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 summaries of information related to child support services comprises: an acquisition unit that acquires string information related to child support services; an acceptance unit that accepts summarization conditions for the string information; a generation unit that generates a summary of the string information that satisfies the summarization conditions by using the string information, the summarization conditions, and a pre-set prompt for summarizing the string information as input to a large-scale language model; and an output unit that outputs the generated summary of the string information.

Description

Technical Field

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

Background Art

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

[0003] In regional 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, in Patent Document 1, a technique for generating a document of investigation results or creating a summary using a generative AI model is disclosed.

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. The information to be included in the document varies depending on its purpose and use, requiring the compilation and summarization of information relevant to the support provided. However, this type of work places a heavy burden on support workers and also relies to the experience of the support workers themselves.

[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 a summary of information related to child support services, An acquisition unit that acquires string information related to child support services, A receiving unit that receives summarization conditions for the aforementioned string information, A generation unit generates a summary of the string information that satisfies the summarization conditions by using the string information, the summarization conditions, and a pre-set prompt for summarizing the string information as input to a large-scale language model, An output unit that outputs a summary of the generated string information, It holds.

[0008] Another embodiment of the present invention has the following configuration. That is, the control method for an information processing system that generates a summary of information related to child support services is: The acquisition process involves obtaining string information related to child support services, A receiving step for receiving summarization conditions for the aforementioned string information, A generation step of generating a summary of the string information that satisfies the summarization conditions by using the string information, the summarization conditions, and a pre-set prompt for summarizing the string information as input to a large-scale language model, An output step which outputs a summary of the generated string information, It holds.

[0009] Another embodiment of the present invention has the following configuration: namely, a program, Computers, Acquisition unit for acquiring string information related to child support services, A receiving unit that accepts summarization conditions for the aforementioned string information, A generation unit generates a summary of the string information that satisfies the summarization conditions by using the string information, the summarization conditions, and a pre-set prompt for summarizing the string information as input to a large-scale language model. Output unit that outputs a summary of the generated string information, 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 an example configuration of a business support system according to the first embodiment of the present invention. [Figure 2] Functional block diagram showing a server terminal according to the first embodiment of the present invention. [Figure 3] Functional block diagram showing a user terminal according to the first embodiment of the present invention. [Figure 4] An explanatory diagram illustrating the concept of summary processing according to the first embodiment of the present invention. [Figure 5A] This diagram shows an example of the configuration of a UI screen according to the first embodiment of the present invention. [Figure 5B] This diagram shows an example of the configuration of a UI screen according to the first embodiment of the present invention. [Figure 5C] This diagram shows an example of the configuration of a UI screen according to the first embodiment of the present invention. [Figure 5D]Example diagram showing a configuration example of a UI screen according to the first embodiment of the present invention [Figure 6A] Example diagram showing a configuration example of a UI screen according to the first embodiment of the present invention [Figure 6B] Example diagram showing a configuration example of a UI screen according to the first embodiment of the present invention [Figure 7] Flowchart of summary processing according to the 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. Note that 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 of the 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 duplicate descriptions of substantially the same configurations may be omitted.

[0013] First, in the embodiments for carrying out 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 according to the embodiments described below are not limited to being applied only to the child support service and may be applied to various fields and services. Also, depending on the fields and services to which they are applied, modifications, adjustments, expansions, etc. may be appropriately made.

[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 how it is handled defined based on their assigned duties and authority.

[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 and summarize appropriate information from a vast amount of data and create various documents when dealing with complex and diverse child abuse cases. These tasks require a high level of expertise and considerable effort, placing a heavy burden on individual staff members. In particular, there has been a lack of adequate functionality for creating situation-appropriate summaries in the field of child support. Therefore, this embodiment provides a work support function to alleviate the workload of the above tasks and enable more appropriate support to those receiving support.

[0019] [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.

[0020] 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; there may be multiple devices, and there may be servers with different roles, such as an authentication server and a database server.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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, for example, as a data reception unit 111, a data management unit 112, a theme information setting unit 113, a representation information setting unit 114, a prompt control unit 115, a knowledge data reference unit 116, a summary generation unit 117, a display control unit 118, an output data control unit 119, and a communication control unit 120.

[0026] 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).

[0027] 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.

[0028] The theme information setting unit 113 manages theme information that indicates multiple themes related to summarization. The theme information indicates the perspectives for summarization, and for each theme, elements to focus on when summarizing (vocabulary, terminology, expressions, etc.), structure, knowledge data, grammar, etc. are predetermined. Specific examples of theme information according to this embodiment will be described later.

[0029] The expression information setting unit 114 manages multiple expression information items related to summarization. The expression information indicates the content of expression used in summarization and is set to define the expression used in the summary. In this embodiment, the expression information is set based on the assumed age group of the person being supported. Specific examples of expression information will be described later.

[0030] The prompt control unit 115 controls and selects the prompts to be 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 theme information and expression information indicated by user instructions. Alternatively, predefined prompts may be used in combination. Furthermore, the prompt control unit 115 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.

[0031] The knowledge data reference unit 116 references knowledge data used in the summarization process according to this embodiment based on user instructions. In this embodiment, knowledge data is referenced from the registered knowledge database based on thematic information, representation information, etc., as information to be input to the generation model. For example, RAG (Retrieval-Augmented Generation) technology may be used to reference the knowledge data. 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.

[0032] The summary generation unit 117 receives various data and prompts as input to the large language model (LLM) obtained as a generative AI through the learning process, and outputs the desired summary data. Details of the input and output to the generative model according to this embodiment will be described later.

[0033] The display control unit 118 controls the display screen, including the summary generated by the summary generation unit 117. The display control unit 118 also displays a screen for receiving various instructions from the user. For example, the display control unit 118 may provide the user terminal 200 with UI (User Interface) screen data for display.

[0034] The output data generation unit 119 generates output data converted into an output format using the summary data generated by the summary generation unit 117. For example, the output data may be in file format or may be composed in a predetermined record format. More specifically, the output data may be report data in a predetermined format.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] Business Data DB141 manages various business data related to support services. For example, it may manage information about children who are receiving support and information about their related parties. It may also manage information about support staff, such as child welfare center staff.

[0039] The generation model DB142 manages the generation model as an LLM used when performing summary generation processing in the summary generation unit 117. The generation model holds a model that has been trained to a certain extent so that it can perform the processing according to this embodiment. Training processing may also be performed periodically.

[0040] The prompt DB 143 manages prompt data for configuring prompts used when the summary generation unit 117 performs summary generation processing. 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 that anticipates the summary 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.

[0041] 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.

[0042] (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.

[0043] (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.).

[0044] The Expression Information DB145 manages information related to expression, such as style, vocabulary, and terminology. In this embodiment, the vocabulary, terminology, and stylistic expressions (such as writing styles like kana and kanji, and annotations like furigana) that can be used in summarization are set in accordance with the age of the person being supported (for example, "preschooler," "lower elementary school student," "upper elementary school student," "junior high or high school student," etc.). In addition, settings that address restrictions and constraints on expression may be included, such as the use of passive or active expressions that take psychological effects into consideration, expressions that meet the disclosure requirements of documents including summaries, and expressions that take into account the trauma and impressions of people viewing the summaries. Based on this expression information, the expression of the summary data is adjusted. In this embodiment, age is used as an example, but it is not limited to this. For example, any classification such as gender, birthplace, or intellectual level may be used. The expression information managed in the Expression Information DB145 is referenced by the prompt control unit 114, the summary generation unit 117, etc., so that summarization is performed according to the expression information.

[0045] The theme information DB146 manages information related to themes for summarization. In this embodiment, themes corresponding to record documents (documents) that use summarization are used. Specifically, for input information related to child support, themes such as "overall summary," "records regarding the child's problematic (maladjusted) behaviors," "records regarding the child's condition," "records regarding the family's (including cohabitants) condition," "records regarding temporary protection," "records regarding the facts (including suspicions) of abuse," "records of dialogue with family and related organizations regarding the measures," "records of what the child says about their family," "records regarding expectations and anxieties about returning home," and "records regarding expectations and anxieties about daily life" may be used. The types of themes are not particularly limited and may be defined based on records from various perspectives such as the characteristics, thoughts, experiences, relationships with related parties, desires, and environment of the person being supported. These themes may be presented so that the user can select them. Each theme is pre-associated with terms, expressions, and knowledge data that should be referenced within the string information of the input information. Then, in order to generate summaries according to the theme, theme information managed in the theme information DB146 is referenced by the prompt control unit 114, knowledge data reference unit 116, summary generation unit 117, etc.

[0046] The summary data DB147 holds the summary data obtained as a result of the summary generation process performed by the summary generation unit 117.

[0047] The output data DB148 holds output data that has been converted to a predetermined output format using the generation results from the summary generation unit 117. The output data DB148 may also store the generation results from the summary generation unit 117 in association with the prompts and various data used during generation.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] [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.

[0054] Support staff, such as those at child welfare centers, specify information about the person being supported and the information that will form the basis of the summary data (summary source data 401). The summary source data 401 may be pre-registered in the business data DB 141, or it may be entered individually by the support staff. The summary source data 401 may contain sensitive information such as personal information.

[0055] Furthermore, when summarizing, the supporter specifies the summarization conditions 402 and the expression information 404. In this embodiment, the specifications for the summarization conditions 402 include thematic information and the degree of summarization (number of characters / compression ratio). The specifications for the expression information 404 include the age group of the person being supported. Specific examples of these specifications will be described later.

[0056] The system prepares knowledge data 403 and prompts 405 based on the specifications regarding the summary conditions 402 and representation information 404. The knowledge data is collected and prepared using RAG technology from the already registered knowledge data DB 144 (knowledge data 403). The prompts 405 are set and selected from a set of predefined prompts (prompts 405).

[0057] Then, the generative model 406 receives the source data 401, summarization conditions 402, knowledge data 403, representation information 404, and prompt 405 as input, causing it to output summary data 407. An example of summary data will be described later.

[0058] [Example of input / output data] Figures 5A to 5D show examples of the configuration of the UI screen 500 for data input of the summarization process according to this embodiment. Figures 6A to 6B show examples of the configuration of the UI screen 600 for data output of the summarization process according to this embodiment.

[0059] Figure 5A shows an example configuration of the UI screen 500 for instructing the summarization process. The data selection section 501 is for specifying the data that will be used as the source data for the summary. By pressing the reference button 502, a window (not shown) in which data can be specified is displayed. Data including the source data may then be specified through this window. The data type input section 503 specifies the type of data that indicates the content of the source data. Depending on the content of the data, for example, "interview record" or "survey record" may be specified in the data type input section 503. The items that can be selected and displayed in the data type input section 503 may be predetermined, and for example, they may be one of the conditions included in the summarization conditions 402 shown in Figure 4. The items selected in list 503 are displayed corresponding to the input area 504.

[0060] The input area 504 is an area for entering string information in a free-form input format. If data is specified in the data selection unit 501, the string contained in the specified data may be extracted by character recognition or the like and automatically displayed in the free-form input area 504.

[0061] The summary theme input unit 505 is an input unit for specifying a theme related to the summary processing. As shown in Figure 5B, the summary theme input unit 505 presents a list 511 in which predefined themes can be selected. In this embodiment, the themes "Overall summary," "Records concerning the child's problematic (maladjusted) behavior," "Records concerning the child's condition," "Records concerning the family's (including cohabitants) condition," "Records concerning temporary protection," and "Records concerning the facts (including suspected) of abuse" are shown in list 511 for selection. The themes shown for selection in the summary theme input unit 505 may be switched, for example, according to the data type specified in the data type input unit 503.

[0062] The summary setting input unit 506 is an input unit for specifying the number of characters or compression ratio of the summary. As shown in Figure 5C, the summary setting input unit 521 is presented as a list 521, allowing selection of predefined character counts and compression ratios. In this embodiment, the character count and compression ratios "within 1200 characters", "within 800 characters", "within 400 characters", "70%", "40%", and "10%" are shown in list 521 for selection. The character count and compression ratios shown here are examples, and other values ​​may be used. Furthermore, the character count and compression ratio may be specified as upper or lower limits. In addition, a configuration that allows numerical input instead of a list format may be used. Moreover, the user may be able to specify the units (such as "%") related to the character count and compression ratio.

[0063] The style setting input unit 507 is an input unit for specifying style settings corresponding to the expression information of the summary. As shown in Figure 5D, the style setting input unit 507 presents a list 531 in which style expressions corresponding to the age of the target recipient, which are predetermined, can be selected. In this embodiment, the style settings "None," "Preschool children," "Lower elementary school students," "Upper elementary school students," and "Junior and senior high school students" are shown in list 531 for selection. As mentioned above, the expression of the summary is not limited to those assumed to be for the age of the target recipient, and the style settings related to the expression may be arbitrarily defined.

[0064] The summary execution button 508 is a button used to instruct the system to execute a summary based on specified string information and settings. The close button 509 is a button used to close the UI screen 500.

[0065] Figure 6A shows an example configuration of a UI screen 600 for displaying the processing results of the summarization process. The summary theme display unit 601 shows the theme used in the summarization process, and displays the value specified in the summary theme input unit 505 of the UI screen 500 shown in Figure 5A. In addition, the summary theme display unit 601 is configured in a list format, similar to the summary theme input unit 505, and is configured so that a theme can be selected from the list when regenerating the summary.

[0066] The summary setting display unit 602 shows the number of characters or compression ratio used as the summary setting in the summarization process, and displays the value specified in the summary setting input unit 506 of the UI screen 500 shown in Figure 5A. In addition, the summary setting display unit 602 is configured in a list format, similar to the summary setting input unit 506, and is configured so that the summary setting can be selected from the list when regenerating the summary.

[0067] The style setting display unit 603 shows the style settings used in the summarization process, and displays the value specified in the style setting input unit 507 of the UI screen 500 shown in Figure 5A. In addition, the style setting display unit 603 is configured in a list format, similar to the style setting input unit 507, and is configured so that the summary setting can be selected from the list when regenerating the summary.

[0068] The summary result display unit 604 shows the results of the summarization process using the generation model 406, as shown in Figure 4. In this example, the summary conditions 402, knowledge data 403, expression information 404, and prompt 405 are set as input data based on the summary theme "Records concerning the state of family members (including cohabitants)", summary setting "within 800 characters", and writing style setting "not specified". Then, the source data 401 is input to the generation model 406 along with these, and summarization processing is performed on the source data 401.

[0069] The summary recording button 605 is a button for recording the results of the summarization process in association with various input data. The summary regeneration button 606 is a button for instructing the system to perform a summary using the same source data but with different settings. For example, by changing the values ​​of at least one of the summary theme display unit 601, the summary setting display unit 602, and the writing style setting display unit 603, and then pressing the summary regeneration button 606, the summarization process will be performed again. The back button 606 is a button for returning to the previous screen (for example, the UI screen 500 shown in Figure 5A). The close button 607 is a button for closing the UI screen 600.

[0070] Figure 6B shows examples of different summarization processing results on the UI screen 600. In this example, summarization conditions 402, knowledge data 403, expression information 404, and prompts 405 are set as input data based on the summarization theme "Records related to temporary protection", summarization setting "10%", and writing style setting "Preschool children". Along with these, the source data 401 is input to the generation model 406, and an example of the result of summarization processing performed on the source data 401 is shown on the summarization result display unit 604. As shown in Figures 6A and 6B, the theme, expression, and length of the summary change depending on the settings.

[0071] [Processing flow] Figure 7 is a flowchart showing the overall flow of the summary processing 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 processing entity is described here as the server device 100.

[0072] 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.

[0073] In step S701, the server device 100 receives string information that will be used as the source data for the summary. For example, the server device 100 displays the UI screen 500 shown in Figure 5A on the user terminal 200 and receives the string information through this screen.

[0074] In step S702, the server device 100 accepts the conditions related to the summary (hereinafter referred to as "summary conditions"). For example, the server device 100 accepts the settings of the summary conditions in the summary theme input section 505, the summary setting input section 506, and the writing style setting input section 507 of the UI screen 500 in Figure 5A.

[0075] In step S703, the server device 100 acquires knowledge data corresponding to the summarization conditions received in step S702. The information items and types of the knowledge data acquired here are defined according to the various parameters selected in the summarization theme input unit 505, the summarization setting input unit 506, and the writing style setting input unit 507. The acquired knowledge data is used in the generation model.

[0076] In step S704, the server device 100 acquires expression information corresponding to the summarization conditions received in step S702. The information items and types of expression information acquired here are defined in accordance with the various parameters selected in the summary theme input unit 505, the summary setting input unit 506, and the writing style setting input unit 507.

[0077] In step S705, the server device 100 generates and selects prompts to be input to the generation model 406 based on the various parameters selected in the summary theme input unit 505, the summary setting input unit 506, and the style setting input unit 507. The prompts here may be selected from a predetermined set, or a single prompt may be generated by combining them with the various information obtained in steps S703 and S704.

[0078] In step S706, the server device 100 inputs the various information and prompts received as input to the generation model 406, thereby generating a summary of the string information (summarization source data 401) received in step S701.

[0079] In step S707, the server device 100 displays a summary of the processing results from step S706. For example, the server device 100 presents the summary results by displaying a UI screen 600, as shown in Figure 6A, on the user terminal 200.

[0080] In step S708, the server device 100 determines whether or not it has received an instruction to regenerate the summary. For example, if any of the settings of the summary theme display unit 601, summary setting display unit 602, or writing style setting display unit 603 of the UI screen 600 shown in Figure 6A are changed and the summary regeneration button 606 is pressed, the server device 100 may determine that it has received an instruction to regenerate. If the instruction to regenerate has been received (step S708: YES), the server device 100 returns to step S703 and repeats the process. If the instruction to regenerate has not been received (step S708: NO), the server device 100 proceeds to step S709.

[0081] In step S709, the server device 100 determines whether or not it has received an instruction to record a summary. For example, when the summary recording button 605 on the UI screen 600 shown in Figure 6A is pressed, the server device 100 may determine that it has received an instruction to record a summary. If the instruction to record a summary has been received (step S709: YES), the server device 100 proceeds to step S710. On the other hand, if the instruction to record a summary has not been received (step S709: NO), this processing flow is terminated.

[0082] In step S710, the server device 100 stores the summarization processing result and the various information used as input for the summary in association. Then, this processing flow ends. When storing the summary, the server device 100 may accept a specification of the recording format (e.g., data format or report format) from the user and record it as output data. It may also be possible to combine multiple summary results into output data. For example, summaries of multiple records concerning a particular child may be combined into one output data. Alternatively, summaries of records concerning multiple children may be combined into one output data (such as ledger data).

[0083] In summary, this embodiment makes it possible to provide functions that improve the efficiency of document creation work for support providers or enhance the quality of their work. In particular, it makes it possible to generate summaries tailored to the purpose and use of the support provider. It also makes it possible to generate summaries that take into account the attributes and status of the person receiving support.

[0084] <Other Embodiments> 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.

[0085] 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.

[0086] 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)).

[0087] 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.

[0088] 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.

[0089] As described above, the following matters are disclosed in this specification:

[0090] (Technology 1) An information processing system that generates summaries of information related to child support services, An acquisition unit that acquires string information related to child support services, A receiving unit that receives summarization conditions for the aforementioned string information, A generation unit generates a summary of the string information that satisfies the summarization conditions by using the string information, the summarization conditions, and a pre-set prompt for summarizing the string information as input to a large-scale language model, An output unit that outputs a summary of the generated string information, An information processing system having

[0091] (Technology 2) The aforementioned summary conditions are configured to be selectable from a number of predetermined themes, as described in Technology 1, for the information processing system described in Technology 1.

[0092] (Technology 3) The information processing system described in Technology 2, wherein, for each of the aforementioned multiple themes, a focus element is defined from among the elements contained in the string information.

[0093] (Technology 4) The information items to be collected from the knowledge database are defined for each of the aforementioned multiple themes, It further includes a collection unit that collects information on information items corresponding to the theme from the aforementioned knowledge database, The information processing system according to Technology 2 or Technology 3, wherein the generation unit further generates a summary of the string information using the collected information.

[0094] (Technology 5) For each of the aforementioned themes, information is provided regarding the availability of expressions relating to style, vocabulary, and at least one of the modes of expression, including active or passive expressions. The information processing system according to any one of the technologies 2 to 4, wherein the generation unit further generates the summary based on information regarding the availability of the expression.

[0095] (Technology 6) The aforementioned multiple themes include at least one of the following: an overall summary, the problematic behavior of the person being supported, the state of the person being supported, the state of those involved with the person being supported, records of responses to the person being supported, records of events that occurred, and records of the relationships between the person being supported and those involved, as described in any of the technologies 2 to 5.

[0096] (Technology 7) The aforementioned summary conditions include the number of characters in the summary, The information processing system according to any one of the technologies 1 to 6, wherein the generation unit generates the summary with the number of characters as the upper limit.

[0097] (Technology 8) The aforementioned summary conditions include the style of the summary, The generation unit adjusts the expression of the summary based on the writing style, as described in any one of the information processing systems from Technology 1 to Technology 7.

[0098] (Technology 9) The information processing system described in Technology 8 is configured such that the style of the summary is predetermined according to multiple age groups corresponding to the target recipients, and can be selected from among these multiple age groups.

[0099] (Technology 10) A control method for an information processing system that generates summaries of information related to child support services, The acquisition process involves obtaining string information related to child support services, A receiving step for receiving summarization conditions for the aforementioned string information, A generation step of generating a summary of the string information that satisfies the summarization conditions by using the string information, the summarization conditions, and a pre-set prompt for summarizing the string information as input to a large-scale language model, An output step which outputs a summary of the generated string information, A control method having

[0100] (Technology 11) Computers, Acquisition unit for acquiring string information related to child support services, A receiving unit that accepts summarization conditions for the aforementioned string information, A generation unit generates a summary of the string information that satisfies the summarization conditions by using the string information, the summarization conditions, and a pre-set prompt for summarizing the string information as input to a large-scale language model. Output unit that outputs a summary of the generated string information, A program designed to function as such. [Industrial applicability]

[0101] 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]

[0102] 1…Business support system 100…Server device 110... Control Unit 111...Data Reception Department 112...Data Management Department 113... Theme Information Setting Section 114... Expression Information Setting Section 115...Prompt control unit 116...Knowledge Data Reference Section 117…Summary generator 118...Display Control Unit 119…Output Data Control Unit 120...Communication Control Unit 130... Communications Department 140...Storage section 141…Business Data Database 142…Generative Model DB 143…Prompt DB 144…Knowledge Data Database 145…Expression information DB 146... Theme Information Database 147…Summary Data DB 148…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 summaries of information related to child support services, An acquisition unit that acquires string information related to child support services, A receiving unit that receives values ​​for each of the multiple items as summary conditions for the string information via a screen configured to allow specifying values ​​for each of the multiple items, A setting unit sets a prompt to be input to a large-scale language model in order to summarize the string information, using a summarization condition indicated by the values ​​of each of the multiple items received by the reception unit and a predefined prompt format. A generation unit generates a summary of the string information that satisfies the summary conditions by using the string information, the summary conditions, and the prompt set in the setting unit as input to the large-scale language model, An output unit that outputs a summary of the generated string information, It has, The aforementioned summary conditions are configured to allow selection from a number of predetermined themes related to the aforementioned child support services. For each of the aforementioned multiple themes, a focus element is defined from among the elements contained in the string information, The aforementioned element of interest is an information processing system that includes at least one of vocabulary, terminology, or expression.

2. The information items to be collected from the knowledge database are defined for each of the aforementioned multiple themes, It further includes a collection unit that collects information on information items corresponding to the theme from the aforementioned knowledge database, The information processing system according to claim 1, wherein the generation unit further generates a summary of the string information using the collected information.

3. For each of the aforementioned themes, information is provided regarding the availability of expressions relating to style, vocabulary, and at least one of the modes of expression, including active or passive expressions. The information processing system according to claim 1, wherein the generation unit further generates the summary based on information regarding the availability of the expression.

4. The information processing system according to claim 1, wherein the aforementioned multiple themes include at least one of the following: an overall summary, the problematic behavior of the person being supported, the state of the person being supported, the state of those involved with the person being supported, records of responses to the person being supported, records of events that occurred, and records of the relationships between the person being supported and those involved.

5. The aforementioned summary conditions include the number of characters in the summary, The information processing system according to claim 1, wherein the generation unit generates the summary with the number of characters as the upper limit.

6. The aforementioned summary conditions include the style of the summary, The information processing system according to claim 1, wherein the generation unit adjusts the expression of the summary based on the writing style.

7. The information processing system according to claim 6, wherein the style of the summary is predetermined according to multiple age groups corresponding to the person to be supported, and is configured to be selectable from among the multiple age groups.

8. A control method for an information processing system that generates summaries of information related to child support services, The acquisition process involves obtaining string information related to child support services, A receiving step of receiving values ​​for each of the multiple items as summary conditions for the string information via a screen configured to allow specifying values ​​for each of the multiple items, A setting step involves setting a prompt to be input into a large-scale language model to summarize the string information, using the summarization conditions indicated by the values ​​of each of the multiple items received in the reception step, and a predefined prompt format. A generation step that generates a summary of the string information that satisfies the summary conditions by using the string information, the summary conditions, and the prompt set in the setting step as input to the large-scale language model, An output step which outputs a summary of the generated string information, It has, The aforementioned summary conditions are configured to allow selection from a number of predetermined themes related to the aforementioned child support services. For each of the aforementioned multiple themes, a focus element is defined from among the elements contained in the string information, The aforementioned element of interest is a control method comprising at least one of vocabulary, terminology, or expression.

9. Computers, Acquisition unit for acquiring string information related to child support services, A receiving unit that receives values ​​for each of the multiple items as summary conditions for the string information via a screen configured to allow specifying values ​​for each of the multiple items, A setting unit sets a prompt to be input to a large-scale language model in order to summarize the string information, using the summarization conditions indicated by the values ​​of each of the multiple items received by the reception unit and a predefined prompt format. A generation unit generates a summary of the string information that satisfies the summary conditions by using the string information, the summary conditions, and the prompt set in the setting unit as input to the large-scale language model. Output unit that outputs a summary of the generated string information, To make it function as, The aforementioned summary conditions are configured to allow selection from a number of predetermined themes related to the aforementioned child support services. For each of the aforementioned multiple themes, a focus element is defined from among the elements contained in the string information, The aforementioned element of interest is a program that includes at least one of the following: vocabulary, terminology, or expressions.

Images