Information processing device, information processing system, information processing method, program

Abstract

The aim is to reduce the workload on administrators. [Means for solving the problem] An information processing device having an input receiving unit that receives input of instructions for generating registered question data and registered answer data; a requesting unit that requests a large-scale language model to generate registered answer data corresponding to the registered question data based on the generation instructions; and an output unit that outputs the registered answer data output from the large-scale language model in response to the request to a terminal device.

Description

Technical Field

[0006] , , , , , , ,

[0005] ,

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

Background Art

[0002] In recent years, chatbot systems that provide answers corresponding to questions when a user inputs a question have become widespread. In such a chatbot system, it is known that question-and-answer information associating questions and answers is prepared, and an answer is presented based on the question-and-answer information for the input question.

Summary of the Invention

Problems to be Solved by the Invention

[0003] In the above-described conventional chatbot system, an administrator of the chatbot system needs to manually input a large number of questions and answers in order to present an effective answer to a question. In particular, when newly introducing a chatbot system, the input work takes a lot of time and places a heavy burden on the administrator.

[0004] The disclosed technology has been made in view of the above circumstances, and aims to reduce the burden on an administrator of manually inputting a large number of questions and answers.

Means for Solving the Problems

[0005] The disclosed technology is an information processing apparatus including an input reception unit that receives an input of generation instructions for registered question data and registered answer data, a request unit that outputs a request to generate registered answer data corresponding to the registered question data based on the generation instructions to a large language model, and an output unit that outputs the registered answer data output from the large language model in response to the request to a terminal device.

Effects of the Invention

[0006] The burden on an administrator of manually inputting a large number of questions and answers can be reduced. [Brief explanation of the drawing]

[0007] [Figure 1] This is a diagram showing an example of the system configuration of a chat system. [Figure 2] This figure shows an example of the hardware configuration of an information processing device. [Figure 3] This figure shows an example of the hardware configuration of a terminal device. [Figure 4] This figure shows an example of a conversation history memory unit. [Figure 5] This figure shows an example of a question and answer memory unit. [Figure 6] This figure shows an example of a document storage unit. [Figure 7] This figure shows an example of a user information storage unit. [Figure 8] This diagram illustrates the functions of each device in the chat system of the first embodiment. [Figure 9] This is the first sequence diagram illustrating the operation of the chat system according to the first embodiment. [Figure 10] This is a second sequence diagram illustrating the operation of the chat system in the first embodiment. [Figure 11] This is the first figure showing an example of the display of the terminal device according to the first embodiment. [Figure 12] This is the first diagram illustrating the prompts of the first embodiment. [Figure 13] The second figure illustrates the prompts of the first embodiment. [Figure 14] The second figure shows an example of the display of the terminal device according to the first embodiment. [Figure 15] This is the third figure, showing an example of the display of the terminal device according to the first embodiment. [Figure 16] This is the fourth figure, showing an example of the display of the terminal device according to the first embodiment. [Figure 17] This is the fifth figure, showing an example of the display of the terminal device according to the first embodiment. [Figure 18]It is the sixth figure showing a display example of the terminal device according to the first embodiment. [Figure 19] It is the first figure showing a display example of the terminal device according to the second embodiment. [Figure 20] It is the first figure for explaining the prompt according to the second embodiment. [Figure 21] It is the second figure showing a display example of the terminal device according to the second embodiment. [Figure 22] It is the second figure for explaining the prompt according to the second embodiment. [Figure 23] It is the first figure showing a display example of the terminal device according to the third embodiment. [Figure 24] It is the figure for explaining the prompt according to the third embodiment. [Figure 25] It is the figure for explaining another prompt according to the third embodiment. [Figure 26] It is the second figure showing a display example of the terminal device according to the third embodiment. [Figure 27] It is the figure showing an example of the system configuration of the chat system according to the fourth embodiment.

Mode for Carrying Out the Invention

[0008] (First Embodiment) Hereinafter, this embodiment will be described with reference to the drawings. FIG. 1 is a diagram showing an example of the system configuration of the chat system.

[0009] The chat system 100 of this embodiment includes an information processing device 200, a first storage device 300, a second storage device 400, a server device 500, a terminal device 600, and a terminal device 700, and is an example of an information processing system in which each is connected via a communication network 1.

[0010] In the chat system 100, the information processing device 200, the first storage device 300, the second storage device 400, and the server device 500 provide a chatbot service to the user of the terminal device 600.

[0011] When a question is input from the terminal device 600, the information processing device 200 refers to the question and answer information stored in the first storage device 300 and outputs the answer to the question to the terminal device 600.

[0012] The first storage device 300 includes a conversation history storage unit 310 and a question and answer storage unit 320. The conversation history storage unit 310 stores conversation history information that associates questions input from the terminal device 600 with answers output to the terminal device 600. The conversation history information may be managed separately for each tenant that installs the chat system 100. In this embodiment, a tenant may be an organization such as a company, and may be the organization to which a user of the chat system 100 belongs.

[0013] The question-answer storage unit 320 stores question-answer information in which questions and answers are associated. In other words, the question-answer storage unit 320 is an example of a group of question-answer information in which question data representing a question and answer data representing an answer are associated. Furthermore, question-answer information is information in which question data representing a question and answer data representing an answer are associated in pairs. Note that the question-answer information is information that is stored in the question-answer storage unit 320 in advance, and may be stored for each tenant that implements the chat system 100.

[0014] In the following explanation, the question data included in the question and answer information stored in the question and answer storage unit 320 will be referred to as registered question data, and the answer data included in the question and answer information will be referred to as registered answer data.

[0015] In this embodiment, the registered question data and registered answer data may be generated by a large-scale language model provided by the server device 500. Furthermore, the registered question data and registered answer data generated by the large-scale language model provided by the server device 500 in this embodiment may be reviewed and edited by the administrator of the chat system 100.

[0016] The second storage device 400 includes a document storage unit 410 and a user information storage unit 420. The document storage unit 410 stores user-specific information that is not publicly available.

[0017] Users of chat system 100 may be, for example, tenants, in which case user-specific information will be tenant-specific information. Alternatively, users of chat system 100 may be individual users, in which case user-specific information will be user-specific information.

[0018] In the following explanation, user-specific information will be referred to as "internal company information," and internal company information will be used as an example of user-specific information.

[0019] In this embodiment, the document storage unit 410 may store internal company information for each tenant. The user information storage unit 420 stores user information about users belonging to each tenant.

[0020] The server device 500 has a large-scale language model storage unit 510 that stores a large-scale language model, and realizes generative AI (Artificial Intelligence). The generative AI generates and outputs text data in response to input prompts, for example, ChatGPT. In the following description, the data output from the large-scale language model may be referred to as output data.

[0021] The server device 500 in this embodiment transmits the output data output by the large-scale language model.

[0022] Furthermore, the prompts in this embodiment are text data that represent instructions or questions for the generative AI implemented by the server device 500. Details of the large-scale language model will be described later.

[0023] Terminal device 600 is primarily used by users of the chat system 100. More specifically, terminal device 600 inputs question data, which represents a question for the chat system 100, into the information processing device 200. Terminal device 600 also displays answer data, which represents the answer to the question indicated by the input question data, output from the information processing device 200, in association with the input question data.

[0024] In the following explanation, the question data transmitted from the terminal device 600 to the information processing device 200 and input to the information processing device 200 will be referred to as input question data. Furthermore, in the following explanation, the answer data output from the information processing device 200 to the terminal device 600 will be referred to as output answer data.

[0025] The terminal device 700 is primarily used by administrators who manage the chat system 100. More specifically, the terminal device 700 performs operations such as generating registered question data and registered answer data to be stored in the question and answer storage unit 320.

[0026] In this embodiment, each of the terminal devices 600 and 700 may be, for example, a smartphone or a tablet terminal.

[0027] In the chat system 100 of this embodiment, when the information processing device 200 receives information to be used to generate registered question data and registered answer data, it outputs a prompt to the server device 500 requesting the generation of registered question data and corresponding registered answer data from the specified information. The information processing device 200 also associates the registered question data and registered answer data output from the large-scale language model in response to the prompt to create question and answer information, and displays a screen on the terminal device 700 for checking and editing the content of the question and answer information. The information processing device 200 then stores the question and answer information, after it has been checked and edited on the terminal device 700, in the question and answer storage unit 320.

[0028] In this embodiment, the large-scale language model 511 provided by the server device 500 is used to generate registered question data and registered answer data. Therefore, according to this embodiment, the administrator of the chat system 100 does not need to manually input the registered question data and registered answer data, thereby reducing the administrator's workload.

[0029] Furthermore, in this embodiment, a screen is displayed on the terminal device 700 that allows the administrator of the chat system 100 to confirm the content. Therefore, according to this embodiment, the administrator can confirm and edit the content of the question and answer information generated by the large-scale language model. In addition, according to this embodiment, appropriate question and answer information can be stored in the question and answer storage unit 320, and it is possible to suppress the output of incorrect output answer data in response to input question data entered by the user.

[0030] In the example shown in Figure 1, the information processing device 200, the first storage device 300, and the second storage device 400 are each represented as separate devices, but this is not limited to the example. The first storage device 300 and the second storage device 400 may be included in the information processing device 200.

[0031] Furthermore, in Figure 1, the information processing device 200 may be implemented by one or more information processing devices, or it may be implemented by multiple information processing devices.

[0032] Furthermore, the chat system 100 only needs to include the information processing device 200 and the terminal device 700; other devices do not need to be included in the chat system 100.

[0033] Next, an example of the hardware configuration of each device in the chat system 100 of this embodiment will be described.

[0034] In this embodiment, the information processing device 200, the first storage device 300, the second storage device 400, and the server device 500 are all general-purpose computers. Therefore, Figure 2 describes the hardware configuration of the information processing device 200 as an example.

[0035] In this embodiment, terminal devices 600 and 700 are smartphones, and Figure 3 illustrates the hardware configuration of terminal device 700 as an example.

[0036] Figure 2 shows an example of the hardware configuration of an information processing device. The information processing device 200 shown in Figure 2 is built by a computer (information processing device) and includes a CPU 201, ROM 202, RAM 203, HD 204, HDD (Hard Disk Drive) controller 205, display 206, external device connection I / F (Interface) 208, network I / F 209, bus line 210, keyboard 211, pointing device 212, DVD-RW (Digital Versatile Disk Rewritable) drive 214, and media I / F 216.

[0037] Of these, the CPU 201 controls the operation of the entire information processing unit 200. The ROM 202 stores programs used to drive the CPU 201, such as IPL. The RAM 203 is used as the work area for the CPU 501. The HD 204 stores various data such as programs. The HDD controller 205 controls the reading or writing of various data to the HD 204 according to the control of the CPU 501. The display 206 displays various information such as cursors, menus, windows, characters, or images. The external device connection I / F 208 is an interface for connecting various external devices. In this case, external devices include, for example, USB (Universal Serial Bus) memory and printers. The network I / F 209 is an interface for data communication using a communication network. The bus line 210 is an address bus, data bus, etc., for electrically connecting each component such as the CPU 201 shown in Figure 2.

[0038] The keyboard 211 is a type of input means equipped with multiple keys for inputting characters, numbers, and various instructions. The pointing device 212 is a type of input means for selecting and executing various instructions, selecting processing targets, and moving the cursor. The DVD-RW drive 214 controls the reading or writing of various data to the DVD-RW 213, which is an example of a removable recording medium. Note that it is not limited to DVD-RW, but may also be DVD-R, etc. The media I / F 216 controls the reading or writing (storage) of data to the recording medium 215, such as flash memory.

[0039] Figure 3 shows an example of the hardware configuration of a terminal device. The terminal device 700 in this embodiment includes a CPU 701, ROM 702, RAM 703, EEPROM 704, CMOS sensor 705, image sensor I / F 706, acceleration / direction sensor 707, media I / F 709, and GPS receiver 711.

[0040] Of these, the CPU 701 is an arithmetic processing unit that controls the operation of the entire terminal device 700. The ROM 702 stores programs used to drive the CPU 701, such as the CPU 701 and the IPL. The RAM 703 is used as the work area for the CPU 701. The EEPROM 704 reads or writes various data, such as smartphone programs, according to the control of the CPU 701. The ROM 702, RAM 703, and EEPROM 704 are examples of the storage devices of the terminal device 700.

[0041] The CMOS (Complementary Metal Oxide Semiconductor) sensor 705 is a type of built-in imaging device that captures an image of a subject (mainly a self-portrait) and obtains image data according to the control of the CPU 701. Note that an imaging device such as a CCD (Charge Coupled Device) sensor may also be used instead of a CMOS sensor.

[0042] The image sensor interface 706 is a circuit that controls the driving of the CMOS sensor 705. The acceleration / direction sensor 707 is a variety of sensors, such as an electronic magnetic compass, gyrocompass, and acceleration sensor that detect the Earth's magnetic field. The media interface 709 controls the reading or writing (storage) of data to or from the recording medium 708, such as flash memory. The GPS receiver 711 receives GPS signals from GPS satellites.

[0043] Furthermore, the terminal device 700 includes a long-range communication circuit 712, an antenna 712a for the long-range communication circuit 712, a CMOS sensor 713, an image sensor interface 714, a microphone 715, a speaker 716, an audio input / output interface 717, a display 718, an external device connection interface 719, a short-range communication circuit 720, an antenna 720a for the short-range communication circuit 720, and a touch panel 721.

[0044] Of these, the long-distance communication circuit 712 is a circuit that communicates with other devices via a communication network. The CMOS sensor 713 is a type of built-in imaging means that captures an image of a subject and obtains image data according to the control of the CPU 701. The image sensor interface 714 is a circuit that controls the driving of the CMOS sensor 713. The microphone 715 is a built-in circuit that converts sound into electrical signals. The speaker 716 is a built-in circuit that converts electrical signals into physical vibrations to produce sounds such as music and speech. The sound input / output interface 717 is a circuit that processes the input and output of sound signals between the microphone 715 and the speaker 716 according to the control of the CPU 701.

[0045] The display 718 is a type of display means, such as a liquid crystal or organic EL (Electro-Luminescence), that displays images of the subject and various icons. The external device connection I / F 719 is an interface for connecting various external devices. The short-range communication circuit 720 is a communication circuit such as NFC (Near Field Communication) or Bluetooth (registered trademark). The touch panel 721 is a type of input means that allows the user to operate the terminal device 700 by pressing the display 718. The display 718 is an example of a display unit of the terminal device 700.

[0046] Note that the hardware configuration shown in Figure 3 is just one example of terminal device 700, and the hardware configuration of terminal device 700 is not limited to this. The hardware configuration of terminal device 700 may also be the configuration shown in Figure 2. Furthermore, the hardware configuration of terminal device 600 may be the same as that of terminal device 700, so its explanation is omitted.

[0047] Next, we will describe each memory unit with reference to Figures 4 to 7. Figure 4 shows an example of a conversation history memory unit.

[0048] The conversation history information stored in the conversation history storage unit 310 shown in Figure 4 includes information items such as conversation ID, date and time, tenant ID, question, and answer, with the values ​​of each item being associated with the information.

[0049] The value of the "Conversation ID" field is identification information used to identify the conversation. The value of the "Date and Time" field indicates the date and time when input question data was entered into terminal device 600 or the date and time when output response data was output to terminal device 600. The value of the "Tenant ID" field is identification information that identifies the tenant to which the user of terminal device 600 belongs.

[0050] The value of the item "Question" indicates the input question data entered into the terminal device 600 as the question text. The value of the item "Answer" indicates the output answer data output to the terminal device 600 as the answer text.

[0051] Thus, the conversation history information in this embodiment includes a conversation ID that identifies the conversation history information, a tenant ID of the tenant to which the user of the terminal device 600 belongs, the date and time when the input question data was entered or the date and time when the output answer data was output, the input question data, and the output answer data.

[0052] Note that the conversation history information shown in Figure 4 is just an example, and the conversation history information in this embodiment may include items other than those shown in Figure 4.

[0053] Figure 5 shows an example of a question and answer storage unit. The question and answer information stored in the question and answer storage unit 320 of this embodiment may be provided for each tenant and managed by each tenant. In the example in Figure 5, the question and answer information managed by the tenant identified by tenant ID "11" is shown.

[0054] The question and answer information includes the following information items: tenant ID, question and answer ID, update date and time, question, answer, contact information, link, etc., with the items "tenant ID" and "question and answer ID" being associated with the other items. In this embodiment, the question and answer information is information in which the value of the item "question and answer ID" is associated with the values ​​of the other items.

[0055] The value of the "Question / Answer ID" field indicates identification information that identifies the question and answer information. The value of the "Update Date and Time" field indicates the date and time the question and answer information was updated. The value of the "Question" field is the registered question data (text data), and the value of the "Answer" field is the registered answer data (text data). Note that the values ​​of the "Question" and "Answer" fields are pre-stored by the administrator of each tenant.

[0056] The value of the item "Contact Information" indicates the contact information that a user of terminal device 600 can use when making inquiries related to registered question data. The contact information may be, for example, an email address or a telephone number, and may be stored in the user information storage unit 420.

[0057] The value of the "Link" field indicates a link that shows information related to the registered question data and registered answer data.

[0058] Note that the items "Contact Information" and "Links" do not necessarily need to be stored in the question and answer storage unit 320; the question and answer storage unit 320 only needs to store the registered question data and the registered answer data.

[0059] Figure 6 shows an example of a document storage unit. In the document storage unit 410 of this embodiment, company information is stored for each tenant and may be managed on a tenant-by-tenant basis. Figure 6 shows an example of company information managed in a tenant identified by tenant ID "11".

[0060] In this embodiment, the document storage unit 410 divides the company information into predetermined units and stores each divided piece of information separately. In the following description, each divided piece of company information will be referred to as a chunk. In the document storage unit 410, the chunks may be stored in association with identification information that identifies the chunk.

[0061] In Figure 6, one page of internal company information in an internal document is considered a chunk, and the page number is used as identifying information to distinguish the chunk. Note that chunks are not limited to one page of internal company information; for example, they could be paragraphs or chapters within an internal document.

[0062] Figure 7 shows an example of a user information storage unit. The user information stored in the user information storage unit 420 of this embodiment may be managed separately for each tenant, as it contains company information for each tenant.

[0063] The user information in this embodiment includes the following information items: Tenant ID, User ID, Username, Email Address, etc. The value of the "Tenant ID" item is identification information that identifies the tenant to which the user identified by the User ID belongs. The value of the "User ID" item is identification information that identifies the user of terminal device 600. The "Username" item indicates the name of the user identified by the User ID, and the value of the "Email Address" item indicates the email address of the user identified by the User ID.

[0064] In this embodiment, the user information storage unit 420 is stored in the second storage device 400, but the second storage device 400 does not necessarily have to contain the user information storage unit 420; it is sufficient if only the document storage unit 410 is provided.

[0065] Next, with reference to Figure 8, the functional configuration of each device included in the chat system 100 of this embodiment will be described. Figure 8 is a diagram illustrating the functions of each device in the chat system of the first embodiment.

[0066] First, the functional configuration of the information processing device 200 will be described. The information processing device 200 in this embodiment includes an input receiving unit 251, a storage control unit 252, a setting reference unit 253, an information acquisition unit 254, a prompt generation unit 255, a request unit 256, a list generation unit 257, an output unit 258, an editing unit 259, and a question answering unit 260.

[0067] The input receiving unit 251 receives various inputs to the information processing device 200. Specifically, the input receiving unit 251 receives various information inputs from the terminal device 700 and input question data from the terminal device 600. The various information inputs from the terminal device 700 include, for example, company information stored in the document storage unit 410, registered question data, information that identifies the company information used to generate registered answer data, and setting information set when generating registered question data and registered answer data.

[0068] The storage control unit 252 controls how the company information is stored in the document storage unit 410 of the second storage device 400. Specifically, the storage control unit 252 divides the company information received from the terminal device 700 into chunks and stores each chunk of company documents in the document storage unit 410.

[0069] Specifically, for example, if the internal company information is a document consisting of multiple pages, the storage control unit 252 divides the internal company information into chunks, treating each page as a chunk, associates each chunk with identification information that identifies the chunk, and stores them in the document storage unit 410.

[0070] The setting reference unit 253 refers to the setting information related to the generation of registered question data and registered answer data from the information received by the input reception unit 251 from the terminal device 700.

[0071] The information acquisition unit 254 acquires company information from the document storage unit 410. Specifically, when the input reception unit 251 receives input instructions to generate registered question data and registered answer data, the information acquisition unit 254 acquires the company information stored in the document storage unit 410 of the second storage device 400 in chunks.

[0072] The prompt generation unit 255 generates prompts to be output to the server device 500. For example, when the information acquisition unit 254 acquires company information in chunks, the prompt generation unit 255 generates prompts requesting the generation of registration question data and registration answer data using the acquired company information. Also, when the setting reference unit 253 references setting information, the prompt generation unit 255 generates prompts requesting the generation of registration question data and registration answer data according to the settings indicated in the setting information.

[0073] Furthermore, the prompt generated by the prompt generation unit 255 requests the server device 500 to output the generated registration question data and registration answer data as JSON format data.

[0074] The request unit 256 outputs the prompt generated by the prompt generation unit 255 to the server device 500. In other words, the request unit 256 makes a prompt-based request to the large-scale language model 511. In this embodiment, making a prompt-based request to the large-scale language model 511 may be expressed as sending the prompt generated by the prompt generation unit 255 to the server device 500.

[0075] The list generation unit 257 generates a list of registered question data and registered answer data pairs based on the output data output from the server device 500 to the information processing device 200. A pair of registered question data and registered answer data refers to registered question data and the registered answer data associated with this registered question data.

[0076] The output unit 258 outputs various types of information from the information processing device 200. Specifically, for example, the output unit 258 outputs to the terminal device 700 information showing a list of registered question data and registered answer data pairs generated by the list generation unit 257. The output unit 258 also outputs the registered question data and registered answer data to be stored in the question and answer storage unit 320 to the first storage device 300. Furthermore, the output unit 258 outputs, for example, company information stored in the document storage unit 410.

[0077] The editorial department 259 edits the question and answer information stored in the question and answer storage unit 320. More specifically, when the editorial department 259 receives an editing operation on registered question data or registered answer data from the terminal device 700, it reflects the editing operation in the question and answer information stored in the question and answer storage unit 320. In other words, the editorial department 259 overwrites the registered question data and registered answer data stored in the question and answer storage unit 320 in response to an editing operation by the administrator of the chat system 100.

[0078] The question answering unit 260 provides a chatbot system using the question answering information stored in the question answering storage unit 320.

[0079] Specifically, when the question answering unit 260 receives input question data from the terminal device 600, it outputs a search request to the first storage device 300 based on the input question data, causing the search unit 330 of the first storage device 300 to search the question answer storage unit 320 with the input question data. The question answering unit 260 also retrieves registered answer data, which is the search result from the question answer storage unit 320, from the first storage device 300. Furthermore, the question answering unit 260 uses its output unit 258 to output the registered answer data obtained from the first storage device 300 as output answer data to the terminal device 600.

[0080] Next, the functions of the first storage device 300 will be described. The first storage device 300 includes a conversation history storage unit 310, a question and answer storage unit 320, a search unit 330, and a storage unit 340. The search unit 330 searches the question and answer storage unit 320 in response to a search request from the information processing device 200 and transmits the search results to the information processing device 200.

[0081] The storage unit 340 stores the registered question data and registered answer data output from the information processing device 200 in the question and answer storage unit 320. Furthermore, when input question data is input and output answer data is output in the information processing device 200, the storage unit 340 stores conversation history information, including the input question data and output answer data, in the conversation history storage unit 310.

[0082] Next, the functions of the second storage device 400 will be described. The second storage device 400 includes a document storage unit 410, a user information storage unit 420, a search unit 430, and a storage unit 440. The search unit 430 searches the document storage unit 410 and the user information storage unit 420 in response to a search request from the information processing device 200, and transmits the search results to the information processing device 200. When an operation to upload company information is performed by the administrator of the chat system 100 or the like, the storage unit 440 stores the new company information in the document storage unit 410.

[0083] Next, the functions of the server device 500 will be described. The server device 500 has a large-scale language model storage unit 510, an input unit 520, and an output unit 530. The large-scale language model storage unit 510 stores a large-scale language model 511 that realizes generative AI.

[0084] The large-scale language model 511 of this embodiment is a computer language model that is generated by performing a training process using a vast amount of unlabeled text as training data and consists of an artificial neural network with many parameters. The large-scale language model 511 can capture much of the syntax and meaning of human language by being sufficiently trained with context-learning techniques such as next sentence prediction, which understands the context by determining whether sentence 1 and sentence 2 are consecutive, and a masked language model, which understands the context by masking words in a sentence and predicting the masked words from the words before and after them.

[0085] The input unit 520 inputs prompts sent from the information processing device 200 to the large-scale language model 511. The output unit 530 outputs (sends) the output data output from the large-scale language model 511 to the information processing device 200. In other words, the output unit 530 sends the output response data output from the large-scale language model 511 to the information processing device 200.

[0086] Next, the functions of terminal devices 600 and 700 will be described. Each of the terminal devices 600 and 700 includes a communication control unit 630, 730, an input receiving unit 640, 740, and a display control unit 650, 750.

[0087] Communication control units 630 and 730 control communication between terminal devices 600 and 700, respectively, and the information processing device 200. Input receiving units 640 and 740 receive input to terminal devices 600 and 700. Display control units 650 and 750 control the display on terminal devices 600 and 700.

[0088] Next, the operation of the chat system 100 of this embodiment will be described with reference to Figure 9. Figure 9 is a first sequence diagram illustrating the operation of the chat system of the first embodiment.

[0089] The operations shown in Figures 9 and 10 are those performed when the administrator of the chat system 100 is logged into the chat system 100 using their own user ID and tenant ID. In other words, the operations shown in Figures 9 and 10 are those performed when the administrator of the chat system 100 has access to the document storage unit 410 and the question and answer storage unit 320 associated with their tenant ID.

[0090] Furthermore, in Figure 9, steps S901 to S906 show the operation of storing the company information specified by the terminal device 700 in the document storage unit 410 of the second storage device 400. Also in Figure 9, steps S907 to S920 show the operation of generating registered question data and registered answer data, and displaying the generated results on the terminal device 700.

[0091] In this embodiment, the operations from step S901 to step S906 and the operations from step S907 to step S920 may be performed at separate and independent timings.

[0092] In the chat system 100, the terminal device 700 displays a generation screen for generating registered question data and registered answer data (step S901). The generation screen may be displayed on the display 718 of the terminal device 700 in response to an operation by the chat system 100 administrator on the terminal device 700.

[0093] Next, the terminal device 700 receives input from the input receiving unit 740, which is used to generate registered question data and registered answer data, as well as setting information (step S902). The information input here includes company information stored in the document storage unit 410, and setting information related to the generation of registered question data and registered answer data.

[0094] Next, the terminal device 700 transmits the input information to the information processing device 200 via the communication control unit 730 (step S903). The information transmitted to the information processing device 200 here includes company information stored in the document storage unit 410 and setting information related to the generation of registered question data and registered answer data.

[0095] When the information processing device 200 acquires information from the terminal device 700, the storage control unit 252 divides the company information contained in the information acquired from the terminal device 700 into chunks, and associates each chunk with identification information that identifies the chunk (step S904).

[0096] Next, the information processing device 200 outputs the company information, which has been divided into chunks, to the second storage device 400 via the output unit 258 (step S905).

[0097] When the second storage device 400 receives chunks of company information from the information processing device 200, the storage unit 440 stores the chunks of company information in the document storage unit 410, which is associated with the tenant ID of the tenant to which the administrator of the chat system 100 belongs (step S906).

[0098] Furthermore, when the terminal device 700 receives an operation from the input receiving unit 740 to instruct the generation of registered question data and registered answer data, the communication control unit 730 transmits the generation instruction for registered question data and registered answer data to the information processing device 200 (step S907). This generation instruction may include information that identifies the internal company information used when generating the registered question data and registered answer data. In other words, the generation instruction may include information that specifies the internal company information that will serve as the source of the registered question data and registered answer data.

[0099] When the information processing device 200 receives the input of this generation instruction via the input receiving unit 251, the information acquisition unit 254 sends a request to acquire chunks of internal company information that are used when generating the registered question data and registered answer data, from among the internal company information identified by the information identifying the internal company information included in the generation instruction (step S908). This acquisition request may include information identifying the internal company information used when generating the registered question data and registered answer data.

[0100] The second storage device 400 receives the acquisition request, identifies the internal company information to be transmitted to the information processing device 200 based on the information that identifies the internal company information contained in the acquisition request, and acquires the chunks contained in the identified internal company information (step S909). Subsequently, the second storage device 400 transmits the acquired chunks to the information processing device 200 (step S910).

[0101] When the information processing device 200 acquires a chunk, the prompt generation unit 255 generates a prompt requesting that a pair of registered question data and registered answer data be generated using the acquired chunk and output as data in JSON format (step S911).

[0102] JSON format data is a data format that allows the information processing device 200 to automatically read and link registered question data and registered answer data.

[0103] In other words, the prompt generation unit 255 of this embodiment generates a prompt requesting that the information processing device 200 output the result of generating a set of registered question data and registered answer data using the specified information in a format that can be read by the information processing device 200. Details of the prompts generated by the prompt generation unit 255 will be described later.

[0104] Next, the information processing device 200 outputs the prompt generated in step S911 to the server device 500 via the request unit 256 (step S912). In other words, the information processing device 200 makes a request to the large-scale language model 511 indicated by the prompt generated in step S911 via the request unit 256. The server device 500 inputs the prompt to the large-scale language model 511 via the input unit 520 and transmits the output data output from the large-scale language model 511 to the information processing device 200 via the output unit 530 (step S913).

[0105] The output data that the server device 500 outputs to the information processing device 200 in step S913 is JSON format data that includes pairs of registered question data and registered answer data using the chunks acquired by the information processing device 200 in step S909. Details of the output data output from the server device 500 will be described later.

[0106] In the chat system 100 of this embodiment, the operations from step S908 to step S913 are repeated until all chunks included in the company information identified in step S907 have been acquired.

[0107] Next, the information processing device 200, specifically the setting reference unit 253, refers to the setting information input from the terminal device 700 in step S903 (step S914).

[0108] If the number of sets of registered question data and registered answer data is not set in step S914, the information processing device 200 proceeds to step S918, which will be described later.

[0109] In step S914, if the number of sets of registered question data and registered answer data is set, the information processing device 200 generates a prompt using the prompt generation unit 255, requesting that the number of sets of registered question data and registered answer data be the set number (step S915). Subsequently, the information processing device 200 outputs the prompt generated in step S915 to the server device 500 using the request unit 256 (step S916).

[0110] The server device 500 inputs a prompt to the large-scale language model 511, and the output unit 530 transmits the output data output from the large-scale language model 511 to the information processing device 200. (Step S917).

[0111] In step S917, the output data sent from the server device 500 to the information processing device 200 is JSON format data containing a set number of pairs of registered question data and registered answer data according to the configuration information.

[0112] Next, the information processing device 200 generates a list of pairs of registered question data and registered answer data included in the output data acquired from the server device 500 in step S913 or step S917 using the list generation unit 257 (step S918).

[0113] Specifically, the list generation unit 257 reads the registered question data and registered answer data from the output data generated in JSON format, and stores the registered question data and registered answer data in variables to generate information that shows a list of pairs of registered question data and registered answer data.

[0114] In step S918, the set of registered question data and registered answer data may be temporarily stored in the question answer storage unit 320.

[0115] Next, the information processing device 200 outputs information showing the list generated in step S918 to the terminal device 700 via the output unit 258 (step S919).

[0116] The terminal device 700 displays a list screen on the display 718 that includes information showing the list acquired from the information processing device 200 in step S919 (step S920).

[0117] Next, referring to Figure 10, the operation of the chat system 100 after a list of registered question data and registered answer data pairs is displayed on the terminal device 700 will be explained.

[0118] Figure 14 is a second flowchart illustrating the operation of the chat system in the first embodiment.

[0119] In the terminal device 700, the input reception unit 740 accepts an operation to select a pair of registered question data and registered answer data to be reviewed from the list screen displayed on the display 718 (step S1001). Subsequently, the terminal device 700 transmits information indicating the selected pair to the information processing device 200 via the communication control unit 730 (step S1002).

[0120] The information processing device 200 retrieves registered question data and registered answer data included in a selected pair from the pairs of registered question data and registered answer data temporarily stored in the question answer storage unit 320 by the editing unit 259 (step S1003). Subsequently, the information processing device 200 sends an instruction to the terminal device 700 to display the editing screen for the retrieved registered question data and registered answer data by the editing unit 259 (step S1004).

[0121] The terminal device 700, via the display control unit 750, displays an editing screen for the set of registered question data and registered answer data selected in step S1001 (step S1005). Subsequently, if an editing operation is input by the input reception unit 740, the terminal device 700 performs editing according to this operation (step S1006).

[0122] Next, the terminal device 700 receives a registration instruction for a pair of registration question data and registration answer data (step S1007) and sends the registration request to the information processing device 200 (step S1008). This registration request includes a pair of registration question data and registration answer data that has been verified by the administrator of the chat system 100.

[0123] The registered question data and registered answer data after the content has been reviewed by the administrator of chat system 100 include the edited registered question data and registered answer data after editing operations have been performed on the editing screen, and the registered question data and registered answer data after only content review without any editing.

[0124] When the information processing device 200 receives a registration request from the input receiving unit 251, the editing unit 259 verifies the content and outputs the set of registration question data and registration answer data to the first storage device 300 (step S1009).

[0125] When the first storage device 300 obtains a set of registered question data and registered answer data from the information processing device 200, it assigns a question-answer ID to it and stores the set of registered question data and registered answer data in the question-answer storage unit 320 as question-answer information, associating the set with the update date and time of the registered question data and registered answer data (step S1010).

[0126] The process of assigning a question-answer ID and associating the question-answer ID with the update date and time for each pair of registered question data and registered answer data to create question-answer information may be performed in the information processing device 200.

[0127] The following describes prompts generated by the information processing device 200 and examples of their display on the terminal device 700, with reference to Figures 11 to 14.

[0128] Figure 11 is the first diagram showing an example of the display of the terminal device according to the first embodiment. The screen 110 shown in Figure 11 is an example of a generated screen that is displayed on the terminal device 700 in step S901 of Figure 9.

[0129] Screen 110 includes an input area 111, a display area 112, and operation buttons 113. The input area 111 includes input fields 114 and 115 for entering settings related to the generation of registered question data and registered answer data.

[0130] Input fields 114 and 115 are for entering the number of sets of registered question data and registered answer data. Specifically, input field 114 is for entering the number of sets of registered question data and registered answer data, and input field 115 is for entering a statement that there is no limit to the number of sets of registered answer data and registered answer data.

[0131] The display area 112 displays information 112a that identifies company information to be stored in the document storage unit 410. The display area 112 also includes operation buttons 116.

[0132] In this embodiment, after the information 112a identifying the company information is displayed in the display area 112, when the operation button 116 is operated, the company information identified by the information 112a identifying the company information is transmitted (uploaded) to the information processing device 200. The information 112a identifying the company information may be, for example, the file name of the company information.

[0133] Operation button 113 is an operation button used to instruct the generation of pairs of registered question data and registered answer data.

[0134] After configuration information is entered and company information is uploaded, when the operation button 113 is pressed, the terminal device 700 sends an instruction to the information processing device 200 to generate a set of registered question data and registered answer data using the uploaded company information, according to the configuration information.

[0135] In this embodiment, the information processing device 200 displays both the setting information and the information that identifies the internal company information used to generate the registered question data and registered answer data, thereby allowing the number of sets of registered question data and registered answer data to be generated for each piece of internal company information to be set.

[0136] Furthermore, in this embodiment, when storing company information in the document storage unit 410, a pair of registered question data and registered answer data can be generated using this company information and stored in the question and answer storage unit 320.

[0137] Furthermore, according to this embodiment, the administrator of the chat system 100 can generate a set of registered question data and registered answer data using this internal company information as the source, and store it in the question and answer storage unit 320, simply by inputting configuration information and selecting the internal company information to upload.

[0138] Therefore, according to this embodiment, the workload of the administrator of the chat system 100 can be reduced.

[0139] In the example in Figure 11, the information referenced when generating the set of registered question data and registered answer data is the internal company information identified by the internal company information identified by information 112a, but this is not limited to this.

[0140] The information referenced when generating pairs of registered question data and registered answer data is not limited to internal company information; it does not have to be internal company information. In other words, the information referenced when generating pairs of registered question data and registered answer data may be information other than user-specific information.

[0141] Furthermore, in the example in Figure 11, the information 112a identifying the internal company information is the file name of the internal company information, but it is not limited to this. The information 112a identifying the internal company information may also be, for example, a link indicating the location where the internal company information is stored.

[0142] In this embodiment, when the operation button 113 on the screen 110 is operated, the information processing device 200 retrieves the company information stored in the document storage unit 410 in chunks, and the prompt generation unit 255 generates a prompt requesting the generation of a set of registered question data and registered answer data.

[0143] The prompts requesting the generation of sets of registered question data and registered answer data are described below with reference to Figure 12. Figure 12 is the first diagram illustrating the prompts of the first embodiment.

[0144] The prompt 12 shown in Figure 12 is a prompt generated by the prompt generation unit 255 in step S911 of Figure 9. In other words, the prompt 12 shown in Figure 12 is a prompt that requests the output of a set of registration question data and registration answer data using the chunks contained in the company information identified on screen 110, as data in JSON format.

[0145] Prompt 12 includes text data 12a, 12b, and 12c. Text data 12a is text data indicating to the large language model 511 that the role of the large language model 511 is to generate registration question data and registration answer data, and that it generates pairs of registration question data and registration answer data and outputs them as data in JSON format.

[0146] Text data 12b is a source of information used to generate a set of registration question data and registration answer data. Here, the source of information is a single chunk contained in the company information identified on screen 110. In this embodiment, by making the source of information included in the prompt a chunk of identified company information, it is possible to request the generation of registration question data and registration answer data while satisfying the token limitations in the large language model 511.

[0147] Text data 12c is text data that indicates the format of the output data when the large-scale language model 511 outputs data in response to a prompt. Specifically, text data 12c indicates that the format of the output data when the large-scale language model 511 outputs a set of registered question data and registered answer data is in JSON format.

[0148] In this embodiment, by having the large-scale language model 511 output pairs of registered question data and registered answer data in JSON format, the information processing device 200 can automatically recognize the pairs of registered question data and registered answer data included in the output data output from the large-scale language model 511. Therefore, in this embodiment, the information processing device 200 can generate a list of pairs of registered question data and registered answer data from the output data output from the large-scale language model 511, using chunks included in the identified company information as the information source.

[0149] Figure 13 is a second diagram illustrating the prompt of the first embodiment. The prompt 13 shown in Figure 13 is a prompt generated by the prompt generation unit 255 in step S915 of Figure 9. In other words, the prompt 13 shown in Figure 13 is a prompt that requests the number of sets of registered question data and registered answer data to be the number corresponding to the setting information entered on screen 110.

[0150] The prompt 13 shown in Figure 13 includes text data 13a and 13b. Text data 13a is text data indicating to the large language model 511 that its role is to generate registration question data and registration answer data, and that it selects a set number of sets from the already generated sets of registration question data and registration answer data. Text data 13b includes sets of registration question data and registration answer data that have already been generated.

[0151] In this embodiment, the information processing device 200 outputs such prompts to the large-scale language model 511, thereby obtaining a set number of registered question data and registered answer data pairs from the chunks contained in the identified company information.

[0152] The selection of registered question data and registered answer data pairs may be randomly determined by the large-scale language model 511, or they may be selected according to conditions set by the administrator of the chat system 100.

[0153] Specifically, for example, in this embodiment, the administrator of the chat system 100 may set categories or themes that should be selected preferentially. This setting may be done, for example, on screen 110, and the set content may be included as part of the configuration information.

[0154] Next, with reference to Figure 14, an example of displaying a list of registered question data and registered answer data pairs corresponding to the output data output from the large-scale language model 511 will be described. Figure 14 is a second diagram showing an example of the display of the terminal device in the first embodiment.

[0155] The screen 140 shown in Figure 14 is an example of a list screen displayed on the terminal device 700 in step S920 of Figure 9.

[0156] Screen 140 includes display area 141. In the example in Figure 13, display area 141 displays a list of registered question data. Specifically, display area 141 is divided into display areas 141a, 141b, ..., where the registered question data generated by the large-scale language model 511 is displayed. 141n is included.

[0157] In this embodiment, when a display area showing registered question data is selected, screen 140 transitions to screen 150 (see Figure 15), which shows the selected registered question data and the registered answer data for this registered question data.

[0158] In the example shown in Figure 14, a list of registered question data is displayed in the display area 141, but this is not limited to that. A list of pairs of registered question data and registered answer data may also be displayed in the display area 141.

[0159] In the following explanation, we will assume that on screen 140, display area 141a, which displays the registered question data "I want to know the rules for claiming travel expenses," is selected.

[0160] Figure 15 is a third diagram showing an example of the display of the terminal device according to the first embodiment. The screen 150 shown in Figure 15 is an example of an editing screen displayed on the terminal device 700 in step S1005 of Figure 10.

[0161] The screen 150 shown in Figure 15 includes display areas 151 and 152, and operation buttons 153 and 154. Display area 151 displays the registered question data selected on screen 140, which is a list screen. Specifically, display area 151 displays the registered question data displayed in display area 141a of screen 140.

[0162] Display area 152 displays the registered question data and the corresponding registered answer data displayed in display area 151. Operation button 153 is an operation button for ending the display of screen 150. Operation button 154 is an operation button for storing the question and answer information, including the registered question data and registered answer data displayed in display areas 151 and 152, into the question and answer storage unit 320.

[0163] In this embodiment, by displaying the registered question data and registered answer data generated by the large-scale language model 511 in association with each other, the user of the terminal device 700 (the administrator of the chat system 100) can be made to confirm the contents of the registered question data and registered answer data.

[0164] Furthermore, in the display area 152 of this embodiment, it is possible to edit (correct) the registered question data displayed in the display area 151 and the registered answer data displayed in the display area 152.

[0165] The registered question data and registered answer data displayed in display areas 151 and 152, respectively, are text data. In this embodiment, the user of the terminal device 700 can modify the content and expression of the registered question data and registered answer data generated by the large-scale language model 511 by editing the registered question data and registered answer data displayed in display areas 151 and 152, respectively.

[0166] Furthermore, in this embodiment, the registered response data may include information other than the answers to the registered question data.

[0167] Specifically, for example, the registered response data may include, in addition to the answer corresponding to the registered question data, information indicating contact details for the user of the terminal device 600 if they wish to make further inquiries. Furthermore, the registered response data of this embodiment may include, in addition to the answer corresponding to the registered question data, links for displaying information related to the content indicated by the registered question data and registered response data.

[0168] In the example shown in Figure 15, the display area 152 shows contact information 152a and a link 152b. In this embodiment, the contact information 152a and the link 152b may be included in the output data output from the large-scale language model 511, or they may be input by the user of the terminal device 700 during editing operations.

[0169] In this embodiment, when the operation button 154 is operated on the screen 150, the registered question data displayed in the display area 151 and the registered answer data displayed in the display area 152 are linked and stored in the question answer storage unit 320 via the information processing device 200.

[0170] In this embodiment, when registered question data is selected on screen 140, which is a list screen, screen 140 transitions to screen 150, but this is not limited to this. Screen 150 may be displayed on screen 140, for example, in a pop-up format when registered question data is selected on screen 140.

[0171] Thus, in this embodiment, the contents of the registered question data and registered answer data generated by the large-scale language model 511 can be confirmed by the administrator of the chat system 100, and further edits can be accepted.

[0172] Therefore, according to this embodiment, it is possible to suppress the storage of inappropriate question and answer information in the question and answer storage unit 320, and to improve the accuracy of the output answer data output in response to the input question data.

[0173] Next, we will explain the case where input question data is entered from the terminal device 600.

[0174] In this embodiment, when input question data is received from the terminal device 600, the information processing device 200, via the question answering unit 260, makes a search request to the first storage device 300 and obtains the result of searching the question answer storage unit 320 from the first storage device 300. The information processing device 200 then outputs the registered question data obtained as the search result of the question answer storage unit 320 to the terminal device 600 as output answer data.

[0175] The following describes examples of displays for the terminal device 600 with reference to Figures 16 to 18. Figure 16 is the fourth figure showing an example of a display for the terminal device of the first embodiment.

[0176] The screen 161A shown in Figure 16 is an example of a screen displayed on the terminal device 600. Screen 161A includes display areas 161a, 161b, and 161d. Display area 161a displays the input question data entered by the user of the terminal device 600. Display area 161b displays the output answer data output from the information processing device 200 to the terminal device 600.

[0177] The output response data displayed here is registered response data associated with registered question data identified as a result of searching the question response storage unit 320 with the input question data.

[0178] Display area 161b includes text data 161b-1 and link 161b-2. Text data 161b-1 includes information indicating contact details for users of terminal device 600 to make further inquiries.

[0179] In this embodiment, the information indicating contact details may be, for example, an email address or a telephone number, and may be stored in the question answer storage unit 320 in association with the registered answer data.

[0180] In this case, when the information processing device 200 transmits output response data to the terminal device 600, it may obtain an email address associated with the registered question data identified as a result of searching the question answer storage unit 320 with the input question data, and transmit it to the terminal device 600 as part of the text data 161b-1.

[0181] Link 161b-2 is a link that displays information related to the content of the input question data and output response data.

[0182] Display area 161d displays a message notifying that the link 161b-2 displayed in display area 161b has been sent to the email address of the user of the terminal device 600.

[0183] In this case, when the information processing device 200 receives input question data from the terminal device 600, it may also receive the tenant ID and user ID of the tenant to which the user of the terminal device 600 belongs, along with the input question data. The information processing device 200 may refer to the user information storage unit 420 and obtain an email address identified from the tenant ID and user ID received along with the input question data. Then, when the information processing device 200 sends output answer data to the terminal device 600, it may send link 161b-2 along with the output answer data to the identified email address, and then display the display area 161d on the terminal device 600.

[0184] In this embodiment, by notifying the user of the terminal device 600 of contact information for further inquiries, as well as information related to the questions and answers, as output response data, it is possible to provide the user with a highly satisfactory response.

[0185] Furthermore, the information processing device 200 of this embodiment may send a notification to the contact information included in the text data 161b-1 indicating that an inquiry has been received from a user of the terminal device 600. By sending such a notification, the user who is the contact information for the inquiry can be prompted to prepare to respond to further inquiries.

[0186] Furthermore, in the example shown in Figure 16, by sending link 161b-2 to the user's email address, the user can access information related to their inquiry even after they have finished using the chat system 100.

[0187] Furthermore, in this embodiment, conversation history information, which associates input question data received from the terminal device 600 with output answer data output in response to this input question data, may be stored in the document storage unit 410.

[0188] In this embodiment, by accumulating conversation history information in the conversation history storage unit 310, the history of past questions and answers can be utilized.

[0189] Figure 17 is the fifth figure showing an example of the display of the terminal device according to the first embodiment. Screen 171B shown in Figure 17 is another example of a screen displayed on the terminal device 600.

[0190] Screen 161B includes display areas 161a and 161e. Display area 161e includes text data 161b-1 indicating contact information for users of terminal device 600 to make further inquiries, and a message 161f.

[0191] Message 161f indicates that a link to display information related to the user's inquiry has been sent to the user's email address.

[0192] As shown in the example in Figure 17, a link to display information related to the user's inquiry can be provided to the user separately from the output response data.

[0193] Figure 18 is the sixth figure showing an example of the display of the terminal device according to the first embodiment. The screen 161C shown in Figure 18 is an example of a screen displayed on the terminal device 600 when the user's email address is not stored in the user information storage unit 420 of the second storage device 400.

[0194] Screen 161C includes display areas 161a, 161b, 161g, 161h, and 161i. Display area 161g displays a message inquiring about the recipient of link 161b-2. Display area 121h displays the email address entered by the user. Display area 121i displays a message notifying the user that link 121b-2 has been sent to the email address entered by the user.

[0195] In the example shown in Figure 18, even if the user's email address is not stored in the user information storage unit 420, the link 121b-2 can be sent to the user if the user so desires.

[0196] In the chat system 100 of this embodiment, when question and answer information is stored in the question and answer storage unit 320 through the operations shown in Figures 9 and 10, the newly stored question and answer information may be used as training data to train the large-scale language model 511. By doing so, the accuracy of the large-scale language model 511 can be improved.

[0197] (Second Embodiment) A second embodiment will be described below with reference to the drawings. The second embodiment differs from the first embodiment in that the administrator of the chat system 100 inputs the registered question data. In the following description of the second embodiment, the differences from the first embodiment will be explained, and components having the same functional configuration as in the first embodiment will be given the same reference numerals as used in the first embodiment, and their explanations will be omitted.

[0198] Figure 19 is the first diagram showing an example of the display of a terminal device according to the second embodiment. Figure 19 is, for example, an example of a generated screen displayed on the terminal device 700 in step S901 of Figure 9.

[0199] The screen 110A shown in Figure 19 includes an input area 111, a display area 112, operation buttons 113a, and an input field 117.

[0200] Input field 117 is an input field for entering registered question data to be stored in the question and answer storage unit 320. The registered question data may be entered by the administrator of the chat system 100 (the user of the terminal device 700).

[0201] Operation button 113a is an operation button used to instruct the generation of a set of registered question data and registered answer data.

[0202] After the configuration information is entered and the company information is uploaded, when the operation button 113a is pressed, the terminal device 700 sends an instruction to the information processing device 200 to generate registered response data using the uploaded company information according to the configuration information.

[0203] The operation of the information processing device 200 in this embodiment will be described below. The operation of the information processing device 200 in this embodiment is the same as in Figure 9, except that the information that the information processing device 200 receives from the terminal device 700 in step S907 and the prompt generated in step S911 are different.

[0204] In this embodiment, the information processing device 200 receives from the terminal device 700 in step S907, which includes the setting information entered on the screen 110A of the terminal device 700, the registered question data, and the identified company information. This information is transmitted to the information processing device 200 when the operation button 113a on the screen 110A of the terminal device 700 is operated.

[0205] Furthermore, the prompt generated by the information processing device 200 of this embodiment in step S911 is a prompt that requests the large-scale language model 511 to generate registered answer data corresponding to the input registered question data.

[0206] The prompts generated by the information processing device 200 of this embodiment will be described below. Figure 20 is the first diagram illustrating the prompts of the second embodiment.

[0207] The prompt 20 shown in Figure 20 is a prompt that requests the output of registered answer data for the registered question data entered on screen 110A as JSON format data, using the chunks contained in the internal company information identified on screen 110A.

[0208] Prompt 20 includes text data 20a, 12b, and 20c. Text data 20a is text data indicating to the large language model 511 that its role is to generate registration question data and registration answer data, and that it generates registration question data for the input registration question data from the chunks included in prompt 20 and outputs it as data in JSON format.

[0209] Text data 20c indicates the format in which the large-scale language model 511 outputs data in response to prompts. Text data 20c may include registered question data entered in the input field 117 of screen 110A.

[0210] In this embodiment, by pre-specifying the internal company information that serves as the information source and the registered question data, the large-scale language model 511 can be made to generate registered answer data for the registered question data specified by the administrator of the chat system 100. Therefore, according to this embodiment, it is possible to prevent question and answer information with content unintended by the administrator of the chat system 100 from being stored in the question and answer storage unit 320.

[0211] Furthermore, according to this embodiment, since the large-scale language model 511 generates the registration question data, the administrator of the chat system 100 does not need to prepare the registration question data, thereby reducing the workload on the administrator of the chat system 100.

[0212] Furthermore, as in this embodiment, if registration question data is pre-entered on screen 110A, the editing screen displayed on the terminal device 700 in step S1005 of Figure 10 may be displayed in a state where the registration answer data can be edited, but editing of the registration question data is prohibited. In other words, in this embodiment, the editing screen displayed on the terminal device 700 may be a screen that allows editing of the registration answer data.

[0213] In this embodiment, a prompt may be output to the large-scale language model 511 requesting the generation of both the registered question data entered by the administrator of the chat system 100 and the corresponding registered answer data, as well as the pair of registered question data and registered answer data.

[0214] Furthermore, in this embodiment, instead of registered question data, the administrator of the chat system 100 may specify themes for registered question data and registered answer data that must be generated.

[0215] The following describes how the administrator of the chat system 100 specifies a theme, referring to Figure 21.

[0216] Figure 21 is a second diagram showing an example of the display of a terminal device according to the second embodiment. The screen 110B shown in Figure 21 includes an input area 111, a display area 112, operation buttons 113, and an input field 117A.

[0217] Input field 117A is where the theme for generating pairs of registered question data and registered answer data is entered.

[0218] In this embodiment, when the operation button 113 is operated on the screen 110B, the prompt generation unit 255 of the information processing device 200 generates a prompt requesting the generation of a set of registered question data and registered answer data, which includes the set of registered question data and registered answer data for the theme entered in the input field 117A.

[0219] Figure 22 is a second diagram illustrating the prompts of the second embodiment. The prompt 20A shown in Figure 22 is a prompt that requests the generation of registered question data and registered answer data, which include a pair of registered question data and registered answer data for the theme entered on screen 110B, using the chunks contained in the company information identified on screen 110B, and outputting them as data in JSON format.

[0220] Prompt 20A includes text data 22a, 12b, 22b, and 12c. Text data 22a is text data indicating to the large language model 511 that the role of the large language model 511 is to generate registration question data and registration answer data, and that it generates registration question data and registration answer data pairs containing the theme included in prompt 20A from the chunks included in prompt 20A, and outputs them as data in JSON format.

[0221] Text data 22b is text data that indicates the theme for which a set of registered question data and registered answer data is always generated. In other words, text data 22b is information that indicates the theme of the set of registered question data and registered answer data to be included in the output data.

[0222] In this embodiment, the administrator of the chat system 100 can specify a theme for the question and answer information to be stored in the question and answer storage unit 320, and cause the large-scale language model 511 to generate pairs of registered question data and registered answer data for the specified theme.

[0223] Therefore, according to this embodiment, the administrator of the chat system 100 can generate a set of registered question data and registered answer data, which includes registered question data and sets of registered question data related to the theme, simply by entering a theme on screen 110B.

[0224] (Third embodiment) A third embodiment will be described below with reference to the drawings. The third embodiment differs from the first embodiment in that the administrator of the chat system 100 notifies the large-scale language model 511 of the role of the chat system 100. In the following description of the third embodiment, the differences from the first embodiment will be explained, and components having the same functional configuration as in the first embodiment will be given the same reference numerals as used in the first embodiment, and their explanation will be omitted.

[0225] Figure 23 is the first diagram showing an example of the display of the terminal device according to the third embodiment. Figure 23 is, for example, an example of a generated screen displayed on the terminal device 700 in step S901 of Figure 9.

[0226] The screen 110C shown in Figure 23 includes an input area 111, a display area 112, operation buttons 113, and an input field 118.

[0227] Input field 118 is an input field for entering information indicating the role of the chat system 100. This information may be entered by the administrator of the chat system 100.

[0228] Specifically, the information indicating the role of the chat system 100 may include, for example, the type of organization to which the chat system 100 user belongs, or the circumstances under which the chat system 100 user enters a question into the chat system 100. In other words, the information indicating the role of the chat system 100 is information indicating the role of the service provided by the information processing device 200 using the question answer storage unit 320 in the input field 118.

[0229] In this embodiment, when the terminal device 700 identifies internal company information, inputs configuration information and information indicating the role of the chat system 100, and then the operation button 113 is operated, it sends an instruction to the information processing device 200 to generate a set of registered question data and registered answer data.

[0230] The operation of the information processing device 200 in this embodiment will be described below. The operation of the information processing device 200 in this embodiment is the same as in Figure 9, except that the information that the information processing device 200 receives from the terminal device 700 in step S907 and the prompt generated in step S911 are different.

[0231] In step S907, the information that the information processing device 200 of this embodiment receives from the terminal device 700 includes the setting information entered on the screen 110C of the terminal device 700, information indicating the role of the chat system 100, and identified company information. This information is transmitted to the information processing device 200 when the operation button 113 on the screen 110C of the terminal device 700 is operated.

[0232] Furthermore, the prompt generated by the information processing device 200 of this embodiment in step S911 includes information indicating the role of the chat system 100.

[0233] The prompts generated by the information processing device 200 of this embodiment are described below. Figure 24 is a diagram illustrating the prompts of the third embodiment.

[0234] The prompt 24 shown in Figure 24 is a prompt that requests the output of a set of registered question data and registered answer data corresponding to the role of the chat system 100 entered on screen 110C, using the chunks contained in the internal company information identified on screen 110C, as data in JSON format.

[0235] Prompt 24 includes text data 12a, 12b, 24a, and 12c. Text data 24a is text data indicating the role of the chat system 100. In other words, text data 24a includes text data entered in the input field 118 of screen 110C.

[0236] In the example in Figure 24, text data 24a indicates that the chat system 100 is installed on the company's internal portal site and is responsible for answering questions from employees.

[0237] In this embodiment, by including information indicating the role of the chat system 100 in the prompts input to the large-scale language model 511, the content of the registered question data and registered answer data generated in the large-scale language model 511 can be made suitable for the needs of the chat system 100 users. Therefore, according to this embodiment, the accuracy of the chat system 100 can be improved.

[0238] In this embodiment, the large-scale language model 511 may also be requested to output a category corresponding to a pair of registered question data and registered answer data, as well as a pattern obtained by paraphrasing the registered question data.

[0239] In other words, the information processing device 200 of this embodiment may include text data in the prompt output to the large-scale language model 511 that requests the output of a category corresponding to a set of registered question data and registered answer data, and a pattern that paraphrases the registered question data.

[0240] Figure 25 illustrates another prompt in the third embodiment. Prompt 25 shown in Figure 25 is the same as prompt 24 described in Figure 24, but with the addition of text data requesting the output of a pair of registered question data and registered answer data, a corresponding category, and a pattern that paraphrases the registered question data.

[0241] Prompt 25 includes text data 25a, 12b, 24a, and 12c. Text data 25a includes text data requesting the output of a set of registration question data and registration answer data, the corresponding category, and a pattern that paraphrases the registration question data. In other words, text data 25a includes text data requesting the output of a different pattern of the registration question data.

[0242] The large-scale language model 511 of the server device 500 outputs to the information processing device 200, in response to a prompt, a pair of registered question data and registered answer data, the category corresponding to this pair, and a pattern that paraphrases the registered question data. Based on the output data obtained from the server device 500, the information processing device 200 causes the terminal device 700 to display a list of registered question data and registered answer data. Furthermore, when a pair of registered question data and registered answer data is selected in the terminal device 700, the information processing device 200 displays an editing screen in the terminal device 700 that includes the pair of registered question data and registered answer data, the category, and a pattern that paraphrases the registered question data.

[0243] Figure 26 is a second diagram showing an example of the display of the terminal device according to the third embodiment. Screen 150A shown in Figure 26 is an example of an editing screen displayed on the terminal device 700 in step S1005 of Figure 10.

[0244] The screen 150A shown in Figure 26 includes display areas 151 and 152, operation buttons 153 and 154, and display areas 155 and 156.

[0245] Display area 155 displays the categories of the registered question data and registered answer data displayed in display areas 151 and 152, respectively. In the example in Figure 26, since the registered question data and registered answer data displayed in display areas 151 and 152 are related to travel expense reimbursement, the category displayed in display area 155 is "Travel Expenses".

[0246] Display area 156 displays a pattern of registered question data that is a rephrasing of the registered question data displayed in display area 151, while the content of the question remains the same. In other words, display area 156 displays an alternative pattern of registered question data. In the following explanation, the rephrased registered question data may be referred to as the modified registered question data.

[0247] Note that in the example in Figure 26, three modified registration question data are displayed, but the number of modified registration question data can be arbitrary and does not have to be three.

[0248] Thus, in this embodiment, the large-scale language model 511 generates categories for pairs of registered question data and registered answer data, as well as patterns that paraphrase the registered question data. Therefore, in this embodiment, the administrator of the chat system 100 does not need to refer to the question and answer information to classify it into categories or manually input patterns that change the expression of the registered question data, and the load on the chat system 100 can be further reduced.

[0249] (Fourth embodiment) A fourth embodiment will be described below with reference to the drawings. The fourth embodiment differs from the first embodiment in that the information processing device 200 has a first storage device 300 and a second storage device 400. In the following description of the fourth embodiment, the differences from the first embodiment will be explained, and components having the same functional configuration as in the first embodiment will be given the same reference numerals as used in the first embodiment, and their explanation will be omitted.

[0250] Figure 27 shows an example of the system configuration of the chat system according to the fourth embodiment.

[0251] The chat system 100A of this embodiment includes an information processing device 200A and a terminal device 700, and the information processing device 200A communicates with a server device 500 via the Internet. The information processing device 200A and the terminal device 700 are connected via a network. However, the information processing device 200A and the terminal device 700 may be connected via a network other than the Internet. Furthermore, the chat system 100 of this embodiment may also include a server device 500.

[0252] In this embodiment, the information processing device 200A includes a question and answer storage unit 320 and a document storage unit 410. The question and answer storage unit 320 in this embodiment may store only question and answer information relating to the organization in which the chat system 100A has been introduced. The document storage unit 410 in this embodiment may store only internal company information of the organization in which the chat system 100A has been introduced.

[0253] When the information processing device 200A identifies the internal company information used in generating the set of registered question data and registered answer data in the terminal device 700, it stores the identified internal company information in chunks in the document storage unit 410.

[0254] Furthermore, when the information processing device 200A receives a command from the terminal device 700 to generate a set of registered question data and registered answer data, it generates a prompt that includes chunks contained in the company information and text data requesting that the set of registered question data and registered answer data referencing the chunks be output in JSON format. The information processing device 200A then outputs the generated prompt to the server device 500.

[0255] Furthermore, when the information processing device 200 acquires output data output by the large-scale language model 511 provided by the server device 500, it generates a list of pairs of registered question data and registered answer data based on the output data and displays it on the terminal device 700.

[0256] When the administrator of the chat system 100A confirms the contents of the registered question data and registered answer data in the terminal device 700, the information processing device 200A stores this set of registered question data and registered question data in the question and answer storage unit 320.

[0257] In this embodiment, by providing the information processing device 200A with a question and answer storage unit 320 and a document storage unit 410, the confidentiality between the question and answer information stored in the question and answer storage unit 320 and the company information stored in the document storage unit 410 can be enhanced.

[0258] Furthermore, in this embodiment, even if the chat system 100A, which includes the information processing device 200A and the terminal device 700, is built within a specific organization, the large-scale language model 511 can generate pairs of registered question data and registered answer data. Therefore, the workload of the administrator of the chat system 100A can be reduced.

[0259] Furthermore, each function of the embodiments described above can be realized by one or more processing circuits. Hereinafter, "processing circuit" in this specification includes processors programmed to execute each function by software, such as processors implemented by electronic circuits, as well as devices such as ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), FPGAs (field programmable gate arrays), and conventional circuit modules designed to execute each of the functions described above.

[0260] Furthermore, the apparatus described in each embodiment represents only one of several computing environments for carrying out the embodiments disclosed herein.

[0261] In one embodiment, the information processing device 200 includes a plurality of computing devices, such as a server cluster. The plurality of computing devices are configured to communicate with each other via any type of communication link, including a network or shared memory, and perform the processing disclosed herein. Similarly, the server device 500 and the information processing device 200 may include a plurality of computing devices configured to communicate with each other.

[0262] Furthermore, the information processing device 200 can be configured to share the disclosed processing steps in various combinations. For example, a process performed by a predetermined unit may be performed by the information processing device 200. Similarly, the functions of a predetermined unit may be performed by the information processing device 200. Also, each element of the information processing device 200 may be combined into a single server device or divided among multiple devices.

[0263] The information processing device 200 may be any device equipped with communication capabilities. For example, the information processing device 200 may be an output device such as a PJ (Projector), IWB (Interactive White Board: an electronic whiteboard with the ability to communicate with each other), or digital signage; a HUD (Head Up Display) device; industrial machinery; imaging devices; sound collection devices; medical equipment; networked home appliances; automobiles (Connected Cars); notebook PCs (Personal Computers); mobile phones; smartphones; tablet terminals; game consoles; PDAs (Personal Digital Assistants); digital cameras; wearable PCs; or desktop PCs.

[0264] Examples of the present invention are as follows: <1> An input receiving unit that accepts input of instructions for generating registered question data and registered answer data, A request unit requests a large-scale language model to generate registered answer data corresponding to the registered question data based on the generation instructions, An information processing device having an output unit that outputs registered response data output from the large-scale language model in response to the aforementioned request to a terminal device. <2> The aforementioned request section further states: The system requests the generation of registration question data based on the information specified in the generation instruction. The output unit is, The output data generated from the large-scale language model includes pairs of registered question data and registered answer data corresponding to the registered question data, which are output to the terminal device. <1> The information processing device described. <3> The claim includes an editing unit that includes registered response data contained in output data output from the large-scale language model, and displays an editing screen on the terminal device that accepts editing of the registered response data. <1> or <2> The information processing device described. <4> The aforementioned request unit is, If the number of pairs of registered question data and corresponding registered answer data included in the output data output from the large-scale language model is greater than a preset number, the large-scale language model is requested to set the number of pairs of registered question data and corresponding registered answer data to the preset number. <2> or <3> The information processing device described. <5> The aforementioned request unit is, The system includes a portion of the specified information and requests the generation of registration response data corresponding to registration question data based on the portion of the specified information. <1> ~ <4> An information processing device as described in any one of the following items. <6> The aforementioned request unit is, The output data is required to be output in JSON format. <1> ~ <5> An information processing device as described in any one of the following items. <7> The aforementioned request includes pre-entered registration question data, The request unit is the information processing apparatus according to <1>, which requests generation of registration response data corresponding to the input registration response data. <8> The request unit includes information indicating a theme of a set of the registration question data and registration response data corresponding to the registration question data, and requests to include, in the output data output from the large language model, a set of the registration question data along the theme and registration response data corresponding to the registration question data. The information processing apparatus according to any one of <1> to <7>. <9> The request includes information indicating a role of a service using a question-and-answer storage unit in which the registration question data and the registration response data are stored. The information processing apparatus according to any one of <1> to <8>. <10> The request unit requests an output of a category corresponding to a set of the registration question data and registration response data corresponding to the registration question data, and other registration question data having a different expression from the registration question data. The information processing apparatus according to any one of <1> to <9>. <11> An information processing system including an information processing apparatus and a terminal device that communicates with the information processing apparatus, where the information processing apparatus has an input reception unit that receives an input of a generation instruction for registration question data and registration response data, a request unit that requests a large language model to generate registration response data corresponding to the registration question data based on the generation instruction, and an output unit that outputs the registration response data output from the large language model in response to the request of the prompt to the terminal device. The terminal device has a display control unit that displays a screen including the registration question data and the registration response data. The information processing system. <12> An information processing method including an information processing apparatus and a terminal device that communicates with the information processing apparatus, The aforementioned information processing device The system accepts input for generating registered question data and registered answer data. The generation instruction requests the large-scale language model to generate registration response data corresponding to registration question data based on the information specified above. In response to the aforementioned request, the registration response data output from the large-scale language model is output to the terminal device. The aforementioned terminal device An information processing method for displaying a screen containing the registered question data and the registered answer data. <13> The question and answer storage unit receives input for instructions to generate registered question data and registered answer data, The large-scale language model is requested to generate registration response data corresponding to the registration question data based on the aforementioned generation instructions. A program that causes an information processing device to execute a process that outputs registered response data, output from the large-scale language model in response to the aforementioned request, to a terminal device.

[0265] Although the present invention has been described above based on various embodiments, the present invention is not limited to the requirements shown in the above embodiments. These points can be modified as long as they do not impair the spirit of the present invention, and can be appropriately determined according to their application. [Explanation of Symbols]

[0266] 100, 100A Chat System 200, 200A Information Processing Equipment 251 Input Reception Section 252 Storage Control Unit 253 Configuration Reference Section 254 Information Acquisition Department 255 Prompt generation unit 256 Request part 257 List Generation Unit 258 Output section 259 Editorial Department 260 Question and answer section 300 First memory device 310 Conversation history memory unit 320 Question and answer storage section 400 Second storage device 410 Document Storage Unit 420 User Information Storage Unit 500 Server Devices 511 Large-scale language models 600, 700 terminal devices [Prior art documents] [Patent Documents]

[0267] [Patent Document 1] Japanese Patent Publication No. 2023-181204

Claims

1. An input receiving unit that accepts input of instructions for generating registered question data and registered answer data, A request unit requests a large-scale language model to generate registered answer data corresponding to the registered question data based on the generation instructions, An information processing device having an output unit that outputs registered response data output from the large-scale language model in response to the aforementioned request to a terminal device.

2. The aforementioned request section further states: The generation of registration question data based on the information specified in the generation instruction is requested. The output unit is, The information processing apparatus according to claim 1, which outputs to the terminal device a pair of registered question data and registered answer data corresponding to the registered question data, which are included in the output data output from the large-scale language model.

3. The information processing apparatus according to claim 1 or 2, comprising an editing unit that includes registered response data contained in output data output from the large-scale language model, and that displays an editing screen on the terminal device for accepting edits to the registered response data.

4. The aforementioned request unit is, The information processing device according to claim 2, wherein if the number of pairs of registered question data and corresponding registered answer data included in the output data is greater than a preset number, the device requests the large-scale language model to set the number of pairs of registered question data and corresponding registered answer data to the preset number.

5. The aforementioned request unit is, The information processing device according to claim 2, which includes a portion of the specified information and requests the generation of registration response data corresponding to registration question data based on the portion of the specified information.

6. The aforementioned request unit is, The information processing apparatus according to claim 1 or 2, which requires outputting output data from the large-scale language model in JSON format.

7. The aforementioned request includes pre-entered registered question data, The information processing apparatus according to claim 1, wherein the request unit requests the generation of registered response data corresponding to the input registered response data.

8. The aforementioned request unit is, The information processing apparatus according to claim 2, which includes information indicating a theme for the set of registered question data and the registered answer data corresponding to the registered question data, and is a prompt requesting that the output data include the set of registered question data and the registered answer data corresponding to the registered question data in accordance with the theme.

9. The aforementioned requirement is, The information processing apparatus according to claim 1 or 2, which includes information indicating the role of a service using a question and answer storage unit that stores the registered question data and the registered answer data.

10. The aforementioned request unit is, The information processing apparatus according to claim 2, which requests the output of the registered question data, the category corresponding to the pair of the registered question data and the registered answer data that corresponds to the registered question data, and other registered question data in which the registered question data is expressed differently.

11. An information processing system including an information processing device and a terminal device that communicates with the information processing device, The aforementioned information processing device is An input receiving unit that accepts input of instructions for generating registered question data and registered answer data, A request unit requests a large-scale language model to generate registered answer data corresponding to the registered question data based on the generation instructions, The system includes an output unit that outputs registered response data output from the large-scale language model in response to the aforementioned request to the terminal device, The aforementioned terminal device is An information processing system having a display control unit that displays a screen including the registered question data and the registered answer data.

12. An information processing method comprising an information processing device and a terminal device that communicates with the information processing device, The aforementioned information processing device The system accepts input for generating registered question data and registered answer data. The large-scale language model is requested to generate registration response data corresponding to the registration question data based on the aforementioned generation instructions. In response to the aforementioned request, the registered response data output from the large-scale language model is output to the terminal device. The aforementioned terminal device An information processing method for displaying a screen containing the registered question data and the registered answer data.

13. The system accepts input for generating registered question data and registered answer data. The large-scale language model is requested to generate registration response data corresponding to the registration question data based on the aforementioned generation instructions. A program that causes an information processing device to execute a process that outputs registered response data, output from the large-scale language model in response to the aforementioned request, to a terminal device.

Images