Programs, information processing devices, methods, and systems

Abstract

Based on user knowledge, the system customizes specific tasks that users are asked to perform. [Solution] A program for operating a computer 20, which is equipped with a processor 29 and memories 25 and 26, causes the processor 29 to perform the following steps: a first step of acquiring knowledge information about the user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented on a different computer 40, and generating and acquiring a specific task from the large-scale language model to request the user to perform; a third step of presenting the specific task acquired in the second step to the user and obtaining the execution result of this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the execution result of the specific task acquired in the third step, and the knowledge information input into the large-scale language model in the second step.

Description

Technical Field

[0001] The present disclosure relates to programs, information processing apparatuses, methods, and systems.

Background Art

[0002] Techniques for sending questions to a user online (i.e., via the Internet), obtaining answers to the questions from the user, and associating the questions and answers to create a database are known.

[0003] In relation to such techniques, Patent Document 1 discloses an interview system configured to execute a process of acquiring and recording the behavior information of one or more users and a process of conducting a questionnaire on a target user specified by one or more users, wherein the process of conducting a questionnaire on the target user includes setting one or more questionnaire items that constitute an interview based on the history of the behavior information of the target user.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, techniques for dynamically generating interview questions based on a user's behavior history or the like have not yet been disclosed. More generally, techniques for dynamically generating a specific task to be requested of a user based on knowledge information about the user and obtaining the execution result of the specific task from the user have not yet been disclosed.

[0006] The purpose of this disclosure is to customize specific tasks that users are asked to perform based on knowledge information about them, thereby making the analysis based on the results of those specific tasks obtained from the user more appropriate. [Means for solving the problem]

[0007] To solve the above problems, a program according to one aspect of the present disclosure is a program for operating a computer comprising a processor and memory. This program causes the processor to perform the following steps: a first step of acquiring knowledge information about a user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented on a computer different from the computer, and causing the large-scale language model to generate and acquire a specific task to be requested from the user to perform; a third step of presenting the specific task acquired in the second step to the user and obtaining the result of executing this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the result of executing the specific task acquired in the third step, and the knowledge information input into the large-scale language model in the second step. [Effects of the Invention]

[0008] According to this disclosure, based on knowledge information about the user, specific tasks that the user is asked to perform can be customized for each user, thereby making the analysis based on the results of specific tasks obtained from the user more appropriate. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows the overall configuration of a system according to one embodiment. [Figure 2] This figure shows the functional configuration of a terminal device according to one embodiment. [Figure 3] This figure shows the functional configuration of a server according to one embodiment. [Figure 4]This figure shows an example of the data structure of a user database according to one embodiment. [Figure 5] This figure shows an example of the data structure of a question data table according to one embodiment. [Figure 6] This figure shows an example of the data structure of a response database according to one embodiment. [Figure 7] A flowchart showing an example of the processing flow in a system according to one embodiment. [Figure 8] This flowchart shows an example of the processing flow in a system according to one embodiment, and is a flowchart of an example of the processing flow following the processing flow in Figure 7. [Figure 9] This figure shows an example of data exchange between a terminal device, a server, and an external server in a system according to one embodiment. [Figure 10] This figure shows another example of data exchange between a terminal device, a server, and an external server in a system according to one embodiment. [Figure 11] This figure shows yet another example of data exchange between a terminal device, a server, and an external server in a system according to one embodiment. [Figure 12] A block diagram showing the basic hardware configuration of Computer 90. [Modes for carrying out the invention]

[0010] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0011] Also, in the following description, a "processor" refers to one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but it may also be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

[0012] Also, at least one processor may be a processor in a broad sense, such as a hardware circuit (e.g., FPGA (Field-Programmable Gate Array) or ASIC (Application Specific Integrated Circuit)) that performs part or all of the processing.

[0013] Also, in the following description, an expression such as "xxx table" may be used to describe information from which an output is obtained for an input. This information may be data of any structure or a learning model such as a neural network that generates an output for an input. Therefore, "xxx table" can be referred to as "xxx information".

[0014] Also, in the following description, the configuration of each table is an example. One table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0015] Also, in the following description, when the processing is described with "program" as the subject, since the program is executed by a processor to perform the defined processing while appropriately using a storage unit and / or an interface unit, etc., the subject of the processing may be a processor (or a device such as a controller having that processor).

[0016] The program may be installed in a device such as a computer, or may be, for example, in a program distribution server or a computer-readable (e.g., non-transitory) recording medium. Also, in the following description, two or more programs may be implemented as one program, or one program may be implemented as two or more programs.

[0017] The functions realized by the components described in this specification may be implemented in circuitry or processing circuitry including a general-purpose processor, a specific-purpose processor, an integrated circuit, ASICs, a CPU, a conventional circuit, and / or a combination thereof, programmed to realize the described functions. The processor includes transistors and other circuits and is regarded as circuitry or processing circuitry. The processor may be a programmed processor that executes a program stored in a memory.

[0018] In this specification, circuitry, unit, and means are hardware programmed to realize the described functions or hardware that executes. The hardware may be any hardware disclosed in this specification or any hardware known as programmed or executing to realize the described functions.

[0019] When the hardware is a processor regarded as of the circuitry type, the circuitry, means, or unit is a combination of hardware and software used to configure the hardware and / or the processor.

[0020] Also, in the following description, an identification number is used as identification information for various objects, but identification information of other types (e.g., an identifier including letters and symbols) may be adopted.

[0021] Furthermore, in the following explanations, when describing similar elements without distinction, a reference code (or a common code among reference codes) may be used, and when describing similar elements with distinction, the element's identification number (or reference code) may be used.

[0022] Furthermore, in the following explanation, only control lines and information lines deemed necessary for the explanation are shown, and not all control lines and information lines in the product are necessarily shown. All components may be interconnected.

[0023] Each information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. For each of the terminal device 10 and the server 20, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0024] <0 System Overview> The following outlines the system relating to this disclosure. However, the following explanation should not be interpreted restrictively, and the content of this disclosure should be understood based on the disclosures herein and the ordinary technical knowledge and common sense of those skilled in the art.

[0025] The system described in this disclosure uses a Large Language Model (LLM), such as ChatGPT, to generate specific tasks that users are asked to execute. The system then presents these tasks to the user, retrieves the execution results of these tasks from the user, and links the specific tasks with their execution results.

[0026] The distinguishing feature of the system described in this disclosure is that it inputs user knowledge information into a large-scale language model and generates specific tasks associated with this knowledge information using the large-scale language model. An example of knowledge information is a user's purchase history. The system described in this disclosure links specific tasks, the results of those tasks, and the purchase history, etc. While it is possible to directly link specific tasks, the results of those tasks, and the purchase history, for example, it is also possible to first link specific tasks, the results of those tasks, etc., with a key for linking these specific tasks, etc., to the purchase history, and then later link the purchase history to specific tasks and the results of those tasks based on this key.

[0027] In the system related to this disclosure, the entity conducting the interview is assumed to be the store or other establishment where the user made a purchase. In this sense, the user is a customer to the entity conducting the interview. Therefore, in the following explanation, "user" and "customer" refer to the same subject, and no particular distinction will be made between the two terms. It should be noted, of course, that the entity conducting the interview is not limited to stores or other establishments.

[0028] The following description will focus on an embodiment in which a specific task is used as an interview question, and the result of performing that specific task is used as the answer to that interview question. Of course, it goes without saying that the specific task is not limited to being an interview question, nor is the result of performing that specific task limited to the answer to that interview question.

[0029] In the system relating to this disclosure, pre-defined questions that serve as the basis for generating interview questions are stored on the system's server, as described later. Preferably, multiple questions are stored, and the system selects one of the questions when generating interview questions using a large-scale language model. In this specification, "question" refers to what is actually presented to the user, and "pre-defined question" refers to the basis for generating the "question." By using the pre-defined question and the user's purchase history, etc., to generate questions using a large-scale language model, the questions generated by the large-scale language model become customized based on the user's behavioral history, etc., and therefore, the user's answers to the customized questions are more likely to be meaningful to the entity conducting the interview from a marketing perspective, etc.

[0030] In particular, the system relating to this disclosure generates additional questions (hereinafter referred to as "additional questions") based on user responses, using a large-scale language model. Preferably, the system pre-determines the direction of exploration for each individual question so that the additional questions delve deeper into the user's responses. Details of the direction of exploration will be described later.

[0031] By pre-determining the direction of in-depth questioning for each question, the direction of the interview can be controlled, and it is expected that more useful interview results can be obtained for the interviewer.

[0032] By having the above configuration, the system related to this disclosure will be able to convey the intent of the question to the user more accurately and increase the probability of obtaining an answer that matches that intent. For example, "Please tell us the reason for purchasing the product you recently bought" is less accurate than "Please tell us the reason for applying for optional service A that you recently applied for." Using expressions like "purchase" and "apply," which have essentially the same meaning but are not common sense, can confuse the user, and if possible, giving a specific name makes it clearer what the question is about.

[0033] Furthermore, it eliminates the need to manually create and distribute specific questions based on the respondent's criteria, and prevents the risk of misinterpreting the criteria and the provided links. Additionally, because questions can be created immediately after a user's action, the time lag between action and response is reduced, allowing for more accurate responses based on fresh memory. Moreover, it allows for double-checking to verify whether the action belongs to the individual, either explicitly or anonymously. For example, by examining the response to the question, "Please tell us which products you purchased on our website last month," it's possible to verify whether the purchase was for product A, which is a requirement for the survey target. (This allows for exclusion of individuals whose actions are not those of the actual participant, such as those involving account reuse.)

[0034] <One Embodiment> In the following embodiment, the user's purchase history is used as knowledge information about the user. Of course, the knowledge information is not limited to purchase history; for example, an interview system using the user's behavioral history (which stores, facilities, etc., the user visited) may also be used, and naturally, the system relating to this disclosure is not limited to System 1 of this embodiment.

[0035] <1 System Configuration Diagram> Figure 1 shows the overall configuration of the experimental results analysis system (hereinafter simply referred to as "the system") 1 of this embodiment. As shown in Figure 1, the system 1 includes a plurality of terminal devices (in Figure 1, terminal devices 10A and 10B are shown; hereinafter collectively referred to as "terminal device 10"), a server 20, and an external server 40. The terminal devices 10, server 20, and external server 40 are connected to each other so as to be able to communicate with each other via a network 80. The network 80 is composed of a wired or wireless network. In this embodiment, server 20 is a server that functions as a web server (including a cloud server) and exchanges information with terminal devices 10 via web pages. In addition, a web page browser for viewing web pages is installed on terminal devices 10, but a dedicated application for providing services from server 20 may be installed and configured to be viewable by the dedicated application.

[0036] Terminal device 10 is a device operated by a user registered with System 1 related to this disclosure. The user of terminal device 10 receives interview questions transmitted from server 20 and uses terminal device 10 to answer the interview questions. Terminal device 10 can be implemented as a stationary PC (Personal Computer), laptop PC, etc. Alternatively, terminal device 10 may be a mobile device such as a tablet compatible with a mobile communication system or a smartphone. Furthermore, terminal device 10 may be a fixed telephone, television receiver (TV), smart speaker, etc., that has communication functions such as the Internet.

[0037] The terminal device 10 is connected to the server 20 via the network 80 in a communicative manner. The terminal device 10 connects to the network 80 by communicating with communication equipment such as a wireless base station 81 that supports communication standards such as 4G, 5G, and LTE (Long Term Evolution), and a wireless LAN router 82 that supports wireless LAN (Local Area Network) standards such as IEEE (Institute of Electrical and Electronics Engineers) 802.11. As shown in Figure 2, the terminal device 10 includes a communication interface 12, an input device 13, an output device 14, a memory 15, a storage unit 16, and a processor 19.

[0038] The communication interface 12 is an interface for inputting and outputting signals so that the terminal device 10 can communicate with external devices. The input device 13 is an input device (for example, a keyboard, touch panel, touchpad, mouse, or other pointing device) for receiving input operations from the user. The output device 14 is an output device (display, speaker, etc.) for presenting information to the user. The memory 15 is for temporarily storing programs and data processed by programs, etc., and is a volatile memory such as DRAM (Dynamic Random Access Memory). The storage unit 16 is a storage device for saving data, such as flash memory or an HDD (Hard Disk Drive). The processor 19 is hardware for executing the instruction set written in the program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0039] Server 20 is managed by the administrator of System 1 in this embodiment, and the stored contents are modified, added, or deleted by this administrator as appropriate.

[0040] Server 20 is a computer connected to network 80. Server 20 includes a communication interface 22, an input / output interface 23, memory 25, storage 26, and a processor 29.

[0041] Communication IF22 is an interface for inputting and outputting signals so that the server 20 can communicate with external devices. Input / Output IF23 functions as an interface to an input device for receiving input operations from the user and an output device for presenting information to the user. Memory 25 is for temporarily storing programs and data processed by programs, etc., and is a volatile memory such as DRAM (Dynamic Random Access Memory). Storage 26 is a storage device for saving data, such as flash memory or HDD (Hard Disk Drive). Processor 29 is hardware for executing the instruction set written in the program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0042] The external server 40 is a separate computer from the terminal device 10 and server 20. This external server 40 stores a large language model (LLM), such as ChatGPT, and a chatbot unit that controls input and output from external devices to this large language model. While a detailed explanation of the large language model itself is omitted as it is publicly known, it is a deep learning model with millions to billions of parameters, pre-trained on a large corpus. Unlike models trained for specific tasks (such as sentiment analysis, named entity recognition, or mathematical reasoning), the large language model is a general-purpose model that excels at a wide range of tasks (see Wikipedia). The large language model may be fine-tuned to make it easier to obtain specific answers to specific questions. Furthermore, a technique called RAG (Retrieval-Augmented Generation), which combines answer generation by the large language model with retrieval of external information, may be employed to improve answer accuracy.

[0043] <1.1 Functional configuration of terminal device 10> Figure 2 is a block diagram showing an example of the functional configuration of the terminal device 10 shown in Figure 1. The terminal device 10 shown in Figure 2 can be implemented, for example, by a PC, a mobile terminal, or a wearable terminal. As shown in Figure 2, the terminal device 10 includes a first communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. Each block included in the terminal device 10 is electrically connected, for example, by a bus.

[0044] The first communication unit 120 performs modulation and demodulation processing for the terminal device 10 to communicate with other devices such as the server 20 and the external server 40. The first communication unit 120 performs transmission processing on the signal generated by the control unit 190 and transmits it to an external source (for example, the server 20). The first communication unit 120 performs reception processing on the signal received from an external source and outputs it to the control unit 190.

[0045] The input device 13 is a device for a user operating the terminal device 10 to input instructions or information. The input device 13 may be implemented as, for example, a keyboard, mouse, reader, etc. If the terminal device 10 is a mobile terminal, it may be implemented as a touch-sensitive device 131, etc., to which instructions are input by touching the operating surface. The input device 13 converts the instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that accepts electrical signals input from an external input device.

[0046] The output device 14 is a device for presenting information to the user operating the terminal device 10. The output device 14 is implemented, for example, by a display 141. The display 141 displays data according to the control of the control unit 190. The display 141 is implemented, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0047] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of the audio signal. The audio processing unit 17 converts the signal received from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is implemented, for example, by an audio processing processor. The microphone 171 receives an audio input and provides the audio signal corresponding to that audio input to the audio processing unit 17. The speaker 172 converts the audio signal received from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0048] The storage unit 180 stores data and programs used by the terminal device 10. For example, the storage unit 180 stores an application program 181 and user information 182.

[0049] User information 182 is information about the user who owns terminal device 10.

[0050] The control unit 190 is realized when the processor 19 reads the application program 181 stored in the storage unit 180 and executes the instructions contained in the application program 181. The control unit 190 controls the operation of the terminal device 10. By operating according to the application program 181 stored in the storage unit 180, the control unit 190 performs the functions of an input operation receiving unit 191, a transmitting / receiving unit 192, a data processing unit 193, and a presentation control unit 194.

[0051] The input operation receiving unit 191 processes instructions or information input from the input device 13. Specifically, for example, the input operation receiving unit 191 receives information based on instructions input from a keyboard, mouse, etc.

[0052] The transmitting / receiving unit 192 performs processing to enable the terminal device 10 to send and receive data with external devices such as the server 20 and the external server 40 in accordance with the communication protocol.

[0053] The data processing unit 193 performs calculations on the data received as input by the terminal device 10 according to the application program 181 and outputs the calculation results to the storage unit 180.

[0054] The presentation control unit 194 controls the output device 14 in order to present the information generated by the data processing unit 193 to the user. Specifically, for example, the presentation control unit 194 displays the information generated by the data processing unit 193 on the display 141. The presentation control unit 194 also outputs the information generated by the data processing unit 193 from the speaker 172.

[0055] <1.2 Functional Configuration of Server 20> Figure 3 shows an example of the functional configuration of server 20. As shown in Figure 3, server 20 functions as a communication unit 201, a storage unit 202, and a control unit 203.

[0056] The communications unit 201 performs processing to enable the server 20 to communicate with external devices.

[0057] The storage unit 202 stores data and programs used by the server 20. The storage unit 202 stores the user database (DB:DataBase) 2022, the question DB 2023, the prompt template 2024, the prompt data 2025, the answer DB 2026, etc.

[0058] User DB2022 is a database that stores information about users who are interviewed by System 1 in this embodiment. The users whose information is stored in User DB2022 are users registered by the operator of System 1. How the operator of System 1 recruits and registers users is not directly related to the content of System 1 in this embodiment, so no further explanation is given. Naturally, the possibility of users voluntarily registering with System 1 is not excluded.

[0059] Furthermore, the user information registered in the user DB2022 in System 1 of this embodiment includes information about the user's purchase history. There are no particular limitations on how information about the user's purchase history is obtained; for example, information about the user's purchase history can be obtained from clients who sell goods, etc. In particular, in System 1 of this embodiment, the entity conducting the interview is often a client who sells goods, etc., and therefore, it is expected that information about the purchase history will often be obtained from this client. Of course, the entity conducting the interview is not limited to clients who sell goods, etc., and in this case, information about the user's purchase history can be obtained by methods such as concluding a contract with the client who sells goods, etc. in advance. Details about User DB2022 will be described later.

[0060] Question DB2023 is a database that stores text and other information related to questions that form the basis of the interview questions conducted by System 1 of this embodiment. Here, "basis of questions" means that the interview questions actually presented to the user are obtained by inputting questions and the like into a large-scale language model stored in an external server 40, as described later. Although there is a direct relationship, the questions and the answers are not necessarily identical. A certain relationship can be established between the questions and the answers by inputting prompts into the large-scale language model. Conversely, from the viewpoint of saving effort in creating interview questions and generating more appropriate questions, the questions may be simpler in content than the actual questions.

[0061] In particular, as will be described later, in System 1 of this embodiment, information about the user's purchase history is input into a large-scale language model, and questions that reflect this purchase history are generated. Therefore, even if the questions are simplified and abstracted, appropriate questions can be generated.

[0062] In this embodiment, the question DB2023 stores, in addition to text and other information related to the questions, text and other information related to the direction of generating (additional) questions that are generated based on the answers received after presenting interview questions based on the questions to the user and obtaining the user's answers, all linked to each question. An example of such text and other information related to the direction of generating additional questions is text and other information related to the direction of in-depth questioning. An example of the direction of in-depth questioning is the reason why the points emphasized in previous questions are important elements for the respondent, or the background information and context of the content answered in previous questions. As will be described later, the direction of in-depth questioning will also be input into the large-scale language model, so there is no need to specify or mention the specific content of the in-depth questioning.

[0063] Textual information regarding the direction of generating additional questions is associated with at least one instance of this information for each question. In other words, multiple instances of textual information regarding the direction of generating additional questions may be stored for a single question. In the question DB2023 shown in Figure 5, which will be described later, only one instance of textual information regarding the direction of in-depth questioning is associated with each question, but only one is shown here for the sake of simplicity.

[0064] Furthermore, once answers to additional questions are obtained, text or other information regarding the direction of generating subsequent questions (third and beyond) based on these answers may be pre-configured in the Question DB2023. Moreover, the text and other information about additional questions stored in the Question DB2023 is not limited to text and other information regarding the direction of further investigation.

[0065] Multiple question databases (DB2023) may be provided for each interview conducted by system 1 of this embodiment. Details of question database 2023 will be described later.

[0066] Prompt template 2024 is data that serves as a template when the prompt generation module 2035 of the control unit 203 (described later) generates prompts to input to the large-scale language model (external server 40). The prompt generation module 2035 (described later) generates prompts to input to the large-scale language model based on this prompt template 2024.

[0067] Prompt data 2025 is prompt data generated by prompt generation module 2035.

[0068] The Answer DB2026 is a database that stores information about the answers users gave to interview questions. In the Answer DB2026, user identification information, interview questions, and identification information for the entire interview are linked to the user's answers and stored in the database. Further details about the Answer DB2026 will be described later.

[0069] The control unit 203 performs the functions shown in the various modules, namely the receive control module 2031, the transmit control module 2032, the user data acquisition module 2033, the question setting module 2034, the prompt generation module 2035, the model input / output module 2036, and the interview execution module 2037, by having the server 20's processor process according to the application program 2021 stored in the memory unit 202.

[0070] The receive control module 2031 controls the process by which the server 20 receives signals from external devices according to a communication protocol.

[0071] The transmission control module 2032 controls the process by which the server 20 transmits signals to external devices according to a communication protocol.

[0072] The user data acquisition module 2033 acquires data on the users to be interviewed. Specifically, the user data acquisition module 2033 acquires the user ID, user address, and purchase history information of the users to be interviewed from the user database 2022. Alternatively, the user data acquisition module 2033 acquires the user ID and user address of the users to be interviewed from the user database 2022 and acquires purchase history information of the users to be interviewed from an external server (not shown in the diagram). If the user data acquisition module 2033 acquires purchase history information from the external server, it stores the acquired purchase history information in the user database 2022. Note that the user address and user name are not required in the user database 2022.

[0073] The question setting module 2034 obtains from the question database 2023 a set of information, including text related to the questions that form the basis of the interview questions to be conducted, and text related to the text related to these questions that describes the direction of further questioning. In system 1 of this embodiment, the information obtained by the question setting module 2034 from the question database 2023, including text related to the questions that form the basis of the interview questions to be conducted, is a set of information about a series of questions to the user (i.e., all questions planned for the user). As will be described later, the prompt generation module 2035 generates prompts based on the information obtained by the question setting module 2034.

[0074] Examples of information acquired by the question setting module 2034 include a request to the large-scale language model on the external server 40, interview rules, an introductory text and a series of questions (which may be multiple questions) as part of the interview flow, and an introductory text indicating the end of the questioning. Each question includes directions for further exploration of that question. However, if multiple questions are presented to the user in a single interview, the question setting module 2034 may acquire a set of information, such as text, related to the questions that form the basis of the interview questions conducted each time.

[0075] The prompt generation module 2035 generates prompt data 2025 to be input into the large-scale language model of the external server 40, based on information acquired by the question setting module 2034, namely, text information related to the questions that form the basis of the interview questions to be conducted, text information related to the direction of further investigation linked to the text information related to these questions, the prompt template 2024 stored in the memory unit 202, and information on the purchase history of the user who is the subject of the interview questions, stored in the user DB 2022. An example of prompt data generated by the prompt generation module 2035 will be described later. In addition, if the prompt generation module 2035 receives an answer from the user to an interview question, it also uses text information related to this answer to generate prompt data 2025. At this time, the prompt generation module 2035 adds (writes) the content of the conversation with the user currently being interviewed, namely the question and the answer to this question, to the prompt already generated by the prompt generation module 2035, and generates prompt data 2025 to be input into the large-scale language model of the external server 40. The prompt generation module 2035 adds the question and its answer to the prompt already generated by the prompt generation module 2035 because, in an interview system that asks dynamic, in-depth questions as in this embodiment, the content of the question itself cannot be predicted in advance. Therefore, if only the answer is input without the question, the large-scale language model will not understand what the conversation is about and is unlikely to be able to generate the continuation successfully. By adding the question and answer to the prompt, the large-scale language model can generate an appropriate question that does not feel out of place in relation to the content of the interview up to that point (questions and answers). The prompt generation module 2035 stores the prompt data 2025 that it has generated in the storage unit 202. However, regarding the content of the conversation with the user, in addition to adding the entire text, a summary, an excerpt of a part, or a combination thereof may be used.

[0076] The model input / output module 2036 inputs the prompt data 2025 generated by the prompt generation module 2035 into the large-scale language model on the external server 40, causing the large-scale language model to generate and retrieve interview questions for the user. In this case, the model input / output module 2036 may directly input the prompt data into the large-scale language model, or it may prepare an API (Application Program Interface) in advance and input the prompt data into the large-scale language model via this API. After obtaining the interview questions for the user, which are the output from the large-scale language model, the model input / output module 2036 stores these questions in the answer DB 2026 of the storage unit 202.

[0077] The interview execution module 2037 retrieves the user address of the user to be interviewed from the user DB 2022, based on the data acquired by the user data acquisition module 2033. It then sends the interview questions acquired by the model input / output module 2036 to this user address and receives the user's answers to these questions. Finally, the interview execution module 2037 stores the questions to the user and the answers to these questions in the answer DB 2026.

[0078] In this process, the interview execution module 2037 generates a web page on the server 20 for sending and receiving interview questions and answers, and requests the user being interviewed to access this web page. When a user accesses the web page, they make a request to access the server 20, and the interview execution module 2037 obtains the parameter information of this request. Since the parameter information can be used as identification information to identify the user, the interview execution module 2037 stores this parameter information in the response DB 2026. Examples of request information include the unique URL assigned to the user, the parameters of the web page, and the referrer, which is information about the web page the user was on immediately before visiting the web page. By identifying the user using the parameter information of the request, it is possible to identify and specify the user who answered the interview using a simple procedure.

[0079] The interview execution module 2037 sends a set of questions to the same user, consisting of a question generated based on the given question and an (additional) question generated based on the direction of further exploration linked to the question, based on the user's response to the given question. The interview execution module 2037 may also perform multiple cycles of sending and receiving these sets of questions to the same user. Furthermore, the interview execution module 2037 may perform the interview only for a predetermined number of times (cycles). After conducting a series of cycles of interviews, the interview execution module 2037 terminates the interview. The timing of termination may be based on instructions from the large-scale language model of the external server 40.

[0080] Figures 9 to 11 show an example of data exchange between server 20 and external server 40. The data shown in Figures 9 to 11 includes the question set by the question setting module 2034, the prompt data 2025 generated by the prompt generation module 2035, the prompt data 2025 input by the model input / output module 2036 to the large-scale language model on external server 40, the interview questions generated by the large-scale language model, and the questions sent by the interview execution module 2037 and the answers from the user.

[0081] In the examples shown in Figures 9 to 11, the user's purchase history uses purchase history of an item purchased as a Mother's Day gift at a specific store. The interview questions asked about the relationship between the user and the recipient of the gift (wife, mother, or someone else), and, as a way to delve deeper, about the reason and timing for giving the gift. In response to these questions, the user answered that the gift was for his mother-in-law and that he purchased it because he gives her a gift every year.

[0082] <2 Data Structure> Figures 4 to 6 show the data structure of the database stored by server 20. Note that Figures 4 to 6 are examples and do not exclude data not shown. Furthermore, even data listed in the same table may be stored in separate memory areas within the storage unit 202.

[0083] The databases shown in Figures 4 to 6 refer to relational databases, which are used to manage data sets called tables, which are structurally defined by rows and columns, and to associate them with each other. In a database, tables are called tables, the columns of a table are called columns, and the rows of a table are called records. In a relational database, relationships can be established and linked between tables.

[0084] Typically, each table has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit 203 of the server 20 can instruct the processor 29 to add, delete, or update records in specific tables stored in the storage unit 202, according to various programs.

[0085] Figure 4 shows an example of the data structure of the user DB 2022 stored in the storage unit 202 of the server 20. As shown in Figure 4, each record in the user DB 2022 includes, for example, the fields "User ID", "User Name", "User Address", and "Purchase History". Each field in the user DB 2022 is pre-stored by the administrator of system 1 in this embodiment. In addition, the "Purchase History" field may be acquired and stored by the user data acquisition module 2033 from an external server or the like. The information stored in the user DB 2022 can be changed and updated as needed.

[0086] The item "User ID" is identification information (ID) used to identify the user who is the subject of the interview in System 1 of this embodiment. The item "User Name" is information about the name of the user identified by the item "User ID". The item "User Address" is information about the user address of the user identified by the item "User ID", and is information about the user's contact information in System 1 of this embodiment. The item "Purchase History" is information about the purchase history of the user identified by the item "User ID".

[0087] Figure 5 shows an example of the data structure of the question database 2023 stored in the storage unit 202 of the server 20. As shown in Figure 5, each record in the question database 2023 includes, for example, the item "Question ID", the item "Question", and the item "Direction of In-Depth Exploration". Each item in the question database 2023 is pre-stored by the administrator of system 1 in this embodiment. The information stored in the question database 2023 can be changed and updated as needed.

[0088] The item "Question ID" is an identifier (ID) used to identify a question. The item "Question" is text or other information related to the question identified by the item "Question ID". The item "Direction of Further Exploration" is text or other information that describes the direction of further exploration, linked to the question identified by the item "Question ID".

[0089] Figure 6 shows an example of the data structure of the response DB 2026 stored in the storage unit 202 of the server 20. As shown in Figure 6, each record in the response DB 2026 includes, for example, the items "Interview ID", "Date and Time", "User ID", "Parameter Information", "Question", and "Answer". Each item in the response DB 2026 stores information about each item when the interview implementation module 2037 of this embodiment conducts an interview with a user. The information stored in the response DB 2026 can be changed and updated as needed.

[0090] The item "Interview ID" is an identification information (ID) used to identify a set of questions sent by the interview execution module 2037 to a specific user, and the receipt of answers to those questions, as one cycle, as a single interview. The item "Implementation Date and Time" is information indicating the date and time when the interview identified by the item "Interview ID" began. The item "User ID" is identification information used to identify the user who is the subject of the interview identified by the item "Interview ID," and is the same as the item "User ID" in the user DB 2022 in Figure 4. The item "Parameter Information" is parameter information of the request information to server 20 when the user accesses server 20 in the interview identified by the item "Interview ID." The item "Question" is information such as text indicating the question used in the interview identified by the item "Interview ID." In system 1 of this embodiment, multiple questions may be used in one interview (one cycle), so multiple questions may be associated with one interview ID. The item "Answer" is information such as text indicating the user's answer to the item "Question."

[0091] <3 Example of Operation> The following describes an example of the operation of server 20 and terminal device 10.

[0092] Figure 7 is a diagram illustrating an example of the operation of the terminal device 10 and the server 20 when conducting an interview with a specific user in System 1 of this embodiment.

[0093] First, in step S750, the control unit 203 of the server 20 selects the user to be interviewed. Specifically, for example, the user data acquisition module 2033 of the control unit 203 refers to the user DB 2022 to select the user to be interviewed and acquires user information for the selected user from the user DB 2022.

[0094] Next, in step S751, the control unit 203 of the server 20 retrieves information about the purchase history of the user selected in step S750 from the user database 2022. Specifically, for example, the user data acquisition module 2033 of the control unit 203 retrieves information about the purchase history of the user selected in step S750 from the user database 2022. If the purchase history of the selected user is not stored in the user database 2022, the user data acquisition module 2033 retrieves information about the purchase history of the selected user from an external server.

[0095] Next, in step S752, the control unit 203 of the server 20 creates a message requesting the user selected in step S750 to answer the interview questions, and sends this message to the selected user. Specifically, for example, the interview execution module 2037 of the control unit 203 creates a message requesting the user selected in step S750 to answer the interview questions, and sends this message to the selected user.

[0096] In step S700, the user who receives the interview response request message from the server 20 receives this message on the terminal device 10 owned by the user. Then, in step S701, the user on the terminal device 10 inputs an interview start command via the input device 13, and the transmitting / receiving unit 192 of the terminal device 10 transmits the start command input to the server 20.

[0097] In step S752, the control unit 203 of the server 20, which has received a start command input from the terminal device 10, generates prompt data 2025 to be input to the large-scale language model of the external server 40. Specifically, for example, the prompt generation module 2035 of the control unit 203 generates prompt data 2025 to be input to the large-scale language model of the external server 40. Subsequently, the model input / output module 2036 inputs the prompt data 2025 generated by the prompt generation module 2035 in step S752 to the large-scale language model of the external server 40, causing this large-scale language model to generate a question for the user and to acquire this question. The interview execution module 2037 sends the acquired question to the terminal device 10.

[0098] Moving on to Figure 8, in step S800, the transmitting / receiving unit 192 of the terminal device 10 receives the interview questions sent from the server 20, and in step S801, the user of the terminal device 10 inputs answers to the interview questions via the input device 13, and the transmitting / receiving unit 192 of the terminal device 10 transmits the input answers to the server 20.

[0099] Subsequently, in steps S850, S802, and S803, the server 20 and terminal device 10 perform the same operations as in steps S752, S800, and S801. In step S851, it is determined whether the question and answer cycle has been performed a predetermined number of times. If it is determined that the cycle has been performed a predetermined number of times (YES in step S851), the program shown in Figure 8 is terminated. If it is determined that the cycle has not yet been performed a predetermined number of times (NO in step S851), the process returns to step S752 and continues.

[0100] <4 Summary> As described in detail above, according to System 1 of this embodiment, interview questions are generated by a large-scale language model on an external server 40 using the user's purchase history. Therefore, the interview questions presented to the user can be customized based on the user's purchase history, thereby making the analysis based on the user's answers more appropriate.

[0101] Furthermore, according to System 1 of this embodiment, since the direction of in-depth questioning is linked to the basic question, the content is enriched to match the design intent of the interview, in light of the purpose of utilizing the user's interview responses, and it is easy to control the topic so that it does not veer too far into irrelevant content. From this perspective as well, it is possible to make the analysis based on the user's responses more appropriate.

[0102] <5 Variations> The embodiments described above are detailed explanations of the configuration in order to make this disclosure easier to understand, and are not necessarily limited to those comprising all the configurations described. Furthermore, some of the configurations of each embodiment can be added to, deleted from, or replaced with other configurations.

[0103] As an example, in the system 1 of the embodiment described above, the large-scale language model was located on an external server 40, but if resources allow, the large-scale language model may be located within server 20.

[0104] Furthermore, in System 1 of the embodiment described above, interview questions and answers to these questions were conducted in text format, but questions and answers may also be provided in formats other than text. For example, questions and instructions may be presented to the user using audio, images, or videos, and the user's answers may also be provided by methods such as the user drawing a picture, selecting an image, or recording a video and uploading it. Thus, in the system relating to this disclosure, the user is asked to perform a specific task, and the user only needs to present the results of performing the requested task.

[0105] Furthermore, in the system 1 of the above-described embodiment, it is also possible to comprehensively create prompts in advance, issue a large number of URLs to users, and send them separately to each user segment.

[0106] Furthermore, in the system related to this disclosure, users are not limited to customers, but may include employees, pre-contracted monitors, or any other group of people who are asked to perform specific tasks.

[0107] Furthermore, in the system relating to this disclosure, the method for presenting a specific task to a user and obtaining the results of that task from the user is not limited to web chat or survey formats, as in System 1 of one embodiment. It is also possible to use external media such as messages on social networking services (SNS) represented by LINE, or methods such as making phone calls using machine voice or having an avatar respond in a web conference. When a specific task is presented via SNS and the results of that task are obtained via SNS, at least the results may be stored on the server of the company providing the SNS. Therefore, it is preferable for the operator of the system relating to this disclosure to be able to access the results stored on the server of this company.

[0108] Furthermore, in the system 1 of the embodiment described above, interviews are conducted considering the user's purchase history, so the questions and answers stored in the answer DB2026 can be considered to have a certain degree of appeal to the products covered by that purchase history. Therefore, in the system 1 of the embodiment, it is also possible to refer to the questions and answers of another user who purchased the same product as the user currently being interviewed, select questions and answers that will serve as persuasive messages to encourage that user to purchase the product, and present them to the user.

[0109] <6.1 Basic Hardware Configuration of a Computer> Figure 12 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 includes at least a processor 901, main memory 902, auxiliary memory 903, and a communication interface IF991. These are electrically connected to each other by a communication bus 921.

[0110] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0111] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0112] Auxiliary storage device 903 refers to a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0113] The IF991 communication interface is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards.

[0114] A network consists of various mobile communication systems, such as the internet, LANs, and wireless base stations. For example, a network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network also includes connections made directly via USB (Universal Serial Bus) cables, etc.

[0115] Furthermore, by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network, a computer 90 can be virtually realized. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure or case, but also a virtualized computer system.

[0116] <6.2 Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of computer 90 (Figure 12) will be explained. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0117] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0118] The control unit is realized when the processor 901 reads various programs stored in the auxiliary storage device 903, loads them into the main memory device 902, and executes processing according to those programs. The control unit can realize various functional units that perform information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0119] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0120] A database, specifically a relational database, is used to manage and link together tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters.

[0121] Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs.

[0122] Furthermore, by storing data, various programs, and various databases in the memory unit, the information processing device and information processing system related to this disclosure can be considered to have been manufactured.

[0123] Furthermore, the databases and masters in this disclosure may include any data structures (lists, dictionaries, associative arrays, objects, etc.) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc., written in any programming language.

[0124] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0125] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.

[0126] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, and Java (registered trademark).

[0127] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.

[0128] The functions realized by the components described herein may be implemented in a circuit or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the functions described herein. A processor is considered to be a circuit or processing circuitry, including transistors and other circuits. A processor may be a programmed processor that executes a program stored in memory.

[0129] In this specification, circuitry, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein.

[0130] If the hardware is a processor that is considered to be a type of circuitry, then the circuitry, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0131] While several embodiments of this disclosure have been described above, these embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications are permitted without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents.

[0132] (Note) The details described in each of the above embodiments are noted below. (Note 1) A program for operating a computer comprising a processor and memory, the program causing the processor to perform the following steps: a first step of acquiring knowledge information about a user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented on a computer different from the computer, and causing the large-scale language model to generate and acquire a specific task to be requested from the user to perform; a third step of presenting the specific task acquired in the second step to the user and obtaining the result of executing this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the result of executing the specific task acquired in the third step, and the knowledge information input into the large-scale language model in the second step. (Note 2) A program for operating a computer comprising a processor and memory, the program causing the processor to perform the following steps: a first step of acquiring knowledge information about a user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented in the computer, and causing the large-scale language model to generate and acquire a specific task to be requested from the user to perform; a third step of presenting the specific task acquired in the second step to the user and obtaining the result of executing this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the result of executing the specific task acquired in the third step, and the knowledge information input into the large-scale language model in the second step. (Note 3) Knowledge information is the user's purchase history, as described in Appendix 1 or 2. (Note 4) In the fourth step, the program described in Appendix 1 or 2 stores in memory the results of the execution of a specific task obtained in the second step and the knowledge information input into the large-scale language model in the second step, linking them together. (Note 5) The program described in Appendix 1 or 2, in which a specific task is an interview question, and the result of performing a specific task is the answer to that interview question. (Note 6) The program described in Appendix 5 has one or more interview questions to be presented to the user pre-stored in memory, and in the second step, generates questions using the questions and knowledge information stored in memory. (Note 7) The program, as described in Appendix 6, has memory containing at least one piece of data associated with an interview question, which, after obtaining the user's response to the question using the question, generates at least one additional question related to the question; the program executes a fifth step in which, after obtaining the user's response to the question in the third step, the program inputs the data stored in memory, at least a part of the response, and at least a part of the question into a large language model, and obtains at least one additional question from the large language model; and in the third step, presents the additional question generated in the fifth step to the user and obtains the user's response to the additional question. (Note 8) The program, as described in Appendix 7, has the processor execute step 5 multiple times to generate and obtain additional questions multiple times, and in step 3, obtains the answers to each of the additional questions presented to the user multiple times. (Note 9) The program, as described in Appendix 1 or 2, stores prompt data in memory that instructs a large-scale language model to generate questions, and in the second step, inputs the prompt data and knowledge information stored in memory into the large-scale language model, causing the large-scale language model to generate and retrieve interview questions for the user. (Note 10) An information processing device comprising a processor and memory, wherein the processor performs the following steps: a first step of acquiring knowledge information about a user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented on a computer different from the computer, and generating and acquiring a specific task from the large-scale language model to request the user to perform; a third step of presenting the specific task acquired in the second step to the user and obtaining the result of executing this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the result of executing the specific task acquired in the third step, and the knowledge information input into the large-scale language model in the second step. (Note 11) An information processing device comprising a processor and memory, wherein the processor performs the following steps: a first step of acquiring knowledge information about a user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented on a computer, and generating and acquiring a specific task from the large-scale language model to be requested to be performed by the user; a third step of presenting the specific task acquired in the second step to the user and obtaining the result of executing this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the result of executing the specific task acquired in the third step, and the knowledge information input into the large-scale language model in the second step. (Note 12) A method performed by a computer having a processor and memory, wherein the processor performs the following steps: a first step of acquiring knowledge information about a user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented on a computer different from the computer, and obtaining from the large-scale language model a specific task to be requested to be performed by the user; a third step of presenting the specific task obtained in the second step to the user and obtaining the result of executing this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the result of executing the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. (Note 13) A method performed by a computer having a processor and memory, wherein the processor performs the following steps: a first step of acquiring knowledge information about a user; a second step of inputting at least a portion of the knowledge information acquired in the first step into a large-scale language model implemented in the computer, and obtaining from the large-scale language model a specific task to be requested to be performed by the user; a third step of presenting the specific task obtained in the second step to the user and obtaining the result of performing this specific task from the user; and a fourth step of associating the specific task acquired in the second step, the result of performing the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. (Note 14) A system comprising: means for acquiring knowledge information about a user; means for inputting at least a portion of the knowledge information acquired by the knowledge information acquisition means into a large-scale language model implemented on a computer different from the computer, and for generating and acquiring a specific task from the large-scale language model to request the user to perform; means for presenting the specific task acquired by the means for generating and acquiring the specific task to the user, and for obtaining the execution result of this specific task from the user; and means for associating a question acquired by the means for generating and acquiring the specific task, the execution result of the specific task acquired by the means for obtaining the execution result of the specific task, and the knowledge information input by the means for generating the specific task into the large-scale language model. (Note 15) A system comprising: means for acquiring knowledge information about a user; means for inputting at least a portion of the knowledge information acquired by the knowledge information acquisition means into a large-scale language model, and for generating and acquiring a specific task from the large-scale language model to request the user to perform; means for presenting the specific task acquired by the means for generating and acquiring the specific task to the user, and for obtaining the execution result of this specific task from the user; and means for associating the specific task acquired by the means for generating and acquiring the specific task, the execution result of the specific task acquired by the means for obtaining the execution result of the specific task, and the knowledge information input by the means for generating the specific task into the large-scale language model. [Explanation of Symbols]

[0133] 1: System, 10: Terminal device, 20: Server, 25: Memory, 26: Storage, 29: Processor, 2021: Application program, 2022: User DB, 2023: Question DB, 2024: Prompt template, 2025: Prompt data, 2026: Answer DB, 2033: User data acceptance module, 2034: Question setting module, 2035: Prompt generation module, 2036: Model input / output module, 2037: Interview execution module

Claims

1. A program for operating a computer that includes a processor and memory, The program is provided to the processor: The first step is to acquire knowledge information about the user, A second step involves inputting at least a portion of the knowledge information obtained in the first step into a large-scale language model implemented on a computer different from the computer, and obtaining a specific task from the large-scale language model that is requested to be performed by the user. A third step involves presenting the specific task obtained in the second step to the user and obtaining the execution result of this specific task from the user. A fourth step involves associating the specific task obtained in the second step, the execution result of the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. A program that executes something.

2. A program for operating a computer that includes a processor and memory, The program is provided to the processor: The first step is to acquire knowledge information about the user, A second step involves inputting at least a portion of the knowledge information obtained in the first step into a large-scale language model implemented on the computer, and obtaining a specific task from the large-scale language model that is requested to be performed by the user. A third step involves presenting the specific task obtained in the second step to the user and obtaining the execution result of this specific task from the user. A fourth step involves associating the specific task obtained in the second step, the execution result of the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. A program that executes something.

3. The program according to claim 1 or 2, wherein the knowledge information is the user's purchase history.

4. The program according to claim 1 or 2, wherein in the fourth step, the program associates the specific task obtained in the second step, the execution result of the specific task obtained in the third step, and the knowledge information input to the large-scale language model in the second step and stores them in the memory.

5. The program according to claim 1 or 2, wherein the specific task is an interview question, and the result of performing the specific task is an answer to the interview question.

6. The memory contains one or more questions from a series of interviews to be presented to the user. In the second step, the question is generated using the question and the knowledge information stored in the memory. The program according to claim 5.

7. The memory stores at least one piece of data associated with the interview question, which, after obtaining the user's response to the question using the interview question, generates at least one additional question related to the interview question. The program further provides the processor with: In the third step, after obtaining the user's answer to the question, the fifth step is performed in which the data stored in the memory, at least a part of the answer, and at least a part of the question are input into the large-scale language model, and at least one additional question is generated and obtained from the large-scale language model. In the third step, the additional questions generated in the fifth step are presented to the user, and the user's answers to the additional questions are obtained. The program according to claim 6.

8. The program according to claim 7, wherein the program causes the processor to execute the fifth step multiple times to generate and obtain the additional questions multiple times, and in the third step, obtains the answers to the additional questions that have been presented to the user multiple times.

9. The memory stores prompt data that instructs the large-scale language model to generate the question. In the second step, the prompt data and knowledge information stored in the memory are input to the large-scale language model, and interview questions for the user are generated and obtained from the large-scale language model. The program according to claim 5.

10. An information processing device comprising a processor and memory, The aforementioned processor, The first step is to acquire knowledge information about the user, The second step involves inputting at least a portion of the knowledge information obtained in the first step into a large-scale language model implemented in an information processing device different from the information processing device, and generating and obtaining a specific task from the large-scale language model to be requested to be executed by the user. A third step involves presenting the specific task obtained in the second step to the user and obtaining the execution result of this specific task from the user. A fourth step involves associating the specific task obtained in the second step, the execution result of the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. An information processing device that performs this task.

11. An information processing device comprising a processor and memory, The aforementioned processor, The first step is to acquire knowledge information about the user, A second step involves inputting at least a portion of the knowledge information obtained in the first step into a large-scale language model implemented in the information processing device, and generating and obtaining a specific task from the large-scale language model to be requested to be executed by the user. A third step involves presenting the specific task obtained in the second step to the user and obtaining the execution result of this specific task from the user. A fourth step involves associating the specific task obtained in the second step, the execution result of the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. An information processing device that performs this task.

12. A method performed by a computer comprising a processor and memory, The aforementioned processor, The first step is to acquire knowledge information about the user, A second step involves inputting at least a portion of the knowledge information obtained in the first step into a large-scale language model implemented on a computer different from the computer, and generating and obtaining a specific task from the large-scale language model to be requested to be performed by the user. A third step involves presenting the specific task obtained in the second step to the user and obtaining the execution result of this specific task from the user. A fourth step involves associating the specific task obtained in the second step, the execution result of the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. How to do it.

13. A method performed by a computer comprising a processor and memory, The aforementioned processor, The first step is to acquire knowledge information about the user, A second step involves inputting at least a portion of the knowledge information obtained in the first step into a large-scale language model implemented on the computer, and obtaining a specific task from the large-scale language model that is requested to be performed by the user. A third step involves presenting the specific task obtained in the second step to the user and obtaining the execution result of this specific task from the user. A fourth step involves associating the specific task obtained in the second step, the execution result of the specific task obtained in the third step, and the knowledge information input into the large-scale language model in the second step. How to do it.

14. It is a system, Means for acquiring knowledge information about users, A means for inputting at least a portion of the knowledge information obtained by the means for acquiring the knowledge information into a large-scale language model implemented in a system different from the system, and obtaining a means for generating and obtaining a specific task to be requested to be executed by the user from the large-scale language model, Means for generating and obtaining the aforementioned specific task, presenting the obtained specific task to the user, and obtaining the execution result of this specific task from the user, Means for associating the specific task obtained by means for generating and obtaining the specific task, the execution result of the specific task obtained by means for obtaining the execution result of the specific task, and the knowledge information input into the large-scale language model by means for generating the specific task. A system that has

15. Means for acquiring knowledge information about users, Means for inputting at least a portion of the knowledge information obtained by the means for acquiring the knowledge information into a large-scale language model, and for generating and obtaining a specific task from the large-scale language model to be requested to be performed by the user, Means for generating and obtaining the aforementioned specific task, presenting the obtained specific task to the user, and obtaining the execution result of this specific task from the user, Means for associating the specific task obtained by means for generating and obtaining the specific task, the execution result of the specific task obtained by means for obtaining the execution result of the specific task, and the knowledge information input into the large-scale language model by means for generating the specific task. A system that has

Images