System

Abstract

An object of a system according to an embodiment is to reduce an adoption cost and prevent a mismatch.SOLUTION: According to an embodiment, a system includes a AI interviewer. The AI interviewer refers to points to be checked in interviews according to the company and past employment information using the RAG. The AI interviewer can use the voice generation AI to conduct a natural conversation. The AI interviewer analyzes the candidate's responses in real-time.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, recruitment activities require reviewing a large number of application forms and conducting multiple interviews, which is costly and can lead to mismatches.

[0005] The system according to the embodiment aims to reduce recruitment costs and prevent mismatches. [Means for solving the problem]

[0006] The system according to the embodiment includes an AI interviewer. The AI ​​interviewer uses RAG to check specific interview points for each company and to refer to past recruitment information. The AI ​​interviewer uses speech generation AI to conduct natural conversations. The AI ​​interviewer analyzes the applicant's responses in real time. [Effects of the Invention]

[0007] The system according to the embodiment can reduce recruitment costs and prevent mismatches. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 AI ​​interviewer system according to the embodiment of the present invention is a system in which an AI interviewer conducts interviews tailored to each company and analyzes applicants' responses in real time through natural dialogue. This allows the AI ​​interviewer system to reduce recruitment costs and prevent mismatches.

[0029] An AI interviewer system according to an embodiment includes an AI interviewer, a RAG, and a speech generation AI. The AI ​​interviewer uses the RAG to check interview questions tailored to the company and to reference past recruitment information. For example, the AI ​​interviewer asks a question such as, "Tell me about your past project experience" based on the skills and experience the company is seeking. The RAG uses an information retrieval algorithm to obtain necessary information from the company's database. For example, it references past recruitment information and the skill set the company is seeking. The speech generation AI uses speech synthesis technology to conduct natural dialogue. For example, it generates appropriate responses to the applicant's answers. The speech generation AI uses natural language processing technology to analyze the applicant's answers in real time. For example, it analyzes the content of the applicant's answers and generates the next question. This allows the AI ​​interviewer system to conduct interviews tailored to the company and analyze the applicant's answers in real time through natural dialogue.

[0030] An AI interviewer can analyze a candidate's non-verbal behavior and adjust the questions they ask based on that information. For example, an AI interviewer could analyze a candidate's facial expressions in real time and, if they appear nervous, ask questions to relax them. For example, if a candidate smiles, they could switch to a more positive topic. An AI interviewer could analyze gestures and, if the candidate appears confident, ask more detailed questions. For example, if a candidate uses their hands to explain something, they could ask questions that delve deeper into that content. This makes it possible to conduct more appropriate interviews by analyzing a candidate's non-verbal behavior and adjusting the questions they ask.

[0031] The AI ​​interviewer can analyze the candidate's tone of voice and speaking style to measure their stress level and insert questions to help them relax if stress levels rise. For example, the AI ​​interviewer can analyze the candidate's tone of voice and speaking style to measure their stress level. For example, if their voice is trembling, the AI ​​interviewer can ask questions about their hobbies to help them relax. The AI ​​interviewer can analyze the speed of speech, and if the candidate is speaking quickly, the AI ​​interviewer can ask questions at a slower pace. For example, if the candidate seems nervous, the AI ​​interviewer can ask questions to help them relax. In this way, the AI ​​interviewer can measure the candidate's stress level and insert appropriate questions to help them relax.

[0032] The AI ​​interviewer can analyze a candidate's past social media posts and ask questions based on the candidate's interests and values. For example, the AI ​​interviewer can analyze a candidate's past social media posts and ask questions based on topics that the candidate is interested in. For example, if a candidate frequently posts about technology, the AI ​​interviewer will ask questions about that field. The AI ​​interviewer will ask questions based on the candidate's values. For example, if a candidate is interested in environmental issues, the AI ​​interviewer will ask questions related to that. In this way, a deeper understanding can be gained by analyzing a candidate's past social media posts and asking questions based on their interests and values.

[0033] An AI interviewer can analyze an applicant's tone of voice and speaking style to select the most appropriate communication style. For example, an AI interviewer could analyze an applicant's tone of voice and ask questions in a calm tone if the applicant speaks calmly. For example, the AI ​​interviewer could proceed with the questions at a slower pace. An AI interviewer could analyze speaking style and, if the applicant speaks quickly, ask questions at a slower pace. For example, if the applicant seems nervous, the AI ​​interviewer could ask questions to relax them. This allows for more effective interviews by analyzing an applicant's tone of voice and speaking style and selecting the most appropriate communication style.

[0034] RAG can refer to a company's latest projects and news and ask questions based on them. For example, RAG can refer to a company's latest projects and ask questions related to those projects. For example, it can ask, "What technology did you use in your recent projects?" RAG can refer to a company's news and ask questions based on that news. For example, it can ask, "Tell us about the new product announced in a recent press release." This allows for more appropriate interviews by referring to a company's latest projects and news and asking questions based on them.

[0035] RAG can analyze past interview data and learn the patterns of successful interviews to optimize questions. For example, RAG analyzes past interview data and learns the patterns of successful interviews. For example, it extracts questions that were frequently used in successful interviews and optimizes questions based on those. RAG analyzes interview evaluation data and learns the characteristics of successful interviews. For example, it extracts question patterns from interviews that received high evaluations and optimizes questions based on those. In this way, by analyzing past interview data and learning the patterns of successful interviews to optimize questions, it is possible to improve the quality of interviews.

[0036] RAG can refer to best practices from other industries and incorporate them into the content of the interview. For example, RAG can refer to best practices from other industries and incorporate that content into the interview. For example, the methods used in successful projects in other industries can be reflected in the questions. RAG can refer to successful cases from other industries and incorporate that content into the interview. For example, the questions can be based on successful cases in other industries. In this way, by referring to best practices from other industries and incorporating them into the content of the interview, the quality of the interview can be improved.

[0037] RAG translates candidate responses in real time, making it possible to cater to international companies. RAG translates candidate responses in real time, making it possible to cater to international companies. For example, translating responses in English into Japanese. RAG supports multiple languages ​​and translates candidate responses in real time, making it possible to cater to international companies. For example, translating responses in French into English. This allows candidate responses to be translated in real time, making it possible to cater to international companies, supporting global recruitment activities.

[0038] The speech generation AI can learn the speaking style and accent of an applicant and realize natural conversations. For example, it can ask questions in a tone that matches the applicant's speaking style. The speech generation AI can learn the pronunciation characteristics of each region and realize natural conversations. For example, it can ask questions in a tone that matches the applicant's accent. In this way, the quality of interviews can be improved by learning the speaking style and accent of an applicant and realizing more natural conversations.

[0039] Speech generation AI supports dialogue in different languages ​​and can accommodate international recruitment activities. Speech generation AI supports dialogue in different languages ​​and can accommodate international recruitment activities. For example, translating an interview in English into Japanese. Speech generation AI uses multilingual speech synthesis technology to support dialogue in different languages. For example, translating an interview in French into English. This allows it to support dialogue in different languages ​​and accommodate international recruitment activities, thereby supporting global recruitment activities.

[0040] Speech generation AI can convert candidate responses into text in real time so that they can be referenced later. Speech generation AI, for example, converts candidate responses into text in real time so that they can be referenced later. For example, by saving the text data after the interview is over. Speech generation AI uses speech recognition technology to convert candidate responses into text in real time. For example, by automatically transcribing candidate responses. This allows for efficient management of interview records by converting candidate responses into text in real time so that they can be referenced later.

[0041] The knowledge test can be customized based on the candidate's field of expertise and interests. For example, the knowledge test can be customized based on the candidate's field of expertise. For example, a candidate for a technical job can be asked questions about the latest programming languages. The knowledge test can be customized based on the candidate's interests. For example, the candidate can be asked questions about fields that interest them. This allows for more appropriate evaluation by customizing the knowledge test questions based on the candidate's field of expertise and interests.

[0042] The knowledge test can analyze answers and automatically generate follow-up questions according to the level of understanding. For example, the knowledge test analyzes the answers of the candidate and automatically generates follow-up questions according to the level of understanding. For example, if the candidate answers correctly, more difficult questions are asked. The knowledge test automatically generates follow-up questions based on the content of the answers. For example, if the candidate talks about a specific technology, additional questions about that technology are asked. In this way, more appropriate evaluation is possible by analyzing the answers to the knowledge test and automatically generating follow-up questions according to the level of understanding.

[0043] The knowledge test can compare the results with other candidates and provide a relative evaluation. The knowledge test can, for example, compare the results with other candidates and provide a relative evaluation. For example, the candidate's score can be compared to the average score. The knowledge test can display the candidate's results in a ranking format and provide a relative evaluation. For example, the candidate's score can be placed in the top 10%. This allows for a more appropriate evaluation by comparing the results of the knowledge test with other candidates and providing a relative evaluation.

[0044] The results of a knowledge test can be visualized, allowing the candidate's strengths and weaknesses to be understood at a glance. The results of a knowledge test can be visualized, for example, allowing the candidate's strengths and weaknesses to be understood at a glance. For example, scores can be displayed in a graph. The results of a knowledge test can be displayed in chart format, visually showing the candidate's strengths and weaknesses. For example, a skill matrix can be used to display the candidate's skill level. In this way, the results of a knowledge test can be visualized, allowing the candidate's strengths and weaknesses to be understood at a glance, enabling more appropriate evaluation.

[0045] The interview results can be summarized by taking into account the candidate's non-verbal behavior. The interview results can be summarized by taking into account the candidate's non-verbal behavior, such as facial expressions and gestures. For example, highlighting scenes in which the candidate smiles. The interview results can be summarized by analyzing the candidate's non-verbal behavior and using that information. For example, highlighting scenes in which the candidate speaks with confidence. This allows for a more appropriate evaluation by taking into account the candidate's non-verbal behavior when summarizing the interview results.

[0046] The feedback materials may include the results of a detailed analysis of the candidate's answers. The feedback materials may, for example, include the results of a detailed analysis of the candidate's answers. For example, the strengths and weaknesses of the candidate's answers may be specifically described. The feedback materials may include the results of an evaluation of the candidate's answers in detail. For example, the evaluation points of the candidate's answers may be specifically indicated. By including the results of a detailed analysis of the candidate's answers in the feedback materials, a more appropriate evaluation may be possible.

[0047] The feedback materials can be provided in different formats. For example, the feedback materials can be provided in video format to visually convey the results of the candidate's interview. For example, a video summarizing the highlights of the interview can be provided. The feedback materials can be provided in infographic format to visually show the results of the candidate's interview. For example, the scores can be displayed in a graph. By providing the feedback materials in different formats, a more appropriate evaluation can be made.

[0048] The feedback materials can be shared with other recruiters to conduct joint evaluations. For example, the feedback materials can be shared with other recruiters to build a system for joint evaluations. For example, feedback can be shared using an online platform. The feedback materials provide a tool for joint evaluations, and multiple recruiters can conduct evaluations. For example, evaluation sheets can be shared and evaluations can be conducted jointly. This allows feedback materials to be shared with other recruiters to conduct joint evaluations, enabling more appropriate evaluations.

[0049] To ease the candidate's tension, music with a relaxing effect can be played in the background. To ease the candidate's tension, for example, music with a relaxing effect can be played in the background. For example, classical music can be played. To ease the candidate's tension, natural sounds can be played in the background. For example, the sound of waves or birds chirping can be played. By playing music with a relaxing effect in the background to ease the candidate's tension, a more appropriate evaluation can be performed.

[0050] It is possible to suggest simple exercises to help candidates relax before the interview. For example, encouraging them to take deep breaths. Suggest some stretching before the interview. For example, stretching the shoulders and neck. By suggesting simple exercises to help candidates relax before the interview, it is possible to reduce tension and enable a more appropriate evaluation.

[0051] Candidates can be provided with guidelines to help them relax before the interview. Guidelines can be provided to candidates to help them relax before the interview. For example, explaining how to take deep breaths and stretch. Specific steps can be provided to help them relax before the interview. For example, explaining relaxation techniques. By providing candidates with guidelines to help them relax before the interview, it is possible to reduce their tension and enable a more appropriate evaluation.

[0052] It is possible to incorporate humor to ease the candidate's tension during the interview. It is possible to incorporate humor to ease the candidate's tension during the interview. For example, ask questions with a light joke. It is possible to incorporate light topics to put the candidate at ease during the interview. For example, ask questions about their hobbies. By incorporating humor to ease the candidate's tension during the interview, it is possible to ease the candidate's tension and allow for a more appropriate evaluation.

[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 AI ​​interviewer system can analyze a candidate's past work history and resume and ask questions based on the candidate's skills and experience. For example, it can ask about projects in which the candidate has demonstrated leadership in the past. If the candidate is knowledgeable in a particular technology, it can ask detailed questions about that technology. This allows the system to analyze a candidate's past work history and resume and ask more appropriate questions, thereby improving the quality of the interview.

[0055] The AI ​​interviewer system can convert candidate responses into text in real time and automatically generate a summary after the interview is over. For example, it can extract the key points of the candidate's responses and create a concise summary. It can also highlight important points in the candidate's responses and reflect them in the summary. This allows for efficient management of interview records by automatically generating a summary after the interview is over.

[0056] The AI ​​interviewer system can analyze a candidate's answers and evaluate their consistency and reliability. For example, it can check whether the candidate's answers are consistent with their past work history. If there are any inconsistencies in the candidate's answers, it can point them out and ask for a detailed explanation. This allows for a more appropriate evaluation by evaluating the consistency and reliability of the candidate's answers.

[0057] The AI ​​interviewer system can analyze the candidate's answers and evaluate the quality of the answers. For example, it can evaluate whether the candidate's answers are specific and logical. If the candidate's answers are unclear, it can point this out and ask for a specific explanation. This allows for a more appropriate evaluation by evaluating the quality of the candidate's answers.

[0058] The AI ​​interviewer system can analyze candidates' answers and extract keywords used in the answers. For example, if a candidate mentions specific skills or experience, those keywords can be extracted and reflected in the interview summary. Important keywords in the candidate's answers can be highlighted and reflected in the summary. In this way, by extracting keywords used in the candidate's answers, interview records can be managed efficiently.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The AI ​​interviewer uses RAG (information retrieval algorithm) to check the interview points that each company wants to confirm and to refer to past recruitment information. For example, based on the skills and experience the company is looking for, it asks questions such as "Tell us about your past project experience." RAG retrieves the necessary information from the company's database and refers to past recruitment information and the skill sets the company is looking for. Step 2: The speech generation AI uses speech synthesis technology to conduct natural dialogue. For example, it generates an appropriate response to the candidate's answer. The speech generation AI uses natural language processing technology to analyze the candidate's answer in real time and generate the next question.

[0061] (Example 2) The AI ​​interviewer system according to the embodiment of the present invention is a system in which an AI interviewer conducts interviews tailored to each company and analyzes applicants' responses in real time through natural dialogue. This allows the AI ​​interviewer system to reduce recruitment costs and prevent mismatches.

[0062] An AI interviewer system according to an embodiment includes an AI interviewer, a RAG, and a speech generation AI. The AI ​​interviewer uses the RAG to check interview questions tailored to the company and to reference past recruitment information. For example, the AI ​​interviewer asks a question such as, "Tell me about your past project experience" based on the skills and experience the company is seeking. The RAG uses an information retrieval algorithm to obtain necessary information from the company's database. For example, it references past recruitment information and the skill set the company is seeking. The speech generation AI uses speech synthesis technology to conduct natural dialogue. For example, it generates appropriate responses to the applicant's answers. The speech generation AI uses natural language processing technology to analyze the applicant's answers in real time. For example, it analyzes the content of the applicant's answers and generates the next question. This allows the AI ​​interviewer system to conduct interviews tailored to the company and analyze the applicant's answers in real time through natural dialogue.

[0063] An AI interviewer can analyze a candidate's non-verbal behavior and adjust the questions they ask based on that information. For example, an AI interviewer could analyze a candidate's facial expressions in real time and, if they appear nervous, ask questions to relax them. For example, if a candidate smiles, they could switch to a more positive topic. An AI interviewer could analyze gestures and, if the candidate appears confident, ask more detailed questions. For example, if a candidate uses their hands to explain something, they could ask questions that delve deeper into that content. This makes it possible to conduct more appropriate interviews by analyzing a candidate's non-verbal behavior and adjusting the questions they ask.

[0064] The AI ​​interviewer can analyze the candidate's tone of voice and speaking style to measure their stress level and insert questions to help them relax if stress levels rise. For example, the AI ​​interviewer can analyze the candidate's tone of voice and speaking style to measure their stress level. For example, if their voice is trembling, the AI ​​interviewer can ask questions about their hobbies to help them relax. The AI ​​interviewer can analyze the speed of speech, and if the candidate is speaking quickly, the AI ​​interviewer can ask questions at a slower pace. For example, if the candidate seems nervous, the AI ​​interviewer can ask questions to help them relax. In this way, the AI ​​interviewer can measure the candidate's stress level and insert appropriate questions to help them relax.

[0065] The AI ​​interviewer can use emotion estimation to analyze the emotional state of a candidate in real time and ask questions that draw out positive emotions. For example, the AI ​​interviewer can analyze the candidate's facial expressions and, if positive emotions are detected, ask questions that delve deeper into that topic. For example, if the candidate smiles, the AI ​​interviewer will ask more detailed questions about the project. The AI ​​interviewer can use voice analysis technology to estimate the candidate's emotions and ask questions that draw out positive emotions. For example, if the candidate is speaking excitedly, the AI ​​interviewer will ask questions that continue on that topic. This makes it possible to analyze the candidate's emotional state and draw out positive emotions, thereby improving the quality of the interview.

[0066] The AI ​​interviewer can analyze a candidate's past social media posts and ask questions based on the candidate's interests and values. For example, the AI ​​interviewer can analyze a candidate's past social media posts and ask questions based on topics that the candidate is interested in. For example, if a candidate frequently posts about technology, the AI ​​interviewer will ask questions about that field. The AI ​​interviewer will ask questions based on the candidate's values. For example, if a candidate is interested in environmental issues, the AI ​​interviewer will ask questions related to that. In this way, a deeper understanding can be gained by analyzing a candidate's past social media posts and asking questions based on their interests and values.

[0067] An AI interviewer can analyze an applicant's tone of voice and speaking style to select the most appropriate communication style. For example, an AI interviewer could analyze an applicant's tone of voice and ask questions in a calm tone if the applicant speaks calmly. For example, the AI ​​interviewer could proceed with the questions at a slower pace. An AI interviewer could analyze speaking style and, if the applicant speaks quickly, ask questions at a slower pace. For example, if the applicant seems nervous, the AI ​​interviewer could ask questions to relax them. This allows for more effective interviews by analyzing an applicant's tone of voice and speaking style and selecting the most appropriate communication style.

[0068] Using emotion estimation capabilities, AI interviewers can improve the quality of interviews by providing real-time feedback according to the candidate's emotional state. For example, an AI interviewer can analyze a candidate's emotional state in real time, and if positive emotions are detected, provide feedback that continues the topic. For example, the AI ​​interviewer might say, "Tell me more about that experience." If negative emotions are detected, the AI ​​interviewer might provide feedback to help the candidate relax. For example, the AI ​​interviewer might say, "Please relax and speak." This allows for real-time feedback according to the candidate's emotional state, improving the quality of interviews.

[0069] RAG can refer to a company's latest projects and news and ask questions based on them. For example, RAG can refer to a company's latest projects and ask questions related to those projects. For example, it can ask, "What technology did you use in your recent projects?" RAG can refer to a company's news and ask questions based on that news. For example, it can ask, "Tell us about the new product announced in a recent press release." This allows for more appropriate interviews by referring to a company's latest projects and news and asking questions based on them.

[0070] RAG can analyze past interview data and learn the patterns of successful interviews to optimize questions. For example, RAG analyzes past interview data and learns the patterns of successful interviews. For example, it extracts questions that were frequently used in successful interviews and optimizes questions based on those. RAG analyzes interview evaluation data and learns the characteristics of successful interviews. For example, it extracts question patterns from interviews that received high evaluations and optimizes questions based on those. In this way, by analyzing past interview data and learning the patterns of successful interviews to optimize questions, it is possible to improve the quality of interviews.

[0071] RAG can refer to best practices from other industries and incorporate them into the content of the interview. For example, RAG can refer to best practices from other industries and incorporate that content into the interview. For example, the methods used in successful projects in other industries can be reflected in the questions. RAG can refer to successful cases from other industries and incorporate that content into the interview. For example, the questions can be based on successful cases in other industries. In this way, by referring to best practices from other industries and incorporating them into the content of the interview, the quality of the interview can be improved.

[0072] RAG translates candidate responses in real time, making it possible to cater to international companies. RAG translates candidate responses in real time, making it possible to cater to international companies. For example, translating responses in English into Japanese. RAG supports multiple languages ​​and translates candidate responses in real time, making it possible to cater to international companies. For example, translating responses in French into English. This allows candidate responses to be translated in real time, making it possible to cater to international companies, supporting global recruitment activities.

[0073] RAG can optimize the order of questions based on the candidate's emotional state. For example, RAG can use an emotion estimation function to analyze the candidate's emotional state, and if a positive emotion is detected, it will ask questions that continue on that topic. For example, it might ask, "Tell me more about that experience." If a negative emotion is detected, RAG will ask questions to put the candidate at ease. For example, it might ask, "Please speak in a relaxed manner." This can improve the quality of interviews by optimizing the order of questions based on the candidate's emotional state.

[0074] The speech generation AI can learn the speaking style and accent of an applicant and realize natural conversations. For example, it can ask questions in a tone that matches the applicant's speaking style. The speech generation AI can learn the pronunciation characteristics of each region and realize natural conversations. For example, it can ask questions in a tone that matches the applicant's accent. In this way, the quality of interviews can be improved by learning the speaking style and accent of an applicant and realizing more natural conversations.

[0075] The voice generation AI can use its emotion estimation function to adjust its tone of voice and speaking style according to the candidate's emotional state. For example, the voice generation AI can use its emotion estimation function to analyze the candidate's emotional state, and if a positive emotion is detected, it will ask questions in a bright tone. For example, if the candidate smiles, it will ask in a bright voice, "Tell me more about that experience." If a negative emotion is detected, the voice generation AI will ask questions in a calmer tone. For example, if the candidate seems nervous, it will ask in a calm voice, "Please speak in a relaxed manner." This allows the quality of the interview to be improved by adjusting the tone of voice and speaking style according to the candidate's emotional state.

[0076] Speech generation AI supports dialogue in different languages ​​and can accommodate international recruitment activities. Speech generation AI supports dialogue in different languages ​​and can accommodate international recruitment activities. For example, translating an interview in English into Japanese. Speech generation AI uses multilingual speech synthesis technology to support dialogue in different languages. For example, translating an interview in French into English. This allows it to support dialogue in different languages ​​and accommodate international recruitment activities, thereby supporting global recruitment activities.

[0077] Speech generation AI can convert candidate responses into text in real time so that they can be referenced later. Speech generation AI, for example, converts candidate responses into text in real time so that they can be referenced later. For example, by saving the text data after the interview is over. Speech generation AI uses speech recognition technology to convert candidate responses into text in real time. For example, by automatically transcribing candidate responses. This allows for efficient management of interview records by converting candidate responses into text in real time so that they can be referenced later.

[0078] The speech generation AI can use its emotion estimation function to provide spoken feedback based on the candidate's emotional state. For example, the speech generation AI can use its emotion estimation function to analyze the candidate's emotional state, and if a positive emotion is detected, it can provide spoken feedback that continues on that topic. For example, it can say, "Tell me more about that experience." If a negative emotion is detected, the speech generation AI can provide spoken feedback to help the candidate relax. For example, it can say, "Please relax and speak." This can improve the quality of interviews by providing spoken feedback based on the candidate's emotional state.

[0079] The knowledge test can be customized based on the candidate's field of expertise and interests. For example, the knowledge test can be customized based on the candidate's field of expertise. For example, a candidate for a technical job can be asked questions about the latest programming languages. The knowledge test can be customized based on the candidate's interests. For example, the candidate can be asked questions about fields that interest them. This allows for more appropriate evaluation by customizing the knowledge test questions based on the candidate's field of expertise and interests.

[0080] The knowledge test can analyze answers and automatically generate follow-up questions according to the level of understanding. For example, the knowledge test analyzes the answers of the candidate and automatically generates follow-up questions according to the level of understanding. For example, if the candidate answers correctly, more difficult questions are asked. The knowledge test automatically generates follow-up questions based on the content of the answers. For example, if the candidate talks about a specific technology, additional questions about that technology are asked. In this way, more appropriate evaluation is possible by analyzing the answers to the knowledge test and automatically generating follow-up questions according to the level of understanding.

[0081] The emotion estimation function can present questions of a level of difficulty that corresponds to the candidate's emotional state. For example, the emotion estimation function analyzes the candidate's emotional state, and if a positive emotion is observed, it presents more difficult questions. For example, if the candidate is confident, it will ask more difficult questions. If a negative emotion is observed, the emotion estimation function will present less difficult questions. For example, if the candidate is nervous, it will ask easier questions. This allows for more appropriate evaluation by presenting questions of a level of difficulty that corresponds to the candidate's emotional state.

[0082] The knowledge test can compare the results with other candidates and provide a relative evaluation. The knowledge test can, for example, compare the results with other candidates and provide a relative evaluation. For example, the candidate's score can be compared to the average score. The knowledge test can display the candidate's results in a ranking format and provide a relative evaluation. For example, the candidate's score can be placed in the top 10%. This allows for a more appropriate evaluation by comparing the results of the knowledge test with other candidates and providing a relative evaluation.

[0083] The results of a knowledge test can be visualized, allowing the candidate's strengths and weaknesses to be understood at a glance. The results of a knowledge test can be visualized, for example, allowing the candidate's strengths and weaknesses to be understood at a glance. For example, scores can be displayed in a graph. The results of a knowledge test can be displayed in chart format, visually showing the candidate's strengths and weaknesses. For example, a skill matrix can be used to display the candidate's skill level. In this way, the results of a knowledge test can be visualized, allowing the candidate's strengths and weaknesses to be understood at a glance, enabling more appropriate evaluation.

[0084] The emotion estimation function can provide feedback based on the candidate's emotional state, increasing their motivation to learn. For example, the emotion estimation function analyzes the candidate's emotional state, and if a positive emotion is detected, it provides feedback to continue the topic. For example, it might say, "Tell me more about that experience." If a negative emotion is detected, it provides feedback to help the candidate relax. For example, it might say, "Please relax and speak." This provides feedback based on the candidate's emotional state, increasing their motivation to learn, and enabling more appropriate evaluation.

[0085] The interview results can be summarized by taking into account the candidate's non-verbal behavior. The interview results can be summarized by taking into account the candidate's non-verbal behavior, such as facial expressions and gestures. For example, highlighting scenes in which the candidate smiles. The interview results can be summarized by analyzing the candidate's non-verbal behavior and using that information. For example, highlighting scenes in which the candidate speaks with confidence. This allows for a more appropriate evaluation by taking into account the candidate's non-verbal behavior when summarizing the interview results.

[0086] The feedback materials may include the results of a detailed analysis of the candidate's answers. The feedback materials may, for example, include the results of a detailed analysis of the candidate's answers. For example, the strengths and weaknesses of the candidate's answers may be specifically described. The feedback materials may include the results of an evaluation of the candidate's answers in detail. For example, the evaluation points of the candidate's answers may be specifically indicated. By including the results of a detailed analysis of the candidate's answers in the feedback materials, a more appropriate evaluation may be possible.

[0087] The emotion estimation function can provide feedback based on the candidate's emotional state. For example, the emotion estimation function analyzes the candidate's emotional state, and if a positive emotion is observed, it provides feedback that continues the topic. For example, it may say, "Tell me more about that experience." If a negative emotion is observed, it provides feedback to help the candidate relax. For example, it may say, "Please relax and speak." This allows for more appropriate evaluation by providing feedback based on the candidate's emotional state.

[0088] The feedback materials can be provided in different formats. For example, the feedback materials can be provided in video format to visually convey the results of the candidate's interview. For example, a video summarizing the highlights of the interview can be provided. The feedback materials can be provided in infographic format to visually show the results of the candidate's interview. For example, the scores can be displayed in a graph. By providing the feedback materials in different formats, a more appropriate evaluation can be made.

[0089] The feedback materials can be shared with other recruiters to conduct joint evaluations. For example, the feedback materials can be shared with other recruiters to build a system for joint evaluations. For example, feedback can be shared using an online platform. The feedback materials provide a tool for joint evaluations, and multiple recruiters can conduct evaluations. For example, evaluation sheets can be shared and evaluations can be conducted jointly. This allows feedback materials to be shared with other recruiters to conduct joint evaluations, enabling more appropriate evaluations.

[0090] The emotion estimation function can suggest areas for improvement based on the candidate's emotional state. For example, the emotion estimation function analyzes the candidate's emotional state, and if positive emotions are observed, it provides feedback to continue the topic. For example, it might say, "Tell me more about that experience." If negative emotions are observed, the emotion estimation function provides feedback to help the candidate relax. For example, it might say, "Please relax as you speak." This allows for more appropriate evaluation by suggesting areas for improvement based on the candidate's emotional state.

[0091] To ease the candidate's tension, music with a relaxing effect can be played in the background. To ease the candidate's tension, for example, music with a relaxing effect can be played in the background. For example, classical music can be played. To ease the candidate's tension, natural sounds can be played in the background. For example, the sound of waves or birds chirping can be played. By playing music with a relaxing effect in the background to ease the candidate's tension, a more appropriate evaluation can be performed.

[0092] It is possible to suggest simple exercises to help candidates relax before the interview. For example, encouraging them to take deep breaths. Suggest some stretching before the interview. For example, stretching the shoulders and neck. By suggesting simple exercises to help candidates relax before the interview, it is possible to reduce tension and enable a more appropriate evaluation.

[0093] The emotion estimation function can monitor the candidate's state of tension in real time and provide appropriate encouragement to relax them at the right time. For example, the emotion estimation function can monitor the candidate's state of tension in real time and provide appropriate encouragement to relax them at the right time. For example, it can say, "Please relax and talk to me." The emotion estimation function can analyze the candidate's state of tension and, if tension increases, provide appropriate encouragement to relax them. For example, it can say, "Take a deep breath and relax." This makes it possible to monitor the candidate's state of tension in real time and provide appropriate encouragement to relax them at the right time, enabling a more appropriate evaluation.

[0094] Candidates can be provided with guidelines to help them relax before the interview. Guidelines can be provided to candidates to help them relax before the interview. For example, explaining how to take deep breaths and stretch. Specific steps can be provided to help them relax before the interview. For example, explaining relaxation techniques. By providing candidates with guidelines to help them relax before the interview, it is possible to reduce their tension and enable a more appropriate evaluation.

[0095] It is possible to incorporate humor to ease the candidate's tension during the interview. It is possible to incorporate humor to ease the candidate's tension during the interview. For example, ask questions with a light joke. It is possible to incorporate light topics to put the candidate at ease during the interview. For example, ask questions about their hobbies. By incorporating humor to ease the candidate's tension during the interview, it is possible to ease the candidate's tension and allow for a more appropriate evaluation.

[0096] The emotion estimation function can suggest relaxation methods based on the candidate's state of tension. The emotion estimation function, for example, analyzes the candidate's state of tension and suggests relaxation methods. For example, it may encourage deep breathing. The emotion estimation function may suggest stretches based on the candidate's state of tension. For example, it may stretch the shoulders or neck. In this way, by suggesting relaxation methods based on the candidate's state of tension, the candidate's tension can be alleviated, allowing for a more appropriate evaluation.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The AI ​​interviewer system can analyze a candidate's past work history and resume and ask questions based on the candidate's skills and experience. For example, it can ask about projects in which the candidate has demonstrated leadership in the past. If the candidate is knowledgeable in a particular technology, it can ask detailed questions about that technology. This allows the system to analyze a candidate's past work history and resume and ask more appropriate questions, thereby improving the quality of the interview.

[0099] The AI ​​interviewer system can convert candidate responses into text in real time and automatically generate a summary after the interview is over. For example, it can extract the key points of the candidate's responses and create a concise summary. It can also highlight important points in the candidate's responses and reflect them in the summary. This allows for efficient management of interview records by automatically generating a summary after the interview is over.

[0100] The AI ​​interviewer system can analyze a candidate's answers and evaluate their consistency and reliability. For example, it can check whether the candidate's answers are consistent with their past work history. If there are any inconsistencies in the candidate's answers, it can point them out and ask for a detailed explanation. This allows for a more appropriate evaluation by evaluating the consistency and reliability of the candidate's answers.

[0101] The AI ​​interviewer system can analyze the candidate's answers and evaluate the quality of the answers. For example, it can evaluate whether the candidate's answers are specific and logical. If the candidate's answers are unclear, it can point this out and ask for a specific explanation. This allows for a more appropriate evaluation by evaluating the quality of the candidate's answers.

[0102] The AI ​​interviewer system can analyze candidates' answers and extract keywords used in the answers. For example, if a candidate mentions specific skills or experience, those keywords can be extracted and reflected in the interview summary. Important keywords in the candidate's answers can be highlighted and reflected in the summary. In this way, by extracting keywords used in the candidate's answers, interview records can be managed efficiently.

[0103] The AI ​​interviewer system analyzes the emotional state of candidates, and if positive emotions are detected, it can ask questions that delve deeper into that topic. For example, if a candidate smiles, it can ask more detailed questions about the project. If a candidate speaks enthusiastically, it can ask questions that continue on that topic. In this way, by analyzing a candidate's emotional state and drawing out positive emotions, it is possible to improve the quality of the interview.

[0104] The AI ​​interviewer system analyzes the emotional state of candidates, and if negative emotions are detected, it can ask questions to put them at ease. For example, if a candidate is nervous, it can ask questions about their hobbies to help them relax. If a candidate is feeling anxious, it can ask questions to help them relax. In this way, the quality of the interview can be improved by analyzing the candidate's emotional state and easing negative emotions.

[0105] The AI ​​interviewer system can analyze the emotional state of a candidate and adjust the order of questions according to changes in emotion. For example, if a candidate shows positive emotions, it will ask questions that continue on that topic. If a candidate shows negative emotions, it will ask questions to put the candidate at ease. This allows the quality of interviews to be improved by analyzing the candidate's emotional state and adjusting the order of questions according to changes in emotion.

[0106] The AI ​​interviewer system can analyze the emotional state of candidates and provide feedback according to changes in their emotions. For example, if a candidate shows positive emotions, it will provide feedback to continue the topic. If a candidate shows negative emotions, it will provide feedback to relax them. This allows the quality of interviews to be improved by analyzing the candidate's emotional state and providing feedback according to changes in emotions.

[0107] The AI ​​interviewer system can analyze the emotional state of the candidate and adjust the progress of the interview according to changes in emotion. For example, if the candidate shows positive emotion, it will ask questions that continue on that topic. If the candidate shows negative emotion, it will ask questions to put the candidate at ease. In this way, the quality of the interview can be improved by analyzing the candidate's emotional state and adjusting the progress of the interview according to changes in emotion.

[0108] The processing flow of the second embodiment will be briefly explained below.

[0109] Step 1: The AI ​​interviewer uses RAG (information retrieval algorithm) to check the interview points that each company wants to confirm and to refer to past recruitment information. For example, based on the skills and experience the company is looking for, it asks questions such as "Tell us about your past project experience." RAG retrieves the necessary information from the company's database and refers to past recruitment information and the skill sets the company is looking for. Step 2: The speech generation AI uses speech synthesis technology to conduct natural dialogue. For example, it generates an appropriate response to the candidate's answer. The speech generation AI uses natural language processing technology to analyze the candidate's answer in real time and generate the next question.

[0110] 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.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0112] 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.

[0113] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0114] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0123] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0129] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0138] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0154] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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]

[0177] 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. Equipped with AI interviewers, The AI ​​interviewer: Using RAG, you can check the points you want to confirm in interviews according to the company and refer to past recruitment information. Using voice generation AI to conduct natural conversations, Analyzing applicants' responses in real time A system characterized by:

2. The AI ​​interviewer: Analyze the candidate's past social media posts and ask questions based on the candidate's interests and values The system of claim 1 .

3. The RAG is See the latest projects and news from the company and ask questions based on that. The system of claim 1 .

4. The voice generation AI is Learn the candidate's speaking style and accent to realize the natural dialogue The system of claim 1 .

5. The AI ​​interviewer: Using emotion estimation function, the emotional state of the candidate is analyzed in real time and questions are asked to elicit positive emotions. The system of claim 1 .

Images