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 for providing response plans for interviews in support work has a reception unit that receives information about the person being supported and information about interviews related to support for the person being supported, a collection unit that collects information from a specified database based on the information received by the reception unit, a generation unit that generates response plans for the interviews by using the information received by the reception unit and the information collected by the collection unit as input for a large-scale language model, and an output unit that outputs the generated response plans for the interviews.

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, systems for rapid information sharing between organizations have been used in community support services. Community support services must take into account a wide range of targets and situations, such as child support and 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, in community support services, the work involved is diverse and involves a high workload, including communication between the recipient and the provider, collaboration and information sharing within and outside the support organization, and careful consideration of the appropriate timing and content of support. Communication between the recipient and the provider includes interviews with the relevant parties. In these situations, the supporter's response can lead to changes (improvement or deterioration) in the situation.

[0004] More specifically, for example, interviews with perpetrators (parents, etc.) in cases of child abuse are extremely important for verifying the facts, understanding the underlying factors of the abuse, motivating them to improve, and building a cooperative relationship to ensure the safety of children. However, perpetrators often respond by denying, resisting, or shifting the blame, making interviews extremely difficult. Conducting effective interviews requires advanced communication skills and strategic preparation tailored to the characteristics and circumstances of each perpetrator, but it is not always possible for personnel to devise and execute optimal interview plans.

[0005] For example, Patent Document 1 discloses a configuration for predicting the development of a conversation in a messaging app using an automatic language processing model, detecting urgency, and collaborating with government agencies, welfare organizations, and the like. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 2025-045816 Summary of the Invention [Problem to be solved by the invention]

[0007] 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.

[0008] 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]

[0009] In order to solve the above problems, one aspect of the present invention has the following configuration: That is, a business support system for providing a response plan for an interview in a support business, comprising: a reception unit that receives information about the support recipient and information about an interview related to support for the support recipient; a collection unit that collects information from a predetermined database based on the information received by the reception unit; a generation unit that generates a response plan for the interview by using the information received by the reception unit and the information collected by the collection unit as input for a large-scale language model; an output unit that outputs the generated response plan for the interview; It has.

[0010] Another aspect of the present invention has the following configuration: That is, a control method of a business support system for providing a response plan for an interview in a support business, comprising: a receiving step of receiving information about the support recipient and information about an interview related to support for the support recipient; a collection step of collecting information from a predetermined database based on the information received in the receiving step; a generation step of generating a response plan for the interview by using the information received in the reception step and the information collected in the collection step as inputs for a large-scale language model; an output step of outputting the generated response plan for the interview; It has.

[0011] Another aspect of the present invention has the following configuration: a program comprising: Computer, a reception unit that receives information on support recipients in support work and information on interviews related to support for said support recipients; a collection unit that collects information from a predetermined database based on the information received by the reception unit; a generation unit that generates a response plan for the interview by using the information received by the reception unit and the information collected by the collection unit as inputs for a large-scale language model; an output unit that outputs the generated response plan for the interview; Run it as: [Effects of the Invention]

[0012] 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]

[0013] [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 showing an example of output data of a generative model according to the first embodiment of the present invention; [Figure 6A] FIG. 1 is an example showing a display example of a UI screen according to the first embodiment of the present invention; [Figure 6B] FIG. 1 is an example showing a display example of a UI screen according to the first embodiment of the present invention; [Figure 7] 1 is a flowchart of a process according to a first embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0014] 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.

[0015] 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.

[0016] 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.

[0017] In the following embodiments, the term "interview" is not limited to communication that assumes one-to-one dialogue, but may also assume one-to-many dialogue. The form of the interview is not particularly limited, and may include face-to-face, online, or telephone. While certain authority related to laws and regulations may be required to conduct the interview or respond to the results, this is not particularly limited.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] First Embodiment [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.

[0022] 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. 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] The control unit 110 is responsible for controlling 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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 information about the interview specified by the user (hereinafter referred to as "interview information"). The information items included in the interview information are not particularly limited, but may include, for example, the purpose of the interview, the interviewee (the supporter himself or herself and related parties), the interviewer, the interview style, and the interview history.

[0034] 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.

[0035] The knowledge data update unit 118 updates the knowledge DB in response to legal amendments, the occurrence of new cases, etc. In this embodiment, the knowledge data update unit 118 may present a response plan for an interview as generated data, and then update the knowledge DB with the interview results of an interview conducted based on the response plan as a new case. The update here may include addition, deletion, editing, etc.

[0036] The display control unit 119 controls the display of the display screen and generated data generated by the output data generation unit 115 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] The business data DB 141 manages various business data related to support services. 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.

[0041] The generative model DB 142 manages generative models as LLMs used when the data generation unit 113 performs data generation processing. The generative models are models that have undergone a certain level of training so that the processing according to this embodiment can be executed. Furthermore, training processing may be performed periodically.

[0042] The prompt DB 143 manages prompt data for constructing 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 anticipates output data corresponding to a proposed response to an interview 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 depending on interview information specified by the user.

[0043] The RAG DB 144 is configured as a knowledge DB and manages the information that is the source of the RAG data input to the generative model. The RAG DB 144 may have a more detailed configuration so as to include, for example, the following data. Note that the following configuration is an example, and only a portion of the data may be included, or more data may be included.

[0044] (1) Current Case Database Users enter information about the parties involved in the case (including child victims, perpetrators, etc.) in the case currently being handled, past interview records, relevant legal proceedings, etc. This may include at least the following information: - Attributes of the people involved in the case (age, gender, occupation, family structure, personality, etc.) - Possible background factors of abuse (mental illness, substance abuse, history of abuse, stress, etc.) - Past interview patterns, emotional responses, and levels of denial and acceptance - Current legal status (temporary protection, measures in place, pending litigation, etc.)

[0045] (2) Legal and Guidance Database Provisions of the Child Welfare Act, Child Abuse Prevention Act, child welfare-related laws, criminal law, civil law, administrative litigation law, state compensation law, and other related laws and regulations, 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 management guidelines, and various notifications related to child abuse.

[0046] (3) Database of past cases Case information such as records of responses (summaries of interview records, communication strategies used, responses of perpetrators, subsequent behavioral changes, etc.) to parties involved in past child abuse cases handled by child consultation centers (including victimized children and perpetrators) and related legal cases.

[0047] (4) Interpersonal Strategy Database Effective interview techniques, questioning methods, persuasion methods, motivational interview phrase examples, response strategies, response policies, support policies, etc., according to the psychological characteristics and reaction patterns (e.g., denial, aggression, avoidance, etc.) of those involved in the case (including child victims and abusers, etc.)

[0048] The generated data DB 145 holds the generated data obtained as a result of the data generation process by the data generation unit 113. The generated data DB 145 may hold data (including prompt data and RAG data) used as input during the data processing in association with the generation result.

[0049] The output data DB 146 holds output data configured based on the processing results by the data generation unit 113. The output data is configured to be output to a user or the like on a UI screen or in a predetermined file format.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] [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.

[0056] A supporter who is a person who is scheduled to conduct an interview, etc., specifies information about the person to be interviewed (support recipient information) and interview information (user-specified data 401). The user-specified data 401 may be specified as business data registered in advance, or may be input individually by the supporter.

[0057] The system prepares knowledge data and prompts based on user-specified data 401. Knowledge data is collected from a knowledge database using RAG technology from already registered information and prepared as RAG data (knowledge data 402). Furthermore, prompts to be used are set and selected from a number of predefined prompts (prompt 403).

[0058] Then, user-specified data 401, knowledge data 402, and prompt 403 are input to a generation model 404, which outputs generation data 405. In this embodiment, the generation data 405 is information about a response plan for an interview.

[0059] [Example of input / output data] 5A to 5C show examples of input / output data according to this embodiment. In FIG. 5A, input data 500 is a specific example of 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 user who is a supporter 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.

[0060] Output data 501 shows a specific example of generated data 405 output from generative model 404. Specifically, output data 501 shows the reaction of the perpetrator (a person related to the person being supported) when an interview is conducted based on input data 500, and a response plan for the supporter (e.g., a child welfare officer). The response plan here may include expected questions and answers, example answers, expected example reactions, etc. Furthermore, it may include the results of analyzing the perpetrator's characteristics, such as personality and tendencies, psychological state, attitude, cognition, etc. Furthermore, it may include questions and information to be conveyed according to the purpose of the interview. Furthermore, it may include information such as actions that should not be performed and keywords that should not be spoken, depending on the perpetrator's characteristics.

[0061] Output data 510 in Fig. 5B and output data 520 in Fig. 5C also show specific examples of generated data 405 output from generative model 404. These output data may be recorded in generated data DB 145 so that they can be checked again at any desired time, or may be held as information such as a survey record.

[0062] The function according to this embodiment may be used, for example, by a supporter user when preparing (preparing) for an interview, or when reviewing (reviewing) after the interview. It may also be used to input information in real time during an interview to obtain appropriate response examples. When used in real time, the user terminal 200 may be, for example, a PC, mobile terminal, wearable terminal, robotics, or the like, prepared at the interview site, creating an environment in which input and output are performed visually or audibly.

[0063] 6A and 6B show examples of the display configuration of a UI screen when providing a function according to this embodiment. FIG. 6A shows an example of a UI screen display assuming the use of a function according to this embodiment before or after an interview. At this time, support recipient information for the support recipient (children and related parties) related to the interview and interview information related to the interview may already be specified. On the UI screen, the user is prompted to input items that require further input as user-specified data (input area 600). For example, input of the following items may be requested as additional information: 1. Perpetrator's Response Category (multiple choice) 2. The perpetrator's last words (text entry)

[0064] These additional information items may be input in a multiple-choice format, or may be input as character string information. Furthermore, these additional information items may be added, changed, or omitted based on the supporter information and interview information that have already been specified. When additional information is input into the input area 600, corresponding response plans are displayed as the output area 601. These may be displayed in chronological order from top to bottom. Therefore, the input area 602 and the corresponding output area 603 are displayed in the same way. A simulation simulating an interview is repeated based on the user's inputs and instructions.

[0065] FIG. 6B shows an example of a UI screen display assuming the use of the function according to this embodiment in real time during an interview. At this time, support recipient information for the support recipient (child or related person) related to the interview and interview information related to the interview may already be specified. On the UI screen, the user is prompted to input items that require further input as user-specified data (input area 610). For example, input of items in the following pattern may be requested as additional information: Pattern 1: 1. Perpetrator's statement (voice input) 2. What to do? (Multiple Choice) Pattern 2: 1. Perpetrator's statement (automated voice input) 2. Automatic output of desirable responses based on the context of the conversation

[0066] These additional information items may be input using a multiple-choice format or as character string information. Alternatively, real-time utterances may be acquired and input as audio information. These additional information items may be added, changed, or omitted in anticipation of real-time processing. Furthermore, the input / output pattern for the additional information is not particularly limited and may be adjusted based on input by the interviewer. When additional information is input into the input area 610, corresponding response plans are displayed in the output area 611. These may be displayed in chronological order from top to bottom. Response plans corresponding to the real-time interview are presented based on the user's input and instructions. Furthermore, automatic real-time output is not limited to display, and may be configured to notify the interviewer of response plans and sample answers by audio or other means.

[0067] [Processing flow] 7 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.

[0068] 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 configured to be in a state where various information managed in each DB can be added, edited, and deleted.

[0069] In step S701, the server device 100 receives from the user the specification of case information related to the interview. The case information here includes support recipient information and interview information. In addition, in accordance with the UI screens shown in FIGS. 6A and 6B, the server device 100 may also receive specification of whether the use is for preparation / review of the interview or real-time use. In addition, input as additional information shown in FIGS. 6A and 6B may also be included.

[0070] In step S702, the server device 100 collects knowledge data based on the case information and composes RAG data.

[0071] In step S703, 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 S702.

[0072] In step S704, the server device 100 inputs the various data obtained in the processes of steps S701 to S703 into the generative model and generates a response plan for the interview. The information input here may be adjusted based on the case information received in step S701.

[0073] In step S705, server device 100 outputs the generated data (response plan for the interview) generated in step S704. For example, the generated data may be displayed as shown in Figures 5A to 5C and 6A to 6B. Alternatively, server device 100 may perform control so that the generated data is stored in a predetermined storage unit.

[0074] In step S706, the server device 100 determines whether or not it is necessary to output further response plans for the interview. For example, as shown in FIGS. 6A and 6B, when an interview simulation is repeated or an instruction that a response plan is required in real time is received, the server device 100 may determine that it is necessary to output further response plans for the interview. If it is determined that it is necessary to output further response plans (step S706: YES), the processing of the server device 100 returns to step S701 and repeats the processing. On the other hand, if it is determined that it is not necessary to output further response plans (step S706: NO), this processing flow ends.

[0075] 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 prepare for interviews more strategically and effectively, tailored to the characteristics and circumstances of individual offenders. This makes it possible to improve the quality of interviews, promote behavioral change in offenders, and contribute to ensuring the safety of children.

[0076] <Other embodiments> In the above embodiment, cases such as child abuse have been described as an example. However, the present invention is not limited to this and may be applied to other support and services. For example, the present invention may be applied to private companies that handle customer service, communication support services, etc. Specifically, customer harassment in customer service may be considered. In addition, questioning or interrogation by the police or the like may be included as a type of "interview."

[0077] 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.

[0078] 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)).

[0079] 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.

[0080] 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.

[0081] As described above, the present specification discloses the following:

[0082] (Technology 1) A business support system for providing a response plan for an interview in a support business, a reception unit that receives information about the support recipient and information about an interview related to support for the support recipient; a collection unit that collects information from a predetermined database based on the information received by the reception unit; a generation unit that generates a response plan for the interview by using the information received by the reception unit and the information collected by the collection unit as input for a large-scale language model; an output unit that outputs the generated response plan for the interview; A business support system with the above. The above configuration makes it possible to, for example, improve the work efficiency and quality of supporters who provide support services. In particular, supporters can prepare more strategic and effective interviews tailored to the characteristics and circumstances of individual offenders. This makes it possible, for example, to improve the quality of interviews, promote behavioral change in offenders, and contribute to ensuring the safety of children.

[0083] (Technology 2) The support service is child support, The business support system described in Technology 1, wherein the specified database is configured to include information items related to at least one of the provisions of child welfare-related laws and regulations, interview records of past child abuse cases at child consultation centers regarding how to deal with perpetrators, and case information including response strategies.

[0084] (Technology 3) The interviews include interviews with the person receiving support and those related to the person receiving support, The business support system according to Technology 1 or Technology 2, wherein the collection unit determines the information items to be collected from the predetermined database depending on the relationship between the interview subject and the support recipient.

[0085] (Technology 4) The business support system according to any one of Technology 1 to Technology 3, wherein the generation unit, when generating a response plan for an interview with a related party of the support target, analyzes at least one of characteristics including personality or tendencies of the related party, psychological state, attitude, and cognition.

[0086] (Technology 5) The business support system according to any one of Technology 1 to Technology 4, wherein the interview response plan includes at least one of questions according to the purpose of the interview, information to be conveyed, an expected reaction of the interviewee, and example answers to the reaction.

[0087] (Technology 6) The business support system according to any one of techniques 1 to 5, wherein the interview response plan includes a simulation of expected questions and answers and conversations in the interview.

[0088] (Technology 7) the collection unit collects information by RAG (Retrieval-Augmented Generation) based on the information received by the reception unit; The task support system according to any one of techniques 1 to 6, wherein the generation unit uses the information collected by the collection unit to determine a prompt to be input to the large-scale language model.

[0089] (Technology 8) an acquisition unit that acquires information on the results of an interview conducted based on the generated interview response plan; an update unit that updates the predetermined database based on the information on the interview results acquired by the acquisition unit; The business support system according to any one of techniques 1 to 7, further comprising:

[0090] (Technology 9) A control method for a business support system for providing a response plan for an interview in a support business, comprising: a receiving step of receiving information about the support recipient and information about an interview related to support for the support recipient; a collection step of collecting information from a predetermined database based on the information received in the receiving step; a generation step of generating a response plan for the interview by using the information received in the reception step and the information collected in the collection step as inputs for a large-scale language model; an output step of outputting the generated response plan for the interview; A control method for a business support system having the above. The above configuration makes it possible to, for example, improve the work efficiency and quality of supporters who provide support services. In particular, supporters can prepare more strategic and effective interviews tailored to the characteristics and circumstances of individual offenders. This makes it possible, for example, to improve the quality of interviews, promote behavioral change in offenders, and contribute to ensuring the safety of children.

[0091] (Technology 10) Computer, a reception unit that receives information on support recipients in support work and information on interviews related to support for said support recipients; a collection unit that collects information from a predetermined database based on the information received by the reception unit; a generation unit that generates a response plan for the interview by using the information received by the reception unit and the information collected by the collection unit as inputs for a large-scale language model; an output unit that outputs the generated response plan for the interview; A program to be executed as. The above configuration makes it possible to, for example, improve the work efficiency and quality of supporters who provide support services. In particular, supporters can prepare more strategic and effective interviews tailored to the characteristics and circumstances of individual offenders. This makes it possible, for example, to improve the quality of interviews, promote behavioral change in offenders, and contribute to ensuring the safety of children. [Industrial Applicability]

[0092] The present invention is useful, for example, as a device, system, and method for improving work efficiency, information sharing, and the quality of work of support staff at support sites in organizations and institutions that provide support services targeting a variety of target populations. [Explanation of symbols]

[0093] 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 for providing interview response plans in support work related to abuse, a reception unit that receives information about the support recipient and information about an interview related to support for the support recipient; a collection unit that collects information from a predetermined database based on the information received by the reception unit; a generation unit that generates a response plan for the interview by using the information received by the reception unit and the information collected by the collection unit as input for a large-scale language model; an output unit that outputs the generated response plan for the interview; and The interview is an interview with the perpetrator of the support recipient, The collection unit determines information items to be collected from the predetermined database depending on the relationship between the perpetrator and the support recipient; A business support system in which the response plan for the interview includes one or more selectable contents corresponding to information regarding at least one of the statements and reactions made by the perpetrator during the interview.

2. The business support system described in Claim 1, wherein the specified database is composed of information items relating to at least one of the provisions of child welfare-related laws and regulations, interview records of past child abuse cases at child consultation centers regarding how to deal with perpetrators, and case information including response strategies.

3. The interviews include interviews with the person receiving support and those related to the person receiving support, The business support system according to claim 1 , wherein the collection unit determines information items to be collected from the predetermined database depending on the relationship between the interviewee and the support recipient.

4. The business support system according to claim 1, wherein the generation unit, when generating a response plan for an interview with a related party of the support recipient, analyzes at least one of the characteristics including personality or tendencies of the related party, psychological state or attitude, and cognition of the related party.

5. 2. The business support system according to claim 1, wherein the interview response plan includes at least one of questions according to the purpose of the interview, information to be communicated, expected reactions of the interviewee, and example answers to the reactions.

6. The business support system according to claim 1 , wherein the interview response plan includes a simulation of expected questions and answers and conversations that may occur in the interview.

7. the collection unit collects information by Retrieval-Augmented Generation (RAG) based on the information received by the reception unit; The task support system according to claim 1 , wherein the generation unit determines a prompt to be input to the large-scale language model using the information collected by the collection unit.

8. an acquisition unit that acquires information on the results of an interview conducted based on the generated interview response plan; an update unit that updates the predetermined database based on the information on the interview results acquired by the acquisition unit; The business support system according to claim 1 , further comprising:

9. A control method for a business support system for providing a response plan for an interview in a support business, comprising: a receiving step of receiving information about the support recipient and information about an interview related to support for the support recipient; a collection step of collecting information from a predetermined database based on the information received in the receiving step; a generation step of generating a response plan for the interview by using the information received in the reception step and the information collected in the collection step as inputs for a large-scale language model; an output step of outputting the generated response plan for the interview; and The interview is an interview with the perpetrator of the support recipient, In the collection step, information items to be collected from the predetermined database are determined according to the relationship between the perpetrator and the support recipient; A method for controlling a business support system, wherein the response plan for the interview includes one or more selectable contents corresponding to information regarding at least one of the statements and reactions made by the perpetrator in the interview.

10. Computer, a reception unit that receives information on support recipients in support work and information on interviews related to support for said support recipients; a collection unit that collects information from a predetermined database based on the information received by the reception unit; a generation unit that generates a response plan for the interview by using the information received by the reception unit and the information collected by the collection unit as inputs for a large-scale language model; an output unit that outputs the generated response plan for the interview; and run it as The interview is an interview with the perpetrator of the support recipient, The collection unit determines information items to be collected from the predetermined database depending on the relationship between the perpetrator and the support recipient; The program wherein the response plan for the interview includes one or more selectable contents corresponding to information regarding at least one of the statements and reactions made by the perpetrator during the interview.

Images