Program, method, and information processing device

Abstract

When a user makes an inquiry by voice, there is a need for a technology that can more easily connect the user to the intended contact point. [Solution] A program for operating a computer having a computer processor, the program causing the computer processor to execute the steps of accepting a question input by voice data from a user seeking advice, generating a response content using a large-scale language model in response to the question input by voice data, identifying an entity that will respond to the question based on the generated response content, and presenting information about the identified entity that will respond to the user seeking advice.

Description

[Technical Field]

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

[0002] When an inquiry is received from a user by telephone, etc., a voice response system automatically responds with voice information, responds using voice synthesis, and the terminal accepts user operations regarding the connection destination (such as specifying a number), and then sends a DTMF (Dual-Tone Multi-Frequency) signal from the terminal to the voice response system, thereby connecting the inquiry destination via voice.

[0003] Patent Document 1 gives the following background: "Because users cannot directly check the commands they have sent, they cannot determine whether their operations are correct," and "the interactive voice response device synthesizes the button number pressed by the user and repeats it to the user, or repeats the voice recognition results of the voice command to the user, allowing the user to confirm again by pressing the buttons whether the number or command is correct."

[0004] Patent Document 1 addresses the issue that "the increase in the number of operations that users must input makes operations more complicated and also lengthens call times," and describes a technology that "provides an automatic voice response device, an automatic voice response system, and an automatic voice response program that can efficiently provide automatic voice responses by displaying the input details up to that point on a screen just before the final decision on the automatic voice response procedure is made, allowing the user to visually confirm that the input details are correct."

[0005] According to the technology of Patent Document 1, this makes it possible to "display the contents of the voice commands received up to that point on the display device used by the user just before the final decision on the automatic voice response procedure, allowing the user to visually check whether there are any errors in the input contents," which is said to have the effect of "realizing an automatic voice response device and automatic voice response system that can provide efficient automatic voice response." [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-130300 Summary of the Invention [Problem to be solved by the invention]

[0007] In the case of such an automated voice response system, the person making the inquiry needs a certain amount of time to listen to the voice guide. As the number of contact options increases, the time it takes to listen to the voice guide also increases, and it is possible that the person will forget a contact option that appeared early in the voice guide and have to listen to the voice guide again.

[0008] Therefore, there is a need for a technology that can more easily connect a client to the intended contact point when the client makes a voice inquiry. [Means for solving the problem]

[0009] According to one embodiment of the present disclosure, there is provided a program for operating a computer including a computer processor, which causes the computer processor to execute the following steps: accepting a question input in the form of voice data from a user seeking consultation; generating a response to the question input in the form of voice data using a large-scale language model; identifying an entity that will respond to the question based on the generated response; and presenting information about the identified entity that will respond to the user seeking consultation. [Effects of the Invention]

[0010] According to the present disclosure, when a client makes an inquiry by voice, the client can more easily connect to the contact point that the client intends to contact. [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 inquiry database 212. As shown in FIG. [Figure 6] FIG. 6 is a diagram showing the data structure of the customer database 213. [Figure 7] FIG. 7 is a diagram showing the data structure of the voice inquiry history database 214. As shown in FIG. [Figure 8] FIG. 8 is a diagram showing the data structure of the matching database 215. As shown in FIG. [Figure 9] FIG. 9 is a diagram showing the flow of processing for identifying the contact point and responding to a consultation request made by voice from a client. [Figure 10] FIG. 10 is a diagram showing the flow of processing in which information for determining whether or not to respond to a consultation from a client is presented to the expert, and the expert receives a designation of whether or not to respond. [Figure 11] FIG. 11 shows an example of an operation screen that presents information to the expert on whether to respond to the consultation from the client and accepts the expert's designation of whether to respond or not. 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 server 20, a user terminal 10, a terminal 10A, an artificial intelligence (large-scale language model) service server 95 (hereinafter also referred to as the "large-scale language model service server 95"), and a voice input device 10B. These devices are connected for communication via a network 80.

[0015] In the illustrated example, a telephone booth 98 installed in various locations is equipped with a voice input device 10B. The telephone booth 98 is used by unspecified users, and the users use the voice input device 10B to access services provided by the server 20. The users may also use their own terminals 10, 10A to access services provided by the server 20.

[0016] The server 20 provides various services by providing the following functions. A service that automatically responds to voice inquiries from the person seeking advice (such as calls to a predefined phone number) with a voice message, identifies the contact point, and connects the person to the contact point. A service that matches clients with experts who can respond to their inquiries In the illustrated example, the terminals used by users of the services provided by the server 20 include the terminal 10, the voice input device 10B, etc., and each user operates their own terminal.

[0017] 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.

[0018] The terminal 10 is a device operated by a user. In this embodiment, the user may be any of the following: · User of the consultant: Legal consultation, other consultation Professional users: legal professionals and other professionals The expert user responds by voice depending on the content of the consultation. Terminal 10 and terminal 10A have the same functional configuration.

[0019] 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 .

[0020] The communication IF 12 is an interface for inputting and outputting signals so that the terminal 10 can communicate with an external device.

[0021] 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.).

[0022] The output device 14 is a device (such as a display or speaker) for presenting information to the user.

[0023] 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).

[0024] The storage 16 is for storing data, and is, for example, a flash memory or a hard disk drive (HDD).

[0025] 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.

[0026] In this embodiment, the server 20 is a device for providing a user with a function for determining the contact point for using a legal consultation service. In this embodiment, the server 20 accepts input of a consultation such as a legal consultation by voice over the telephone or the like from the user of the terminal 10, and performs the following processes by analyzing the results of transcription using voice recognition or the like. A process of causing the server 95 of the large-scale language model service to generate a response content for the user of the client, and a process of transmitting the generated response content to the user of the client by voice. - Processing to identify the contact point that corresponds to the consultation content of the user who is seeking advice, and match the contact point with an expert by telephone connection, etc. - A process to provide the expert user with information to decide whether or not to respond to an inquiry based on the voice input received from the user seeking advice (for example, if there is a conflict with an existing customer and the consultation cannot be accepted) In this way, the server 20 makes it easier for the client to connect with the expert by identifying the contact point for voice consultation over the telephone or the like and connecting the client with the expert.

[0027] On the other hand, when an expert responds to a telephone inquiry, it can be difficult to determine whether to proceed with the consultation based on the content of the inquiry until the expert actually speaks to the person on the phone. For example, the expert may not be able to respond to the consultation due to circumstances such as a conflict with the expert's existing client. The server 20 stores information about the person based on the results of a voice conversation (chat) with the person. This provides the expert, who is the contact point for the information about the person, with information on whether to respond to the voice inquiry from the person, making it easier for the expert to proceed with the work without responding to an inquiry that the expert did not intend. This makes it easier to match the person with an expert and ensure that the expert is more suited to the person.

[0028] The server 20 may accept requests for legal consultation from clients to legal experts by matching users who provide legal consultation as experts, such as law firms, with users who request legal consultation from experts, such as business companies or individuals. For example, the content of the consultation may be posted on a bulletin board that can be viewed by third parties, and the expert's response may also be made public. Alternatively, the content of the consultation may be kept private and not disclosed to third parties, allowing the client to consult with the expert. The server 20 stores such client consultation content and the expert's response.

[0029] The server 20 includes a communication IF 22 , an input / output IF 23 , a memory 25 , a storage 26 , and a processor 29 .

[0030] The communication IF 22 is an interface for inputting and outputting signals so that the server 20 can communicate with external devices.

[0031] 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.

[0032] 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).

[0033] The storage 26 is for storing data, and is, for example, a flash memory or a hard disk drive (HDD).

[0034] 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.

[0035] The large-scale language model service server 95 is a server that executes language processing tasks using a language model constructed by a learning process including artificial intelligence (AI). An LLM (Large Language Model) is a server that has previously learned a large amount of large-scale data (text data, etc.), such as web content on the Internet, or a large amount of data stored in a specified database, and can execute various language processing tasks by providing the task.

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

[0037] <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.

[0038] The communication unit 201 performs processing for the server 20 to communicate with external devices.

[0039] The storage unit 202 stores various databases such as a user database 211, an inquiry destination database 212, a customer database 213, a voice inquiry history database 214, a matching database 215, and a voice input device database 216.

[0040] The user database 211 is a database that manages information about each user, as will be described in detail later.

[0041] The inquiry database 212 is a database that manages information on the contact points that receive inquiries from clients. Details will be described later.

[0042] The customer database 213 is a database of the customers of the specialists who provide consultations. Details will be described later.

[0043] The voice inquiry history database 214 is a database for managing the contents of inquiries received by voice from clients, as will be described in detail later.

[0044] The matching database 215 is a database that manages the matching status of the contact point that responds to the consultation input by the client through voice input. Details will be described later.

[0045] The voice input device database 216 is a database that manages information on voice input devices that are installed in various locations and that receive consultation details from clients through voice input.

[0046] The control unit 203 is realized by the processor 29 reading a program stored in the storage unit 202 and executing instructions included in the program. By operating in accordance with the program, the control unit 203 exhibits functions shown as a reception control module 2041, a transmission control module 2042, a user management module 2043, a voice response processing module 2044, an LLM usage module 2045, an inquiry destination management module 2046, and a matching processing module 2047.

[0047] The reception control module 2041 controls the process by which the server 20 receives signals from external devices in accordance with a communication protocol.

[0048] The transmission control module 2042 controls the process in which the server 20 transmits signals to external devices in accordance with a communication protocol.

[0049] 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.

[0050] The voice response processing module 2044 is a program module that performs processing to generate a response by the large-scale language model service server 95 in response to a consultation request input by voice from the client, while updating the voice inquiry history database 214.

[0051] The LLM usage module 2045 is a program module that generates prompts based on the content of the consultation input by the user in free text, images, voice, etc., and generates answers by sending the generated prompts to the large-scale language model service server 95.

[0052] The inquiry destination management module 2046 is a program module that performs processing to receive designation of inquiry destination information from the user (expert user) who receives the inquiry, and to update the inquiry destination database 212 .

[0053] The matching processing module 2047 is a program module that performs processing to refer to the inquiry destination database 212 based on the information of the seeker stored in the voice inquiry history database 214, determine the inquiry destination, match the seeker with the inquiry destination, update the matching database 215, and manage the matching status.

[0054] <1.3 Configuration of Terminal 10> FIG. 3 is a diagram showing the configuration of the terminal 10. As shown in FIG.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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.

[0063] 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.

[0064] The motion sensor 170 includes an acceleration sensor, an angular velocity sensor, etc., and detects the movement of the terminal 10 .

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] The storage control unit 195 controls the storage of data in the storage unit 180 .

[0072] 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.

[0073] The user information 181 is information about a user who uses the services of the server 20 .

[0074] <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."

[0075] The item "user ID" is information that identifies each user.

[0076] The item "Name" is information indicating the name of the user.

[0077] The item "telephone number" is information about the user's telephone number.

[0078] The item "email address" is information about the email address used to contact the user.

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

[0080] 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.

[0081] 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.

[0082] 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 lawyers 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.

[0083] The item "status" is information indicating the user's status regarding legal advice.

[0084] 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.

[0085] Specifically, the item "field" includes information on each field classified as a field of legal consultation. For example, if the server 20 provides a service introducing experts such as lawyers and classifies the fields of experts according to the type of consultation content (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.

[0086] The item "evaluation value" is information indicating an evaluation value obtained by evaluating the manner of legal consultation by the user.

[0087] 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 inquiry database 212. Inquiry database 212 includes an item "inquiry ID," an item "business ID," an item "handling department," an item "handling details," an item "telephone number," and an item "management user ID."

[0088] The item "contact ID" is information that identifies each contact point for inquiries made by voice.

[0089] The item "business operator ID" is information that identifies each business operator.

[0090] The item “business ID” may be associated with the item “business ID” of the user database 211.

[0091] The item "department in charge of inquiries" is information about the contact point that handles inquiries related to the inquiries.

[0092] The item "department to contact" may include the following as contact information: - Information about the user you are responding to For example, a department in an organization For example, the qualifications of the person handling the consultation (for example, the qualifications of a lawyer or other person who can provide knowledge and advice based on legal procedures regarding the content of the consultation) A chat system that responds to inquiries by outputting trained models, etc. The item "Response details" is information about the response details of the contact person.

[0093] The item "content of response" may include the following as the content of the response. - Areas of consultation based on legal procedures, such as the following areas: "Divorce and gender issues" (property division, child support, divorce, etc.) "Debt" (contracts, statutes of limitations, debt consolidation, overpayments, mortgages, etc.) "Inheritance" (gifts, inheritance procedures, wills, etc.) "Traffic accidents" (settlement negotiations, residual disabilities, fault ratio, etc.) "Internet" (removal requests, defamation, etc.) "Consumer harm" (fraudulent business practices, etc.) "Crime and criminal cases" (criminal defense, crime victimization, etc.) "Labor" (harassment, wages, etc.) "Debt collection" (security rights, forced execution, etc.) General corporate business inquiries (such as inquiries about billing procedures), general information systems inquiries, etc. The item "telephone number" is contact information for inquiries.

[0094] More specifically, the item "telephone number" includes the telephone number of the department to which the inquiry should be directed, the telephone number of the person in charge of the inquiry, an extension number, and the like.

[0095] The item "management user ID" is information for identifying the user who manages the contact information.

[0096] The item “management user ID” may be associated with the item “user ID” of the user database 211 .

[0097] 6 is a diagram showing the data structure of customer database 213. Customer database 213 includes the following items: "Customer ID," "Business ID," "Customer Name," "Address or Residence," "Customer Person in Charge," "Responsible Person in Charge," and "Customer Registration Date."

[0098] The item "Customer ID" is information that identifies each customer of the organization to be contacted.

[0099] The item "business ID" is information that identifies the organization to which the inquiry should be directed.

[0100] The item “business ID” may be associated with the item “business ID” of the user database 211.

[0101] The item "customer name" is information about the name of the customer to contact.

[0102] The item "Address or Residence" is information about the address or residence of the customer to whom the inquiry is directed.

[0103] The item "customer's person in charge" is information about the person in charge of the customer to whom the inquiry is directed.

[0104] The item "response person" is information for identifying the person in charge of the customer in the organization of the inquiry destination.

[0105] The item "person in charge" may be associated with the item "user ID" in the user database 211.

[0106] The item “customer registration date” is information on when the customer information was registered in the customer database 213 .

[0107] 7 is a diagram showing the data structure of the voice inquiry history database 214. The voice inquiry history database 214 includes an item "voice inquiry ID," an item "inquirer ID," an item "inquirer telephone number," an item "inquiry telephone number," an item "consultation voice data," an item "automatic response history," an item "inquiry department," and an item "consultant information."

[0108] The item "Voice inquiry ID" is information that identifies each voice inquiry from a client.

[0109] More specifically, the item "voice inquiry ID" is information for identifying each inquiry received from a client by telephone or the like.

[0110] The item "inquirer ID" is information that identifies the person making the inquiry.

[0111] The item "inquirer ID" may be associated with the item "user ID" in the user database 211. Also, it is possible that a person making an inquiry by telephone is not registered in the user database 211 or the like.

[0112] The item "inquirer's telephone number" is information about the telephone number of the person making the inquiry.

[0113] The item "inquiry source phone number" may include the following: If the phone number used by the user making the inquiry is not blocked but is publicly displayed, information about the publicly displayed phone number - The system responds to inquiries by voice, and receives phone numbers entered by voice or touch-tone from the user. - A telephone number entered by a human operator who has spoken to the user making the inquiry The item "contact telephone number" is information on the telephone number of the person to contact for a response to the inquiry.

[0114] More specifically, the item "contact telephone number" is information obtained when the voice response processing module 2044 of the server 20 determines the contact person for inquiries regarding the consultation content of the client by referring to the contact database 212 during the process of responding to the client by voice.

[0115] The item "Consultation voice data" is information on the voice data of the consultation content received by voice from the client.

[0116] The item "automatic response history" is information on the consultation content of the client and the result of the response by the voice response processing module 2044 of the server 20.

[0117] More specifically, the item "automatic response history" is information including data transcribed by the server 20 or the large-scale language model service server 95, etc., about the consultation content of the client, and text of the response content generated by the large-scale language model service server 95 by including the transcription data of the consultation content of the client in a prompt and providing the prompt to the large-scale language model service server 95. For example, in the item "automatic response history," the transcription data of the client's voice and the text of the response result from the large-scale language model service server 95 in response to the transcription data may be associated and sequentially stored as a chat-style dialogue.

[0118] The item "Inquiry department" is information identifying the department that will handle the consultation of the requester.

[0119] The item “Inquiry department” may be associated with the item “Inquiry ID” in the inquiry database 212 .

[0120] The item "information of the client" is information of the client that is accumulated by the voice response processing module 2044 of the server 20 by responding to the client.

[0121] The item "information of the consultant" may include the following as information of the consultant: · Information that will be used to determine whether or not an expert can accept a consultation

[0122] (1) For example, the name, title, address, or residence of the person seeking advice. By identifying the person seeking advice based on the name and address, the expert can determine whether there is a conflict. If there is a conflict and the expert cannot accept the case, the voice response processing module 2044 may not disclose contact information (telephone number, organization, name of person in charge, etc.) to the person seeking advice.

[0123] (2) For example, the content of the consultation. If different people are consulting about the same topic, there is a possibility of a conflict. In this case, the expert user may be notified that different people are consulting about the same topic, and a message may be displayed suggesting to the expert user that the meeting be scheduled on a different date (for example, a different time). This makes it possible to avoid hearing the same case at the same time in an organization of experts, even if different people are consulting about the same issue from conflicting people, and increases the likelihood that one of the cases will be accepted.

[0124] (3) The track record of other attorneys in taking on the consultation content of the client. Depending on the expert, if another attorney is currently representing the client or has represented the client in the past, the expert may take this into consideration when deciding whether to take on the consultation. For example, the expert user may determine whether the expert user can resolve a case that could not be resolved even by the other attorney, or whether the likelihood of this is low. If the expert user has received information about the name or title of the other attorney from the client, the name of the other attorney may be presented to the expert user.

[0125] (4) The stage of negotiations between the client. For example, whether the parties are currently negotiating with each other or whether a lawsuit has been filed. This information can provide expert users with information to determine whether an urgent response is required.

[0126] 8 is a diagram showing the data structure of the matching database 215. The matching database 215 includes an item "matching ID," an item "voice inquiry ID," an item "response availability status," an item "consultation stage," an item "matching date and time," an item "contact with another inquiry contact," and an item "respondent user ID."

[0127] The item "matching ID" is information for identifying each history of matching between an inquiry destination and a request based on information acquired from the requester by the matching processing module 2047.

[0128] The item "Voice inquiry ID" is information that identifies each voice inquiry from a client.

[0129] The item “Voice Query ID” may be associated with the item “Voice Query ID” in the voice query history database 214 .

[0130] The item "Response availability status" is information on the status of whether or not a response is made to the consultation from the client.

[0131] The item "Response availability status" may include the following regarding whether or not a response is made. OK: Respond to inquiries from clients regarding their consultations. NG: Do not respond to the consultation content from the person seeking advice. Furthermore, it may be possible to classify the reasons for not responding as follows:

[0132] "Conflict": There is a conflict with the client, so the client cannot respond to the inquiry. "Different departments or users": The department or user is not the one that can handle the content of the consultation. For example, the department may not have the resources to handle the consultation because it is in a different field, or another department may be more suitable to handle the consultation. In addition, depending on the information in the item "Consultant Information" in the voice inquiry history database 214, there may be cases where the caller does not respond. In this way, the server 20 may accept, from the user of the inquiry destination, a designation of the reason for not responding in the item "Response availability status" of the matching database 215, and may store the content of the designation.

[0133] The item "stage of consultation" is information about the stage of consultation of the consultant.

[0134] The item "stage of consultation" may include the following stages of consultation: General consultation: A stage where general knowledge is needed, rather than specific individual consultation. Consultation on an individual case: The stage at which a consultation is made on an individual specific case. Furthermore, it may be possible to manage whether the stage is a negotiation stage or a stage of litigation procedures such as sending a complaint. For example, when the matching processing module 2047 determines the contact point for inquiries regarding the consultation content of the client, it may update the item "Stage of consultation" in the matching database 215 according to the information of the client accumulated in the voice inquiry history database 214.

[0135] The item "matching date and time" is information on the timing when the matching processing module 2047 matched the inquiry destination based on the information acquired from the seeker.

[0136] The item "Contact of another contact" is information on an alternative contact that is presented to the client regardless of the contact identified based on the voice inquiry history database 214 and the contact database 212, which indicate the content of the client's consultation.

[0137] The item "replying user ID" is information for identifying the user who will be in charge of handling the requester through matching.

[0138] The item “respondent user ID” may be associated with the item “user ID” of the user database 211.

[0139] <3 operations> FIG. 9 is a diagram showing the flow of processing for identifying the contact point and responding to a consultation request made by voice from a client.

[0140] In step S911, the terminal 10 accepts an operation to start a voice inquiry from the user. For example, the terminal 10 accepts an operation to make a call to a contact number such as a main telephone number of the inquiry destination from the user of the client.

[0141] In step S921, the voice response processing module 2044 of the server 20 responds by synthesizing a predetermined message to the terminal 10. For example, the voice response processing module 2044 selects a question sentence (for example, a question to be asked of the client about the content of the inquiry) for determining the contact point for the terminal 10 that has made the call, voice-synthesizes the question sentence, and transmits the voice to the terminal 10.

[0142] The voice response processing module 2044 sends the client a voice message urging the client to input the content of the consultation and the contact point by voice, and encourages the client to input this information by voice, but does not present the client with an identification number for connecting to each contact point (for example, a message such as "Press button 1 for requirement A (or contact point A) and button 2 for requirement B (or contact point B)" is not presented to the client), and may accept free text voice input from the client.

[0143] Here, in addition to the example in which the server 20 accepts voice inquiries at the user's terminal 10, questions may be input by voice data from users who are seeking advice via voice input devices used by various users. For example, telephone booths may be installed throughout the city. In this way, voice input devices that accept consultations by voice from users are installed in various locations. In response to a call from a voice input device in each location, the voice response processing module 2044 may store the input content of the question from the user who is seeking advice, accepted by the voice input device, in the voice inquiry history database 214, in association with information on the installation locations of the voice input devices in each location.

[0144] In step S913, the terminal 10 plays back the voice of the predetermined message received from the server 20, and receives a question input by voice from the user seeking advice.

[0145] In step S923, the voice response processing module 2044 of the server 20 performs processing to determine the destination of inquiry based on the question input by voice data from the client and the inquiry destination database 212. For example, the voice response processing module 2044 accepts a question input by voice data from the client user. The voice response processing module 2044 generates a response to the question input by voice data using a large-scale language model. More specifically, the voice response processing module 2044 attaches the voice data from the client (or attaches transcription data obtained by speech recognition of the voice data from the client) and includes information from the inquiry destination database 212 in the prompt to generate a response to the client including the result of the determination of the destination of inquiry. The voice response processing module 2044 transmits the generated prompt to the large-scale language model service server 95.

[0146] Furthermore, the voice response processing module 2044 may analyze transcription data obtained by transcribing voice data from the client and identify the person to contact by referring to the contact database 212. For example, by transcribing the voice data of the consultation content, text data such as "I would like to know about..." is obtained. The voice response processing module 2044 may identify information corresponding to the consultation content (e.g., each word extracted by breaking down the transcription data into words), determine the consultation content of the client based on words corresponding to nouns, etc. (e.g., words such as "divorce"), and identify the person to contact by referring to the contact database 212. For example, the voice response processing module 2044 may input the voice data from the client and information from the contact database 212, and provide a prompt to the large-scale language model service server 95 for identifying the person to contact, thereby identifying the person to contact based on the result generated by the server 95.

[0147] In step S925, the voice response processing module 2044 of the server 20 obtains the results generated by the large-scale language model service server 95 as a response to the question, and updates the voice query history database 214.

[0148] In step S927, the voice response processing module 2044 of the server 20 identifies an entity that will respond to the client's question based on the response content generated by the large-scale language model service server 95, and updates the voice inquiry history database 214.

[0149] The voice response processing module 2044 may, for example, analyze the results generated by the large-scale language model service server 95, identify the contact point based on the generated results suggesting the contact point, such as "The contact point is...", and update the voice inquiry history database 214.

[0150] The voice response processing module 2044 may identify at least one of an expert who will respond to the client's inquiry and a chat system using a trained model that returns a response to the client's inquiry input as the entity that will respond.

[0151] In step S929, the voice response processing module 2044 of the server 20 presents information about the identified entity that will handle the consultation to the user of the consultation. Specifically, the voice response processing module 2044 voice-synthesizes a response message including the information about the identified entity that will handle the consultation, and outputs the synthesized message to the terminal 10.

[0152] The matching processing module 2047 refers to the voice inquiry history database 214, identifies an expert user corresponding to the content of the question as the entity that will respond, receives a designation from the identified expert user as to whether or not to connect the client to the consultation, and updates the matching database 215. When the identified expert user designates to connect the client to the consultation, the voice response processing module 2044 may present information about the identified expert user to the client user (such as by outputting it by voice).

[0153] The matching processing module 2047 may also refer to the voice inquiry history database 214 to identify one or more entities that will handle the consultation content of the client. The voice response processing module 2044 may refer to the matching database 215 and present (by voice, for example) information on the identified one or more entities that will handle the consultation to the client's user. The voice response processing module 2044 may accept an operation from the client's user to designate the entity that will handle the consultation to be presented (by speaking about the entity that will handle the consultation by voice, by designating the entity that will handle the consultation by touch-tone, for example), and connect (for example, by telephone) the entity that will handle the consultation according to the received designation to the client's user so that they can be contacted.

[0154] In step S915, the terminal 10 plays back a message including information about the person who will be attending.

[0155] FIG. 10 is a diagram showing the flow of processing in which information for determining whether or not to respond to a consultation from a client is presented to the expert, and the expert receives a designation of whether or not to respond.

[0156] In step S1021, the matching processing module 2047 of the server 20 refers to the voice inquiry history database 214, and if the inquiry destination is specified, updates the matching database 215. The matching processing module 2047 presents the information acquired from the client through a voice response to the expert user.

[0157] Here, the voice response processing module 2044 may output voice data asking the user who is seeking advice for the name of the user who is seeking advice. The voice response processing module 2044 acquires from the user who is seeking advice an input from the user who is seeking advice (data in which the user speaks the name of the user who is seeking advice). The matching processing module 2047 presents the input content related to the name of the user who is seeking advice to the entity that will handle the consultation and that is identified by the voice input from the user who is seeking advice. This makes it easier for the entity that will handle the consultation to determine whether the consultation content from the user who is seeking advice conflicts with the consultation content of another user (whether it is possible to accept the consultation), etc.

[0158] The voice response processing module 2044 may also output voice data inquiring about the address of the user who is seeking advice. The voice response processing module 2044 acquires from the user the content of the consultation made by the user who is seeking advice (data in which the user's address is spoken aloud). The matching processing module 2047 presents the input content of the user who is seeking advice to the identified entity that will handle the consultation. This makes it easier for the entity that will handle the consultation to determine whether the consultation content from the user who is seeking advice conflicts with the consultation content of another user.

[0159] Here, the server 20 stores information on the consultation content from each client in the voice inquiry history database 214. The voice response processing module 2044 may output voice data inquiring about the consultation content of the client to the client user. The voice response processing module 2044 acquires from the client user input (data of the client user's voice utterance of the consultation content) in response to the voice data inquiring about the consultation content. The matching processing module 2047 determines whether the input content of the consultation content of the client is the same as the consultation content from other clients stored in a database such as the voice inquiry history database 214. For example, the matching processing module 2047 may provide a prompt to the large-scale language model service server 95 to evaluate whether the consultation content of the client is the same as the other stored consultation content, and determine whether the consultation content is the same based on the response of the server 95. If the matching processing module 2047 determines that the consultation content from different clients is the same, it notifies the identified entity that will handle the consultation. This makes it easier to determine whether consultations from different clients relate to the same case and whether it is possible to respond to both consultations at the same time (whether to not respond to one of them).

[0160] In this way, when it is determined that there are consultation contents of the same content, the matching processing module 2047 may suggest to the entity that will handle the consultation that a meeting be set on a different day from each of the clients. For example, if an organization that handles consultations has multiple staff members and receives consultations from both parties involved in the same case, it may be easy to prioritize handling one of them by having the meeting dates different.

[0161] The voice response processing module 2044 responds to the user who is seeking advice by: The agent's track record in accepting cases regarding the consultation content of the user who is seeking advice; Whether the user inquiring is currently involved in a lawsuit; Facts regarding the content of the consultation by the user, Alternatively, voice data may be output asking at least one of the above questions.

[0162] The voice response processing module 2044 acquires input contents of the client user in response to the voice data inquiring about at least one of the questions from the client user, and updates the voice inquiry history database 214. The matching processing module 2047 may present the input contents of the client user in response to the voice data inquiring about at least one of the questions to the identified entity that will handle the interaction.

[0163] In this way, by obtaining various information from the user seeking advice, it is possible to provide the expert user with information to decide whether to respond to the user's consultation, which further promotes matching between the user seeking advice and the expert.

[0164] The voice response processing module 2044 may determine whether the consultation content is a general question or relates to a specific case, based on the question input by the user of the consultation. The matching processing module 2047 may present the determination result to the identified entity that will handle the consultation. This provides the entity that will handle the consultation (e.g., an expert) with information to help them decide whether to handle the consultation, making it even easier for them to decide whether to handle the consultation.

[0165] The voice response processing module 2044 may output voice data inquiring about the negotiation stage of the consultation content of the solicitor user to the solicitor user. The voice response processing module 2044 acquires from the solicitor user input content (data spoken by the solicitor user about the negotiation stage) in response to the voice data inquiring about the negotiation stage. The matching processing module 2047 presents the input content related to the negotiation stage of the solicitor user to the identified entity that will handle the consultation. This provides the entity that will handle the consultation (e.g., an expert) with information to help them decide whether or not to handle the consultation, making it even easier for them to decide whether or not to handle the consultation.

[0166] In step S1011, the terminal 10 presents the information acquired from the client to the user identified as the contact point, and accepts a designation as to whether to connect with the client (for example, whether to respond to a call from the client by telephone).

[0167] In step S1023, the server 20 updates the matching database 215 in accordance with the specification of the expert user identified as the contact point. The matching processing module 2047 connects the expert user and the client user in accordance with the specification of the expert user, or responds to the client user with another contact point.

[0168] Here, the server 20 stores information on the name of each client in the customer database 213. The matching processing module 2047 may determine whether or not a client receiving a consultation via voice has a conflict with another client (a client in the customer database 213) based on the input content (voice inquiry history database 214) related to the name of the client who is receiving a consultation via voice and the name of each client stored in the customer database 213. For example, the customer database 213 stores information on clients who may have a conflict (such as name, business details, etc.) in association with each client, and also information on the other party (specified by the other party's name, address, representative name, etc.) when the client is consulting on legal procedures. In this way, the matching processing module 2047 may determine whether or not a conflict exists between the client user and a client in the customer database 213.

[0169] When it is determined that there is a conflict with another client, the matching processing module 2047 may not present information about the entity that will be handling the client to the user of the client who accepts input of a question by voice data.

[0170] The matching processing module 2047 may receive, from the specified entity (expert user) that will provide the service, a designation as to whether or not the expert user will respond to the consultation content of the user requesting the consultation via voice. When the matching processing module 2047 receives, from the specified entity that will provide the service, a designation that the expert user cannot respond to the consultation, the matching processing module 2047 may present, to the user requesting the consultation, information on a contact point other than that of the specified entity that will provide the service.

[0171] Furthermore, the voice response processing module 2044 may provide a response to the consultation content to a user who has received a question input via voice data by a messaging means other than voice data (for example, email, sending and receiving messages between user accounts via a messaging tool, etc.).

[0172] <4 Screen example> FIG. 11 shows an example of an operation screen that presents information to the expert on whether to respond to the consultation from the client and accepts the expert's designation of whether to respond or not.

[0173] The response operation screen 1100 is an operation screen for accepting operations to respond to an inquiry from a user who is an expert to be contacted.

[0174] The account display area 1102 is an area where information about the user's account is displayed.

[0175] More specifically, the account display area 1102 is an area that displays the user's name and the like.

[0176] The inquiry details display area 1104 is an area for displaying the details of an inquiry.

[0177] The list display area 1106 is an area for displaying a list of inquiries received by voice.

[0178] The list display area 1106 may include the following details for each inquiry: Information that can be used to determine whether to respond to the consultation of the person seeking advice, as explained in step S1021 etc.:

[0179] (1) Based on whether or not there is a conflict with existing customers Name of the person seeking advice (information identifying the other party in legal proceedings for an existing client) Address and residence of the person seeking advice (information identifying the other party in legal proceedings for an existing client) Content of the consultation (Is it the same issue as the one being consulted about by an existing customer?)

[0180] (2) Whether the consultation is about solving a specific problem or general consultation Here, the server 20 may receive from the expert user a setting as to whether the expert will respond to the consultation depending on whether the consultation is for solving a specific problem or a general consultation.

[0181] For example, if the setting is "If the consultation content is a general consultation, do not respond to voice inquiries from the client", the server 20 may respond to the client by voice, present the client with a question asking whether the consultation content is for solving a specific problem or a general consultation, and upon receiving a voice input from the client indicating that it is "a general consultation", the server 20 may store the result in the voice inquiry history database 214 and present the client with a voice guide indicating that the client will not be connected to the expert to whom the inquiry should be made.

[0182] (3) Whether the consultation is at the negotiation stage or has progressed to litigation proceedings. Here, the server 20 may receive a setting from the expert user as to whether the expert will provide consultation depending on whether the consultation content is at the negotiation stage or has progressed to litigation procedures.

[0183] (4) Other information stored in the voice inquiry history database 214 Designation of whether to respond to the inquiry as explained in step S1011 etc. (whether to respond or not, and if not, the reason, etc.) Contact information of the person making the inquiry: The telephone number of the person making the inquiry. By accepting an operation from the user to specify the telephone number to be displayed, inquiries from the person making the inquiry by telephone may be answered by telephone. Inquiry date and time: By showing the user the time that has passed since the inquiry was made, it can be used as a basis for deciding which inquiry to respond to. In this way, when the server 20 receives an audio consultation from a client, the list display area 1106 allows the expert to check the audio, while also allowing the expert to check on the screen the results of the transcription and consultation content organized by the large-scale language model service server 95, making it easy to communicate whether or not to accept the case.

[0184] The conflict confirmation operation section 1108 is an operation member that accepts an operation to confirm a customer who is in conflict with the client pertaining to the inquiry.

[0185] More specifically, the conflict confirmation operation section 1108 is an area that, in response to a user's operation, displays the result of determining whether there is a conflict based on the customer name, address, etc. and the name, address, etc. of the person seeking advice in the customer database 213. For example, the presence or absence of a conflict may be determined by storing in advance in the server 20 information on other parties with whom the customer is in a competitive relationship or on opposing parties in legal proceedings.

[0186] In addition, when a customer is considering or is actually taking steps to issue a warning or file a lawsuit, the server 20 may determine whether or not there is a conflict by referring to the other party's information in the data such as a warning letter, complaint, and briefs stored in the memory unit.

[0187] The other inquiry destination designation section 1110 is an operation member for accepting the designation of other inquiries to be presented to the inquirer when there is a circumstance that makes it impossible to respond to the inquiry.

[0188] The other inquiry destination designation unit 1110 corresponds to the process of step S1023 etc. and the item "Contact another inquiry destination" in the matching database 215. The server 20 may accept an operation from a user to designate another inquiry in association with an inquiry that is not being handled, and update the matching database 215. The server 20 may also transmit to the solicitor by voice that the inquiry destination cannot handle the inquiry and information on the other inquiry destination. The server 20 may, for example, notify the solicitor by telephone of the information on the other inquiry destination and accept from the solicitor a designation of whether to connect to the other inquiry destination by using a push-tone or an utterance from the solicitor indicating that the solicitor will connect to the other inquiry destination.

[0189] The schedule confirmation operation section 1112 is an operation member that accepts an operation to set the date and time for responding to an inquiry.

[0190] In the illustrated example, the schedule confirmation operation unit 1112 displays a message urging each client to schedule a meeting on a different date (for example, a different date) since the inquiries from each client contain the same content and there is a possibility that inquiries have been received from both parties to the dispute.

[0191] The contact device confirmation operation unit 1114 is an operation member that accepts an operation to confirm information about the telephone booth in use when the person making the inquiry uses a telephone booth for inquiries that is installed in various locations.

[0192] In the illustrated example, the contact device confirmation operation unit 1114 displays the location of the telephone booth for each consultation in response to a user operation, thereby allowing the user to determine the regional distribution of the people making inquiries.

[0193] <Modification> As described above, the process of determining the contact person by the large-scale language model service server 95 in response to a voice inquiry from a client based on the content of the client's utterance has been described.

[0194] In addition to the aspects described in the above embodiment, the following may be adopted.

[0195] (1) The server 20 may respond to inquiries from clients in a chat format, have the large-scale language model service server 95 generate an answer for legal or other inquiries, and present the generated answer to the client. The server 20 may accept inquiries from clients via voice input from a telephone booth 98 or the client's user terminal 10, and present the answer generated by the large-scale language model service server 95 to the client in a manner other than voice (e.g., text, image) and by a means of communication related to the consultation (e.g., telephone). For example, the client may voice the content of the inquiry over the telephone and receive the answer by email or the like.

[0196] (2) In the above embodiment, an example has been described in which the server 20 determines whether an expert will not respond to the consultation of the seeker (cannot respond to the consultation), and an example has been described in which the expert's user specifies whether or not to respond. In this way, when an expert will not respond to the consultation of the seeker, the server 20 may notify the seeker that the expert is unavailable, as described above, by calling the seeker's terminal, etc. In this case, the server 20 may notify the seeker that the expert is unavailable, as well as advice regarding the content of the seeker's consultation (for example, the result of generating an answer to the consultation content by the large-scale language model service server 95 based on information about the consultation content of the seeker).

[0197] (3) The server 20 may accept inquiries from registered telephone numbers, but may not accept consultations made by telephone or the like from unregistered telephone numbers, and may encourage registration or present other contact points. For example, if the call is from a telephone number registered in the "telephone number" item of the user database 211, the server 20 may respond to legal or other consultations through a voice dialogue between the person seeking advice and the chat system as described in the above modified example (1), but may not provide a consultation service through a dialogue with the chat system as described above if the call is not registered in the "telephone number" item of the user database 211.

[0198] The server 20 may also provide a paid consultation service through dialogue with a voice chat system. For example, the user database 211 may manage whether or not each user has signed up for a paid plan.

[0199] (4) Classify the question to generate an answer using a large-scale language model service, and create prompts based on the classification results. In addition to what has been described in the above embodiment, in order to have the large-scale language model service generate the answer intended by the user, the user's question may be classified, a prompt may be created based on the classified results, and the created prompt may be provided to the server 95 of the large-scale language model service.

[0200] 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.

[0201] 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.

[0202] 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."

[0203] 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.

[0204] 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."

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] <Additional Notes> The matters explained in the above embodiment will be supplemented below.

[0211] (Appendix 1) A program for operating a computer having a computer processor, the program causing the computer processor to execute the following steps: accepting a question input by voice data from a user seeking consultation; generating a response content using a large-scale language model in response to the question input by voice data; identifying an entity that will respond to the question based on the generated response content; and presenting information about the identified entity that will respond to the user seeking consultation.

[0212] (Appendix 2) The program according to claim 1, wherein in the identifying step, the entity that will provide the response is identified as at least one of an expert who will respond to the client's consultation and a chat system using a trained model that returns a response to the client's consultation input.

[0213] (Appendix 3) A program according to any one of appendices 1 to 2, wherein in the identifying step, an expert user corresponding to the content of the question is identified as the entity that will respond to the question, and a designation of whether or not to connect the identified expert user to the user of the client is accepted from the identified expert user, and in the presenting step, if the identified expert user designates that the user of the client should connect to the client, information about the identified expert user is presented to the user of the client.

[0214] (Appendix 4) A program according to any one of appendices 1 to 3, wherein in the specifying step, one or more entities that will handle the call are specified, and in the presenting step, information on the specified one or more entities that will handle the call are presented to the user of the client, an operation to designate the presented entity that will handle the call is accepted from the user of the client, and the accepted designated entity and the user of the client are connected so as to be able to communicate with each other.

[0215] (Appendix 5) The program further causes the computer processor to execute the steps of outputting voice data asking the user for the name of the client, and acquiring from the user an input from the client in response to the voice data asking for the name, wherein in the identifying step, the input relating to the name of the client is presented to the identified entity that will handle the interaction, the program according to any one of Appendices 1 to 4.

[0216] (Appendix 6) The program according to appendix 5, wherein in the outputting step, voice data inquiring about the address of the seeker is output to the seeker user, and in the acquiring step, input content of the seeker user in response to the voice data inquiring about the address is acquired from the seeker user, and in the identifying step, the input content of the seeker user's address is presented to the identified entity that will handle the interaction.

[0217] (Appendix 7) The program according to any one of appendices 5 to 6, wherein the storage unit stores information on the consultation content from each client, and in the outputting step, voice data inquiring about the consultation content of the client is output to the client's user, and in the acquiring step, input content of the client's user in response to the voice data inquiring about the consultation content is acquired from the client's user, and in the identifying step, it is determined whether the input content related to the consultation content of the client is the same as the consultation content from other clients stored in the storage unit, and if it is determined that the consultation content is the same, this fact is presented to the identified entity that will handle the response.

[0218] (Appendix 8) The program according to appendix 7, wherein, in the step of identifying, if it is determined that there are consultation matters of the same content, the program suggests to the identified entity that will be handling the consultation to set up a meeting on a different day than the date on which each of the consultation matters is scheduled.

[0219] (Appendix 9) 9. The program according to any one of appendices 5 to 8, wherein the storage section stores information on the name of each client, and in the identifying step, the presence or absence of a conflict with another client is determined based on the input content related to the client's user name and the names of each client stored in the storage section, and if it is determined that there is a conflict with another client, in the presenting step, information on the entity that will handle the response is not presented to the client user who accepts the question input by voice data.

[0220] (Appendix 10) The program further causes the computer processor to execute the steps of outputting voice data to the client user asking at least one of the following questions: the client user's record of accepting cases related to the client user's consultation content; whether the client user is currently in litigation; and facts related to the client user's consultation content; and acquiring from the client user the input content of the client user in response to the voice data asking at least one of the questions; and the program described in any of Appendices 1 to 9, wherein in the identification step, the input content of the client user in response to the voice data asking at least one of the questions is presented to the identified entity that will handle the consultation.

[0221] (Appendix 11) The program described in any of Appendices 1 to 10, further causing the computer processor to execute the steps of determining, based on a question input received from the user seeking advice, whether the consultation content is a general question or relates to a specific issue, and presenting the determination result to the identified entity that will handle the consultation.

[0222] (Appendix 12) The program further causes the computer processor to execute the steps of outputting voice data to the user of the client asking about the negotiation stage of the consultation content of the user of the client, and acquiring from the user of the client input content in response to the voice data asking about the negotiation stage, wherein in the identifying step, the input content related to the negotiation stage of the user of the client is presented to the identified entity that will handle the consultation. The program described in any of Appendices 1 to 11.

[0223] (Appendix 13) The program described in any of Appendices 1 to 12 further causes the computer processor to execute a step of receiving, from the identified entity that will handle the consultation, a designation of whether or not to handle the consultation content of the user who is seeking advice, and if a designation that the entity cannot handle the consultation is received from the identified entity that will handle the consultation, in a presentation step, presents to the user who is seeking advice information of a contact point other than that of the identified entity that will handle the consultation.

[0224] (Appendix 14) 14. The program according to any one of appendices 1 to 13, which presents an answer to a user who has input a question via voice data to the user by a messaging means other than the voice data.

[0225] (Appendix 15) A program according to any one of Appendices 1 to 14, wherein in the receiving step, a question is received as voice data from the user seeking consultation by a voice input device, wherein the voice input devices are installed in various locations, and the program further causes the computer processor to store the question input from the user seeking consultation received by the voice input device in a memory unit in association with information on the installation locations of the voice input devices in various locations.

[0226] (Appendix 16) A method for operating a computer having a computer processor, the method comprising the steps of: receiving a question input by voice data from a user seeking advice; generating a response to the question input by voice data using a large-scale language model; identifying an entity that will respond to the question based on the generated response; and presenting information about the identified entity that will respond to the user seeking advice.

[0227] (Appendix 17) An information processing device, wherein a control unit of the information processing device executes the steps of: accepting a question input by voice data from a user seeking consultation; generating a response content using a large-scale language model in response to the question input by voice data; identifying an entity that will respond to the question based on the generated response content; and presenting information about the identified entity that will respond to the user seeking consultation.

Claims

1. A program for operating a computer having a computer processor, the program causing the computer processor to: receiving a question input by voice data from a user who is seeking advice; generating a response content using a large-scale language model in response to the input of the question using the voice data; Identifying a subject that will respond to the question based on the generated response content; and presenting information about the identified entity that will handle the call to the user of the client.

2. In the step of specifying, as the entity that will handle the call, An expert who will respond to the consultation of the person seeking advice; a chat system using a trained model that returns a response to the consultation input of the consultant; The program according to claim 1, wherein the program specifies at least one of the following:

3. In the step of specifying, a user of an expert corresponding to the content of the question is specified as the entity that will handle the inquiry, and a designation of whether or not to connect the specified expert user to the requester is received; 2. The program according to claim 1, wherein, in the presenting step, when the user of the identified expert specifies to connect with the user of the client, information about the user of the identified expert is presented to the user of the client.

4. In the step of identifying, one or more entities that will handle the call are identified; 2. The program according to claim 1, wherein, in the presenting step, information on the one or more identified entities that will handle the call is presented to the user of the client, an operation to designate the presented entity that will handle the call is accepted from the user of the client, and the accepted designated entity that will handle the call is connected to the user of the client so that they can be contacted.

5. The program further causes the computer processor to: a step of outputting voice data to the user of the client asking for the name of the user of the client; acquiring from the user of the client an input content of the client in response to the voice data asking for the client's name; 2. The program according to claim 1, wherein, in the step of specifying, the input content relating to the name of the user of the requester is presented to the identified entity that will handle the request.

6. In the outputting step, voice data is output to the user of the client inquiring about the address of the client, In the acquiring step, an input content of the user of the client in response to the voice data inquiring about the address is acquired from the user of the client, 6. The program according to claim 5, wherein, in the step of specifying, the input content relating to the address of the user of the requester is presented to the specified entity that will handle the request.

7. The memory unit stores information about the consultation content from each client, In the outputting step, audio data is output to the user of the client inquiring about the consultation content of the client, In the acquiring step, an input content of the user of the client in response to the voice data inquiring about the consultation content is acquired from the user of the client, 6. The program according to claim 5, wherein in the step of specifying, it is determined whether the input content relating to the consultation content of the client is the same as the consultation content from another client stored in the storage unit, and if it is determined that the consultation content has the same content, a notification to that effect is presented to the identified entity that will handle the consultation.

8. 8. The program according to claim 7, wherein, when it is determined in the step of specifying that there is a consultation subject with the same content, the program suggests to the identified entity that will handle the consultation to set up a meeting on a date different from that of each of the clients.

9. The memory unit stores the name information of each client. In the step of specifying, the presence or absence of a conflict with another client is determined based on the input content related to the name of the user of the client and the names of each client stored in the storage unit; 6. The program according to claim 5, wherein, when it is determined that there is a conflict with another client, in the presenting step, information about the entity that will handle the consultation is not presented to the user of the client who accepts input of a question by the voice data.

10. The program further causes the computer processor to: To the user who is seeking advice, The agent's track record in accepting cases regarding the consultation content of the user of the consultation; Whether or not the user is currently in the process of litigation; Facts relating to the content of the consultation by the user of the consultation; outputting voice data asking at least one of the above questions; acquiring from the user of the client an input content in response to the voice data asking at least one of the questions, 2. The program according to claim 1, wherein in the step of specifying, the content of an input made by the user of the client in response to the voice data asking about at least one of the users of the client is presented to the identified entity that will handle the consultation.

11. The program further causes the computer processor to: Based on the input of the question received from the user of the consultation, Is the enquiry a general question? Whether the consultation is about a specific case, and determining The program according to claim 1 , further comprising: a step of presenting the result of said determination to said identified entity that will handle said call.

12. The program further causes the computer processor to: a step of outputting voice data to the user of the client inquiring about the negotiation stage of the consultation content of the user of the client; acquiring, from the user of the client, input content of the user of the client in response to the voice data inquiring about the negotiation stage; 2. The program according to claim 1, wherein, in the specifying step, input content relating to a negotiation stage of the user of the consultation is presented to the identified entity that will handle the consultation.

13. The program further causes the computer processor to: receiving, from the identified entity that will provide the consultation, a designation as to whether or not the entity will provide the consultation in response to the consultation content of the user of the consultation request; 2. The program according to claim 1, wherein, when a designation that the consultation cannot be handled is received from the identified entity that will handle the consultation, in the presenting step, information on a contact point other than the identified entity that will handle the consultation is presented to the user of the consultation requester.

14. 2. The program according to claim 1, wherein the program presents the answer to the question input by the voice data to the user of the consultation who has received the question input by the voice data, by a messaging means different from the voice data.

15. In the receiving step, a question is input by a voice input device from the user of the consultation request using the voice data, wherein the voice input device is installed in each location, The program further causes the computer processor to:

2. The program according to claim 1, wherein the storage section stores the question input from the user of the consultation accepted by the voice input device in association with information on the installation locations of the voice input devices in various locations.

16. 1. A method of operating a computer having a computer processor, the method comprising: receiving a question input by voice data from a user who is seeking advice; generating a response content using a large-scale language model in response to the input of the question using the voice data; Identifying a subject that will respond to the question based on the generated response content; and presenting information about the identified entity that will handle the call to the user of the caller.

17. An information processing device, wherein a control unit of the information processing device receiving a question input by voice data from a user who is seeking advice; generating a response content using a large-scale language model in response to the input of the question using the voice data; Identifying a subject that will respond to the question based on the generated response content; and presenting information about the identified entity that will handle the consultation to the user of the consultation request.

Images