Program, method, and information processing apparatus

Abstract

To provide a program, a method and an information processor for making a matter more smoothly progress after an expert receives consultation from a consultant.SOLUTION: A program for operating a server including a storage unit configured to manage each of consultation contents from a consultant as a record of an item, and a control unit, the program causing the control unit to execute a step of receiving registration of the consultation contents of the consultant, and storing the consultation contents in the storage unit in association with the record of the item, and a step of transmitting, to a large scale language model, a prompt for extracting a discussion point corresponding to the consultation contents based on information on the consultation contents associated with the record of the item. S1123, the program causes the computer to execute a step S1125 of acquiring information on a discussion point, and a step S1127 of storing the acquired information on the discussion point in a storage unit in association with a record of an item related to a consultation content.SELECTED DRAWING: Figure 11

Description

[Technical Field]

[0001] The present disclosure relates to a program, a method, and an information processing device. [Background technology]

[0002] Various stakeholders, including ordinary consumers and businesses, carry out legal procedures, and therefore often seek legal advice from lawyers and other experts.

[0003] Patent Document 1 describes a technology that aims to "provide legal consultation services at low cost" and "uses an electronic network to interconnect providers and recipients of legal consultation services, and provides legal consultation services via the electronic network."

[0004] According to the technology of Patent Document 1, this makes it possible to "control the sending and receiving of legal consultation service information between the provider terminal and the provided terminal using an electronic network," which is said to have the effect of "making it possible to provide legal consultation services at a lower cost." [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2001-222611 Summary of the Invention [Problem to be solved by the invention]

[0006] The expert will listen to the client's concerns and then organize the details. They will then consider what arguments to make when drafting legal documents such as contracts, warning letters, complaints, and answers. However, it can be difficult to predict the amount of research work required, which places a burden on the expert. Furthermore, the research work may be postponed.

[0007] Therefore, there is a need for technology that allows a case to proceed more smoothly after an expert receives a consultation from a client. [Means for solving the problem]

[0008] According to one embodiment of the present disclosure, a program for operating a computer including a processor is provided. The program is configured to manage each consultation content from a client as a case record in a storage unit. The program causes the processor to execute the steps of accepting registration of the consultation content from the client and storing it in the storage unit in association with the case record, acquiring information on the points of discussion by providing a large-scale language model with a prompt that extracts points of discussion corresponding to the consultation content based on the information on the consultation content associated with the case record, and storing the acquired information on the points of discussion in the storage unit in association with the case record related to the consultation content. [Effects of the Invention]

[0009] According to the present disclosure, the case can be progressed more smoothly after the expert receives the consultation from the client. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing the configuration of the system 1. [Figure 2] FIG. 2 is a diagram showing the configuration of the server 20. As shown in FIG. [Figure 3] FIG. 3 is a diagram showing the configuration of the terminal 10. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing the data structure of the user database 211. As shown in FIG. [Figure 5] FIG. 5 is a diagram showing the data structure of the chat consultation history database 212. As shown in FIG. [Figure 6] FIG. 6 is a diagram showing the data structure of the LLM usage history database 213. [Figure 7]FIG. 7 is a diagram showing the data structure of the prompt database 214. As shown in FIG. [Figure 8] FIG. 8 is a diagram showing the data structure of the expert consultation history database 215. As shown in FIG. [Figure 9] FIG. 9 is a diagram showing the data structure of the case management database 216. As shown in FIG. [Figure 10] FIG. 10 is a diagram showing the flow of processing in which a user receives legal advice via chat, requests consultation from an expert, and the expert accepts the case. [Figure 11] FIG. 11 is a diagram showing the flow of processing for summarizing the consultation content from the client using a large-scale language model and associating it with a case record. [Figure 12] FIG. 12 is a diagram showing the flow of processing for breaking down the consultation content from the client, accepting an operation to rearrange the contents, and generating document data. [Figure 13] FIG. 13 is a diagram showing the flow of processing for expressing the person correlation diagram in text. [Figure 14] FIG. 14 is a diagram showing the flow of a process for presenting a question to the user to increase the resolution of information about a person. [Figure 15] FIG. 15 shows an example of an operation screen on which a client performs an operation to request a consultation from a specialist. [Figure 16] FIG. 16 shows an example of an operation screen on which an expert operates upon receiving a consultation request from a client. [Figure 17] FIG. 17 shows an example of a screen displaying case records. [Figure 18] FIG. 18 shows an example of a screen resulting from generating a summary of the consultation content based on the voice data of the consultation content in a case. [Figure 19] FIG. 19 shows an example of an operation screen for accepting an operation to organize the consultation contents. [Figure 20] FIG. 20 shows an example of an operation screen that accepts an operation to organize the correlations between characters. [Figure 21] FIG. 21 is a diagram showing the flow of processing for identifying the points of contention in the consultation content of the client using a large-scale language model and storing them in association with the record of the case. [Figure 22] FIG. 22 is a diagram showing the flow of processing for generating a list of materials and evidence registered in a case record. [Figure 23] FIG. 23 shows an example of an operation screen that displays information extracted from a case record using a large-scale language model. [Figure 24] FIG. 24 shows an example of an operation screen that displays a list of materials and evidence in a case record. [Figure 25] FIG. 25 is a diagram showing the flow of a process for generating legal document data based on the information in the case record. [Figure 26] FIG. 26 is a diagram showing the flow of a process for generating possible counterarguments to a point of contention. [Figure 27] FIG. 27 is a diagram showing the flow of a process for supporting the reading and comprehension of a contract. [Figure 28] FIG. 28 shows an example of an operation screen for generating legal document data. [Figure 29] FIG. 29 shows an example of an operation screen that displays possible counterarguments to the points at issue. [Figure 30] FIG. 30 shows an example of an operation screen that supports the reading and comprehension of a contract. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following description, the same components are denoted by the same reference numerals. The names and functions of the components are also the same. Therefore, detailed descriptions thereof will not be repeated.

[0012] <Outline of embodiment> <1.1 Overall system configuration> FIG. 1 is a diagram showing the configuration of the system 1.

[0013] 1 includes a case management service server 20 that manages legal consultation cases, a user terminal 10, a precedent search service server 91, a law search service server 92, a book browsing service server 93, an information media service server 94, an artificial intelligence (large-scale language model) service server 95 (hereinafter also referred to as the "large-scale language model service server 95"), a business operator server 96, an SNS server 97, and a user terminal 10A. These devices are connected to each other for communication via a network 80.

[0014] In the illustrated example, terminals such as terminal 10 and terminal 10A are shown as terminals used by users of the project management service provided by server 20, and each user operates a terminal.

[0015] In this embodiment, each device (terminal device, server, etc.) can also be considered as an information processing device. That is, a collection of devices can be considered as one "information processing device," and system 1 can be formed as a collection of multiple devices. The way in which multiple functions required to realize system 1 according to this embodiment are allocated to one or multiple pieces of hardware can be determined appropriately in consideration of the processing capacity of each piece of hardware and / or the specifications required for system 1.

[0016] Terminal 10 is a device operated by a user. In this embodiment, terminal 10 is operated by a professional user who provides legal consultations. The professional user prepares legal documents such as contracts, warning documents, response documents, complaints, and answers depending on the content of the consultation. Terminal 10 and terminal 10A have similar functional configurations. Terminal 10 is realized, for example, as follows. · Handheld devices such as smartphones and tablets Desktop PCs (Personal Computers), laptop PCs Wearable devices worn by users (wristwatches, glasses, etc.) The terminal 10 includes a communication IF (Interface) 12 , an input device 13 , an output device 14 , a memory 15 , a storage 16 , and a processor 19 .

[0017] The communication IF 12 is an interface for inputting and outputting signals so that the terminal 10 can communicate with an external device.

[0018] The input device 13 is a device for receiving input operations from a user (for example, a touch panel, a touch pad, a pointing device such as a mouse, a keyboard, etc.).

[0019] The output device 14 is a device (such as a display or speaker) for presenting information to the user.

[0020] The memory 15 is for temporarily storing programs and data to be processed by the programs, and is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0021] The storage 16 is for storing data, and is, for example, a flash memory or a hard disk drive (HDD).

[0022] The processor 19 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, and the like.

[0023] The server 20 is a device for providing users with a service for managing cases, which are units of legal consultation work. In this embodiment, the server 20 accepts registration of case-related information from users of the terminal 10, and provides functions for summarizing the consultation content, investigating issues related to the consultation content, researching legal precedents or books corresponding to the issues, and preparing legal documents. The server 20 provides a case management service by having the artificial intelligence (large-scale language model) service server 95 generate information related to these functions based on the case information, and then recording the generated results in the server 20 while responding to the user.

[0024] In this embodiment, the server 20 is also a device for providing a legal consultation service to a user. In this embodiment, the server 20 accepts legal consultation requests from users of the terminals 10 in free text chat format, causes the artificial intelligence (large-scale language model) service server 95 to generate a response to the received legal consultation content, and returns the generated result to the user, thereby providing the legal consultation service. Users may include clients who seek consultation and experts who respond to the consultation. Specifically, the server 20 provides legal consultation services to the following users: Users who handle legal matters, such as the legal department of a business company, and respond to legal inquiries Users who do not necessarily perform legal work exclusively, such as business divisions of a business company Users who provide legal advice to clients as a professional, such as law firms The server 20 may accept requests for legal consultation from clients to legal experts by matching users who provide legal consultation as experts, such as law firms, with users who request legal consultation from experts, such as business companies or individuals. For example, the content of the consultation may be posted on a bulletin board that can be viewed by third parties, and the expert's response may also be made public. Alternatively, the content of the consultation may be kept private and not disclosed to third parties, allowing the client to consult with the expert. The server 20 stores such client consultation content and the expert's response.

[0025] The server 20 includes a communication IF 22 , an input / output IF 23 , a memory 25 , a storage 26 , and a processor 29 .

[0026] The communication IF 22 is an interface for inputting and outputting signals so that the server 20 can communicate with external devices.

[0027] The input / output IF 23 functions as an interface with an input device for receiving input operations from the user and an output device for presenting information to the user.

[0028] The memory 25 is for temporarily storing programs and data to be processed by the programs, and is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0029] The storage 26 is for storing data, and is, for example, a flash memory or a hard disk drive (HDD).

[0030] The processor 29 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0031] The precedent search service server 91 has a database of precedents and allows users to search for judgments made by courts and the like.

[0032] The server 92 for the legal search service has a database of legal documents and allows users to search for legal documents.

[0033] The book browsing service server 93 is a service that allows users to browse electronic content such as magazines, books, etc. For example, by paying a fixed fee periodically, users can browse electronic books in fields such as law.

[0034] The information media service server 94 provides information services, such as collecting and making available blog posts, Q&A sites, news articles, IR information, etc. The information media service server 94 stores information on interpretations based on laws and regulations, as well as guidelines prepared by government agencies and other organizations to publicize operational rules.

[0035] In addition to the above, the information media service server 94 may also provide services that collect and provide the following information. Whether the organization is (or may be) a party that falls under the conditions for contract termination, such as being an anti-social force. For example, there may be publicly available information, such as a database or news article, that indicates that the organization falls under the above conditions. The reputation of a business company or other organization, such as when consumers have a negative reaction and the information is spread in the news, on social media, etc. For example, information may be spread on social media with negative keywords and a certain number of impressions. Information about business performance, such as sales, revenue (profit amount, profit margin, etc.), and assessment results regarding business continuity (continued losses, possibility of bankruptcy, bond ratings, etc.). The large-scale language model service server 95 is a server that executes language processing tasks using a language model constructed by a learning process including artificial intelligence (AI). An LLM (Large Language Model) is a server that has previously learned a large amount of large-scale data (text data, etc.), such as web content on the Internet, or a large amount of data stored in a specified database, and can execute various language processing tasks by providing the task.

[0036] The large-scale language model service server 95 accepts prompt inputs such as text, images, and voice, and generates and responds to the prompts. Examples of LLMs include GPT-3 and GPT-4 developed by OpenAI, and BERT developed by Google.

[0037] The business's server 96 stores data generated in the course of business activities. This data has access rights, and access to the data is restricted to users belonging to the business and external users not belonging to the business.

[0038] The SNS server 97 provides services that encourage interaction between users, such as a service that allows users to view each other's posts. For example, there are services that allow users to view posts by searching the Internet even if they do not have a user account on the SNS, and services that allow users to view posts by other users if they have a user account.

[0039] <1.2 Functional configuration of server 20> 2 is a diagram showing the configuration of the server 20. As shown in FIG. 2, the server 20 functions as a communication unit 201, a storage unit 202, and a control unit 203.

[0040] The communication unit 201 performs processing for the server 20 to communicate with external devices.

[0041] The storage unit 202 stores various databases such as a user database 211, a chat consultation history database 212, an LLM usage history database 213, a prompt database 214, an expert consultation history database 215, and a case management database 216.

[0042] The user database 211 is a database that manages information about each user, as will be described in detail later.

[0043] The chat consultation history database 212 is a database showing the history of consultations that users have had using the services provided by the server 20. Details will be described later.

[0044] The LLM usage history database 213 is a database showing the history of responses generated by the artificial intelligence service server 95 in response to user inquiries. Details will be described later.

[0045] The prompt database 214 is a database that manages templates of prompts to be sent to the large-scale language model service server 95. Details will be described later.

[0046] The expert consultation history database 215 is a database showing the history of consultations that a user has had with experts, as will be described in detail later.

[0047] The case management database 216 is a database for managing cases, which are units of consultation-related work. Details will be described later.

[0048] The control unit 203 is realized by the processor 29 reading a program stored in the storage unit 202 and executing instructions included in the program. By operating in accordance with the program, the control unit 203 exhibits functions shown as a reception control module 2041, a transmission control module 2042, a user management module 2043, a chat consultation processing module 2044, an LLM usage module 2045, a learning processing module 2046, a matching processing module 2047, and a case management module 2048.

[0049] The reception control module 2041 controls the process by which the server 20 receives signals from external devices in accordance with a communication protocol.

[0050] The transmission control module 2042 controls the process in which the server 20 transmits signals to external devices in accordance with a communication protocol.

[0051] The user management module 2043 is a module for managing information about each user who uses the system 1. Specifically, the user management module 2043 accepts registration of information about each user and updates the user database 211.

[0052] The chat consultation processing module 2044 is a program module that processes legal consultation requests received from users via chat and responds to them.

[0053] Specifically, the chat consultation processing module 2044 receives input of the content of the consultation from the user, causes the large-scale language model service server 95 to generate a response, and updates the chat consultation history database 212 .

[0054] The LLM usage module 2045 is a program module that generates prompts based on the content of the consultation input by the user in free text, images, voice, etc., and generates answers by sending the generated prompts to the large-scale language model service server 95.

[0055] Specifically, the LLM usage module 2045 manages the text entered by the user as a series of texts, and updates the LLM usage history database 213 based on the prompts sent to the large-scale language model service server 95 and the responses from the large-scale language model service server 95.

[0056] The learning processing module 2046 is a program module that trains a trained model that outputs answers to questions based on data stored in the server 20 as the chat consultation history database 212 and the like.

[0057] The matching processing module 2047 is a program module that accepts an operation from a client to request legal advice from a specialist, and matches the client with a specialist such as a lawyer.

[0058] The case management module 2048 is a program module that accepts registration of various information about cases, records it in records, and reads out the information recorded in the records and presents it to the user.

[0059] If a deadline is set for a case, the case management module 2048 issues a notification based on the deadline.

[0060] <1.3 Configuration of Terminal 10> FIG. 3 is a diagram showing the configuration of the terminal 10. As shown in FIG.

[0061] As shown in FIG. 3, the terminal 10 includes multiple antennas (antenna 111, antenna 112), communication units (first communication unit 120, second communication unit 121) corresponding to the respective antennas, an input device 130 (including a touch-sensitive device 131), a display 132, an audio processing unit 140, a microphone 141, a speaker 142, a position information sensor 150, a camera 160, a motion sensor 170, a memory unit 180, and a control unit 190. The terminal 10 also has functions and configurations (e.g., a battery for storing power, a power supply circuit for controlling the supply of power from the battery to each circuit, etc.) that are not specifically shown in FIG. 3. As shown in FIG. 3, the blocks included in the terminal 10 are electrically connected by a bus or the like.

[0062] The antenna 111 emits a signal emitted by the terminal 10 as a radio wave. The antenna 111 also receives a radio wave from space and provides the received signal to the first communication unit 120.

[0063] The antenna 112 emits a signal emitted by the terminal 10 as a radio wave. The antenna 112 also receives a radio wave from space and provides the received signal to the second communication unit 121.

[0064] The first communication unit 120 performs modulation / demodulation processing and the like for transmitting and receiving signals via the antenna 111 so that the terminal 10 can communicate with other wireless devices. The second communication unit 121 performs modulation / demodulation processing and the like for transmitting and receiving signals via the antenna 112 so that the terminal 10 can communicate with other wireless devices. The first communication unit 120 and the second communication unit 121 are communication modules including a tuner, a received signal strength indicator (RSSI) calculation circuit, a cyclic redundancy check (CRC) calculation circuit, a high-frequency circuit, and the like. The first communication unit 120 and the second communication unit 121 perform modulation / demodulation, frequency conversion, and the like for wireless signals transmitted and received by the terminal 10, and provide the received signals to the control unit 190.

[0065] Input device 130 has a mechanism for accepting input operations by a user. Specifically, input device 130 is configured as a touch screen and includes touch-sensitive device 131. Touch-sensitive device 131 accepts input operations by a user of terminal 10. Touch-sensitive device 131 detects the user's touch position on the touch panel, for example, by using a capacitive touch panel. Touch-sensitive device 131 outputs a signal indicating the user's touch position detected by the touch panel to control unit 190 as an input operation.

[0066] The display 132 displays data such as images, videos, and text under the control of the control unit 190. The display 132 is realized by, for example, an LCD, an organic EL display, or the like.

[0067] The audio processing unit 140 modulates and demodulates audio signals. The audio processing unit 140 modulates a signal provided from the microphone 141 and provides the modulated signal to the control unit 190. The audio processing unit 140 also provides the audio signal to the speaker 142. The audio processing unit 140 is realized, for example, by a processor for audio processing. The microphone 141 accepts audio input and provides an audio signal corresponding to the audio input to the audio processing unit 140. The speaker 142 converts the audio signal provided from the audio processing unit 140 into audio and outputs the audio to the outside of the terminal 10.

[0068] The location information sensor 150 is a sensor that detects the location of the terminal 10, and is, for example, a GPS (Global Positioning System) module. The GPS module is a receiving device used in a satellite positioning system. The satellite positioning system receives signals from at least three or four satellites, and detects the current location of the terminal 10 equipped with the GPS module based on the received signals.

[0069] The camera 160 is a device that receives light with a light receiving element and outputs the received light as a captured image. The camera 160 is, for example, a depth camera that can detect the distance from the camera 160 to a subject being photographed.

[0070] The motion sensor 170 includes an acceleration sensor, an angular velocity sensor, etc., and detects the movement of the terminal 10 .

[0071] The storage unit 180 is configured with, for example, a flash memory or the like, and stores data and programs used by the terminal 10. The various types of information stored in the storage unit 180 will be described later.

[0072] The control unit 190 controls the operation of the terminal 10 by reading a program stored in the storage unit 180 and executing instructions included in the program. The control unit 190 is, for example, an application processor. By operating in accordance with the program, the control unit 190 fulfills the functions of an operation reception unit 191, a transmission / reception unit 192, a data processing unit 193, a notification control unit 194, and a storage control unit 195.

[0073] Operation acceptance unit 191 performs processing to accept a user's input operation to an input device such as touch-sensitive device 131. Operation acceptance unit 191 determines the type of operation, such as whether the user's operation is a flick operation, a tap operation, or a drag (swipe) operation, based on information about the coordinates where the user has touched touch-sensitive device 131 with a finger or the like.

[0074] The transmitting / receiving unit 192 performs processing for the terminal 10 to transmit and receive data to and from an external device such as the server 20 in accordance with a communication protocol.

[0075] The data processing unit 193 performs calculations on data that the terminal 10 has received as input in accordance with a program, and outputs the calculation results to a memory or the like.

[0076] The notification control unit 194 performs processing for displaying a display image on the display 132, processing for outputting sound from the speaker 142, and processing for generating vibrations.

[0077] The storage control unit 195 controls the storage of data in the storage unit 180 .

[0078] A description will be given of various types of information stored in storage unit 180. In one aspect, storage unit 180 stores various types of information such as user information 181.

[0079] The user information 181 is information about a user who uses the services of the server 20 .

[0080] <2 Data Structure> 4 is a diagram showing the data structure of the user database 211. The user database 211 includes an item "user ID," an item "name," an item "email address," an item "attributes," an item "business ID," an item "qualifications held," an item "registration date," an item "status," an item "field," and an item "evaluation value."

[0081] The item "user ID" is information that identifies each user.

[0082] The item "Name" is information indicating the name of the user.

[0083] The item "email address" is information about the email address used to contact the user.

[0084] The item "attribute" is information indicating the attribute of the user.

[0085] Specifically, the item "attributes" includes the following as user attributes: · Legal counselors - Professionals who provide legal advice, such as lawyers and other qualified professionals The item "business ID" is information that identifies the organization to which the user belongs.

[0086] Specifically, the item "business ID" is information for identifying the organization to which the user belongs, and the following organizations are possible. ·Law firm Business companies Individuals (you may be consulted as an individual, not as a member of an organization) The item "Qualifications held" is information indicating qualifications held by the user.

[0087] Specifically, the item "Qualifications held" is information for identifying the qualifications held by the user, and may include the following qualifications. · National qualifications such as lawyer, patent attorney, certified public accountant, etc. Qualifications certified by businesses, general incorporated associations, and other organizations The item "registration date" is information indicating the date and time when the user registered for the service.

[0088] The item "status" is information indicating the user's status regarding legal advice.

[0089] Specifically, the item "status" includes the following as the user's status: Accepting consultation: The expert user is able to accept consultations from the client. · Consultation suspended: A state in which the expert user is not accepting consultations. For example, it is possible that the number of consultations exceeds a certain number and new consultations are not being accepted. The server 20 changes the user's status in the item "status" in response to the user's operation. The item "field" is information indicating the field in which the user has expertise.

[0090] Specifically, the "field" item includes information on each field classified as a field of legal consultation. For example, if the information media service server 94 provides a service introducing experts such as lawyers and classifies the fields of experts according to the type of consultation (debt consolidation, traffic accidents, divorce, inheritance, etc.), the field may include information on each of these classified fields. The server 20 may update the user database 211 in response to an operation by the user to specify a field, or may set the field of the expert user by referring to the field of legal consultation based on the expert user's track record of providing legal consultation.

[0091] The item "evaluation value" is information indicating an evaluation value obtained by evaluating the manner of legal consultation by the user.

[0092] Specifically, the item "evaluation value" includes the following as user evaluation values: Expert rating: A rating based on the number of inquiries and frequency of responses from clients. Evaluation value as a consultant: an evaluation value based on the track record of the consultant consulting with an expert and being entrusted by the expert, the track record of the consultant organizing the content of the consultation (inputting the content of the consultation) using the legal consultation service provided by the server 20, etc. 5 is a diagram showing the data structure of the chat consultation history database 212. The chat consultation history database 212 includes an item "consultation thread ID," an item "consultant user ID," an item "post ID," an item "post content," an item "related posts," an item "posting date and time," an item "search target database," an item "search results," an item "LLM output," an item "answer," and an item "user rating."

[0093] The item "Consultation thread ID" is information for identifying each consultation thread in which a user makes a consultation via chat in the legal consultation service provided by the server 20.

[0094] The item "consultant user ID" is information for identifying the user making the consultation.

[0095] Specifically, the item “consultant user ID” corresponds to the item “user ID” of the user database 211.

[0096] The item "Post ID" is information that identifies each post associated with a thread.

[0097] The item "Posted Content" is information indicating the content posted by the user.

[0098] The item "related post" is information indicating other posts related to the post indicated in the item "post ID" for multiple posts managed in a thread.

[0099] Specifically, the item "related post" is information that identifies the most recent post made by a user among multiple posts managed in a thread. In this way, every time a user posts a consultation in a thread indicated by the item "consultation thread ID," the consultation is associated with the item "post ID" of the most recent post made and managed in the chat consultation history database 212, thereby making it possible to manage the order of a series of posts in a thread.

[0100] The item "Posting date and time" is information indicating the timing when the user posted.

[0101] Specifically, the item "posting date and time" may be the time when a question was received from a user in free text or the like.

[0102] The item "database to be searched" is information that specifies the database to be referenced by search when generating an answer by the server 95 of the large-scale language model service.

[0103] Specifically, the item "database to be searched" may include the following information as the database to be referenced. Information obtained by searching the Internet Information provided by the case law search service server 91 Information provided by legal search service server 92 Information provided by the book browsing service server 93 Information provided by the information media service server 94 Information provided by the artificial intelligence (large-scale language model) service server 95 Information provided by the operator's server 96 Information provided by SNS server 97 The item "search results" is information indicating the search results of a search performed on the referenced database based on the user's posted content.

[0104] Specifically, the item "search results" includes the results of a search performed by the server 20 as follows based on the content posted by the user indicated in the item "post ID." - Extract words from user posts and use them as search keys. At this time, legal terms are used as search keys without being broken down into further words, based on legal terms stored in a legal terminology database (not shown). The semantics of user posts is analyzed and vectorized using techniques such as Word2Vec. Documents in the database to be referenced are also vectorized in the same way, and documents stored in the database are searched for based on the proximity of the vectors. The item "LLM output" is information indicating the results generated by the large-scale language model service server 95 based on user posts.

[0105] Specifically, the item "LLM output" includes the result of having the large-scale language model service server 95 generate an answer as follows. The results of searching each database shown in the "Search Results" section are summarized by the large-scale language model service server 95. When generating an answer, the background information such as "a user from the legal department will make the decision" was included in the prompt, and the answer was generated by the large-scale language model service server 95. The item "answer" is information indicating the answer presented to the user.

[0106] Specifically, for the item "answer", an answer including the result generated by the large-scale language model service server 95 and information generated by the server 20 may be presented to the user as follows. - Responses including links to the sources of information that can be used to refer to the results summarized by the large-scale language model service server 95 The server 20 adds the original text of the provisions stored in the legal database and the precedents stored in the precedent database to the results summarized by the server 95 of the large-scale language model service, and provides the answer. The item "user evaluation" is information indicating the user's evaluation of the answer presented by the server 20.

[0107] 6 is a diagram showing the data structure of the LLM usage history database 213. The LLM usage history database 213 includes an item "usage ID," an item "consultation thread ID," an item "posting ID," an item "prompt," an item "LLM output result," an item "usage date and time," and an item "case ID."

[0108] When the server 20 provides legal consultation services to users, it may cause the large-scale language model service server 95 to execute a task using posts entered by the users. It may also cause the large-scale language model service server 95 to generate information in response to the registration of case data in the case management service provided by the server 20.

[0109] The item "Usage ID" is information that identifies each history of answers generated by the server 95 of the large-scale language model service.

[0110] The item "consultation thread ID" is information for identifying a thread in which a user seeks advice in the legal consultation service provided by the server 20.

[0111] Specifically, the item “consultation thread ID” corresponds to the item “consultation thread ID” in the chat consultation history database 212 .

[0112] The item "Post ID" is information that identifies a post of a question entered by a user, for which an answer is to be generated by the large-scale language model service server 95.

[0113] Specifically, the item “Posting ID” corresponds to the item “Posting ID” in the chat consultation history database 212 .

[0114] The item "prompt" is information indicating the content of the prompt applied when sending to the server 95 of the large-scale language model service.

[0115] Specifically, the item "prompt" may include the content of a prompt that is defined as follows and sent to the server 95 of the large-scale language model service. A prompt template defined in the prompt database 214 (to be described later) is added to the search results (item "search results" in the chat consultation history database 212) obtained by searching each database based on the content of the question entered by the user, and the result is sent to the server 95 of the large-scale language model service. A prompt that is sent to the server 95 of the large-scale language model service by applying data registered in association with a case in the case management database 216 to a prompt template defined in the prompt database 214 described later. The item "LLM output result" is information indicating the content output by the server 95 of the large-scale language model service by sending a prompt to the server 95 of the large-scale language model service.

[0116] The item "Date and time of use" is information on the date and time when the answer was generated by the server 95 of the large-scale language model service.

[0117] The item "case ID" is information for identifying each case managed in the case management database 216, which will be described later.

[0118] 7 is a diagram showing the data structure of the prompt database 214. The prompt database 214 includes the following items: a "prompt ID," an "operator ID," a "prompt template," an "authority setting," and an "availability."

[0119] The item "prompt ID" is information that identifies each prompt.

[0120] The item "Business ID" is information that identifies the organization that uses Prompt.

[0121] Specifically, the item “business ID” corresponds to the item “business ID” in the user database 211.

[0122] The item "prompt template" is information indicating the contents of the prompt template.

[0123] Specifically, the item "prompt template" may include a prompt template containing the following content: A summary of information entered by a user in a legal consultation service or case management database 216. For example, a summary may be required to be within a certain number of characters. - A text of the consultation (for example, a transcript of the voice data of the consultation using character recognition) that lists the facts related to the consultation in chronological order. - A text that asks the client to explain the correlation between the people who appear in the consultation. - Extracting the next action to be taken from the transcript of the conversation between the consultant and the expert. For example, keywords such as "summary," "next action," and "next time" can be identified from the transcript of the conversation as content that refers to the next action to be taken, and the content of the utterances associated with these keywords can be used as the next action. Also, if the minutes data contains keywords that indicate the next action to be taken, such as "next action," "summary," and "work until next time," the minutes can be referenced to extract the next action. - Extracting the issues that the client is concerned about and their concerns based on the content of the client's conversation and the results of assessing emotions from voice data Extracting the concerns of the client from the content of their consultation Identifying legal issues from the consultation content and concerns of the client. For example, it is possible to identify issues by extracting words from the consultation content and concerns of the client. In addition, the server 20 may store a list of keywords for each issue, and identify issues by comparing words extracted from the consultation content and concerns of the client with the list of keywords for each issue. - A system that summarizes legal precedents, laws, and book descriptions related to legal issues. For example, it identifies legal issues based on the concerns of the client, searches the case precedent search service server 91, the law search service server 92, the book browsing service server 93, and other databases for those issues, and summarizes the search results. It may also be possible to extract the supporting provisions that correspond to the issues. - Search for legal precedents. Point out the changes in interpretation of legal precedents that correspond to the issues at issue. For example, if the original judgment is revised, the revised parts of the higher court's judgment will be displayed. -Compare past interpretations of legal precedents with the latest interpretations and point out the differences. For example, search for specific examples of the issue and compare the interpretations in previously published books with the latest interpretations. Based on the information stored in the case management database 216, legal documents such as contracts, term sheets, warning letters, responses, complaints, answers, and briefs are prepared. For example, a complaint may be prepared by referring to the information of the parties. - Outputting the expected counterarguments of the opposing party to the arguments on the points at issue in legal documents such as complaints and briefs. For example, searching for past precedents on the points at issue and generating expected counterarguments on the large-scale language model service server 95 based on these precedents. - The citation relationship of the clauses in the contract is output according to a specified format. For example, it is possible to output the clauses that cite the contract and the clauses that are quoted in the contract in pairs. Generates a list of documents and evidence registered in the case management database 216 - A system that generates a list of evidence mentioned in data such as complaints and briefs registered in the case management database 216 A format in which an answer is generated by the large-scale language model service server 95. For example, there may be a format in which items to be included in the answer are specified, and there may be a prompt instructing the server to generate an answer according to the specified items. Such items may include legal issues, a list of stakeholders, generating answers separately for each stakeholder, advantages and disadvantages of each stakeholder, etc. - Instructions to generate summaries for data that is not disclosed to third parties and is referenced by users belonging to an organization, such as data stored on a business's server 96 The item "Usage authority setting" is information indicating the range of users who have the authority to use the prompt to cause the large-scale language model service server 95 to generate an answer.

[0124] Specifically, the item "Usage authority setting" may include information on the authority set as follows: When generating a summary of data that is not disclosed to third parties, such as data stored in a business's server 96, users who do not belong to that organization do not have the authority, and only users who belong to the organization have the authority. - Set permissions according to the user's department (for example, generate summaries for data that can be accessed by a specific department, such as corporate planning) - Set permissions based on user role (for example, generate summaries for data that can be accessed by users with specific roles, such as management) The item "Availability" is information indicating whether or not the prompt can be used as a template.

[0125] Specifically, the "Availability" item includes information on whether or not the prompt template is permitted to be used. For example, the large-scale language model service server 95 may update a prompt template to generate a better answer and stop using the previous prompt template.

[0126] 8 is a diagram showing the data structure of the expert consultation history database 215. The expert consultation history database 215 includes an item "expert consultation ID", an item "chat consultation ID", an item "consultation content", an item "field", an item "expert ID", an item "consultation date and time", and an item "acceptance result".

[0127] The item "expert consultation ID" is information for identifying each request made by a client to an expert for consultation.

[0128] Specifically, the item “expert consultation ID” corresponds to the item “expert consultation” in the chat consultation history database 212 .

[0129] The item "chat consultation ID" is information for identifying each consultation that a client has made via chat in the legal consultation service provided by the server 20 when the client requests a consultation from a specialist.

[0130] Specifically, the item “chat consultation ID” corresponds to the item “chat consultation ID” in the chat consultation history database 212 .

[0131] The item "content of consultation" is information indicating the content of the consultation that the client requests the expert to provide.

[0132] Specifically, the item "Consultation Content" includes information about the content of the consultation request entered by the seeker when the seeker makes an operation to request a consultation from an expert. The server 20 may acquire the content entered by the seeker into the chat system by referring to the chat consultation history database 212, and have the large-scale language model service server 95 summarize at least one of the seeker's consultation content and the answer to the question generated by the large-scale language model service server 95, so that the seeker can use the summarized result as information about the content of the request when making a request to an expert. This makes it even easier for the seeker to input the content of the request to an expert.

[0133] The item "field" is information indicating the field of consultation, which is set in a request for consultation from a consultant to a specialist.

[0134] Specifically, the item "field" includes information on the field set by the server 20 or the user (consultant or expert).

[0135] In addition, for example, the server 20 may identify the field of consultation by extracting legal terms contained in the content of the user's question in the chat consultation history database 212 and the answer generated by the large-scale language model service server 95.

[0136] The item "expert ID" is information for identifying the expert who responded to the request for consultation from the client.

[0137] Specifically, the item “expert ID” corresponds to the item “user ID” of the user database 211 .

[0138] The item "Consultation Date and Time" is information about the date and time when the request for consultation with the specialist by the client was registered.

[0139] The item "acceptance result" is information indicating whether or not the expert has accepted the consultation request of the client.

[0140] Specifically, the item "Acceptance result" includes the following information: Acceptance: The expert has accepted the client's request for consultation (e.g., the expert has registered that he or she has accepted the request). · Not accepted: The expert responded to the client's request for consultation but did not accept the case (a certain period of time has passed since the consultation date and time, or the expert registered that they did not accept the case) 9 is a diagram showing the data structure of the case management database 216. The case management database 216 includes an item "case ID," an item "consultant user ID," an item "expert user ID," an item "consultation audio data," an item "consultation content memo," an item "consultation date and time," an item "AI summary of consultation content," an item "AI issue extraction," an item "AI research results," an item "document data," and an item "legal document data."

[0141] The item "case ID" is information that identifies each case.

[0142] The item "consultant user ID" is information for identifying the user who will be the consultant.

[0143] Specifically, the item “consultant user ID” corresponds to the item “user ID” of the user database 211.

[0144] The item "expert user ID" is information for identifying a user who will become an expert.

[0145] Specifically, the item “expert user ID” corresponds to the item “user ID” of the user database 211 .

[0146] The item "Consultation voice data" is voice data of the conversation when the client consults with the specialist.

[0147] Specifically, the item "consultation voice data" may include the following: The audio data itself Transcription data obtained by performing character recognition processing on audio data - Speaker emotion data obtained by performing speaker and emotion determination processing on audio data The item "Consultation content memo" is memo information entered by the expert or the person seeking advice.

[0148] The item "Consultation date and time" is information about the time when the consultant consulted the specialist.

[0149] Specifically, the item "Consultation date and time" is The item "AI summary of consultation content" is information on the results of summarizing data on the consultation content of the client by the server 95 of the large-scale language model service.

[0150] Specifically, the item "AI summary of consultation content" includes the results of a summary created by the server 95 of the large-scale language model service based on the transcription data of the voice data relating to the conversation between the consultant and the expert.

[0151] The item "AI issue extraction" is information on the issue identified by the server 95 of the large-scale language model service for the data on the consultation content of the client.

[0152] The item "AI research results" is information resulting from the summary of information on the issue, such as precedents, laws, interpretations, and commentaries, by the large-scale language model service server 95.

[0153] Specifically, the item "AI research results" includes the results of searching various databases, such as a case law search service server 91, a law search service server 92, and a book browsing service server 93, for the issue, and summarizing the search results using a large-scale language model service server 95.

[0154] The item "document data" is information provided by the client about the case, information collected by the expert, and the like.

[0155] Specifically, the item "document data" includes information such as documents that will not be disclosed to the other party, documents that will be made public, and evidence to be submitted in legal proceedings.

[0156] The item "legal document data" is data on documents submitted in legal procedures.

[0157] Specifically, the item "legal document data" includes data on documents such as: Contract Term Sheet Warning letter Response letter (response to the warning letter) ·complaint Answer ·Preparation document <3. Operation (First Embodiment)> FIG. 10 is a flowchart showing the flow of processing in which a user receives legal advice via chat, requests consultation from an expert, and the expert accepts the case.

[0158] In step S1021, the server 20 presents an operation screen for accepting input of questions regarding legal consultation to the user who is the client.

[0159] In step S1011, the terminal 10 displays an answer generated by the large-scale language model service server 95 in response to the legal consultation question input by the user. The terminal 10 accepts, on the operation screen, an operation from the user to request legal advice from an expert regarding the question.

[0160] The server 20 is configured to store information on experts such as lawyers who can respond to legal consultations in the user database 211. The server 20 refers to the chat consultation history database 212 and extracts candidate experts who can respond to the consultation request based on the content of the consultation requested by the user, the answers generated by the large-scale language model service server 95, and information on the experts. For example, the server 20 may identify a field related to the content of the consultation from terms included in the content of the consultation and the content of the generated answers, and extract lawyers who specialize in that field from the user database 211.

[0161] The terminal 10 displays the experts extracted by the server 20 as candidates to request consultation from. The terminal 10 presents the extracted expert candidates to the user along with information about the experts (for example, their names, fields of expertise, etc.).

[0162] The terminal 10 may receive input of conditions for selecting an expert from the user. For example, there may be a case where the user wants to further narrow down the candidate experts extracted by the server 20 or search for an expert different from the extracted experts. The server 20 may extract candidate experts according to the conditions and candidate experts received from the user.

[0163] The terminal 10 may accept an operation from the user to make the user's question about legal advice publicly viewable by third parties. The server 20 may make the question about legal advice viewable by third parties in response to the operation to make the question publicly viewable. When making the question and answer viewable by third parties, the server 20 may generate an answer by instructing the large-scale language model service server 95 to generate an answer that does not include the user's personal information.

[0164] In step S1023, the server 20 outputs to the user who is the expert, based on the chat consultation history database 212, a message that the client has requested a consultation from the expert, and a response to the consultation that is based on the response generated by the large-scale language model service server 95.

[0165] Here, the server 20 may generate a prompt instructing the server 95 of the large-scale language model service to generate an answer to the question of the user who is the seeker, in accordance with specified items, and have the server 20 generate the answer. For example, the server 20 may generate a prompt instructing the server 95 to generate an answer by organizing the specified items as follows: Stakeholder items Timing information items Discussion items The monetary value of the legal consultation (e.g., the amount of compensation) Related laws, regulations and precedents The server 20 sends a prompt to the large-scale language model service server 95 instructing it to generate an answer in accordance with the specified items as described above, accepts the generated answer, and updates the chat consultation history database 212.

[0166] The server 20 may output to the expert content based on the answer generated in accordance with specified items. For example, the server 20 manages the case management database 216 used by the expert, and creates a prompt to generate an answer in accordance with the specified items as described above so as to be consistent with the items of the records managing each case in the case management database 216. In this way, the server 20 may update the case record in the case management database 216 based on the results generated by the large-scale language model service server 95.

[0167] The server 20 evaluates the user's consultation based on the question entered by the user and the answer generated by the large-scale language model service server 95, which are stored in the chat consultation history database 212, and updates the item "possibility of accepting the case" in the chat consultation history database 212 based on the evaluation result.

[0168] The server 20 may refer to the chat consultation history database 212 and output to the expert a score that evaluates the user's consultation regarding the request made by the user who is the seeker.

[0169] The server 20 may refer to the expert consultation history database 215 and evaluate the possibility of the legal consultation of the client resulting in the expert being appointed, depending on the track record of the legal consultation of the client resulting in the expert being appointed.

[0170] The server 20 may refer to the chat consultation history database 212 and evaluate the possibility of accepting the case based on at least one of the following: the amount of data of the question entered by the user regarding the legal consultation, whether the large-scale language model has successfully provided an answer, or whether the answer generated by the large-scale language model has a certain amount of data or more.

[0171] The server 20 may refer to the chat consultation history database 212 and output to the expert, with priority, legal consultation requests that are evaluated to have a certain degree of possibility of being accepted.

[0172] In step S1025, when the server 20 receives an operation from the expert to respond to the request of the client, the server 20 updates the expert consultation history database 215 and notifies the user who is the client.

[0173] In step S1013, the terminal 10 notifies the user that the expert has responded to the request.

[0174] As described above, an example has been described in which an expert receives a consultation from a client who uses a legal consultation service by matching with the client and registers information about the case in the case management database 216. However, this is not limited to this, and there may also be cases in which an expert receives an inquiry from a client and manages the case in the case management database 216.

[0175] FIG. 11 is a diagram showing the flow of processing for summarizing the consultation content from the client using a large-scale language model and associating it with a case record.

[0176] In step S1121, the case management module 2048 of the server 20 outputs to the terminal 10 an operation screen for managing cases.

[0177] In step S1111, the terminal 10 accepts an operation on the operation screen from the client to upload consultation data indicating the content of the consultation. The consultation data may be, for example, voice data, video recording data of a meeting, or notes entered during a meeting between the client and a specialist.

[0178] In step S1123, the case management module 2048 of the server 20 accepts the consultation data from the terminal 10 and registers it in the case record of the case management database 216.

[0179] The case management module 2048 accepts voice data indicating the content of the consultation as consultation data. Upon accepting the voice data, the case management module 2048 performs character recognition processing to acquire transcription data by transcribing the voice data. The case management module 2048 associates the transcription data with the client and stores it in a record in the case management database 216, thereby registering it as case information.

[0180] The case management module 2048 processes the voice data to determine the speaker and the emotion, and further stores at least one of the information on the results of the speaker determination in the transcription data, the information on the results of the emotion determination, and the information on the timing of the consultation from the client in the case management database 216.

[0181] In step S1125, the case management module 2048 of the server 20 transmits a prompt to the large-scale language model service server 95 to summarize the consultation content indicated in the consultation data along predetermined items. Here, the predetermined items may correspond to each subfield indicated in the case management database 216.

[0182] The case management module 2048 may obtain the result of summarizing the consultation content by prompting the large-scale language model service server 95 to summarize the consultation content indicated in the consultation data along predetermined items.

[0183] The case management module 2048 may obtain a chronologically summarized result by providing a prompt to the large-scale language model service server 95 to organize the consultation contents included in the consultation data in chronological order.

[0184] For example, the case management module 2048 may send the following prompt to the large-scale language model service server 95, causing the large-scale language model service server 95 to generate a sentence that organizes the consultation content in chronological order: Identify the date included in the transcript of the consultation and extract the consultation content (facts, etc.) associated with the date (for example, a statement such as "Something happened around ____ years ago"). Extracting facts that occurred in the past based on verb expressions in the past tense (for example, from a statement such as "I lent money," it is determined that "I lent" is an expression in the past tense, and extracted as a fact that occurred in the past) If there is no time period for the fact, it will be treated as the most recent fact detected. Extracting relative time periods by detecting demonstrative pronouns and words that indicate time periods (for example, if someone says "two months ago," it will detect that the time period is relatively earlier or later than the time period indicated by the demonstrative pronoun (for example, the most recently detected time period). For example, "two months ago" indicates a time period even earlier than the time period indicated by the demonstrative pronoun). If there is no demonstrative pronoun, the facts are based on the time of the consultation. In step S1127, the case management module 2048 of the server 20 obtains the result of summarizing the consultation content from the large-scale language model service server 95 and registers it in the case record for the client in the case management database 216. The case management module 2048 associates the consultation content summarized by the large-scale language model service server 95 along predetermined items with the client, and stores the association in the case management database 216 so that it can be referenced by the expert who will respond to the client's consultation.

[0185] When the case management module 2048 receives the summarized results organized in chronological order from the large-scale language model service server 95, it stores them in the case management database 216 in association with the client.

[0186] Each consultation from a client is managed as a case including predetermined management items in the case management database 216. The case management module 2048 may store each item of the consultation content summarized according to the predetermined items in association with each management item managed as a case in the case management database 216.

[0187] In the case management database 216, at least one of the following predetermined management items is managed as a case: the consultation content from the client, the next action to be taken, and the client's concerns. The case management module 2048 may obtain the summary result by issuing a prompt to the large-scale language model service server 95 to summarize at least one of the predetermined management items as a predetermined item.

[0188] The case management module 2048 may extract concerns of the client based on the voice data of the consultation content of the client and information on the result of emotion determination, and store the information on the concerns of the client as case information in the case management database 216. For example, based on the result of emotion determination, the following cases may be extracted as concerns of the client: - Text corresponding to the voice of the consultation content when the emotion is judged to be "anger" or "anxiety" - Text corresponding to the voice of the consultation content before and after the evaluation score of the emotion changed by a certain amount (emotions fluctuated) Text corresponding to the voice when the volume of the voice data of the client exceeds a certain level (and may also include the time before and after this point) (such as when the voice is loud) - When the transcription of the client's audio data contains statements that indicate concern. For example, statements may include "I'm worried," "I want to do something" (statements that express a desire to solve the problem), "I don't want this," "I'm angry" (statements that express a negative emotional reaction), "I don't want this to happen" (statements that express a desire to avoid a specific action or falling into a specific state), or "Is it okay to do this?" (statements that express a desire to confirm whether it is okay to take a specific action or move into a specific state, for example, "Is it okay to negotiate directly with the other party?"). Keywords that appear in the client's statements that appear more than a certain number of times or that appear frequently (because they are repeated, there is a possibility that the client is concerned about the matters corresponding to the keywords) The case management module 2048 may provide the large-scale language model service server 95 with a prompt, the client's voice data, a transcription of the voice data, emotion determination results, etc., so that the server 95 of the large-scale language model service can extract information on the client's concerns as described above.

[0189] In step S1129, the case management module 2048 of the server 20 outputs the case record information to the terminal 10.

[0190] In step S1113, the terminal 10 displays the information of the record of the case.

[0191] FIG. 12 is a diagram showing the flow of processing for breaking down the consultation content from the client, accepting an operation to rearrange the contents, and generating document data.

[0192] In step S1221, the case management module 2048 of the server 20 breaks down the consultation contents of the client and outputs to the terminal 10 an operation screen that displays each of the contents as objects that can be rearranged by the user.

[0193] In step S1211, the terminal 10 displays the information of the record of the case. The terminal 10 displays an operation screen and accepts an operation from the user to rearrange the objects corresponding to the consultation contents.

[0194] In step S1223, the case management module 2048 of the server 20 provides a prompt to the large-scale language model service server 95 to generate sentences in chronological order for the consultation content indicated by each object, based on the rearranged order, in response to the operation to rearrange the objects. As a result, the case management module 2048 obtains a summary result of the consultation content from the client, organized in chronological order, and registers it in the case management database 216. The case management module 2048 outputs the summary result organized in chronological order to the terminal 10.

[0195] In step S1213, the terminal 10 displays the results summarized by the server 95 of the large-scale language model service, organized in chronological order.

[0196] FIG. 13 is a diagram showing the flow of processing for expressing the person correlation diagram in text.

[0197] In step S1311, the terminal 10 displays an operation screen and accepts uploading of an image of a person correlation diagram related to the consultation content from the user.

[0198] In step S1323, the case management module 2048 of the server 20 transmits a prompt to the large-scale language model service server 95 to generate a sentence showing the correlation between people based on the received image of the person correlation diagram.

[0199] Here, the character correlation diagram is a diagram showing the relationships between the characters.

[0200] Specifically, the case management module 2048 provides the server 95 of the large-scale language model service with a rule for interpreting the image of the person correlation diagram as a prompt, as follows, to cause the server 95 of the large-scale language model service to generate a sentence showing the relationship between people.

[0201] For example, the prompt may include the following instructions: Circles, rectangles, and other shapes represent characters. If a shape contains a person's name or image, the shape represents the character. If a character's name is placed near a shape, the shape represents the character and the text represents the character's name. Arrows connecting shapes such as circles and rectangles represent the subject of an action and the recipient of the action. If text is associated with the arrow, the text will indicate the action. If the lines connecting shapes such as circles and rectangles are equal signs, they simply indicate the relationship between people. If text is placed in relation to the equals line, the text will indicate the relationship between the characters. Based on the above rules, please explain the given diagram in words. In step S1325, the case management module 2048 of the server 20 obtains the results of generating sentences showing correlations between people from the large-scale language model service server 95, and registers them in the case record for the client in the case management database 216.

[0202] In step S1327, the case management module 2048 of the server 20 outputs the sentence indicating the correlation between the people to the terminal 10 as information of the case record in the case management database 216.

[0203] In step S1313, the terminal 10 displays a sentence indicating the correlation between people as information of the record of the case.

[0204] FIG. 14 is a diagram showing the flow of a process for presenting a question to the user to increase the resolution of information about a person.

[0205] In step S1411, the terminal 10 accepts the upload of voice data of the consultation content.

[0206] In step S1423, the case management module 2048 of the server 20 acquires a transcription of the voice data of the consultation content and registers it in the case record of the case management database 216.

[0207] In step S1425, if the case management module 2048 of the server 20 identifies a word indicating a person in the transcription data, it presents the client or expert user with a question asking about the relationship between the identified person and other characters involved in the consultation content, and accepts input of a response.

[0208] For example, when a word consisting of a proper noun and a title (such as "san") attached to a name is identified in the transcription data, the case management module 2048 may identify the word as indicating a person. Furthermore, the case management module 2048 may identify a word indicating a person by comparing the transcription data with a dictionary indicating people's names.

[0209] In step S1413, the terminal 10 accepts from the user an answer to the question about the relationship between the people.

[0210] In step S1427, the case management module 2048 of the server 20 registers the answer about the relationship between the people in the record of the case in the case management database 216. The case management module 2048 outputs information about the record including the sentence indicating the relationship between the people to the terminal 10.

[0211] In step S1415, the terminal 10 displays the information of the record of the case.

[0212] <4. Screen Example (First Embodiment)> FIG. 15 shows an example of an operation screen on which a client performs an operation to request a consultation from a specialist.

[0213] The operation screen 1200 is a screen for accepting legal advice requests in chat format from users who are seeking legal advice.

[0214] The account display area 1202 is an area for displaying information about the account of the user who is the client.

[0215] The chat display area 1204 is an area that displays questions entered during legal consultation and answers generated by the large-scale language model service server 95.

[0216] The navigation display area 1212 is an area that displays information to assist the user in receiving legal advice in a chat format.

[0217] In the illustrated example, the navigation display area 1212 informs the user that an answer has been generated for the user ("AI answer display area 1222") and the details of the operation to request an expert.

[0218] The chat input receiving section 1214 is an area where a question can be input by inputting text from the user.

[0219] As shown in the figure, the chat input receiving unit 1214 may display information suggesting what to input in order to prompt the user to input a question, which corresponds to step S1011 in FIG.

[0220] The AI ​​answer display area 1222 is an area that displays an answer generated by the large-scale language model service server 95 in response to a question entered by a user.

[0221] The request display area 1224 is an area for displaying a screen for requesting legal advice from an expert.

[0222] The request display area 1224 corresponds to step S1011 in FIG.

[0223] The candidate attorney display area 1226 is an area that displays lawyers who are candidates for clients.

[0224] The candidate requestee display area 1226 corresponds to step S1011 etc. in Fig. 10. In the example shown in the figure, the candidate requestee display area 1226 receives an operation from the user to select a lawyer to hire.

[0225] The condition specification receiving section 1228 is an operation member that receives the specification of conditions for extracting candidate lawyers to request consultation.

[0226] The condition specification receiving unit 1228 corresponds to step S1011 in FIG.

[0227] The request operation receiving unit 1230 is an operation member that receives an operation to request a consultation with a lawyer.

[0228] The request operation receiving unit 1230 corresponds to step S1011 in FIG.

[0229] FIG. 16 shows an example of an operation screen on which an expert operates upon receiving a consultation request from a client.

[0230] The operation screen 1232 is a screen that displays the consultation content from the client to the user who is an expert and accepts operations to respond to the request.

[0231] The account display area 1234 is an area that displays information about the account of a user who is an expert.

[0232] The request content display area 1236 is an area where the content of the consultation from the client is displayed.

[0233] The details display area 1238 is an area where the details of the consultation from the client are displayed.

[0234] As shown in the figure, the details display area 1238 displays the consultations from the client in a selectable manner by the expert. This corresponds to step S1023 in Fig. 10. In the details display area 1238, as shown in the figure, the server 20 refers to the chat consultation history database 212 and displays the score value of the consultation, etc.

[0235] The contact operation receiving section 1240 is an operation member that receives an operation to contact a client in response to a consultation request from the client.

[0236] The contact operation receiving unit 1240 corresponds to step S1025 in FIG.

[0237] The case display area 1242 is an area where the specialist displays the case that has been requested by the client and is currently being handled (accepted).

[0238] The details display area 1244 is an area that displays details of the case that the expert is handling.

[0239] The search operation receiving section 1246 is an operating member that receives an operation to search for a requested case.

[0240] FIG. 17 shows an example of a screen displaying case records.

[0241] The operation screen 1300 is a screen for accepting operations for managing cases.

[0242] The account display area 1302 is an area where information about the user's account is displayed.

[0243] In the illustrated example, the account display area 1302 displays information for identifying the logged-in user.

[0244] The new case registration area 1304 is an area where an operation to register a new case is accepted.

[0245] The new case registration area 1304 accepts the registration of data for each subfield of the case management database 216 and updates the case management database 216 .

[0246] The client designation section 1306 is an operation member for receiving designation of information about a client related to a case.

[0247] If there is a master in which the information of the client is already registered, the client designation unit 1306 searches the master in response to the user's input of text, etc. In the example of Fig. 18, the information of the client is registered in the client designation unit 1306.

[0248] The interview data designation section 1308 is an operation member that accepts designation of data for an interview between a client and a specialist.

[0249] The interview data designation unit 1308 accepts uploads of interview data such as audio data and recorded data. In addition, although not shown, it also accepts registration of notes related to the case. The example in Figure 18 shows that uploading of recorded data has been accepted.

[0250] The case list display area 1310 is an area for displaying a list of cases.

[0251] The case list display area 1310 reads and displays records from the case management database 216 according to the user's viewing authority. The server 20 also accepts an operation to search for cases by client information, etc., and displays the search results in the list display area 1312, etc. The example in Fig. 18 shows that a new record has been added to the case management database 216 as a result of accepting the registration of a new case in the new case registration area 1304. The example in Fig. 18 also shows that, as a result of accepting the registration of a new case, a prompt has been sent to the large-scale language model service server 95 using the information registered in the case record, and the response result has been registered in the case record.

[0252] The list display area 1312 is an area for displaying a list of records of the case.

[0253] The list display area 1312 accepts an operation from the user to specify each record, and displays detailed information about the specified record. In the example of Fig. 18, in the record of a newly registered case, the transcription viewing operation section 1314 displays that the audio data has been transcribed (corresponding to step S1123 in Fig. 11). Also in the example of Fig. 18, the summary viewing operation section 1316 displays that the consultation content has been summarized by the large-scale language model service server 95 (corresponding to steps S1125 and S1127 in Fig. 11).

[0254] FIG. 18 shows an example of a screen resulting from generating a summary of the consultation content based on the voice data of the consultation content in a case.

[0255] The transcription viewing operation unit 1314 is an operation member that accepts an operation to view transcription data obtained by transcribing the audio data of the consultation content.

[0256] The summary viewing operation section 1316 is an operation member that accepts an operation to view the results of a summary of the consultation content.

[0257] The person correlation display area 1318 is an area for displaying detailed information about the person related to the consultation content.

[0258] In the illustrated example, the person correlation display area 1318 displays the names of people identified by the large-scale language model service server 95 based on the consultation content. In the illustrated example, the user is asked about the relationships between people, and the answer is accepted. This corresponds to step S1425 in FIG. 14.

[0259] The extracted person display area 1320 is an area for displaying the name of a person identified from the consultation content.

[0260] In the illustrated example, the extracted person display area 1320 displays that multiple people have been identified.

[0261] The correlation specification section 1322 is an operation member that accepts specification of an answer to a question about the relationship between people.

[0262] In the illustrated example, the correlation designation unit 1322 receives input of the relationships between the characters from the user.

[0263] FIG. 19 shows an example of an operation screen for accepting an operation to organize the consultation contents.

[0264] The summary result display area 1324 is an area for displaying the results of summarizing the consultation content.

[0265] In the example of Fig. 19, the summary result display area 1324 breaks down the results of summarizing the consultation content, for example, into sentences, and displays each as an object. In the example of Fig. 19, the user is prompted to perform an operation to rearrange the objects in chronological order, and a message is displayed indicating that the sentences will be output in the rearranged order (corresponding to step S1221 in Fig. 12, etc.).

[0266] In the example of FIG. 20, the summary result display area 1324 supports the creation of text for the person correlation diagram.

[0267] The first object 1326 is the result of summarizing the consultation content.

[0268] A first object 1326 receives an operation from the user to rearrange the positions of a second object 1328 and a third object 1330 .

[0269] The second object 1328 is the result of summarizing the consultation content.

[0270] The third object 1330 is the result of summarizing the consultation content.

[0271] The generation operation unit 1332 is an operation member that accepts an operation to generate a sentence based on objects whose order has been specified.

[0272] In the illustrated example, the generation operation unit 1332 receives an operation from the user to cause the large-scale language model service server 95 to generate a sentence that organizes facts related to the consultation content in chronological order, assuming that the facts are arranged in chronological order as a first object 1326, a second object 1328, and a third object 1330.

[0273] FIG. 20 shows an example of an operation screen that accepts an operation to organize the correlations between characters.

[0274] The correlation image designation section 1334 is an operation member that accepts the designation of an image to be uploaded.

[0275] The correlation image designation unit 1334 accepts uploading of an image of a person correlation diagram (corresponding to steps S1311, S1323, etc. in FIG. 13). As shown in the figure, an explanatory text explaining how to create a person correlation diagram may be displayed near the correlation image designation unit 1334. For example, as explained in the prompt in step S1323 above, a text explaining the roles of the shapes, text, etc. used in the person correlation diagram (e.g., "represent each character with a shape such as a rectangle or circle," "enter the names of the characters in association with the shapes," "represent the relationships between characters with arrows and text associated with the arrows") is displayed near the correlation image designation unit 1334 (in the example shown in the figure, in the summary result display area 1324). This allows the user to easily create a person correlation diagram and easily obtain text showing the correlations between people.

[0276] Furthermore, in addition to uploading images, the correlation image designation unit 1334 may also accept uploads of presentation application files and files created with document tools. For example, by acquiring these files and processing them as images, it is possible to generate text showing correlations between people based on the figures and the like contained in these files.

[0277] The generation operation unit 1336 is an operation member that accepts an operation to make the server 95 of the large-scale language model service generate sentences relating to person correlation based on the image uploaded in the correlation image designation unit 1334 .

[0278] In response to a user's operation, the generation operation unit 1336 causes the server 20 to send a prompt to the server 95 of the large-scale language model service to generate a sentence indicating the correlation of people for the image accepted for upload by the correlation image designation unit 1334. This enables the server 20 to obtain the sentence indicating the correlation of the people from the server 95 of the large-scale language model service.

[0279] The correlation display area 1338 is an area for displaying a sentence indicating the correlation between people, which is generated in response to an operation on the generation operation unit 1336 .

[0280] The correlation display area 1338 corresponds to steps S1327, S1313, etc. in FIG.

[0281] <5. Operation (Second Embodiment)> A second embodiment will be described. The expert will listen to the client's concerns and then organize the details. They will then consider what arguments to make when drafting legal documents such as contracts, warning letters, complaints, and answers. However, it can be difficult to predict the amount of research work required, which places a burden on the expert. Furthermore, the research work may be postponed. Therefore, in the second embodiment, an example in which the server 20 supports sorting out points of contention and conducting research corresponding to the points of contention based on the content of the consultation will be mainly described. FIG. 21 is a diagram showing the flow of processing for identifying the points of contention in the consultation content of the client using a large-scale language model and storing them in association with the record of the case.

[0282] In step S2121, the case management module 2048 of the server 20 provides a prompt to the large-scale language model service server 95 to extract legal issues corresponding to the consultation content, based on the consultation content information associated with the case record in the case management database 216. As a result, the case management module 2048 obtains information on legal issues related to the consultation content from the large-scale language model service server 95, and updates the case management database 216.

[0283] The case management module 2048 identifies concerns of the client regarding the consultation content, based on the information about the consultation content in the case management database 216. For example, the case management module 2048 provides a prompt to the large-scale language model service server 95, causing the client to point out concerns about the consultation content. In this way, the case management module 2048 may identify concerns of the client regarding the consultation content, and provide a prompt to the large-scale language model service server 95, causing the server 95 to point out issues corresponding to the identified concerns, thereby acquiring information about legal issues regarding the consultation content.

[0284] In step S2123, the case management module 2048 of the server 20 searches the law database (server 92 for the law search service), case law database (server 91 for the case search service), legal book database (server 93 for the book reading service), and multiple other legal information sources (server 94 for the information media service, server 97 for the SNS, the Internet, etc.) for the issues obtained by the processing of step S2121 that are associated with the case record in the case management database 216.

[0285] In step S2125, the case management module 2048 of the server 20 causes the large-scale language model service server 95 to summarize the results of the search of multiple information sources, and stores the summarized results in the case management database 216 in association with the record of the case related to the issue.

[0286] For example, the case management module 2048 may search the case law search service server 91 for the issue, and detect that a higher court has amended a lower court's judgment in the searched case. The case management module 2048 may present to the user the content of the amendments made to the judgment by the higher court that have been detected.

[0287] Additionally, the case management module 2048 may search for information stored in multiple information sources, searching a first information source that is past information in chronological order, and a second information source that is future in chronological order than the first information source (for example, by referencing the update dates of various data stored in the database), comparing the results of searching the first information source with the results of searching the second information source, and issuing a prompt to the large-scale language model service server 95 to point out any differences, thereby causing the large-scale language model service server 95 to output the differences and store them in the case management database 216. The case management module 2048 may present the output results of the differences to the user.

[0288] FIG. 22 is a diagram showing the flow of processing for generating a list of materials and evidence registered in a case record.

[0289] In step S2211, the terminal 10 accepts an operation from the user on the operation screen to register materials and evidence related to the consultation content.

[0290] In step S2221, the case management module 2048 of the server 20 accepts registration of documents and evidence from the user and registers the information on the documents and evidence in the case record in the case management database 216. The case management database 216 manages documents, evidence, briefs, and other document data used in litigation proceedings related to the consultation content of the case in association with the case record.

[0291] In step S2223, the case management module 2048 of the server 20 sends a prompt to the large-scale language model service server 95 to list various data such as documents, evidence, and briefs based on the data in the case management database 216. In this way, the case management module 2048 uses the large-scale language model to generate information showing the list of various document data registered in the case management database 216.

[0292] In step S2225, the case management module 2048 of the server 20 acquires information indicating the list from the large-scale language model service server 95 and registers it in the case record for the client in the case management database 216.

[0293] In step S2227, the case management module 2048 of the server 20 extracts evidence described in the brief based on the data of the brief. For example, the case management module 2048 identifies the location in the data of the brief that refers to evidence (such as a phrase indicating evidence).

[0294] In step S2229, the case management module 2048 of the server 20 refers to the case management database 216, and outputs to the terminal 10 the list of information and the results of extracting evidence to be described in the brief.

[0295] In step S2213, the terminal 10 displays the list of materials, evidence, etc., and the extracted results of evidence to be described in the brief.

[0296] <6. Screen Example (Second Embodiment)> FIG. 23 shows an example of an operation screen that displays information extracted from a case record using a large-scale language model.

[0297] The case list display area 1340 is an area for displaying a list of cases.

[0298] The list display area 1342 is an area for displaying a list of records of the case.

[0299] In the example of Fig. 23, the list display area 1342 displays in the issue browsing operation unit 1344 that the large-scale language model service server 95 has identified an issue (corresponding to step S2121 in Fig. 21). Also, in the example of Fig. 23, the list display area 1342 displays in the research browsing operation unit 1346 that the large-scale language model service server 95 has searched multiple information sources corresponding to the issue and summarized the results (corresponding to steps S2123 and S2125 in Fig. 21).

[0300] The issue viewing operation unit 1344 is an operation member that accepts an operation to check an issue identified by the server 95 of the large-scale language model service.

[0301] The issue viewing operation unit 1344 displays the issue corresponding to the consultation content in response to the user's operation.

[0302] The research browsing operation section 1346 is an operation member that accepts an operation to search a plurality of information sources for a topic and check a summary of the search results.

[0303] In the example shown, the research viewing operation unit 1346 searches for legal precedents and the large-scale language model service server 95 outputs an indication that the interpretation of the legal precedent has changed. In response to this, the research viewing operation unit 1346 displays a message that the judgment has been revised.

[0304] FIG. 24 shows an example of an operation screen that displays a list of materials and evidence in a case record.

[0305] The evidence list display area 1348 is an area that displays a list of evidence associated with the record of the case specified by the user.

[0306] The evidence list display area 1348 corresponds to steps S2223, S2225, etc. in FIG.

[0307] The evidence acquisition unit 1350 is an operation member that accepts an operation to acquire information on evidence in association with a case.

[0308] The evidence acquisition unit 1350 accepts registration of various data that serve as evidence, such as documents, images, audio, etc. This corresponds to steps S2211 and S2221 in FIG.

[0309] The list display area 1352 is an area for displaying a list of evidence associated with the case.

[0310] The list display area 1352 corresponds to steps S2229 and S2213 in FIG.

[0311] The description confirmation operation unit 1354 is an operation member that accepts an operation to confirm a list of evidence described in document data such as a brief associated with a case.

[0312] The description confirmation operation unit 1354 corresponds to steps S2229 and S2213 in Fig. 22. The server 20 detects descriptions specifying evidence in document data such as briefs, and outputs a list of the detected evidence in a list format or the like.

[0313] <7. Operation (Third Embodiment)> A third embodiment will be described. After hearing the client's concerns, the expert will organize the content of the consultation, clarify the legal issues, and then prepare legal documents such as a complaint and answer by constructing arguments that address the issues. Therefore, in the third embodiment, a technique will be described in which the server 20 supports the creation of such documents as a complaint, an answer, a contract, a term sheet, and the like. FIG. 25 is a diagram showing the flow of a process for generating legal document data based on the information in the case record.

[0314] In step S2511, the terminal 10 accepts an operation to generate a legal product from the user. Examples of legal products include the following. · Contracts, term sheets, and other documents that set out the details of the agreement between the parties Legal arguments between the parties, such as warning letters and responses - Complaints, answers, briefs, and other legal proceedings such as lawsuits or trials In step S2521, the case management module 2048 of the server 20 extracts information to be included in the deliverable from the consultation content information associated with the case record in the case management database 216.

[0315] In step S2523, the case management module 2048 of the server 20 uses the extracted information to generate a prompt for outputting the deliverable using a large-scale language model, and transmits the generated prompt to the server 95 of the large-scale language model service.

[0316] In step S2525, the case management module 2048 of the server 20 obtains the results of the generated deliverable from the large-scale language model service server 95 and registers them in the case management database 216 as a record of the case for the client.

[0317] Here, the case management database 216 manages, as case records, at least one of information on the parties involved in the consultation content and information on the attorneys in the legal proceedings. In step S2521, the case management module 2048 may extract at least one of the managed party information and attorney information. In step S2523, the case management module 2048 may use at least one of the extracted party information and attorney information to generate a prompt to output, as a deliverable, at least one of first document data to be submitted in the legal proceedings, second document data for notifying the parties of their legal arguments, and third document data that is a document regarding the contract terms agreed upon between the parties. In step S2525, the case management module 2048 receives at least one of the first document data, second document data, and third document data as a response output by the large-scale language model service server 95 and registers it in the case record of the case management database 216.

[0318] In addition, in step S2523, when the first document data is to be output, the case management module 2048 may generate a prompt to output at least one of a complaint, an answer, or a brief, and when the third document data is to be output, may generate a prompt to output at least one of a contract or a term sheet setting out the terms of the contract.

[0319] Here, standard writing styles (document formats, headings, etc.) for complaints, answers, and briefs are provided in books (which may be books provided by the book browsing service server 93), websites, etc. The case management module 2048 may refer to these standard writing styles and sample document data, and generate prompts including instructions for applying information related to the consultation content to generate a deliverable, and provide the prompts to the large-scale language model service server 95, thereby causing the large-scale language model service server 95 to generate the deliverable.

[0320] For example, the case management module 2048 may cause the server 95 of the large-scale language model service to output a document such as a rebuttal by providing the server 95 of the large-scale language model service with a prompt such as the following: There are books (for example, available to users on the server 93 of a book browsing service) and web articles that contain examples of general rebuttal documents for making legal claims. The prompt includes an instruction to refer to these examples, for example, examples of rebuttal documents based on essential facts, and create a document that reflects the information on the content of the claim stored in the case management database 216. Include in the prompt instructions to prepare the document in accordance with the guidelines outlined above for writing a general rebuttal (e.g., separate the "denial" and "defense" sections). In addition, to suggest evidence to be submitted to support the argument along with the rebuttal, the case management module 2048 may provide the following prompt to the large-scale language model service server 95: The prompt should include instructions to list evidence submitted in past cases (such as records of each case stored in the case management database 216, precedents stored in a precedent database, or commentaries on precedents published in articles or books) for the defenses asserted in the rebuttal. Include in the prompt a list of evidence presented in previous cases to support a denial in the rebuttal This makes it easier for the user to understand, for example, the level of evidence that led to the defense being accepted, and makes it even easier to prepare a written rebuttal.

[0321] Furthermore, the case management database 216 manages information on term sheets that define contract terms as case records. In step S2523, the case management module 2048 may use the information on the term sheet in the case record to generate a prompt for outputting a contract as third document data. The case management module 2048 receives contract data as a response output from the large-scale language model service server 95.

[0322] Here, for term sheets and contracts, standard writing styles (document formats, headings, etc.) are provided in books (which may be books provided by the book reading service server 93), websites, etc. The case management module 2048 may refer to these standard writing styles and sample document data, and generate a prompt including instructions for applying information related to the consultation content (such as contract terms) to generate a deliverable, and provide this to the large-scale language model service server 95, thereby causing the large-scale language model service server 95 to generate the deliverable.

[0323] Additionally, in step S2523, the case management module 2048 may generate a prompt that includes creating a contract definition by referring to an encyclopedia or dictionary database that contains terminology definitions, thereby allowing the large-scale language model service server 95 to output a contract with unified terminology.

[0324] The case management module 2048 stores the received response from the large-scale language model service server 95 in the case management database 216 in association with the record of the case from which the information related to prompt generation was extracted.

[0325] In step S2527, the server 20 outputs the information on the deliverables of the record of the case in the case management database 216 to the terminal 10.

[0326] In step S2513, the terminal 10 displays information about the generated product.

[0327] FIG. 26 is a diagram showing the flow of a process for generating possible counterarguments to a point of contention.

[0328] In step S2611, the terminal 10 receives from the user an operation to generate a possible counterargument to the issue, based on the information on the issue stored in the issue management database 216 in association with the case.

[0329] In step S2621, the case management module 2048 of the server 20 generates a prompt to cause the large-scale language model to output a counterargument to the content of the claims between the parties in the document data held in the case management database 216.

[0330] Specifically, the case management database 216 manages information on written data describing the content of arguments asserted between the parties regarding the consultation for each point of contention as a case record. The case management module 2048 generates a prompt that causes the large-scale language model to output a rebuttal to the content of arguments asserted between the parties in the written data.

[0331] In step S2623, the case management module 2048 of the server 20 transmits the generated prompt to the large-scale language model service server 95. In this way, the case management module 2048 provides the generated prompt to the large-scale language model, causing the large-scale language model service server 95 to output a rebuttal.

[0332] In step S2625, the case management module 2048 of the server 20 acquires the outputted objection information from the large-scale language model service server 95, and registers it in the case management database 216 as the case record for the client.

[0333] In step S2621, the case management module 2048 may search for rebuttals based on the content of the claims between the parties in the document data, using the content of the claims in the document data of each case (including other cases other than the case for which a rebuttal is to be output) stored in the case management database 216 or data on published judgments as search targets, and generate a prompt to summarize the search results in a large-scale language model. In step S2623, the case management module 2048 may provide the generated prompt to the large-scale language model, thereby outputting the summarized rebuttal to the large-scale language model service server 95.

[0334] For example, depending on the type of claim in a case (classified by the underlying clause), such as a traffic accident or a claim for the return of an excessive payment, the content of the arguments made by the parties regarding the points at issue in past cases can be identified from the judgments and each case managed in the case management database 216, and a prompt to summarize the content of the identified rebuttals can be given to the server 95 of the large-scale language model service, thereby allowing the server 95 of the large-scale language model service to generate the content of the rebuttals that the other party is likely to make regarding the points at issue.

[0335] In step S2627, the case management module 2048 of the server 20 outputs the objection information of the case record in the case management database 216 to the terminal 10.

[0336] As a result, the case management module 2048 presents the counterargument output by the large-scale language model service server 95 to the user.

[0337] In step S2613, the terminal 10 displays information about the generated objection.

[0338] FIG. 27 is a diagram showing the flow of a process for supporting the reading and comprehension of a contract.

[0339] In step S2711, the terminal 10 accepts an operation from the user to specify a contract in the case record.

[0340] In step S2721, the case management module 2048 of the server 20 generates a prompt that illustrates the citation relationship of each clause in the contract data specified by the user. The prompt includes information that specifies the contract data (for example, a link to the contract data or the full text of the contract data).

[0341] In step S2723, the case management module 2048 of the server 20 transmits the generated prompt to the server 95 of the large-scale language model service.

[0342] In step S2725, the case management module 2048 of the server 20 obtains the output information on the illustration of the citation relationships of each clause from the large-scale language model service server 95 and registers it in the case record for the client in the case management database 216.

[0343] In step S2727, the case management module 2048 of the server 20 outputs to the terminal 10 information on the illustration of the citation relationship of each clause in the case record.

[0344] In step S2713, the terminal 10 displays the generated information on the illustration of the citation relationship of each clause.

[0345] <8 Screen Example (Third Embodiment)> FIG. 28 shows an example of an operation screen for generating legal document data.

[0346] The generation support section 1356 is an area that accepts operations to support the generation of a deliverable.

[0347] The registration information designation section 1358 is an operation member that accepts designation of information on the case to be included in the result to be generated.

[0348] In the illustrated example, the registered information designation unit 1358 designates that the information of the parties involved, the content of the arguments on the issues, etc., among the information on the case, be included in the deliverable. This corresponds to steps S2511, S2521, etc. in FIG. 25.

[0349] The artifact specification unit 1360 is an operation member that accepts specification of the type of artifact to be generated by the server 95 of the large-scale language model service.

[0350] The deliverable designation unit 1360 accepts the following designations from the user as the type of deliverable: The first document data to be submitted in legal proceedings (e.g., complaint, answer, brief) Secondary document data for notifying the parties of their legal claims (e.g., warning letters, response letters) Third document data that is a document regarding the contractual terms agreed upon between the parties (e.g., a contract, a term sheet setting out the contractual terms) The dictionary specification unit 1362 is an operation member that accepts specification of a dictionary to be referred to by the server 95 of the large-scale language model service when generating a deliverable.

[0351] The generation operation unit 1364 is an operation member that accepts an operation to cause the server 95 of the large-scale language model service to generate a product based on specified conditions.

[0352] The generation operation unit 1364 corresponds to step S2511 in FIG.

[0353] The viewing operation unit 1366 is an operation member that accepts an operation to view the results generated by the server 95 of the large-scale language model service.

[0354] FIG. 29 shows an example of an operation screen that displays possible counterarguments to the points at issue.

[0355] The rebuttal generation section 1368 is an area that accepts an operation to generate a rebuttal that is expected from the other party with respect to the point at issue.

[0356] The generation operation unit 1370 is an operation member that accepts an operation to generate a counterargument by the large-scale language model service server 95 in response to the content of the argument registered in the record of the case.

[0357] The generation operation unit 1370 corresponds to step S2611 in FIG.

[0358] The generated result display area 1372 is an area for displaying the counterarguments generated by the server 95 of the large-scale language model service.

[0359] The generation result display area 1372 corresponds to steps S2627, S2613, etc. in FIG.

[0360] The case browsing operation unit 1374 is an operation member that accepts an operation to browse other cases that were used as information sources when the large-scale language model service server 95 generated a counterargument.

[0361] The case viewing operation unit 1374 may, for example, display links to other cases managed in the case management database 216, and information on the content of claims (including the content of claims of the opposing party) contained in the document data registered in other cases.

[0362] The precedent viewing operation unit 1376 is an operation member that accepts an operation to view a precedent that was used as an information source when the server 95 of the large-scale language model service generated a rebuttal.

[0363] The case law viewing operation unit 1376 may, for example, display excerpts of cases stored in the case law search service server 91, links to cases, links to court cases, excerpts from books that mention cases in the book viewing service server 93, links to the books, etc.

[0364] FIG. 30 shows an example of an operation screen that supports the reading and comprehension of a contract.

[0365] The contract work support section 1378 is an area that receives operations to support work to create a contract by referring to the contract based on the data stored in the case management database 216 .

[0366] The generation operation unit 1380 is an operation member that accepts an operation to cause the large-scale language model service server 95 to generate a contract based on data registered in a specified case.

[0367] In the illustrated example, the generation operation unit 1380 accepts an operation to adjust the description of the data of the contract to be registered in the case, which corresponds to step S2711 in FIG.

[0368] The generated result display area 1382 is an area where the contract generated by the server 95 of the large-scale language model service is displayed.

[0369] The information media service server display area 1384 is an area that displays the results of the citation relationships of the contract output by the large-scale language model service server 95.

[0370] In the illustrated example, when there is a clause citation relationship, the server display area 1384 of the information media service displays a list of the citing source and the citing clause side by side. This corresponds to steps S2727, S2713, etc. in FIG. 27.

[0371] The dictionary designation section 1386 is an operation member that accepts the designation of a dictionary that defines the wording to be used in the contract.

[0372] The template registration operation section 1388 is an operation member that accepts an operation to register the generated contract as a template.

[0373] As shown in the example, the template registration operation unit 1388 displays that registration of a template is accepted on a clause-by-clause basis. Using the newly registered or updated template in this manner, the server 20 causes the large-scale language model service server 95 to generate a contract in response to a user's operation. For example, the server 20 may refer to the stored contract templates, generate a prompt to create a contract in accordance with specified conditions, and transmit the prompt to the large-scale language model service server 95 to obtain the generated contract. The server 20 may also make registered contract templates searchable and provide the templates to the user.

[0374] <Modification> The above-described embodiments may be combined with each other. In addition to the aspects described in the above-described embodiments, the following may be adopted.

[0375] (1) Improved reliability of generated answers In the above embodiment, if the answer generated by the large-scale language model service server 95 includes a case law number, a legal provision, a guideline citation, etc. as evidence, the server 20 may check whether the generated answer is an actual case law, law, guideline, etc. by searching databases such as the case law search service server 91, the legal search service server 92, the book browsing service server 93, and the information media service server 94. Specifically, the server 20 determines whether the answer generated by the large-scale language model service server 95 includes a description of the content of the case law and the case law number. For example, case law numbers are assigned according to predetermined rules (e.g., "Heisei XX Year (Gyo-Ke) No. XXXXX"), and extracts descriptions that conform to these rules as the case law number. The server 20 queries the case law search service server 91, etc., based on the case law number to obtain the judgment, abstract, etc. of the case law and determines whether they are similar to or identical to the results generated by the large-scale language model service server 95. For example, the server 20 may determine whether the documents are similar based on the degree of agreement between words contained in the sentences, or may vectorize the meanings of the documents and determine whether the documents are similar based on the distance between the vectors.

[0376] If the server 20 determines that they are not similar, it may have the large-scale language model service server 95 generate a new answer, or may respond to the user with the number of an actual case that exists as a result of an inquiry to the case law search service server 91, etc. For example, it may search for similar judgments from the case law search service server 91, etc., for the introduction to a case included in the answer generated by the large-scale language model service server 95, and respond with the number of the case that corresponds to the search result.

[0377] This allows the server 95 of the large-scale language model service to determine whether a generated answer is valid by referring to the original case, etc., even if the answer contains a non-existent case, etc.

[0378] Furthermore, when a case law number, a legal provision, a guideline source, a reference document, or the like is stated as a basis in an answer generated by the large-scale language model service server 95, the server 20 may perform a check to determine whether the content of the generated answer is stated in the reference document, etc., by issuing a prompt to the large-scale language model service server 95 to cause the check. Based on the check result, the server 20 may evaluate the reliability of the answer generated by the large-scale language model service server 95, and may present the evaluation result to the user.

[0379] For example, the server 20 may present the generated answer and the basis to the user, and may also present to the user whether or not the basis contains any description as a result of checking the basis.

[0380] Furthermore, for example, if the server 95 of the large-scale language model service performs the matching and outputs a message indicating that there is no description in the evidence, the server 20 may notify the user that "Answer generation failed" or the like without presenting the user with the answer generated by the server 95 of the large-scale language model service.

[0381] (2) Specify domestic and international information sources. The server 20 may receive from the user a designation of whether the information is published domestically or overseas (or in a specific country), and may then refer to the information source according to the user's designation (for example, if the user designates Europe, the server 20 may define a prompt to summarize the results of a search for information in Europe) and receive an instruction to have the large-scale language model service server 95 generate an answer.

[0382] This allows users to be provided with information on legal reorganization as well as overseas cases.

[0383] (3) Classify the question to generate an answer using a large-scale language model service, and create prompts based on the classification results. In addition to what has been described in the above embodiment, in order to have the large-scale language model service generate the answer intended by the user, the user's question may be classified, a prompt may be created based on the classified results, and the created prompt may be provided to the server 95 of the large-scale language model service.

[0384] For example, the server 20 may store a list of categories for classifying questions in advance, and for each category, a standard for causing the large-scale language model service to generate an answer may be prepared.

[0385] When the server 20 receives a question input from a user, it determines which category in the question list the input question falls into. For example, the server 20 receives the user's question as input and provides a prompt to the server 95 of the large-scale language model service stating, "Please answer which category in the category list the input question falls into." This causes the server 95 of the large-scale language model service to generate an answer indicating which category in the category list the user's question falls into. When the server 20 receives the answer generated by the server 95 of the large-scale language model service, the server 20 references the category list and generates a prompt including "criteria for generating an answer" associated with the corresponding category, and provides the generated prompt to the server 95 of the large-scale language model service. This allows the server 20 to obtain the answer generated by the server 95 of the large-scale language model service for the question received from the user based on the "criteria for generating an answer" indicated in the category list.

[0386] For example, the server 20 may categorize the user's question and select information resources such as books and legal precedents as "criteria for generating an answer."

[0387] For example, if it can be determined from the user's question that the user wants to know about the procedure, the answer to the user may not need to include information about legal precedents. Therefore, in this case, the server 20 creates a prompt using the absence of legal precedents as the "criterion for generating an answer." For example, if the user inputs a question such as "Please tell me about points to note regarding a mutually agreed-upon divorce," the server may want to provide an answer about the procedure.

[0388] Furthermore, if it can be determined from the user's question that the user wants to know about cases or definitions of terms, an answer may be generated based on legal precedents as the "criterion for generating an answer."

[0389] In this way, by providing a prompt for the classification to which the question applies, rather than sending all the information at once to the large-scale language model service server 95 and having it generate an answer, it may be possible to reduce the amount of computing resources consumed by the large-scale language model service server 95.

[0390] (4) Re-examination under the direction of an expert when a point of discussion or research is conducted by the large-scale language model service server 95 based on the information in the case record. In the above embodiment, using Figures 21 to 25, we have explained that when consultation content data is registered in a case record, the large-scale language model service server 95 extracts legal issues, performs a search corresponding to the issues, and registers the results in the case record.

[0391] The server 20 may present the expert user with the issues extracted by the large-scale language model service server 95 and a summary of the search results corresponding to the issues, accept confirmation from the expert, and register them in the case management database 216. At this time, the server 20 may accept instructions from the expert, such as a lawyer, to redo the extraction of the issues and the search investigation corresponding to the issues, and may re-extract the issues and present the results to the user.

[0392] (5) Compare the results of legal interpretations with search results from sources other than legal sources, such as law books and precedents. The server 20 may present legal interpretations given in law-related books and precedents to the user over time in a manner that allows comparison with the values ​​of people in the world.

[0393] For example, the server 20 searches the information media service server 94 and the SNS server 96 for legal issues. For example, by searching SNS etc. for recent past legal precedents, the reactions of SNS users can be obtained as search results. The server 20 may compare interpretations of past legal precedents with the results of searching user reactions on SNS etc. and summarizing them using the large-scale language model service server 95, and present these results to the user. This can suggest possible future changes in legal precedents, legal amendments, and academic theories.

[0394] (6) Support for reading and comprehending court decisions In the above embodiment, an example of searching for legal issues and precedents etc. corresponding to the issues has been described.

[0395] Here, if there is a judgment of a higher court that amends the original judgment, the server 20 may reinterpret the original judgment based on the content of the amendment in the judgment of the higher court and display it. This makes it possible to make the high court judgment easier to read, for example, by partially amending the original judgment.

[0396] (7) Preparation of reports on the results of investigations into legal issues The server 20 may also cause the large-scale language model service server 95 to generate a report in accordance with a predetermined format for documents, email text, etc., to facilitate the expert reporting the results of an investigation based on legal issues regarding a case to the client.

[0397] (8) Generate a contract while maintaining the indentation settings of the contract The server 20 may set indents in the contract data so that each article, paragraph, and subparagraph can be identified (for example, by using different amounts of indentation for articles, paragraphs, and subparagraphs), and generate the contract based on the information in the case record.

[0398] Although several embodiments of the present disclosure have been described above, these embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are intended to be included in the scope of the inventions and their equivalents as defined in the claims, as well as in the scope and spirit of the inventions.

[0399] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory.

[0400] In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0401] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0402] <Additional Notes> The matters explained in the above embodiment will be supplemented below.

[0403] <Additional Notes to the First Embodiment>

[0404] (Supplementary Note 1) A program for operating a computer having a computer processor, the program causing the computer processor to execute the steps of: accepting input of consultation data indicating the content of a consultation from a client; obtaining a summary of the consultation content by prompting a large-scale language model to summarize the consultation content indicated in the consultation data along predetermined items; and associating the consultation content summarized along the predetermined items with the client and storing the summary in a memory unit so that it can be referenced by an expert who responds to the client's consultation.

[0405] (Appendix 2) A program as described in Appendix 1, in which, in the receiving step, voice data indicating the content of the consultation is received as consultation data, and in the step of acquiring transcription data obtained by transcribing the voice data and storing it in a memory unit, the transcription data is stored in association with the client, and at least one of information on the results of determining the speaker in the transcription data, information on the results of determining emotions, and information on the timing of the consultation from the client is further stored in the memory unit.

[0406] (Appendix 3) A program described in any of Appendices 1 to 2, wherein in the acquiring step, a prompt is given to organize the consultation content contained in the consultation data in chronological order, thereby acquiring the summarized results, and in the storing step in a memory unit, the summarized results organized in chronological order are stored in association with the client.

[0407] (Appendix 4) A program as described in Appendix 3, which uses a large-scale language model to divide and organize the consultation content in chronological order, and based on the results summarized, displays each divided result on a screen as an object, accepts an operation from the user to rearrange the objects, and in response to the operation to rearrange the objects, provides the large-scale language model with a prompt to generate sentences in chronological order based on the rearranged order, thereby further obtaining summarized results organized in chronological order.

[0408] (Appendix 5) A program described in any of Appendices 1 to 4, wherein the memory unit manages each consultation from a client as a case including predetermined management items, and in the step of storing in the memory unit, each item of the consultation content summarized according to the predetermined items is stored in association with each management item managed as a case in the memory unit.

[0409] (Appendix 6) A program as described in Appendix 5, in which a memory unit manages, as predetermined management items, at least one of the consultation content from the client, the next action to be taken, and the client's concerns as a case, and in the acquisition step, obtains the summary results by providing a prompt to a large-scale language model to summarize at least one of the predetermined management items as a predetermined item.

[0410] (Appendix 7) A program as described in Appendix 6, in which, in the receiving step, audio data indicating the content of the consultation is received as consultation data, the audio data is transcribed into transcription data, in the step of acquiring and storing the transcription data in a memory unit, the transcription data is stored in association with the client, and information on the results of determining the client's emotions is further stored in the memory unit, in the acquiring step, the client's concerns are extracted based on the audio data of the client's consultation content and the information on the results of determining the emotions, and in the step of storing the information on the client's concerns in a memory unit, the information on the client's concerns is stored as case information.

[0411] (Appendix 8) The program according to any one of Appendices 1 to 7, further causing the computer processor to execute the steps of: accepting input of image data showing a person correlation diagram related to the consultation content from the client; analyzing the image data and obtaining sentences showing the person correlation by prompting the large-scale language model to generate sentences showing the person correlation; and outputting the obtained sentences showing the person correlation.

[0412] (Appendix 9) A program that further executes the following steps: (a) in a receiving step, audio data indicating the content of the consultation is received as consultation data; (b) in a step of acquiring transcription data obtained by transcribing the audio data and storing the transcription data in a memory unit, the transcription data is stored in association with the client; (c) in the transcription data, a step of identifying words indicating a person; (d) in the case where a word indicating a person is identified, a step of presenting a question to the client or the expert asking about the relationship between the identified person and other characters involved in the content of the consultation and accepting input of a response; and a step of storing the accepted response in a memory unit.

[0413] (Supplementary Note 10) A method executed by a computer having a computer processor, the method comprising the steps of: receiving input of consultation data indicating the content of a consultation from a client; obtaining a result of summarizing the consultation content by prompting a large-scale language model to summarize the consultation content indicated in the consultation data along predetermined items; and associating the consultation content summarized along the predetermined items with the client and storing the summarized consultation content in a memory unit so that it can be referenced by an expert who responds to the client's consultation.

[0414] (Supplementary Note 11) An information processing device, wherein a control unit of the information processing device executes the steps of: accepting input of consultation data indicating the content of a consultation from a client; obtaining a result of summarizing the consultation content by prompting a large-scale language model to summarize the consultation content indicated in the consultation data along predetermined items; and associating the consultation content summarized along the predetermined items with the client and storing the summarized consultation content in a memory unit so that it can be referenced by an expert who responds to the client's consultation.

[0415] <Additional notes on the second embodiment>

[0416] (Appendix 1) A program for operating a computer having a processor, the program being configured to manage each consultation content from a client as a case record in a memory unit, the program causing the processor to execute the steps of: accepting registration of the consultation content from the client and storing it in the memory unit in association with the case record; acquiring information on the points of discussion by providing a large-scale language model with a prompt to extract points of discussion corresponding to the consultation content based on the information on the consultation content associated with the case record; and storing the acquired information on the points of discussion in the memory unit in association with the case record related to the consultation content.

[0417] (Appendix 2) The program described in Appendix 1, wherein in the acquiring step, based on information about the consultation content, the concerns that the client has regarding the consultation content are identified, and issues corresponding to the identified concerns are acquired using a large-scale language model.

[0418] (Appendix 3) The program is a program described in any of Appendixes 1 to 2, which causes a processor to further execute the steps of searching a statute database, case law database, legal book database, and other legal information sources for an issue stored in the memory unit in association with a case record, summarizing the results of searching the multiple information sources using a large-scale language model, and storing the summarized results in the memory unit in association with the case record related to the issue.

[0419] (Appendix 4) A program as described in Appendix 3, in which in the searching step, a case law database is searched, and in the searched case, a higher court has amended the judgment of a lower court, and the contents of the amendments made by the detected higher court are presented to the user.

[0420] (Appendix 5) The program described in Appendix 3, wherein in the searching step, for information stored in a plurality of information sources, a first information source that is past information in chronological order and a second information source that is future information in chronological order than the first information source are searched, the results of searching the first information source and the results of searching the second information source are compared, and the content that differs is output to a large-scale language model, and the output results of the content that differs are presented to the user.

[0421] (Appendix 6) A program described in any of Appendices 1 to 5, which manages in a memory unit documents, evidence, preparatory documents, and other written data used in litigation proceedings related to the consultation content of a case in association with the case record, and generates information showing a list of these documents based on the various written data registered in the memory unit using a large-scale language model.

[0422] (Appendix 7) A program as described in Appendix 6, which manages in a memory unit documents related to the consultation content of a case, evidence, preparatory documents and other written data used in litigation proceedings in association with the case record, extracts evidence described in the preparatory documents based on the data of the preparatory documents registered in the memory unit, and presents the extracted results to the user.

[0423] (Appendix 8) 1. A computer-implemented method comprising: a processor; and a memory unit, the method comprising: The memory unit is configured to manage each consultation content from the client as a case record, and the method includes the steps of: accepting registration of the consultation content from the client and storing it in the memory unit in association with the case record; acquiring information on the points of discussion by providing a large-scale language model with a prompt to extract points of discussion corresponding to the consultation content based on the information on the consultation content associated with the case record; and storing the acquired information on the points of discussion in the memory unit in association with the case record related to the consultation content.

[0424] (Appendix 9) An information processing device having a memory unit, configured to manage each consultation content from a client as a case record in the memory unit, wherein a control unit of the information processing device executes the steps of accepting registration of the consultation content from the client and storing it in the memory unit in association with the case record; acquiring information on the points of discussion by providing a large-scale language model with a prompt to extract points of discussion corresponding to the consultation content based on the information on the consultation content associated with the case record; and storing the acquired information on the points of discussion in the memory unit in association with the case record related to the consultation content.

[0425] <Additional notes on the third embodiment>

[0426] (Appendix 1) A program for operating a computer having a processor, the program being configured to manage, in a memory unit, each consultation content from a client as a case record, the program causing the processor to execute the following steps: extracting information to be included in a deliverable from information on the consultation content associated with the case record; using the extracted information to generate a prompt that causes the deliverable to be output by a large-scale language model; providing the generated prompt to the large-scale language model and accepting a response from the large-scale language model; and presenting the deliverable as the accepted response to a user.

[0427] (Appendix 2) A program as described in Appendix 1, wherein the memory unit manages, as case records, at least one of information on the parties involved in the consultation content or information on the agents in the legal proceedings; in the extraction step, at least one of information on the parties or information on the agents is extracted; in the generation step, at least one of the extracted information on the parties or information on the agents is used to generate a prompt to output, as an output, at least one of first document data to be submitted in the legal proceedings, second document data for notifying the parties of their legal claims, and third document data which is a document regarding the contract terms agreed upon between the parties; and in the receiving step, at least one of the first document data, second document data, and third document data is accepted as the output response.

[0428] (Appendix 3) The program described in Appendix 2, wherein in the generating step, when the first document data is to be output, a prompt is generated to output at least one of a complaint, an answer, or a brief, and when the third document data is to be output, a prompt is generated to output at least one of a contract or a term sheet setting out the terms of the contract.

[0429] (Appendix 4) A program as described in any of appendices 2 to 3, wherein a memory unit manages information on a term sheet that defines contract terms as a record of the project, and in a generating step, uses the information in the term sheet to generate a prompt that causes a contract to be output as third document data, and in a receiving step, receives the contract data as the output response.

[0430] (Appendix 5) 5. The program of claim 4, wherein the generating step generates a prompt that includes creating a contract definition by referring to an encyclopedia or dictionary database that contains definitions of terms.

[0431] (Appendix 6) A program as described in any of Appendices 1 to 5, wherein the memory unit manages, as a record of a case, information on written data describing the content of arguments made between the parties regarding the consultation for each point of contention, and the program further causes the processor to generate a prompt that causes the large-scale language model to output a rebuttal to the content of arguments made between the parties in the written data, provide the generated prompt to the large-scale language model, thereby causing the large-scale language model to output the rebuttal, and present the outputted rebuttal to the user.

[0432] (Appendix 7) A program as described in Appendix 6, which searches for rebuttals based on the content of the arguments between the parties in the written data, searching the content of the arguments in the written data of each case stored in a memory unit or the data of published judgments, generates prompts to summarize the search results in a large-scale language model, and outputs the summarized rebuttals to the large-scale language model by providing the generated prompts to the large-scale language model.

[0433] (Appendix 8) A program described in any of Appendices 1 to 7, in which a memory unit manages contract data in association with case records, a generating step generates a prompt that illustrates the citation relationship of each clause in the contract data, and a receiving step receives the illustrated information by providing the prompt to a large-scale language model.

[0434] (Appendix 9) 9. The program according to any one of appendices 1 to 8, wherein the response from the large-scale language model received in the receiving step is stored in a memory unit in association with the record of the case from which information related to prompt generation was extracted.

[0435] (Appendix 10) A method operated by a computer having a processor, configured to manage each consultation content from a client as a case record in a memory unit, the method comprising the steps of: extracting information to be included in a deliverable from information on the consultation content associated with the case record; using the extracted information to generate a prompt that causes the deliverable to be output by a large-scale language model; providing the generated prompt to the large-scale language model and accepting a response from the large-scale language model; and presenting the deliverable as the accepted response to a user.

[0436] (Appendix 11) An information processing device configured to manage each consultation content from a client as a case record in a storage unit, wherein a control unit of the information processing device executes the steps of: extracting information to be included in a deliverable from information on the consultation content associated with the case record; using the extracted information, generating a prompt that causes the deliverable to be output by a large-scale language model; providing the generated prompt to the large-scale language model and accepting a response from the large-scale language model; and presenting the deliverable as the accepted response to a user.

Claims

1. A program for operating a computer having a processor, The storage unit is configured to manage each consultation content from the client as a case record, The program causes the processor to: a step of accepting registration of consultation contents of the client, associating the consultation contents with the case record, and storing the same in the storage unit; acquiring information on the issues by providing a prompt to a large-scale language model to extract issues corresponding to the consultation content based on the consultation content information associated with the case record; and storing the acquired information on the points of contention in the storage unit in association with a record of the case related to the consultation content.

2. 2. The program according to claim 1, wherein, in the acquiring step, concerns that the client has about the consultation content are identified based on the information about the consultation content, and points of contention corresponding to the identified concerns are acquired using the large-scale language model.

3. The program further causes the processor to searching a plurality of legal information sources, including a statute database, a case law database, a law book database, and the like, for the issue stored in the storage unit in association with the case record; Summarizing the results of the search of the plurality of information sources using the large-scale language model; 2. The program according to claim 1, further comprising: storing the summarized results in the storage unit in association with a record of the case related to the point of contention.

4. In the searching step, the case precedent database is searched, and it is detected that a higher court has amended a lower court's judgment in the searched case; The program according to claim 3 , wherein the program presents to a user the content of the amendments made to the judgment sentence amended by the higher court relating to the detection.

5. In the searching step, a first information source that is past information in time series and a second information source that is future information in time series than the first information source are searched for in the information stored in the plurality of information sources; comparing the search results of the first information source with the search results of the second information source, and outputting differences to the large-scale language model; 4. The program according to claim 3, wherein an output result of the content difference is presented to a user.

6. The storage unit manages, in association with the record of the case, documents related to the consultation content of the case, evidence, briefs, and other document data used in litigation proceedings, 2. The program according to claim 1, further comprising: generating information indicating a list of the various document data registered in the storage unit using the large-scale language model.

7. The storage unit manages, in association with the record of the case, documents related to the consultation content of the case, evidence, briefs, and other document data used in litigation proceedings, 7. The program according to claim 6, wherein evidence described in a brief is extracted based on data of the brief registered in the storage unit, and the extracted results are presented to a user.

8. 1. A method implemented by a computer having a processor and a memory, comprising: The storage unit is configured to manage each consultation content from the client as a case record, The method further comprises the processor: a step of accepting registration of consultation contents from a client, and storing the contents in the storage unit in association with a case record; acquiring information on the issues by providing a prompt to a large-scale language model to extract issues corresponding to the consultation content based on the consultation content information associated with the case record; and storing the acquired information on the points of contention in the storage unit in association with a record of the case related to the consultation content.

9. An information processing device including a storage unit, The storage unit is configured to manage each consultation content from the client as a case record, a control unit of the information processing device, a step of accepting registration of consultation contents from a client, and storing the contents in the storage unit in association with a case record; acquiring information on the issues by providing a prompt to a large-scale language model to extract issues corresponding to the consultation content based on the consultation content information associated with the case record; and storing the acquired information on the points of discussion in the storage unit in association with a record of a case related to the consultation content.

Images