested by the results of the psychological test; The psychology, cognitive characteristics, and behavioral characteristics of the person receiving support; The mechanism and probable causes of the maladaptive behavior of the person being supported; The current and potential impacts and prognosis of the abuse in the case identified in said case information; The strengths of the recipient and their family, A care plan for the person and their family, including potentially effective psychological treatments; and Conclusions and treatment proposals for the above case information; The business support system according to technology 7 generates at least one of the items and the basis for deriving each item as the analysis result.

[0136] (Technology 9) The business support system described in Technology 8, wherein the generation unit makes inferences regarding the mechanism and presumed cause of the maladaptive behavior of the support recipient by associating at least one of the information on the abuse situation, upbringing, emotional state, psychological characteristics, and cognitive characteristics contained in the case information with the effects of abuse and behavioral science findings in the third database.

[0137] (Technology 10) The business support system described in Technology 8 or Technology 9, wherein the generation unit selects, for the care plan, from among the psychological treatment methods contained in the third database, a psychological treatment method that is suitable for the age and developmental stage of the person to be supported and the characteristics of abuse, based on at least one of the effects of abuse, psychological characteristics, cognitive characteristics, behavioral characteristics, and strengths.

[0138] (Technology 11) The business support system according to any one of techniques 1 to 10, wherein the output unit outputs the analysis results as a report configured in a predetermined format.

[0139] (Technology 12) A business support system for support work for support recipients, a reception unit that receives case information including information indicating the status of the support recipient; a collection unit that collects information related to a predetermined field from a predetermined knowledge database; a generation unit that generates, as an analysis result, information including an assessment of the situation of the support recipient and a response plan based on information in the predetermined field for the assessment, by using the case information and the information collected by the collection unit as inputs to a large-scale language model; an output unit that outputs the generated analysis results as a report in a predetermined format; A business support system with the above.

[0140] (Technology 13) The support services are support related to abuse of the support recipients, The predetermined knowledge database includes: The business support system described in Technology 12 is configured to include a fifth database containing information on at least one of child welfare-related laws and regulations, administrative manuals, past precedents and response cases, risk factors for abuse, the effects of abuse, and expert knowledge regarding effective intervention strategies.

[0141] (Technology 14) The generation unit An abuse situation assessment to assess the abuse situation in the case indicated by the case information; A risk assessment assessing the on-site response process, related legal action basis, and potential legal risks and avoidance or mitigation measures in the case identified in the case information; and Proposals for future responses to the cases indicated by the case information; The business support system according to Technology 12 or Technology 13 generates at least one of the above as the analysis result.

[0142] (Technology 15) The business support system of claim 14, wherein the generation unit generates, as an on-site response flow in the risk assessment, initial response procedures for ensuring the safety of the support recipient, at least one of the following: the necessity and method of meeting in person with the support recipient, consideration of response outside of business hours and on holidays, procedures and legal basis for on-site inspections, and requirements and procedures for temporary protection.

[0143] (Technology 16) A control method for a business support system that analyzes cases in support work, a receiving step of receiving case information including the results of a psychological test on the support recipient and information indicating the situation of the support recipient; a collection step of collecting information for analysis from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an evaluation of the situation of the support recipient and the basis for the evaluation, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis result; A control method for a business support system having the above.

[0144] (Technology 17) A method for controlling a business support system for support work for a support recipient, comprising: a receiving step of receiving case information including information indicating the status of the support recipient; a collection step of collecting information related to a predetermined field from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an assessment of the situation of the support recipient and a response plan based on information in the predetermined field for the assessment, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis results as a report configured in a predetermined format; A control method for a business support system having the above.

[0145] (Technology 18) On the computer, a receiving step of receiving case information including the results of a psychological test on the support recipient and information indicating the situation of the support recipient; a collection step of collecting information for analysis from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an evaluation of the situation of the support recipient and the basis for the evaluation, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis result; A program to execute.

[0146] (Technology 19) On the computer, a receiving step of receiving case information including information indicating the status of the support recipient; a collection step of collecting information related to a predetermined field from a predetermined knowledge database; a generation step of generating, as an analysis result, information including an assessment of the situation of the support recipient and a response plan based on information in the predetermined field for the assessment, by using the case information and the information collected in the collection step as inputs to a large-scale language model; an output step of outputting the generated analysis results as a report configured in a predetermined format; A program to execute. [Industrial Applicability]

[0147] The present invention is useful as a device, system, and method for, for example, improving work efficiency, information sharing, and the quality of work performed by support staff at the support site in organizations and institutions that provide various support services. [Explanation of symbols]

[0148] 1. Business support system 100...Server device 110...Control unit 111...Data Collection Department 112...Data Management Department 113...Data generation unit 114...Prompt control unit 115...Output data generation unit 116...RAG Data Collection Unit 117...RAG data generation unit 118...Knowledge Data Update Department 119...Display control unit 120...Communication control unit 130…Communications Department 140...Storage section 141...Business data DB 142...Generative model DB 143...Prompt DB 144...DB for RAG 145...Generated data DB 146...Output data DB 200...User terminal 210...Control unit 220...Storage section 230…Communications Department 240...Operation unit 250...Display section 260…External IF 300... Collaboration system NW...Network

Claims

1. A business support system that analyzes cases in support work, a reception unit that receives case information including psychological test results of the support recipient and information indicating the situation of the support recipient; a collection unit that collects information for analysis from a predetermined knowledge database by Retrieval-Augmented Generation (RAG) based on at least one of the psychological test results of the support recipient and information indicating the situation of the support recipient, which are included in the case information; a generation unit that generates, as an analysis result, information that associates an evaluation of the situation of the support recipient with a basis for the evaluation, by using the case information, the information collected by the collection unit, and a prompt as input to a large-scale language model; an output unit that outputs the generated analysis result; and The generation unit selects the prompt to be input to the large-scale language model from a plurality of prompts that are predefined corresponding to a plurality of analytical processes using information contained in the case information, based on at least one of the psychological test results of the support recipient and information indicating the situation of the support recipient, which are contained in the case information.

2. The support services are support related to abuse of the support recipients, The predetermined knowledge database includes: a first database containing at least any of information on risk factors for abuse, protective factors, effects of abuse, intervention methods, perpetrator characteristics, psychiatric, psychological, behavioral science, and area-specific information; a second database containing information related to psychological test interpretations; The business support system according to claim 1 , comprising at least one of the following:

3. The generation unit an abuse risk assessment that assesses the level of abuse risk in the case as indicated by the case information and the basis for that abuse risk; A response policy proposal that generates a response policy proposal based on the results of the abuse risk assessment, including measures to ensure the safety of children, care policies for children, intervention policies for parents, and policies for collaboration with related organizations; A psychological assessment to evaluate the psychological impact of abuse and the current psychological state of the person receiving support, based on the results of psychological testing and behavioral observations of the person receiving support, and the basis for such findings; A closure likelihood assessment that assesses the case information's outlook for closure, the factors that may challenge closure, and the goals and conditions for closure; and Proposal of additional investigation items, proposing the items, purposes, and methods for which additional information collection or assessment is recommended in the analysis of the case information; The business support system according to claim 2 , wherein at least one of the following information is generated as the analysis result:

4. The business support system according to claim 3 , wherein the abuse risk assessment includes individual assessments of parental factors, child factors, environmental factors, support factors, and protective factors, and a comprehensive assessment that integrates each of the individual assessments.

5. The business support system according to claim 3 , wherein the response policy proposal includes a follow-up proposal corresponding to risk factors of abuse risk identified by the abuse risk assessment.

6. 4. The business support system according to claim 3, wherein the psychological state assessment derives information on at least one of the intellectual function, developmental characteristics, personality characteristics, and traumatic response of the support recipient based on the results of the psychological test.

7. The support services are support related to abuse of the support recipients, The predetermined knowledge database includes: a third database containing information on the effects of abuse, psychological treatments, psychiatric, psychological, behavioral science, and / or community-specific information; a fourth database containing information related to psychological test interpretations; The business support system according to claim 1 , comprising at least one of the following:

8. The generation unit The main complaint and circumstances of abuse in the case as indicated in the case information; Findings directly suggested by the results of the psychological test; The psychology, cognitive characteristics, and behavioral characteristics of the person receiving support; The mechanism and probable causes of the maladaptive behavior of the person being supported; The current and potential impacts and prognosis of the abuse in the case identified in said case information; The strengths of the recipient and their family, A care plan for the person and their family, including potentially effective psychological treatments; and Conclusions and treatment proposals for the above case information; 8. The business support system according to claim 7, wherein at least one of the items and the basis for deriving each item is generated as the analysis result.

9. The business support system of claim 8, wherein the generation unit makes inferences regarding the mechanisms and presumed causes of the maladaptive behavior of the support recipient by associating at least one of information on the abuse situation, upbringing, emotional state, psychological characteristics, and cognitive characteristics contained in the case information with the effects of abuse and behavioral science findings in the third database.

10. The business support system described in claim 8, wherein the generation unit selects, for the care plan, from among the psychological treatment methods contained in the third database, a psychological treatment method that is suitable for the age and developmental stage of the person being supported and the characteristics of abuse, based on at least one of the effects of abuse, psychological characteristics, cognitive characteristics, behavioral characteristics, and strengths.

11. The business support system according to claim 1 , wherein the output unit outputs the analysis results as a report in a predetermined format.

12. A business support system for support work for support recipients, a reception unit that receives case information including information indicating the status of the support recipient; a collection unit that collects information on a predetermined field from a predetermined knowledge database by Retrieval-Augmented Generation (RAG) based on information indicating the situation of the support recipient included in the case information; a generation unit that generates, as an analysis result, information that associates an assessment of the situation of the support recipient with a response plan based on information related to the predetermined field for the assessment, by using the case information, the information collected by the collection unit, and a prompt as input for a large-scale language model; an output unit that outputs the generated analysis results as a report in a predetermined format; and The generation unit selects the prompt to be input to the large-scale language model from a plurality of prompts that are pre-defined corresponding to a plurality of analytical processes using information contained in the case information, based on information that indicates the situation of the person being supported, which is contained in the case information.

13. The support services are support related to abuse of the support recipients, The predetermined knowledge database includes: The business support system described in claim 12, further comprising a fifth database containing at least one of information regarding child welfare-related laws and regulations, information regarding administrative manuals, information regarding past court decisions and case studies, knowledge regarding risk factors for abuse, knowledge regarding the effects of abuse, and knowledge regarding effective intervention strategies.

14. The generation unit An abuse situation assessment to assess the abuse situation in the case indicated by the case information; A risk assessment assessing the on-site response process, related legal action basis, and potential legal risks and avoidance or mitigation measures in the case identified in the case information; and Proposals for future responses to the cases indicated by the case information; The business support system according to claim 12 , wherein at least one of the following is generated as the analysis result:

15. The business support system of claim 14, wherein the generation unit generates, as an on-site response flow in the risk assessment, initial response procedures for ensuring the safety of the support recipient, at least one of the following: the necessity and method of meeting in person with the support recipient, consideration of response outside of business hours and on holidays, procedures and legal basis for on-site inspections, and requirements and procedures for temporary protection.

16. A control method for a business support system that analyzes cases in support work, a receiving step of receiving case information including the results of a psychological test on the support recipient and information indicating the situation of the support recipient; a collection step of collecting information for analysis from a predetermined knowledge database by RAG (Retrieval-Augmented Generation) based on at least one of the psychological test results of the support recipient and information indicating the situation of the support recipient, which are included in the case information; a generation step of generating, as an analysis result, information that associates an evaluation of the situation of the support recipient with a basis for the evaluation, by using the case information, the information collected in the collection step, and a prompt as input to a large-scale language model; an output step of outputting the generated analysis result; and A control method for a business support system, wherein in the generation process, the prompt to be input to the large-scale language model is selected from a plurality of prompts predefined in correspondence with a plurality of analytical processes using information contained in the case information, based on at least one of the psychological test results of the support recipient and information indicating the situation of the support recipient, which are contained in the case information.

17. A method for controlling a business support system for support work for a support recipient, comprising: a receiving step of receiving case information including information indicating the status of the support recipient; a collection step of collecting information on a predetermined field from a predetermined knowledge database by Retrieval-Augmented Generation (RAG) based on information indicating the situation of the support recipient included in the case information; a generation step of generating, as an analysis result, information that associates an assessment of the situation of the support recipient with a response plan based on information related to the predetermined field by using the case information, the information collected in the collection step, and a prompt as input to a large-scale language model; an output step of outputting the generated analysis results as a report configured in a predetermined format; and A control method for a business support system, in which, in the generation process, the prompt to be input into the large-scale language model is selected from a plurality of prompts pre-defined corresponding to a plurality of analytical processes using information contained in the case information, based on information indicating the situation of the person being supported, which is contained in the case information.

18. On the computer, a receiving step of receiving case information including the results of a psychological test on the support recipient and information indicating the situation of the support recipient; a collection step of collecting information for analysis from a predetermined knowledge database by RAG (Retrieval-Augmented Generation) based on at least one of the psychological test results of the support recipient and information indicating the situation of the support recipient, which are included in the case information; a generation step of generating, as an analysis result, information that associates an evaluation of the situation of the support recipient with the basis for the evaluation, by using the case information, the information collected in the collection step, and prompts as inputs to a large-scale language model; an output step of outputting the generated analysis result; Execute A program in which, in the generation process, the prompt to be input into the large-scale language model is selected from a plurality of pre-defined prompts corresponding to a plurality of analytical processes using information contained in the case information, based on at least one of the psychological test results of the support recipient and information indicating the situation of the support recipient, which are contained in the case information.

19. On the computer, a receiving step of receiving case information including information indicating the status of the support recipient; a collection step of collecting information on a predetermined field from a predetermined knowledge database by Retrieval-Augmented Generation (RAG) based on information indicating the situation of the support recipient included in the case information; a generation step of generating, as an analysis result, information that associates an assessment of the situation of the support recipient with a response plan based on information related to the predetermined field by using the case information, the information collected in the collection step, and a prompt as input to a large-scale language model; an output step of outputting the generated analysis results as a report configured in a predetermined format; Execute A program in which, in the generation process, the prompt to be input into the large-scale language model is selected from a plurality of prompts pre-defined corresponding to a plurality of analytical processes using information contained in the case information, based on information indicating the situation of the person being supported, which is contained in the case information.

Images