System

Abstract

An object of a system according to an embodiment is to realize an efficient and fair interview.SOLUTION: A system according to an embodiment includes a AI clone generation unit, a dialogue generation unit, and an evaluation unit. The AI clone generation unit generates a AI clone based on a profile of a user and a past dialogue. The dialogue generation unit generates a dialogue using the AI clone generated by the AI clone generation unit. The evaluation unit evaluates the answer of the interviewer based on the interaction generated by the interaction generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it is difficult to ensure the efficiency and fairness of interviews, and there is room for improvement.

[0005] The system according to the embodiment aims to realize an efficient and fair interview. [Means for solving the problem]

[0006] The system according to the embodiment includes an AI clone generation unit, a dialogue generation unit, and an evaluation unit. The AI ​​clone generation unit generates an AI clone based on a user's profile and past dialogue data. The dialogue generation unit generates a dialogue using the AI ​​clone generated by the AI ​​clone generation unit. The evaluation unit evaluates the interviewee's responses based on the dialogue generated by the dialogue generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can realize an efficient and fair interview. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The virtual interview system according to the embodiment of the present invention is a system that uses AI clones to realize efficient and fair interviews. This virtual interview system offers various benefits such as time reduction, elimination of blurring, and language support, allowing you to experience the future of communication.

[0029] A virtual interview system according to an embodiment includes an AI clone generation unit, a dialogue generation unit, and an evaluation unit. The AI ​​clone generation unit generates an AI clone based on a user's profile and past dialogue data. For example, the AI ​​clone generation unit generates an AI clone based on profile information such as the user's age, gender, occupation, and interests. The AI ​​clone generation unit also analyzes past dialogue data (text data, voice data, dialogue history, etc.) to learn user characteristics. The dialogue generation unit generates a dialogue using the AI ​​clone generated by the AI ​​clone generation unit. For example, the dialogue generation unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to generate a dialogue based on prompts including the purpose of the interview and questions. The dialogue generation unit also learns the voice, speaking style, facial expressions, etc. of the interviewee to realize a realistic dialogue. The evaluation unit evaluates the interviewee's responses based on the dialogue generated by the dialogue generation unit. For example, the evaluation unit evaluates the interviewee's responses based on predetermined evaluation criteria and provides feedback using consistent standards. The evaluation unit also uses the accuracy of answers, emotional expression, and conversational fluency as evaluation criteria. This allows the virtual interview system according to the embodiment to realize efficient and fair interviews. For example, there is no need to adjust interview schedules, and interviews can be conducted anytime, anywhere. Furthermore, the AI ​​clone generates answers quickly, shortening the interview time. Furthermore, the AI ​​clone can respond consistently without being affected by emotions or physical condition. This improves the quality of the interview, and allows the interviewee to feel as if they are conversing with a real person.

[0030] The dialogue generation unit can analyze the non-verbal behavior of the interviewee and generate dialogue content based on the non-verbal behavior. The dialogue generation unit, for example, analyzes the gestures of the interviewee and adjusts the dialogue content based on that information. For example, if the interviewee waves their hand, dialogue indicating a greeting or agreement is generated. The dialogue generation unit also tracks the interviewee's gaze and analyzes the direction and movement of their gaze. For example, if the interviewee is looking at a particular document, questions or comments related to that document are generated. The dialogue generation unit also infers the interviewee's intentions and emotions based on the non-verbal behavior data and conducts dialogue accordingly. For example, if the interviewer nods their head, dialogue indicating agreement is generated. This makes it possible to provide dialogue based on the interviewee's non-verbal behavior.

[0031] The dialogue generation unit can customize an individual dialogue style based on the interviewee's past dialogue data. The dialogue generation unit, for example, analyzes the interviewee's past dialogue data and customizes the individual dialogue style. For example, it generates a dialogue based on the interviewee's preferred topics and question formats. The dialogue generation unit also learns the interviewee's speaking style and expression based on the past dialogue data and conducts a dialogue that matches that. For example, it incorporates phrases and expressions that the interviewee frequently uses. The dialogue generation unit also references the interviewee's past dialogue history and generates questions and comments that take into account the content of previous dialogues. For example, it revisits topics that were discussed in the previous interview. This makes it possible to provide an individual dialogue style based on the interviewee's past dialogue data.

[0032] The system can also be applied to at least one other field of education or counseling. For example, in the field of education, the system introduces dialogue using an AI clone to support students' learning. For example, it provides questions and explanations tailored to each student's individual learning progress. In the field of counseling, the system utilizes an AI clone to engage in dialogue tailored to the client's emotions and concerns. For example, it provides stress relief and mental health support. In the field of medicine, the system introduces dialogue using an AI clone to support communication with patients. For example, it conducts pre-consultation interviews and health consultations. This allows the system to be applied to other fields such as education and counseling.

[0033] The system allows multiple AI clones to cooperate and converse, enabling it to handle more complex scenarios. For example, the system simulates a group discussion in which multiple AI clones cooperate, where AI clones with different perspectives and opinions engage in a debate. The system also allows multiple AI clones to work together to support complex problem-solving, where AI clones with different expertise cooperate to propose solutions. The system also allows multiple AI clones to cooperate in scenario-based training, where emergency response or business simulations are carried out, enabling it to handle more complex scenarios.

[0034] The system can analyze the progress of the interview in real time and suggest the most appropriate questions and answers. For example, the system monitors the progress of the interview in real time and suggests the next most appropriate question. For example, it generates related questions based on the interviewer's answers. The system also analyzes the progress of the interview and provides optimal feedback to the interviewer's answers in real time. For example, if the interviewer's answers are insufficient, it suggests supplementary questions. The system also evaluates the interviewer's level of understanding and interest based on the progress of the interview and generates questions and answers accordingly. For example, it asks questions related to topics in which the interviewer has shown interest. In this way, the system can analyze the progress of the interview in real time and suggest the most appropriate questions and answers.

[0035] The system can automatically summarize the contents of an interview so that it can be referenced later. For example, the system analyzes the contents of an interview in real time and automatically generates a summary. For example, it extracts important points and keywords to create a summary. The system can also analyze recorded data of an interview and automatically generate a text summary. For example, it can use speech recognition technology to convert the contents of the interview into text and create a summary. The system can also summarize the contents of the interview and save it in a database so that it can be referenced later. For example, it can save the summary data in a searchable format. This allows the contents of the interview to be automatically summarized and referenced later.

[0036] The system automatically adjusts interview schedules, enabling interviews to be conducted at optimal times. For example, the system analyzes the interviewee's schedule and automatically suggests the optimal timing for the interview. For example, it adjusts the interview date and time based on the interviewee's free time. The system also automatically adjusts interview schedules, allowing interviews to be conducted at optimal times that suit the interviewee's convenience. For example, it adjusts the schedule in cooperation with the interviewee's calendar. The system also automates interview schedule adjustments, reducing the burden on the interviewee. For example, it suggests the optimal schedule based on the interviewee's desired date and time. This allows the system to automatically adjust interview schedules, enabling interviews to be conducted at optimal times.

[0037] The system can also apply the efficiency of interviews to other business processes. For example, the system applies interview efficiency technology to meetings, analyzing the progress of a meeting in real time and suggesting the most appropriate agenda item and remarks. For example, the system suggests the next agenda item based on the progress of the meeting. The system also supports the efficiency of presentations. For example, the system analyzes the presenter's speaking style and content in real time and provides optimal advice. The system also applies efficiency technology to business processes in general, analyzing the progress of work in real time and making optimal suggestions. For example, the system suggests tasks based on the progress of a project. In this way, the efficiency of interviews can be applied to other business processes.

[0038] The system can automatically translate the contents of an interview to facilitate communication between participants who speak different languages. For example, the system can translate the contents of an interview in real time to support communication between participants who speak different languages. For example, it can perform automatic translation from English to Japanese. The system can also analyze recorded interview data and automatically generate text translations. For example, it can convert the contents of an interview into text and translate and provide it in different languages. The system can also display the contents of an interview in multiple languages ​​in real time to enable participants who speak different languages ​​to understand it simultaneously. For example, it can display subtitles and translate voice. This allows the system to automatically translate the contents of an interview to facilitate communication between participants who speak different languages.

[0039] The system can make the evaluation criteria for interviews transparent and share them with interviewers in advance. For example, the system shares the evaluation criteria for interviews with interviewers in advance to ensure transparency. For example, it provides a document that clearly states the evaluation items and criteria. The system also makes the evaluation criteria for interviews available online so that interviewers can check them in advance. For example, it posts the evaluation criteria on a website. The system also explains the evaluation criteria for interviews to interviewers and holds seminars and workshops to deepen their understanding. For example, it holds an explanatory meeting on the evaluation criteria. In this way, the evaluation criteria for interviews can be made transparent and shared with interviewers in advance.

[0040] The system can automatically record the results of interviews so that they can be verified later. For example, the system automatically records and films the contents of interviews and stores them in a database so that they can be verified later. For example, the audio and video of the interviews are stored in the cloud. The system can also automatically generate the results of interviews as text data so that they can be referenced later. For example, the system can convert the contents of the interviews into text using voice recognition technology and store the text in a database. The system can also automatically record the evaluation results of the interviews so that they can be verified later. For example, the system can automatically perform scoring based on evaluation criteria and save the results. In this way, the results of the interviews can be automatically recorded and verified later.

[0041] The system can provide fair evaluations while maintaining the anonymity of interviewees. For example, the system anonymizes the personal information of interviewees, allowing evaluators to evaluate without bias. For example, evaluations are made while concealing the interviewee's name and gender. The system also provides fair evaluations based on evaluation criteria while maintaining the anonymity of interviewees. For example, evaluations are made based only on the content of the interviewee's responses. To ensure the anonymity of interviewees, the system also conducts interviews in a format where the evaluator and interviewer do not meet face-to-face. For example, the interview is conducted via online text chat. This allows for fair evaluations while maintaining the anonymity of interviewees.

[0042] The system can also apply fair evaluation criteria to other evaluation processes. For example, the system applies fair evaluation criteria for interviews to performance reviews, thereby evaluating employees using consistent standards. For example, it standardizes evaluation items and criteria. The system also applies fair evaluation criteria to recruitment processes, thereby evaluating candidates using consistent standards. For example, it standardizes evaluation criteria for interviews and exams. The system also applies fair evaluation criteria to evaluation processes at educational institutions, thereby evaluating students using consistent standards. For example, it standardizes evaluation criteria for exams and assignments. This allows fair evaluation criteria to be applied to other evaluation processes.

[0043] The system can integrate the interview evaluation results with other data to perform a comprehensive evaluation. For example, the system can integrate the interview evaluation results with performance data to perform a comprehensive evaluation. For example, the system can combine the interview evaluation score and performance data to perform a comprehensive evaluation. The system can also integrate the interview evaluation results with other performance data to perform a comprehensive evaluation of the employee. For example, the system can combine project results and team evaluations to perform an evaluation. The system can also integrate the interview evaluation results with academic performance data from an educational institution to perform a comprehensive evaluation of the student. For example, the system can combine test scores and extracurricular activity evaluations to perform an overall evaluation. In this way, the system can integrate the interview evaluation results with other data to perform a comprehensive evaluation.

[0044] The system can automatically adjust the progress of the interview to keep the pace steady. For example, the system analyzes the progress of the interview in real time and makes adjustments to keep the pace steady. For example, it suggests the next question based on the interviewer's response time. The system also automatically adjusts the progress of the interview to keep the pace steady for the interviewer. For example, it adjusts the timing of questions based on the interviewer's response. The system also monitors the progress of the interview and provides feedback in real time to keep the pace steady. For example, if the interviewer is speaking too quickly, it suggests that the interviewer speak more slowly. In this way, the system automatically adjusts the progress of the interview to keep the pace steady.

[0045] The system can simulate the content of an interview in advance and select the optimal scenario. For example, the system simulates the content of an interview in advance and selects the optimal scenario. For example, a scenario is generated based on the profile of the interviewee. The system also simulates an interview and predicts the interviewee's reaction to select the optimal scenario. For example, the system adjusts the scenario based on past interview data. The system also simulates interview scenarios in advance and selects the optimal scenario based on the interviewee's level of understanding and interest. For example, the system prioritizes topics that the interviewee is interested in. In this way, the system simulates the content of the interview in advance and selects the optimal scenario.

[0046] The system can also apply the elimination of inconsistencies to other communication processes. For example, the system applies the elimination of inconsistencies to negotiations, analyzing the progress of the negotiations in real time and making optimal proposals. For example, the system generates the next proposal according to the progress of the negotiations. The system also analyzes the progress in real time and suggests optimal remarks to eliminate inconsistencies in discussions. For example, the system provides feedback in accordance with the progress of the discussion. The system also applies the elimination of inconsistencies to other communication processes in general, analyzing the progress in real time and making optimal proposals. For example, the system suggests tasks according to the progress of a project. This allows the elimination of inconsistencies to be applied to other communication processes.

[0047] The system can visualize the progress of the interview and make adjustments in real time. For example, the system visualizes the progress of the interview in real time, allowing the interviewer to understand the progress. For example, the progress may be displayed in a graph or chart. The system also visualizes the progress of the interview and allows the interviewer to adjust the progress. For example, the system suggests the next question or answer depending on the progress. The system also monitors the progress of the interview in real time and provides feedback to adjust the progress. For example, if the interviewer is falling behind, the system suggests that the interviewer speed up. In this way, the progress of the interview is visualized and adjustments may be made in real time.

[0048] The system can translate the contents of an interview in real time, facilitating communication between participants who speak different languages. For example, the system can translate the contents of an interview in real time, supporting communication between participants who speak different languages. For example, it can perform automatic translation from English to Japanese. The system can also analyze recorded interview data and automatically generate text translations. For example, it can convert the contents of an interview into text and provide it translated into different languages. The system can also display the contents of an interview in multiple languages ​​in real time, allowing participants who speak different languages ​​to understand it simultaneously. For example, it can display subtitles and translate voice. This allows the system to translate the contents of an interview in real time, facilitating communication between participants who speak different languages.

[0049] The system can record interview content in multiple languages ​​so that it can be referenced later. For example, the system records interview content in multiple languages ​​so that it can be referenced later. For example, the system records interview content in English, Japanese, Chinese, etc. The system also converts recorded interview data into text in multiple languages ​​so that it can be referenced later. For example, the system converts interview content into text, translates it into different languages, and saves it. The system also records interview content in multiple languages ​​and saves it in a searchable format. For example, the system tags interview content in multiple languages ​​so that it can be searched. This allows interview content to be recorded in multiple languages ​​so that it can be referenced later.

[0050] The system supports the progress of an interview in multiple languages, enabling communication that transcends language barriers. The system, for example, supports the progress of an interview in multiple languages, enabling communication that transcends language barriers. For example, it displays the progress of the interview in multiple languages. The system also supports the progress of an interview in multiple languages, allowing participants who speak different languages ​​to understand at the same time. For example, it translates and displays interview questions and answers in real time. The system also supports the progress of an interview in multiple languages, enabling participants to communicate in their own language. For example, it performs voice translation and displays subtitles. In this way, the system supports the progress of an interview in multiple languages, enabling communication that transcends language barriers.

[0051] The system can also apply multilingual support to other communication processes. For example, the system applies multilingual support technology to international conferences, allowing participants to communicate in different languages. For example, the system translates and displays the content of the conference in real time. The system also supports multilingual support for webinars, allowing participants to understand the content in their own language. The system also applies multilingual support technology to other communication processes in general, allowing participants of different languages ​​to understand at the same time. For example, the content of a presentation can be displayed in multiple languages. This allows multilingual support to be applied to other communication processes.

[0052] The system can automatically summarize the contents of an interview and provide it in different languages. For example, the system automatically summarizes the contents of an interview and provides it in different languages. For example, the system summarizes the contents of the interview and displays it in English, Japanese, Chinese, etc. The system also analyzes recorded data of the interview, automatically generates summaries, and translates them into different languages. For example, the system converts the contents of the interview into text and provides the summaries in multiple languages. The system also automatically summarizes the contents of the interview and saves them in a searchable format in different languages. For example, the system tags the summary data in multiple languages ​​and makes it searchable. This allows the system to automatically summarize the contents of the interview and provide it in different languages.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The system can analyze the nonverbal behavior of the interviewee and generate dialogue content based on that nonverbal behavior. For example, if the interviewee waves their hand, dialogue indicating a greeting or agreement can be generated. If the interviewee is looking at a specific document, questions or comments related to that document can be generated. Furthermore, if the interviewer nods their head, dialogue indicating agreement can be generated. This makes it possible to provide dialogue based on the interviewee's nonverbal behavior.

[0055] The system can customize individual conversation styles based on the interviewee's past conversation data. For example, it generates conversations based on the interviewee's preferred topics and question formats. It also learns the interviewee's speaking style and expression and conducts conversations that match those. It also references the interviewee's past conversation history and generates questions and comments that take into account the content of previous conversations. This makes it possible to provide an individual conversation style based on the interviewee's past conversation data.

[0056] The system can also be applied to at least one other field of education or counseling. For example, in the field of education, dialogue using an AI clone can be introduced to support students' learning. For example, questions and explanations tailored to each individual's learning progress can be provided. In the field of counseling, an AI clone can be used to engage in dialogue tailored to the client's emotions and concerns. For example, stress reduction and mental health support can be provided. Furthermore, in the field of medicine, dialogue using an AI clone can be introduced to support communication with patients. For example, pre-examination interviews and health consultations can be conducted. This allows the system to be applied to other fields such as education and counseling.

[0057] The system can handle more complex scenarios by having multiple AI clones cooperate and converse. For example, multiple AI clones can cooperate to simulate a group discussion, where AI clones with different perspectives and opinions engage in a debate. Multiple AI clones can also work together to assist in solving complex problems, where AI clones with different expertise collaborate to propose solutions. Furthermore, multiple AI clones can cooperate to conduct scenario-based training, where emergency response or business simulations are carried out. This allows multiple AI clones to cooperate and converse to handle more complex scenarios.

[0058] The system can analyze the progress of the interview in real time and suggest the most appropriate questions and answers. For example, it generates related questions based on the interviewer's answers. It can also analyze the progress of the interview and provide optimal feedback to the interviewer's answers in real time. For example, if the interviewer's answers are insufficient, it can suggest supplementary questions. Furthermore, it evaluates the interviewer's level of understanding and interest based on the progress of the interview and generates questions and answers accordingly. For example, it asks questions related to topics that the interviewer has shown interest in. This allows the system to analyze the progress of the interview in real time and suggest the most appropriate questions and answers.

[0059] The system can automatically summarize the contents of an interview for later reference. For example, the system may analyze the contents of an interview in real time and automatically generate a summary. For example, it may extract important points and keywords to create a summary. It may also analyze recorded interview data and automatically generate a text summary. For example, it may use speech recognition technology to convert the interview contents into text and create a summary. It may also summarize the interview contents and save it in a database for later reference. For example, it may save the summary data in a searchable format. This allows the contents of an interview to be automatically summarized and referenced later.

[0060] The system can automatically adjust interview schedules and conduct interviews at the optimal time. For example, it analyzes the interviewee's schedule and automatically suggests the optimal interview timing. For example, it adjusts the interview date and time based on the interviewee's free time. It can also automatically adjust interview schedules to conduct interviews at the optimal time that suits the interviewee's convenience. For example, it adjusts the schedule in conjunction with the interviewee's calendar. It can also automate interview schedule adjustments, reducing the burden on the interviewee. For example, it suggests the optimal schedule based on the interviewee's desired date and time. This allows the system to automatically adjust interview schedules and conduct interviews at the optimal time.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The AI ​​clone generator generates an AI clone based on the user's profile and past dialogue data. For example, it generates an AI clone based on profile information such as the user's age, gender, occupation, and interests, and analyzes past dialogue data (text data, voice data, dialogue history, etc.) to learn the user's characteristics. Step 2: The dialogue generation unit generates dialogue using the AI ​​clone generated by the AI ​​clone generation unit. For example, it uses a generation AI (text generation AI or multimodal generation AI) to generate dialogue based on prompts including the purpose of the interview and the questions, and learns the voice, speaking style, facial expressions, etc. of the interviewee to realize a realistic dialogue. Step 3: The evaluation unit evaluates the interviewee's answers based on the dialogue generated by the dialogue generation unit. For example, the evaluation unit evaluates the interviewee's answers based on pre-defined evaluation criteria and provides consistent feedback. Evaluation criteria include the accuracy of the answers, the expression of emotions, and the fluency of the dialogue.

[0063] (Example 2) The virtual interview system according to the embodiment of the present invention is a system that uses AI clones to realize efficient and fair interviews. This virtual interview system offers various benefits such as time reduction, elimination of blurring, and language support, allowing you to experience the future of communication.

[0064] A virtual interview system according to an embodiment includes an AI clone generation unit, a dialogue generation unit, and an evaluation unit. The AI ​​clone generation unit generates an AI clone based on a user's profile and past dialogue data. For example, the AI ​​clone generation unit generates an AI clone based on profile information such as the user's age, gender, occupation, and interests. The AI ​​clone generation unit also analyzes past dialogue data (text data, voice data, dialogue history, etc.) to learn user characteristics. The dialogue generation unit generates a dialogue using the AI ​​clone generated by the AI ​​clone generation unit. For example, the dialogue generation unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to generate a dialogue based on prompts including the purpose of the interview and questions. The dialogue generation unit also learns the voice, speaking style, facial expressions, etc. of the interviewee to realize a realistic dialogue. The evaluation unit evaluates the interviewee's responses based on the dialogue generated by the dialogue generation unit. For example, the evaluation unit evaluates the interviewee's responses based on predetermined evaluation criteria and provides feedback using consistent standards. The evaluation unit also uses the accuracy of answers, emotional expression, and conversational fluency as evaluation criteria. This allows the virtual interview system according to the embodiment to realize efficient and fair interviews. For example, there is no need to adjust interview schedules, and interviews can be conducted anytime, anywhere. Furthermore, the AI ​​clone generates answers quickly, shortening the interview time. Furthermore, the AI ​​clone can respond consistently without being affected by emotions or physical condition. This improves the quality of the interview, and allows the interviewee to feel as if they are conversing with a real person.

[0065] The dialogue generation unit can estimate the emotions of the interviewee in real time and generate dialogue content according to the emotions. The dialogue generation unit, for example, analyzes the facial expressions and tone of voice of the interviewee to estimate the emotions in real time. For example, if the interviewee is nervous, it generates questions and comments to relax the interviewee. The dialogue generation unit also adjusts the tone and content of the dialogue according to the emotional state of the interviewee. For example, if the interviewee is excited, it generates dialogue in a calm tone to respond calmly. The dialogue generation unit also provides feedback that matches the emotions of the interviewee based on the emotion estimation data. For example, if the interviewee is feeling anxious, it generates feedback that gives the interviewer a sense of security. This makes it possible to provide dialogue that matches the emotions of the interviewee.

[0066] The dialogue generation unit can analyze the non-verbal behavior of the interviewee and generate dialogue content based on the non-verbal behavior. The dialogue generation unit, for example, analyzes the gestures of the interviewee and adjusts the dialogue content based on that information. For example, if the interviewee waves their hand, dialogue indicating a greeting or agreement is generated. The dialogue generation unit also tracks the interviewee's gaze and analyzes the direction and movement of their gaze. For example, if the interviewee is looking at a particular document, questions or comments related to that document are generated. The dialogue generation unit also infers the interviewee's intentions and emotions based on the non-verbal behavior data and conducts dialogue accordingly. For example, if the interviewer nods their head, dialogue indicating agreement is generated. This makes it possible to provide dialogue based on the interviewee's non-verbal behavior.

[0067] The dialogue generation unit can customize an individual dialogue style based on the interviewee's past dialogue data. The dialogue generation unit, for example, analyzes the interviewee's past dialogue data and customizes the individual dialogue style. For example, it generates a dialogue based on the interviewee's preferred topics and question formats. The dialogue generation unit also learns the interviewee's speaking style and expression based on the past dialogue data and conducts a dialogue that matches that. For example, it incorporates phrases and expressions that the interviewee frequently uses. The dialogue generation unit also references the interviewee's past dialogue history and generates questions and comments that take into account the content of previous dialogues. For example, it revisits topics that were discussed in the previous interview. This makes it possible to provide an individual dialogue style based on the interviewee's past dialogue data.

[0068] The system can also be applied to at least one other field of education or counseling. For example, in the field of education, the system introduces dialogue using an AI clone to support students' learning. For example, it provides questions and explanations tailored to each student's individual learning progress. In the field of counseling, the system utilizes an AI clone to engage in dialogue tailored to the client's emotions and concerns. For example, it provides stress relief and mental health support. In the field of medicine, the system introduces dialogue using an AI clone to support communication with patients. For example, it conducts pre-consultation interviews and health consultations. This allows the system to be applied to other fields such as education and counseling.

[0069] The system allows multiple AI clones to cooperate and converse, enabling it to handle more complex scenarios. For example, the system simulates a group discussion in which multiple AI clones cooperate, where AI clones with different perspectives and opinions engage in a debate. The system also allows multiple AI clones to work together to support complex problem-solving, where AI clones with different expertise cooperate to propose solutions. The system also allows multiple AI clones to cooperate in scenario-based training, where emergency response or business simulations are carried out, enabling it to handle more complex scenarios.

[0070] The system can use the emotion estimation function to provide feedback based on the emotions of the interviewee in real time. For example, the system uses the emotion estimation function to provide feedback based on the emotions of the interviewee in real time. For example, if the interviewee is feeling anxious, the system provides feedback that gives a sense of security. The system also adjusts the content and tone of the feedback depending on the emotional state of the interviewee. For example, if the interviewee is excited, the system provides feedback that responds calmly. The system also provides specific advice that matches the emotions of the interviewee based on the emotion estimation data. For example, if the interviewee is confused, the system provides an easy-to-understand explanation. In this way, feedback based on the emotions of the interviewee can be provided in real time.

[0071] The system can analyze the progress of the interview in real time and suggest the most appropriate questions and answers. For example, the system monitors the progress of the interview in real time and suggests the next most appropriate question. For example, it generates related questions based on the interviewer's answers. The system also analyzes the progress of the interview and provides optimal feedback to the interviewer's answers in real time. For example, if the interviewer's answers are insufficient, it suggests supplementary questions. The system also evaluates the interviewer's level of understanding and interest based on the progress of the interview and generates questions and answers accordingly. For example, it asks questions related to topics in which the interviewer has shown interest. In this way, the system can analyze the progress of the interview in real time and suggest the most appropriate questions and answers.

[0072] The system can automatically summarize the contents of an interview so that it can be referenced later. For example, the system analyzes the contents of an interview in real time and automatically generates a summary. For example, it extracts important points and keywords to create a summary. The system can also analyze recorded data of an interview and automatically generate a text summary. For example, it can use speech recognition technology to convert the contents of the interview into text and create a summary. The system can also summarize the contents of the interview and save it in a database so that it can be referenced later. For example, it can save the summary data in a searchable format. This allows the contents of the interview to be automatically summarized and referenced later.

[0073] The system automatically adjusts interview schedules, enabling interviews to be conducted at optimal times. For example, the system analyzes the interviewee's schedule and automatically suggests the optimal timing for the interview. For example, it adjusts the interview date and time based on the interviewee's free time. The system also automatically adjusts interview schedules, allowing interviews to be conducted at optimal times that suit the interviewee's convenience. For example, it adjusts the schedule in cooperation with the interviewee's calendar. The system also automates interview schedule adjustments, reducing the burden on the interviewee. For example, it suggests the optimal schedule based on the interviewee's desired date and time. This allows the system to automatically adjust interview schedules, enabling interviews to be conducted at optimal times.

[0074] The system can also apply the efficiency of interviews to other business processes. For example, the system applies interview efficiency technology to meetings, analyzing the progress of a meeting in real time and suggesting the most appropriate agenda item and remarks. For example, the system suggests the next agenda item based on the progress of the meeting. The system also supports the efficiency of presentations. For example, the system analyzes the presenter's speaking style and content in real time and provides optimal advice. The system also applies efficiency technology to business processes in general, analyzing the progress of work in real time and making optimal suggestions. For example, the system suggests tasks based on the progress of a project. In this way, the efficiency of interviews can be applied to other business processes.

[0075] The system can automatically translate the contents of an interview to facilitate communication between participants who speak different languages. For example, the system can translate the contents of an interview in real time to support communication between participants who speak different languages. For example, it can perform automatic translation from English to Japanese. The system can also analyze recorded interview data and automatically generate text translations. For example, it can convert the contents of an interview into text and translate and provide it in different languages. The system can also display the contents of an interview in multiple languages ​​in real time to enable participants who speak different languages ​​to understand it simultaneously. For example, it can display subtitles and translate voice. This allows the system to automatically translate the contents of an interview to facilitate communication between participants who speak different languages.

[0076] The system can use the emotion estimation function to make suggestions to reduce the interviewee's stress level. For example, the system uses the emotion estimation function to monitor the interviewee's stress level in real time and make suggestions to reduce stress. For example, it can suggest breathing techniques to help them relax. The system also provides specific advice to reduce stress depending on the interviewee's emotional state. For example, if the interviewee is nervous, it can suggest relaxing music. The system also configures the environment to reduce the interviewee's stress level based on the emotion estimation data. For example, it can adjust the lighting and sound so that the interviewee can relax. This allows the system to make suggestions to reduce the interviewee's stress level.

[0077] The system can make the evaluation criteria for interviews transparent and share them with interviewers in advance. For example, the system shares the evaluation criteria for interviews with interviewers in advance to ensure transparency. For example, it provides a document that clearly states the evaluation items and criteria. The system also makes the evaluation criteria for interviews available online so that interviewers can check them in advance. For example, it posts the evaluation criteria on a website. The system also explains the evaluation criteria for interviews to interviewers and holds seminars and workshops to deepen their understanding. For example, it holds an explanatory meeting on the evaluation criteria. In this way, the evaluation criteria for interviews can be made transparent and shared with interviewers in advance.

[0078] The system can automatically record the results of interviews so that they can be verified later. For example, the system automatically records and films the contents of interviews and stores them in a database so that they can be verified later. For example, the audio and video of the interviews are stored in the cloud. The system can also automatically generate the results of interviews as text data so that they can be referenced later. For example, the system can convert the contents of the interviews into text using voice recognition technology and store the text in a database. The system can also automatically record the evaluation results of the interviews so that they can be verified later. For example, the system can automatically perform scoring based on evaluation criteria and save the results. In this way, the results of the interviews can be automatically recorded and verified later.

[0079] The system can provide fair evaluations while maintaining the anonymity of interviewees. For example, the system anonymizes the personal information of interviewees, allowing evaluators to evaluate without bias. For example, evaluations are made while concealing the interviewee's name and gender. The system also provides fair evaluations based on evaluation criteria while maintaining the anonymity of interviewees. For example, evaluations are made based only on the content of the interviewee's responses. To ensure the anonymity of interviewees, the system also conducts interviews in a format where the evaluator and interviewer do not meet face-to-face. For example, the interview is conducted via online text chat. This allows for fair evaluations while maintaining the anonymity of interviewees.

[0080] The system can also apply fair evaluation criteria to other evaluation processes. For example, the system applies fair evaluation criteria for interviews to performance reviews, thereby evaluating employees using consistent standards. For example, it standardizes evaluation items and criteria. The system also applies fair evaluation criteria to recruitment processes, thereby evaluating candidates using consistent standards. For example, it standardizes evaluation criteria for interviews and exams. The system also applies fair evaluation criteria to evaluation processes at educational institutions, thereby evaluating students using consistent standards. For example, it standardizes evaluation criteria for exams and assignments. This allows fair evaluation criteria to be applied to other evaluation processes.

[0081] The system can integrate the interview evaluation results with other data to perform a comprehensive evaluation. For example, the system can integrate the interview evaluation results with performance data to perform a comprehensive evaluation. For example, the system can combine the interview evaluation score and performance data to perform a comprehensive evaluation. The system can also integrate the interview evaluation results with other performance data to perform a comprehensive evaluation of the employee. For example, the system can combine project results and team evaluations to perform an evaluation. The system can also integrate the interview evaluation results with academic performance data from an educational institution to perform a comprehensive evaluation of the student. For example, the system can combine test scores and extracurricular activity evaluations to perform an overall evaluation. In this way, the system can integrate the interview evaluation results with other data to perform a comprehensive evaluation.

[0082] The system can use the emotion estimation function to provide fair feedback based on the emotions of the interviewee. For example, the system uses the emotion estimation function to provide fair feedback based on the emotions of the interviewee. For example, if the interviewee is feeling anxious, the system provides feedback that gives a sense of security. The system also adjusts the content and tone of the feedback according to the emotional state of the interviewee. For example, if the interviewee is excited, the system provides feedback that responds calmly. The system also provides specific advice that matches the emotions of the interviewee based on the emotion estimation data. For example, if the interviewee is confused, the system provides an easy-to-understand explanation. This makes it possible to provide fair feedback based on the emotions of the interviewee.

[0083] The system can monitor the emotions or physical condition of the interviewee in real time and minimize inconsistencies. The system, for example, monitors the emotions and physical condition of the interviewee in real time and minimizes inconsistencies. For example, the system analyzes the interviewee's heart rate and facial expressions to understand their emotional state. The system also adjusts the progress of the interview according to the interviewee's emotions and physical condition. For example, if the interviewee is tired, the system suggests taking a break. The system also responds according to the interviewee's condition based on the emotional and physical condition data. For example, if the interviewee is nervous, the system provides advice on how to relax. In this way, the system monitors the emotions and physical condition of the interviewee in real time and minimizes inconsistencies.

[0084] The system can automatically adjust the progress of the interview to keep the pace steady. For example, the system analyzes the progress of the interview in real time and makes adjustments to keep the pace steady. For example, it suggests the next question based on the interviewer's response time. The system also automatically adjusts the progress of the interview to keep the pace steady for the interviewer. For example, it adjusts the timing of questions based on the interviewer's response. The system also monitors the progress of the interview and provides feedback in real time to keep the pace steady. For example, if the interviewer is speaking too quickly, it suggests that the interviewer speak more slowly. In this way, the system automatically adjusts the progress of the interview to keep the pace steady.

[0085] The system can simulate the content of an interview in advance and select the optimal scenario. For example, the system simulates the content of an interview in advance and selects the optimal scenario. For example, a scenario is generated based on the profile of the interviewee. The system also simulates an interview and predicts the interviewee's reaction to select the optimal scenario. For example, the system adjusts the scenario based on past interview data. The system also simulates interview scenarios in advance and selects the optimal scenario based on the interviewee's level of understanding and interest. For example, the system prioritizes topics that the interviewee is interested in. In this way, the system simulates the content of the interview in advance and selects the optimal scenario.

[0086] The system can also apply the elimination of inconsistencies to other communication processes. For example, the system applies the elimination of inconsistencies to negotiations, analyzing the progress of the negotiations in real time and making optimal proposals. For example, the system generates the next proposal according to the progress of the negotiations. The system also analyzes the progress in real time and suggests optimal remarks to eliminate inconsistencies in discussions. For example, the system provides feedback in accordance with the progress of the discussion. The system also applies the elimination of inconsistencies to other communication processes in general, analyzing the progress in real time and making optimal proposals. For example, the system suggests tasks according to the progress of a project. This allows the elimination of inconsistencies to be applied to other communication processes.

[0087] The system can visualize the progress of the interview and make adjustments in real time. For example, the system visualizes the progress of the interview in real time, allowing the interviewer to understand the progress. For example, the progress may be displayed in a graph or chart. The system also visualizes the progress of the interview and allows the interviewer to adjust the progress. For example, the system suggests the next question or answer depending on the progress. The system also monitors the progress of the interview in real time and provides feedback to adjust the progress. For example, if the interviewer is falling behind, the system suggests that the interviewer speed up. In this way, the progress of the interview is visualized and adjustments may be made in real time.

[0088] The system can use the emotion estimation function to achieve a smooth progress based on the emotions of the interviewer. The system, for example, uses the emotion estimation function to achieve a smooth progress based on the emotions of the interviewer. For example, if the interviewer is nervous, the system provides advice to relax. The system also adjusts the progress according to the emotional state of the interviewer. For example, if the interviewer is excited, the system provides feedback to help the interviewer respond calmly. The system also uses the emotion estimation data to progress the interview in line with the emotions of the interviewer. For example, if the interviewer is confused, the system provides an easy-to-understand explanation. This makes it possible to achieve a smooth progress based on the emotions of the interviewer.

[0089] The system can translate the contents of an interview in real time, facilitating communication between participants who speak different languages. For example, the system can translate the contents of an interview in real time, supporting communication between participants who speak different languages. For example, it can perform automatic translation from English to Japanese. The system can also analyze recorded interview data and automatically generate text translations. For example, it can convert the contents of an interview into text and provide it translated into different languages. The system can also display the contents of an interview in multiple languages ​​in real time, allowing participants who speak different languages ​​to understand it simultaneously. For example, it can display subtitles and translate voice. This allows the system to translate the contents of an interview in real time, facilitating communication between participants who speak different languages.

[0090] The system can record interview content in multiple languages ​​so that it can be referenced later. For example, the system records interview content in multiple languages ​​so that it can be referenced later. For example, the system records interview content in English, Japanese, Chinese, etc. The system also converts recorded interview data into text in multiple languages ​​so that it can be referenced later. For example, the system converts interview content into text, translates it into different languages, and saves it. The system also records interview content in multiple languages ​​and saves it in a searchable format. For example, the system tags interview content in multiple languages ​​so that it can be searched. This allows interview content to be recorded in multiple languages ​​so that it can be referenced later.

[0091] The system supports the progress of an interview in multiple languages, enabling communication that transcends language barriers. The system, for example, supports the progress of an interview in multiple languages, enabling communication that transcends language barriers. For example, it displays the progress of the interview in multiple languages. The system also supports the progress of an interview in multiple languages, allowing participants who speak different languages ​​to understand at the same time. For example, it translates and displays interview questions and answers in real time. The system also supports the progress of an interview in multiple languages, enabling participants to communicate in their own language. For example, it performs voice translation and displays subtitles. In this way, the system supports the progress of an interview in multiple languages, enabling communication that transcends language barriers.

[0092] The system can also apply multilingual support to other communication processes. For example, the system applies multilingual support technology to international conferences, allowing participants to communicate in different languages. For example, the system translates and displays the content of the conference in real time. The system also supports multilingual support for webinars, allowing participants to understand the content in their own language. The system also applies multilingual support technology to other communication processes in general, allowing participants of different languages ​​to understand at the same time. For example, the content of a presentation can be displayed in multiple languages. This allows multilingual support to be applied to other communication processes.

[0093] The system can automatically summarize the contents of an interview and provide it in different languages. For example, the system automatically summarizes the contents of an interview and provides it in different languages. For example, the system summarizes the contents of the interview and displays it in English, Japanese, Chinese, etc. The system also analyzes recorded data of the interview, automatically generates summaries, and translates them into different languages. For example, the system converts the contents of the interview into text and provides the summaries in multiple languages. The system also automatically summarizes the contents of the interview and saves them in a searchable format in different languages. For example, the system tags the summary data in multiple languages ​​and makes it searchable. This allows the system to automatically summarize the contents of the interview and provide it in different languages.

[0094] The system can use the emotion estimation function to understand differences in emotions between participants who speak different languages ​​and optimize communication. For example, the system uses the emotion estimation function to understand differences in emotions between participants who speak different languages ​​and optimize communication. For example, the system analyzes the emotional states of participants in real time. The system also understands differences in emotions between participants who speak different languages ​​and communicates accordingly. For example, the system provides feedback tailored to the emotional states of participants. The system also understands differences in emotions between participants who speak different languages ​​and optimizes communication based on the emotion estimation data. For example, the system generates questions and answers according to the emotional states. This makes it possible to understand differences in emotions between participants who speak different languages ​​and optimize communication.

[0095] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0096] The system can estimate the interviewee's emotions and adjust the progress of the interview based on the estimated emotions. For example, if the interviewee is nervous, it generates questions or comments to relax them. If the interviewee is excited, it generates dialogue in a calm tone to respond calmly. Furthermore, if the interviewee is feeling anxious, it provides reassuring feedback. This allows the system to provide dialogue that is appropriate for the interviewee's emotions.

[0097] The system can analyze the nonverbal behavior of the interviewee and generate dialogue content based on that nonverbal behavior. For example, if the interviewee waves their hand, dialogue indicating a greeting or agreement can be generated. If the interviewee is looking at a specific document, questions or comments related to that document can be generated. Furthermore, if the interviewer nods their head, dialogue indicating agreement can be generated. This makes it possible to provide dialogue based on the interviewee's nonverbal behavior.

[0098] The system can customize individual conversation styles based on the interviewee's past conversation data. For example, it generates conversations based on the interviewee's preferred topics and question formats. It also learns the interviewee's speaking style and expression and conducts conversations that match those. It also references the interviewee's past conversation history and generates questions and comments that take into account the content of previous conversations. This makes it possible to provide an individual conversation style based on the interviewee's past conversation data.

[0099] The system can also be applied to at least one other field of education or counseling. For example, in the field of education, dialogue using an AI clone can be introduced to support students' learning. For example, questions and explanations tailored to each individual's learning progress can be provided. In the field of counseling, an AI clone can be used to engage in dialogue tailored to the client's emotions and concerns. For example, stress reduction and mental health support can be provided. Furthermore, in the field of medicine, dialogue using an AI clone can be introduced to support communication with patients. For example, pre-examination interviews and health consultations can be conducted. This allows the system to be applied to other fields such as education and counseling.

[0100] The system can handle more complex scenarios by having multiple AI clones cooperate and converse. For example, multiple AI clones can cooperate to simulate a group discussion, where AI clones with different perspectives and opinions engage in a debate. Multiple AI clones can also work together to assist in solving complex problems, where AI clones with different expertise collaborate to propose solutions. Furthermore, multiple AI clones can cooperate to conduct scenario-based training, where emergency response or business simulations are carried out. This allows multiple AI clones to cooperate and converse to handle more complex scenarios.

[0101] Using the emotion estimation function, the system can provide real-time feedback based on the interviewee's emotions. For example, if the interviewee feels anxious, the system can provide reassuring feedback. If the interviewee is excited, the system can provide calm feedback. If the interviewee seems confused, the system can provide an easy-to-understand explanation. This allows the system to provide real-time feedback based on the interviewee's emotions.

[0102] The system can analyze the progress of the interview in real time and suggest the most appropriate questions and answers. For example, it generates related questions based on the interviewer's answers. It can also analyze the progress of the interview and provide optimal feedback to the interviewer's answers in real time. For example, if the interviewer's answers are insufficient, it can suggest supplementary questions. Furthermore, it evaluates the interviewer's level of understanding and interest based on the progress of the interview and generates questions and answers accordingly. For example, it asks questions related to topics that the interviewer has shown interest in. This allows the system to analyze the progress of the interview in real time and suggest the most appropriate questions and answers.

[0103] The system can automatically summarize the contents of an interview for later reference. For example, the system may analyze the contents of an interview in real time and automatically generate a summary. For example, it may extract important points and keywords to create a summary. It may also analyze recorded interview data and automatically generate a text summary. For example, it may use speech recognition technology to convert the interview contents into text and create a summary. It may also summarize the interview contents and save it in a database for later reference. For example, it may save the summary data in a searchable format. This allows the contents of an interview to be automatically summarized and referenced later.

[0104] The system can automatically adjust interview schedules and conduct interviews at the optimal time. For example, it analyzes the interviewee's schedule and automatically suggests the optimal interview timing. For example, it adjusts the interview date and time based on the interviewee's free time. It can also automatically adjust interview schedules to conduct interviews at the optimal time that suits the interviewee's convenience. For example, it adjusts the schedule in conjunction with the interviewee's calendar. It can also automate interview schedule adjustments, reducing the burden on the interviewee. For example, it suggests the optimal schedule based on the interviewee's desired date and time. This allows the system to automatically adjust interview schedules and conduct interviews at the optimal time.

[0105] Using the emotion estimation function, the system can provide fair feedback based on the interviewee's emotions. For example, if the interviewee feels anxious, the system can provide reassuring feedback. If the interviewee is excited, the system can provide calm feedback. Furthermore, if the interviewee seems confused, the system can provide an easy-to-understand explanation. This allows the system to provide fair feedback based on the interviewee's emotions.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The AI ​​clone generator generates an AI clone based on the user's profile and past dialogue data. For example, it generates an AI clone based on profile information such as the user's age, gender, occupation, and interests, and analyzes past dialogue data (text data, voice data, dialogue history, etc.) to learn the user's characteristics. Step 2: The dialogue generation unit generates dialogue using the AI ​​clone generated by the AI ​​clone generation unit. For example, it uses a generation AI (text generation AI or multimodal generation AI) to generate dialogue based on prompts including the purpose of the interview and the questions, and learns the voice, speaking style, facial expressions, etc. of the interviewee to realize a realistic dialogue. Step 3: The evaluation unit evaluates the interviewee's answers based on the dialogue generated by the dialogue generation unit. For example, the evaluation unit evaluates the interviewee's answers based on pre-defined evaluation criteria and provides consistent feedback. Evaluation criteria include the accuracy of the answers, the expression of emotions, and the fluency of the dialogue.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0149] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0158] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0159] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0160] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0161] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0162] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0163] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0164] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0165] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0166] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0167] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0168] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0169] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0170] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0171] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0172] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0173] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0174] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an AI clone generation unit that generates an AI clone based on a user's profile and past conversation data; a dialogue generation unit that generates a dialogue using the AI ​​clone generated by the AI ​​clone generation unit; an evaluation unit that evaluates the interviewee's response based on the dialogue generated by the dialogue generation unit; A system characterized by:

2. The dialogue generation unit The emotion of the interviewee is estimated in real time, and a dialogue content is generated according to the emotion.

2. The system of claim 1.

3. The dialogue generation unit Analyzing the non-verbal behavior of the interviewer and generating dialogue content based on the non-verbal behavior 2. The system of claim 1.

4. The dialogue generation unit Customize individual conversation styles based on the interviewee's past conversation data 2. The system of claim 1.

5. The system comprises: It also has applications in at least one other field: education or counseling.

2. The system of claim 1.

Images