Information processing system and its control method, and program

Abstract

This enables the provision of functions that improve the efficiency of document creation tasks or enhance the quality of work performed by support providers who offer support services. [Solution] An information processing system for generating explanatory materials corresponding to a person to be supported includes: an input unit that accepts document data; a first generation unit that generates first explanatory data indicating the content of the document data; a first reception unit that accepts the specification of attribute information of the person to be supported from among predetermined attribute information; a setting unit that sets a first prompt for converting the first explanatory data into second explanatory data corresponding to the person to be supported, in accordance with the attribute information; a second generation unit that generates the second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model; and an output unit that generates and outputs explanatory materials including the second explanatory data.

Description

Technical Field

[0003]

[0001] The present invention relates to an information processing system, a control method thereof, and a program.

Background Art

[0002] In recent years, in support services, a system for providing support to support recipients in view of their situations has been used. For example, in regional support, it is necessary to respond based on various recipients and situations such as child support, abuse response, child injury and accident response, maternal and child health, DV (Domestic Violence) response, sexual violence response, delinquency and crime response, developmental disorder response, elderly welfare, disabled welfare, delinquency / crime investigation, harassment, etc.

[0003] In support services, it is necessary to conduct various investigations according to the support content and create documents based on the investigation results. For example, there are documents such as the support response history and documents for explaining to support recipients. In recent years, AI-related technologies such as machine learning and generative AI (Artificial Intelligence) have developed and are being utilized in various fields. For example, Patent Document 1 discloses a technique for generating a document of investigation results or creating a summary using a generative AI model.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the support settings described above, it is necessary to extract and document essential information based on extensive survey results and past support achievements. Furthermore, when explaining the contents of these documents to those receiving support, it is necessary to adjust the language and amount of information to facilitate their understanding. However, this type of work places a heavy burden on support workers and also relies to their experience and knowledge.

[0006] In view of the above issues, the present invention aims to provide a function that can improve the efficiency of document creation work or the quality of work performed by support providers who provide support services. [Means for solving the problem]

[0007] To solve the above problems, one embodiment of the present invention has the following configuration. That is, an information processing system that generates explanatory materials corresponding to the person to be supported, An input unit that accepts document data input, A first generation unit generates first explanatory data that shows the contents of the document data, A first reception unit that accepts the designation of attribute information of the person to be supported from among predefined attribute information, A setting unit sets a first prompt for converting the first explanatory data to second explanatory data corresponding to the person being supported, in accordance with the attribute information; A second generation unit generates second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model, An output unit that generates and outputs explanatory materials including the second explanatory data, It has.

[0008] Another embodiment of the present invention has the following configuration: namely, a control method for an information processing system that generates explanatory materials corresponding to a person to be supported, The input process for receiving document data, A first generation step of generating first explanatory data that shows the contents of the document data, A first reception step in which the attribute information of the person to be supported is selected from a predetermined set of attribute information, A setting step of setting a first prompt for converting the first explanatory data to second explanatory data corresponding to the person being supported, in accordance with the attribute information, A second generation step of generating second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model, Output process for generating and outputting explanatory materials including the second explanatory data, It has.

[0009] Another embodiment of the present invention has the following configuration: namely, a program, Computers, An input unit that accepts document data input, A first generation unit that generates first explanatory data indicating the content of the document data, The first reception desk accepts the designation of attribute information of the person to be supported from among the predefined attribute information. A setting unit sets a first prompt for converting the first explanatory data into second explanatory data corresponding to the person being supported, in accordance with the attribute information. A second generation unit generates the second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model. An output unit that generates and outputs explanatory materials including the second explanatory data, To make it function as such. [Effects of the Invention]

[0010] According to the present invention, it is possible to provide functions that improve the efficiency of document creation work for support providers or improve the quality of their work. [Brief explanation of the drawing]

[0011] [Figure 1]Configuration diagram showing a configuration example of a business support system according to a first embodiment of the present invention [Figure 2] Functional block configuration diagram showing a server device according to a first embodiment of the present invention [Figure 3] Functional block configuration diagram showing a user terminal according to a first embodiment of the present invention [Figure 4] Explanatory diagram for explaining the concept of processing according to a first embodiment of the present invention [Figure 5A] Example diagram showing a configuration example of a UI screen according to a first embodiment of the present invention [Figure 5B] Example diagram showing a configuration example of a UI screen according to a first embodiment of the present invention [[ID=十六]] を翻訳することができません。エラーメッセージを表示します:エラー:翻訳できないコードが見つかりました。コード: [Figure 5C] Example diagram showing a configuration example of a UI screen according to a first embodiment of the present invention [Figure 5D] Example diagram showing a configuration example of a UI screen according to a first embodiment of the present invention [Figure 5E] Example diagram showing a configuration example of a UI screen according to a first embodiment of the present invention [Figure 6] Flowchart of processing according to a first embodiment of the present invention

Mode for Carrying Out the Invention

[0012] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings and the like. The embodiments described below are one embodiment for explaining the present invention and are not intended to be construed as limiting the present invention. Also, not all configurations described in each embodiment are essential configurations for solving the problems of the present invention. In each drawing, the same reference numerals are assigned to the same components to indicate the correspondence. Note that, in order to avoid unnecessary redundancy and facilitate the understanding of those skilled in the art, part of the description may be omitted or simplified. For example, detailed descriptions of well-known matters and redundant descriptions of substantially the same configurations may be omitted.

[0013] 注:原文中“[[ID=十六]] ”可能存在编号错误,按照正常编号顺序应为“ ”,但根据翻译要求保留原文内容进行翻译,因此出现了上述无法翻译的提示。实际翻译时请根据正确内容进行调整。First, the embodiments for carrying out the present invention will be described assuming child support services, which are a type of administrative service. It should be noted that some or all of the functions and components of the embodiments described later are not limited to child support services, but may be applied to various fields and services. Furthermore, modifications, adjustments, and expansions may be made as appropriate depending on the field or service to which they are applied.

[0014] Furthermore, the term "personal information" as used in the following explanation includes data whether or not it was collected directly from an individual, and may include data consisting of one or more items. In addition, if other types of information are generated or derived based on personal information including PII (Personally Identifiable Information), such other types of information may also be treated as personal information. Personal information is generally managed with strict restrictions on its handling as sensitive data (hereinafter collectively referred to as "sensitive data"). In the following embodiment of the present invention, we envision a service related to child support in government agencies, etc., under management based on such restrictions.

[0015] Furthermore, the configuration according to the present invention assumes the use of sensitive data requiring careful handling, such as personal information, and therefore assumes a network with restricted user access. While the method of access restriction is not particularly limited, one example is the use of a closed network not connected to the internet. These users are also expected to have access to data, its scope, and handling defined based on their assigned duties and authority. When handling data that does not contain sensitive information, the network configuration is not limited to the above and may be modified as appropriate.

[0016] In this embodiment, a generative AI (generative model) generated by performing a predetermined learning process based on machine learning technology is used. The learning algorithm, learning method, and learning data for generating the generative AI are not particularly limited and may be adjusted or combined as appropriate to provide the functions described later.

[0017] Large Language Models (LLMs) in Generative AI are built on large datasets and are capable of producing output that takes the context of the input data into account. Examples of well-known LLMs include ChatGPT®, Copilot, Gemini, Claude, Llama, and OpenELM.

[0018] <First Embodiment> Support staff, such as those at child welfare centers, are required to extract appropriate information from a vast amount of data and create various documents when dealing with complex and diverse child abuse cases. Document creation may involve summarizing multiple pieces of information necessary for the job, or concisely highlighting notable case characteristics. Furthermore, they are required to explain and notify those receiving support (including victims and perpetrators in child abuse cases) of the document's contents. This explanation and notification may involve understanding the case overview and explaining it to relevant parties, or immediately sharing and explaining the case overview during personnel changes or handovers. These tasks require a high level of expertise and considerable effort, placing a significant burden on individual staff members. In particular, there has been a need for a function to organize and coordinate the content to be explained and the methods of explanation for people with diverse backgrounds in the field of child support.

[0019] Therefore, in this embodiment, a business support function is provided to reduce the workload of the above-mentioned tasks and enable more appropriate support to be provided to those receiving support.

[0020] [System Configuration] Figure 1 is a schematic diagram showing an example configuration of a business support system (information processing system) according to the first embodiment of the present invention. The business support system 1 is a system whose main functions are, for example, communication with users and support for decision-making. The business support system 1 enables the input, viewing, and sharing of records both inside and outside the organization that performs the work, and provides functions such as chat communication between supporters, registration and sharing of photos of people being supported, and simulation of past support trends. Here, as an example of an organization to which this system can be applied, a child guidance center that performs child support work is used as an example, but it is not limited to this. This system may be applied to, or configured to link with, systems of organizations such as municipal offices, maternal and child health centers, schools, kindergartens, nurseries, medical institutions, police, prosecutors, fire departments, child welfare agencies, NPOs (Non-Profit Organizations), and private companies that cooperate with these organizations. The business support system 1 consists of a server device 100, a user terminal 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.

[0021] The server device 100 is a device for providing various functions provided by the business support system 1 to the user terminal 200. The server device 100 provides applications to the user terminal 200 to support business efficiency and manages information registered via the user terminal 200. Some or all of the functions described later may be provided on the user terminal 200 side or on the linked system 300 side, which can be linked via a network NW. The server device 100 may be configured on-premises using a general-purpose computer such as a workstation or personal computer, or it may be logically implemented by cloud computing (such as SaaS (Software as a Service)). In this embodiment, for the sake of explanation, one server device 100 is shown as an example, but it is not limited to this, and there may be multiple devices, and there may be servers with different roles, such as an authentication server, a database server, and an AI server.

[0022] The user terminal 200 is an operating terminal used by users such as staff of the child guidance center. The user terminal 200 may consist of an information processing device such as a personal computer, tablet, smartphone, or POS terminal. The user terminal 200 provides users with the functions of Web services provided by the server device 100 and applications installed and running on the user terminal 200. In the example in Figure 1, one user terminal 200 is shown, but many more user terminals may be used. The configurations of multiple user terminals 200 may be different or the same. Also, the available functions may differ depending on the role and authority of the user using the user terminal 200.

[0023] The collaborative system 300 is an external system that functions in conjunction with the server device 100 via a network NW. The collaborative system 300 may be configured, for example, as a child consultation record system, primarily providing functions such as recording child consultations and issuing administrative documents. The child consultation record system may perform functions such as issuing child numbers and reception numbers related to children, issuing medical examination 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 collaborative system 300 is not particularly limited, and it may be configured to provide various functions related to business support, for example. Although only one collaborative system 300 is shown, it is not limited to this configuration and may be composed of one or more devices depending on the functions and services.

[0024] A network (NW) consists of the internet, intranet, wireless LAN (Local Area Network), WAN (Wide Area Network), etc. The communication standards and wired / wireless connections related to the network (NW) are not particularly limited, and a network (NW) may be configured using a combination of multiple communication standards. As mentioned above, considering the confidentiality of the information handled, a network (NW) may be constructed as a closed network accessible only to designated users, rather than a public network such as the internet.

[0025] Figure 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 is composed of a control unit 110, a communication unit 130, and a storage unit 140. Each part is configured to communicate with each other via an internal bus or the like.

[0026] 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 Processing Unit), etc., and provides various functions by reading and executing various programs and data stored in the memory unit 140. The control unit 110 functions as, for example, a data reception unit 111, a data management unit 112, a prompt setting unit 113, an explanatory data generation unit 114, a data conversion unit 115, a knowledge data reference unit 116, an information setting unit 117, an output data generation unit 118, a display control unit 119, and a communication control unit 120.

[0027] The data reception unit 111 receives instructions and data according to this embodiment based on user instructions. The various data received by the data reception unit 111 may be recorded in the storage unit 140 or provided to an external party (for example, the linked system 300).

[0028] The data management unit 112 manages the recording, retrieval, and updating of data for the various databases (DBs) configured in the storage unit 140. Examples of data managed in each DB will be described later.

[0029] The prompt setting unit 113 sets, selects, and controls the prompts used in the generation model according to this embodiment based on user instructions. The prompts used will differ depending on the type and content of the generated data output by the generation model. In this embodiment, prompts may be selected based on attribute information and descriptive condition information indicated by user instructions. Alternatively, predefined prompts may be used in combination. Furthermore, the prompt setting unit 113 may adjust the knowledge data referenced by the knowledge data reference unit 116 and various input information into input prompts by combining them with predefined prompt data.

[0030] The explanatory data generation unit 114 generates explanatory data from the specified document data to explain the content of the document data. In this embodiment, the explanatory data is generated using a generation model based on a large-scale language model. Specific examples of explanatory data will be described later.

[0031] The data conversion unit 115 converts the explanatory data generated by the explanatory data generation unit 114 according to the attributes of the target audience for which the explanation is to be given. In this embodiment, the explanatory data is converted using a generation model based on a large-scale language model. Specific examples of conversion will be described later.

[0032] The knowledge data reference unit 116 references knowledge data used in various processes according to this embodiment based on user instructions. In this embodiment, as information to be input to the generation model, knowledge data is referenced from the registered knowledge database based on the content and conditions to be explained, the attributes of the person being explained to, etc. For the reference of knowledge data, for example, RAG (Retrieval-Augmented Generation) technology may be used. Note that 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.

[0033] The information setting unit 117 sets various types of information used when generating or converting explanatory data according to this embodiment. Examples of configurable information according to this embodiment include attribute information and explanatory condition information. Specific examples of these will be described later, but the system may be configured so that the user can specify from a pre-defined set of options (setting values) for various information items. The information items included in the information may also be defined in advance.

[0034] The output data generation unit 118 generates output data converted to an output format using various data generated by the explanatory data generation unit 114 and the data conversion unit 115. For example, the output data may be in file format or composed in a predetermined recording format. More specifically, the output data may be data in a format composed in a predetermined format. Examples of formats include presentation format, document format, web page format, explanatory video format, etc. The output data generation unit 118 may also generate output data using a generation model based on a large-scale language model.

[0035] The display control unit 119 performs display control for displaying various processing results, which will be described later. 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 the user terminal 200 with UI (User Interface) screen data for display.

[0036] The communication control unit 120 controls communication with external devices (e.g., user terminals 200 and linked systems 300) and transmits and receives data. This communication control may be performed, for example, according to the configuration of a closed network or access restrictions.

[0037] The communication unit 130 is a communication interface for communicating with external devices via a network NW. The communication unit 130 may be configured to support multiple communication standards depending on the configuration of the network NW.

[0038] The memory unit 140 is a storage device for storing programs, data, etc., for executing various control processes and functions within the control unit 110. The memory unit 140 is composed of volatile / non-volatile storage devices such as RAM (Random Access Memory), ROM (Read Only Memory), HDD (Hard Disk Drive), and flash memory. The memory unit 140 includes a database (DB) for managing data corresponding to the functions described later.

[0039] The document data DB141 manages various document data related to support work. For example, it may manage the results of investigations conducted on information about children who are receiving support and information about their related parties, as well as information about the people receiving support. The "document data" in this embodiment is not limited to documents in a predetermined format, but may also include, for example, notes recorded during interviews, conversation data (audio data), and video data.

[0040] The generation model DB142 manages the generation models used in various processes performed by the explanatory data generation unit 114, the data conversion unit 115, and the output data generation unit 118. The generation models hold models that have been trained to a certain extent so that they can perform the processes according to this embodiment. Training processes may also be performed periodically.

[0041] The prompt DB 143 manages prompt data for configuring prompts used in various processes performed by the explanatory data generation unit 114, the data conversion unit 115, and the output data generation unit 118. Prompts correspond to commands and instructions used as input to the generation model and are used differently depending on the content to be output. For example, a prompt format for a process described later may be predefined as prompt data. The prompt data registered in the prompt DB 143 may be configured to be directly input into the generation model, or it may be adjusted or selected based on instructions from the user.

[0042] Knowledge Data DB144 is configured as a knowledge database and manages the information that forms the basis of the knowledge data input into the generative model. Knowledge Data DB144 may have a configuration that includes data such as the following. Note that the configuration and names below are just examples, and it may include only a part of them, or it may include much more data.

[0043] (1) Legal and manual database Articles of relevant laws and regulations such as the Child Welfare Act, the Child Abuse Prevention Act, the Penal Code, the Civil Code, the Administrative Litigation Act, the Administrative Appeals Act, and the National Compensation Act, as well as related administrative manuals, guidelines for responding to sexual abuse at child guidance centers, other child abuse-related guidelines, a manual for responding to child abuse, guidelines for the operation of child guidance centers, and various notifications related to child abuse.

[0044] (2) Terminology Database Definitions of terms specific to the child welfare industry. In particular, this includes special usages and abbreviations used in practice that differ from dictionary definitions (e.g., case, entry, sexual abuse, etc.).

[0045] (3) Representation Database This includes examples of expressions for explanations tailored to the target audience, techniques for the flow of explanation, advice based on the listener's reaction, and expression information tailored to the language used and the speaker's native language. For example, it may include information on the use of passive or active expressions that take psychological effects into consideration, expressions that meet the disclosure requirements for documents including summaries, and expressions that take into account the trauma and feelings of those who read the summary, as well as information that addresses restrictions and constraints on expression. In addition, it may include information on terminology, vocabulary, grammar, expression style, level of abstraction, descriptive structure, animation, moving images, icon images, character images, etc.

[0046] The configuration information DB145 manages information about the attributes of the person being supported who is to be explained. Attributes include various items. For example, the language used for explanation, age group, intellectual level, gender, and the person's role in the event are listed as attribute information. Attribute information is indicated by values ​​that show the classification to which the person belongs in various predefined information items. For language, for example, "Japanese" or "English" may be selectable. For age group, for example, "preschooler," "lower elementary school," "upper elementary school," "junior high / high school student," "adult," or "elderly" may be selectable. For intellectual level, for example, based on IQ (Intelligence Quotient), the intellectual level may be selected as "slow," "standard," or "high." For role, for example, "victim," "perpetrator," or "related party" may be selectable.

[0047] The explanatory data DB146 manages the explanatory data generated by the explanatory data generation unit 114, the converted explanatory data obtained by the data conversion unit 115, and the document data from which the explanatory data was derived, by associating them with each other.

[0048] Output data DB147 manages output data in a predetermined output format generated based on explanatory data. Output data DB147 may also manage information on the person being explained to and the person providing the explanation (the person giving the explanation).

[0049] Figure 3 is a block diagram showing an example of the functional configuration of the user terminal 200 according to this embodiment. The user terminal 200 is composed of 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.

[0050] The control unit 210 is responsible for controlling 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 memory unit 220.

[0051] The memory unit 220 is a storage device for storing programs, data, and other information necessary for executing various control processes and functions of the control unit 210. The memory unit 220 is composed of volatile / non-volatile storage devices such as RAM (Random Access Memory), ROM (Read Only Memory), HDD (Hard Disk Drive), and flash memory.

[0052] The communication unit 230 is a communication interface for communicating with external devices via a network NW. The communication unit 230 may be configured to support multiple communication standards depending on the configuration of the network NW.

[0053] The operation unit 240 is an interface for receiving operations from the user of the user terminal 200. The operation unit 240 may consist of a mouse, keyboard, etc. The display unit 250 is an interface for displaying various screens and consists of a display, etc. A touch panel display that integrates 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 a connection interface to, for example, an imaging unit (not shown) for taking images or sensors for acquiring predetermined information.

[0054] [Data flow] Figure 4 is a schematic diagram illustrating the data flow in the business support system 1 according to this embodiment. The flow shown here is implemented in the server device 100 and focuses on the parts relevant to this embodiment. Therefore, the data flow is not limited to this, and further data flows (for example, data input by the user) may be added as needed.

[0055] Support staff, such as those at child welfare centers, specify information about the person receiving support and the data that will serve as the basis for explanatory data (document data 401). Document data 401 may be pre-registered in document data DB 141, or it may be entered individually by the support staff. Document data 401 may contain sensitive information such as personal information.

[0056] Furthermore, when creating explanatory data, the supporter specifies explanatory condition information 402. In this embodiment, explanatory condition information 402 specifies chief complaint information indicating the condition of the person receiving support related to child support, and scene information indicating the situation requiring explanation. Specific examples of these specifications will be described later.

[0057] On the system side, knowledge data 403 and prompt 404 are prepared based on the specifications regarding the explanatory condition information 402. The knowledge data is collected and prepared using RAG technology from the already registered knowledge data DB 144. Furthermore, prompt 404 is set and selected from a predefined set of prompts.

[0058] Then, the generative model 405 receives document data 401, explanatory condition information 402, knowledge data 403, and prompt 404 as input, causing it to output explanatory data 407. The explanatory data 407 may include string information, image information, statistical information, etc. Examples of explanatory data will be described later.

[0059] Furthermore, when creating explanatory data, supporters are required to specify attribute information 406 regarding the person being supported (the person being explained to) for whom the content of the explanatory data will be explained. Specific examples of attribute information 406 will be described later.

[0060] On the system side, knowledge data 408 and prompt 409 are prepared based on the specifications regarding attribute information 406. The knowledge data is collected and prepared using RAG technology from the already registered knowledge data DB 144. Furthermore, prompt 409 is set and selected from a predefined set of prompts.

[0061] Then, when explanatory data 407, attribute information 406, knowledge data 408, and prompts 409 are input to the generative model 410, the explanatory data 407 is transformed to reflect the attributes of the person being explained to. An example of the transformed explanatory data 411 will be described later.

[0062] Furthermore, the generated model 413 receives the converted explanatory data 411 and a prompt 412 for generating the final output data, thereby outputting explanatory materials 414 as output data. In this embodiment, explanatory materials are created step by step using the generated model as described above.

[0063] Note that generative models 405, 410, and 413 may each be separate generative models that have been trained to be specialized for their respective processes. Alternatively, the same generative model may be used, but the structure of the input prompts may be adjusted according to each process.

[0064] [Input / Output Examples] Figures 5A to 5E show examples of UI screen configurations according to this embodiment. Each UI screen is displayed in an operable manner, for example, on the display unit 250 of the user terminal 200.

[0065] Figure 5A shows an example configuration of the UI screen 500 as the initial screen of the function according to this embodiment. The data selection unit 501 is a part for specifying document data that will be the source data for explanatory data. By pressing the reference button 502, a window (not shown) in which data can be specified is displayed. Document data may then be specified through that window. The chief complaint information input unit 503 is a part for specifying information indicating the chief complaint from among predefined options. The chief complaint may be, for example, "psychological abuse," "sexual abuse," or "physical abuse." The scene information input unit 504 is a part for specifying information indicating the scene in which the explanation will be given from among predefined options. The scene may be, for example, "guidance intervention," "temporary protection," or "interview." The values ​​that can be selected in the chief complaint information input unit 503 and the scene information input unit 504 are predetermined.

[0066] The Start Generation button 505 is used to instruct the start of explanatory data based on the specified data and settings. The Close button 506 is used to close the UI screen 500 (interrupt the process).

[0067] Figure 5B shows an example configuration of a UI screen 510 for displaying the results of generating explanatory data based on the information entered in the UI screen 500 shown in Figure 5A.

[0068] Setting information items 511, 512, and 513 represent the values ​​set in the data selection section 501, chief complaint information input section 503, and scene information input section 504 of the UI screen 500 shown in Figure 5A, respectively. The generation result display section 514 is the part that displays the content of the explanatory data generated based on the set information. In this example, based on the content of the document data, chief complaint information, and scene information, explanatory information is generated and displayed for items such as "Legal basis for intervention and our responsibilities," "Legal position of this case (basis for intervention)," and "Cooperation with immediate investigative authority is required." Note that the items and content shown here will be adjusted according to the settings, etc.

[0069] The Next button 515 is a button that instructs the system to proceed with processing based on the generated explanatory data. The Close button 516 is a button that closes the UI screen 510 (interrupts processing).

[0070] Figure 5C shows an example of the configuration of the UI screen 520 that is displayed when the Next button 515 is pressed on the UI screen 510 shown in Figure 5B.

[0071] The generation result display unit 521 is a part for displaying the content of the generated explanatory data. The content displayed in the generation result display unit 521 is the same as that of the generation result display unit 514 in the UI screen 510 shown in Figure 5B.

[0072] The language information input unit 522 is a component for specifying the language to be used for explanation to the person being explained to. The languages ​​that can be specified may be predetermined. The language information input unit 522 may also be configured to allow selection of dialects or specific linguistic expression conditions. For example, in Japanese, it may be possible to specify the "desu / masu" style or the "da / dearu" style, and in English, it may be possible to specify American English or British English.

[0073] The age category information input section 523 is a part for specifying the age category of the person being explained to. The age categories may include, for example, "preschool children," "lower elementary school students," "upper elementary school students," "junior high and high school students," "adults," and "elderly."

[0074] The intellectual level information input unit 524 is a part for specifying the intellectual level of the person being explained to (for example, IQ or learning progress level). The intellectual level may be selectable based on, for example, IQ, with options such as "slow," "standard," and "high."

[0075] The position information input section 525 is a part for specifying the position of the person being described in the document data (for example, abuse). The position may be selectable from options such as "victim," "perpetrator," or "related party."

[0076] Furthermore, the attribute information of the person being described that can be entered on UI screen 520 is not limited to the items that can be entered in the input section above, and may include many more information items. Also, the number of inputtable information items may increase or decrease depending on the event, and the selectable values ​​may change. Also, the granularity of the selectable values ​​may change depending on the event. Specifically, in cases of abuse, it may be possible to select whether the "perpetrator" is the "father" or the "mother". Moreover, in addition to relatives such as "adoptive parents," "siblings," and "common-law partners," it may also be possible to select the parents' friends, facility staff, foster parents, etc.

[0077] The conversion execution button 526 is a button used to instruct the conversion of explanatory data based on the input attribute information. The close button 527 is a button used to close the UI screen 520 (interrupt the process).

[0078] Figure 5D shows an example configuration of UI screen 530 for displaying the results of converting explanatory data based on the information entered in UI screen 520 shown in Figure 5C.

[0079] The generation result display unit 531 is a part for displaying the content of the generated explanatory data. The content displayed in the generation result display unit 531 is the same as that of the generation result display unit 514 in the UI screen 510 shown in Figure 5B.

[0080] The conversion result display unit 532 is a part for displaying the content of the converted explanatory data.

[0081] The change input section 533 is where the user confirms the content shown in the conversion result display section 532 and inputs the content they wish to change. The change input section 533 is configured to allow free input of string information. The information entered in the change input section 533 is combined with the processing content and prompts from the previous processing and used as input information for the generation model to regenerate the explanatory data after conversion.

[0082] The setting information display unit 534 is a part for displaying various information set on the UI screen 500 shown in Figure 5A and the UI screen 520 shown in Figure 5C.

[0083] The regenerate button 535 is a button that instructs the regeneration of the converted explanatory data based on the content displayed in the generation result display unit 531 and the conversion result display unit 532, and the information entered by the user in the change input unit 533. After the converted explanatory data is regenerated, the display content of the conversion result display unit 532 on the UI screen 530 is updated. The regenerate button 535 may be controlled to be pressable only when input has been made in the change input unit 533.

[0084] The explanatory material generation button 536 is a button that instructs the generation of explanatory materials as output data based on the converted explanatory data. The format of the explanatory materials may be predetermined or it may be specified by the user. The close button 537 is a button that closes the UI screen 530 (interrupts processing).

[0085] Figure 5E shows an example configuration of UI screen 540 for displaying the generated explanatory materials.

[0086] The generation result display unit 541 is a section for displaying the content of the generated explanatory data. The content displayed in the generation result display unit 541 is the same as that of the generation result display unit 531 in the UI screen 530 shown in Figure 5D.

[0087] The conversion result display unit 542 is a section for displaying the content of the converted explanatory data. The content displayed in the conversion result display unit 542 is the same as that of the conversion result display unit 532 in the UI screen 530 shown in Figure 5D.

[0088] The explanatory drawing display unit 543 is for displaying explanatory drawings if they were generated along with the explanatory data. The user may specify whether or not to generate drawings. Alternatively, the content of the drawings and whether or not they are necessary may be adjusted to match the converted explanatory data. In this case, the creation and adjustment of the drawings may be performed using a generation model.

[0089] The setting information display unit 544 is a part for displaying various information set on the UI screen 500 shown in Figure 5A and the UI screen 520 shown in Figure 5C. The content displayed on the setting information display unit 544 is the same as that displayed on the setting information display unit 534 of the UI screen 530 shown in Figure 5D.

[0090] The save button 545 is a button used to instruct the system to save the generated data. The save location may be predetermined or specified by the user. The generated data may also be configured to be saved to various databases. The close button 546 is a button used to close the UI screen 540 (interrupt the process).

[0091] The above UI screen configuration is just one example and is not limited to this. For example, some components may be configured as pop-up screens. Alternatively, explanatory condition information and attribute information may be configured to be input together on a single screen. Furthermore, when generating explanatory drawings, a separate UI screen may be provided for those drawings.

[0092] [Processing flow] Figure 6 is a flowchart showing the overall processing flow 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. For the sake of simplicity, the server device 100 is described as the processing entity here.

[0093] Before this processing flow begins, various information will be registered and configured to be accessible in each database of the server device 100. Furthermore, the server device 100 will be in a state where it is possible to add, edit, delete, etc., the various information managed in each database.

[0094] In step S601, the server device 100 receives the specification of document data that will be the source data for the explanatory materials. In this embodiment, the server device 100 receives the specification of document data via the UI screen 500 shown in Figure 5A, which is displayed on the user terminal 200.

[0095] In step S602, the server device 100 receives the specification of explanation condition information regarding the explanation. In this embodiment, the server device 100 receives the specification of explanation condition information via the UI screen 500 shown in Figure 5A.

[0096] In step S603, the server device 100 acquires knowledge data corresponding to the explanatory condition information received in step S602. The information items and types of the knowledge data acquired here are defined in accordance with the values ​​of each item in the explanatory condition information.

[0097] In step S604, the server device 100 inputs the document data received in step S601, the explanation condition information received in step S602, and the knowledge data acquired in step S603 as input data into the generation model. The server device 100 also selects and sets a prompt corresponding to the explanation condition information from a predetermined set of prompts and inputs it into the generation model. As a result, the server device 100 generates explanation data for the document data received in step S601.

[0098] In step S605, the server device 100 displays the explanatory data generated in step S604. In this embodiment, the server device 100 displays the UI screen 510 on the user terminal 200 and displays the explanatory data.

[0099] In step S606, the server device 100 receives the specification of attribute information regarding the person to be explained. In this embodiment, the server device 100 receives the specification of attribute information via the UI screen 520 shown in Figure 5C.

[0100] In step S607, the server device 100 sets a prompt to be input to the generation model based on the attribute information received in step S606. The prompt here may be selected from a predetermined set according to the attribute information, or a single prompt may be generated according to a combination of values ​​of various information.

[0101] In step S608, the server device 100 inputs the explanatory data generated in step S604, the attribute information received in step S606, and the prompt set in step S607 as input data into the generation model. The server device 100 also references the knowledge data corresponding to the attribute information received in step S606 from the knowledge database and inputs it into the generation model. As a result, the server device 100 converts the explanatory data generated in step S604 into content appropriate for the person being explained to.

[0102] In step S609, the server device 100 displays the explanatory data converted in step S608. In this embodiment, the server device 100 displays the UI screen 530 on the user terminal 200 and displays the converted explanatory data.

[0103] In step S610, the server device 100 determines whether or not it has received an instruction to regenerate the converted explanatory data. In this embodiment, the server device 100 may determine that it has received an instruction to regenerate when the regenerate button 535 on the UI screen 530 displayed on the user terminal 200 is pressed. If the instruction to regenerate has been received (step S610: YES), the server device 100 proceeds to step S611. On the other hand, if the instruction to regenerate has not been received (step S610: NO), the server device 100 proceeds to step S612. Note that the case where the instruction to regenerate has not been received is described as when the explanatory material generation button 536 on the UI screen 530 is pressed.

[0104] In step S611, the server device 100 resets the prompt based on the information entered by the user in the change input section 533 of the UI screen 530. The method of setting here may be the same as or different from that in step S607. For example, the server device 100 may include the string information entered in the change input section 533 directly into the prompt to configure the prompt for regeneration. After that, the server device 100 returns to step S608 and repeats the process.

[0105] In step S612, the server device 100 generates explanatory materials using the converted explanatory data generated in step S608, based on instructions from the user. In this embodiment, explanatory materials in a predetermined format may be generated by inputting predefined prompts and explanatory data before and after conversion into the generation model.

[0106] In step S613, the server device 100 outputs the explanatory material generated in step S612. In this embodiment, the server device 100 may be configured to display the generation result via, for example, the UI screen 540 shown in Figure 5E and record it in a predetermined storage area according to the user's instructions. Alternatively, after creating and displaying the explanatory material, the system may be configured to regenerate part or all of the content based on the user's instructions. In this case, the process in step S612 may be repeated. The process flow then ends.

[0107] [Case example 1] An example of a case (dummy case) according to this embodiment is shown below. The report content below corresponds to the content of the document data.

[0108] (Reported content: Psychological abuse resulting from witnessing domestic violence) Scene of the incident: When the call was made, the father (husband) was in an agitated state, banging on the cupboard door and yelling at the mother (wife). The mother was cowering in the corner of the room. The perpetrator (father) is in his 40s. He claims that his actions were "my wife's fault for not listening to me" and that "it was a marital argument even in front of the children," showing no signs of remorse whatsoever. Alcohol consumption does not appear to have had any effect. Police officers are currently trying to persuade him. Victim (mother)'s situation: In her 40s. No physical injuries. While telling the police she "can't take it anymore" and "wants to separate," she also said, "I can't leave home because I'm worried about my children." Child's situation: 8 years old (3rd grade elementary school). The child was trembling in another room, but remained expressionless when a police officer spoke to them. They said, "It's okay, because Mom and Dad always fight." There were no signs of crying or distress, strongly suggesting that the child was used to the situation (psychological signs of familiarity and indifference). Request to the Child Guidance Center: We requested urgent action regarding ensuring the safety of the mother and child (considering the need for temporary protection) and determining whether guidance and intervention can be provided to the father.

[0109] (Example of explanatory data generated based on the report content) [Legal basis for intervention and our responsibilities] Our organization is a public institution that is responsible for protecting children and promoting their welfare, based on the Child Welfare Act (Act No. 164 of 1947) and the Act on the Prevention of Child Abuse, etc. (Act No. 82 of 2000). Our involvement in this matter is not an undue intervention against a specific individual, but rather an action taken as part of our public responsibility based on the aforementioned laws and regulations. [Legal status of this case (basis for intervention)] Upon receiving a report that domestic violence (DV) is occurring continuously in your household and that a child has witnessed the situation, our office has commenced an investigation based on the following legal definitions. Legal basis and relationship to the case Article 2 of the Child Abuse Prevention Act clearly defines acts of violence against a spouse in front of a child as psychological abuse of a child (words or actions that severely harm the child's mind or body). Article 25 of the Child Welfare Act When we receive a report of a suspected case of child abuse, our office has an obligation to promptly verify the facts and provide appropriate assistance. [Immediate investigative authority and cooperation required] To prioritize the safety of children and their healthy physical and mental development, our office conducts fact-finding investigations and provides guidance based on the following authority: Article 25-2 of the Child Welfare Act (Request for Information): We request necessary information from relevant parties and organizations (schools, medical institutions, police, etc.) in order to understand the child's current situation and family circumstances. Article 26, Paragraph 1, Item 2 of the Child Welfare Act (Investigation, Guidance, etc.): We conduct necessary investigations, diagnoses, or provide guidance. Accordingly, parents (fathers and mothers) are required to cooperate promptly with the fact-finding investigations and guidance conducted by our office based on the above laws and regulations.

[0110] (Example 1 of the conversion result of explanatory data) In the case of attribute information where the age category is "preschool child (approximately 3 to 6 years old)" and the position is "victim" [1. Self-introduction and role (translation of legal basis and responsibilities)] "Hello, [child's name]. My name is [my name]. I'm from a place called the 'Children's Counseling Center.' This is a place where we work to ensure that children can live safely. Today, I came to talk to you and your mother." [2. What happened? Confirm the rules (translation of illegality and harmfulness)] "Earlier, I heard from the police that your dad was shouting loudly and banging things around the house. It was really loud, and it was quite a shock, wasn't it?" [3. You are not at fault (exemption from liability for the victim)] "Dad wasn't angry because you weren't being a good girl. You didn't do anything wrong. You said, 'It's nothing unusual, so I'm fine,' but I bet you were really nervous and scared, weren't you? You held back your tears. You did so well."

[0111] For example, based on various knowledge data, we perform transformations of terms and other elements with the following objectives:

[0112] (Conversion Example 1-1) The element of the original explanatory data: "Responsibilities under the Child Welfare Act" Translation for preschool children: "A job to protect them so they can spend their days with a smile." Objective: To emphasize the role of "protecting children's safety" rather than authority, thereby providing a sense of security.

[0113] (Conversion example 1-2) The element in the original explanatory data is "Psychological abuse (witnessing domestic violence)". Translation for preschool children: "Shouting loudly or hitting things." Objective: To avoid using abstract language and instead describe specific actions observed by children.

[0114] (Example 2 of the conversion result of explanatory data) In the case of attribute information where the age category is "adult" and the position is "perpetrator" [1. Legal basis for intervention (denial of the perception of "marital dispute")] "Mr. / Ms. [Father's Name], this is [Your Name] from the Child Guidance Center. I received a call from the police a short while ago and am calling you now. I understand that you said, 'This is just a marital dispute,' and 'It's my wife's fault for not listening to me.' Under Japanese law, this incident will not be treated as a simple 'marital dispute.' From your child's perspective, something very frightening happened within the home, and as an administrative agency, we believe that a situation has occurred that raises concerns about your child's safety, and therefore we have come to speak with you." [2. Awareness of the harmful and illegal nature of the act (denial of "blaming my wife")] "Using violence or intimidation to force someone into submission is unacceptable, regardless of the reason. The fact that you chose violence because you couldn't control the situation is not your wife's fault; it was your own choice. What are your thoughts on that?" [3. Impact on children (Dispelling the misconception that they are "used to it")] "When your child didn't cry because they said, 'It's just like this,' it didn't mean they were okay. It meant they had frozen their heart and given up, thinking, 'Crying is useless,' or 'If I just disappear, it'll all be over.' This means that, as a result of similar incidents happening over a long period of time, your child's heart has been deeply wounded."

[0115] For example, based on various knowledge data, we perform transformations of terms and other elements with the following objectives: (Conversion Example 2-1) The element of the original explanatory data: "Responsibilities under the Child Welfare Act" Translation for the perpetrator: "Intervention by a public institution" Objective: Not to intervene in the private sphere (family), but to confirm the facts of a situation where a child's safety is threatened and to take appropriate action.

[0116] The above examples of explanatory data before and after conversion, including their representations and items, are merely illustrative and not limiting. They can be arbitrarily adjusted according to the input explanatory condition information, attribute information items, and their settings. Specifically, the items of the referenced knowledge data and the descriptions of the prompts may be adjusted.

[0117] In summary, this embodiment makes it possible to provide functions that improve the efficiency of document creation work for support providers or improve the quality of their work. In particular, when providing explanations to support recipients based on document data in support services, it becomes possible to easily view, create, and refer to explanatory materials tailored to the support recipient. As a result, it becomes possible to not only improve the efficiency of creating explanatory materials but also to provide more appropriate explanations.

[0118] Furthermore, it is possible to configure the system to execute processing step by step using a generative model, thereby reducing the load on each individual process. In addition, since the data creation process can be understood sequentially, it becomes easier for users to grasp the process.

[0119] <Other Embodiments> In the above embodiment, it was shown that, in addition to text information, diagrams are generated as explanatory data. These diagrams may include not only explanatory images, but also, for example, character images or animations that reduce the psychological burden during the explanation or provide common topics, especially if the person being explained to is a preschooler. In other words, the explanatory data is not necessarily limited to the content to be explained, but may be configured to include information that can be used as a communication tool during the explanation.

[0120] Furthermore, the system may be configured to automatically switch the items, style, presentation, output format, presence or absence of images, and presence or absence of statistical information included in the generated explanatory data and the converted explanatory data, depending on the combination of values ​​of the explanatory condition information and attribute information.

[0121] In the embodiments described above, child abuse was used as an example of a support service, but the invention is not limited to this. The functions of the present invention are applicable to various fields and services in terms of analysis and the use and sharing of the information underlying it. For example, it may be applied to the analysis of child injury and accident response, maternal and child health, domestic violence (DV) response, sexual violence response, delinquency and crime response, developmental disability response, elderly welfare, disability welfare, delinquency and crime investigation, and harassment. Furthermore, it is not limited to government services, but may also be applied to services used by private companies and individuals.

[0122] Furthermore, in the present invention, the functions of one or more embodiments described above can also be realized by supplying a program or application to a system or device using a network or storage medium, and one or more processors in the computer of that system or device reading and executing the program.

[0123] In this specification, expressions such as "first" and "second" are used, but these are used merely to distinguish them from other elements and are not intended to be interpreted as limiting them to specific components. Therefore, these expressions may be appropriately reinterpreted depending on the configuration and aspects to which the present invention is applied.

[0124] Alternatively, it may be implemented by a circuit that performs one or more functions (for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array)).

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

[0126] Thus, the present invention is not limited to the embodiments described above. It is also intended and within the scope of protection to be provided for the combination of each configuration of the embodiments, as well as for modifications and applications by those skilled in the art based on the description in the specification and well-known technology.

[0127] As described above, the following matters are disclosed in this specification:

[0128] (Technology 1) An information processing system that generates explanatory materials tailored to the person being supported, An input unit that accepts document data input, A first generation unit generates first explanatory data that shows the contents of the document data, A first reception unit that accepts the designation of attribute information of the person to be supported from among predefined attribute information, A setting unit sets a first prompt for converting the first explanatory data to second explanatory data corresponding to the person being supported, in accordance with the attribute information; A second generation unit generates second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model, An output unit that generates and outputs explanatory materials including the second explanatory data, An information processing system having [a certain feature].

[0129] (Technology 2) A second reception unit that receives the designation of at least one of the chief complaint information indicating the condition of the person to be supported and scene information indicating the scene explaining the document data, A collection unit collects knowledge data from a knowledge database in response to the specifications received at the second reception unit, Equipped with, The information processing system according to Technical Reference 1, wherein the first generation unit generates the first explanatory data using the document data and the knowledge data as input to a large-scale language model.

[0130] (Technology 3) The information processing system described in Technology 2, wherein the collection unit uses RAG (Retrieval-Augmented Generation) to collect knowledge data corresponding to the chief complaint information and the scene information from the knowledge database.

[0131] (Technology 4) The system includes a display control unit that displays the second explanatory data and a screen configured to accept modification instructions for the second explanatory data, The setting unit sets a second prompt that includes a correction instruction received via the screen, The information processing system according to any one of the technologies 1 to 3, wherein the second generation unit regenerates the second explanatory data using the second prompt.

[0132] (Technology 5) The attribute information includes information categorized by age group, intellectual level, the role of the person receiving support in the event, gender, nationality, language, or native language. The information processing system according to any one of the technologies 1 to 4, wherein the setting unit sets the first prompt so as to switch at least one of the terms, vocabulary, grammar, expression mode, level of abstraction, and descriptive structure in the second descriptive data according to the value specified as attribute information.

[0133] (Technology 6) The setting unit sets the first prompt to include a description for generating a drawing that shows the contents of the first explanatory data in accordance with the attribute information, The second generation unit generates the drawing using the first prompt which includes the description, The output unit generates the explanatory materials, further including the drawings, according to any one of the information processing systems described in Technology 1 to Technology 5.

[0134] (Technology 7) A control method for an information processing system that generates explanatory materials tailored to the person being supported, The input process for receiving document data, A first generation step of generating first explanatory data that shows the contents of the document data, A first reception step in which the attribute information of the person to be supported is selected from a predetermined set of attribute information, A setting step of setting a first prompt for converting the first explanatory data to second explanatory data corresponding to the person being supported, in accordance with the attribute information, A second generation step of generating second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model, Output process for generating and outputting explanatory materials including the second explanatory data, A control method for an information processing system having [a certain feature].

[0135] (Technology 8) Computers, An input unit that accepts document data input, A first generation unit that generates first explanatory data indicating the content of the document data, The first reception desk accepts the designation of attribute information of the person to be supported from among the predefined attribute information. A setting unit sets a first prompt for converting the first explanatory data into second explanatory data corresponding to the person being supported, in accordance with the attribute information. A second generation unit generates the second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model. An output unit that generates and outputs explanatory materials including the second explanatory data, A program designed to function as such. [Industrial applicability]

[0136] The present invention is useful, for example, as a device, system, or method for improving operational efficiency, information sharing, and the quality of work performed by support workers at support sites in organizations and institutions that provide various support services. [Explanation of Symbols]

[0137] 1…Business support system 100…Server device 110... Control Unit 111...Data Reception Department 112...Data Management Department 113... Prompt settings section 114...Explanatory data generation unit 115...Data conversion unit 116...Knowledge Data Reference Section 117... Information Setting Department 118... Output data generation unit 119...Display Control Unit 120...Communication Control Unit 130... Communications Department 140...Storage section 141…Document Data Database 142…Generative Model DB 143…Prompt DB 144…Knowledge Data Database 145...Configuration Information DB 146...Explanatory data database 147…Output Data DB 200... User terminals 210... Control Unit 220...Storage section 230... Communications Department 240...Operation unit 250...Display section 260...External IF 300... Integration System NW...Network

Claims

1. An information processing system that generates explanatory materials tailored to the person being supported, An input unit that accepts document data input, A first generation unit generates first explanatory data that shows the contents of the document data, A first reception unit that accepts the designation of attribute information of the person to be supported from among predefined attribute information, A second reception unit that receives designation of at least one of the chief complaint information indicating the condition of the person to be supported and scene information indicating the scene explaining the document data, A collection unit collects knowledge data from a knowledge database in response to the specifications received at the second reception unit, A setting unit selects a prompt from among multiple prompts corresponding to the value specified as attribute information, for converting the first explanatory data into second explanatory data corresponding to the person being supported, and sets it as the first prompt. A second generation unit generates the second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model, An output unit that generates and outputs explanatory materials including the second explanatory data, It has, The first generation unit generates the first explanatory data using the document data and the knowledge data as input to a large-scale language model. The first reception unit is an information processing system that switches user-specifiable attribute information items or values ​​based on the content indicated by the document data.

2. The information processing system according to claim 1, wherein the collection unit uses RAG (Retrievable Augmented Generation) to collect knowledge data corresponding to the chief complaint information and the scene information from the knowledge database.

3. The system includes a display control unit that displays the second explanatory data and a screen configured to accept modification instructions for the second explanatory data, The setting unit sets a second prompt that includes a correction instruction received via the screen, The information processing system according to claim 1, wherein the second generation unit regenerates the second explanatory data using the second prompt.

4. The attribute information includes information categorized by age group, intellectual level, the role of the person receiving support in the event, gender, nationality, language, or native language. The information processing system according to claim 1, wherein the setting unit selects a prompt from the plurality of prompts and sets it as the first prompt so as to switch at least one of the terms, vocabulary, grammar, expression style, level of abstraction, and descriptive structure in the second descriptive data according to the value specified as attribute information.

5. The setting unit further includes in the first prompt a description for generating a drawing showing the contents of the first explanatory data according to the value specified as the attribute information, The second generation unit generates the drawing using the first prompt which includes the description, The information processing system according to claim 1, wherein the output unit generates the explanatory materials, further including the drawings.

6. A control method for an information processing system that generates explanatory materials tailored to a person receiving support, using computer software executed by a computer, The input process for receiving document data, A first generation step of generating first explanatory data that shows the contents of the document data, The first system accepts the designation of attribute information of the person to be supported from among the predefined attribute information. The reception process and A second reception step that receives the designation of at least one of the chief complaint information indicating the condition of the person to be supported and scene information indicating the scene describing the document data, A collection step in which knowledge data is collected from a knowledge database in response to the specifications received in the second reception step described above, A setting step of selecting a prompt from among multiple prompts corresponding to the value specified as attribute information, for converting the first explanatory data into second explanatory data corresponding to the person being supported, and setting it as the first prompt; A second generation step of generating second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model, Output process for generating and outputting explanatory materials including the second explanatory data, It has, In the first generation step, the document data and the knowledge data are used as input to a large-scale language model to generate the first explanatory data. A control method for an information processing system, in the first receiving step, which switches user-specifiable attribute information items or values ​​based on the content indicated by the document data.

7. Computers, An input unit that accepts document data input, A first generation unit generates first explanatory data that shows the contents of the document data, The first reception unit accepts the designation of attribute information of the person to be supported from among the predefined attribute information. A second reception unit that receives designation of at least one of the following: chief complaint information indicating the condition of the person to be supported and scene information indicating a scene explaining the document data. A collection unit that collects knowledge data from a knowledge database in response to the specifications received at the second reception unit. A setting unit selects a prompt from among multiple prompts corresponding to the value specified as attribute information, for converting the first explanatory data into second explanatory data corresponding to the person being supported, and sets it as the first prompt. A second generation unit generates the second explanatory data using the first explanatory data and the first prompt as input to a large-scale language model. An output unit that generates and outputs explanatory materials including the second explanatory data, To make it function as, The first generation unit generates the first explanatory data using the document data and the knowledge data as input to a large-scale language model. The first receiving unit is a program that switches user-specifiable attribute information items or values ​​based on the content indicated by the document data.

Images