Program, method, and information processing apparatus

Abstract

To provide a program, a method and an information processor for further promoting the solution of the problem of a consultant based on legal consultation.SOLUTION: In the system, the server stores, in the storage unit, information for managing a plurality of stages until problem solving for the legal consultation, and the program causes the server to execute a step of referring to the information stored in the storage unit and presenting any one of the plurality of stages to the user, a step of receiving an input of a question from the user while presenting any one of the plurality of stages to the user, a step of causing the large scale language model to generate an answer to the input question and outputting the generated answer to the user, a step of determining that a condition for proceeding to a next stage subsequent to a certain stage of the plurality of stages is satisfied and presenting information indicating that the next stage has been advanced when it is determined that the condition for proceeding to the next stage is satisfied, and a step of outputting the answer generated by the large scale language model.SELECTED DRAWING: Figure 9

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] On the other hand, before consulting a legal expert, clients may gather information themselves by searching the Internet, referring to Q&A sites, or referring to books, and then attempt to solve the problem based on the legal consultation.

[0007] However, some clients may not be able to think about how to proceed, and may not be motivated to seek legal advice from a legal professional, leaving the problem unresolved. As a result, they may not even reach the stage where a legal consultation professional can provide their services.

[0008] Therefore, there is a need for technology that can further promote the resolution of clients' problems through legal consultation. [Means for solving the problem]

[0009] According to one embodiment of the present disclosure, there is provided a program for operating a computer having a processor, wherein a memory unit stores information for managing multiple stages leading up to the resolution of a legal consultation issue, and the program causes the processor to execute the following steps: referencing the information stored in the memory unit and indicating to a user which of the multiple stages the user is at; accepting a question from the user while indicating to the user which of the multiple stages the user is at; generating an answer to the input question using a large-scale language model and outputting the generated answer to the user; and determining whether the conditions for proceeding to the next stage following a certain stage of the multiple stages have been met; and if it is determined that the conditions for proceeding to the next stage have been met, in the step of indicating which stage the user is at, the program presents information indicating that the user has progressed to the next stage. [Effects of the Invention]

[0010] According to the present disclosure, it is possible to further encourage clients to resolve their problems through legal consultation. [Brief explanation of the drawings]

[0011] [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 expert consultation history database 214. As shown in FIG. [Figure 8] FIG. 8 is a diagram showing the data structure of the stage management database 215. [Figure 9] FIG. 9 is a flowchart showing the flow of a process in which a plurality of stages of legal consultation are presented to the user, and the user is informed that they can proceed to the next stage by accumulating information at a certain stage. [Figure 10] FIG. 10 is a flowchart showing the flow of processing in which the chat system presents a specific question to a user, accepts a reply from the user, and generates an answer using the LLM. [Figure 11] FIG. 11 is a flowchart showing the process of generating an answer using the LLM when a user corrects a question, assuming that all questions posted after the corrected question have also been corrected. [Figure 12] FIG. 12 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. [Figure 13] FIG. 13 is an example of a screen that displays to the user a number of steps leading up to the resolution of a problem regarding legal advice, and assists the user in inputting a question. [Figure 14] FIG. 14 shows an example of a screen in which the chat system presents a specific question to the user, accepts the input of a response, and generates an answer using the LLM. [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. DETAILED DESCRIPTION OF THE INVENTION

[0012] 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.

[0013] <Outline of embodiment> <1.1 Overall system configuration> FIG. 1 is a diagram showing the configuration of the system 1.

[0014] 1 includes a legal consultation service server 20, 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 for communication via a network 80.

[0015] In the illustrated example, terminals such as terminal 10 and terminal 10A are shown as terminals used by users of the legal consultation service provided by server 20, and each user operates a terminal.

[0016] 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.

[0017] The terminal 10 is a device operated by a user. In this embodiment, it is assumed that a client who seeks legal advice operates the terminal 10. It is also assumed that an expert who provides an answer to the legal advice operates the terminal 10A. The terminal 10 and the terminal 10A have the same functional configuration. The 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 .

[0018] The communication IF 12 is an interface for inputting and outputting signals so that the terminal 10 can communicate with an external device.

[0019] 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.).

[0020] The output device 14 is a device (such as a display or speaker) for presenting information to the user.

[0021] 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).

[0022] The storage 16 is for storing data, and is, for example, a flash memory or a hard disk drive (HDD).

[0023] 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.

[0024] The server 20 is a device for providing a legal consultation service to a user. In this embodiment, the server 20 receives 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 answers to the received legal consultation requests, and returns the generated answers to the users, thereby providing the legal consultation service.

[0025] In this embodiment, the server 20 matches users who are experts with users who are seeking legal advice, thereby accepting requests for legal advice from the users. For example, the content of the consultation by the user may be posted on a bulletin board that can be viewed by third parties, and the expert's response may also be made public, or the content of the consultation by the user may be kept private and not disclosed to third parties, allowing the user to consult with the expert.

[0026] The server 20 includes a communication IF 22 , an input / output IF 23 , a memory 25 , a storage 26 , and a processor 29 .

[0027] The communication IF 22 is an interface for inputting and outputting signals so that the server 20 can communicate with external devices.

[0028] 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.

[0029] 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).

[0030] The storage 26 is for storing data, and is, for example, a flash memory or a hard disk drive (HDD).

[0031] 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.

[0032] The precedent search service server 91 has a database of precedents and allows users to search for judgments made by courts and the like.

[0033] The server 92 for the legal search service has a database of legal documents and allows users to search for legal documents.

[0034] 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.

[0035] 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.

[0036] 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 a certain number of impressions along with negative keywords. 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.

[0037] 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.

[0038] The business's server 96 stores data generated in the course of business activities carried out by the business.

[0039] The SNS server 97 provides a service that encourages interaction between users, such as a service that allows users to mutually view content posted by each other.

[0040] <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.

[0041] The communication unit 201 performs processing for the server 20 to communicate with external devices.

[0042] 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, an expert consultation history database 214, and a stage management database 215.

[0043] The user database 211 is a database that manages information about each user, as will be described in detail later.

[0044] The chat consultation history database 212 is a database showing the history of consultations that users, who are the clients, have made using the services provided by the server 20. Details will be described later.

[0045] 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 consultation content. Details will be described later.

[0046] The expert consultation history database 214 is a database showing the history of consultations that a user has made with experts, as will be described in detail later.

[0047] The stage management database 215 is a database for managing multiple stages leading up to the resolution of legal consultation issues, as will be described in detail 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 performs 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, and a matching processing module 2046.

[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 clients via chat and responds to them.

[0053] Specifically, the chat consultation processing module 2044 receives input of the consultation content from the user who is seeking advice, generates a response using the large-scale language model service server 95, 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 entered in free text by the client, 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 a series of texts entered by the client user, 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 matching processing module 2046 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.

[0057] <1.3 Configuration of Terminal 10> FIG. 3 is a diagram showing the configuration of the terminal 10. As shown in FIG.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] The motion sensor 170 includes an acceleration sensor, an angular velocity sensor, etc., and detects the movement of the terminal 10 .

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] The storage control unit 195 controls the storage of data in the storage unit 180 .

[0075] 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.

[0076] The user information 181 is information about a user who uses the services of the server 20 .

[0077] <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."

[0078] The item "user ID" is information that identifies each user.

[0079] The item "Name" is information indicating the name of the user.

[0080] The item "email address" is information about the email address used to contact the user.

[0081] The item "attribute" is information indicating the attribute of the user.

[0082] 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.

[0083] 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 The item "Qualifications held" is information indicating qualifications held by the user.

[0084] 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.

[0085] The item "status" is information indicating the user's status regarding legal advice.

[0086] 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.

[0087] 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.

[0088] The item "evaluation value" is information indicating an evaluation value obtained by evaluating the manner of legal consultation by the user.

[0089] 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 "chat consultation ID," an item "consultant user ID," an item "status," an item "first stage questions and answers," an item "whether to move to second stage," an item "second stage questions and answers," an item "whether to move to third stage," an item "third stage questions and answers," an item "whether to move to fourth stage," an item "fourth stage questions and answers," an item "whether to make consultation content public," an item "consultation with an expert," and an item "possibility of acceptance."

[0090] The item "chat consultation ID" is information for identifying each consultation that a client makes via chat in the legal consultation service provided by the server 20.

[0091] The item "consultant user ID" is information for identifying the user who is the client.

[0092] Specifically, the item “consultant user ID” corresponds to the item “user ID” of the user database 211.

[0093] The item "status" is information for managing which of a number of stages the consultation by the client is at until the problem is solved.

[0094] Specifically, the item "status" includes the following stages: Details will be described later in the explanation of the stage management database 215. First stage: The stage where the client's problem is organized. The large-scale language model service server 95 analyzes and summarizes the content entered by the user, and saves the client's problem (what the client wants to solve) for use by lawyers, etc. Second stage: Information gathering stage. Based on the issues organized in the first stage, the server 20 searches the internet, the server 91 of the case law search service, the server 92 of the law search service, the server 93 of the book browsing service, the server 94 of the information media service, the server 96 of the business operator, the server 97 of the SNS, etc., and presents the search results and the results summarized by the server 95 of the large-scale language model service to the client. Third stage: A stage in which the client inputs a question to the legal consultation service via chat provided by the server 20 and receives a response from the server 20. Based on the content of the client's problem organized in the first stage and the information collected in the second stage, the client and the chat system provided by the server 20 interact to resolve any unclear points of the client. The chat system responds to the client by generating answers using the large-scale language model service server 95, searching and collecting information. Phase 4: Searching for a lawyer to resolve the issue The item "Questions and answers in the first stage" is information indicating a history of questions input by the user and answers provided by the server 20 in the first stage of multiple stages.

[0095] Specifically, the item "Questions and Answers in the First Stage" manages multiple questions from users in the first stage in the form of a thread, etc. It also includes questions presented to the client by the legal consultation service provided by the server 20 and the client's answers to those questions.

[0096] The item "Can it be moved to the second stage?" is information indicating the result of determining whether it is possible to move from the first stage to the second stage that follows the first stage.

[0097] Specifically, the item "whether to transition to the second stage" may be set to a state in which transition to the second stage is possible by determining that the server 20 can proceed to the second stage as follows. The same may be applied to the process of determining whether or not transition from the second stage to the third stage is possible, and the process of determining whether or not transition from the third stage to the fourth stage is possible. If the number of questions entered by the user in the first stage and the number of answers provided by the server 20 are equal to or greater than a certain level, the server 20 determines that the system can proceed to the second stage. Based on the user's question, the server 20 generates an answer using the large-scale language model service server 95, and if the generated answer contains legal terms, the server 20 determines that it is possible to proceed to the second stage. For example, if the legal terms contain terms that indicate issues associated with provisions of laws and regulations or issues presented in legal precedents, the server 20 determines that it is possible to proceed to the second stage. This makes it possible to identify provisions and legal precedents that can be applied to the client's problem. Based on the user's question, the server 20 generates an answer using the large-scale language model service server 95. If the generated answer contains information indicating that the answer generation failed, such as "Answer could not be generated," the server 20 determines that the process cannot proceed to the second stage. The item "Questions and answers in the second stage" is information indicating the history of questions input by the user and answers provided by the server 20 in the second stage.

[0098] The item "whether or not to proceed to the third stage" is information indicating the result of determining whether or not it is possible to proceed from the second stage to the third stage that follows the second stage.

[0099] The item "Questions and answers in the third stage" is information indicating the history of questions input by the user and answers provided by the server 20 in the third stage.

[0100] The item "whether or not to proceed to the fourth stage" is information indicating the result of determining whether or not it is possible to proceed from the third stage to the fourth stage that follows the third stage.

[0101] The item "Fourth stage questions and answers" is information indicating the history of questions input by the user and answers provided by the server 20 in the fourth stage.

[0102] The item "Publication of consultation content" is information indicating whether the content of legal consultation input by the client in the service of the server 20 can be made public so that it can be viewed by a third party.

[0103] Specifically, the item "Whether consultation content should be made public" accepts a designation from the person seeking advice as to whether or not the consultation content of the person seeking advice should be made public in the following services. A service that posts legal consultation Q&A, making the content of consultations from clients and the responses of lawyers and other experts available for third parties to view. The service allows clients to search for lawyers, and clients can search for experts while viewing the results of the experts' responses to various questions. The item "Consultation with an expert" is information for identifying each request when a client requests consultation with an expert.

[0104] Specifically, the item "Consultation with an Expert" corresponds to the item "Expert Consultation ID" in the expert consultation history database 214, which will be described later.

[0105] The item "possibility of acceptance" is information indicating an evaluation value that evaluates the possibility that the client's consultation request will be accepted.

[0106] Specifically, the item "possibility of accepting the case" evaluates the possibility that a consultation request will be accepted as follows. A value that evaluates the consultation of the client based on the content of the text entered by the client in a chat conversation with the service provided by the server 20, the number of times the text was entered, the number of times the client consulted, etc. For example, if the client's problem is specific, there may be a relatively high possibility that the request for consultation with a specialist will be accepted. A value that evaluates the consultation of the client based on whether the amount of information provided in the chat provided by the server 20 when the client inputs a question (including the amount of information in the response generated by the server 95 of the large-scale language model service) is above a certain level. The more organized and organized the information is, the higher the possibility that the consultation request will be accepted. - A value that evaluates the client based on the client's past experience of requesting a specialist for consultation and the specialist accepting the case. 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 ID," an item "posting ID," an item "prompt," an item "LLM output result," and an item "usage date and time."

[0107] The item "Usage ID" is information that identifies each history of answers generated by the server 95 of the large-scale language model service.

[0108] The item "Consultation ID" is information for identifying each consultation that a client makes via chat in the legal consultation service provided by the server 20.

[0109] Specifically, the item “Consultation ID” corresponds to the item “Chat Consultation ID” in the chat consultation history database 212 .

[0110] The item "Post ID" is information for identifying a question posted by a user of a consulter, for which an answer is to be generated by the large-scale language model service server 95.

[0111] Specifically, the item "Post ID" is information that is assigned to each post of each user managed in the chat consultation history database 212 and that identifies each post.

[0112] 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.

[0113] 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. The prompt template for each stage, defined in the stage management database 215 described later, is added to the question entered by the user, and the resulting prompt is sent to the server 95 of the large-scale language model service. 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.

[0114] 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.

[0115] 7 is a diagram showing the data structure of the expert consultation history database 214. The expert consultation history database 214 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 "assignment result".

[0116] The item "expert consultation ID" is information for identifying each request made by a client to an expert for consultation.

[0117] Specifically, the item “expert consultation ID” corresponds to the item “expert consultation” in the chat consultation history database 212 .

[0118] 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.

[0119] Specifically, the item “chat consultation ID” corresponds to the item “chat consultation ID” in the chat consultation history database 212 .

[0120] The item "content of consultation" is information indicating the content of the consultation that the client requests the expert to provide.

[0121] 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.

[0122] The item "field" is information indicating the field of consultation, which is set in a request for consultation from a consultant to a specialist.

[0123] Specifically, the item "field" includes information on the field set by the server 20 or the user (consultant or expert).

[0124] 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.

[0125] The item "expert ID" is information for identifying the expert who responded to the request for consultation from the client.

[0126] Specifically, the item “expert ID” corresponds to the item “user ID” of the user database 211 .

[0127] 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.

[0128] The item "acceptance result" is information indicating whether or not the expert has accepted the consultation request of the client.

[0129] 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) 8 is a diagram showing the data structure of the stage management database 215. The stage management database 215 includes an item "stage", an item "stage definition", an item "question content to the user", and an item "prompt".

[0130] The item "stage" is information indicating each of a plurality of stages until the problem is solved regarding legal consultation.

[0131] The item "stage definition" is information that defines the content of each stage.

[0132] Specifically, the item "Definition of Stages" includes the following definitions for each stage: Stage 1: Identifying the client's issues regarding legal advice Phase 2: Information gathering Third stage: A stage in which the client inputs a question through the chat-style legal consultation service provided by the server 20, and the server 20 generates an answer using the server 95 of the large-scale language model service and presents it to the client. Stage 4: Find a lawyer and request a consultation to resolve the issue The item "Question to user" is information indicating one or more questions to be presented to the user by the server 20 at each stage.

[0133] Specifically, the item "Question to the user" presents the following questions to the user: If it is determined that the content of the question from the client is ambiguous regarding a legal issue, the system will present specific questions that the client should ask. For example, if the search results based on the content of the client's question (or the search results summarized by the server 95 of the large-scale language model service) do not contain legal terms (or if the server 95 of the large-scale language model service generates a response indicating that generation was unsuccessful, such as "Answer could not be generated" or "Not found"), it will be determined that the content of the client's question is ambiguous regarding a legal issue. Questions about the knowledge, skills, and experience of the person seeking advice. For example, whether or not the person has any qualifications. The server 20 may change the questions presented to the person seeking advice depending on the person's knowledge, etc. Furthermore, the server 20 may acquire information on the person's knowledge, skills, experience, etc., and update the user database 211. The server 20 may also make the information on the knowledge, skills, experience, etc., answered by the person seeking advice available to the expert at the stage of requesting consultation from the expert. The time period related to the question. For example, the scope of applicable laws and regulations, company rules, etc. can be identified, and answers according to the time period of these laws and regulations, company rules, etc. can be generated by the large-scale language model service server 95. The server 20 determines whether there are any typos or omissions in the question entered by the client, and presents the client with questions to check for typos or omissions. For example, a proofreading function that detects typos or omissions is applied to the sentences or words in the client's question to detect the typos or omissions. The server 20 presents candidates for the typos and omissions as well as candidates for the correct expression in the client's question, and accepts an answer from the client. If the client provides an answer that confirms that there are any typos or omissions, the server 20 corrects the typos, updates the chat consultation history database 212 based on the user's question, and causes the large-scale language model service server 95 to generate an answer. The item "prompt" is information indicating the contents of a prompt template. For example, prompt templates corresponding to each stage may be stored.

[0134] For example, in the first stage, a prompt including an instruction to summarize the content input by the client is sent to the server 95 of the large-scale language model service in order to organize the client's problem.

[0135] In the second stage, in order to collect information, a prompt including an instruction to summarize at least either the content input by the client or the results of a search on the Internet or the like by the server 20 based on the content input by the client is sent to the server 95 of the large-scale language model service. The server 20 presents to the client at least either the results of the search on the Internet or the results generated by the server 95 of the large-scale language model service.

[0136] In the third stage, the server 20 accepts input of the consultation content from the person seeking advice, and transmits a prompt including an instruction to the server 95 of the large-scale language model service to have the server 20 summarize at least one of the results of a search on the Internet, etc., so that the person seeking advice can resolve any unclear points while interacting with the chat system. The server 20 presents at least one of the results of the search on the Internet, etc., or the results generated by the server 95 of the large-scale language model service to the person seeking advice.

[0137] <3 operations> FIG. 9 is a flowchart showing the flow of a process in which a plurality of stages of legal consultation are presented to the user, and the user is informed that they can proceed to the next stage by accumulating information at a certain stage.

[0138] In step S921, the server 20 presents to the user, who is the client, an operation screen for accepting input of a question about legal consultation from the client.

[0139] The server 20 stores information for managing multiple stages leading up to the resolution of legal consultation issues in the stage management database 215 and the chat consultation history database 212. For example, the server 20 manages the multiple stages including, as one of the stages, a stage for organizing a user's question.

[0140] The server 20 refers to the chat consultation history database 212 and presents to the user which of a plurality of stages the user is currently at.

[0141] In step S911, the terminal 10 accepts input of a question from the user while indicating to the user, who is the client, which of a plurality of stages the client is currently at.

[0142] The terminal 10 may accept an operation from the user to specify that one of multiple stages is the stage of sorting out the problem. In response to the specification, the server 20 updates the chat consultation history database 212 so that the user is managed as being at the stage of sorting out the problem. The server 20 presents specific questions to the user at the stage of sorting out the problem and accepts the user's responses to the specific questions. In this way, the content of the user's question itself can be summarized. For example, the server 20 presents questions for sorting out the user's problem as follows. Stakeholder questions: Ask users to list the people involved in the problem they are facing. Questions about interested parties, relatives, and other relationships may also be included. Questions about the parties involved in debts and credits: Questions about which stakeholders you want to have do what Questions about when the issue arose Questions asking about monetary values ​​associated with the issue: for example, questions asking about the extent of damage if any. Questions to ask about the client's level of desire and motivation to solve the problem In step S923, the server 20 generates an answer to the question entered by the client using the large-scale language model. The server 20 creates a prompt to be sent to the large-scale language model service server 95 based on the question entered by the client and the stage management database 215. The server 20 transmits the created prompt to the large-scale language model service server 95, causing the large-scale language model service server 95 to generate the answer, and receives the generated answer. For example, the server 20 performs processing such as extracting words contained in the question entered by the user and vectorizing the question sentence based on the question entered by the user. The server 20 may search public information sources such as the Internet, the case law search service server 91, the law search service server 92, the book browsing service server 93, the information media service server 94, and the SNS server 97 based on the extracted words (or may search closed information sources available to authorized users, such as data stored on a business's server 96), include the search results in the prompt, and have the large-scale language model service server 95 generate an answer by summarizing the content. The server 20 may also vectorize the user's question, extract information to be sent to the large-scale language model service server 95 according to the distance between the vectorized data stored in the information source and the question, and have the large-scale language model service server 95 summarize the content to generate an answer.

[0143] The server 20 updates the chat consultation history database 212 and the LLM usage history database 213 in response to these processes.

[0144] In the stage of organizing the problem, the server 20 generates an answer using a large-scale language model based on the user's response to a specific question presented to the user. For example, the server 20 may send a prompt to the server 95 of the large-scale language model service to summarize the problem the user wants to solve, using the specific question and the user's response to the specific question as the target, thereby causing the server 95 of the large-scale language model service to generate a sentence organizing the user's problem.

[0145] In step S925, the server 20 determines that the condition for proceeding to the next stage following a certain stage of the plurality of stages has been met. If it is determined that the condition for proceeding to the next stage has been met, the server 20 updates the chat consultation history database 212 and presents information indicating that the user has progressed to the next stage.

[0146] The server 20 may determine that the conditions for proceeding to the next stage are met as described in the explanation of the chat consultation history database 212. For example, the server 20 may determine that the conditions for proceeding to the next stage are met (or not met) in the following cases: The answer generated by the large-scale language model service server 95 does not contain a specific word. For example, if the generated answer does not contain a legal term, it may be determined that the condition for proceeding to the next stage is not met, and if the legal term is included, it may be determined that the condition for proceeding to the next stage is met. If the answer generated by the large-scale language model service server 95 includes an output indicating that "the answer could not be generated successfully," it may be determined that the conditions for proceeding to the next stage are not met, and if there is no such output, it may be determined that the conditions for proceeding to the next stage are met. In step S927, the server 20 outputs the answer generated by the large-scale language model service server 95 to the user.

[0147] The server 20 may identify cases relating to the legal issue related to the answer based on the generated answer and output the identified cases together with the answer. For example, the server 20 may extract words included in the generated answer, weight words corresponding to legal terms (e.g., issues, parties), and search the case law search service server 91, the book browsing service server 93, the information media service server 94, etc. for the extracted words, thereby identifying cases relating to the legal issue.

[0148] In step S913, the terminal 10 displays the answer generated by the large-scale language model service server 95. The terminal 10 displays a chat input screen and accepts further question input from the user. The server 20 causes the large-scale language model service server 95 to generate an answer in response to the user's question input.

[0149] FIG. 10 is a flowchart showing the flow of processing in which the chat system presents a specific question to a user, accepts a reply from the user, and generates an answer using the LLM.

[0150] In step S1011, the terminal 10 displays a screen for accepting input of a question in a chat format, and accepts input of a question from the user.

[0151] In step S1023, the server 20 determines whether the content of the question input by the user is clear regarding legal issues.

[0152] Specifically, the server 20 may make the above determination as follows. The server 20 searches a database, such as the Internet, based on the question entered by the user. For example, it extracts words contained in the question and performs a search. The server 20 determines whether the search results contain legal terms (e.g., terms found in laws and regulations, or points of contention found in books and precedents), and if no legal terms are found, it determines that the content of the question is unclear about a legal issue. The server 20 determines that the content of the question is unclear about legal issues when the search results obtained by searching a database such as the Internet based on the question entered by the user and summarizing them using a large-scale language model do not contain legal terms. The server 20 determines that the content of the question is unclear regarding legal issues when it sends a prompt to the large-scale language model service server 95 based on the content of the question entered by the user to generate an answer, but outputs a message indicating that the large-scale language model was unable to generate an answer.

[0153] In step S1025, if the server 20 determines that the legal issue is unclear, it presents a specific question to the user and updates the chat consultation history database 212.

[0154] Specifically, the server 20 may present a specific question to the user as follows. Presents questions that challenge the user's knowledge, skill, and / or experience regarding legal issues Present a question asking about the time it takes to answer the user's question In step S1013, the terminal 10 displays the specific question and accepts the user's reply to the specific question in a chat format.

[0155] In step S1027, the server 20 generates an answer to the question using the large-scale language model service server 95 based on the user's response to the specific question and the input question, and updates the chat consultation history database 212 and the LLM usage history database 213.

[0156] For example, if the server 20 receives from a user information about the user's knowledge, skills, and experience regarding legal issues in response to a specific question, the server 20 may create a prompt to generate an answer based on the user's knowledge, skills, and experience (e.g., the prompt may include a message such as "explain for people with less knowledge, skills, and experience") and send the prompt to the server 95 for the large-scale language model service.

[0157] For example, the server 20 may create a prompt to generate an answer appropriate to the time based on the time information received as the user's response (for example, the prompt may include content instructing the user to refer to laws and regulations that apply to the time period, to refer to internal company documents that are appropriate to the time period, or to perform an Internet search for information that has been made public during the time period and refer to the search results), and send the prompt to the large-scale language model service server 95.

[0158] FIG. 11 is a flowchart showing the process of generating an answer using the LLM when a user corrects a question, assuming that all questions posted after the corrected question have also been corrected.

[0159] In step S1113, the terminal 10 displays the answer generated by the large-scale language model. The terminal 10 displays, in a chat format, questions previously asked by the user and the answers to those questions provided by the server 20 side by side.

[0160] The terminal 10 accepts input of a question from the user, and at this time, accepts input specifying a question that was asked incorrectly in the past. For example, the terminal 10 may accept input of a question from the user that does not take into account the content that was previously entered, such as "Please tell me the following without considering past posts," and that includes the content of a new question.

[0161] In step S1129, the server 20 causes the large-scale language model service server 95 to generate an answer without considering the incorrect question specified by the user, and outputs the generated answer. For example, the server 20 refers to the chat consultation history database 212 to identify the post specified by the user. It is also possible to generate a prompt without using the content of posts made in the thread after the specified post in order to generate the prompt, and cause the large-scale language model service server 95 to generate an answer.

[0162] In step S1115, the terminal 10 displays the answer generated by the server 95 of the large-scale language model service.

[0163] FIG. 12 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.

[0164] In step S1221, the server 20 presents an operation screen for accepting input of questions regarding legal consultation to the user who is the client.

[0165] In step S1211, 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 consultation with an expert regarding the legal consultation related to the question.

[0166] 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.

[0167] 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.).

[0168] 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.

[0169] 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.

[0170] In step S1223, 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.

[0171] 9 to 12, 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 client in accordance with specified items, and cause the server 20 to 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.

[0172] The server 20 may output to the expert content based on the answers generated in accordance with the specified items. For example, the server 20 communicates with a case management database system used by the expert, and generates a prompt to generate an answer in accordance with the specified items as described above so as to match the items of the records managing each case in the case management database system. In this way, the server 20 may update the case record in the case management database system based on the results generated by the large-scale language model service server 95.

[0173] 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.

[0174] 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.

[0175] The server 20 may refer to the expert consultation history database 214 and evaluate the possibility of the legal consultation of the client resulting in the expert being appointed to the case, depending on the track record of the legal consultation of the client resulting in the expert being appointed to the case.

[0176] 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.

[0177] 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 as having a certain degree of possibility of being accepted.

[0178] In step S1225, 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 214 and notifies the user who is the client.

[0179] In step S1213, the terminal 10 notifies the user that the expert has responded to the request.

[0180] <4 Screen example> FIG. 13 is an example of a screen that displays to the user a number of steps leading up to the resolution of a problem regarding legal advice, and assists the user in inputting a question.

[0181] FIG. 14 shows an example of a screen in which the chat system presents a specific question to the user, accepts the input of a response, and generates an answer using the LLM.

[0182] The operation screen 1200 is a screen for accepting legal advice requests in chat format from users who are seeking legal advice.

[0183] The account display area 1202 is an area for displaying information about the account of the user who is the client.

[0184] 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.

[0185] The stage display area 1206 is an area that displays the stage at which the user's consultation is progressing until the problem is resolved, based on information managed in the chat consultation history database 212 .

[0186] In the illustrated example, the stage display area 1206 shows four stages as multiple stages, emphasizing that the first stage, "organizing the tasks," has been completed and the second stage, "gathering information," is now underway. This corresponds to step S911 in FIG. 9.

[0187] The user question display area 1208 is an area for displaying a question input by the user as the content of the consultation.

[0188] The AI ​​answer display area 1210 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.

[0189] The AI ​​answer display area 1210 corresponds to steps S927, S913, etc. in FIG.

[0190] The navigation display area 1212 is an area that displays information to support consultations in chat format, such as displaying to the user which of multiple stages in the process of resolving the legal consultation issue they are at and questions that prompt the user to answer.

[0191] In the illustrated example, the navigation display area 1212 displays that the server 20 has referred to the chat consultation history database 212, determined that the amount of information obtained in the first stage is sufficient, and has therefore moved on to the second stage, the "information gathering" phase. This corresponds to step S925 in FIG. 9.

[0192] Furthermore, as shown in the example of Fig. 14, the navigation display area 1212 determines that the content of the question entered by the user is unclear regarding a legal issue and presents a specific question to the user. In the example of Fig. 14, the specific question displayed to the user is whether or not the user has any legal qualifications, and also suggests other specific questions to be asked to the user. This corresponds to steps S1025, S1013, etc. in Fig. 10.

[0193] The chat input receiving section 1214 is an area where a question can be input by inputting text from the user.

[0194] 9, the chat input receiving unit 1214 may display information suggesting what to input in order to prompt the user to input a question, as shown in the figure. This corresponds to step S911 in FIG.

[0195] Furthermore, as shown in the example of Fig. 14, when it is determined that the legal issue is unclear, the chat input receiving unit 1214 receives an answer to a specific question presented to the user. This corresponds to step S1013 in Fig. 10. The example of Fig. 14 suggests that the user input whether or not they have any legal qualifications.

[0196] The disclosure operation receiving unit 1216 is an operating member that receives an operation by the user to specify whether or not to disclose the question entered by the user, the answer generated by the large-scale language model service server 95, and the answer from the expert.

[0197] The disclosure operation receiving unit 1216 receives a designation from the user as to whether information relating to the consultation content should be made public or kept private.

[0198] The user question display area 1218 is an area for displaying a question input by the user as the content of the consultation.

[0199] In the illustrated example, the user question display area 1218 displays the question entered by the user in the second stage, the "information gathering" phase.

[0200] The AI ​​answer display area 1220 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.

[0201] In the illustrated example, the AI ​​answer display area 1220 indicates that the large-scale language model service server 95 has generated an answer to the effect that it was unable to generate the content of the answer.

[0202] FIG. 15 shows an example of an operation screen on which a client performs an operation to request a consultation from a specialist.

[0203] 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.

[0204] The request display area 1224 is an area for displaying a screen for requesting legal advice from an expert.

[0205] The request display area 1224 corresponds to step S1211 in FIG.

[0206] The candidate attorney display area 1226 is an area that displays lawyers who are candidates for clients.

[0207] The candidate requestee display area 1226 corresponds to step S1211 etc. in Fig. 12. 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.

[0208] The condition specification receiving section 1228 is an operation member that receives the specification of conditions for extracting candidate lawyers to request consultation.

[0209] The condition specification receiving unit 1228 corresponds to step S1211 in FIG.

[0210] The request operation receiving unit 1230 is an operation member that receives an operation to request a consultation with a lawyer.

[0211] The request operation receiving unit 1230 corresponds to step S1211 in FIG.

[0212] FIG. 16 shows an example of an operation screen on which an expert operates upon receiving a consultation request from a client.

[0213] 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.

[0214] The account display area 1234 is an area that displays information about the account of a user who is an expert.

[0215] The request content display area 1236 is an area where the content of the consultation from the client is displayed.

[0216] The details display area 1238 is an area where the details of the consultation from the client are displayed.

[0217] 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 S1223 in Fig. 12. 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.

[0218] 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.

[0219] The contact operation receiving unit 1240 corresponds to step S1225 in FIG.

[0220] 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).

[0221] The details display area 1244 is an area that displays details of the case that the expert is handling.

[0222] The search operation receiving section 1246 is an operating member that receives an operation to search for a requested case.

[0223] <Modification> In addition to the aspects described in the above embodiment, the following may be adopted.

[0224] (1) The stage where the client interacts with the chat system:

[0225] (1-1) Supporting the client in entering questions by presenting past questions, etc. The server 20 may refer to the chat consultation history database 212, and based on at least one of the content of the question entered by the user and the answer to the content of the question generated by the server 95 of the large-scale language model service, identify similar questions from other clients, and present at least one of the identified questions from other clients and the answers to the questions from other clients generated by the server 95 of the large-scale language model service to the clients. This allows the client to get suggestions on what kind of questions to enter when entering a question, encouraging use of the chat system and facilitating the solution of the problems the client is facing.

[0226] Furthermore, the server 20 may determine the field of the client's question based on at least either the content of the client's question or the content of the answer to the question generated by the large-scale language model service server 95, and manage the field in the chat consultation history database 212, etc. This allows the server 20 to identify example sentences of questions, etc. that have been asked in the past in the same or similar fields and present them to the client, making it even easier for the client to input a question.

[0227] (1-2) Reducing the burden on users by reducing the number of times they input information into the chat system The server 20 may suggest to the client the information to be entered by the client in the navigation display area 1212 in FIG. 13 or the like, thereby assisting the client in entering information into the chat system all at once, thereby reducing the number of times the client has to enter information.

[0228] For example, the server 20 may display a message prompting the user to input information necessary for generating an answer, such as the consultation content of the user, the user's profile, a URL to be referenced, and the like. (1-3) Classify questions to generate answers using a large-scale language model service, and create prompts based on the classified 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. 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. 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. 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." 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. 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." 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.

[0229] (2) Stage of requesting consultation from a consultant to an expert: In the above embodiment, the server 20 organizes the user's question and the answer generated by the large-scale language model service server 95 in a specified format and registers the log in a case management system used by the expert. In addition, the server 20 may summarize the content of at least one of the log of questions entered by the consultant in the chat system or the log of answers generated by the large-scale language model service server 95 as described above, extract chronological information about the facts, and manage the information in a specified format on the server 20. When a consultant consults an expert via the server 20, the information organized in a specified format managed by the server 20 may be made available to the expert like a medical record.

[0230] This can reduce the burden on the person seeking advice from repeatedly explaining the content of the consultation. For example, it can reduce the burden of speaking to an expert such as a lawyer about the content entered into the chat system. For example, if the person seeking advice has had a difficult experience, the burden of repeatedly speaking about that experience can be reduced, which can increase the opportunities to receive services from experts and promote the resolution of the problem.

[0231] (3) The stage when a client requests a consultation from an expert (expert side): We explained an example in which, when a client requests a consultation from an expert, the lawyer, who is the expert, also displays a list of consultation requests. (3-1) Whether or not the consultant can access information about the consultation Of the experts registered on the server 20, if an expert satisfies certain conditions, the expert may be able to refer to information about the consultation content, such as the possibility of accepting the case, as explained in the example of Fig. 16. The certain conditions may include, for example, the following: In the matching service between consultants and experts provided by the server 20, there is a high track record of experts responding to consultations (such as answering questions as an expert, accepting consultation requests from consultants, etc.) In the service provided by the server 20, paid experts may be able to access more information about consultation requests than non-paid experts. For example, paid experts may be able to view information such as responses generated by the large-scale language model service server 95 regarding the content of the consultation request, and summaries of the consultation content, such as information on the "acceptance probability" item managed in the chat consultation history database 212, while free experts may be limited to viewing some of the information. This allows paid experts to have more information to decide whether or not to accept the consultation, further increasing the convenience of the experts. (3-2) Present the results of the assessment of whether or not the case is a party to the case to the expert as a possible candidate for the case. In addition, the server 20 may present the results of an evaluation of whether the consultation content of the client is relevant to the parties involved, to the specialist, as a basis for estimating the possibility of accepting the consultation request from the client. If the consultation is from a person who is not a party involved, it may be difficult to accept the consultation from that client, due to considerations such as the suitability of the party involved. For example, the server 20 determines, based on the content of the user's consultation, whether the content of the consultation is about a problem that has arisen not with the user himself / herself but with a third party. For example, the server 20 may prompt the server 95 of the large-scale language model service to determine whether the content of the user's consultation is related to the user himself / herself as described above, or whether it is about a third party that is not related to the user who is the user who is the consultant (whether the outcome of the problem has no particular relevance to the user who is the consultant), and accept the response from the server 95 of the large-scale language model service to the prompt. Examples of inquiries that involve a low level of involvement include, "A famous streamer did this. Is there any legal problem with this?" and "A relative or friend did this. Is there any problem with this?" These are questions that ask about the appropriateness of the behavior, rather than the person making the inquiry themselves wanting to confirm whether it is legally problematic. (3-3) Indicate to the expert whether the consultation is of public interest or not as a possible case. The server 20 may present to the expert the results of an evaluation of whether the consultation content of the client is in the public interest. If the consultation content is in the public interest, some experts may preferentially accept the case based on their own past experience, etc. Examples of matters in the public interest include the use of public funds, matters related to public health such as the natural environment, and matters related to fraud. For example, the server 20 may prompt the server 95 of the large-scale language model service to determine whether the content of the user's consultation is related to a public interest or a specific issue that is of public interest (e.g., whether it is related to public health), and accept the response from the server 95 of the large-scale language model service to the prompt. In this way, if the consultation content is in the public interest, the score (possibility of being accepted) of the consultation may be increased. Such settings may be set for each expert. (3-4) Present the expert with an estimate of the amount to be claimed as a possible case. The server 20 may also provide the expert with an estimate of the amount to be claimed in the event that the consultation with the client leads to a dispute. If the amount to be claimed is low, the client may decide not to settle the matter through litigation. For example, the server 20 may prompt the server 95 of the large-scale language model service to evaluate the amount of claim if the content of the user's consultation is contested in court based on the level of damages and settlement amounts indicated in legal precedents and posts by experts, and then accept the response of the server 95 of the large-scale language model service to the prompt. For example, it may be possible to estimate the level of the amount as a guideline from accumulated legal precedents, such as "approximately ____ million yen for defamation." Experts may also announce the level of settlement amounts on social media, etc. In this way, the score (possibility of accepting) of the consultation may be changed based on the estimated amount of the claim (for example, the score may be increased if the amount of the claim is high). (3-5) Indicate to the specialist how often the consultation requests from the client are accepted The server 20 may evaluate the possibility of accepting a consultation from a client based on the ratio of the number of cases that have been accepted to the number of clients, and present the evaluation result to the specialist. For example, the server 20 may calculate the ratio of the number of consultation cases of each client to the number of cases accepted for that client for a certain number of clients, and if the ratio is significantly different from the average or median, may notify the expert of this fact. For example, if the number of cases accepted is extremely low compared to the number of consultation cases, it may indicate that the client is inclined to give up on resolving the case, and this may be presented to the expert as a score on the likelihood of accepting the case. This makes it easier for the expert to decide whether to accept each consultation case and to consider how to proceed with the consultation with the client (for example, by suggesting that the client identify the case they want to resolve). (3-6) Inform the expert whether the number of consultations from the client is extremely high or not. The server 20 may evaluate the acceptance probability score by taking into account the fact that the number of consultation cases a client has is extremely high compared to the average or median, or exceeds a certain number. For example, if a client has a huge number of consultation cases, the server 20 may narrow down the cases that the client needs to resolve and concentrate resources on them. As a result, the server 20 may present each consultation case to the expert with a low acceptance probability, while also informing the expert of the large number of consultation cases. This makes it easier for the expert to decide whether to accept the client's consultation, taking into account the reasons for the low acceptance probability, and may be able to discuss with the client how to proceed with the consultation (e.g., narrowing down to important consultations).

[0232] (4) Specific uses In the above embodiment, an example has been described in which the chat system answers questions from the client about legal advice, while matching the client with a request for legal advice from an expert.

[0233] For example, the server 20 may respond to the following inquiries from the client. Procedural consultations for sole proprietors. For example, to accommodate tax-related consultations for sole proprietors, information on tax returns may be provided and the sole proprietor may be able to request consultations with tax accountants. Consultation for software developers. For example, if the server 20 can provide consultation regarding software licenses, when the server 20 receives the software source code, it may send a prompt to the large-scale language model service server 95 to check whether any software indicated in the source code requires a license, and conduct a license audit.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] <Additional Notes> The matters explained in the above embodiment will be supplemented below.

[0239] <Additional notes on the first embodiment>

[0240] (Appendix 1) A program for operating a computer having a processor, wherein a memory unit stores information for managing multiple stages leading up to the resolution of a legal consultation problem, and the program causes the processor to execute the following steps: referencing the information stored in the memory unit and indicating to a user which of the multiple stages the user is at; accepting a question from the user while indicating to the user which of the multiple stages the user is at; generating an answer to the input question using a large-scale language model and outputting the generated answer to the user; and determining whether the conditions for proceeding to the next stage following a certain stage of the multiple stages have been met; and when it is determined that the conditions for proceeding to the next stage have been met, in the step of indicating which stage the user is at, the program presents information indicating that the user has progressed to the next stage.

[0241] (Appendix 2) The program further includes a step of causing the processor to determine whether the content of the question input by the user is clear in terms of legal issues, and if it is determined in the determining step that the legal issues are not clear, presenting a specific question to the user and accepting the user's response to the specific question, and in a step of outputting the answer, generating an answer using a large-scale language model based on the accepted user response.

[0242] (Appendix 3) The program described in Appendix 2, wherein in the determining step, the program determines that the legal issue is unclear in at least one of the following cases: when the search results obtained by searching a database such as the Internet based on the input question do not contain legal terms; when the summary results obtained by using a large-scale language model to summarize the search results obtained by searching a database such as the Internet based on the input question do not contain legal terms; or when the large-scale language model outputs a message indicating that it was unable to generate an answer.

[0243] (Appendix 4) 4. The program according to any one of appendices 2 to 3, wherein in the determining step, presenting a specific question comprises presenting a question that inquires about at least one of the knowledge, skills, or experience of the user asking the question about a legal issue, and accepting the user's response to the specific question.

[0244] (Appendix 5) A program as described in any of Appendices 2 to 4, wherein in the determining step, a specific question is presented by presenting a question asking about the timing related to the content of the user's question, and a response from the user to the specific question is accepted, and in the answer output step, an answer is generated using a large-scale language model based on the timing information as the accepted user response.

[0245] (Appendix 6) The storage unit manages a step of organizing the user's issues as one of the multiple steps, The program according to any one of appendices 1 to 5, further comprising a step of causing the processor to receive an operation from the user specifying that one of the multiple stages is a stage of organizing the task, and managing the stage as a stage where the user is organizing the task in accordance with the specification, presenting a specific question to the user in the stage of organizing the task and accepting the user's response to the specific question, and in a step of outputting the answer, generating an answer using a large-scale language model based on the accepted user response.

[0246] (Appendix 7) 7. The program according to any one of appendices 1 to 6, wherein in the step of accepting a question input, an input specifying a question that has been asked incorrectly in the past is accepted from the user, and in the output step, an answer is output from a large-scale language model without taking into account the specified incorrect question.

[0247] (Appendix 8) A program described in any of Appendices 1 to 7, in which, in the step of outputting an answer, a case relating to the legal issue related to the answer is identified based on the generated answer, and the identified case is output together with the answer.

[0248] (Appendix 9) A method executed by a computer having a processor, wherein a memory unit stores information managing multiple stages leading up to the resolution of a legal consultation problem, the method comprising the steps of: referring to the information stored in the memory unit and indicating to a user which of the multiple stages the user is at; accepting a question from the user while indicating to the user which of the multiple stages the user is at; generating an answer to the input question using a large-scale language model and outputting the generated answer to the user; and determining whether the conditions for proceeding to the next stage following a certain stage of the multiple stages have been met; and if it is determined that the conditions for proceeding to the next stage have been met, in the step of indicating which stage the user is at, presenting information indicating that the user has progressed to the next stage.

[0249] (Appendix 10) An information processing device, in which a memory unit stores information managing multiple stages leading up to the resolution of a legal consultation problem, and a control unit of the information processing device executes the following steps: referring to the information stored in the memory unit and indicating to a user which of the multiple stages the user is at; accepting a question from the user while indicating to the user which of the multiple stages the user is at; generating an answer to the input question using a large-scale language model and outputting the generated answer to the user; and determining whether the conditions for proceeding to the next stage following a certain stage of the multiple stages have been met; and when it is determined that the conditions for proceeding to the next stage have been met, in the step of indicating which stage the user is at, the information processing device presents information indicating that the user has progressed to the next stage.

[0250] <Additional notes on the second embodiment>

[0251] (Appendix 1) A program for operating a computer having a computer processor, the program causing the computer processor to execute the following steps: accepting input of a question regarding legal advice from a user; generating an answer by instructing a large-scale language model to generate an answer to the accepted question; presenting the generated answer to the user; accepting an operation from the user who has presented the answer to request legal advice from an expert regarding the question; and, upon accepting the request operation, outputting to the expert a request and content based on the generated answer.

[0252] (Appendix 2) A program as described in Appendix 1, in which, in the generating step, a large-scale language model is instructed to generate an answer in accordance with specified items, and in the output step, content based on the answer generated in accordance with the specified items is output to an expert.

[0253] (Appendix 3) A program according to any one of appendices 1 to 2, wherein a memory unit stores a history of questions entered by a user and answers generated by a large-scale language model, and the program further causes a computer processor to execute a step of evaluating the user's consultation based on the history, and in the output step, outputs a score evaluating the user's consultation related to the request to the expert.

[0254] (Appendix 4) The storage unit is configured to store information of the expert, and the program further includes: A program according to any one of appendices 1 to 3, which executes a step of extracting candidates for experts who can respond to the consultation request based on the content of the consultation request made by the user, the answer to be generated, and information about the experts.

[0255] (Appendix 5) The program according to appendix 4, wherein in the sending step, the candidate experts extracted in the extracting step are presented to the user along with information about the experts, and the program further causes the computer processor to execute a step of receiving input of conditions for selecting an expert from the user, and in the extracting step, extracts candidate experts according to the received conditions and candidate experts.

[0256] (Appendix 6) The program described in any of Appendices 1 to 5, further causes the computer processor to execute a step of evaluating the likelihood that the consultation request will result in an acceptance by an expert, and in the output step, prioritizes and outputs to the expert legal consultation requests that have a certain or higher likelihood of being accepted.

[0257] (Appendix 7) The program described in Appendix 6, in which in the evaluation step, the program refers to the history of the client's consultations with experts related to the request and evaluates the likelihood of the client being accepted based on the client's track record of legal advice resulting in the expert accepting the case.

[0258] (Appendix 8) A program described in any of Appendices 6 to 7, wherein in the evaluation step, the possibility of accepting the case is evaluated based on at least one of the following: the amount of data of the question entered by the user regarding 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.

[0259] (Appendix 9) The program further includes a step of causing the computer processor to receive an operation from the user to make the user's question about legal consultation publicly viewable by third parties, a step of making the question about legal consultation viewable by third parties in accordance with the operation of making it public, and a step of generating an answer by instructing the large-scale language model to generate an answer that does not include the user's personal information, in the generating step.

[0260] (Appendix 10) A method for operating a computer having a computer processor, the method comprising the steps of: receiving input of a question regarding legal advice from a user; generating an answer by instructing a large-scale language model to generate an answer to the received question; presenting the generated answer to the user; receiving an operation from the user who presented the answer to request legal advice from an expert regarding the question; and, upon receiving the request operation, outputting to the expert a request and content based on the generated answer.

[0261] (Appendix 11) An information processing device, wherein a control unit of the information processing device executes the steps of: accepting input of a question regarding legal consultation from a user; generating an answer by instructing a large-scale language model to generate an answer to the accepted question; presenting the generated answer to the user; accepting an operation from the user who has presented the answer to request legal consultation from an expert regarding the question; and, by accepting the request operation, outputting to the expert a request and content based on the generated answer.

Claims

1. A program for operating a computer having a processor, The memory unit stores information for managing multiple steps leading up to the resolution of legal consultation issues, The program causes the processor to: a step of referring to the information stored in a storage unit and indicating to a user which of the plurality of stages the user is currently in; a step of accepting a question input from the user while indicating to the user which of the plurality of stages the user is currently in; generating an answer to the input question using a large-scale language model, and outputting the generated answer to the user; determining whether a condition for proceeding to a next stage subsequent to a certain stage of the plurality of stages is satisfied; When it is determined that the condition for proceeding to the next stage is met, in the step of indicating which stage the user is at, the program presents information indicating that the user has proceeded to the next stage.

2. The program further causes the processor to determining whether the content of the question input by the user is clear about legal issues; If it is determined in the determining step that the legal issue is unclear, specific questions are presented to the user and responses to the specific questions are received from the user; 2. The program according to claim 1, wherein in the step of outputting the answer, the answer is generated by the large-scale language model based on the received user response.

3. In the determining step, If the search results from a database such as the Internet based on the entered question do not include legal terms, If the search results obtained by searching a database such as the Internet based on the input question are summarized by the large-scale language model and the summary result does not contain legal terms, If the large-scale language model outputs that it was unable to generate an answer, 3. The program according to claim 2, wherein the program determines that the legal issue is unclear in at least one of the following cases:

4. In the determining step, the specific question is presented by Presenting a question that tests the user's knowledge, skill, and / or experience regarding legal issues; The program of claim 2 , further comprising accepting a user's response to the specific question.

5. In the determining step, the specific question is presented by Present a question asking about the timing of the question content of the user's question, Accepting the user's response to the specific question; 3. The program according to claim 2, wherein in the step of outputting the answer, the answer is generated by the large-scale language model based on information about the timing of the received user response.

6. The storage unit manages the plurality of stages including a stage of sorting out the user's issues, The program further causes the processor to receiving an operation from the user to specify that one of the plurality of stages is a stage of organizing the task; In response to the designation, the system manages the task as if the user is in a stage of sorting out the task, and in the stage of sorting out the task, presents specific questions to the user and accepts the user's responses to the specific questions; 2. The program according to claim 1, wherein in the step of outputting the answer, the answer is generated by the large-scale language model based on the received user response.

7. In the step of receiving an input of a question, receiving an input from the user specifying a question that was previously answered incorrectly; The program according to claim 1 , wherein the output step causes the large-scale language model to output the answer without taking into account any incorrect questions related to the specification.

8. In the step of outputting the answer, The program according to claim 1 , further comprising: identifying a case relating to a legal issue related to the generated answer based on the answer; and outputting the identified case together with the answer.

9. 1. A computer-implemented method comprising: The memory unit stores information for managing multiple steps leading up to the resolution of legal consultation issues, The method further comprises the processor: a step of referring to the information stored in a storage unit and indicating to a user which of the plurality of stages the user is currently in; a step of accepting a question input from the user while indicating to the user which of the plurality of stages the user is currently in; generating an answer to the input question using a large-scale language model, and outputting the generated answer to the user; determining whether a condition for proceeding to a next stage subsequent to a stage of the plurality of stages is satisfied; A method in which, when it is determined that the conditions for proceeding to the next stage are met, in the step of indicating which stage the user is at, information indicating that the user has proceeded to the next stage is presented.

10. An information processing device, The memory unit stores information for managing multiple steps leading up to the resolution of legal consultation issues, a control unit of the information processing device, a step of referring to the information stored in a storage unit and indicating to a user which of the plurality of stages the user is currently in; a step of accepting a question input from the user while indicating to the user which of the plurality of stages the user is currently in; generating an answer to the input question using a large-scale language model, and outputting the generated answer to the user; determining whether a condition for proceeding to a next stage subsequent to a stage of the plurality of stages is satisfied; When it is determined that the condition for proceeding to the next stage is satisfied, in the step of presenting which stage the user is at, the information processing device presents information indicating that the user has proceeded to the next stage.

Images