Program, method, device and system

Abstract

To efficiently and multifacetedly extract information from a conversation partner on a given question topic. [Solution] The program causes a processor to execute the following steps: an item generation step in which a generation AI generates multiple items belonging to a predetermined question theme based on the theme; a question generation step in which the generation AI generates questions to obtain answers from the dialogue partner for items among the multiple items for which the dialogue partner has not yet answered, based on the dialogue partner's answers and the multiple items generated by the generation AI; and a question presentation step in which the questions generated by the generation AI are presented to the dialogue partner.

Description

[Technical Field]

[0001] The present disclosure relates to programs, methods, devices and systems. [Background technology]

[0002] Patent Document 1 describes a method for conducting online question and answer sessions with applicants during job interviews at companies. Patent Document 1 describes that if a first reply sent from an applicant terminal does not satisfy the conditions set by the company for a first question topic to which the first message belongs, a second message generated in response to the first reply is a message that asks an additional question about the first question topic. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2025-077486 Summary of the Invention [Problem to be solved by the invention]

[0004] Patent Document 1 describes that follow-up questions may be questions to obtain more details about the first reply. However, Patent Document 1 does not sufficiently disclose how to ask for more detailed information, making it impossible to efficiently dig deeper into information about the applicant. This is not limited to job interviews, but applies to any dialogue that includes questions to elicit answers from the other party.

[0005] The purpose of this disclosure is to efficiently and multifacetedly extract information from a conversation partner in a dialogue using generative AI. [Means for solving the problem]

[0006] In order to solve the above problem, one aspect of the program disclosed herein is a program for operating a computer having a processor and a memory, and the program causes the processor to execute the following steps: an item generation step of causing a generation AI to generate multiple items belonging to a predetermined question theme based on the question theme; a question generation step of causing the generation AI to generate questions to obtain answers from the dialogue partner for items among the multiple items for which the dialogue partner has not yet answered, based on the dialogue partner's answer and the multiple items generated by the generation AI; and a question presentation step of presenting the questions generated by the generation AI to the dialogue partner. [Effects of the Invention]

[0007] According to the present disclosure, in a dialogue using generative AI, it is possible to extract information from a dialogue partner efficiently and multifacetedly. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram showing the overall configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the applicant's terminal device. [Figure 3] FIG. 3 is a block diagram showing the functional configuration of the server. [Figure 4] FIG. 4 is a diagram showing the data structure of the applicant table. [Figure 5] FIG. 5 is a diagram showing the data structure of the question theme table. [Figure 6] FIG. 6 is a diagram showing the data structure of the item table. [Figure 7] FIG. 7 is a diagram showing the data structure of the question and answer table. [Figure 8] FIG. 8 is a diagram showing the data structure of the interview session table. [Figure 9] FIG. 9 is a diagram showing the data structure of the evaluation table. [Figure 10]FIG. 10 is a diagram for explaining the setting process in the system. [Figure 11] FIG. 11 is a diagram illustrating an example of an item generation prompt input from the server to the generation AI. [Figure 12] FIG. 12 is a diagram for explaining the interview process in the system. [Figure 13] FIG. 13 is a diagram for explaining the process following FIG. [Figure 14] FIG. 14 is a diagram illustrating a question generation prompt input from the server to the generation AI. [Figure 15] FIG. 15 is a diagram illustrating a correspondence item extraction prompt input from the server to the generation AI. [Figure 16] FIG. 16 is a flowchart of the first interview progress control. [Figure 17] FIG. 17 is a flowchart of the second interview progress control. [Figure 18] FIG. 18 is a diagram illustrating an example of a setting screen on the administrator's terminal device. [Figure 19] FIG. 19 is a diagram showing an example of an interview screen on the applicant's terminal device. [Figure 20] FIG. 20 is a diagram illustrating an example of an analysis screen on the administrator's terminal device. [Figure 21] FIG. 21 is a diagram for explaining the process of the modified example, which corresponds to FIG. [Figure 22] FIG. 22 is a block diagram showing the basic hardware configuration of a computer. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated description will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.

[0010] In the following description, a "processor" refers to one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). The at least one processor may be single-core or multi-core.

[0011] Furthermore, the at least one processor may be a processor in the broad sense, such as a hardware circuit (for example, a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC)) that performs part or all of the processing.

[0012] In the following explanation, information that produces an output for an input may be described using expressions such as "xxx table," but this information may be data of any structure, or may be a learning model such as a neural network that produces an output for an input. Therefore, an "xxx table" may be referred to as "xxx information."

[0013] Furthermore, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0014] In addition, in the following explanation, processing may be described using the "program" as the subject, but since a program is executed by a processor to perform specified processing while appropriately using a memory unit and / or an interface unit, etc., the subject of the processing may also be the processor (or a device such as a controller that has that processor).

[0015] The program may be installed in a device such as a computer, or may be stored in, for example, 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 realized as one program, or one program may be realized as two or more programs.

[0016] Furthermore, in the following description, identification numbers are used as identification information for various objects, but other types of identification information (for example, identifiers including alphabetic characters or symbols) may also be used.

[0017] In addition, in the following description, when describing elements of the same type without distinguishing between them, reference symbols (or common symbols among the reference symbols) may be used, and when describing elements of the same type with distinction between them, the identification numbers (or reference symbols) of the elements may be used.

[0018] In the following description, the control lines and information lines are those that are considered necessary for the description, and do not necessarily represent all the control lines and information lines in the product. All components may be interconnected.

[0019] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the terminal device 10, the server 20, and the terminal device 40, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0020] <Summary> An example of an information processing system according to this embodiment is a system that utilizes a generation AI to conduct online interviews for recruiting personnel for an organization such as a company. The generation AI generates multiple items related to a question theme for an applicant, and based on the applicant's answers and the multiple items generated by the generation AI, generates questions for items for which the applicant has not yet answered, and presents the generated questions to the applicant. This allows for efficient and multifaceted elicitation of information from the applicant about the specified question theme.

[0021] <1. Overall system configuration> Fig. 1 is a block diagram illustrating the configuration of an information processing system 1 according to an embodiment. As shown in Fig. 1, the information processing system 1 includes a first terminal device 10 operated by an applicant, a server 20, a generation AI system 30, and a second terminal device 40 operated by an administrator. The first terminal device 10, the server 20, the generation AI system 30, and the second terminal device 40 are connected to each other so as to be able to communicate with each other via a communication network N such as the Internet or a LAN (Local Area Network).

[0022] For simplicity of illustration, FIG. 1 shows an example in which the system 1 includes one terminal device 10, but this is not limited thereto, and in reality, the system may include multiple terminal devices 10 for use by multiple applicants. Similarly, the server 20, the generation AI system 30, and the terminal device 40 may each be configured as a single device or as a collection of multiple devices. For example, the multiple functions required to realize the server 20 may be distributed to one or multiple physical servers depending on the processing capabilities of each hardware.

[0023] The terminal device 10 is a device used by an applicant who applies for a job at an organization, and is an information processing device operated by the applicant. The terminal device 10 is realized by, for example, a mobile terminal such as a smartphone or a tablet, a stationary personal computer (PC), or a laptop PC.

[0024] The terminal device 10 is realized by a computer including hardware such as a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage 16, and a processor 19. The communication IF 12 is an interface for inputting and outputting signals so that the terminal device 10 can communicate with devices in the system 1, such as the server 20. The input device 13 is a device for accepting input operations from a user (e.g., a touch panel, a touchpad, a pointing device such as a mouse, a keyboard, etc.). The output device 14 is a device for presenting information to a user (e.g., a display, a speaker, etc.). The memory 15 is for temporarily storing programs and data processed by the programs, etc., and is, for example, a volatile memory such as a DRAM. The storage 16 is for saving data, and is, for example, a flash memory, a hard disk drive, etc. The processor 19 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0025] The server 20 conducts online job interviews by transmitting and receiving information to and from the terminal device 10. The server 20 is realized by a computer including hardware such as a communication IF (Interface) 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29.

[0026] The communication IF 22 is an interface for inputting and outputting signals so that the server 20 can communicate with devices in the system 1, such as the terminal device 10. The input / output IF 23 functions as an interface with an input device for accepting input operations from a user and an output device for outputting information to the user. The memory 25 is for temporarily storing programs and data processed by the programs, etc., and is, for example, a volatile memory such as a DRAM. The storage 26 is for saving data and is a non-volatile memory. The storage 26 includes, for example, a flash memory, a hard disk drive, etc. The processor 29 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0027] The generative AI system 30 is equipped with a generative AI model and is a system for realizing a dialogue between an applicant and the generative AI model. The generative AI system 30 is physically constructed on one or more server computers. The generative AI system 30 is connected to the terminal device 10 and the server 20 via a communication network N, and provides each function through an API (Application Programming Interface). The generative AI system 30 may be constructed on, for example, a cloud-based infrastructure.

[0028] The generative AI system 30 has an LLM (large-scale language model). The generative AI system 30 may be a multimodal generative AI model capable of integrated processing of text data, audio data, etc. The generative AI system 30 may be provided as an external cloud service, or may be an AI model in an on-premise environment running on a server within an organization. Also, while FIG. 1 shows an example in which the generative AI system 30 is independent from the server 20, the server 20 may be configured to include the functions of the generative AI system 30 (e.g., an LLM). The number of LLMs included in the generative AI system 30 may be one or more.

[0029] LLM is a single-modal natural language model constructed by learning from large amounts of text data, and is used in many NLG (Natural Language Generation) tasks, such as generating answers to specific questions, automatically generating sentences, and summarizing text. LLM is an example of a generative AI model. Examples of LLMs include: OpenAI: GPT-4 Google: Gemini 1.5 Flash ·Anthropic: Claude 3.5 Sonnet

[0030] The generative AI system 30 inputs text data sent from the server 20 into the LLM, and causes the LLM to output an answer to the input prompt. The generative AI system 30 transmits the answer output from the LLM to the server 20. Note that the generative AI system 30 may also input text data sent from the terminal device 10 into the LLM, cause the LLM to output a response to the prompt input to the LLM, and transmit the response output from the LLM to the terminal device 10.

[0031] The terminal device 40 is a device used by an administrator in charge of recruiting personnel for an organization, and is an information processing device operated by the administrator. The terminal device 40 is realized, for example, by a mobile terminal such as a smartphone or a tablet, a desktop personal computer (PC), or a laptop PC. Like the terminal device 10, the terminal device 40 is realized by a computer equipped with hardware such as a communication interface (IF), an input device, an output device, a memory, a storage, and a processor.

[0032] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the terminal device 10, the server 20, the generation AI system 30, and the terminal device 40, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0033] <2. Terminal Device Configuration> Fig. 2 is a block diagram showing the functional configuration of the terminal device 10. As shown in Fig. 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a camera 160, a position information sensor 150, a storage unit 180, and a control unit 190. The blocks included in the terminal device 10 are electrically connected by, for example, a bus or the like.

[0034] The communication unit 120 is realized by the communication IF 12. The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on a signal generated by the control unit 190 and transmits the signal to the outside (for example, the server 20). The communication unit 120 performs reception processing on a signal received from the outside and outputs the signal to the control unit 190.

[0035] The input device 13 is a device for a user operating the terminal device 10 to input instructions or information. The input device 13 is realized, for example, by a touch-sensitive device 131 that inputs instructions by touching the operation surface. If the terminal device 10 is a PC or the like, the input device 13 may be realized by a reader, keyboard, mouse, or the like. The input device 13 may be realized by a microphone 171 that accepts input of voice information. The input device 13 converts instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may include, for example, a receiving port that accepts electrical signals input from an external input device.

[0036] The output device 14 is a device for presenting information to a user operating the terminal device 10. The output device 14 is realized, for example, by a display 141 or the like. The display 141 displays data according to the control of the control unit 190. The display 141 is realized, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display or the like. The output device 14 may also be realized by a speaker 172 that outputs audio information.

[0037] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of an audio signal. The audio processing unit 17 converts a signal provided 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 realized, for example, by a processor for audio processing. The microphone 171 receives audio input and provides an audio signal corresponding to the audio input to the audio processing unit 17. The speaker 172 converts the audio signal provided from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0038] The camera 160 is a device that receives light with a light receiving element and outputs the light as an image capturing signal.

[0039] The position information sensor 150 is a sensor that detects the position of the terminal device 10, and is, for example, a GPS (Global Positioning System) module. The GPS module is a receiving device used in a satellite positioning system. The satellite positioning system receives signals from at least three or four satellites, and detects the current position of the terminal device 10 equipped with the GPS module based on the received signals. The position information sensor 130 may detect the current position of the terminal device 10 from the position of the wireless base station to which the terminal device 10 is connected.

[0040] The storage unit 180 is realized by, for example, the memory 15 and the storage 16, and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, user information 181 and device information 182. The user information 181 includes, for example, information about applicants (users) who use the terminal device 10. The user information 181 includes, for example, the user's ID, name, age, address, date of birth, contact information, etc. The device information 182 is information about the terminal device 10. The device information 182 includes, for example, the device name, manufacturer, model number, OS (operating system) type and version, serial number, hardware information (for example, CPU, memory (RAM), storage capacity, etc.), network information (for example, MAC address), etc.

[0041] The control unit 190 is realized by the processor 19 reading a program stored in the storage unit 180 and executing instructions included in the program. The control unit 190 controls the operation of the terminal device 10. The control unit 190 functions as an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193 by operating in accordance with the program.

[0042] The operation reception unit 191 performs processing for receiving instructions or information input from the input device 13. For example, the operation reception unit 191 receives instruction information input from the touch-sensitive device 131 or the like. The operation reception unit 191 receives audio instructions input from the microphone 171. For example, the operation reception unit 191 receives an audio signal input from the microphone 171 and converted into a digital signal by the audio processing unit 17.

[0043] The transmitting / receiving unit 192 performs processing for the terminal device 10 to transmit and receive data to and from an external device such as the server 20 in accordance with a communication protocol. For example, the transmitting / receiving unit 192 transmits information input by a user or instructions from the user to the server 20. The transmitting / receiving unit 192 also receives information provided by the server 20.

[0044] The presentation control unit 193 controls the output device 14 to present visual information to the user. For example, the presentation control unit 193 causes various types of information to be displayed on the display 141. The presentation control unit 193 also causes audio information to be output from the speaker 172. The control unit 190 controls the speech and actions of an avatar 71 (described below) displayed on the display 141 via the presentation control unit 193.

[0045] <3. Server configuration> 3 is a diagram showing an example of the functional configuration of the server 20. As shown in FIG. 3, the server 20 performs the functions of a communication unit 201, a storage unit 202, and a control unit 203.

[0046] The communication unit 201 performs processing for the server 20 to communicate with external devices such as the terminal device 10, the generation AI system 30, and the terminal device 40 via the communication network N.

[0047] The storage unit 202 stores an applicant table 2021, a question theme table 2022, an item table 2023, a question and answer table 2024, an interview session table 2025, an evaluation table 2026, and the like.

[0048] The applicant table 2021 stores information about applicants who apply for a job at an organization and participate in an online recruitment interview. The question theme table 2022 stores information about question themes, which are the themes of questions asked to applicants during the recruitment interview. The item table 2023 stores information about multiple items belonging to a question theme. The question and answer table 2024 stores specific questions to be presented to applicants and definitions of answers to those questions. The interview session table 2025 stores information about interview sessions indicating the duration of each recruitment interview for each applicant. The evaluation table 2026 stores information about the evaluation of applicants for each interview session.

[0049] The control unit 203 is realized by the processor 29 executing a program stored in the storage unit 202, and controls the overall operation of the server 20. The control unit 203 operates in accordance with the program, and functions as a reception control module 2031, a transmission control module 2032, a presentation control module 2033, a setting processing module 2034, and an interaction processing module 2035.

[0050] The reception control module 2031 performs processing to receive signals sent to the communication unit 201 via the communication network N from the terminal device 10, the generation AI system 30, and the terminal device 40.

[0051] The transmission control module 2032 uses the communication unit 201 to perform processing for transmitting signals to the terminal device 10, the generation AI system 30, and the terminal device 40 via the communication network N.

[0052] The presentation control module 2033 controls the process of presenting various information to applicants via the terminal device 10 and the process of presenting various information to an administrator via the terminal device 40 .

[0053] The setting processing module 2034 controls the process of displaying a setting screen on the terminal device 40 for the administrator and the process of making settings related to the job interview based on information input by the administrator via the terminal device 40. The setting processing module 2034 accepts information about the applicant. For example, the setting processing module 2034 accepts the applicant's name, birthday, email address, personal information (e.g., resume data and curriculum vitae data), etc. The setting processing module 2034 accepts, from the terminal device 40, a setting of a question theme, which is a theme of questions to be asked of the applicant during the job interview. The setting processing module 2034 accepts, from the terminal device 40, setting of information about the question theme (e.g., question time, number of items to be asked, supplementary explanations, etc.). The setting processing module 2034 sets multiple items belonging to the question theme by having the generation AI system 30 generate multiple items belonging to the set question theme. The multiple items belonging to the question theme are generated, for example, based on supplementary explanations. In this case, the number of generated items does not need to match the number of supplementary explanations. A greater number of items than supplementary explanations may be generated. Also, a preset number of items may be generated from a predetermined number of supplemental explanatory sentences.

[0054] The dialogue processing module 2035 controls dialogue with the applicant during the job interview. The dialogue processing module 2035 causes the generation AI system 30 to present questions generated by the generation AI system 30 to the applicant via the terminal device 10 and receives answers from the applicant via the terminal device 10. The dialogue processing module 2035 causes the generation AI system 30 to generate multiple items belonging to a question theme. Multiple items belonging to a single question theme are question items with different perspectives. The dialogue processing module 2035 causes the generation AI system 30 to generate questions to obtain answers from the applicant for items for which answers have not yet been received, based on the applicant's answers and the multiple items generated by the generation AI. The dialogue processing module 2035 controls the progress of a questioning step that repeats a questioning routine that causes the generation AI system 30 to generate questions and present the questions to the applicant on the terminal device 10. The progress of the question step is controlled based on the question time per question topic and the number of items already listened to, and preferably based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already listened to, and the target number of items to be listened to.

[0055] <4. Data Structure> Fig. 4 is a diagram showing the data structure of the applicant table 2021. As shown in Fig. 4, the applicant table 2021 has columns such as applicant name, email address, and personal information, with the applicant ID as a key, for example.

[0056] Applicant ID is a column that stores an identifier for uniquely identifying an applicant. Applicant Name is a column that stores the name of the applicant. Email Address is a column that stores the email address of the applicant. Personal Information is a column that stores information about the applicant's attributes, career, etc. The personal information may include link information to a storage area in which information about the applicant's attributes, career, etc. is stored. Personal Information may be information indicated, for example, by the applicant's resume data, applicant's work history data, etc.

[0057] Fig. 5 is a diagram showing the data structure of the question theme table 2022. As shown in Fig. 5, the question theme table 2022 has columns such as question theme, question time, target number of items to be listened to, supplementary explanation, etc., with question theme ID as a key.

[0058] The question theme ID is a column that stores an identifier for uniquely identifying a question theme. The question theme is a column that stores text indicating the question theme. The question theme indicates the concept, intent, purpose, or perspective of the questions to be asked to the applicant during the job interview. The question time is a column that stores the time limit assigned to the question theme. The target number of items to be asked is a column that stores the target number of items to be answered by the applicant out of the multiple items belonging to the question theme. The supplementary explanation is a column that stores text that supplements the question theme to indicate the direction for deciding on multiple items to dig deeper into the question theme. The supplementary explanation for one question theme can be one or more sentences.

[0059] Fig. 6 is a diagram showing the data structure of the item table 2023. As shown in Fig. 6, the item table 2023 has columns such as item, question theme ID, and listening flag, with the item ID as a key.

[0060] The item ID is a column that stores an identifier for uniquely identifying an item. An item is the content of a question item that belongs to a question theme. An item can also be considered a detailed theme that subdivides a question theme. The question theme ID is a column that stores an identifier for uniquely identifying a question theme. The questionnaire flag is a column that stores a flag (e.g., True / False) that indicates whether or not an answer has been obtained from the applicant for the corresponding item. For example, if an answer to a question regarding the corresponding item has already been obtained, a flag of "True" is stored in the questionnaire flag. If an answer to a question regarding the corresponding item has not yet been obtained, a flag of "False" is stored in the questionnaire flag.

[0061] Fig. 7 is a diagram showing the data structure of the question and answer table 2024. As shown in Fig. 7, the question and answer table 2024 has columns such as questions and answer definitions, with item IDs as keys, for example.

[0062] The item ID is the same as the item ID included in the item table 2023, and is a column that stores an identifier for uniquely identifying an item. The question is a column that stores a specific question to be output to the applicant. The answer definition is a column that stores the definition of the answer to the question corresponding to the item ID. Specifically, the answer definition stores the criteria for determining that an answer from an applicant to a question corresponding to each item ID must meet in order to be considered as "answered."

[0063] Fig. 8 is a diagram showing the data structure of the interview session table 2025. As shown in Fig. 8, the interview session table 2025 has columns such as applicant ID, interview date and time, and question theme ID, with the interview session ID as a key, for example.

[0064] The interview session ID is a column that stores an identifier for uniquely identifying an interview session. The applicant ID is the same as the applicant ID included in the applicant table 2021, and is a column that stores an identifier for uniquely identifying an applicant. The interview date and time is a column that stores the start date and time and the end date and time of the interview session. The question theme ID is the same as the question theme ID included in the question theme table 2022, and is a column that stores an identifier for uniquely identifying a question theme.

[0065] Fig. 9 is a diagram showing the data structure of the evaluation table 2026. As shown in Fig. 9, the evaluation table 2026 has columns such as an interview session ID, a question theme ID, an item ID, an answer, and a score, with an evaluation ID as a key, for example.

[0066] The evaluation ID is a column that stores an identifier for uniquely identifying an applicant's evaluation in one interview session. The interview session ID is the same as the interview session ID included in the interview session table 2025, and is a column that stores an identifier for uniquely identifying an interview session. The question theme ID is the same as the question theme ID included in the question theme table 2022, and is a column that stores an identifier for uniquely identifying the question theme ID. The item ID is the same as the item ID included in the item table 2023, and is a column that stores an identifier for uniquely identifying an item. The answer is a column that stores an answer from an applicant regarding an item corresponding to the item ID. The score is a column that stores the score of an answer from an applicant regarding an item corresponding to the item ID. A higher score value indicates a higher evaluation. The score may be obtained by inputting supplementary explanations, items, questions, answer definitions, etc. related to the question theme into the generation AI system 30 and having the generation AI system 30 output the score.

[0067] <5. Operation> The operation of the information processing system 1 will be described.

[0068] FIG. 10 is a diagram illustrating the setting process in system 1. In step S1, terminal device 40 operated by an administrator in charge of recruiting for an organization accesses server 20 and inputs setting information for a recruitment interview. The input setting information includes, for example, question topic, question time, target number of interview items, supplementary explanation for the question topic, and personal information about the applicant. In step S2, terminal device 40 operated by the administrator transmits the setting information to server 20.

[0069] In step S3, the server 20 creates an item generation prompt P1 that causes the generation AI system 30 to generate multiple items belonging to the question theme based on the set question theme, etc. For example, the server 20 creates the item generation prompt P1 that requests the output of multiple items belonging to the question theme based on set information such as the question theme, question time, target number of items to be asked, supplementary explanation of the question theme, and personal information about the applicant. The item generation prompt P1 is automatically created internally in the server 20.

[0070] FIG. 11 is a diagram illustrating an example of an item generation prompt P1 input from the server 20 to the generation AI system 30. As shown in FIG. 11, the item generation prompt P1 includes a request to generate multiple items belonging to each question theme based on the question theme, a supplemental explanation for the question theme, and personal information about the applicant (e.g., a resume and a curriculum vitae corresponding to the applicant ID). The item generation prompt P1 may also include a request to determine the number of items to be generated based on a target number of listening items and the duration of the question. The number of items to be generated may be equal to or greater than the target number of listening items. The item generation prompt P1 may also include a request to determine the priority of multiple items belonging to one question theme based on the question theme, the supplemental explanation, and the personal information. The information included in the item generation prompt P1 references information entered in the setting screen 60 of FIG. 18 (described later).

[0071] Returning to FIG. 10, in step S4, the server 20 inputs the item generation prompt P1 to the generation AI system 30. In step S5, the generation AI system 30 generates multiple items belonging to each question theme according to the item generation prompt P1 (item generation step). In step S6, the generation AI system 30 determines the priority of the multiple items belonging to each question theme as the order of priority when presenting questions to the applicant (prioritization step). The priority is determined based on predetermined criteria, such as highly evaluating items that are highly relevant to the applicant's personal information (resume, curriculum vitae) or items that correspond to content that is particularly emphasized in the supplemental explanation.

[0072] In step S7, the generation AI system 30 transmits multiple items belonging to the generated question theme and the priorities of those items to the server 20. In step S8, the server 20 stores each item and its priority received from the generation AI system 30.

[0073] Figure 12 is a diagram for explaining the interview processing in system 1. Figure 13 is a flowchart continuing from Figure 12. In step S11, the applicant logs in to a job interview site provided by server 20 via terminal device 10. If server 20 successfully authenticates the login information sent from terminal device 10, in step S13, it causes terminal device 10 to display interview screen 70 of Figure 19, which will be described later. In step S14, the applicant operates terminal device 10 to send a request to start an interview to server 20.

[0074] When the server 20 receives the interview start request, in step S15, it starts counting the elapsed time of the interview. In step S16, the server 20 identifies a target question theme from the multiple question themes set on the setting screen 60 in Fig. 18 (described later). For example, the server 20 identifies the target question theme in the order displayed from the top of the list of question themes.

[0075] In step S17, the server 20 selects the item with the highest priority among the multiple items belonging to the identified question theme as the target item, and creates a question generation prompt P2 that causes the generation AI system 30 to generate a question for the applicant regarding the target item (question generation step). The question generation prompt P2 is automatically created internally in the server 20.

[0076] FIG. 14 is a diagram illustrating a question generation prompt P2 input from the server 20 to the generation AI system 30. As shown in FIG. 14, the question generation prompt P2 includes a request to generate a question to obtain an answer from the applicant for an item among the multiple items for which the applicant has not yet answered, based on the applicant's answer and multiple items belonging to the question theme. The question generation prompt P2 includes a request to generate a question to be presented to the applicant and a definition of the answer to the question, based on the multiple items belonging to the question theme. If there are multiple items for which the applicant has not yet answered, the question generation prompt P2 may include a request to generate a question for the item with the highest priority among the multiple unanswered items.

[0077] Returning to Figure 12, in step S18, the server 20 inputs the question generation prompt P2 to the generation AI system 30, and in step S19, the generation AI system 30 generates a question (and a definition of the answer to that question) for an unheard item in accordance with the question generation prompt P2 (question generation step).

[0078] In step S20, the generation AI system 30 transmits the generated question (and a definition of the answer to the question) to the server 20. In step S21, the server 20 causes the terminal device 10 to present the question generated by the generation AI system 30 to the applicant (question presentation step). That is, the server 20 transmits the question to the terminal device 10 used by the applicant. In step S22, the terminal device 10 converts the question from text to speech and outputs the converted speech to the applicant.

[0079] In step S23, the applicant inputs a voice response into the terminal device 10. In step S24, the terminal device 10 converts the input voice response into text and transmits the converted response to the server 20. Note that the conversion between text and voice may be performed by the server 20 instead of by the terminal device 10.

[0080] In step S25, the server 20 generates an answered item extraction prompt P3 including a request to extract an item to which the applicant's answer corresponds from a plurality of items belonging to the question theme.

[0081] 15 is a diagram illustrating an example of an answered item extraction prompt P3 input from the server 20 to the generative AI system 30. As shown in FIG. 15, the answered item extraction prompt P3 includes a request to extract, from among a plurality of items belonging to the current question theme, items to which the applicant's answer corresponds, based on the applicant's answer and the plurality of items belonging to the current question theme. The server 20 may include the applicant's answer and the plurality of items belonging to the current question theme in the answered item extraction prompt P3, or may input them to the generative AI system 30 separately from the answered item extraction prompt P3.

[0082] Returning to FIG. 13, in step S26, the server 20 inputs the answered item extraction prompt P3 to the generation AI system 30. In step S27, the generation AI system 30 extracts items corresponding to the applicant's answer from multiple items belonging to the question theme in accordance with the answered item extraction prompt P3. In this case, the server 20 inputs the answer received from the terminal device 10 to the generation AI system 30 and has the generation AI system 30 determine whether the answer satisfies the definition of an answer to the question. In step S28, the generation AI system 30 transmits the extracted items to the server 20. The server 20 identifies the extracted items as items for which answers have been received from the applicant.

[0083] In step S29, the server 20 determines whether answers have been received for all of the multiple items belonging to the question theme, i.e., whether the current question theme has ended. If it is determined that the current question theme has not ended, in step S30, the server 20 removes the extracted items from the multiple items belonging to the question theme and moves on to the remaining items that have not been received. That is, the server 20 moves on to the items for which answers from applicants have not been received, and returns to step S17. In this way, the server 20 defines each set of steps from step S17 to step S30 as a question routine, and performs a question step in which the question routine is repeated.

[0084] When it is determined that the current question theme has ended, the server 20 determines in step S31 whether there is a next question theme for which questions have not yet been asked to the applicant. If it is determined that there is a next question, the server 20 moves on to the next question theme in step S32 and returns to step S17. In this way, the server 20 performs a question step for the next question theme, repeating the question routine consisting of steps S17 to S30.

[0085] If it is determined that there is no next question, then in step S33, the server 20 transmits an end notification indicating that the current interview has been completed to the terminal device 10. In step S34, upon receiving the end notification, the terminal device 10 displays an end screen indicating that the current interview session is ending.

[0086] Next, we will explain the first interview progress control, which controls the progress of an ongoing interview when the remaining time, obtained by subtracting the elapsed time from the question time, becomes short. Figure 16 is a flowchart of the first interview progress control. As shown in Figure 16, in step S41, the server 20 calculates the remaining time for the current question theme. The remaining time is calculated by subtracting the elapsed time since step S15 in Figure 12 from the question time set for the current question theme.

[0087] In step S42, the server 20 calculates the number of collected items for the current question theme. That is, the server 20 identifies the number of collected items, which is the number of items for which answers have been collected from applicants, among the multiple items belonging to the current question theme (identification step). The number of collected items is calculated by counting the number of items extracted in step S27 of FIG. 13.

[0088] In step S43, the server 20 determines whether the remaining time has reached a predetermined value. The predetermined value is a value greater than zero and less than the question time. For example, if the question time is 5 minutes, the predetermined value may be 1 minute. If it is determined that the remaining time has not reached the predetermined value, the server 20 returns to step S41. On the other hand, if it is determined that the remaining time has reached the predetermined value, the server 20 determines in step S44 whether the number of items already listened to for the current question topic has reached a target value.

[0089] If it is determined that the number of items already collected for the current question theme has not reached the target value, the server 20 returns to step S41 and continues the question step. On the other hand, if it is determined that the number of items already collected for the current question theme has reached the target value, in step S45, the server 20 completes the currently executing question routine and then ends the current question theme. In step S46, the server 20 determines whether there is a next question theme for which the applicant has not yet been asked. If it is determined that there is a next question, the server 20 moves on to the next question theme in step S47. If it is determined that there is no next question theme, the server 20 ends the interview. In the progress control step described above, the progress of the question step (the repetition of the question routine consisting of the above-mentioned steps S17 to S30) is controlled based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already collected, and the target value for the number of items to be collected.

[0090] Next, a second interview progress control that controls the progress of the ongoing interview when the elapsed time reaches the question time will be described. Figure 17 is a diagram for explaining the second interview progress control. As shown in Figure 17, in step S51, the server 20 calculates the remaining time for the current question theme. In step S52, the server 20 calculates the number of items that have been listened to for the current question theme.

[0091] In step S53, the server 20 determines whether the elapsed time has reached the question time, i.e., whether the remaining time has reached zero. If it is determined that the remaining time has not reached zero, the server 20 returns to step S51. On the other hand, if it is determined that the remaining time has reached zero, the server 20 determines in step S54 whether the number of items already listened to for the current question topic has reached a target value.

[0092] If it is determined that the number of items already collected for the current question theme has not reached the target value, then in step S55, the server 20 completes the currently executing question routine and then ends the current question theme. On the other hand, if it is determined that the number of items already collected for the current question theme has reached the target value, then the server 20 ends the question step for the current question theme. That is, if it is determined that the number of items already collected for the current question theme has reached the target value, then in step S56, the server 20 determines whether there is a next question theme for which questions have not yet been asked to the applicant. If it is determined that there is a next question, then in step S57, the server 20 moves on to the next question theme. If it is determined that there is no next question theme, then the server 20 ends the interview. In the progress control steps described above, the progress of the question step (the repetition of the question routine consisting of the aforementioned steps S17 to S30) is controlled based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already collected, and the target value for the number of items to be collected.

[0093] The first interview progress control of FIG. 16 and the second interview progress control of FIG. 17 may be executed independently of each other, or may be executed in conjunction with each other. For example, when the determination in step S44 of FIG. 16 is NO and the question step is continued, the server 20 may proceed to the processing of step S53 of FIG. 17. Furthermore, when the determination in step S44 of FIG. 16 is YES and the question routine currently being executed is continued, the server 20 may terminate the currently executed question routine midway if the determination in step S54 of FIG. 17 is YES. Furthermore, when the determination in step S44 of FIG. 16 is YES and the currently executed question routine is continued in step S55, if the extension time after the question time has elapsed reaches a predetermined value, the server 20 may terminate the current question topic even if the currently executed question routine has not been completed (even if the applicant has not yet answered the current question).

[0094] <Screen example> Next, an example of a screen used in the information processing system 1 will be described. FIG. 18 is a diagram illustrating a setting screen 60 on the administrator's terminal device 40. Note that this screen example is merely an example, and various screen configurations and screen contents can be adopted. As shown in FIG. 18, the setting screen 60 is a screen on which the administrator inputs the settings for the online interview in step S1 of FIG. 10. The setting screen 60 has a question theme section 61, a question time section 62, a target number of interview items section 63, a supplementary explanation input section 64, an add button section 65, and a confirm button section 66.

[0095] The question topic section 61 displays question topics set as topics to be asked to the applicant. In the example of Fig. 18, self-introduction, advantages, disadvantages, and strengths / specialties are set as question topics.

[0096] The question time section 62 displays the question time set as a time limit available for asking questions to applicants about the corresponding question topic. For example, an administrator using the terminal device 40 can set the question time using a pull-down menu.

[0097] The target number of items to be asked for display unit 63 displays the target number of items to be asked for, which is set as the target number of items to be asked for answers to be asked from applicants for a plurality of items belonging to the corresponding question theme. For example, an administrator using terminal device 40 can set the target number of items to be asked for using a pull-down menu.

[0098] The supplementary explanation input section 64 displays a field for inputting a supplementary explanation for the question theme in free text.

[0099] The add button 65 is a UI component for displaying a field for adding and setting a new question theme. By selecting the add button section 65, the administrator using the terminal device 40 can add and set a new question theme.

[0100] The confirm button section 66 is a UI component for confirming the settings displayed on the setting screen 60 and transmitting them to the server 20. By selecting the confirm button section 66, the administrator using the terminal device 40 transmits the settings displayed on the setting screen 60 to the server 20.

[0101] 19 is a diagram illustrating an example of an interview screen 70 on the applicant's terminal device 10. Note that this screen example is merely an example, and various screen configurations and screen contents may be adopted. As shown in FIG. 19, the interview screen 70 has an avatar 71, an applicant screen 72, a question theme display section 73, and an exit button 74.

[0102] The avatar 71 plays the role of a virtual interviewer. The avatar 71 has, for example, a human appearance and is an interface that speaks to the applicant. The terminal device 10 controls the movement of the avatar 71 based on the voice data received from the server 20. When the avatar 71 speaks, the mouth of the avatar 71 may be depicted as moving. The speech of the avatar 71 is realized, for example, by audio output from the speaker 172, but the content of the speech may also be displayed as text on the interview screen 70. In this case, the avatar 71 may function only as an icon without speaking.

[0103] The applicant screen 72 displays an image of the applicant captured by the camera 160 of the terminal device 10. The question theme display section 73 displays the question theme currently selected during the interview. The applicant operating the terminal device 10 selects the exit button 74 to exit the interview screen 70. The interview screen 70 may also display the text of each question, the remaining time for questions, etc. The interview screen 70 may also display an indicator showing whether voice input to the terminal device 10 is enabled.

[0104] FIG. 20 is a diagram illustrating an example of an analysis screen 80 on the administrator's terminal device 40. Note that this screen example is merely an example, and various screen configurations and screen contents can be adopted. As shown in FIG. 20, the server 20 displays an analysis screen 80 showing the interview results on the administrator's terminal device 40 after the interview is completed. The analysis screen 80 displays a summary of the applicant's answers to each item belonging to the question theme and a coverage rate, which is the response rate for each item for each question theme. By viewing this analysis screen 80, the administrator can evaluate the applicant and can also use it as a reference for questions to ask the applicant if there is a next interview opportunity.

[0105] <Summary> As described above, according to the information processing system 1, the generation AI generates multiple items belonging to a question theme, and based on the applicant's answers and the multiple items generated by the generation AI, the generation AI generates questions to obtain answers from the applicant about unasked items, thereby making it possible to efficiently and multifacetedly extract information from the applicant about the question theme.

[0106] (Variation) FIG. 21 is a diagram for explaining the processing of a modified example, equivalent to FIG. 10 . Note that steps similar to those in FIG. 10 are assigned the same reference numerals and detailed descriptions are omitted. In the above-described embodiment, the priority of multiple items belonging to a question theme was determined by the generation AI system 30. However, in this modified example, the priority is determined by the administrator. As shown in FIG. 10 , in step S5, the generation AI system 30 generates multiple items for each question theme, and in step S106, transmits the generated items to the server 20. The server 20 transmits the items received from the generation AI system 30 to the administrator's terminal device 40. In step S108, the terminal device 40 displays the multiple items for each question theme. In step S109, the administrator operates the terminal device 40 to specify the priority of the multiple items displayed on the terminal device 40. The terminal device 40 transmits the specified priority to the server 20. In step S111, the server 20 stores each item and its priority.

[0107] Furthermore, the dialogue to which System 1 is applied is not limited to job interviews, but may be any dialogue including questions and answers. For example, System 1 can be used in various situations, such as job interview practice, meetings with members within an organization, interviews using an avatar with a primary interview contact in a specialized job, telephone reception work, user interviews, and role-play practice for sales or customer service. In other words, the dialogue partner is not limited to a job applicant, but may be any human being who is expected to answer questions.

[0108] Furthermore, the dialogue is not limited to voice dialogue, but may be text dialogue. In the above-described embodiment, an example was given in which the applicant dialogues with the generative AI model by voice via the avatar 71, but for example, the applicant may dialogue with the generative AI model through text-based chat. The terminal device 10 that outputs questions to the dialogue partner is not limited to a device such as a personal computer, but may also be a robot.

[0109] In the above-described embodiment, the progress of the interview is controlled based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already listened to, and the target number of items to be listened to, but this is not limiting, and the progress of the question step may also be controlled based on the question time and the number of items already listened to. For example, the allocated time to be allocated to one item may be calculated based on the number of items belonging to the question theme and the question time, and when the allocated time has elapsed, the system may move on to the question of the next item.

[0110] In the above-described embodiment, the server 20 inputs prompts P2 and P3 to the generative AI system 30 in steps S18 and S26 of Figure 12, respectively. However, a comprehensive prompt may be input to the generative AI system 30 in advance. The comprehensive prompt may include instructions to generate multiple items belonging to a question theme when a question theme is input, and to generate questions for unasked items based on the answer and the multiple items when an answer from an applicant is input. The generative AI system 30 may be an AI agent.

[0111] The server 20 may provide the above-mentioned functions to a system external to the information processing system 1 through an API (Application Programming Interface).

[0112] The server 20 may have the generation AI system 30 determine whether the answer from the applicant is a negative answer, and if the answer is determined to be negative, may end the question item corresponding to that answer and move on to other unasked items.

[0113] <Basic computer hardware configuration> 22 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main memory device 902, an auxiliary memory device 903, and a communication IF 991 (interface), which are electrically connected to one another by a communication bus 921.

[0114] The processor 901 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0115] The main storage device 902 is used to temporarily store programs, data to be processed by the programs, etc. The main storage device 902 is, for example, a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0116] The auxiliary storage device 903 is a storage device for saving data and programs, and is, for example, a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0117] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards.

[0118] The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a direct connection using a USB (Universal Serial Bus) cable, etc.

[0119] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 90 and interconnecting them via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0120] <Basic functional configuration of computer 90> The following describes the functional configuration of a computer realized by the basic hardware configuration (FIG. 22) of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0121] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 interconnected via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0122] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0123] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can allocate a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with the programs. Furthermore, the control unit can cause the processor 901 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0124] A database refers to a relational database, which manages data sets called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a table, a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated.

[0125] Typically, each table and each master has a column set as a primary key to uniquely identify a record, but setting a primary key to a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs.

[0126] Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0127] Note that the databases and masters in this disclosure may include any data structure in which information is structurally defined (such as a list, dictionary, associative array, or object). The data structure also includes data that can be considered as a data structure by combining data with functions, classes, methods, etc. written in any programming language.

[0128] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0129] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that implements the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for providing such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tape, non-volatile memory cards, and ROMs.

[0130] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, and Java (registered trademark).

[0131] Furthermore, the program code of the software that realizes the functions of the embodiments 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 processor of the computer may read and execute the program code stored in the storage means or storage medium.

[0132] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory.

[0133] In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0134] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0135] Although several embodiments of the present disclosure have been described above, these embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are intended to be included in the scope of the inventions and their equivalents as defined in the claims, as well as in the scope and spirit of the inventions.

[0136] (Addendum) The matters described in the above embodiments will be supplemented below.

[0137] (Appendix 1) A program for operating a computer having a processor and memory, the program causing the processor to execute the following steps: an item generation step for causing a generation AI to generate multiple items belonging to a question theme based on a predetermined question theme; a question generation step for causing the generation AI to generate questions to obtain answers from the dialogue partner for items among the multiple items for which the dialogue partner has not yet answered, based on the dialogue partner's answer and the multiple items generated by the generation AI; and a question presentation step for presenting the questions generated by the generation AI to the dialogue partner.

[0138] (Appendix 2) The program described in Appendix 1, wherein the question generation step includes having the generation AI extract items from the plurality of items to which the dialogue partner's answer corresponds, and having the generation AI generate questions for the remaining unheard items after excluding the extracted items from the plurality of items.

[0139] (Appendix 3) A program as described in Appendix 1 or 2, which causes a processor to execute a supplementary explanation acceptance step for accepting a supplementary explanation that supplements the question theme, and an item generation step includes having a generation AI generate multiple items based on the question theme and the supplementary explanation.

[0140] (Appendix 4) 4. The program according to any one of appendices 1 to 3, further causing the processor to execute a question step of repeating a question routine including a question generation step and a question presentation step, a reception step of receiving a question time set for a question theme, a determination step of determining the number of items already heard, which is the number of items for which the dialogue partner's answers have already been heard, among a plurality of items, and a progress control step of controlling the progress of the question step with respect to the question theme based on the question time and the number of items already heard.

[0141] (Appendix 5) The program described in Appendix 4, wherein the progress control step includes controlling the progress of the question step based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already listened to, and the target number of items to be listened to.

[0142] (Appendix 6) The program described in Appendix 5, wherein the progress control step includes continuing the question step if the number of items listened to has not reached a target value when the remaining time reaches a predetermined value, and terminating the question step regarding the question theme after the question routine currently being executed is completed when the number of items listened to has reached the target value when the remaining time reaches a predetermined value.

[0143] (Appendix 7) The program described in Appendix 5 or 6, wherein the progress control step includes terminating the question step regarding the question theme after the question routine currently being executed is completed if the number of items already listened to has not reached the target value when the elapsed time reaches the question time, and terminating the question step regarding the question theme if the number of items already listened to has reached the target value when the elapsed time reaches the question time.

[0144] (Appendix 8) The question generation step is a program described in any one of Appendices 1 to 7, in which the generation AI generates a question to be presented to the dialogue partner and a definition of an answer to the question based on multiple items.

[0145] (Appendix 9) 9. The program of any one of appendices 1 to 8, wherein the program causes a processor to execute a prioritization step of setting priorities of a plurality of items as priorities for presenting questions to a dialogue partner.

[0146] (Appendix 10) A program for operating a computer having a processor and a memory, the program causing the processor to execute an item generation step of causing a generation AI to generate multiple items belonging to a question theme based on a predetermined question theme, a question generation step of causing the generation AI to generate a question to obtain an answer from the dialogue partner based on the dialogue partner's answer and the multiple items generated by the generation AI, and a question presentation step of presenting the question generated by the generation AI to the dialogue partner, and further causing the program to execute a question step of repeating a question routine including the question generation step and the question presentation step, a reception step of receiving a question time set for the question theme, a determination step of specifying the number of items already heard, which is the number of items among the multiple items for which the dialogue partner's answer has already been heard, and a progress control step of controlling the progress of the question step with respect to the question theme based on the question time and the number of items already heard.

[0147] (Appendix 11) The program described in Appendix 10, wherein the progress control step includes controlling the progress of the question step based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already listened to, and the target number of items to be listened to.

[0148] (Appendix 12) The program described in Appendix 11, wherein the progress control step includes continuing the question step if the number of items listened to has not reached a target value when the remaining time reaches a predetermined value, and terminating the question step regarding the question theme after the question routine currently being executed is completed when the number of items listened to has reached the target value when the remaining time reaches a predetermined value.

[0149] (Appendix 13) The program described in Appendix 11 or 12, wherein the progress control step includes terminating the question step regarding the question theme if the number of items listened to has reached a target value when the elapsed time reaches the question time, and terminating the question step regarding the question theme after the question routine currently being executed is completed when the number of items listened to has not reached the target value when the elapsed time reaches the question time.

[0150] (Appendix 14) 14. A computer-implemented method comprising a processor and a memory, wherein the processor performs all of the steps of any one of claims 1 to 13.

[0151] (Supplementary Note 15) An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps described in any one of Supplementary Notes 1 to 13.

[0152] (Appendix 16) 14. A system comprising a configuration for performing all of the steps recited in any one of Supplementary Notes 1 to 13. [Explanation of symbols]

[0153] 1. Information Processing Systems 10 Applicant's (interviewee's) terminal device 20 Server (information processing device) 26 Storage (Memory) 29 processors 30 Generative AI System 40 Administrator's terminal device N Communication Network

Claims

1. A program for operating a computer having a processor and a memory, The program causes the processor to: an item generation step of causing a generation AI to generate a plurality of items belonging to a predetermined question theme based on the question theme; a question generation step of causing the generation AI to generate a question for obtaining an answer from the conversation partner for an item among the plurality of items for which the conversation partner has not yet received an answer, based on the conversation partner's answer and the plurality of items generated by the generation AI; a question presentation step of presenting the question generated by the generation AI to the conversation partner; Execute The question generation step includes: extracting, from the plurality of items, an item to which the answer of the dialogue partner corresponds, by the generation AI; causing the generation AI to generate the questions for the remaining unlistened items excluding the extracted items from the plurality of items; Including, the program.

2. the program causes the processor to execute a supplemental explanation receiving step of receiving a supplemental explanation for the question theme; 2. The program according to claim 1, wherein the item generating step includes causing the generating AI to generate the plurality of items based on the question theme and the supplemental explanatory text.

3. the program causes the processor to execute a questioning step of repeating a questioning routine including the question generating step and the question presenting step; The program causes the processor to: a receiving step of receiving a question time set for the question theme; a step of identifying a number of items that have been listened to, which is the number of items for which the answer of the conversation partner has been listened to, among the plurality of items; a progress control step of controlling the progress of the question step with respect to the question theme based on the question time and the number of items already listened to; The program according to claim 1 , further comprising:

4. 4. The program according to claim 3, wherein the progress control step includes controlling the progress of the question step based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already listened to, and a target number of items to be listened to.

5. The progress control step includes: If the number of listened items has not reached the target value when the remaining time reaches the predetermined value, the questioning step is continued; When the remaining time reaches the predetermined value, if the number of listened items has reached the target value, the question step for the question theme is terminated after the question routine currently being executed is completed; The program according to claim 4 , comprising:

6. The progress control step includes: If the number of items already listened to has not reached the target value when the elapsed time reaches the question time, terminating the question step regarding the question theme after the question routine currently being executed is completed; If the number of items already listened to reaches the target value when the elapsed time reaches the question time, terminating the question step regarding the question theme; The program according to claim 4 , comprising:

7. the question generation step includes causing the generation AI to generate a question to be presented to the dialogue partner and a definition of an answer to the question, based on the plurality of items; The program of claim 1, wherein causing the generation AI to extract items corresponding to the dialogue partner's answer includes causing the generation AI to extract items corresponding to questions corresponding to the definition that the dialogue partner's answer satisfies.

8. The program according to claim 1 , wherein the program causes the processor to execute a prioritization step of setting priorities of the plurality of items as priorities for presenting the questions to the conversation partner.

9. A program for operating a computer having a processor and a memory, The program causes the processor to: an item generation step of causing a generation AI to generate a plurality of items belonging to a predetermined question theme based on the question theme; a question generation step of causing the generation AI to generate a question for obtaining an answer from the conversation partner based on the answer of the conversation partner and the plurality of items generated by the generation AI; a question presentation step of presenting the question generated by the generation AI to the conversation partner; Execute the program causes the processor to execute a questioning step of repeating a questioning routine including the question generating step and the question presenting step; The program causes the processor to: a receiving step of receiving a question time set for the question theme; a step of identifying a number of items that have been listened to, which is the number of items for which the answer of the conversation partner has been listened to, among the plurality of items; a progress control step of controlling the progress of the question step with respect to the question theme based on the question time and the number of items already listened to; A program that further executes the above.

10. 10. The program according to claim 9, wherein the progress control step includes controlling the progress of the question step based on the remaining time obtained by subtracting the elapsed time from the question time, the number of items already listened to, and a target number of items to be listened to.

11. The progress control step includes: If the number of listened items has not reached the target value when the remaining time reaches the predetermined value, the questioning step is continued; When the remaining time reaches the predetermined value, if the number of listened items has reached the target value, the question step for the question theme is terminated after the question routine currently being executed is completed; The program according to claim 10, comprising:

12. The progress control step includes: If the number of items already listened to reaches the target value when the elapsed time reaches the question time, terminating the question step regarding the question theme; If the number of items already listened to has not reached the target value when the elapsed time reaches the question time, terminating the question step regarding the question theme after the question routine currently being executed is completed; The program according to claim 10, comprising:

13. A computer-implemented method comprising a processor and a memory, wherein the processor performs all the steps of any one of claims 1 to 12.

14. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps recited in any one of claims 1 to 12.

15. A system comprising arrangements for performing all the steps of any one of claims 1 to 12.

Images