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

Abstract

The aim is to provide answers based on user-specific information. [Means for solving the problem] An information processing device comprising: an input receiving unit that receives input of question data; a prompt output unit that, upon receiving the input of question data, outputs a prompt to a large-scale language model requesting the generation of answer data for the question data based on user-specific information; and an information output unit that outputs the answer data output from the large-scale language model based on the prompt output from the prompt output unit as output answer data to a terminal device.

Description

Technical Field

[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, large language models that are trained with a large amount of data using models having ten times or more the number of intermediate variables or parameters compared to conventional general language models are known. In this large language model, by inputting a prompt including a small amount of exemplary data formats, the pre-trained model understands the patterns in the prompt and generates and outputs words and sentences according to the input. Note that a prompt is an example of text data for expressing instructions or questions to a large language model.

Summary of the Invention

Problems to be Solved by the Invention

[0003] The above-described large language model performs learning based on information generally publicly available on the Internet or the like. For this reason, in the above-described large language model, it has been difficult to present answers based on information that is not generally publicly available, such as user-specific information of users who use the large language model.

[0004] The disclosed technology has been made in view of the above circumstances, and aims to present answers based on user-specific information.

Means for Solving the Problems

[0005] The disclosed technology is an information processing device comprising: an input receiving unit that receives input of question data; a prompt output unit that, upon receiving the input of the question data, outputs a prompt to a large-scale language model requesting the generation of answer data for the question data based on user-specific information; and an information output unit that outputs the answer data output from the large-scale language model based on the prompt output from the prompt output unit as output answer data to a terminal device. [Effects of the Invention]

[0006] It can provide answers based on user-specific information. [Brief explanation of the drawing]

[0007] [Figure 1] This figure shows an example of the system configuration of the chat system according to the first embodiment. [Figure 2] This figure shows an example of the hardware configuration of the information processing device according to the first embodiment. [Figure 3] This figure shows an example of the hardware configuration of the terminal device according to the first embodiment. [Figure 4] This figure shows an example of a conversation history storage unit according to the first embodiment. [Figure 5] This figure shows an example of a question-answer storage unit according to the first embodiment. [Figure 6] This figure shows an example of a document storage unit according to the first embodiment. [Figure 7] This figure shows an example of a user information storage unit according to the first embodiment. [Figure 8] This diagram illustrates the functions of each device in the chat system of the first embodiment. [Figure 9] This is a sequence diagram illustrating the operation of the chat system in the first embodiment. [Figure 10] The first figure shows an example of a prompt in the first embodiment. [Figure 11] The second figure shows an example of a prompt in the first embodiment. [Figure 12] It is the first figure showing a display example of the terminal device of the first embodiment. [Figure 13] It is the second figure showing a display example of the terminal device of the first embodiment. [Figure 14] It is the third figure showing a display example of the terminal device of the first embodiment. [Figure 15] It is the fourth figure showing a display example of the terminal device of the first embodiment. [Figure 16] It is a sequence diagram explaining the operation of the chat system of the second embodiment. [Figure 17] It is a figure showing an example of a prompt of the second embodiment. [Figure 18] It is a sequence diagram explaining the operation of the chat system of the third embodiment. [Figure 19] It is a figure showing a display example of the terminal device of the third embodiment. [Figure 20] It is a sequence diagram explaining the operation of the chat system of the fourth embodiment. [Figure 21] It is a figure showing a display example of the terminal device of the fourth embodiment. [Figure 22] It is a figure showing an example of a prompt in the fourth embodiment. [Figure 23] It is a sequence diagram explaining the operation of the chat system of the fifth embodiment. [Figure 24] It is the first figure showing a display example of the terminal device of the fifth embodiment. [Figure 25] It is the second figure showing a display example of the terminal device of the fifth embodiment. [Figure 26] It is the third figure showing a display example of the terminal device of the sixth embodiment. [Figure 27] It is a sequence diagram explaining the operation of the chat system of the sixth embodiment. [Figure 28] It is the first figure showing an example of a prompt of the sixth embodiment. [Figure 29] It is the second figure showing an example of a prompt of the sixth embodiment. [Figure 30]It is a third figure showing an example of a prompt of the sixth embodiment. [Figure 31] It is a figure for explaining the functions of each device of the chat system of the seventh embodiment. [Figure 32] It is a figure showing an example of a document storage unit of the seventh embodiment. This [Figure 33] It shows an example of a chunk storage unit of the seventh embodiment. [Figure 34] It is a figure showing an example of a scenario storage unit of the seventh embodiment. [Figure 35] It is a first sequence diagram for explaining the operation of the chat system of the seventh embodiment. [Figure 36] It is a second sequence diagram for explaining the operation of the chat system of the seventh embodiment. [Figure 37] It is a first figure showing an example of a display of a terminal device in the seventh embodiment. [Figure 38] It is a second figure showing an example of a display of a terminal device in the seventh embodiment. [Figure 39] It is a third figure showing an example of a display of a terminal device of the seventh embodiment. [Figure 40] It is a third sequence diagram for explaining the operation of the chat system of the seventh embodiment. [Figure 41] It is a fourth figure showing an example of a display of a terminal device of the seventh embodiment.

Embodiments for Carrying Out the Invention

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

[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 chatbot services to the users of the terminal device 600.

[0011] When the information processing device 200 receives a question from the terminal device 600, it outputs an 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. 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 installs the chat system 100.

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] The server device 500 has a large-scale language model storage unit 510 and implements generative AI (Artificial Intelligence). The generative AI generates text data in response to input prompts, such as ChatGPT (registered trademark), and outputs it to the information processing device 200. In this embodiment, the prompts are text data that express instructions or questions to the generative AI implemented by the server device 500. Details of the large-scale language model will be described later.

[0019] Terminal device 600 is primarily used by users of the chat system 100. Terminal device 700 is primarily used by administrators who manage the chat system 100. Terminal devices 600 and 700 may be, for example, smartphones or tablet devices.

[0020] In the chat system 100 of this embodiment, when a user inputs a question in the terminal device 600, the terminal device 600 transmits question data indicating the question to the information processing device 200.

[0021] When the information processing device 200 receives input question data, it retrieves conversation history information from the conversation history storage unit 310 of the first storage device 300 for a certain period prior to the input of the question to the terminal device 600. The information processing device 200 then outputs a prompt to the server device 500 requesting the generation of a query (search key) for searching the document storage unit 410 of the second storage device 400 using the input question and the retrieved conversation history information.

[0022] The server device 500 inputs a prompt to the large-scale language model stored in the large-scale language model storage unit 510, requesting the generation of a query, and transmits the output data output from the large-scale language model to the information processing device 200. The information processing device 200 uses the output data received from the server device 500 as a query to search the document storage unit 410 of the second storage device 400 and obtains the company information from the search results.

[0023] The information processing device 200 then outputs a prompt to the server device 500 requesting it to generate an answer to a question entered from the terminal device 600, using the company information obtained as search results as the information source.

[0024] The server device 500 inputs a prompt to the large-scale language model stored in the large-scale language model storage unit 510, requesting the generation of a response, and transmits the output data output from the large-scale language model to the information processing device 200. The information processing device 200 transmits the output data received from the server device 500 as response data to the terminal device 600.

[0025] The terminal device 600 displays the response data received from the information processing device 200 as the answer to the entered question.

[0026] In this embodiment, by doing so, it is possible to generate answers to questions from a large-scale language model based on user-specific information that is not publicly available. Therefore, according to this embodiment, it is possible to provide responses based on user-specific information.

[0027] Furthermore, in this embodiment, the information source used to generate the answer is internal company information obtained by searching the document storage unit 410 based on conversation history information before the question was entered. Therefore, according to this embodiment, the internal company information used as the information source can be narrowed down and sent to the server device 500, thereby improving the accuracy of the answer while satisfying the token limitations in the large-scale language model.

[0028] 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.

[0029] 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.

[0030] Furthermore, the chat system 100 only needs to include the information processing device 200 and the terminal device 600; other devices do not need to be included in the chat system 100.

[0031] Next, an example of the hardware configuration of each device in the chat system 100 of this embodiment will be described.

[0032] 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.

[0033] In this embodiment, terminal devices 600 and 700 are smartphones, and Figure 3 illustrates the hardware configuration of terminal device 600 as an example.

[0034] Figure 2 shows an example of the hardware configuration of an information processing device according to the first embodiment. The information processing device 200 shown in Figure 2 is built by a computer (information processing device) and includes, as shown in Figure 2, 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.

[0035] 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.

[0036] 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.

[0037] Figure 3 shows an example of the hardware configuration of the terminal device according to the first embodiment. The terminal device 600 of this embodiment includes a CPU 601, ROM 602, RAM 603, EEPROM 604, CMOS sensor 605, image sensor I / F 606, acceleration / direction sensor 607, media I / F 609, and GPS receiver 611.

[0038] Of these, the CPU 601 is an arithmetic processing unit that controls the operation of the entire terminal device 600. The ROM 602 stores programs used to drive the CPU 601, such as the CPU 601 and the IPL. The RAM 603 is used as the work area for the CPU 601. The EEPROM 604 reads or writes various data, such as smartphone programs, according to the control of the CPU 601. The ROM 602, RAM 603, and EEPROM 604 are examples of the storage devices of the terminal device 600.

[0039] The CMOS (Complementary Metal Oxide Semiconductor) sensor 605 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 601. Note that an imaging device such as a CCD (Charge Coupled Device) sensor may also be used instead of a CMOS sensor.

[0040] The image sensor interface 606 is a circuit that controls the driving of the CMOS sensor 605. The acceleration / direction sensor 607 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 609 controls the reading or writing (storage) of data to the recording medium 608, such as flash memory. The GPS receiver 611 receives GPS signals from GPS satellites.

[0041] Furthermore, the terminal device 600 includes a long-range communication circuit 612, an antenna 612a for the long-range communication circuit 612, a CMOS sensor 613, an image sensor interface 614, a microphone 615, a speaker 616, an audio input / output interface 617, a display 618, an external device connection interface 619, a short-range communication circuit 620, an antenna 620a for the short-range communication circuit 620, and a touch panel 621.

[0042] Of these, the long-distance communication circuit 612 is a circuit that communicates with other devices via a communication network. The CMOS sensor 613 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 601. The image sensor interface 614 is a circuit that controls the driving of the CMOS sensor 613. The microphone 615 is a built-in circuit that converts sound into electrical signals. The speaker 616 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 617 is a circuit that processes the input and output of sound signals between the microphone 615 and the speaker 616 according to the control of the CPU 601.

[0043] The display 618 is a type of display means, such as a liquid crystal or organic EL (electroluminescence), that displays images of the subject and various icons. The external device connection I / F 619 is an interface for connecting various external devices. The short-range communication circuit 620 is a communication circuit such as NFC (Near Field Communication) or Bluetooth (registered trademark). The touch panel 621 is a type of input means that allows the user to operate the terminal device 600 by pressing the display 618. The display 618 is an example of a display unit of the terminal device 600.

[0044] Note that the hardware configuration shown in Figure 3 is just one example of a terminal device 600, and the hardware configuration of the terminal device 600 is not limited to this. The hardware configuration of the terminal device 600 may also be the configuration shown in Figure 2.

[0045] Next, each memory unit will be described with reference to Figures 4 to 7. Figure 4 is a diagram showing an example of a conversation history memory unit of the first embodiment.

[0046] 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.

[0047] 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 the question was entered into terminal device 600 or the date and time when the answer 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.

[0048] The value of the item "Question" indicates the data (question data) entered into the terminal device 600 as the question text. The value of the item "Answer" indicates the data (answer data) output to the terminal device 600 as the answer text.

[0049] In the following description, the data output to the terminal device 600 as an answer will be referred to as output answer data. Therefore, the conversation history information in this embodiment includes a conversation ID that identifies the conversation history information, the tenant ID of the tenant to which the user of the terminal device 600 belongs, the date and time when the question data was entered or the date and time when the output answer data was output, the question data, and the output answer data.

[0050] 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.

[0051] Figure 5 shows an example of a question-answer storage unit in the first embodiment. The question-answer information stored in the question-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-answer information managed by the tenant identified by tenant ID "11" is shown.

[0052] The question and answer information includes the tenant ID, question and answer ID, update date and time, question, answer, etc., with the "tenant ID" and "question and answer ID" items associated with the other items. In this embodiment, the question and answer information is information in which the value of the "question and answer ID" item is associated with the values ​​of the other items.

[0053] 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 question data (text data) that represents the question, and the value of the "Answer" field is the answer data (text data) that represents the answer. Note that the values ​​of the "Question" and "Answer" fields are stored in advance by the administrator of each tenant.

[0054] In the following explanation, the question data stored in the question-answer storage unit 320 by the administrator of each tenant will be referred to as registered question data, and the answer data stored in the question-answer storage unit 320 by the administrator of each tenant will be referred to as registered answer data.

[0055] Figure 6 shows an example of a document storage unit in the first embodiment. In the document storage unit 410 of this embodiment, internal company information is stored for each tenant and may be managed on a tenant-by-tenant basis. Figure 6 shows an example of internal company information managed in a tenant identified by tenant ID "11".

[0056] 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.

[0057] 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.

[0058] Figure 7 shows an example of a user information storage unit in the first embodiment. The user information stored in the user information storage unit 420 of this embodiment may be managed separately for each tenant, and the internal company information may be stored separately for each tenant.

[0059] 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. The user information may also include information indicating the user's attributes. Information indicating the user's attributes may, for example, include information indicating the department to which the user belongs.

[0060] Furthermore, 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 have the user information storage unit 420; it is sufficient if only the document storage unit 410 is provided.

[0061] 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.

[0062] 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 search request unit 252, a conversation history acquisition unit 253, an information acquisition unit 254, a prompt generation unit 255, a prompt output unit 256, and an information output unit 257.

[0063] The input receiving unit 251 receives various inputs to the information processing device 200. Specifically, the input receiving unit 251 receives question data from the terminal device 600.

[0064] The search request unit 252 makes search requests to the first storage device 300 and the second storage device 400. Specifically, the search request unit 252 sends a search request to the first storage device 300 for the conversation history storage device 310, using the question data as the search key. The search request unit 252 also sends a search request to the second storage device 400 for the document storage device 410, based on a query generated by the server device 500.

[0065] The conversation history acquisition unit 253 acquires conversation history information, which is the search result of the conversation history storage unit 310 in response to a search request from the search request unit 252, from the first storage device 300.

[0066] The information acquisition unit 254 acquires company information, which is the search result of the document storage unit 410 in response to a search request from the search request unit 252, from the second storage device 400.

[0067] The prompt generation unit 255 generates a prompt to be output to the server device 500. For example, when information to be included in the prompt is obtained, the prompt generation unit 255 generates a prompt in a predetermined format that includes the obtained information.

[0068] The prompt output unit 256 outputs the prompt generated by the prompt generation unit 255 to the server device 500. The information output unit 257 outputs various types of information from the information processing device 200.

[0069] 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 conversation history storage unit 310 and 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. When question data is input and output answer data is output in the information processing device 200, the storage unit 340 stores the conversation history information, including the question data and output answer data, in the conversation history storage unit 310. 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 330 searches the conversation history storage unit 310 and 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. 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] Next, the operation of the chat system 100 of this embodiment will be described with reference to Figure 9. Figure 9 is a sequence diagram illustrating the operation of the chat system of the first embodiment.

[0076] In the chat system 100, when the terminal device 600 receives a question input via the input receiving unit 640, it transmits the question data to the information processing device 200 (step S901). The question data transmitted here may include the tenant ID of the tenant to which the user of the terminal device 600 belongs.

[0077] When the information processing device 200 receives the input of question data via the input receiving unit 251, the search request unit 252 sends a search request including the tenant ID to the first storage device 300 (step S902).

[0078] When the first storage device 300 receives this search request, the search unit 330 searches the conversation history storage unit 310 (step S903).

[0079] The processing of the search unit 330 will now be explained. The search unit 330 identifies conversation history information that includes the tenant ID included in the search request from the conversation history information stored in the conversation history storage unit 310, and obtains conversation history information related to the question and content indicated by the question data as a search result from the identified conversation history information.

[0080] Specifically, the search unit 330 identifies conversation history information including the tenant ID included in the search request, and from the identified conversation history information, it obtains conversation history information that continued up until immediately before the question data was entered in step S901.

[0081] The conversation history information that continued until just before the question data was entered in step S901 is conversation history information in which the time the question data was entered and the time the output response data was output immediately before this question data was entered are within a certain period of time. In this embodiment, if the next question data is entered within a certain period of time after the output response data has been output, the series of questions and answers are assumed to be responses concerning a common inquiry.

[0082] In this embodiment, by acquiring conversation history information in this way, it is possible to obtain conversation history information related to the question indicated by the question data and its content.

[0083] When the search unit 330 of the first storage device 300 searches the conversation history storage unit 310, it transmits the search result to the information processing device 200, and the information processing device 200 acquires the conversation history information using the conversation history acquisition unit 253 (step S904).

[0084] Here, if conversation history information is obtained from the first storage device 300 as a search result, the information processing device 200 performs the following steps S905 to S907.

[0085] In addition, conversation history information is acquired when, before the question data entered in step S901 is entered, question data related to the question indicated by the question data entered in step S901 is entered, and corresponding output answer data is output. In this case, conversation history information including this question data and output answer data is stored in the conversation history storage unit 310.

[0086] Furthermore, if conversation history information is not obtained from the first storage device 300 as a search result, the information processing device 200 proceeds to step S908. The case in which conversation history information is not obtained is when the question data entered in step S901 indicates the first question in the inquiry.

[0087] The information processing device 200 generates a prompt in the prompt generation unit 255 that requests the generation of a query for searching the document storage unit 410 (step S905). At this time, the prompt generation unit 255 includes the question data entered in step S901 and the conversation history information acquired by the conversation history acquisition unit 253, and generates a prompt that requests the generation of a query based on the question data and the conversation history information.

[0088] Next, the information processing device 200 sends a prompt to the server device 500 requesting the generation of a query via the prompt output unit 256 (step S906).

[0089] The server device 500 inputs a prompt to the large-scale language model 511 via the input unit 520, and sends the output data output from the large-scale language model 511 as a query to the information processing device 200 via the output unit 530 (step S907).

[0090] The information processing device 200, via the search request unit 252, sends a search request to the document storage unit 410 of the second storage device 400 for internal company information that can serve as a source of information when generating output answer data for question data (step S908).

[0091] Specifically, if the search request unit 252 has obtained a query in step S907, it sends a search request based on the query to the second storage device 400. If the search request unit 252 has not obtained a query, that is, if it has not obtained conversation history information in step S904, it sends a search request including the question data entered in step S901 to the second storage device 400.

[0092] When the second storage device 400 receives a search request, the search unit 430 searches the document storage unit 410 (step S909) and transmits the company information of the search results to the information processing device 200 (step S910).

[0093] When the information processing device 200 acquires internal company information from the search results using the information acquisition unit 254, the prompt generation unit 255 generates a prompt requesting the generation of an answer to the question data using the internal company information from the search results as the information source (step S911), and transmits it to the server device 500 (step S912).

[0094] When the server device 500 receives this prompt, the input unit 520 inputs the 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 as response output data to the information processing device 200 (step S913).

[0095] When the information processing device 200 acquires output response data, the information output unit 257 outputs the acquired output response data to the terminal device 600 (step S914). The terminal device 600 displays the output response data on the display 618 using the display control unit 650 (step S915). At this time, the display control unit 650 displays the output response data on the display 618 in association with the question data.

[0096] Furthermore, the information processing device 200, via its information output unit 257, sends a request to the first storage device 300 to save conversation history information, which includes the question data received in step S901 and the output response data output to the terminal device 600 in step S912 (step S916). Here, the request to save conversation history information includes the tenant ID of the tenant to which the user of the terminal device 600 belongs.

[0097] In the first storage device 300, the storage unit 340 stores new conversation history information in the conversation history storage unit 310 (step S917). Specifically, the storage unit 340 assigns a new conversation ID and date and time to the question data, output answer data, and tenant ID acquired from the information processing device 200, and stores them in the conversation history storage unit 310 as conversation history information. In this embodiment, the conversation history storage unit 310 is updated in this way.

[0098] Next, with reference to Figures 10 and 11, we will describe examples of prompts output from the information processing device 200 to the server device 500.

[0099] Figure 10 is the first figure showing an example of a prompt in the first embodiment. Prompt 10 is an example of a prompt requesting query generation, which is sent from the information processing device 200 to the server device 500 in step S905 of Figure 9.

[0100] In the example shown in Figure 10, the question data entered into the information processing device 200 in step S901 of Figure 9 is "Who should I contact?", and the conversation history information obtained in step S904 includes the question "How do I record my attendance?" and the answer "How do I record my attendance?".

[0101] Prompt 10 includes text data 10a, 10b, and 10c. Text data 10a is text data that indicates the content of the inquiry from the user of the terminal device 600 and the content of the request to generate a query for searching the document storage unit 410 based on the conversation history so far.

[0102] Furthermore, text data 10b indicates the content of the inquiry from the user of the terminal device 600. Specifically, text data 10b includes the question data "Who should I contact?" which was received by the information processing device 200 in step S901. Also, text data 10c indicates the question and answer included in the conversation history information acquired in step S904. Specifically, text data 10c includes the question "How do I record my attendance?" and the answer "How do I record my attendance?" which were included in the conversation history information acquired by the information processing device 200 in step S904.

[0103] In this embodiment, by inputting such a prompt 10 into the large-scale language model 511 of the server device 500, the server device 500 can generate a query for searching the second storage device 400 from the question indicated by the input question data and conversation history information including content related to the question indicated by the question data.

[0104] Furthermore, in this embodiment, by searching the document storage unit 410 of the second storage device 400 with such a query, the information source used when generating output answer data for question data can be internal company information that is highly likely to contain the answer to the question indicated by the question data. Therefore, according to this embodiment, the accuracy of the answer can be improved.

[0105] Figure 11 is a second figure showing an example of a prompt in the first embodiment. Prompt 11 is an example of a prompt that requests the generation of output response data, which is sent from the information processing device 200 to the server device 500 in step S910 of Figure 9.

[0106] Prompt 11 includes text data 11a, 11b, and 10b. Text data 11a is text data that requests the generation of output response data for the question indicated by the question data, based on the information source.

[0107] Text data 11b is the information source. The information source indicated by text data 11b is the company information obtained from the second storage device 400 in step S909 of Figure 9. In other words, the information source indicated by text data 11b is the company information obtained as a search result when the document storage unit 410 is searched using a query generated from the user inquiry content and conversation history information of the terminal device 600.

[0108] In this embodiment, by inputting a prompt 11 containing internal company information as a source of information into the large-scale language model 511 of the server device 500, a response based on tenant-specific information can be obtained from the large-scale language model 511.

[0109] Furthermore, according to this embodiment, internal company information that serves as a source of information is obtained by searching based on queries that include conversation history information. Therefore, according to this embodiment, it is possible to obtain answers to user inquiries from the large-scale language model 511 using internal company information that is highly likely to contain content related to the content of the user's inquiry as a source of information, thereby improving the accuracy of the answers.

[0110] Furthermore, in this embodiment, since a portion of the internal company information stored in the document storage unit 410 is extracted and included in the prompt, it is possible to obtain a response using internal company information as a source while satisfying the limit on the number of tokens that can be given to the large-scale language model 511 as a prompt.

[0111] Next, with reference to Figures 12 to 15, examples of displays for the terminal device 600 will be described. Figure 12 is the first diagram showing an example of a display for the terminal device of the first embodiment.

[0112] The screen 121 shown in Figure 12 is an example of a screen displayed on the terminal device 600 in step S913 of Figure 9.

[0113] Screen 121 includes display areas 121a and 121b. Display area 121a displays the question data entered by the user of the terminal device 600. Display area 121b displays the output response data from the chat system 100, as well as text data 121b-1 and a link 121b-2.

[0114] Text data 121b-1 includes information indicating contact details for users of terminal device 600 who wish to make further inquiries. This contact information may include, for example, an email address or telephone number. This contact information may be stored, for example, in the user information storage unit 420. Specifically, the user information storage unit 420 may store information indicating each user's assigned duties, etc., associated with the user ID.

[0115] When the information processing device 200 sends output response data to the terminal device 600, it may also obtain the email address of the user responsible for the task corresponding to the question indicated in the question data and send it to the terminal device 600 along with the output response data.

[0116] Link 121b-2 is a link that displays information related to the content shown in the question data and output response data.

[0117] In this embodiment, by notifying the user of the terminal device 600 of contact information for further inquiries, along with the questions and answers and related information, along with the output response data, it is possible to provide the user with a highly satisfactory response.

[0118] Furthermore, the information processing device 200 of this embodiment may send a notification to the contact information included in the text data 121b-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.

[0119] Figure 13 is a second diagram showing an example of the display of the terminal device according to the first embodiment. Screen 121A shown in Figure 13 is another example of a screen displayed on the terminal device 600 in step S913 of Figure 9.

[0120] Screen 121A includes display areas 121a, 121b, and 121d. Display area 121d displays a message notifying that the link 121b-2 displayed in display area 121b has been sent to the email address of the user of the terminal device 600.

[0121] In this case, the information processing device 200 may receive the user ID of the terminal device 600 along with the question data, and 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. Then, when the information processing device 200 sends the output response data to the terminal device 600, it may send the link 121b-2 along with the output response data to the identified email address, and then display the display area 121d on the terminal device 600.

[0122] In the example shown in Figure 13, by sending a link 121b-2 to the user's email address to display information related to the user's inquiry, the user can access information related to their inquiry even after they have finished using the chat system 100.

[0123] Figure 14 is a third diagram showing an example of the display of the terminal device according to the first embodiment. Screen 121B shown in Figure 14 is another example of a screen displayed on the terminal device 600 in step S913 of Figure 9.

[0124] Screen 121B includes display areas 121a and 121e. Display area 121e displays text data 121b-1 and message 121f. Message 121f is a message indicating that a link to display information related to the user's inquiry has been sent to the user's email address.

[0125] In the example shown in Figure 14, a link to display information related to the user's inquiry can be provided to the user separately from the output response data.

[0126] Figure 15 is the fourth figure showing an example of the display of the terminal device according to the first embodiment. The screen 121C shown in Figure 15 is another example of the screen displayed on the terminal device 600 in step S913 of Figure 9. Screen 121C may be displayed when the user's email address is not stored in the user information storage unit 420 of the second storage device 400.

[0127] Screen 121B includes display areas 121a, 121b, 121g, 121h, and 121i. Display area 121g displays a message inquiring about the recipient of link 121b-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.

[0128] In the example shown in Figure 15, 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.

[0129] (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 server device 500 is instructed to correct the output response data generated by the large-scale language model 511. 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 those used in the description of the first embodiment, and their explanations will be omitted.

[0130] Figure 16 is a sequence diagram illustrating the operation of the chat system in the second embodiment. The processes from step S1601 to step S1613 in Figure 16 are the same as the processes from step S901 to step S913 in Figure 9, so their explanation is omitted.

[0131] When the information processing device 200 obtains output response data from the server device 500, the prompt generation unit 255 generates a prompt requesting correction of the output response data (step S1614) and sends it to the server device 500 (step S1615). When the server device 500 receives the prompt requesting correction, the input unit 520 inputs the prompt to the large-scale language model 511, and the output unit 530 sends the output data output from the large-scale language model 511 to the information processing device 200 as correction result data (step S1616).

[0132] Furthermore, if the server device 500 finds that the output response data output in step S1613 is incorrect after correction, it may send the corrected output response data to the information processing device 200. Also, if the output response data output in step S1613 is correct, the server device 500 may send the corrected output response data output in step S1613 to the information processing device 200 once again.

[0133] Next, the information processing device 200 transmits the correction result data received from the server device 500 to the terminal device 600 as output answer data for the question data (step S1617).

[0134] The process from step S1617 to step S1620 is the same as the process from step S914 to step S917 in Figure 9, so the explanation is omitted.

[0135] Next, with reference to Figure 17, the prompt generated in step S1614 will be described. Figure 17 shows an example of a prompt in a second embodiment.

[0136] The prompt 17 shown in Figure 17 is a prompt requesting correction of the output response data output by the large-scale language model 511.

[0137] Prompt 17 includes text data 17a, 17b, 17c, and 17d. Text data 17a is text data indicating a request for correction of output response data output from the large-scale language model 511. Text data 17b indicates the content of the inquiry from the user of the terminal device 600. Specifically, text data 17b includes the question data "What plans are there?" which the information processing device 200 received as input in step S1601.

[0138] Furthermore, text data 17c includes output response data acquired by the information processing device 200 in step S1613 of Figure 16. Specifically, text data 17c includes the output response data acquired by the information processing device 200 in step S1613: "There are three plans below: 1. Started plan 2. Standard plan 3. Enterprise plan".

[0139] Furthermore, the text data 17d represents the internal company information that the information processing device 200 acquired in step S1610 of Figure 16.

[0140] In this embodiment, by having the large-scale language model 511 proofread the output response data it has output to check for errors, it is possible to suppress the output of incorrect answers to the user of the terminal device 600 and improve the accuracy of the answers.

[0141] (Third embodiment) A third embodiment will be described below with reference to the drawings. The third embodiment differs from the first embodiment in that it allows editing of company information stored in the document storage unit 410. 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 the first embodiment will be given the same reference numerals as those used in the description of the first embodiment, and their explanations will be omitted.

[0142] Figure 18 is a sequence diagram illustrating the operation of the chat system in the third embodiment. Figure 18 shows the operation of the chat system 100 when an internal information administrator or the like edits internal company information stored in the document storage unit 410.

[0143] In the chat system 100, terminal device 700 sends a request to information processing device 200 to display the management screen of the chat system 100 (step S1801). Information processing device 200 receives this display request and sends an instruction to terminal device 700 to display the management screen (step S1802).

[0144] The terminal device 700 displays the management screen via the display control unit 750 (step S1803). The management screen in this embodiment may include, for example, operation buttons that transition to screens for editing, adding (uploading), and deleting company information.

[0145] In step S1803 of Figure 18, it is assumed that an operation to edit internal company information was performed on the management screen.

[0146] When terminal device 700 receives an operation to edit internal company information, it sends a request to information processing device 200 to retrieve a list of internal company information for the tenant to which the user of terminal device 700 belongs (step S1804). This request to retrieve the list includes the tenant ID of the tenant to which the user of terminal device 700 belongs.

[0147] When the information processing device 200 receives a request to retrieve a list, the information retrieval unit 254 sends a request to the second storage device 400 to retrieve a list including the tenant ID (step S1805).

[0148] The second storage device 400 receives a request to retrieve a list, retrieves a list of company information stored in the document storage unit 410 that is associated with the tenant ID included in the request to retrieve a list (step S1806), and transmits it to the information processing device 200 (step S1807). Once the information processing device 200 has retrieved the list, it transmits a display instruction to the terminal device 700 (step S1808). In this embodiment, the list of company information may be a list of chunks stored in the document storage unit 410.

[0149] The terminal device 700 receives a display instruction and displays a list screen of company information (step S1809). Subsequently, when the terminal device 700 receives an operation to select the company information to be edited from the list screen (step S1810), it sends an edit request for the selected company information to the information processing device 200 (step S1811). The edit request may include identification information that identifies the selected company information (chunk).

[0150] When the information processing device 200 receives an editing request, it sends an instruction to the terminal device 700 to display the editing screen for the selected company information (step S1812).

[0151] The terminal device 700 receives a display instruction and displays the editing screen for the selected company information. (Step S1813), accept editing operation (Step S1814).

[0152] When the editing operation is complete, the terminal device 700 transmits the edited company information to the information processing device 200 (step S1815). When the information processing device 200 receives the edited company information, it transmits the edited company information to the second storage device 400 (step S1816).

[0153] The second storage device 400 stores the edited company information in the document storage unit 410 via the storage unit 440 (step S1817). More specifically, the storage unit 440 may overwrite the edited company information in the document storage unit 410 with the company information selected as the target of editing.

[0154] The editing screen displayed on the terminal device 700 is described below. Figure 19 shows an example of the display of the terminal device in the third embodiment.

[0155] The screen 191 shown in Figure 19 is an example of an editing screen displayed on the terminal device 700 in step S1813 of Figure 18.

[0156] Screen 191 includes a display area 191a and operation buttons 191b. The display area 191a may display the company information selected in step S1810 of Figure 18. The company information displayed in the display area 191a may be, for example, information obtained by converting company documents printed on paper into text data using OCR (Optical Character Recognition) processing or the like.

[0157] In this embodiment, the user of the terminal device 700 can edit the company information (text data) displayed in the display area 191a by manual input or other means.

[0158] Operation button 191b is used to send the text data displayed in the display area 191a to the information processing device 200 as edited company information.

[0159] In this embodiment, when the operation button 191b is operated, the terminal device 700 transmits the company information displayed in the display area 191a at the time the operation button 191b was operated to the information processing device 200 as edited company information.

[0160] In this embodiment, for example, even if the OCR processing fails to read or if there is a misrecognition, the administrator can correct it. Therefore, according to this embodiment, the internal company information that serves as the information source provided to the server device 500 can be made more accurate. Therefore, according to this embodiment, it is possible to suppress the output of incorrect output response data in response to question data.

[0161] (Fourth embodiment) A fourth embodiment will be described below with reference to the drawings. The fourth embodiment differs from the first embodiment in that it is possible to set information to be prioritized in the information source provided to the server device 500. 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 those used in the description of the first embodiment, and their explanations will be omitted.

[0162] Figure 20 is a sequence diagram illustrating the operation of the chat system according to the fourth embodiment. The processes from step S2001 to step S2003 in Figure 20 are the same as the processes from step S1801 to step S1803 in Figure 18, so their explanation is omitted.

[0163] In step S2003 of Figure 20, it is assumed that an operation to add company information was performed on the management screen.

[0164] The terminal device 700 receives an operation to select internal company information to be uploaded (step S2004), and when it receives an instruction to set priority information to be referenced preferentially for the selected internal company information (step S2005), it sends a request to the information processing device 200 to display the priority information setting screen (step S2006).

[0165] When the information processing device 200 receives a request to display the priority information setting screen, it sends a display instruction to the terminal device 700 (step S2007). The terminal device 700 receives the display instruction and displays the priority information setting screen (step S2008).

[0166] Next, the terminal device 700 accepts the operation to set priority information (step S2009), and once the setting is complete, it transmits the additional company information and priority information to the information processing device 200 (step S2010). At this time, the company information and priority information are assigned the tenant ID of the tenant to which the user of the terminal device 700 belongs.

[0167] When the information processing device 200 receives internal company information and priority information to which a tenant ID has been assigned, it transmits this to the second storage device 400 (step S2011).

[0168] When the second storage device 400 receives internal company information and priority information to which the tenant ID has been assigned, the storage unit 440 stores the internal company information and priority information to which the tenant ID has been assigned in the document storage unit 410.

[0169] The priority information setting screen will be described below with reference to Figure 21. Figure 21 is a diagram showing an example of the display of the terminal device in the fourth embodiment.

[0170] The screen 181 shown in Figure 21 is an example of a priority information setting screen displayed on the terminal device 700 in step S2009 of Figure 20.

[0171] Screen 181 includes an input field 181a and an operation button 181b. Input field 181a is an input field for entering priority information, and operation button 181b is an operation button for storing the priority information entered in input field 181a in association with internal company information.

[0172] In this embodiment, after the internal company information to be uploaded is selected, priority information is entered into the input field 181a on screen 181, and when the operation button 181b is operated, the entered priority information is associated with the selected internal company information and transmitted to the information processing device 200.

[0173] Next, referring to Figure 22, we will explain the prompt when priority information is associated with internal company information.

[0174] Figure 22 shows an example of a prompt in the fourth embodiment. The prompt 22 shown in Figure 22 is an example of a prompt requesting the generation of a response, which is sent from the information processing device 200 to the server device 500 in step S910 of Figure 9.

[0175] Prompt 22 includes text data 22a, 22b, 22c, and 22d. Text data 22a indicates a request to generate a response based on the information source in response to an inquiry from the user of the terminal device 600, and to refer to the preferred information if preferred information is associated with the information source.

[0176] Text data 22b indicates the content of the inquiry from the user of the terminal device 600. Text data 22c is the information source. The information source indicated by text data 22c is the company information obtained from the second storage device 400 in step S909 of Figure 9. Text data 22d indicates priority information associated with the information source indicated by text data 22c.

[0177] In this embodiment, by inputting such a prompt 22 to the large-scale language model 511 of the server device 500, output response data prioritizing pre-set priority information can be obtained.

[0178] Therefore, according to this embodiment, it is possible to obtain output response data generated based on appropriate information sources for question data, and to suppress the output of incorrect output response data.

[0179] (Fifth embodiment) A fifth embodiment will be described below with reference to the drawings. The fifth embodiment differs from the first embodiment in that the question answer storage unit 320 is searched before requesting a response from the server device 500. In the following description of the fifth 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 those used in the description of the first embodiment, and their explanations will be omitted.

[0180] Figure 23 is a sequence diagram illustrating the operation of the chat system according to the fifth embodiment. In the chat system 100 of this embodiment, when the information processing device 200 receives input of question data from the terminal device 600 (step S2301), the search request unit 252 sends a search request to the first storage device 300 (step S2302).

[0181] The search request sent to the first storage device 300 here includes the tenant ID and question data, and requests a search of the question answer storage unit 320, which stores question answer information associated with the tenant ID.

[0182] The first storage device 300 receives this search request and, using the search unit 330, searches the question and answer storage unit 320, which stores question and answer information associated with the tenant ID (step S2303), and transmits the registered answer data extracted as a search result to the information processing device 200 (step S2304). Specifically, the search unit 330 searches the question and answer information associated with the tenant ID and extracts registered answer data as a search result from the question and answer information that is associated with the question indicated by the question data.

[0183] Here, if no registered response data is extracted, that is, if the question data entered in step S2301 and the corresponding question are not stored in the question response storage unit 320, the information processing device 200 proceeds to step S902 in Figure 9 and performs the processing from step S902 onward.

[0184] Furthermore, if one or more registered response data are extracted, the information processing device 200 performs the processing described later in step S2305 and beyond.

[0185] The information processing device 200 transmits the registered response data acquired from the first storage device 300 to the terminal device 600 (step S2305). The terminal device 600, using the display control unit 650, displays the registered response data acquired from the information processing device 200 as the answer to the question data (step S2306).

[0186] In this case, the registered response data displayed on the terminal device 600 is extracted from the question and answer information stored in the question and answer storage unit 320.

[0187] Furthermore, in this embodiment, for example, if the terminal device 600 is instructed to obtain a response using the large-scale language model 511, the processing from step S2307 onwards may be performed.

[0188] The terminal device 600 receives an operation from the input receiving unit 640 to instruct the terminal device 600 to obtain a response from the server device 500 on the screen displayed in step S2306 (step S2307). Subsequently, the terminal device 600 transmits to the information processing device 200 that it has been instructed to obtain a response from the server device 500 (step S2308).

[0189] When the information processing device 200 receives notification in step S2308 of an instruction to obtain a response from the server device 500, it performs the processing from step S902 onwards in Figure 9.

[0190] The following describes an example of the display of the terminal device 600 of this embodiment with reference to Figures 24 to 26.

[0191] Figure 24 is the first diagram showing an example of the display of the terminal device according to the fifth embodiment. The screen 240 shown in Figure 24 is an example of a screen displayed on the terminal device 600 when no registered response data is extracted in step S2304 of Figure 23.

[0192] Screen 240 may be displayed on the terminal device 600 in step S915 of Figure 9 when the processes up to step S2304 in Figure 23 are executed in the chat system 100, and then the processes from step S902 onwards in Figure 9 are executed.

[0193] Screen 240 includes display areas 240a and 240b. Display area 240a displays question data entered by the user of terminal device 600. Display area 240b displays output response data from chat system 100.

[0194] In the example shown in Figure 24, the display area 240b displays text data indicating that the question answer storage unit 320 did not contain the answer corresponding to the question indicated by the question data displayed in the display area 240a. The display area 240b also displays text data indicating that the answer obtained from the server device 500 having a large-scale language model 511 is used as the output answer data for the question data.

[0195] In this embodiment, even if the question answer storage unit 320 does not store registered answer data corresponding to the question indicated by the question data, the output answer data generated by the server device 500 can be presented to the user.

[0196] Figure 25 is a second diagram showing an example of the display of the terminal device according to the fifth embodiment. The screen 240A shown in Figure 25 is an example of a screen that is displayed on the terminal device 600 in step S2306 when one registered response data is acquired in step S2304 of Figure 23.

[0197] Screen 240 includes display areas 240a, 240c, and 240d. Display area 240c displays registered answer data included in the question answer information stored in the question answer storage unit 320. In other words, display area 240c displays registered answer data obtained as search results in step S2304.

[0198] The display area 240d shows text data indicating that it is possible to acquire output response data generated by the large-scale language model 511 of the server device 500, and an operation button 240d-1 that instructs the acquisition of the response generated by the large-scale language model 511 (generating AI) of the server device 500.

[0199] In this embodiment, when the operation button 240d-1 displayed in the display area 240d is operated, the processing from step S2307 onwards in Figure 23 may be performed.

[0200] Figure 26 is a third diagram showing an example of the display of the terminal device according to the sixth embodiment. The screen 240B shown in Figure 26 is an example of a screen that is displayed on the terminal device 600 in step S2306 when multiple registered response data are acquired in step S2304 of Figure 23.

[0201] Screen 240B includes display areas 240a and 240e. Display area 240e displays multiple registered answer data 240e-1 included in the question answer information stored in the question answer storage unit 320, and operation buttons 240d-1.

[0202] The multiple registered response data 240e-1, in other words, the display area 240e contains the multiple registered response data obtained as search results in step S2304.

[0203] Furthermore, in this embodiment, when the operation button 240d-1 is operated on screen 240B, the processing from step S2307 onwards in Figure 23 may be performed.

[0204] In this embodiment, by displaying the operation button 240d-1, the server device 500 can generate output response data according to the user's request.

[0205] Furthermore, in this embodiment, before the server device 500 generates an answer, the question answer storage unit 320 is searched, and registered answer data associated with the registered question data corresponding to the question indicated by the question data is output. In this case, the registered answer data is an appropriate answer to the question indicated by the question data. In this embodiment, by outputting answers to questions in combination with the question answer storage unit 320 and the server device 500 in this way, the frequency of outputting incorrect or inappropriate answers can be reduced.

[0206] (Sixth Embodiment) A sixth embodiment will be described below with reference to the drawings. The sixth embodiment differs from the first embodiment in that it is possible to switch whether or not to use information other than internal company information as the information source. In the following description of the sixth embodiment, the differences from the first embodiment will be explained, and components having the same functional configuration as the first embodiment will be given the same reference numerals as those used in the description of the first embodiment, and their explanations will be omitted.

[0207] Figure 27 is a sequence diagram illustrating the operation of the chat system according to the sixth embodiment.

[0208] When the information processing device 200 receives input of question data from the terminal device 600 (step S2701), the prompt generation unit 255 refers to the setting information regarding the information source to be provided to the large-scale language model 511 (step S2702).

[0209] Specifically, the prompt generation unit 255 refers to configuration information indicating whether the information sources provided to the large-scale language model 511 should be internal company information and information publicly available on the internet, or only information publicly available on the internet.

[0210] The configuration information in this embodiment may, for example, be entered by the user of the terminal device 600. In that case, the configuration information may be entered when question data is entered in the terminal device 600 and transmitted to the information processing device 200 together with the question data.

[0211] Furthermore, the configuration information of this embodiment may be stored in the information processing device 200 in advance by a user of the terminal device 700, who is the administrator of internal company information. Also, the configuration information may be set to limit the information source provided to the large-scale language model 511 to only internal company information. In this case, the information processing device 200 may execute the processing from step S902 onwards in Figure 9 after step S2702.

[0212] Furthermore, the process of referencing the configuration information may be executed at a different time than step S2702. Specifically, the timing of referencing the configuration information may be before step S2701.

[0213] If the information processing device 200 is configured to provide information sources to the large-scale language model 511 as internal company information and information publicly available on the internet, it proceeds to step S2703. The chat system 100 then performs the processing from step S2703 to step S2714 and obtains output response data to be output to the terminal device 600.

[0214] The process from steps S2703 to S2714 in Figure 27 is the same as the process from steps S902 to S913 in Figure 9, except that the prompt generated in step S2712 is different from the prompt generated in step S911 in Figure 9. Therefore, the explanation is omitted. Details of the prompt generated in step S2712 will be described later.

[0215] Furthermore, if the information processing device 200 is configured to provide information to the large-scale language model 511 only from publicly available information on the internet, the process proceeds to step S2715. The chat system 100 then performs the processing from step S2715 to step S2717 and obtains the output response data from the server device 500.

[0216] The process from steps S2715 to S2717 in Figure 27 is the same as the process from steps S911 to S913 in Figure 9, except that the prompt generated in step S2715 is different from the prompt generated in step S911 in Figure 9. Therefore, the explanation is omitted. Details of the prompt generated in step S2715 will be described later.

[0217] When the information processing device 200 obtains output response data from the server device 500, it proceeds to step S2718, and the chat system 100 performs the processing from step S2718 to step S2721.

[0218] The process from step S2718 to step S2721 is the same as the process from step S914 to step S917 in Figure 9, so the explanation is omitted.

[0219] Next, with reference to Figures 28 to 30, the prompts transmitted from the information processing device 200 to the server device 500 in this embodiment will be described.

[0220] Figure 28 is the first diagram showing an example of a prompt in the sixth embodiment. The prompt 28 shown in Figure 28 is an example of a prompt generated by the prompt generation unit 255 in step S2715 of Figure 27.

[0221] Prompt 28 includes text data 28a and text data 28b. Text data 28a is text data requesting the generation of output answer data for the question indicated by the question data. Text data 28b is text data indicating the question data entered in step S2701.

[0222] In this embodiment, by inputting such a prompt 28 to the large-scale language model 511, output response data can be obtained using information from the Internet that the large-scale language model 511 used for training as the information source.

[0223] Figure 29 is a second diagram showing an example of a prompt in the sixth embodiment. The prompt 29 shown in Figure 29 is an example of a prompt generated by the prompt generation unit 255 in step S2712 of Figure 27.

[0224] Prompt 29 includes text data 29a, 28a, and 29b. Text data 29a is text data that requests the generation of output response data based on internal company information shown as text data 29b and information from the internet that the large-scale language model 511 used for training.

[0225] Text data 29b is company information acquired by the information processing device 200 in step S2711 of Figure 27.

[0226] In this embodiment, by inputting such a prompt 29 into the large-scale language model 511, the user can be presented with an answer generated from internal company information and publicly available information.

[0227] Figure 30 is a third figure showing an example of a prompt in the sixth embodiment. The prompt 30 shown in Figure 30 is another example of a prompt generated by the prompt generation unit 255 in step S2712 of Figure 27.

[0228] Prompt 30 includes text data 30a, 28a, and 29b. Text data 30a requests the generation of output response data using internal company information shown as text data 29b, and if no answer exists in the internal company information, it requests the generation of output response data using information from the internet that the large-scale language model 511 used for training.

[0229] In this embodiment, by inputting such a prompt 30 into the large-scale language model 511, even if the answer is not included in the internal company information used as the source, the user can be presented with an answer generated from publicly available information.

[0230] Thus, in this embodiment, the information source used when generating output response data can be set to include both internal company information and publicly available information, or to include only publicly available information. Therefore, in this embodiment, if a user of the chat system 100 desires a general response, they only need to set the information source used when generating output response data to include only publicly available information. Alternatively, if a user of the chat system 100 requests a response from internal company information, they can set the information source used when generating output response data to include both internal company information and publicly available information.

[0231] Thus, according to this embodiment, it is possible to provide answers based on the information sources requested by the user.

[0232] (Seventh Embodiment) The seventh embodiment will be described below with reference to the drawings. The seventh embodiment differs from the first embodiment in that it specifies the range to be searched from internal company information according to the user's operation or the content of the question. In the following description, the differences from the first embodiment will be explained, and components having the same functional configuration as the first embodiment will be given the same reference numerals as those used in the description of the first embodiment, and their explanation will be omitted.

[0233] The following is an overview of this embodiment. In this embodiment, the large-scale language model 511 generates an answer using internal company information desired by the user asking the question as the source of information. More specifically, in this embodiment, the user asking the question is asked to specify the range of internal company information to be used as the source of information for the answer, and the results of searching for internal company information within the specified range are included in the prompt requesting the large-scale language model 511 to generate an answer.

[0234] Furthermore, in this embodiment, if the user asking the question does not specify the scope of internal company information, the scope of internal company information to be used as the source of the answer is determined according to the content of the question. Then, in this embodiment, the results of searching for internal company information within the specified scope are included in the prompt requesting the large-scale language model 511 to generate an answer.

[0235] In this embodiment, by doing so, it is possible to provide the user who asked the question with an answer that uses the company information the user desires as the source of information.

[0236] Figure 31 is a diagram illustrating the functions of each device in the chat system of the seventh embodiment.

[0237] First, the second storage device 400A included in the chat system 100A of this embodiment will be described.

[0238] The second storage device 400A of this embodiment includes a document storage unit 410A, a chunk storage unit 415, a user information storage unit 420, and a scenario storage unit 425. The document storage unit 410A of this embodiment is provided with multiple storage areas, and company information is stored in each storage area according to the settings of the administrator of the chat system 100A. In the following description, each of the multiple storage areas provided in the document storage unit 410A will be referred to as a folder. The chunk storage unit 415 stores chunks for each piece of company information.

[0239] The scenario storage unit 425 stores information for identifying the search range of company information stored in the second storage device 400A. In the following description, the information stored in the scenario storage unit 425 will be referred to as scenario information. The scenario information in this embodiment may be pre-set by the administrator of the chat system 100A and stored in the scenario storage unit 425.

[0240] Details of the document storage unit 410A, chunk storage unit 415, and scenario storage unit 425 will be described later.

[0241] Next, the functions of the information processing device 200A will be described. The information processing device 200A in this embodiment includes an input receiving unit 251, a search request unit 252, a conversation history acquisition unit 253, an information acquisition unit 254, a prompt generation unit 255, a prompt output unit 256, an information output unit 257, a division unit 258, a scenario setting unit 259, a scenario acquisition unit 260, a search range identification unit 261, and a question analysis unit 262.

[0242] The splitting unit 258 divides the company information stored in the document storage unit 410A into multiple chunks. The scenario setting unit 259 sets the scenario information. In other words, the scenario setting unit 259 generates scenario information according to the operation on the terminal device 700 and stores it in the scenario storage unit 425 of the second storage device 400A.

[0243] The scenario acquisition unit 260 acquires scenario information stored in the scenario storage unit 425 of the second storage device 400A in response to the operation of the terminal device 600. The search range identification unit 261 identifies the search range of the chunks stored in the chunk storage unit 415 based on the scenario information acquired by the scenario acquisition unit 260. The question analysis unit 262 analyzes the question data input from the terminal device 600. Specifically, the question analysis unit 262 performs morphological analysis on the question data and acquires user attributes associated with the terminal device 600 into which the question data was input, etc., to identify the scenario information to be referenced.

[0244] Next, with reference to Figures 32 to 34, the document storage unit 410A, chunk storage unit 415, and scenario storage unit 425 of the second storage device 400A of this embodiment will be described.

[0245] Figure 32 shows an example of a document storage unit according to the seventh embodiment. In this embodiment, the document storage unit 410A has multiple folders created, and company information is stored in each folder. The folders may be created in advance by the administrator of the chat system 100A or the like.

[0246] In the document storage unit 410A, the file name of the company information to be stored, the folder name in which the company information is stored, the update date and time of the company information, etc., may be stored in association with the company information.

[0247] In the example in Figure 32, it can be seen that the internal information file named "Sales Report" was stored in the "Sales Materials" folder at 9:00 AM on June 24, 2024. Also in the example in Figure 32, it can be seen that the internal information file named "Regarding Paid Leave" was stored in the "Development Department" folder at 9:00 AM on June 18, 2024.

[0248] The folders created in the document storage unit 410A may, for example, be created for each business activity within the tenant, or for each department within the tenant. Folders in the document storage unit 410A can be arbitrarily created by the administrator of the tenant implementing the chat system 100.

[0249] Figure 33 shows an example of a chunk storage unit in the seventh embodiment. In Figure 33, the file name of the internal company information, the update date and time of the internal company information, the chunk ID that identifies the chunk, and the chunk are associated with each other.

[0250] Furthermore, in the example shown in Figure 33, one page of internal information from the internal document "Sales Report" is treated as a chunk, and the page number is used as the chunk ID to identify the chunk.

[0251] Furthermore, a chunk is not limited to a single page of internal company information; for example, it could be a paragraph within an internal document, or even a chapter.

[0252] Figure 34 shows an example of a scenario storage unit in the seventh embodiment. The scenario information in this embodiment may be stored for each tenant.

[0253] The scenario information stored in the scenario storage unit 425 of this embodiment has the following information items associated with it: tenant ID, specified item, and search target folder. The value of the item "specified item" indicates an item that allows the user to specify the range of internal company information to be used as the source of the answer. In other words, the value of the item "specified item" is an item for classifying internal company information, and the internal company information is classified according to the specified item and stored in the document storage unit 410A.

[0254] In this embodiment, the list of items indicated by the item "Specified Item" is displayed on the terminal device 600 as an option to select when specifying the scope of internal company information. The value of the item "Search Target Folder" indicates the folder name associated with the specified item.

[0255] In the example in Figure 34, the specified items are "Sales Department," "Development Department," and "Paid Leave," and these are displayed on the terminal device 600. In addition, in the example in Figure 34, the specified item "Sales Department" is associated with the "Sales Materials" folder, the specified item "Development Department" is associated with the "Development Department" folder, and the specified item "Paid Leave" is associated with the "Attendance Management" folder and the "Labor Management" folder.

[0256] Therefore, in Figure 34, the terminal device 600 may display operation buttons such as "Sales Department," "Development Department," and "Take Paid Leave" as options to select when choosing a specified item. If the operation button indicating "Sales Department" is selected from the displayed options, the company information stored in the "Sales Department" folder in the document storage unit 410A is designated as the source of the response.

[0257] In the example shown in Figure 34, the specified item is set separately from the folder name provided in the document storage unit 410A, but this is not limited to this. In this embodiment, the folder name provided in the document storage unit 410A may also be used as the specified item.

[0258] In that case, the terminal device 600 may display a list of folder names created in the document storage unit 410A as a list of items for specifying the scope of internal company information to be used as a source.

[0259] Furthermore, in the example shown in Figure 34, the scenario information is information that associates specified items with search target folders, but it is not limited to this. The scenario information may also include operation information that specifies the operation of the chat system 100A for each specified item. The operation information may be, for example, information that indicates the operation of the chat system 100A when there is insufficient information obtained from the question entered from the terminal device 600. The operation information may also be information that indicates the operation of the chat system 100A when there are multiple folders associated with the specified items.

[0260] Next, referring to FIG. 35, the operation of the chat system 100A when storing in-company information in the second storage device 400A will be described. FIG. 35 is a first sequence diagram for explaining the operation of the chat system according to the seventh embodiment.

[0261] In the chat system 100, the terminal device 700 causes the display control unit 750 to display an administrator screen for an administrator (step S3501). Subsequently, the terminal device 700 receives, via the input reception unit 740, an operation of selecting a folder for storing in-company information (step S3502). Subsequently, the terminal device 700 receives, via the input reception unit 740, a selection of in-company information to be stored in the folder (step S3503). Subsequently, the terminal device 700 transmits (uploads) the selected in-company information to the information processing device 200 via the communication control unit 730 (step S3504).

[0262] When the information processing device 200A receives in-company information via the input reception unit 251, it transmits the received in-company information to the second storage device 400A via the information output unit 257 (step S3505), and transmits a reception notification indicating that the in-company information has been received to the terminal device 700 (step S3506). The second storage device 400A stores the in-company information in the selected folder in the document storage unit 410A by the storage unit 440 (step S3507).

[0263] Subsequently, the information processing device 200A divides the in-company information into chunks by the division unit 258 (step S3508). Subsequently, the information processing device 200A transmits the divided chunks to the second storage device 400A via the information output unit 257 (step S3509).

[0264] The second storage device 400A stores, by the storage unit 440, the chunks received from the information processing device 200A in the chunk storage unit 415 together with information for specifying the in-company information in which the chunks are included (step S3510).

[0265] Subsequently, the information processing apparatus 200A transmits, via the information output unit 257, a completion notice indicating that the registration of the in-company information has been completed to the terminal device 700 (step S3511).

[0266] Next, referring to FIG. 36, the operation of the chat system 100A when storing scenario information in the scenario storage unit 425 will be described. FIG. 36 is a second sequence diagram for explaining the operation of the chat system according to the seventh embodiment.

[0267] In the chat system 100A of the present embodiment, the terminal device 700 causes the display control unit 750 to display an administrator screen for administrators (step S3601). Subsequently, the terminal device 700 receives, via the input reception unit 740, an operation for setting scenario information (step S3602). Subsequently, the terminal device 700 transmits, via the communication control unit 730, a display request for the scenario setting screen to the information processing apparatus 200A (step S3603).

[0268] When the information processing apparatus 200A receives this display request, the scenario setting unit 259 outputs, via the information output unit 257, a display instruction for the scenario setting screen to the terminal device 700 (step S3604).

[0269] The terminal device 700 receives this display instruction and causes the display control unit 750 to display the scenario setting screen (step S3605). Subsequently, the terminal device 700 receives, via the input reception unit 740, the input of scenario information (step S3606).

[0270] For example, when a specified item is input and a folder name associated with the specified item is selected on the scenario setting screen of the terminal device 700, the specified item, the selected folder name, and the tenant ID of the tenant to which the user of the terminal device 700 belongs may be associated as scenario information. <^{0000918}> The specified items entered here may be entered by a new user of the terminal device 700, or they may be selected from the scenario information stored in the scenario storage unit 425.

[0272] Next, the terminal device 700 transmits the input scenario information to the information processing device 200A via the communication control unit 730 (step S3607).

[0273] When the scenario setting unit 259 of the information processing device 200A receives scenario information from the terminal device 700, it outputs the received scenario information to the second storage device 400A via the information output unit 257 (step S3608).

[0274] The second storage device 400A stores the scenario information received from the information processing device 200A in the scenario storage unit 425 (step S3609) and notifies the information processing device 200A that the storage is complete (step S3610). Upon receiving this notification, the information processing device 200A sends a notification to the terminal device 700 via the information output unit 257 indicating that the reception of the scenario information is complete (step S3611). The terminal device 700 displays the notification received from the information processing device 200A via the display control unit 750 (step S3612).

[0275] In this embodiment, by performing the above process and setting the scenario information in this manner, a list of specified items to be displayed on the terminal device 600 can be created.

[0276] Next, an example of the display of the terminal device 700 will be described with reference to Figure 37. Figure 37 is the first diagram showing an example of the display of the terminal device in the seventh embodiment. The screen 140 shown in Figure 37 is an example of the administrator screen displayed on the terminal device 700 in step S3501 of Figure 35 and step S3601 of Figure 36.

[0277] Screen 140 includes a display area 141 and operation buttons 142. The display area 141 displays a list of company information stored in folders provided in the document storage unit 410A. In the example in Figure 14, a list of company information stored in the "Sales Department" folder is displayed.

[0278] Operation button 142 is an operation button for displaying the scenario setting screen. In this embodiment, when operation button 142 is operated on screen 140, a request to display the scenario setting screen is sent from the terminal device 700 to the information processing device 200A, and screen 140 transitions to the scenario setting screen.

[0279] Figure 38 is a second diagram showing an example of the display of the terminal device in the seventh embodiment. The screen 150 shown in Figure 38 is an example of a scenario setting screen displayed on the terminal device 700 in step S3604 of Figure 36. Furthermore, screen 150 is an example of a scenario setting screen for setting scenario information for the specified item "Sales Department".

[0280] Furthermore, screen 150 includes display areas 151 and 152 and operation buttons 153. Display area 151 displays display area 154 for selecting an object to be associated with a specified item, and display area 154 includes operation buttons 154a and 154b.

[0281] The target associated with the specified item may be the folder to be searched, or it may be action information associated with each specified item. Operation button 154a is an operation button for selecting the folder to be searched as the target associated with the specified item. Operation button 154b is an operation button for adding a new target to be associated with the specified item.

[0282] In Figure 38, in display area 154, operation button 154a is selected, and in display area 152, a selection field for the folder to be associated with the specified item "Sales Department" is displayed. Specifically, in display area 152, the "Sales Materials" folder is associated with the specified item "Sales Department". Operation button 153 is an operation button for storing scenario information, including the specified item and folder name associated in display area 152, into the second storage device 400A.

[0283] In this embodiment, when the operation button 153 is operated after the specified item has been associated with the search target folder and operation information on screen 150, scenario information is transmitted from the terminal device 700 to the information processing device 200A.

[0284] In this embodiment, the administrator of the chat system 100A can configure the operation of the chat system 100A when it starts providing services through the chat system 100A.

[0285] Figure 39 is a third diagram showing an example of the display of a terminal device according to the seventh embodiment. The screen 160 shown in Figure 39 is an example of a screen for setting the operation of the chat system 100A when the chat system 100A starts providing a service.

[0286] Screen 160 includes settings fields 161 and 162. Setting field 161 is where the message to be displayed to the terminal device 600 when the chat system 100A starts providing its service is configured. In the example in Figure 39, it can be seen that the setting was configured to display the message, "Do you have any questions? Please choose to enter your question directly or search using the buttons."

[0287] In the settings section 162, it can be seen that when a specified item is selected in the list of specified items to be displayed on the terminal device 600 at the start of service provision by the chat system 100A, the system is configured to perform processing according to the scenario information associated with that specified item. In this embodiment, as described above, the administrator of the chat system 100A can set the operation of the chat system 100A at the start of the service provided by the chat system 100A.

[0288] Next, referring to FIG. 40, the operation of the chat system 100A when a user of the terminal device 600 makes a query will be described. FIG. 40 is a third sequence diagram for explaining the operation of the chat system according to the seventh embodiment.

[0289] In the chat system 100A, the terminal device 600 causes the display control unit 650 to display a chat screen (step S4001). A list of designated items for the user of the terminal device 600 is displayed as a list of operation buttons on this chat screen.

[0290] The following processing from step S4002 to step S4012 shows the operation of the chat system 100A when an operation button is selected on the chat screen displayed on the terminal device 600 in step S4001.

[0291] When the terminal device 600 accepts the selection of an operation button displayed on the chat screen (step S4002), the communication control unit 630 transmits information specifying the selected operation button to the information processing device 200A (step S4003). In other words, when the terminal device 600 accepts the selection of a designated item from the list of designated items, it notifies the information processing device 200A of the selected designated item.

[0292] When the information processing device 200A receives information that identifies the selected operation button (selected specified item), the scenario acquisition unit 260 sends a request to the second storage device 400A to acquire scenario information corresponding to the specified item (step S4004). When the second storage device 400A receives this acquisition request, it searches the scenario storage unit 425 using the specified item and acquires the scenario information corresponding to the specified item (step S4005). Subsequently, the second storage device 400A sends the acquired scenario information to the information processing device 200A (step S4006).

[0293] When the information processing device 200A acquires scenario information, the search range identification unit 261 identifies the company information within the search target folder included in the scenario information as the search range (step S4007). Subsequently, the information processing device 200A outputs a message to the terminal device 600 via the information output unit 257 indicating that it will output a response based on the company information within the search range (step S4008).

[0294] When the terminal device 600 receives input of question data on the chat screen, the communication control unit 630 transmits the question data to the information processing device 200A (step S4009).

[0295] When the information processing device 200A receives the input of question data via the input receiving unit 251, the search request unit 252 sends a search request within the search range specified in step S4007 to the second storage device 400A (step S4010). The search request sent to the second storage device 400A here may be the result of morphological analysis, etc., performed by the question analysis unit 262 on the question data input in step S4009.

[0296] When the second storage device 400A receives a search request, the search unit 430 searches for chunks within the search range identified in step S4007 among the chunks stored in the chunk storage unit 415 (step S4011), transmits the search results to the information processing device 200A (step S4012), and proceeds to step S4022, which will be described later.

[0297] The following steps S4013 to S4018 demonstrate the operation of the chat system 100A when, in the chat screen displayed on the terminal device 600 in step S4001, no operation button is selected and a question is entered directly.

[0298] When question data is input to the terminal device 600, the communication control unit 630 transmits the question data to the information processing device 200A (step S4013). When the information processing device 200A receives the input of question data via the input receiving unit 251, the question analysis unit 262 analyzes the question data and identifies the specified items (step S4014). In other words, the question analysis unit 262 analyzes the question data and, based on the analysis results, identifies the scenario information to be referenced.

[0299] The processing of the question analysis unit 262 is described below. In this embodiment, the question analysis unit 262 may, for example, refer to the scenario storage unit 425 of the second storage device 400A and identify a specified item based on the content of the question indicated by the question data.

[0300] Furthermore, the question analysis unit 262 may obtain user attributes by referring to the user information of the user of the terminal device 600, and identify the specified items based on the user attributes. User attributes include, for example, the department to which the user belongs. In this case, it is assumed that the information processing device 200A has already obtained the user ID of the user of the terminal device 600 and the tenant ID of the tenant to which the user belongs. The question analysis unit 262 may refer to the scenario storage unit 425 of the second storage device 400A and identify the specified items based on the user attributes of the terminal device 600.

[0301] Next, the information processing device 200A sends a request to the second storage device 400A to acquire scenario information for the specified item identified by the scenario acquisition unit 260 (step S4015). The processes from step S4015 to step S4018 in Figure 40 are the same as the processes from step S4004 to step S4007, so the explanation is omitted. Also, the processes from step S4019 to step S4021 are the same as the processes from step S4010 to step S4012 in Figure 40, so the explanation is omitted. Note that the search request sent to the second storage device 400A in step S4019 may be the result of morphological analysis, etc., performed by the question analysis unit 262 on the question data input in step S4013.

[0302] In this embodiment, even if the user of the terminal device 600 does not select any specified items, the specified items can be automatically identified from the content of the question data and the user's attributes, thereby increasing the probability that response data based on the information source desired by the user will be output.

[0303] The information processing device 200A, using the second storage device 400 prompt generation unit 255, generates a prompt requesting the generation of an answer to a question, using the search results as the information source (step S4022).

[0304] More specifically, in step S4002, when the prompt generation unit 255 receives input of a specified item indicating the classification of internal company information, it includes the chunks obtained as search results for internal company information classified under the input specified item as internal company information to be included in the prompt requesting the generation of an answer to the question.

[0305] Furthermore, in step S4013, when question data is input, the prompt generation unit 255 includes the chunks obtained as search results for internal company information classified into specified items identified by the question analysis unit 262 as internal company information to be included in the prompt requesting the generation of an answer to the question.

[0306] The processes from steps S4022 to S4028 in Figure 40 are the same as the processes from steps S911 to S917 in Figure 9, so their explanation will be omitted.

[0307] The chat screen of this embodiment will be described below with reference to Figure 41. Figure 41 is the fourth figure showing an example of the display of the terminal device of the seventh embodiment. Screen 170 shown in Figure 41 is an example of the chat screen displayed on the terminal device 600 in step S4026 of Figure 41. Also, screen 170 shown in Figure 41 is an example of the chat screen displayed in step S4026 when a specified item is selected from the list of specified items in step S4001 of Figure 40.

[0308] Screen 170 includes display areas 171, 172, 173, 174, and 175. Display area 171 includes display areas 171a and 171b. Display area 171a displays a message prompting the user to select a specified item or enter question data. The message displayed here may be pre-configured as part of the operation information included in the scenario information.

[0309] Display area 171b displays a list of specified items and corresponding operation buttons. In other words, display area 171b displays multiple operation buttons as options for selecting a specified item.

[0310] Display area 172 displays the specified item selected in display area 171b. In the example in Figure 41, it can be seen that the specified item "Development Department" was selected.

[0311] Display area 173 includes display area 173a and operation button 173b. Display area 173a displays the message to be sent to the terminal device 600 in step S4008 of Figure 40. More specifically, display area 173a displays a message indicating that the user should answer the question regarding the specified item "Development Department". Operation button 173b is an operation button for restarting the question from the beginning. When operation button 173b is selected, the display from display area 172 onwards may be hidden.

[0312] Display area 174 displays the question data entered by the user. Display area 175 includes display areas 175a, 175b, 175c, and operation button 175d. Display area 175a displays the answer data output from the large-scale language model 511. Display area 175b displays information indicating the storage location of the internal company information that served as the source of the data.

[0313] Display area 175c displays a message indicating that response data has been generated by the large-scale language model 511. Operation button 175d is an operation button for the user to end a conversation using the chat system 100A.

[0314] Furthermore, the display area 171 on screen 170 in Figure 41 may be displayed on the terminal device 600, for example, when the user directly inputs question data in step S4001 of Figure 40, and the specified item is not identified by the processing of the question analysis unit 262 in step S4014.

[0315] Furthermore, in this embodiment, if the user directly inputs the question data and the specified item is not identified by the processing of the question analysis unit 262 in step S4014, the information processing device 200A may display a message on the terminal device 600 asking for the user's attributes. If the specified item is not identified by the processing of the question analysis unit 262, the information processing device 200A may display a message on the terminal device 600 that includes a question to help the user identify the specified item.

[0316] Furthermore, if the user directly inputs question data and the specified item is not identified by the processing of the question analysis unit 262 in step S4014, the information processing device 200A may display a question statement on the terminal device 600 to obtain additional questions from the user. In this case, the information processing device 200A may generate a prompt requesting the user of the terminal device 600 to generate a question statement to prompt the user to input further information, output this prompt to the large-scale language model 511, and transmit the question statement output from the large-scale language model 511 to the terminal device 600.

[0317] In this embodiment, internal company information is pre-classified according to specified items and stored in the document storage unit 410A. Then, in this embodiment, by having the user of the terminal device 600 select specified items, the system can search for internal company information within the range desired by the user and generate answers to questions. Therefore, according to this embodiment, the likelihood of outputting appropriate answers to user questions can be increased, and the accuracy of answers to questions can be improved.

[0318] Furthermore, in this embodiment, based on the results of explaining the question data input from the terminal device 600, a designated item indicating the classification of internal company information is identified, and the internal company information identified and associated with the designated item is used as the search target when acquiring information sources to generate the answer. Therefore, according to this embodiment, even if the user does not select a designated item, the system can generate an answer to the question by searching for internal company information within the range desired by the user, thereby improving the accuracy of the answer to the question.

[0319] Furthermore, while the embodiments described above have explained an example of user-specific information using internal company information, user-specific information is not limited to this. User-specific information can also be applied to store information and user-specific information, for example. Store information includes store identification information (store name, address, telephone number), purchase history information, etc.

[0320] Furthermore, user-specific information includes personally identifiable information, account information, purchase history information, browsing history information, location information, preference information, activity information, etc. Personally identifiable information includes information used to identify a specific individual, such as name, address, telephone number, and email address. Account information includes information related to a specific online account, such as username, password, and account number. Purchase history information includes information such as products and services purchased by the user, purchase date and time, and payment method. Browsing history information includes information such as pages viewed by the user on websites and apps, search history, and click history. Location information includes location-related information such as the user's current location and past travel history. Preference information is information indicating content preferences and tastes, including information about content, products, and services that the user may be interested in. Activity information is information about social media activity, such as posts shared by the user, likes, and comments. This includes information such as your browsing history and the people you follow.

[0321] 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.

[0322] Furthermore, the apparatus described in each embodiment represents only one of several computing environments for carrying out the embodiments disclosed herein.

[0323] 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.

[0324] 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.

[0325] 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.

[0326] Examples of the present invention are as follows: <1> An input receiving unit that accepts the input of question data, Upon receiving the input of the aforementioned question data, a prompt output unit outputs a prompt to the large-scale language model requesting the generation of answer data for the aforementioned question data based on user-specific information. An information processing device having an information output unit that outputs response data output from the large-scale language model based on the prompt output from the prompt output unit as output response data to a terminal device. <2> The unit includes a conversation history acquisition unit that acquires conversation history information from a first storage device that was in the conversation history up to the moment the aforementioned question data was input. The prompt output unit is, The conversation history acquisition unit outputs a prompt to the large-scale language model requesting the generation of a query to search for a second storage device that stores user-specific information, which includes the conversation history information acquired by the conversation history acquisition unit. <1> The information processing device described. <3> The information acquisition unit has an information acquisition unit that acquires user-specific information which is the search result of the second storage device based on the query output from the large-scale language model in response to the input of a prompt requesting the generation of the aforementioned query. The prompt output unit is, The user-specific information to be included in the prompt requesting the generation of the aforementioned response data shall be the user-specific information acquired by the information acquisition unit. <2> The information processing device described. <4> The prompt output unit is, If the conversation history information is not acquired by the conversation history acquisition unit, the user-specific information acquired as a result of searching the second storage device using the question data shall be included as the user-specific information in the prompt requesting the generation of the answer data. <2> The information processing device described. <5> The prompt output unit is, The system includes the response data output from the large-scale language model and outputs a prompt to the large-scale language model requesting correction of the response data. <1> ~ <4> An information processing device as described in any one of the following items. <6> The system includes an information output unit that receives input of priority information to be associated with the user-specific information, and stores the user-specific information in a storage device in association with the priority information. The prompt output unit is, When the user-specific information is associated with the priority information, a prompt is output to the large-scale language model requesting the generation of response data that includes the priority information and prioritizes the priority information. <1> ~ <5> An information processing device as described in any one of the following items. <7> The system includes a search request unit that transmits a search request based on the aforementioned question data to a first storage device that stores question and answer information, in which registered question data and registered answer data are associated. The prompt output unit is, If the first storage device does not contain registered response data corresponding to the question data, a prompt requesting the generation of the response data is output to the large-scale language model. <1> ~ <6> An information processing device as described in any one of the following items. <8> The prompt output unit is, The first storage device stores registered response data corresponding to the question data, and when instructed to generate a response using the large-scale language model, it outputs a prompt to the large-scale language model requesting the generation of the response data. <7> The information processing device described. <9> The prompt output unit is, Based on the user-specific information and the information learned by the large-scale language model, a prompt requesting the generation of the response data is output to the large-scale language model. <1> ~ <8> An information processing device as described in any one of the following items. <10> The prompt output unit is, If the user-specific information does not include the question data and corresponding answer data, a prompt is output to the large-scale language model requesting the generation of the answer data based on the information learned by the large-scale language model. <1> ~ <8> An information processing device as described in any one of the following items. <11> The system includes a prompt generation unit that, upon receiving the input of the aforementioned question data, generates a prompt requesting the generation of answer data for the aforementioned question data. <1> ~ <10> An information processing device as described in any one of the following items. <12> The user-specific information is stored in the second storage device, categorized by specified items. The aforementioned input receiving unit is The system accepts input for items indicating the classification of user-specific information. The prompt output unit is, The search results obtained by searching for the user-specific information classified into the items based on the aforementioned question data are to be included as the user-specific information in the prompt requesting the generation of the aforementioned response data. <1> The information processing device described. <13> The user-specific information is stored in the second storage device, categorized by specified items. The system includes a question analysis unit that identifies the items corresponding to the question data based on the results of analyzing the question data, The prompt output unit is, The search results obtained by searching for user-specific information classified into the items identified by the question analysis unit using the aforementioned question data are to be included as user-specific information in the prompt requesting the generation of the aforementioned response data. <1> The information processing device described. <14> 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 receives question data from the aforementioned terminal device, Upon receiving the input of the aforementioned question data, a prompt output unit outputs a prompt to the large-scale language model requesting the generation of answer data for the aforementioned question data based on user-specific information. The system includes an information output unit that outputs response data output from the large-scale language model based on the prompt output from the prompt output unit as output response data to the terminal device, The aforementioned terminal device is An information processing system having a display control unit that displays the aforementioned question data and the aforementioned output answer data in association. <15> 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 terminal device receives input of question data, A prompt is output to the large-scale language model requesting the generation of response data to the aforementioned question data based on user-specific information. Based on the outputted prompt, the response data output from the large-scale language model is output to the terminal device as output response data. The aforementioned terminal device An information processing method for displaying the aforementioned question data and the aforementioned output response data in association. <16> We accept the input of question data. A prompt is output to the large-scale language model requesting the generation of response data to the aforementioned question data based on user-specific information. A program that causes an information processing device to execute a process that outputs response data output from the large-scale language model based on the outputted prompt to a terminal device as output response data.

[0327] 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]

[0328] 100 Chat Systems 200 Information Processing Devices 251 Input Reception Section 252 Search Request Section 253 Conversation History Acquisition Unit 254 Information Acquisition Department 255 Prompt generation unit 256 Prompt output section 257 Information Output Unit 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]

[0329] [Patent Document 1] Japanese Patent Publication No. 2023-129333

Claims

1. An input receiving unit that accepts the input of question data, Upon receiving the input of the aforementioned question data, a prompt output unit outputs a prompt to the large-scale language model requesting the generation of answer data for the aforementioned question data based on user-specific information. An information processing device having an information output unit that outputs response data output from the large-scale language model based on the prompt output from the prompt output unit as output response data to a terminal device.

2. The unit includes a conversation history acquisition unit that acquires conversation history information from a first storage device that was in the conversation history up to the moment the aforementioned question data was input. The prompt output unit is, The information processing apparatus according to claim 1, which outputs a prompt to the large-scale language model requesting the generation of a query for searching a second storage device that stores user-specific information and includes the conversation history information acquired by the conversation history acquisition unit.

3. The information acquisition unit has an information acquisition unit that acquires user-specific information which is the search result of the second storage device based on the query output from the large-scale language model in response to the input of a prompt requesting the generation of the aforementioned query. The prompt output unit is, The information processing apparatus according to claim 2, wherein the user-specific information to be included in the prompt requesting the generation of the response data is user-specific information acquired by the information acquisition unit.

4. The prompt output unit is, The information processing apparatus according to claim 2, wherein, if the conversation history information is not acquired by the conversation history acquisition unit, user-specific information acquired as a result of searching the second storage device using the question data is included as user-specific information in the prompt requesting the generation of the answer data.

5. The prompt output unit is, The information processing apparatus according to claim 1 or 2, which includes response data output from the large-scale language model and outputs a prompt to the large-scale language model requesting correction of the response data.

6. The system includes an information output unit that receives input of priority information to be associated with the user-specific information, and stores the user-specific information in a storage device in association with the priority information. The prompt output unit is, The information processing apparatus according to claim 1 or 2, wherein, when the priority information is associated with the user-specific information, it outputs a prompt to the large-scale language model requesting the generation of response data that includes the priority information and prioritizes the priority information.

7. The system includes a search request unit that transmits a search request based on the aforementioned question data to a first storage device that stores question and answer information, in which registered question data and registered answer data are associated. The prompt output unit is, The information processing apparatus according to claim 1 or 2, wherein if the first storage device does not contain registered answer data corresponding to the question data, it outputs a prompt to the large-scale language model requesting the generation of the answer data.

8. The prompt output unit is, The information processing apparatus according to claim 7, wherein the first storage device stores registered response data corresponding to the question data, and when instructed to generate a response by the large-scale language model, outputs a prompt to the large-scale language model requesting the generation of the response data.

9. The prompt output unit is, The information processing apparatus according to claim 1, which outputs a prompt to the large-scale language model requesting the generation of the response data based on the user-specific information and the information learned by the large-scale language model.

10. The prompt output unit is, The information processing device according to claim 1, wherein, if the user-specific information does not include the question data and corresponding answer data, the device outputs a prompt to the large-scale language model requesting the generation of the answer data based on the information learned by the large-scale language model.

11. The information processing apparatus according to claim 1 or 2, further comprising a prompt generation unit that, upon receiving input of the aforementioned question data, generates a prompt requesting the generation of answer data for the aforementioned question data.

12. The user-specific information is stored in the second storage device, categorized by specified items. The aforementioned input receiving unit is The system accepts input for items indicating the classification of user-specific information. The prompt output unit is, The information processing device according to claim 1, wherein the search results obtained by searching for user-specific information classified into the items based on the question data are included as user-specific information in a prompt requesting the generation of the answer data.

13. The user-specific information is stored in the second storage device, categorized by specified items. The system includes a question analysis unit that identifies the items corresponding to the question data based on the results of analyzing the question data, The prompt output unit is, The information processing apparatus according to claim 1, wherein the search results obtained by searching for user-specific information classified into the items identified by the question analysis unit using the question data are included as user-specific information in a prompt requesting the generation of the answer data.

14. 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 receives question data from the aforementioned terminal device, Upon receiving the input of the aforementioned question data, a prompt output unit outputs a prompt to the large-scale language model requesting the generation of answer data for the aforementioned question data based on user-specific information. The system includes an information output unit that outputs response data output from the large-scale language model based on the prompt output from the prompt output unit as output response data to the terminal device, The aforementioned terminal device is An information processing system having a display control unit that displays the aforementioned question data and the aforementioned output answer data in association.

15. 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 terminal device receives input of question data, A prompt is output to the large-scale language model requesting the generation of response data to the aforementioned question data based on user-specific information. Based on the outputted prompt, the response data output from the large-scale language model is output to the terminal device as output response data. The aforementioned terminal device An information processing method for displaying the aforementioned question data and the aforementioned output response data in association.

16. We accept the input of question data. A prompt is output to the large-scale language model requesting the generation of response data to the aforementioned question data based on user-specific information. A program that causes an information processing device to execute a process that outputs response data output from the large-scale language model based on the outputted prompt to a terminal device as output response data.

Images