Information processing method for assisting with child welfare consultation work, program, and information processing system

Abstract

[Problem] The purpose of the present invention is to achieve a method that makes it possible to reduce the burden on on-site staff, particularly by using a trained language model to generate sentences. [Solution] Provided is an information processing method that is for assisting with child welfare consultation work and that is provided by a server which is connected, via a network, to a user terminal of a user which is related to child welfare consultation, wherein a control unit of the server: receives, from the user terminal, at least input information including child identification information which identifies a child, access information which is for determining at least one of protection and assistance of the child, and investigation record information which is obtained by investigation; stores the input information in a storage unit of the server; and generates text data for instructing the generation of a summary sentence which is based at least on the child identification information, the access information, and the investigation record information that have been acquired from the storage unit.

Description

Information processing method, program, and information processing system for supporting child consultation services

[0001] The present invention relates to an information processing method, a program, and an information processing system for supporting child consultation services.

[0002] In the past, various efforts have been made by various parties concerned to assess the risk of child abuse and protect children from abuse. However, issues such as a shortage of on-site personnel and an increase in the number of child abuse cases have been raised.

[0003] Against this background, Patent Document 1, for example, discloses a technology for automating the assessment of abuse risk, which captures images of a child's body and automatically identifies signs of abuse based on the captured images.

[0004] Patent No. 6801902

[0005] Although automated technologies such as those disclosed in Patent Literature 1 for determining signs of abuse using images can be expected to reduce the burden on on-site personnel, measures to further reduce the burden are needed. Furthermore, these issues are not limited to information regarding child abuse exchanged between child consultation centers and local government agencies, but also apply to information related to public agencies such as municipalities and the national government (especially information related to social issues such as domestic violence, sexual violence, bullying, harassment, crime, delinquency, physical disabilities, mental disabilities, developmental disabilities, child poverty, and elder abuse, in areas related to food, clothing, shelter, and physical safety, and areas related to peace of mind such as discrimination and verbal abuse).

[0006] Therefore, the present invention aims to realize a method that can reduce the burden on on-site staff and provide support for investigations, assistance policies, support plans, etc. by generating sentences using a trained language model.

[0007] In one aspect of the present invention, there is provided an information processing method for supporting child consultation services, which is provided by a server connected via a network to user terminals of users related to child consultation services, wherein a control unit of the server accepts at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information from the user terminal, stores the input information in a memory unit of the server, and generates text data for instructing the generation of a summary sentence based at least on the child identification information, assessment information, and investigation record information obtained from the memory unit.

[0008] According to the present invention, in particular, by generating sentences using a trained language model, the burden on on-site personnel can be reduced.

[0009] 1 is a block diagram showing an information processing system according to a first embodiment of the present invention. FIG. 1 is a functional block diagram showing the server 100 of FIG. 1. FIG. 2 is a functional block diagram showing the user terminal 200 of FIG. 1. FIG. 3 is a diagram showing an example of child data stored in the server 100. FIG. 4 is a diagram showing an example of reception data stored in the server 100. FIG. 5 is a diagram showing an example of a checklist (front side) used when registering reception data. FIG. 6 is a diagram showing an example of a checklist (back side) used when registering reception data. FIG. 7 is a diagram showing an example of user data stored in the server 100. FIG. 8 is an example of a flowchart relating to an information processing method according to a first embodiment of the present invention. FIG. 9 is another example of a flowchart relating to an information processing method according to a first embodiment of the present invention. FIG. 10 is a diagram showing yet another example of a flowchart relating to an information processing method according to a first embodiment of the present invention. FIG. 11 is a diagram showing an example of a home screen of an application displayed on a user terminal. FIG. 12 is a diagram showing an example of a screen displayed on a user terminal for requesting a risk assessment evaluation of an application. FIG. 13 is a diagram showing an example of a screen displayed on a user terminal for registering an image of an application. FIG. 14 is a diagram showing an example of a screen displayed on a user terminal for checking changes in risk assessment items of an application. FIG. 15 is a diagram showing an example of a screen displayed on a user terminal for using a chat communication function of an application. FIG. 16 is a diagram showing an example of a screen displayed on a user terminal for outputting the results of a risk assessment evaluation of an application. 1 is a flowchart illustrating an example of a sentence generation process according to an information processing method according to a first embodiment of the present invention. FIG. 2 is a functional block diagram illustrating the server 100 of FIG.

[0010] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that the embodiments described below do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all of the components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, features shown in each embodiment can be applied to other embodiments as long as they are not mutually inconsistent.

[0011] (Embodiment 1) <Configuration> FIG. 1 is a block diagram showing a business support system (information processing system) according to a first embodiment of the present invention. This system 1 includes a user terminal 200 used by a user related to child consultation, such as a child consultation center employee; a child consultation record system 300 that records and manages information related to child consultation; and a sentence generation system 400 that generates sentences based on input text data using a trained language model. Note that all or part of the functions of the child consultation record system 300 may be provided on the server 100. If all functions are provided on the server 100, the child consultation record system 300 may be unnecessary in this system 1. Alternatively, all or part of the functions of the child consultation record system 300 may be implemented as functions of the user terminal 200, such as an application executed on the user terminal 200. Similarly, all or part of the functions of the sentence generation system 400 may be provided on the server 100. If all functions are provided on the server 100, the sentence generation system 400 may be unnecessary in this system 1. Alternatively, all or part of the functions of the sentence generation system 400 may be implemented as functions of the user terminal 200, such as an application executed on the user terminal 200.

[0012] The server 100 and the user terminal 200 are connected via a network NW. The network NW is configured by the Internet, an intranet, a wireless LAN (Local Area Network), a WAN (Wide Area Network), or the like.

[0013] The server 100 is a device that provides applications for supporting business efficiency to multiple user terminals 200A, 200B related to users of child consultation services, such as child consultation center staff, manages information registered from each of the multiple user terminals 200A, 200B, and provides, for example, evaluation results and research findings from risk assessment evaluations regarding the possibility of child (child) abuse based on the registered information.The server 100 may be, for example, a general-purpose computer such as a workstation or personal computer, or may be logically realized by cloud computing.In this embodiment, for convenience of explanation, one server is shown as an example, but the present invention is not limited to this, and multiple servers may be used, and the server may have servers with different roles, such as an authentication server and a database server.

[0014] As described above, the user terminals 200A and 200B are information processing devices such as personal computers or tablet terminals owned by users who are involved in child consultations, such as staff at child consultation centers, and who use applications provided by the server 100. However, they may also be configured as smartphones, mobile phones, PDAs, etc. For ease of explanation, the user terminals 200A and 200B will be collectively referred to as the user terminal 200 below.

[0015] The present system is also connected to a child consultation record system 300 via a network NW, allowing users using user terminals 200 to register various information related to their children, including child information, to the server 100 or the child consultation record system 300. The server 100 can send and receive information to and from the child consultation record system 300, enabling data integration. The child consultation record system 300 primarily functions to record child consultations and issue administrative documents, such as issuing child ID numbers and reception numbers related to children, issuing consultation tickets and temporary custody decision notices, managing family information and fees in conjunction with administrative information, and managing the progress of procedures. The present system, on the other hand, primarily functions to support communication with users and decision-making, allowing for the input, viewing, and sharing of records both inside and outside child consultation centers, chatting between child consultation center staff, registering and sharing photos of children, and simulating past temporary custody trends. As described above, the server 100 and the child consultation record system 300 are connected via the network NW, and data is shared between them using, for example, a QR code (registered trademark), a child number, or a reception number as a key, so that the user does not need to input and register information into both the server 100 and the child consultation record system 300; by registering information into one system, it is possible to synchronize with the other system. Note that, as described above, if the server is provided with all or part of the functions of the child consultation record system 300, and processing can be completed in the server 100, data sharing using a QR code (registered trademark), etc. may not be necessary.

[0016] The system is also connected to a text generation system 400 via a network NW, and a user using a user terminal 200 can input text data into the trained language model of the text generation system 400 via the user terminal 200 to generate text data corresponding to the text data. The text generation system 400 may use a large-scale language model such as ChatGPT to accept text data such as questions and requests in a chat format, input the data into a trained language model (e.g., a large-scale language model), and generate text data corresponding to the questions or requests (e.g., a summary based on a summary request and the original text, or an example based on a request for example). The trained language model may be, for example, a learning model trained using a large amount of data on the web as training data. In particular, the learning model may be an externally provided learning model. Furthermore, the provided learning model may be a learning model that has undergone additional training by a user or a server provider (i.e., an administrator) in a specialized field such as child consultation.

[0017] In this embodiment, system 1 is described as being configured such that each user uses a user terminal 200 to perform operations on server 100, but server 100 may also be configured as a standalone system, with the server itself equipped with the functionality for users to perform operations.

[0018] Fig. 2 is a functional block diagram of the server 100 of Fig. 1. The server 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0019] The communication unit 110 is a communication interface for communicating with the user terminal 200, the child consultation record system 300, and the text generation system 400 via the network NW, and communication is carried out using communication protocols such as TCP / IP (Transmission Control Protocol / Internet Protocol) and closed network protocols.

[0020] The storage unit 120 stores input data and programs for executing various control processes and functions in the control unit 130, and is composed of RAM (Random Access Memory), ROM (Read Only Memory), etc. The storage unit 120 also includes a child data storage unit 121 for storing various data related to users and children, a reception data storage unit 122 for storing various data related to reception, and a user data storage unit 123 for storing various data related to users. Furthermore, the storage unit 120 can also temporarily store data communicated with the user terminal 200, the child consultation record system 300, and the sentence generation system 400. A database (not shown) storing various data may be constructed outside the storage unit 120 or the server 100.

[0021] The control unit 130 controls the overall operation of the server 100 by executing programs stored in the storage unit 120, and is composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc. The functions of the control unit 130 include a reception unit 131 that receives input from the user terminal 200 or the child consultation record system 300, a data management unit 132 that refers to and processes various data, a risk assessment unit 133 that analyzes information input by the user and performs an assessment, and a sentence generation instruction unit 134. The reception unit 131, data management unit 132, risk assessment unit 133, and sentence generation instruction unit 134 are activated by programs stored in the storage unit 120 and executed by the server 100, which is a computer (electronic calculator).

[0022] The reception unit 131 receives instructions and various information from the user terminal 200 via the communication unit 110 when the user makes a predetermined input via a user interface such as a screen provided by the server 100 and displayed via a web browser or application on the user terminal 200. Alternatively, the reception unit 131 receives information from the child consultation record system 300 via the communication unit 110 in response to a request from the server 100 or the user terminal 200. Alternatively, the reception unit 131 transmits text data for instructing sentence generation (also referred to as "sentence generation instruction information") from the server 100 or the user terminal 200 to the sentence generation system 400, and receives sentence data generated by the sentence generation system 400 in response to the text data via the communication unit 110.

[0023] The data management unit 132 manages various data related to users, such as various user data, child data, reception data, and evaluation data, and performs predetermined processing such as registering and reading data from the corresponding data storage unit in the memory unit 120.

[0024] The risk assessment unit 133 performs a process of assessing the risk of child abuse based on information registered from the user terminal 200 (or the child consultation record system 300).

[0025] The sentence generation instruction unit 134 generates text data (sentence generation instruction information, including so-called prompts) for instructing the user to generate a sentence based at least on the child identification information, risk assessment information (described below), and investigation record information (described below) acquired from the memory unit 120 (e.g., the reception data storage unit 122). The generated text data is stored in the memory unit 120, linked at least to the child identification information (and further linked to input date and time information, a reception ID, etc.). The sentence for instructing the user to generate a sentence may be, for example, a summary of the risk assessment information and investigation record information associated with the child, enabling the automatic generation of various diagnostic documents, administrative documents, and documents to be submitted to judicial institutions in specified administrative formats. The sentence for instructing the user to generate a sentence may also be, for example, user support information (e.g., advice on what should be investigated, what should be considered, etc.) estimated from the risk assessment information and investigation record information associated with the child at one or more past points in time. In addition, the text data for instructing the generation of a sentence is not limited to child identification information, risk assessment information, and investigation record information, and any of these pieces of information may be deleted, or may include any of the information from the reception data described below.

[0026] Fig. 3 is a functional block diagram showing the user terminal 200 of Fig. 1. The user terminal 200 includes a communication unit 210, a display operation unit 220, a storage unit 230, a camera 240, and a control unit 250.

[0027] The communication unit 210 is a communication interface for communicating with the server 100 via the network NW, and communication is performed according to a communication protocol such as TCP / IP.

[0028] The display operation unit 220 is a user interface used by the user to input instructions and display text, images, etc. in accordance with input data from the control unit 250. If the user terminal 200 is configured as a personal computer, the display operation unit 220 is configured with a display, keyboard, and mouse, and if the user terminal 200 is configured as a smartphone or tablet terminal, the display operation unit 220 is configured with a touch panel, etc. This display operation unit 220 is started by a control program stored in the storage unit 230 and executed by the user terminal 200, which is a computer (electronic calculator). Via the display operation unit, the user can perform operations such as pressing keys on the keyboard in the case of a keyboard, moving a cursor with the mouse in the case of a mouse, and tapping, swiping, and pinching in the case of a touch panel in response to the aptitude test provided.

[0029] The storage unit 230 stores input data, programs for executing various control processes and functions in the control unit 250, and is composed of RAM, ROM, etc. The storage unit 230 also temporarily stores the contents of communication with the server 100.

[0030] The camera 240 has a function of capturing images of parts of the child's body, for example.

[0031] The control unit 250 controls the overall operation of the user terminal 200 by executing the programs stored in the storage unit 230, and is composed of a CPU, GPU, etc.

[0032] The server 100 may be configured to have the function of a display operation unit, in which case the user terminal 200 may not be included.

[0033] The functional configuration of the child consultation record system 300 is also substantially the same as that of the server 100 or the user terminal 200, and therefore a description thereof will be omitted.

[0034] FIG. 4 is a diagram showing an example of child data stored in the server 100. As shown in FIG.

[0035] The child data 1000 shown in FIG. 4 stores various data related to children. For ease of explanation, FIG. 4 shows an example of one child (a child identified by child ID "10001"), but information on multiple children can be stored. The various data related to children can include, for example, child information (child's name, address, contact information such as email address, gender, age, school name, grade, homeroom teacher name, commuting situation, tag information, etc.), guardian information (guardian's name, ID, address, contact information, gender, etc.), related party information (related party's name, ID, address, contact information, gender, etc.), family group information (family group name, ID, description of the group name, group members (including guardians in past marriages and common-law marriages, etc.)), related institution information (related institution name, ID, type (medical institution, police, educational institution, etc.), address, contact information), etc.

[0036] FIG. 5 is a diagram showing an example of reception data stored in the server 100. As shown in FIG.

[0037] The reception data 2000 shown in FIG. 5 stores various data related to reception. For ease of explanation, FIG. 5 shows an example of one reception (a reception identified by reception ID "20001"), but information on multiple receptions can be stored. Typically, receptions are registered in association with child data (e.g., a child ID) related to a registered child. However, depending on management purposes, receptions may be registered in association with any ID, such as parental information (e.g., a parental ID), related institution information (e.g., a related institution ID), or user ID (including the institution ID related to the institution to which the user belongs). In particular, in an emergency, reception processing may be performed first before registering child data related to the child. In such cases, the reception data may be managed in association with the user ID (institution ID), and after the child data is registered, the reception data may be registered in association with the child data (child ID). Note that although reception data is data received by the reception unit 131, once associated with child information, it may be managed as part of the associated information (e.g., part of the child information).

[0038] As various data related to reception, for example, basic information of reception (date and time of reception, person who made the entry, type of abuse (physical abuse, neglect, etc.), start date of response, etc.), risk assessment information regarding consideration of whether to carry out emergency dispatch or at least one of investigation and protection, information regarding whether or not a limit assessment applies (items such as a recurrence of a situation that raises doubts about the child's safety, canceling an interview, or pretending not to be home despite a visit), image information about the child, information about the child's wounds, information about the child's psychological diagnosis, information about the child's home situation, decision-making results and / or safety confirmation results. Results, items related to the response (whether temporary protection was implemented, whether temporary protection was lifted, whether measures were taken in child welfare institutions, etc., whether measures were lifted in child welfare institutions, whether measures were taken in foster parents, whether measures were lifted in foster parents, whether cooperation with related organizations was implemented, whether social resources or services were used, whether a monitoring system was established or used in the local government or community), the person who approved the survey record, etc., survey record information (survey date and time, survey title, minutes (survey results (facts)), information on the assessment, information on future responses, additional information obtained from the survey) The database can store information such as risk assessment information (information obtained through the survey), images of the child obtained during the survey, wound information on the child obtained during the survey, psychological evaluation information on the child obtained during the survey, information on the child's home situation obtained during the survey, the date and time of the next interview for the survey, the status in the survey completion dictionary, the safety scale at the time of survey completion (information on the child's safety input results in subjective numbers), response details, and the person who approved the survey record), evaluation information (information on past protection rates, the probability of severe abuse, recurrence rate, response time, information on the required investigation, past similar cases (information on the relevant abuse type among multiple abuse types), graphs (for example, radar charts (charts showing the balance of the probability of severe abuse, recurrence rate, response time, etc.), bar graphs, bubble charts, etc., which may be graphs for each reception date and time (input date and time) or graphs that can be compared chronologically according to the reception date and time (input date and time)), and recommendation information (recommendations and reference information for future responses). Note that at least some of the above data is accepted at the time of acceptance.

[0039] Risk assessment information includes, for example, input date and time information, serious confirmation item check information (for example, S-rank items shown in Figure 6, check information related to items for which it is determined that safety should be ensured if even one item is checked, and includes, for example, at least one of item check information for considering emergency dispatch or item check information for considering investigative protection), and item check information requiring investigation (for example, A-rank and B-rank items shown in Figure 7, check information related to items for which it is determined that safety should be considered if even one item is checked; in particular, check information related to items to be confirmed during an investigation).

[0040] A limit assessment is a promise made with a parent or guardian that includes a prior promise of compulsory intervention if the promise is broken. For example, the limit assessment includes items to check whether the parent or guardian cancels a scheduled interview without notice, refuses a home visit, or has injuries on the child, making it impossible to confirm the child's safety. Information regarding whether a limit assessment applies may be information indicating whether one or more of the above-mentioned limit assessment items apply. The limit assessment items may be commonly set, or may be optional items set by the user in association with at least one of the child information and guardian information.

[0041] 6 and 7 are diagrams showing examples of check sheets used when registering reception data.

[0042] The checklist includes, for example, a checklist, as shown in Figures 6 and 7. The checklist is divided into three major categories: serious items (S-rank items) to be checked before determining whether temporary protection (notification / referral) is necessary; A-rank items to be investigated before determining whether temporary protection (notification / referral) is necessary; and B-rank items to be investigated before the assistance policy meeting. The S-rank items are further divided into intermediate categories: items related to severe physical abuse, items related to severe neglect, items related to suspected sexual abuse, and items related to severe other abuse. The intermediate categories are ultimately divided into 10 to 20 check items. For example, child consultation center staff members check each check item for three points: suspicion before the investigation, suspicion after the investigation, and confirmation of the relevant information through the investigation. Furthermore, for example, the checklist includes a column for child consultation center staff members to record their decision regarding temporary protection of a child and the reasons for their decision. Additionally, for example, the checklist includes a column for entering information corresponding to the reception data.

[0043] FIG. 8 is a diagram showing an example of user data stored in the server 100. As shown in FIG.

[0044] The user data 3000 shown in FIG. 8 stores various data related to users. For ease of explanation, FIG. 4 shows an example of one user (identified by user ID "30001"), but information on multiple users can be stored. The various data related to users can include, for example, basic information about the user (contact information such as user name, address, email address, or phone number, affiliation information, job title, access permission information, etc.), child information related to the user (child IDs corresponding to or associated with the user, child IDs linked to accepted child information, child IDs linked to provided child information, etc., particularly list information), etc. Note that the user data may include a user ID (account) registered for each employee or other affiliated person at a user institution. Alternatively, or in addition, a common user ID (account) may be registered for each user institution.

[0045] <Processing Flow> The processing flow of the information processing method executed by the information processing system 1 of this embodiment will be described with reference to Fig. 9. This is an example of a flowchart relating to the information processing method according to the first embodiment of the present invention.

[0046] To use the system 1, a user (e.g., a child consultation center employee or other child consultation-related user) accesses the server 100 using a web browser or application on the user terminal 200. If using the service for the first time, the user registers basic information in the user data 3000 and obtains a user account. If a user account has already been obtained, the user can use the service by logging in after completing a predetermined authentication process, such as entering an ID and password. After this authentication, a predetermined user interface screen is displayed via a website, application, or the like, and the process proceeds to step S101 shown in FIG. 9 . FIG. 12 shows an example of the application home screen displayed on the user terminal 200. The user can select the registration menu on this screen to perform the registration process described below. FIG. 12 displays a list of registered child data, as well as corresponding status information, update date information, rating information, and payment provider information.

[0047] First, in step S101, the reception unit 131 of the control unit 130 of the server 100 receives registration of basic information about a child, such as child information, from the user terminal 200 via the communication unit 110. The data management unit 132 of the control unit 130 of the server 100 stores the received basic information in the child data storage unit 121 of the memory unit 120 as child data 1000, in association with the child ID. Here, if the user has registered the basic information in the child consultation record system 300, the user can import the basic information registered in the child consultation record system 300 into an application provided by the server 100 by reading a QR code (registered trademark) with the camera built into the user terminal 200 and entering a number, such as a child number, on the displayed screen.

[0048] As shown in FIG. 10, the reception unit 131 receives, in no particular order, the registration of basic information, child information related to the child, such as the child's name, address, contact information such as an email address, gender, age, school name, grade, teacher's name, commuting situation, tag information, etc. (step S201); guardian information related to the guardian, such as the guardian's name, ID, address, contact information, gender, etc. (step S202); related party information related to the child, such as the name, ID, address, contact information, gender, etc. of related parties such as uncles, aunts, friends of the child's older brother, and the mother's boyfriend / girlfriend (step S203); family group information related to the family group, such as the family group name, ID, description of the group name, and group members (including children, siblings, past marital relationships, and guardians in common-law marriages) (step S204); and related institution information related to the related institutions, such as the related institution's name, ID, type (medical institution, police, educational institution, etc.), address, contact information, etc. (step S205).

[0049] Next, in step S102, the reception unit 131 accepts registration of reception information from the user terminal 200. First, the user inputs reception data, such as basic reception information (e.g., type of abuse (physical abuse, neglect, etc.), start date and time of response, etc.), on an application screen displayed on the user terminal 200. The data management unit 132 of the control unit 130 of the server 100 stores the received reception data in the reception data storage unit 122 of the memory unit 120 as reception data 2000, associated with a reception ID. Here, if the user has registered the reception information in the child consultation record system 300, the user can import the reception data registered in the child consultation record system 300 into the application provided by the server 100 by performing a predetermined read / write operation on the user terminal 200 (e.g., reading a QR code (registered trademark) with the camera built into the user terminal 200, entering a number such as a child number on the displayed screen, or sending a child data read request from the server 100 or the user terminal 200 to the child consultation record system 300).

[0050] As shown in FIG. 11, in association with the reception information, the reception unit 131 accepts, in no particular order, from the user terminal 200, registration of investigation record information such as the date and time of response, investigation title, minutes (investigation results (facts)), assessment, future response, etc. (step S301); accepts registration of child image-related information such as image information of the child and / or information on the child's wound, psychological diagnosis information of the child, and information on the child's home situation (step S302); subsequently, accepts registration of risk assessment information (information obtained before the investigation or information obtained by the investigation) (step S303); and also accepts input information entered by multiple users via a chat application (step S304). Furthermore, the reception unit 131 can generate a sentence using the sentence generation system 400 based on the child identification information, risk assessment information, investigation record information, etc. obtained from the memory unit 120 (step S305). The data management unit 132 of the control unit 130 of the server 100 stores the received basic information in the reception data storage unit 122 of the storage unit 120 as reception data 2000 in association with the reception ID.

[0051] Here, the registration of the above investigation record information is assumed to be an operation performed by staff within the child consultation center based on information obtained from staff working outside the center, the registration of the above child image related information and the registration of the above risk assessment information are assumed to be operations performed by staff working outside the center to check the safety of children, and the above chat communication is assumed to be an operation performed by staff working outside the center to report the investigation results and confirm the response measures sent by staff working inside the center, and so on.A series of registered information may be entered and accepted by multiple staff members both inside and outside the center.

[0052] FIG. 14 shows an example of an image registration screen. On the image registration screen, the user imports an image (e.g., an image captured with a built-in camera in the user terminal 200 or an image captured with a digital camera, smartphone, or other mobile device and then saved in the user terminal 200) and selects the image type, such as wound, psychological diagnosis, or home condition. If wound is selected as the image type, the user can further select the child's body part related to the wound, and also select wound / fracture type (e.g., scar, bruise, bite mark, burn, hair loss, bloodshot eye, etc.), and further select details of the wound / fracture from a list (e.g., discoloration, bleeding, swelling, sore, old wound, keloid, multiple or mixed lesions, deformity / enlargement / loss, etc.). Examples of images related to psychological diagnosis include photographs of drawings drawn by the child or images of developmental characteristic findings from a medical institution. Examples of images related to home condition include the condition of the room (e.g., the state of trash) or the household items that caused the wound (e.g., a photograph of the stairs in a home if there is testimony that the child fell down the stairs). In addition to these, any image related to the child is acceptable, and if the cause of the injury is outside the home (e.g., a park or school), the image may be selected and saved separately as an image related to the relevant facility.

[0053] An example of a chat communication screen is shown in Fig. 16. When a user selects an icon for using chat communication displayed at the top of the application screen, a list of individuals or group names with whom to conduct chat communication is displayed, and by selecting each individual or group name, chat communication can be conducted between users.

[0054] Here, to input risk assessment information, the user can select the risk assessment information recording menu on the reception information input screen, for example, as shown in Figure 13, and select the risk assessment information registration form. Specific examples of the information accepted in the risk assessment information registration form (various data related to the above-mentioned acceptance) include: 1) acceptance date and time (enter the date the risk assessment was conducted, etc.), 2) inputter (select the inputter), 3) information at the time of notification acceptance (enter or select the information at the time of notification acceptance), 4) emergency dispatch (select the appropriate risk assessment item for considering emergency dispatch), 5) consideration of investigative protection (select the risk assessment item for considering investigative protection), 6) limit assessment applicable (check whether limit assessment is applicable), 7) image attachment (register images of "wound," "psychological diagnosis," "home situation," and "other." In the case of a wound, also enter the part of the body and the nature of the injury), 8) decision-making, safety confirmation (select the decision-making result. Based on the entered information, it is possible to check simulation results such as recurrence rate, probability of being classified as severe abuse, and number of days to respond, as well as past similar cases), 9) action items (select the action taken and enter the date and time of the action), 10) approver (set the approver for the investigation record). The registration form may also have a function for copying at least a portion of previously registered content (e.g., by selecting the child ID associated with the risk assessment information to be copied and generating a copy). As shown in the example screen of Figure 15, a user can select the "Risk Assessment History" menu to display risk assessment information for at least a portion of the items included in the risk assessment information (e.g., items related to the consideration of whether to perform an emergency dispatch or investigation and protection) based on at least date and time information, allowing the user to check the update information for each item of each child's risk assessment information in chronological order (i.e., check the history). This can be achieved, for example, by registering the information in association with date and time information and the child ID.When inputting risk assessment information, the user may refer to the check sheets exemplified in Figures 6 and 7 and input the items as assessment items via an application on the user terminal 200, or the input may be received by displaying a user interface screen on the application where items at least partially identical or similar to the check sheet can be input as an input form, or the check contents may be automatically input by image analysis of a check sheet image taken by the camera 240 of the user terminal 200. In addition, it may be possible to change the contents of at least some of the assessment items (for example, check or uncheck) on a screen displaying the changes in risk assessment information.

[0055] 9, the risk assessment unit 133 of the control unit 130 performs a risk assessment of the possibility of child abuse based on the registered basic information of the child and the reception data (particularly the risk assessment information) (i.e., generates assessment data). The generated assessment data may be linked to the reception ID and stored as reception data. The risk assessment unit 133 may, for example, input information such as past basic information about the child (age, sex, address (city / town / village)), reception information (type of abuse, reception time, reception category (new, re-notification, re-reception) and risk assessment information associated with the reception information (reception route, main abuser, applicability of each item of risk assessment), information on whether or not the child is subject to limit assessment, image information about the child, information about the child's wounds, psychological diagnosis information about the child, information on the child's home situation, decision-making result information and / or safety confirmation result information, items related to the implementation of the response (whether temporary protection was implemented, whether temporary protection was lifted, whether measures were taken to place the child in a child welfare institution, etc., whether measures were lifted to place the child in a child welfare institution, etc., whether measures were taken to place the child in a foster parent, whether measures were lifted to place the child in a foster parent, whether cooperation with related organizations was implemented, whether social resources or services were used, whether or not the child was provided with a foster parent, whether or not the child was provided with a foster parent, whether or not cooperation with related organizations was implemented ... the child was provided with a foster parent, whether or not the child was provided with a foster parent, whether or not the child was provided with a foster parent, whether or not the child When some or all of the information is entered, the system displays the past protection rate (an indicator of the tendency for children to be temporarily protected), past similar cases (classification of abuse into multiple types, and the characteristics of the type that this case most closely resembles), and the investigation record information (survey date and time, survey title, minutes of meeting (survey results (facts)), additional information obtained through the investigation (risk assessment information (information obtained through the investigation), images of the child obtained during the investigation, information on the child's wounds obtained during the investigation, psychological diagnosis information of the child obtained during the investigation and information on the child's home situation obtained during the investigation, date and time of the next interview for the investigation, status at the end of the investigation, safety scale at the end of the investigation (information on the safety of children entered as a subjective number), details of the response, etc.).The evaluation data (output information) may be generated using a risk assessment learning model (e.g., a learning model created by learning for each indicator or a common learning model) that outputs some or all of information such as the probability of severe abuse, the recurrence rate and response time, and the preventive effect of intervention or support, or a growth prediction model (e.g., a learning model that shows growth predictions learned based on height or weight measurement information for a specified number of people, measurement timing information (e.g., the number of days since birth), and basic information of the measurement subject (e.g., age (including months), gender, address, nationality, presence or absence of illness, and / or presence or absence of abuse), and may be a learning model created by learning for each item of basic information (e.g., by age group, gender, etc.) or a common learning model). The learning model may be previously trained as training data by extracting at least some of the input information and result information corresponding to the output information from past data, and may be stored in the storage unit 120 or an external server. The more types of input information included in the training data, the more precise the output information (such as the probability of serious abuse) can be. As another example, the risk assessment unit 133 may extract similar past cases based on a combination of some or all of the input information (particularly risk assessment information), and calculate statistical values ​​from the results of the extracted past cases to generate some or all of the output information. Note that these various types of information and methods for generating evaluation data are merely examples and are not limited to these. Furthermore, the risk assessment unit 133 may generate evaluation data by further referencing, for example, at least one of investigation record information and photographic information as the accepted data referenced for evaluation.

[0056] Next, in step S104, the risk assessment unit 133 transmits the output information generated in the above step to the user terminal 200, and the output information is displayed in a predetermined format on the user interface screen of the application on the user terminal 200.

[0057] Figure 17 shows an example screen displayed on a user terminal for outputting the risk assessment results of a business support application. By selecting the "Simulation" tab on the application's personal page screen displayed on the user terminal 200, a radar chart showing case characteristics based on three indicators: past protection rate, recurrence probability, response time, and severity (probability of severe abuse), as shown in Figure 17, and a screen visualizing past similar cases, is displayed. A high value for the past protection rate indicates a tendency for similar cases to be temporarily protected in the past, helping users determine the urgency of whether to temporarily protect them. The radar chart also represents a balance between severity (the probability of falling into a category defined as a severe case (e.g., 24 patterns) out of multiple abuse categories (e.g., 36 patterns)), recurrence rate (probability of recurrence in the corresponding group of similar cases), and response time (the number of days required to close the corresponding group of cases). A larger area on the radar chart indicates characteristics such as severeness and a high recurrence rate, and a tendency for cases to take longer to close. For past similar cases, past cases are classified into multiple types (e.g., 36 types) and the characteristics of the pattern that most closely matches the current case are displayed. If there are past cases that fit the same pattern, past case records are displayed. In this example, Case 47 is displayed as a "Re-admitted Physical Abuse Case." This case is understood to have been frequently reported by municipalities, with 30% of cases involving head, face, and abdominal injuries, 27% showing signs of ongoing abuse, and 7% of cases involving witnessing violence by the reporter and difficulty communicating with the guardian, a pattern seen in 5.2% of past cases. By reviewing past case records, users can gain insights into how the case may evolve. In addition to the example shown, evaluation data may be generated and displayed, such as the extent (or type) of concurrent serious abuse based on the severity of the relevant condition. Based on information on the responses to similar cases, recommendations may also be presented, such as what to investigate first, what type of support to provide, and whether to collaborate with relevant organizations.

[0058] Referring to FIG. 18 , the flow of the sentence generation process of the information processing method executed by the information processing system 1 of this embodiment will be described. First, the sentence generation instruction unit 134 generates text data (sentence generation instruction information) for instructing the generation of a sentence based on reception information, such as child identification information, risk assessment information, and investigation record information, acquired from the storage unit 120 (e.g., the reception data storage unit 122) (step S401). A specific example of the text data could be, for example, "Please summarize the following information (1) to (4): (1) child information (e.g., child identification information), (2) reception information (reception identification information), (3) risk assessment item information (selection information such as applicable, suspected, not applicable, unknown), and (4) investigation record information (e.g., child's statement: "My mother's boyfriend hit me." Mother: "(silence)." Common-law husband: "I don't know," etc.)." Other specific examples of the text data could be, for example, "The record of the first interview is '...'. The record of the X+1th interview is '...'. The record of the X+2nd interview is '...'." The prompt may be, for example, "Based on this information, please tell me what points should be investigated and what should be considered." Next, the text generation instruction unit 134 transmits the generated text data (text generation instruction information) to the text generation system 400 via the communication unit 110 (step S402). Next, the reception unit 131 receives the text data created by the text generation system 400 via the communication unit 110, associates it with at least the child identification information (and further associates it with input date and time information, a reception ID, etc.), and stores it in the storage unit 120 (step S403). Next, the data management unit 132 transmits output information including the received text data to the user terminal 200, and the output information is displayed in a predetermined format on the user interface screen of the application on the user terminal 200.

[0059] In addition, the control unit 130 may further include a correction unit that corrects the text data received from the text generation system 400 via the user terminal 200, and the text data corrected by the correction unit may be linked to child information and stored in the memory unit 120.

[0060] The control unit 130 also includes a document data generation unit (not shown) that reads format data from the storage unit 120, constituting a predetermined format (e.g., a document format for government submission, such as various diagnostic documents and administrative documents designated by the government, or documents to be submitted to judicial institutions (e.g., explanatory materials)), and inputs text data received from the text generation system 400 via the user terminal 200 into the appropriate fields of the format data as input data. This enables the automatic generation of various document data (e.g., document data for government submission). The generated document data may be linked to at least the child's identification information (and may also be linked to input date and time information, a reception ID, etc.) and stored in the storage unit 120. The document data can then be transmitted over a network or printed, thereby reducing the burden of document submission.

[0061] 19 is a functional block diagram of a server 100 provided in a business support system (information processing system) according to a second embodiment of the present invention. Note that, hereinafter, detailed description of the same configuration as in the first embodiment will be omitted, and it is assumed that the same or similar functions are provided.

[0062] The control unit 130 in the second embodiment further includes a needs assessment unit 135. The needs assessment unit 135 may be provided together with the risk assessment unit 133, or may be provided instead of the risk assessment unit 133. Hereinafter, the risk assessment unit 133 and the needs assessment unit 135 may be collectively referred to as the "assessment unit."

[0063] In the first embodiment, risk assessment information was accepted, but in the second embodiment, needs assessment information is accepted instead of or in addition to the risk assessment information. Like the risk assessment information, the needs assessment information is linked at least to the child identification information (and further linked to input date and time information, reception ID, etc.) and stored in the storage unit 120. Note that, hereinafter, risk assessment information and needs assessment information may be collectively referred to as "assessment information."

[0064] As described above, risk assessment information is information used to consider or determine emergency deployment or protection (e.g., temporary protection, investigative protection, etc.). Needs assessment information, like risk assessment information, is information linked to children, but it is information regarding the support sought by children and / or those related to the child (e.g., family members or related organizations). Support may involve assistance from others in resolving problems that are difficult for the recipient to solve on their own, such as consultation support, lifestyle support, childcare support, financial assistance (public assistance), employment support, school support, medical support, psychological support, or support that acts as a bridge between the recipient and organizations providing such support. More specifically, it may include, for example, financial assistance, nursery school enrollment, support for developmental disabilities, or enhancing the strengths that allow the recipient to successfully cope with matters related to the child's safety. Note that risk assessment information is not limited to emergency deployment or protection, but may also apply to interventions in general. Intervention refers to acts of interference by others that aim to bring about specific change or transformation in the subject, such as (1) acts of separating children from their guardians (caregivers), or children from parties other than their guardians, such as referral to a child consultation center or local government, temporary protection, various investigations such as visits and interviews, admission to a child welfare institution, or arrest and detention of an abuser; (2) acts that directly improve the child's upbringing or upbringing environment, including food, clothing, and shelter, such as lifestyle guidance, parenting guidance, and health guidance; (3) medical measures (such as prescribing medication) or psychotherapy to improve or alleviate physical and mental challenges (such as illness or disability) faced by individual children or guardians (caregivers); and (4) food support such as welfare assistance and children's cafeterias for those in poverty or who have lost their jobs.

[0065] The needs assessment information includes, for example, input date and time information, needs item check information (check items for estimating the support required by the child or at least one person related to the child, which may be items extracted in advance by analyzing past support data from the child consultation record system 300 or the like. For example, it may be in the form of a checklist, as in Figures 6 and 7 of the risk assessment information), or user-entered information (for example, it may be information extracted from free-form entries entered by the user, or it may be information extracted from presented entry items classified according to specified support).

[0066] The needs assessment unit 135 performs a needs assessment regarding the support desired by the child and / or persons related to the child based on the registered basic information of the child and reception data (especially the needs assessment information) (i.e., generates assessment data regarding each expected support). The generated assessment data may be stored as reception data linked to a reception ID. The needs assessment unit 135 receives, as input information, for example, basic information about the child in the past (age, sex, address (city / town / village)), reception information (type of abuse, reception time, reception category (new, re-notification, re-reception) and needs assessment information associated with the reception information (reception route, main abuser, applicability to each item of needs assessment, etc.), information on whether or not the child is eligible for limit assessment, image information about the child, wound information about the child, psychological diagnosis information about the child, information on the child's home situation, decision-making result information and / or safety confirmation result information, relevant information on items related to response implementation (whether temporary protection was implemented, whether temporary protection was lifted, whether placement in a child welfare institution or the like was implemented, whether placement in a child welfare institution or the like was lifted, whether placement in a foster parent was implemented, whether placement in a foster parent was lifted, whether collaboration with related organizations was implemented, whether social resources or services were used, whether a monitoring system in a local government or local community was established or used), information related to assessment, etc. When some or all of the following information is input, such as the current case, information about future responses, and investigation record information (survey date and time, survey title, minutes (survey results (facts), additional information obtained by the investigation (risk assessment information (information obtained by the investigation), images of the child obtained during the investigation, information about the child's wounds obtained during the investigation, information about the child's psychological diagnosis obtained during the investigation and information about the child's home situation obtained during the investigation, date and time of the next interview for the investigation, status at the time of completion of the investigation, safety scale at the time of completion of the investigation (information on the child's safety input in subjective numerical values), response details, etc.), evaluation data (output information) may be generated using a needs assessment learning model that outputs some or all of the following information: similar past cases (abuse is classified into multiple types, and the characteristics of the type to which the current case most closely resembles are displayed; if there are past cases that belong to the same type, the past case records are displayed), and the recommendation rate for each support based on the current case and similar cases.The learning model may be pre-trained as training data by extracting from past data at least a portion of the input information and result information corresponding to the output information, and may be stored in the storage unit 120 or an external server. The training data may include more types of input information than the input information described above, resulting in more precise output information. As another example, the needs assessment unit 135 may extract similar past cases based on a combination of some or all of the input information (especially needs assessment information), calculate statistics from the results of the extracted past cases, and generate some or all of the output information. Note that these various types of information and methods for generating evaluation data are merely examples and are not limited thereto. Furthermore, the needs assessment unit 135 may generate evaluation data by further referencing, for example, at least one of survey record information and photograph information as accepted data referenced for evaluation.

[0067] The needs assessment unit 135 then transmits the generated output information (assessment data) to the user terminal 200, and displays the output information in a predetermined format on the user interface screen of the application on the user terminal 200. The text generation instruction unit 134 then generates text data (text generation instruction information) for instructing the generation of a text based at least on the child identification information, assessment information (at least one of risk assessment information and needs assessment information), and survey record information (described below) acquired from the memory unit 120 (e.g., the reception data storage unit 122). The generated text data is linked at least to the child identification information (and further linked to input date and time information, a reception ID, etc.) and stored in the memory unit 120.

[0068] As described above, according to this embodiment, the burden on on-site personnel can be reduced, particularly by generating sentences using a trained language model.

[0069] While information regarding child abuse exchanged between child consultation centers and various local government agencies has been explained as an example, any information can be targeted, and is not limited to this. In particular, information exchanged between public agencies such as municipalities and the national government (particularly information related to social issues such as domestic violence, sexual violence, bullying, harassment, crime, delinquency, physical disabilities, mental disabilities, developmental disabilities, child poverty, and elder abuse, in areas related to food, clothing, shelter, and physical safety, and areas related to peace of mind such as discrimination and verbal abuse) can be targeted, and the configuration can be such that corresponding information is managed according to the target user. For example, (1) between public health centers and maternal and child health centers, between public health centers and maternal and child health centers, between public health centers and maternal and child health centers, between public health centers, maternal and child health centers and local governments, etc., information on children, family members, childcare stress in families, childcare services used, etc. collected at public health centers and maternal and child health centers, (2) between domestic violence victim centers and between domestic violence victim centers and local governments, etc., information on domestic violence facts regarding perpetrators, victims, and / or bystanders obtained at domestic violence victim centers, (3) between welfare centers and between welfare centers and local governments, etc., information on disabilities and public assistance obtained by staff, etc. (4) between probation offices, or between probation offices and local governments, etc., investigation record information on crimes and investigation record information on trials obtained by probationers, and may be used to estimate various indicators based on the relevant survey items in each survey (such as the probability of being involved in the occurrence (including reoccurrence) of at least one of domestic violence, sexual violence, bullying, harassment, crime, delinquency, child poverty, and elder abuse, or the occurrence (including reoccurrence) of physical or mental disabilities that may arise secondarily from these).

[0070] The details of the embodiments of the present invention will be listed again below. An information processing method, a program, and an information processing system according to the embodiments of the present invention have the following configuration: [Item 1] An information processing method for supporting child consultation services, provided by a server connected via a network to a user terminal of a user associated with child consultation, wherein a control unit of the server receives, from the user terminal, at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation, as input information, stores the input information in a memory unit of the server, and generates text data for instructing the generation of a summary sentence based at least on the child identification information, the assessment information, and the investigation record information obtained from the memory unit. [Item 2] An information processing method for supporting child consultation services, provided by a server connected via a network to the user terminal of a user related to child consultation, wherein the control unit of the server receives, from the user terminal, at least child identification information for identifying the child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by investigation as input information, stores the input information in a memory unit of the server, and generates text data for instructing the generation of user support information estimated from the assessment information and the investigation record information at one or more points in the past linked to the child identification information obtained from the memory unit. [Item 3] A program that executes an information processing method for supporting child consultation services, provided by a server connected via a network to the user terminal of a user related to child consultation, wherein the control unit of the server receives, from the user terminal, at least child identification information that identifies a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information, stores the input information in a memory unit of the server, and generates text data for instructing the generation of a summary sentence based at least on the child identification information, assessment information, and investigation record information obtained from the memory unit.[Item 4] A program that executes an information processing method for supporting child consultation services, provided by a server connected via a network to the user terminal of a user related to child consultation, wherein the control unit of the server receives, from the user terminal, at least child identification information that identifies the child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by investigation as input information, stores the input information in a memory unit of the server, and generates text data for instructing the generation of user support information that is estimated from the assessment information and the investigation record information at one or more points in the past that are linked to the child identification information obtained from the memory unit. [Item 5] An information processing system that supports child consultation services, including a server that connects via a network to user terminals of users related to child consultation services, wherein a control unit of the server receives, from the user terminal, at least child identification information that identifies a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information, stores the input information in a memory unit of the server, and generates text data for instructing the generation of a summary sentence based at least on the child identification information, assessment information, and investigation record information obtained from the memory unit. [Item 6] An information processing system that supports child consultation services, including a server that connects via a network to user terminals of users related to child consultation services, wherein a control unit of the server receives, from the user terminal, at least child identification information that identifies the child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information, stores the input information in a memory unit of the server, and generates text data for instructing the generation of user support information that is estimated from the assessment information and the investigation record information at one or more points in the past that are linked to the child identification information obtained from the memory unit.

[0071] Although the embodiments of the present disclosure have been described above, they can be implemented in various other forms, and various omissions, substitutions, and modifications can be made. These embodiments, modifications, and omissions, substitutions, and modifications are included in the technical scope of the claims and their equivalents.

[0072] 1 Business support system, 100 First server, 110 Communication unit, 120 Storage unit, 130 Control unit, 200 First user terminal, 300 Child consultation record system, 400 Text generation system, NW Network

Claims

1. An information processing method for supporting child consultation services, provided by a server connected via a network to user terminals of users related to child consultation services, wherein a control unit of the server receives at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information from the user terminal, stores the input information in a memory unit of the server, and generates text data for instructing the generation of a summary text based at least on the child identification information, assessment information, and investigation record information obtained from the memory unit.

2. An information processing method for supporting child consultation services, provided by a server connected via a network to user terminals of users related to child consultation services, wherein a control unit of the server receives, from the user terminal, at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information, stores the input information in a memory unit of the server, and generates text data for instructing the generation of user support information estimated from the assessment information and the investigation record information at one or more points in the past linked to the child identification information obtained from the memory unit.

3. A program for executing an information processing method for supporting child consultation services, provided by a server connected via a network to a user terminal of a user related to child consultation, wherein a control unit of the server: accepts from the user terminal at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information; stores the input information in a memory unit of the server; and generates text data for instructing the generation of a summary text based at least on the child identification information, assessment information, and investigation record information obtained from the memory unit.

4. A program for executing an information processing method for supporting child consultation services, provided by a server connected via a network to a user terminal of a user related to child consultation, wherein a control unit of the server: accepts from the user terminal at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information; stores the input information in a memory unit of the server; and generates text data for instructing the generation of user support information estimated from the assessment information and the investigation record information at one or more points in the past linked to the child identification information obtained from the memory unit.

5. An information processing system for supporting child consultation services, including a server connected via a network to user terminals of users related to child consultation services, wherein a control unit of the server: accepts from the user terminal at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information; stores the input information in a memory unit of the server; and generates text data for instructing the generation of a summary sentence based at least on the child identification information, assessment information, and investigation record information obtained from the memory unit.

6. An information processing system for supporting child consultation services, including a server connected via a network to user terminals of users related to child consultation services, wherein a control unit of the server: accepts, from the user terminal, at least child identification information for identifying a child, assessment information for determining at least one of protection and support for the child, and investigation record information obtained by an investigation as input information; stores the input information in a memory unit of the server; and generates text data for instructing the generation of user support information estimated from the assessment information and the investigation record information at one or more points in the past linked to the child identification information obtained from the memory unit.

Images