Program, method, information processing device and system

Abstract

To easily evaluate communication abilities of a dialogue partner in a dialogue session in multiple languages. [Solution] A program that executes the following steps: a first setting step that accepts input to set the basic language of an interaction session to a first language; a second setting step that accepts input to set the interaction language of a second question theme to a second language, while allowing the interaction language of a first question theme to be set to the first language, for multiple question themes in the interaction session, including a first question theme and a second question theme; a question generation step that causes a generation AI to generate a question to obtain an answer from a dialogue partner, for a question theme selected from the multiple question themes, in a dialogue language corresponding to the selected question theme; and a question presentation step that presents the question generated by the generation AI to the dialogue partner.

Description

[Technical Field]

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

[0002] Patent Document 1 describes an information processing device that can assist a user in formulating an opinion. The information processing device acquires a first sentence related to the user's opinion, acquires first evaluation information related to an evaluation of the persuasiveness of the first sentence, and outputs information prompting the user to input a second sentence related to the user's opinion based on the first evaluation information. At least a portion of the information displayed by the terminal device is displayed in a predetermined language, and at least another portion of the information displayed by the terminal device may be displayed in a language different from the predetermined language. Specifically, on the terminal device, the sentence input by the user and information prompting the user to input the next sentence may be displayed in English, and feedback on the summary sentence may be displayed in Japanese. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7721027 Summary of the Invention [Problem to be solved by the invention]

[0004] However, although Patent Document 1 discloses an example in which the language of the sentence entered by the user is different from the language of the feedback for the summary sentence, it is not suitable for evaluating the communication ability of a dialogue partner in multiple languages ​​in a given dialogue session.

[0005] An object of the present disclosure is to easily evaluate the communication skills of a dialogue partner in multiple languages ​​in a dialogue session. [Means for solving the problem]

[0006] In order to solve the above problem, one embodiment of a program of the present disclosure is a program for operating a computer having a processor and a memory, the program causing the processor to execute the following steps: a first setting step for accepting input to set the basic language of an interaction session to a first language; a second setting step for accepting input to set the interaction language of a second question theme to a second language, while allowing the interaction language of a first question theme to be set to the first language, for a plurality of question themes including a first question theme and a second question theme in the interaction session; a question generation step for causing a generation AI to generate a question to obtain an answer from a dialogue partner in the interaction language corresponding to the selected question theme, for a question theme selected from the plurality of question themes; and a question presentation step for presenting the question generated by the generation AI to the dialogue partner. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to easily evaluate the communication skills of a dialogue partner in multiple languages ​​in a dialogue session. [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 interview session table. [Figure 6] FIG. 6 is a diagram showing the data structure of the question theme table. [Figure 7] FIG. 7 is a diagram showing the data structure of the item table. [Figure 8]FIG. 8 is a diagram showing the data structure of the question-and-answer definition table. [Figure 9] FIG. 9 is a diagram illustrating the data structure of the set phrase table. [Figure 10] FIG. 10 is a diagram showing the data structure of the response table. [Figure 11] FIG. 11 is a diagram showing the data structure of the evaluation table. [Figure 12] FIG. 12 is a diagram for explaining the setting process in the system. [Figure 13] FIG. 13 is a diagram illustrating an example of an item generation prompt input from the server to the generation AI. [Figure 14] FIG. 14 is a diagram for explaining the interview process in the system. [Figure 15] FIG. 15 is a diagram for explaining the process following FIG. [Figure 16] FIG. 16 is a diagram illustrating a question generation prompt input from the server to the generation AI. [Figure 17] FIG. 17 is a diagram illustrating a basic setting screen on the administrator's terminal device. [Figure 18] FIG. 18 is a diagram illustrating an example of a question theme setting screen on the terminal device of the administrator. [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 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 the server 20 and the user terminal device 10, descriptions 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 a company or other organization. The system sets the base language of the interview session to a first language, and allows the dialogue language for a first question theme to be set to the first language, while setting the dialogue language for a second question theme to a second language different from the first language. The system then has the generation AI generate questions to obtain answers from the applicant, who is the dialogue partner, in the dialogue language corresponding to the question theme. This allows for a simple evaluation of the applicant's communication skills in multiple languages ​​during the interview session.

[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 of an organization that hires personnel. 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 2.5 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 73 (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, an interview session table 2022, a question theme table 2023, an item table 2024, a question-answer definition table 2025, a set phrase table 2026, an answer table 2027, an evaluation table 2028, etc. Each table may be stored in a storage unit external to the server 20.

[0048] The applicant table 2021 stores information about applicants who apply for a job at an organization and participate in online recruitment interviews. The interview session table 2022 stores information about each recruitment interview session for each applicant, including the basic language used in each interview session. The question theme table 2023 stores information about question themes, which are the themes of questions asked to applicants during the recruitment interview. The item table 2024 stores information about multiple items belonging to each question theme. The question-answer definition table 2025 stores specific questions to be presented to applicants and definitions of answers to those questions. The set phrase table 2026 stores set phrases to be presented to applicants at predetermined times. The answer table 2027 stores answers obtained from applicants in interview sessions. The evaluation table 2028 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 employment interview based on information input by the administrator via the terminal device 40. The setting processing module 2034 accepts information related to 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 the setting of the basic language for the employment interview session from the terminal device 40. The setting processing module 2034 accepts the setting of a question theme, which is the theme of the questions to be asked of the applicant during the employment interview, from the terminal device 40. The setting processing module 2034 accepts the setting of information related to the question theme (e.g., supplementary explanation, question time, number of items to be listened to, etc.) from the terminal device 40.

[0054] The setting processing module 2034 sets multiple items belonging to the set 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 items generated does not need to match the number of supplementary explanations. A number of items greater than the number of supplementary explanations may be generated. Also, a predetermined number of items may be generated from a predetermined number of supplementary explanations. The items generated by the generation AI system 30 serve as guidelines for generating questions that delve deeper into the question theme, and may function as a checklist for checking whether the applicant's answers correspond to the requirements of the question theme.

[0055] The dialogue processing module 2035 controls dialogue with the applicant during the job interview. The dialogue processing module 2035 causes the applicant to present questions generated by the generation AI system 30 from 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. Based on the applicant's answers and the multiple items generated by the generation AI, 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. The dialogue processing module 2035 causes the terminal device 10 to present questions to the applicant in a dialogue language set as described below.

[0056] <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.

[0057] 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.

[0058] Fig. 5 is a diagram showing the data structure of the interview session table 2022. As shown in Fig. 5, the interview session table 2022 has columns such as job offer ID, job offer name, base language, and applicant ID, with the interview session ID as a key, for example.

[0059] The job vacancy ID is a column that stores an identifier for uniquely identifying a job vacancy with specific job vacancy conditions (for example, job type, position, recruitment period, number of applicants, etc.). The job vacancy name is a column that stores the name of a job vacancy with the same job vacancy conditions. 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.

[0060] The base language is the language used for the basic matters of the interview session. The base language is used for matters other than the dialogue in the interview session, for which the dialogue language described below is used. For example, the base language may be used for text displayed on the interview screen 70 that is different from the text of the dialogue with the applicant (e.g., title text, display text of UI components, etc.). The base language may be used for explanatory text that is different from the dialogue with the applicant. For example, the base language may be used for explanatory text that indicates to the applicant that the interview has begun. The base language may be used for explanatory text that indicates to the applicant that the interview has ended.

[0061] Fig. 6 is a diagram showing the data structure of the question theme table 2023. As shown in Fig. 6, the question theme table 2023 has columns such as job ID, question order, dialogue language, question theme, and supplementary explanation, with a question theme ID as a key, for example.

[0062] The question theme ID is a column that stores an identifier for uniquely identifying a question theme. The job vacancy ID is the same as the job vacancy ID included in the question theme table 2023, and is a column that stores an identifier for uniquely identifying one job vacancy with specific job vacancy conditions (e.g., job type, position, recruitment period, number of applicants, etc.). The question order is a column that stores the order in which question themes are presented in an interview session. The dialogue language is a column that stores the language (e.g., Japanese, English, etc.) used in the dialogue regarding the corresponding question theme. The question theme is a column that stores text indicating the subject of the question theme. The question theme is entered in a language specified as the corresponding dialogue language. The question theme is composed of subcolumns: "Title," which indicates the title of the question theme, and "Content," which indicates the content of the question theme. The supplementary explanation is a column that stores a further explanation of the question theme to indicate the direction for determining multiple items for further digging into the question theme. The supplementary explanation is entered in a language specified as the base language.

[0063] Fig. 7 is a diagram showing the data structure of the item table 2024. As shown in Fig. 7, the item table 2024 has columns such as item, question theme ID, and listening flag, with the item ID as a key.

[0064] The item ID is a column that stores an identifier for uniquely identifying an item. The item is a column that stores the content of a specific question item that belongs to a question theme. The question theme ID is a column that stores an identifier for identifying the question theme to which the item belongs. The answer 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.

[0065] Fig. 8 is a diagram showing the data structure of the question-and-answer definition table 2025. As shown in Fig. 8, the question-and-answer definition table 2025 has columns such as questions and answer definitions, with item IDs as keys, for example.

[0066] The item ID is the same as the item ID included in the item table 2024, 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 question is a question in the language specified as the dialogue language. 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 is a column that stores the criteria for determining that an answer from the applicant to a question corresponding to each item ID must meet in order to be considered to have "been obtained." The answer definition is written in the basic language, but may also be written in the dialogue language.

[0067] Fig. 9 is a diagram showing the data structure of the set phrase table 2026. As shown in Fig. 9, the set phrase table 2026 has columns such as language and set phrase (wording), with set phrase ID as a key, for example.

[0068] The formula ID is a column that stores an identifier for uniquely identifying the meaning of a formula to be presented to an applicant under a specific situation. Specific situations may include, for example, the start of an interview, the transition to the next question topic, the end of an interview, and a change in the dialogue language. That is, the formula ID is associated with a specific situation. The language is a column that stores the type of language in which the formula is expressed. The formula is a column that stores specific formulas to be presented to an applicant under a specific situation. Formulas are pre-stored for each language type under one formula ID. That is, the server 20 pre-stores formulas corresponding to a first language (e.g., Japanese) and a second language (e.g., English) as phrases to be presented to an applicant during part of an interview session.

[0069] Fig. 10 is a diagram showing the data structure of the answer table 2027. As shown in Fig. 10, the answer table 2027 has columns such as item ID, dialogue language, answer, etc., with answer ID as a key.

[0070] The answer ID is a column that stores an identifier for uniquely identifying an answer from an applicant to a question. The item ID is the same as the item ID included in the item table 2024, and is a column that stores an identifier for uniquely identifying the item of the question answered by the corresponding answer. The dialogue language is the dialogue language set for the question theme of the question answered by the corresponding answer. The answer is the answer from the applicant to the question. In other words, the answer table 2027 stores answers in association with the dialogue language corresponding to the question theme.

[0071] Fig. 11 is a diagram showing the data structure of the evaluation table 2028. As shown in Fig. 11, the evaluation table 2028 has columns such as an interview session ID, a question theme ID, an item ID, an answer ID, and a score, with an evaluation ID as a key, for example.

[0072] The evaluation ID is a column that stores an identifier for uniquely identifying the evaluation of an applicant in one interview session. The interview session ID is the same as the interview session ID included in the interview session table 2022, 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 2023, 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 2024, and is a column that stores an identifier for uniquely identifying an item. The answer ID is the same as the answer ID included in the answer table 2027, and is a column that stores the answer from the applicant.

[0073] The score is a column that stores the score resulting from evaluating the applicant's answer. A higher score value indicates a higher evaluation. The score may be obtained by inputting supplementary explanations, items, questions, answer definitions, evaluation items, evaluation criteria, etc. related to the question theme into the generation AI system 30 and having the generation AI system 30 output the score.

[0074] The evaluation items may be different between answers to a question theme in which a first language is set as the dialogue language and answers to a question theme in which a second language is set as the dialogue language. For example, the evaluation items for a question theme in which a language different from the base language is set as the dialogue language may include language ability, while the evaluation items for a question theme in which the same language as the base language is set as the dialogue language may not include language ability.

[0075] The evaluation criteria may be different for answers to a question theme in which a first language is set as the dialogue language and answers to a question theme in which a second language is set as the dialogue language. For example, the evaluation criteria for a specific evaluation item in a question theme in which a language different from the base language is set as the dialogue language may be set lower than the evaluation criteria for the specific evaluation item in a question theme in which the same language as the base language is set as the dialogue language.

[0076] <5. Operation> The operation of the information processing system 1 will be described.

[0077] 12 is a diagram illustrating the setting process in the system 1. In step S1, the administrator inputs basic settings including job information and a base language on a basic setting screen 50 (described below) displayed on the terminal device 40. In step S2, the terminal device 40 transmits the job information and base language input on the basic setting screen 50 to the server 20. If the administrator selects a first language (for example, Japanese) as the base language, the server 20 accepts input to set the base language of the interactive session to the first language (first setting step).

[0078] In step S3, the administrator inputs a question theme, a dialogue language, and a supplementary explanation on a question theme setting screen 60 (described later) displayed on the terminal device 40. In step S4, the terminal device 40 transmits the question theme, dialogue language, and supplementary explanation input on the question theme setting screen 60 to the server 20. When the administrator sets multiple question themes, the server 20 allows the dialogue language of a first question theme to be set to a first language (e.g., Japanese), and accepts input to set the dialogue language of a second question theme to a second language (e.g., English) (second setting step). In other words, different languages ​​may be mixed as the dialogue languages ​​for multiple question themes.

[0079] The server 20 accepts an input for setting the content of a question theme in the same language as the dialogue language set for the question theme (theme setting step). For example, the server 20 accepts an input for setting the content of a first question theme in the first language for which the first language is set as the dialogue language, and accepts an input for setting the content of a second question theme in the second language for which the second language is set as the dialogue language.

[0080] The server 20 accepts an input for setting a supplementary explanatory text in the basic language for all question themes that supplements the question theme (supplementary explanatory text setting step). Specifically, even when the dialogue language for a target question theme is set to the second language, the server 20 accepts an input for setting a supplementary explanatory text in the first language that supplements the target question theme.

[0081] In step S5, the server 20 generates an item generation prompt P1 for causing the generation AI system 30 to generate multiple items belonging to the question theme based on the information received in steps S2 and S4. For example, the server 20 generates the item generation prompt P1 requesting the output of multiple items belonging to the question theme based on setting information such as the question theme, supplementary explanations for the question theme, and personal information about the applicant. The item generation prompt P1 is automatically generated internally in the server 20.

[0082] 13 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. 13, the item generation prompt P1 includes a request to generate multiple items belonging to each question theme based on the question theme, a supplementary explanatory text for the question theme, and personal information of the applicant (e.g., a resume and curriculum vitae corresponding to the applicant ID).

[0083] Returning to Figure 12, in step S6, the server 20 inputs the item generation prompt P1 to the generation AI system 30, and in step S7, the generation AI system 30 generates multiple items belonging to each question theme in accordance with the item generation prompt P1 (item generation step). In step S8, the generation AI system 30 transmits the multiple items belonging to the generated question theme to the server 20. In step S9, the server 20 stores each item received from the generation AI system 30.

[0084] FIG. 14 is a diagram for explaining the interview processing in system 1. FIG. 15 is a flowchart continuing from FIG. 14. 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 FIG. 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.

[0085] When the server 20 receives the request to start an interview, in step S15 it selects a set phrase corresponding to the start of the interview from the set phrase table 2026 and transmits it to the terminal device 10. In doing so, the server 20 selects a set phrase ID corresponding to the start of the interview from the set phrase table 2026, and then selects a set phrase corresponding to the basic language set in the interview session table 2022. In step S16, the terminal device 10 converts the set phrase received from the server 20 from text to voice and outputs the converted voice to the applicant.

[0086] In this way, in a situation where the first language is applied by setting the first language as the base language, the server 20 presents the applicant with a phrase corresponding to the first language (first phrase presentation step). If the second language is applied by setting the second language as the base language, the server 20 presents the applicant with a phrase corresponding to the second language (second phrase presentation step). Note that the set phrases may be displayed as text on the interview screen 70.

[0087] In step S17, the server 20 identifies one question theme from the multiple set question themes as a current question theme. For example, the server 20 identifies the current question theme according to the question order set in the question theme table 2023. In step S18, the server 20 sets the item with the highest priority among the multiple items belonging to the identified current question theme as a target item, and creates a question generation prompt P2 that causes the generation AI system 30 to generate a question for the applicant about the target item (question generation step). The question generation prompt P2 is automatically created internally in the server 20.

[0088] FIG. 16 is a diagram illustrating a question generation prompt P2 input from the server 20 to the generation AI system 30. As shown in FIG. 16, the question generation prompt P2 includes a request to generate a question for obtaining an answer from the applicant for an item in the current question theme to which the applicant has not yet answered, based on the applicant's answer and a plurality of items belonging to the current question theme. The question generation prompt P2 includes a request to generate a question to be presented to the applicant and a definition of an answer to the question, based on the plurality of items belonging to the current question theme. If the dialogue language of the current question theme is a second language (e.g., English), the question generation prompt P2 includes a question theme written in the second language as the current question theme. As an example, in the question generation prompt P2, the title and representative question sentence of the current question theme are written in the second language, which is the same as the dialogue language, and the sentence requesting the generation of a question for the applicant is written in the first language, which is the same as the base language. In other words, if the dialogue language is different from the base language, the question generation prompt P2 is a hybrid language prompt that mixes the first language and the second language. In the question generation prompt P2, at least a part of the current question theme (for example, the title or the representative question sentence) may be written in the second language that is the same as the dialogue language.

[0089] Returning to Figure 14, in step S19, the server 20 inputs the question generation prompt P2 to the generation AI system 30, and in step S20, 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).

[0090] In step S21, the generation AI system 30 transmits the generated question and a definition of the answer to the question to the server 20. In step S22, 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 S23, the terminal device 10 converts the question from text to speech and outputs the converted speech to the applicant. The question may also be displayed as text on the interview screen 70.

[0091] In step S24, the applicant inputs a voice response to the terminal device 10. In step S25, the terminal device 10 converts the input voice response into text and transmits the converted response to the server 20. The server 20 stores the response from the applicant in association with the dialogue language set for the question theme corresponding to the response (storage step). Note that the conversion between text and voice in this embodiment may be performed by the server 20 instead of the terminal device 10.

[0092] Here, the server 20 may cause the generation AI system 30 to determine whether the language of the applicant's response to the question presented to the applicant matches the dialogue language set for the question theme of the presented question (language determination step). If the generation AI system 30 determines that the language of the applicant's response does not match the set dialogue language, the server 20 may present the applicant with guidance encouraging them to respond in the set dialogue language (guidance presentation step). For example, if an applicant responds to a question in a question theme that requires dialogue in a second language in a language other than the second language, the server 20 presents guidance encouraging the applicant to respond in the second language. Note that if the generation AI system 30 determines that the language of the response does not match the set dialogue language, the server 20 may store the determination result that the language of the applicant's response does not match the set dialogue language without presenting the guidance to the applicant.

[0093] As shown in FIG. 15, in step S26, the server 20 generates an answered item extraction prompt including a request to extract items corresponding to the applicant's answer from multiple items belonging to the question theme. The answered item extraction prompt includes a request to extract items corresponding to the applicant's answer from the multiple items belonging to the current question theme based on the applicant's answer and the multiple items belonging to the current question theme. In step S27, the server 20 inputs the answered item extraction prompt to the generation AI system 30. In step S28, the generation AI system 30 extracts items corresponding to the applicant's answer from the multiple items belonging to the question theme in accordance with the answered item extraction prompt. In step S29, the generation AI system 30 transmits the extracted items to the server 20.

[0094] In step S30, 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 S31, the server 20 removes the extracted item 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 that have not received answers from applicants, and returns to step S18. In this way, the server 20 defines each set of steps from step S18 to step S31 as a question routine, and performs a question step that repeats this question routine.

[0095] If it is determined that the current question theme has ended, the server 20 determines in step S32 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 selects a set phrase corresponding to the change in question theme from the set phrase table 2026 and transmits it to the terminal device 10 in step S33. In this case, the server 20 selects a set phrase ID corresponding to the change in question theme from the set phrase table 2026, and then selects a set phrase corresponding to the base language set in the interview session table 2022. If the dialogue language changes when transitioning to the next question theme, the server 20 may transmit a set phrase explaining the next dialogue language to the terminal device 10. For example, if the dialogue language of the current question theme is a first language and the dialogue language of the next question theme will change to a second language, the server 20 transmits a set phrase indicating that the next dialogue language will be the second language to the terminal device 10. In step S34, the terminal device 10 converts the standard phrases received from the server 20 from text to voice and outputs the converted voice to the applicant. Note that the standard phrases may be displayed as text on the interview screen 70.

[0096] In step S35, the server 20 moves on to the next question theme and returns to step S 18. In this way, the server 20 performs a question step for repeating a question routine consisting of steps S18 to S31 for the next question theme.

[0097] If it is determined that there is no next question, in step S36, the server 20 selects a set phrase corresponding to the end of the interview from the set phrase table 2026 and transmits it to the terminal device 10. In this case, the server 20 selects a set phrase ID corresponding to the end of the interview from the set phrase table 2026, and then selects a set phrase corresponding to the basic language set in the interview session table 2022. In step S37, the terminal device 10 converts the set phrase received from the server 20 from text to voice and outputs the converted voice to the applicant. The set phrase may be displayed as text on the interview screen 70.

[0098] In step S38, the server 20 transmits an end notification indicating that the current interview has been completed to the terminal device 10. In step S39, upon receiving the end notification, the terminal device 10 displays an end screen indicating that the current interview session will end.

[0099] The server 20 may refer to the evaluation table 2028 and display the applicant's evaluation on the interview result screen of the terminal device 40. On the interview result screen, a label indicating the dialogue language for each question theme may be displayed. The server 20 may input at least a question, an answer definition corresponding to the question, the applicant's answer to the question, the evaluation items for the question theme to which the question belongs, and the evaluation criteria for the question theme to which the question belongs to the generative AI system 30, and cause the generative AI system 30 to output a score, which may be used as the applicant's evaluation. The server 20 may also cause the generative AI system 30 to output an evaluation statement in addition to the score.

[0100] The evaluation items may be different for answers to a question topic in which the first language is set as the dialogue language and answers to a question topic in which the second language is set as the dialogue language. For example, for a first question topic in which the dialogue language is the base language (native language), the depth of the logical structure of the answer and the originality of thought may be set as important evaluation items. On the other hand, for a second question topic in which the dialogue language is a second language (foreign language), in addition to these evaluation items, language abilities such as "appropriateness of vocabulary," "accuracy of grammar," and "fluency of speech" may be set as evaluation items.

[0101] The evaluation criteria may be different for answers to a question theme in which a first language is set as the dialogue language and answers to a question theme in which a second language is set as the dialogue language. For example, for a second question theme in which the dialogue language is a second language (foreign language), the evaluation criteria for evaluation items other than language ability (e.g., depth of logical structure) may be relaxed compared to a first question theme in which the dialogue language is a first language (native language). If the server 20 determines that the language of the answers from the applicant does not match the set dialogue language, the server 20 may request the generator A1 to deduct points from the applicant's evaluation score.

[0102] <6. Screen Examples> Next, an example of a screen used in the information processing system 1 will be described. FIG. 17 is a diagram illustrating a basic setting screen 50 on the administrator's terminal device 40. Note that this screen example is merely an example, and various screen configurations and screen contents may be adopted. As shown in FIG. 17, the basic setting screen 50 is a screen on which the administrator inputs basic settings for the online interview in step S1 of FIG. 12. The basic setting screen 50 is, for example, a web browser screen, but it may also be a screen of a dedicated application. The basic setting screen 50 has an input field for job information and an input field for the base language. For example, the basic setting screen 50 has, as input fields for job information, a job ID input section 51, a job name input section 52, a job requirements input section 54, etc. The basic setting screen 50 has a base language input section 53 as an input field for the base language. The basic setting screen 50 also has a confirm button section 55 for confirming the input content and sending it to the server 20.

[0103] The job vacancy ID input section 51 is a section in which the administrator inputs a job vacancy ID. The job vacancy ID may be automatically input by the server 20. The job vacancy name input section 52 is a section in which the administrator inputs the title of the job vacancy. The job vacancy condition input section 54 is a section in which the administrator inputs the job vacancy conditions (e.g., job type, position, recruitment period, number of people to be recruited, etc.).

[0104] The basic language input section 53 is a field where the administrator inputs the basic language to be used for basic matters in the interview session. The basic language is used for matters other than dialogue in the interview session. For example, the basic language may be used for the title text on the interview screen 70, the display text of UI components, etc. The basic language may be the language used when outputting the aforementioned standard phrases to the applicant. The basic language input section 53 is displayed so that the dialogue language for the question theme can be selectively set to a first language or a second language, for example, using a pull-down menu. In the example of Figure 17, Japanese is set as the first language for the basic language. The basic language may also be used for dialogue in the interview session.

[0105] The confirm button section 55 is a UI component for confirming the settings displayed on the basic setting screen 50 and transmitting them to the server 20. When the administrator using the terminal device 40 selects the confirm button section 55, the settings displayed on the basic setting screen 50 are transmitted to the server 20.

[0106] FIG. 18 is a diagram illustrating a question theme 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 may be adopted. As shown in FIG. 18, the question theme setting screen 60 is a screen on which the administrator inputs settings such as the question theme for the online interview in step S3 of FIG. 12. The question theme setting screen 60 is, for example, a web browser screen, but it may also be a screen for a dedicated application. The question theme setting screen 60 has an input field for the question theme, an input field for supplementary explanations of the question theme, and an input field for the dialogue language used in the interview session. A first question theme is set on one question theme setting screen 60, and a second question theme is set on another question theme setting screen 60 of the same format. Note that the question theme setting screen 60 does not have to be a screen for setting a single question theme, but may be a screen for simultaneously setting multiple question themes.

[0107] For example, the question theme setting screen 60 has, as input fields for information about the question theme, a question theme input section 61, a supplementary explanation input section 64, a dialogue language input section 65, etc. The question theme setting screen 60 also has a confirm button section 66 for confirming the input content and transmitting it to the server 20.

[0108] The question theme input section 61 is a field where the content of a question theme in an interview session is input. For example, the question theme input section 61 includes a question title input section 62 and a representative question input section 63. The question title input section 62 is a field where a question theme title, which is the title of a question theme, is input. For example, question theme titles such as "Self-introduction," "Strengths," or "Negotiating skill" are input. The representative question input section 63 is a field where a representative question, which is a representative question for a question theme, is input. For example, the representative question may be the opening question for a question theme. In this case, if the question title is "Self-introduction," the question content may be something like "Please introduce yourself." Note that the question theme may only include the question title, omitting the representative question. The supplementary explanation input section 64 is a field where the administrator inputs supplementary explanations for the question theme in free text to indicate the direction for determining multiple items for further digging into the question theme.

[0109] The dialogue language input section 65 is a field where the administrator inputs the dialogue language to be used in dialogue with the applicant during the interview session. The dialogue language input section 65 is displayed so that the dialogue language of the question theme can be selectively set to a first language or a second language, for example, using a pull-down menu (display step). In the example of FIG. 18, English, which is the second language, is set as the dialogue language. The dialogue language is the language used for questions presented to the applicant from the terminal device 10 during the interview session and for the applicant's answers to those questions. The dialogue language can be set to the same language as the base language, but can also be set to a language different from the base language. The administrator can set the dialogue language to the first language when setting a first question theme on one question theme setting screen 60, and can set the dialogue language to the second language when setting a second question theme on another question theme setting screen 60.

[0110] The Confirm button section 66 is a UI component for confirming the settings displayed on the question theme 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 question theme setting screen 60 to the server 20.

[0111] 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 interview title display section 71, a dialogue language display section 72, an avatar 73, an applicant screen 74, and an exit button 75.

[0112] The interview title display unit 71 displays the interview title (e.g., "Employment Interview") using the basic language set in steps S1 and S2 of Fig. 12. The dialogue language display unit 72 displays the dialogue language of the current question theme from among the dialogue languages ​​set in steps S3 and S4 of Fig. 12.

[0113] The avatar 73 plays the role of a virtual interviewer. The avatar 73 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 73 based on the speech data received from the server 20. When the avatar 73 speaks, the mouth of the avatar 73 may be depicted as moving. The speech of the avatar 73 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 73 does not need to perform a speaking action.

[0114] The applicant screen 74 displays an image of the applicant captured by the camera 160 of the terminal device 10. The applicant operating the terminal device 10 selects the exit button 75 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 of the terminal device 10 is enabled.

[0115] <Summary> As described above, system 1 allows a language different from the base language in an interview session to be set as the dialogue language for each question theme. Then, the generation AI system 30 can generate questions in the dialogue language of the question theme and present them to the applicant. For example, while the base language is Japanese, the dialogue language for the first question theme can be Japanese and the dialogue language for the second question theme can be English. This allows an organization's hiring manager to carefully evaluate the applicant's personality, thinking ability, etc. in their native language while accurately measuring their language ability for specific questions. This makes it possible to easily evaluate an applicant's communication skills in multiple languages ​​within a single interview session.

[0116] (Variation) 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 in which the person at the first interview desk in a specialized business is used as an avatar, telephone reception work, user interviews, and role-play practice for sales or customer service. In other words, the person being spoken to is not limited to a job applicant, but may be any person who is expected to answer questions.

[0117] 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 73, but for example, the applicant may also 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.

[0118] In the above-described embodiment, the server 20 inputs prompts to the generative AI system 30 in steps S18 and S26 of Figure 14, but a comprehensive prompt may also 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.

[0119] 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).

[0120] In the above-described embodiment, the server 20 transmitted the formula phrase to the terminal device 10 without going through the generation AI system 30. However, the server 20 may request the generation AI system 30 to generate a sentence including the formula phrase without modifying the formula phrase, and may transmit the sentence output by the generation AI system 30 to the terminal device 10. When a question output from the AI ​​system 30 includes a formula phrase, the question should be generated in the dialogue language, so the formula phrase may be output in the second language. In the above-described embodiment, the base language was set to the first language, thereby outputting the formula phrase in the first language. However, the base language may be set to the second language, thereby outputting the formula phrase in the second language.

[0121] <Basic computer hardware configuration> 20 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.

[0122] 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.

[0123] The main memory device 902 is used to temporarily store programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0124] The auxiliary storage device 903 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] <Basic functional configuration of computer 90> A description will now be given of the functional configuration of the computer realized by the basic hardware configuration of the computer 90. The computer comprises at least the functional units of a control unit, a storage unit, and a communication unit.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] (Addendum) The matters described in the above embodiments will be supplemented below.

[0145] (Appendix 1) A program for operating a computer having a processor and a memory, the program causing the processor to execute the following steps: a first setting step for accepting input for setting the basic language of an interaction session to a first language; a second setting step for accepting input for setting the interaction language of a second question theme to a second language, while allowing the interaction language of a first question theme to be set to the first language, for a plurality of question themes including a first question theme and a second question theme in the interaction session; a question generation step for causing a generation AI to generate a question to obtain an answer from a dialogue partner, for a question theme selected from the plurality of question themes, in a dialogue language corresponding to the selected question theme; and a question presentation step for presenting the question generated by the generation AI to the dialogue partner.

[0146] (Appendix 2) 2. The program of claim 1, further causing the processor to execute a theme setting step of accepting input in a second language to set a second question theme.

[0147] (Appendix 3) The program further causes the processor to execute a supplementary explanation setting step of receiving input to set a supplementary explanation in the first language that supplements the second question theme, and an item generation step of causing the generation AI to generate a plurality of items belonging to the second question theme based on the second question theme and the supplementary explanation, wherein the question generation step includes causing the generation AI to generate a question regarding one of the plurality of items based on the response of the dialogue partner.

[0148] (Appendix 4) A program as described in any of Appendices 1 to 3, in which phrases corresponding to a first language and a second language are pre-stored as phrases to be presented to a dialogue partner during a portion of a dialogue session, and the program causes a processor to execute a first phrase presentation step of presenting phrases corresponding to the first language to the dialogue partner in a situation in which the first language is applied, and a second phrase presentation step of presenting phrases corresponding to the second language to the dialogue partner in a situation in which the second language is applied.

[0149] (Appendix 5) 5. The program according to any one of appendices 1 to 4, further causing the processor to execute a storage step of storing the answer from the dialogue partner in association with the dialogue language corresponding to the selected question theme.

[0150] (Appendix 6) The program described in any one of Appendices 1 to 5, further causing the processor to execute a language determination step in which the generation AI determines whether the language of the response from the dialogue partner to the posed question matches the dialogue language set in the question theme of the posed question.

[0151] (Appendix 7) The program described in Appendix 6, wherein the program further causes the processor to execute a guidance presentation step of presenting guidance to the dialogue partner encouraging the dialogue partner to respond in the dialogue language that has been set, when it is determined that the language of the response does not match the dialogue language that has been set.

[0152] (Appendix 8) The program according to any one of Appendices 1 to 7, further causing the processor to execute an evaluation step in which the answer is evaluated by the generation AI, and at least one of the evaluation items and evaluation criteria in the evaluation step differ between the answer to the first question theme and the answer to the second question theme.

[0153] (Appendix 9) The dialogue in the dialogue session is an interview for recruitment, and the program is described in any of Appendices 1 to 8.

[0154] (Appendix 10) A program described in any of Appendices 1 to 9, wherein the program further causes the processor to execute a display step of displaying on an administrator terminal a setting screen that allows the dialogue language for each of a plurality of question themes to be selectively set to a first language or a second language.

[0155] (Appendix 11) 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 10. (Appendix 12) 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 10.

[0156] (Appendix 13) 11. A system comprising a configuration for performing all of the steps of any one of claims 1 to 10. [Explanation of symbols]

[0157] 1. Information Processing Systems 10 Applicant's (interviewee's) terminal device 20 servers 25 memory 30 Generative AI System 40 Administrator's terminal device 50 Basic settings screen 60 Question theme setting screen

Claims

1. A program for operating a computer having a processor and a memory, The program causes the processor to: a first setting step of receiving an input for setting a base language of the interactive session to a first language; a second setting step of accepting an input for setting a dialogue language of a plurality of question themes including a first question theme and a second question theme in the dialogue session to a second language while allowing the dialogue language of the first question theme to be set to the first language; a question generation step of inputting a prompt to the generation AI in the dialogue language corresponding to a question theme selected from the plurality of question themes, the prompt including a request for the generation AI to generate a question for obtaining an answer from a dialogue partner based on information about the selected question theme; a question presentation step of presenting the question generated by the generation AI to the conversation partner; an evaluation step of inputting a prompt to the generation AI including a request for the generation AI to evaluate an answer from the dialogue partner to the presented question; A program that executes.

2. The program according to claim 1 , further causing the processor to execute a theme setting step of accepting an input in the second language to set the second question theme.

3. The program causes the processor to: a supplemental explanation setting step of receiving an input for setting a supplemental explanation in the first language that supplementarily explains the second question theme; and further executing an item generating step of causing the generation AI to generate a plurality of items belonging to the second question theme based on the second question theme and the supplemental explanation text; The program of claim 1 , wherein the request included in the prompt that causes the generation AI to generate the question includes causing the generation AI to generate the question regarding one of the plurality of items based on the response of the conversation partner.

4. phrases corresponding to the first language and the second language are stored in advance as phrases to be presented to the dialogue partner in a part of the dialogue session; The program causes the processor to: a first word presentation step of presenting the word corresponding to the first language to the dialogue partner in a situation in which the first language is applied; and a second phrase presentation step of presenting the phrase corresponding to the second language to the conversation partner in a situation in which the second language is applied.

5. 2. The program according to claim 1, further causing the processor to execute a storage step of storing the answer from the dialogue partner in association with the dialogue language corresponding to the selected question theme.

6. The program of claim 1, further causing the processor to execute a language determination step of inputting a prompt to the generation AI including a request for the generation AI to determine whether the language of the response from the dialogue partner to the presented question matches the dialogue language set in the question theme of the presented question.

7. 7. The program according to claim 6, further causing the processor to execute a guidance presentation step of presenting guidance to the dialogue partner encouraging the dialogue partner to respond in the set dialogue language when it is determined that the language of the response does not match the set dialogue language.

8. The program described in claim 1, wherein at least one of the evaluation items and evaluation criteria in the evaluation step differs between the answer to the first question theme and the answer to the second question theme.

9. The program of claim 1 , wherein the interaction in the interaction session is an interview for a job offer.

10. 2. The program according to claim 1, further causing the processor to execute a display step of displaying on an administrator terminal a setting screen on which the dialogue language for each of the plurality of question themes can be selectively set to the first language or the second language.

11. A computer-implemented method comprising a processor and a memory, wherein the processor performs all the steps of any one of claims 1 to 10.

12. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps according to any one of claims 1 to 10.

13. A system comprising an arrangement for performing all the steps of any one of claims 1 to 10.

Images