system

Abstract

The system according to this embodiment aims to conduct fair and objective recruitment based on the skills and aptitudes of candidates. [Solution] The system according to the embodiment comprises a document analysis unit, an interview support unit, an answer analysis unit, and a job offer decision unit. The document analysis unit analyzes the candidate's documents. The interview support unit generates interview questions based on the results analyzed by the document analysis unit. The answer analysis unit analyzes the candidate's answers based on the questions generated by the interview support unit. The job offer decision unit makes a job offer decision based on the results analyzed by the answer analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that bias is likely to occur in the adoption process and it is difficult to conduct a fair and objective evaluation.

[0005] The system according to the embodiment aims to perform fair and objective recruitment based on the skills and suitability of candidates.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a document analysis unit, an interview support unit, an answer analysis unit, and a job offer decision unit. The document analysis unit analyzes the candidate's documents. The interview support unit generates interview questions based on the results analyzed by the document analysis unit. The answer analysis unit analyzes the candidate's answers based on the questions generated by the interview support unit. The job offer decision unit makes a job offer decision based on the results analyzed by the answer analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can perform fair and objective recruitment based on the skills and aptitudes of candidates. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The recruitment support system according to an embodiment of the present invention is a system that provides a bias-free recruitment process using generative AI. This recruitment support system provides comprehensive support from document screening to interviews and job offers, and realizes objective and fair recruitment based on the skills and aptitudes of candidates. This mechanism allows companies to build a more innovative and sustainable business environment by emphasizing diversity and recruiting excellent talent. First, conventional interviews and document screenings lack objectivity, making fair recruitment difficult. For example, the subjectivity and preconceptions of interviewers can influence the process, causing excellent talent to be overlooked. In contrast, the present invention uses generative AI to eliminate bias and perform objective evaluations based on the skills and aptitudes of candidates. Specifically, the generative AI first analyzes the candidate's documents and evaluates their skills and experience. For example, it analyzes the contents of resumes and work histories to evaluate the candidate's skill set and past performance. At this time, the generative AI objectively evaluates the candidate's skills and aptitudes based on data it has learned in advance. Next, the generative AI supports the interview process. For example, the generative AI generates interview questions and analyzes the candidate's answers to evaluate their skills and aptitudes. Furthermore, the generative AI can analyze recordings and videos of interviews, evaluating candidates' facial expressions and tone of voice to provide a more detailed assessment. It can also support the hiring process. For example, the generative AI can make hiring decisions based on the candidate's evaluation. In this process, the AI ​​evaluates not only the candidate's skills and aptitude, but also whether they fit the company's needs and culture. By using this generative AI, bias can be eliminated, enabling objective and fair hiring based on candidates' skills and aptitude. This allows companies to build a more innovative and sustainable business environment by emphasizing diversity and hiring top talent. For example, when a company hires engineers for a new project, the generative AI analyzes the candidate's application materials to evaluate their skills and experience. Next, the generative AI generates interview questions and analyzes the candidate's answers to assess their skills and aptitude. Finally, the generative AI makes hiring decisions based on the candidate's evaluation. In this way, bias can be eliminated, enabling objective and fair hiring.This allows the recruitment support system to eliminate bias and achieve objective and fair recruitment based on candidates' skills and aptitudes.

[0029] The recruitment support system according to this embodiment comprises a document analysis unit, an interview support unit, an answer analysis unit, and a job offer decision unit. The document analysis unit analyzes the candidate's documents. For example, the document analysis unit analyzes the contents of resumes and work histories and evaluates the candidate's skill set and past achievements. The document analysis unit uses generative AI to objectively evaluate the candidate's skills and aptitudes. For example, the document analysis unit uses text mining technology to extract the candidate's skills and experience. The document analysis unit can also use keyword extraction technology to identify the candidate's important skills and achievements. Furthermore, the document analysis unit can use document classification technology to classify and evaluate the candidate's documents by category. For example, the document analysis unit analyzes the candidate's resume and evaluates their skill set and past achievements. Next, the interview support unit generates interview questions based on the results analyzed by the document analysis unit. The interview support unit generates interview questions using generative AI. For example, the interview support unit generates appropriate questions based on the candidate's skills and aptitudes. Furthermore, the interview support unit can analyze audio and video recordings of interviews to evaluate the candidate's facial expressions and tone of voice. For example, the interview support unit can use voice analysis technology to evaluate the candidate's tone of voice. It can also use video analysis technology to evaluate the candidate's facial expressions. In addition, the interview support unit can use emotion analysis technology to evaluate the candidate's emotions. For example, the interview support unit can analyze the candidate's tone of voice and evaluate their emotions. Next, the response analysis unit analyzes the candidate's answers based on the questions generated by the interview support unit. The response analysis unit analyzes the candidate's answers using generation AI. For example, the response analysis unit analyzes the candidate's answers using text analysis technology. It can also use emotion analysis technology to evaluate the candidate's emotions. Furthermore, the response analysis unit can use content consistency evaluation technology to evaluate the consistency of the candidate's answers. For example, the response analysis unit analyzes the candidate's answers and evaluates their skills and aptitude. Finally, the job offer decision unit makes a job offer decision based on the results analyzed by the response analysis unit. The hiring decision department uses a generation AI to make hiring decisions. For example, the hiring decision department evaluates not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture.The hiring decision unit can also evaluate candidates using a scoring system. For example, the hiring decision unit makes hiring decisions based on the candidate's skills and aptitudes. As a result, the hiring support system according to this embodiment can eliminate bias and achieve objective and fair hiring based on the candidate's skills and aptitudes.

[0030] The Document Analysis Department analyzes candidates' documents. For example, it analyzes the contents of resumes and work histories to evaluate candidates' skill sets and past achievements. Specifically, the Document Analysis Department uses generative AI to objectively evaluate candidates' skills and aptitudes. The generative AI utilizes natural language processing technology to extract text data from candidates' documents and uses text mining technology to analyze candidates' skills and experience in detail. For example, it analyzes the job descriptions and project details listed in resumes to evaluate what skills candidates possess and what results they have achieved. It can also use keyword extraction technology to identify key skills and achievements of candidates. This allows the Document Analysis Department to accurately grasp candidates' skill sets and evaluate them in comparison to the skills required by the company. Furthermore, it can also use document classification technology to categorize and evaluate candidates' documents. For example, it can analyze a candidate's resume, categorize it into categories such as technical skills, management skills, and communication skills, and evaluate each category. This allows the document analysis department to comprehensively evaluate candidates' skills and aptitudes and select candidates who match the company's needs.

[0031] The Interview Support Department generates interview questions based on the results analyzed by the Document Analysis Department. The Interview Support Department uses a generation AI to generate interview questions. Specifically, the generation AI generates appropriate questions based on the candidate's skills and aptitudes. For example, based on the project experience listed in the candidate's resume, it generates questions about the specific role and achievements in those projects. The Interview Support Department can also analyze audio and video recordings of interviews to evaluate the candidate's facial expressions and tone of voice. Using voice analysis technology, it evaluates the candidate's tone of voice and determines their level of nervousness and confidence. Furthermore, using video analysis technology, it can evaluate the candidate's facial expressions and determine emotional changes and sincerity. It can also evaluate the candidate's emotions using emotion analysis technology. For example, by analyzing the candidate's tone of voice and evaluating their emotions, it can understand what emotions the candidate is experiencing. This allows the Interview Support Department to evaluate not only the candidate's skills and aptitudes, but also their emotions and attitudes, enabling a more comprehensive judgment.

[0032] The Response Analysis Unit analyzes candidates' responses based on questions generated by the Interview Support Unit. The Response Analysis Unit uses a generative AI to analyze candidates' responses. Specifically, the generative AI uses text analysis technology to analyze candidates' responses in detail. For example, it extracts keywords and phrases from candidates' responses and evaluates how well they match the skills and aptitudes sought by the company. It can also evaluate candidates' emotions using sentiment analysis technology. For example, it judges candidates' emotions and attitudes from the choice of words and expressions used in their responses. Furthermore, it can evaluate the consistency of candidates' responses using content consistency evaluation technology. For example, it checks whether candidates provide consistent answers to different questions and whether there are any contradictions. This allows the Response Analysis Unit to evaluate not only candidates' skills and aptitudes, but also the consistency and reliability of their responses, enabling more accurate judgments.

[0033] The hiring decision unit makes hiring decisions based on the results analyzed by the response analysis unit. The hiring decision unit uses generative AI to make hiring decisions. Specifically, the generative AI evaluates not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. For example, it evaluates whether the candidate's skill set matches the skills the company is looking for, and whether the candidate's values ​​and behaviors are compatible with the company's culture. The hiring decision unit can also evaluate candidates using a scoring system. For example, it assigns scores to each item based on the candidate's skills and aptitude and makes an overall evaluation. This allows the hiring decision unit to objectively evaluate the candidate's skills and aptitude and select the candidate who is best suited to the company's needs. Furthermore, the hiring decision unit can also make hiring decisions based on past hiring data and the company's success stories. For example, it can analyze data on candidates who have been hired in the past, identify common characteristics of successful candidates, and make hiring decisions based on those. This allows the hiring decision unit to make more accurate hiring decisions and contribute to the company's success.

[0034] The document analysis unit can analyze the contents of resumes and work histories to evaluate a candidate's skill set and past achievements. For example, the document analysis unit can analyze the contents of resumes and work histories to evaluate a candidate's skill set and past achievements. The document analysis unit can extract a candidate's skills and experience using text mining techniques. Furthermore, the document analysis unit can identify a candidate's key skills and achievements using keyword extraction techniques. In addition, the document analysis unit can categorize and evaluate a candidate's documents using document classification techniques. For example, the document analysis unit can analyze a candidate's resume to evaluate their skill set and past achievements. This allows the document analysis unit to accurately evaluate a candidate's skill set and past achievements. Some or all of the above processing in the document analysis unit may be performed using or without a generative AI. For example, the document analysis unit can input a candidate's resume into a generative AI and have the generative AI perform the evaluation of the skill set and past achievements.

[0035] The interview support unit can analyze audio and video recordings of interviews to evaluate the candidate's facial expressions, tone of voice, and other characteristics. For example, the interview support unit can analyze audio and video recordings of interviews to evaluate the candidate's facial expressions and tone of voice. The interview support unit can use voice analysis technology to evaluate the candidate's tone of voice. Furthermore, the interview support unit can use video analysis technology to evaluate the candidate's facial expressions. In addition, the interview support unit can use emotion analysis technology to evaluate the candidate's emotions. For example, the interview support unit can analyze the candidate's tone of voice to evaluate their emotions. This allows the interview support unit to perform a more detailed evaluation by evaluating the candidate's facial expressions and tone of voice. Some or all of the above-described processes in the interview support unit may be performed using or without a generative AI. For example, the interview support unit can input the interview recording data into a generative AI and have the generative AI perform the evaluation of the candidate's facial expressions and tone of voice.

[0036] The hiring decision unit can evaluate not only a candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. For example, the hiring decision unit evaluates not only a candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. The hiring decision unit can use a scoring system to evaluate candidates. For example, the hiring decision unit makes hiring decisions based on a candidate's skills and aptitude. This allows the hiring decision unit to make optimal hiring decisions by also evaluating whether the candidate is a good fit for the company's needs and culture. Some or all of the above-described processes in the hiring decision unit may be performed using or without a generating AI. For example, the hiring decision unit can input candidate evaluation data into a generating AI and have the generating AI perform an evaluation of whether the candidate is a good fit for the company's needs and culture.

[0037] The document analysis unit can perform a detailed analysis of a candidate's past projects and achievements during document analysis to assess the depth of their skills. For example, the document analysis unit can use a generative AI to analyze the scale and complexity of projects the candidate has been involved in to assess the depth of their skills. The document analysis unit can also use a generative AI to analyze specific data related to the candidate's performance (e.g., sales growth rate, project completion rate) to assess the depth of their skills. Furthermore, the document analysis unit can use a generative AI to analyze details of the technologies and tools the candidate has used to assess the depth of their skills. For example, the document analysis unit can perform a detailed analysis of the candidate's past projects and achievements to assess the depth of their skills. This allows the document analysis unit to accurately assess the depth of a candidate's skills by performing a detailed analysis of their past projects and achievements. Some or all of the above processes in the document analysis unit may be performed using a generative AI, or they may not. For example, the document analysis unit can input the candidate's project data into a generative AI and have the generative AI perform the skill depth assessment.

[0038] The document analysis unit can compare a candidate's self-assessment with their actual performance during document analysis and evaluate its reliability. For example, the document analysis unit can use a generating AI to compare a candidate's self-assessment with their actual performance data and evaluate its reliability. Furthermore, if a candidate's self-assessment is excessive, the generating AI can point out the discrepancy and evaluate its reliability. Additionally, if a candidate's self-assessment is underestimated, the generating AI can emphasize their actual performance and evaluate its reliability. For example, the document analysis unit can compare a candidate's self-assessment with their actual performance and evaluate its reliability. This allows the document analysis unit to evaluate reliability by comparing a candidate's self-assessment with their actual performance. Some or all of the above processing in the document analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the document analysis unit can input candidate self-assessment data and performance data into a generating AI and have the generating AI perform the reliability evaluation.

[0039] The document analysis unit can analyze a candidate's social media activity during document analysis to supplement relevant skills and achievements. The document analysis unit can also use a generative AI to analyze a candidate's social media and blog posts to supplement their expertise and achievements. For example, the document analysis unit analyzes a candidate's social media activity to supplement relevant skills and achievements. This allows the document analysis unit to supplement relevant skills and achievements by analyzing a candidate's social media activity. Some or all of the above processing in the document analysis unit may be performed using a generative AI, or not. For example, the document analysis unit can input a candidate's social media data into a generative AI and have the generative AI perform the supplementation of skills and achievements.

[0040] The document analysis unit can evaluate region-specific skills and experience by considering the candidate's geographical location information during document analysis. For example, if a candidate has experience in a specific region, the generating AI in the document analysis unit can evaluate that region-specific skill and experience. Furthermore, if a candidate has experience in a multinational corporation, the generating AI in the document analysis unit can evaluate that international skill and experience. Additionally, if a candidate has been involved in region-specific projects, the generating AI in the document analysis unit can evaluate that experience. For example, the document analysis unit evaluates region-specific skills and experience by considering the candidate's geographical location information. This allows the document analysis unit to evaluate region-specific skills and experience by considering the candidate's geographical location information. Some or all of the above processing in the document analysis unit may be performed using the generating AI, or not. For example, the document analysis unit can input the candidate's geographical location data into the generating AI and have the generating AI perform the evaluation of region-specific skills and experience.

[0041] The interview support unit can generate optimal questions by referring to the candidate's past interview history during interview support. For example, the interview support unit can use a generating AI to analyze the content of questions the candidate has been asked in past interviews and generate optimal questions. The interview support unit can also use a generating AI to analyze the content of answers the candidate has given in past interviews and generate relevant questions. Furthermore, the interview support unit can use a generating AI to analyze the candidate's performance in past interviews and generate optimal questions. For example, the interview support unit can generate optimal questions by referring to the candidate's past interview history. In this way, the interview support unit can generate optimal questions by referring to the candidate's past interview history. Some or all of the above processes in the interview support unit may be performed using a generating AI, or they may not be performed using a generating AI. For example, the interview support unit can input the candidate's interview history data into a generating AI and have the generating AI perform the generation of optimal questions.

[0042] The interview support department can apply different question algorithms to candidates depending on their area of ​​expertise during interviews. For example, if a candidate is in the engineering field, the generative AI can generate technical questions. Similarly, if a candidate is in the marketing field, the generative AI can generate questions related to marketing strategies. Furthermore, if a candidate is in the design field, the generative AI can generate questions related to the design process. In short, the interview support department applies different question algorithms depending on the candidate's area of ​​expertise. This allows the interview support department to ask more appropriate questions by applying different question algorithms according to the candidate's area of ​​expertise. Some or all of the above processing in the interview support department may be performed using or without the generative AI. For example, the interview support department can input candidate area data into the generative AI and have the generative AI apply the question algorithms.

[0043] The interview support unit can evaluate the consistency of a candidate's answers and generate questions that point out inconsistencies during interviews. For example, the interview support unit can use a generating AI to compare a candidate's past and current answers and evaluate consistency. Furthermore, if there are inconsistencies in a candidate's answers, the generating AI can generate questions that highlight those inconsistencies. Additionally, if a candidate's answers are consistent, the generating AI can generate questions that emphasize that consistency. For example, the interview support unit can evaluate the consistency of a candidate's answers and generate questions that point out inconsistencies. This allows the interview support unit to perform a more accurate evaluation by assessing the consistency of a candidate's answers and pointing out inconsistencies. Some or all of the above processing in the interview support unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the interview support unit can input candidate answer data into a generating AI and have the generating AI perform consistency evaluation and inconsistency pointing.

[0044] The interview support unit can generate appropriate questions during interviews, taking into account the candidate's cultural background. For example, the interview support unit can use a generative AI to generate appropriate questions based on the candidate's cultural background. The interview support unit can also use a generative AI to generate culturally sensitive questions, taking into account the candidate's cultural background. Furthermore, the interview support unit can use a generative AI to generate questions that respect diversity, taking into account the candidate's cultural background. For example, the interview support unit generates appropriate questions, taking into account the candidate's cultural background. This enables the interview support unit to ask appropriate questions by considering the candidate's cultural background. Some or all of the above processing in the interview support unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the interview support unit can input the candidate's cultural background data into a generative AI and have the generative AI generate appropriate questions.

[0045] The response analysis unit can analyze the detailed content of a candidate's responses and evaluate the depth of their skills during response analysis. For example, the response analysis unit can use a generating AI to analyze the candidate's responses in detail and evaluate the depth of their skills. The response analysis unit can also use a generating AI to analyze specific examples and data included in the candidate's responses and evaluate the depth of their skills. Furthermore, the response analysis unit can use a generating AI to evaluate relevant skills and experience based on the candidate's responses. For example, the response analysis unit can analyze the detailed content of a candidate's responses and evaluate the depth of their skills. In this way, the response analysis unit can accurately evaluate the depth of skills by analyzing the detailed content of a candidate's responses. Some or all of the above processing in the response analysis unit may be performed using a generating AI or not. For example, the response analysis unit can input candidate response data into a generating AI and have the generating AI perform the evaluation of the depth of skills.

[0046] The response analysis unit can compare the candidate's responses with past performance data to evaluate their reliability during response analysis. For example, the response analysis unit can use a generating AI to compare the candidate's responses with past performance data and evaluate their reliability. The response analysis unit can also use the generating AI to emphasize the reliability of a candidate's responses if they match past performance data. Furthermore, if a candidate's responses do not match past performance data, the generating AI can point out the discrepancies and evaluate the reliability. For example, the response analysis unit compares the candidate's responses with past performance data to evaluate their reliability. This allows the response analysis unit to perform a more accurate evaluation of the candidate's responses by comparing them with past performance data. Some or all of the above processing in the response analysis unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the response analysis unit can input the candidate's response data and past performance data into the generating AI and have the generating AI perform the reliability evaluation.

[0047] The response analysis unit can evaluate the consistency of a candidate's responses and point out inconsistencies during response analysis. For example, the response analysis unit can use a generating AI to compare a candidate's past and current responses and evaluate consistency. The response analysis unit can also use a generating AI to point out inconsistencies in a candidate's responses. Furthermore, if a candidate's responses are consistent, the generating AI can emphasize that consistency. For example, the response analysis unit evaluates the consistency of a candidate's responses and points out inconsistencies. This allows the response analysis unit to perform a more accurate evaluation by evaluating the consistency of a candidate's responses and pointing out inconsistencies. Some or all of the above processing in the response analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the response analysis unit can input candidate response data into a generating AI and have the generating AI perform consistency evaluation and point out inconsistencies.

[0048] The response analysis unit can perform appropriate evaluations by considering the candidate's cultural background during response analysis. For example, the response analysis unit can have the generating AI perform appropriate evaluations based on the candidate's cultural background. The response analysis unit can also have the generating AI perform culturally sensitive evaluations by considering the candidate's cultural background. Furthermore, the response analysis unit can have the generating AI perform evaluations that respect diversity based on the candidate's cultural background. For example, the response analysis unit can perform appropriate evaluations by considering the candidate's cultural background. This enables the response analysis unit to perform appropriate evaluations by considering the candidate's cultural background. Some or all of the above processing in the response analysis unit may be performed using the generating AI, or it may be performed without using the generating AI. For example, the response analysis unit can input candidate cultural background data into the generating AI and have the generating AI perform appropriate evaluations.

[0049] The hiring decision unit can make the optimal decision by comparing a candidate's past performance with the company's needs in detail when making a hiring decision. For example, the hiring decision unit can use a generating AI to compare a candidate's past performance data with the company's needs in detail and make the optimal hiring decision. The hiring decision unit can also use a generating AI to compare a candidate's skill set with the skills the company is looking for and make the optimal hiring decision. Furthermore, the hiring decision unit can use a generating AI to compare a candidate's past project experience with the company's current project needs and make the optimal hiring decision. For example, the hiring decision unit can use a generating AI to compare a candidate's past performance with the company's needs in detail and make the optimal decision. In this way, the hiring decision unit can make the optimal hiring decision by comparing a candidate's past performance with the company's needs in detail. Some or all of the above processing in the hiring decision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the hiring decision unit can input candidate performance data and company needs data into a generating AI and have the generating AI execute the optimal decision.

[0050] The hiring decision unit can evaluate a candidate's cultural fit by comparing it to the company's culture. For example, the hiring decision unit can use a generating AI to compare the candidate's cultural background with the company's culture and evaluate cultural fit. The hiring decision unit can also use a generating AI to compare the candidate's values ​​with the company's values ​​and evaluate cultural fit. Furthermore, the hiring decision unit can use a generating AI to compare the candidate's past workplace culture with the company's culture and evaluate cultural fit. For example, the hiring decision unit can use a generating AI to evaluate a candidate's cultural fit by comparing it to the company's culture. This allows the hiring decision unit to make more appropriate hiring decisions by comparing a candidate's cultural fit with the company's culture. Some or all of the above processing in the hiring decision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the hiring decision unit can input candidate cultural background data and company culture data into a generating AI and have the generating AI perform the evaluation of cultural fit.

[0051] The hiring decision unit can evaluate region-specific skills and experience by considering the candidate's geographical location when making hiring decisions. For example, if a candidate has experience in a particular region, the hiring decision unit's generating AI can evaluate that region-specific skills and experience. Furthermore, if a candidate has experience in a multinational corporation, the generating AI can evaluate that international skills and experience. Additionally, if a candidate has been involved in region-specific projects, the generating AI can evaluate that experience. For example, the hiring decision unit evaluates region-specific skills and experience by considering the candidate's geographical location. This allows the hiring decision unit to evaluate region-specific skills and experience by considering the candidate's geographical location. Some or all of the above processing in the hiring decision unit may be performed using or without the generating AI. For example, the hiring decision unit can input the candidate's geographical location data into the generating AI and have the generating AI perform the evaluation of region-specific skills and experience.

[0052] The hiring decision unit can analyze a candidate's social media activity and supplement relevant skills and achievements when making a hiring decision. For example, the hiring decision unit analyzes a candidate's social media activity and supplements relevant skills and achievements. This allows the hiring decision unit to supplement relevant skills and achievements by analyzing a candidate's social media activity. Some or all of the above processing in the hiring decision unit may be performed using or without a generative AI. For example, the hiring decision unit can input a candidate's social media data into a generative AI and have the generative AI perform the supplementation of skills and achievements.

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

[0054] The recruitment support system can not only evaluate candidates' skills and aptitudes, but also assess their learning ability. For example, the document analysis unit can analyze a candidate's past learning history and self-study efforts to evaluate their learning ability. The interview support unit can generate questions that assess how candidates understand and apply new information. Furthermore, the response analysis unit can evaluate the candidate's learning ability from their answers, and the offer decision unit can make a decision on whether to offer a position considering this learning ability. In this way, the recruitment support system can assess a candidate's learning ability and determine their future growth potential.

[0055] The recruitment support system can also evaluate candidates' teamwork abilities. For example, the document analysis unit can analyze a candidate's role and contribution in past projects to assess their teamwork skills. The interview support unit can generate questions to evaluate a candidate's team experience and how they collaborate. Furthermore, the response analysis unit can evaluate a candidate's teamwork abilities from their answers, and the offer decision unit can make a decision on whether to offer a position, taking teamwork abilities into consideration. In this way, the recruitment support system can identify suitable personnel for the organization by evaluating candidates' teamwork abilities.

[0056] The recruitment support system can also evaluate candidates' leadership abilities. For example, the document analysis unit can analyze a candidate's past leadership experience and achievements to assess their leadership skills. The interview support unit can generate questions about the candidate's leadership style and leadership. Furthermore, the response analysis unit can evaluate the candidate's leadership abilities from their answers, and the offer decision unit can make a decision on whether to offer a position to a candidate, taking leadership abilities into consideration. In this way, the recruitment support system can identify future leadership candidates by evaluating their leadership abilities.

[0057] The recruitment support system can also evaluate candidates' problem-solving abilities. For example, the document analysis unit analyzes examples of problem-solving in a candidate's past projects to assess their problem-solving skills. The interview support unit generates questions related to the candidate's problem-solving abilities and can evaluate them through specific examples. Furthermore, the response analysis unit evaluates the candidate's problem-solving abilities from their answers, and the offer decision unit can make a decision on whether to offer a position, taking problem-solving abilities into consideration. In this way, the recruitment support system can assess a candidate's adaptability to practical work by evaluating their problem-solving abilities.

[0058] The recruitment support system can also evaluate candidates' creativity. For example, the document analysis unit analyzes creative efforts in a candidate's past projects and achievements to assess their creativity. The interview support unit generates questions about a candidate's creativity and can evaluate it through specific examples. Furthermore, the response analysis unit evaluates creativity from the candidate's answers, and the offer decision unit can make a decision on whether to offer a position considering creativity. In this way, the recruitment support system can identify individuals with innovative ideas by evaluating candidates' creativity.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The document analysis department analyzes the candidate's documents. For example, it analyzes the contents of resumes and work histories to evaluate the candidate's skill set and past achievements. The document analysis department uses generative AI and employs text mining, keyword extraction, and document classification technologies to objectively evaluate the candidate's skills and suitability. Step 2: The Interview Support Department generates interview questions based on the results analyzed by the Document Analysis Department. Using a generation AI, it generates appropriate questions based on the candidate's skills and aptitude. It can also analyze the interview audio and video recordings and evaluate the candidate's facial expressions, tone of voice, and emotions using voice analysis technology, video analysis technology, and sentiment analysis technology. Step 3: The response analysis unit analyzes the candidate's answers based on the questions generated by the interview support unit. Using generation AI, the unit analyzes the candidate's answers using text analysis technology, sentiment analysis technology, and content consistency evaluation technology to assess their skills and suitability. Step 4: The Offer Decision Unit makes an offer decision based on the results analyzed by the Response Analysis Unit. Using a generation AI, it evaluates not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. A scoring system is used to evaluate the candidate and make an offer decision.

[0061] (Example of form 2) The recruitment support system according to an embodiment of the present invention is a system that provides a bias-free recruitment process using generative AI. This recruitment support system provides comprehensive support from document screening to interviews and job offers, and realizes objective and fair recruitment based on the skills and aptitudes of candidates. This mechanism allows companies to build a more innovative and sustainable business environment by emphasizing diversity and recruiting excellent talent. First, conventional interviews and document screenings lack objectivity, making fair recruitment difficult. For example, the subjectivity and preconceptions of interviewers can influence the process, causing excellent talent to be overlooked. In contrast, the present invention uses generative AI to eliminate bias and perform objective evaluations based on the skills and aptitudes of candidates. Specifically, the generative AI first analyzes the candidate's documents and evaluates their skills and experience. For example, it analyzes the contents of resumes and work histories to evaluate the candidate's skill set and past performance. At this time, the generative AI objectively evaluates the candidate's skills and aptitudes based on data it has learned in advance. Next, the generative AI supports the interview process. For example, the generative AI generates interview questions and analyzes the candidate's answers to evaluate their skills and aptitudes. Furthermore, the generative AI can analyze recordings and videos of interviews, evaluating candidates' facial expressions and tone of voice to provide a more detailed assessment. It can also support the hiring process. For example, the generative AI can make hiring decisions based on the candidate's evaluation. In this process, the AI ​​evaluates not only the candidate's skills and aptitude, but also whether they fit the company's needs and culture. By using this generative AI, bias can be eliminated, enabling objective and fair hiring based on candidates' skills and aptitude. This allows companies to build a more innovative and sustainable business environment by emphasizing diversity and hiring top talent. For example, when a company hires engineers for a new project, the generative AI analyzes the candidate's application materials to evaluate their skills and experience. Next, the generative AI generates interview questions and analyzes the candidate's answers to assess their skills and aptitude. Finally, the generative AI makes hiring decisions based on the candidate's evaluation. In this way, bias can be eliminated, enabling objective and fair hiring.This allows the recruitment support system to eliminate bias and achieve objective and fair recruitment based on candidates' skills and aptitudes.

[0062] The recruitment support system according to this embodiment comprises a document analysis unit, an interview support unit, an answer analysis unit, and a job offer decision unit. The document analysis unit analyzes the candidate's documents. For example, the document analysis unit analyzes the contents of resumes and work histories and evaluates the candidate's skill set and past achievements. The document analysis unit uses generative AI to objectively evaluate the candidate's skills and aptitudes. For example, the document analysis unit uses text mining technology to extract the candidate's skills and experience. The document analysis unit can also use keyword extraction technology to identify the candidate's important skills and achievements. Furthermore, the document analysis unit can use document classification technology to classify and evaluate the candidate's documents by category. For example, the document analysis unit analyzes the candidate's resume and evaluates their skill set and past achievements. Next, the interview support unit generates interview questions based on the results analyzed by the document analysis unit. The interview support unit generates interview questions using generative AI. For example, the interview support unit generates appropriate questions based on the candidate's skills and aptitudes. Furthermore, the interview support unit can analyze audio and video recordings of interviews to evaluate the candidate's facial expressions and tone of voice. For example, the interview support unit can use voice analysis technology to evaluate the candidate's tone of voice. It can also use video analysis technology to evaluate the candidate's facial expressions. In addition, the interview support unit can use emotion analysis technology to evaluate the candidate's emotions. For example, the interview support unit can analyze the candidate's tone of voice and evaluate their emotions. Next, the response analysis unit analyzes the candidate's answers based on the questions generated by the interview support unit. The response analysis unit analyzes the candidate's answers using generation AI. For example, the response analysis unit analyzes the candidate's answers using text analysis technology. It can also use emotion analysis technology to evaluate the candidate's emotions. Furthermore, the response analysis unit can use content consistency evaluation technology to evaluate the consistency of the candidate's answers. For example, the response analysis unit analyzes the candidate's answers and evaluates their skills and aptitude. Finally, the job offer decision unit makes a job offer decision based on the results analyzed by the response analysis unit. The hiring decision department uses a generation AI to make hiring decisions. For example, the hiring decision department evaluates not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture.The hiring decision unit can also evaluate candidates using a scoring system. For example, the hiring decision unit makes hiring decisions based on the candidate's skills and aptitudes. As a result, the hiring support system according to this embodiment can eliminate bias and achieve objective and fair hiring based on the candidate's skills and aptitudes.

[0063] The Document Analysis Department analyzes candidates' documents. For example, it analyzes the contents of resumes and work histories to evaluate candidates' skill sets and past achievements. Specifically, the Document Analysis Department uses generative AI to objectively evaluate candidates' skills and aptitudes. The generative AI utilizes natural language processing technology to extract text data from candidates' documents and uses text mining technology to analyze candidates' skills and experience in detail. For example, it analyzes the job descriptions and project details listed in resumes to evaluate what skills candidates possess and what results they have achieved. It can also use keyword extraction technology to identify key skills and achievements of candidates. This allows the Document Analysis Department to accurately grasp candidates' skill sets and evaluate them in comparison to the skills required by the company. Furthermore, it can also use document classification technology to categorize and evaluate candidates' documents. For example, it can analyze a candidate's resume, categorize it into categories such as technical skills, management skills, and communication skills, and evaluate each category. This allows the document analysis department to comprehensively evaluate candidates' skills and aptitudes and select candidates who match the company's needs.

[0064] The Interview Support Department generates interview questions based on the results analyzed by the Document Analysis Department. The Interview Support Department uses a generation AI to generate interview questions. Specifically, the generation AI generates appropriate questions based on the candidate's skills and aptitudes. For example, based on the project experience listed in the candidate's resume, it generates questions about the specific role and achievements in those projects. The Interview Support Department can also analyze audio and video recordings of interviews to evaluate the candidate's facial expressions and tone of voice. Using voice analysis technology, it evaluates the candidate's tone of voice and determines their level of nervousness and confidence. Furthermore, using video analysis technology, it can evaluate the candidate's facial expressions and determine emotional changes and sincerity. It can also evaluate the candidate's emotions using emotion analysis technology. For example, by analyzing the candidate's tone of voice and evaluating their emotions, it can understand what emotions the candidate is experiencing. This allows the Interview Support Department to evaluate not only the candidate's skills and aptitudes, but also their emotions and attitudes, enabling a more comprehensive judgment.

[0065] The Response Analysis Unit analyzes candidates' responses based on questions generated by the Interview Support Unit. The Response Analysis Unit uses a generative AI to analyze candidates' responses. Specifically, the generative AI uses text analysis technology to analyze candidates' responses in detail. For example, it extracts keywords and phrases from candidates' responses and evaluates how well they match the skills and aptitudes sought by the company. It can also evaluate candidates' emotions using sentiment analysis technology. For example, it judges candidates' emotions and attitudes from the choice of words and expressions used in their responses. Furthermore, it can evaluate the consistency of candidates' responses using content consistency evaluation technology. For example, it checks whether candidates provide consistent answers to different questions and whether there are any contradictions. This allows the Response Analysis Unit to evaluate not only candidates' skills and aptitudes, but also the consistency and reliability of their responses, enabling more accurate judgments.

[0066] The hiring decision unit makes hiring decisions based on the results analyzed by the response analysis unit. The hiring decision unit uses generative AI to make hiring decisions. Specifically, the generative AI evaluates not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. For example, it evaluates whether the candidate's skill set matches the skills the company is looking for, and whether the candidate's values ​​and behaviors are compatible with the company's culture. The hiring decision unit can also evaluate candidates using a scoring system. For example, it assigns scores to each item based on the candidate's skills and aptitude and makes an overall evaluation. This allows the hiring decision unit to objectively evaluate the candidate's skills and aptitude and select the candidate who is best suited to the company's needs. Furthermore, the hiring decision unit can also make hiring decisions based on past hiring data and the company's success stories. For example, it can analyze data on candidates who have been hired in the past, identify common characteristics of successful candidates, and make hiring decisions based on those. This allows the hiring decision unit to make more accurate hiring decisions and contribute to the company's success.

[0067] The document analysis unit can analyze the contents of resumes and work histories to evaluate a candidate's skill set and past achievements. For example, the document analysis unit can analyze the contents of resumes and work histories to evaluate a candidate's skill set and past achievements. The document analysis unit can extract a candidate's skills and experience using text mining techniques. Furthermore, the document analysis unit can identify a candidate's key skills and achievements using keyword extraction techniques. In addition, the document analysis unit can categorize and evaluate a candidate's documents using document classification techniques. For example, the document analysis unit can analyze a candidate's resume to evaluate their skill set and past achievements. This allows the document analysis unit to accurately evaluate a candidate's skill set and past achievements. Some or all of the above processing in the document analysis unit may be performed using or without a generative AI. For example, the document analysis unit can input a candidate's resume into a generative AI and have the generative AI perform the evaluation of the skill set and past achievements.

[0068] The interview support unit can analyze audio and video recordings of interviews to evaluate the candidate's facial expressions, tone of voice, and other characteristics. For example, the interview support unit can analyze audio and video recordings of interviews to evaluate the candidate's facial expressions and tone of voice. The interview support unit can use voice analysis technology to evaluate the candidate's tone of voice. Furthermore, the interview support unit can use video analysis technology to evaluate the candidate's facial expressions. In addition, the interview support unit can use emotion analysis technology to evaluate the candidate's emotions. For example, the interview support unit can analyze the candidate's tone of voice to evaluate their emotions. This allows the interview support unit to perform a more detailed evaluation by evaluating the candidate's facial expressions and tone of voice. Some or all of the above-described processes in the interview support unit may be performed using or without a generative AI. For example, the interview support unit can input the interview recording data into a generative AI and have the generative AI perform the evaluation of the candidate's facial expressions and tone of voice.

[0069] The hiring decision unit can evaluate not only a candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. For example, the hiring decision unit evaluates not only a candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. The hiring decision unit can use a scoring system to evaluate candidates. For example, the hiring decision unit makes hiring decisions based on a candidate's skills and aptitude. This allows the hiring decision unit to make optimal hiring decisions by also evaluating whether the candidate is a good fit for the company's needs and culture. Some or all of the above-described processes in the hiring decision unit may be performed using or without a generating AI. For example, the hiring decision unit can input candidate evaluation data into a generating AI and have the generating AI perform an evaluation of whether the candidate is a good fit for the company's needs and culture.

[0070] The document analysis unit can estimate a candidate's emotions and adjust the document evaluation criteria based on the estimated emotions. For example, if a candidate is nervous, the generating AI can adjust the evaluation criteria to account for performance in a relaxed state. The document analysis unit can also evaluate the depth of skills based on the candidate's confidence if the generating AI is confident. Furthermore, if a candidate is stressed, the generating AI can adjust the evaluation criteria to mitigate the effects of stress. For example, the document analysis unit estimates the candidate's emotions and adjusts the evaluation criteria based on the estimated emotions. This allows the document analysis unit to provide a more appropriate evaluation by adjusting the evaluation criteria based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the document analysis unit may be performed using or without a generating AI. For example, the document analysis department can input candidate emotional data into a generating AI and have the AI ​​adjust the evaluation criteria based on those emotional data.

[0071] The document analysis unit can perform a detailed analysis of a candidate's past projects and achievements during document analysis to assess the depth of their skills. For example, the document analysis unit can use a generative AI to analyze the scale and complexity of projects the candidate has been involved in to assess the depth of their skills. The document analysis unit can also use a generative AI to analyze specific data related to the candidate's performance (e.g., sales growth rate, project completion rate) to assess the depth of their skills. Furthermore, the document analysis unit can use a generative AI to analyze details of the technologies and tools the candidate has used to assess the depth of their skills. For example, the document analysis unit can perform a detailed analysis of the candidate's past projects and achievements to assess the depth of their skills. This allows the document analysis unit to accurately assess the depth of a candidate's skills by performing a detailed analysis of their past projects and achievements. Some or all of the above processes in the document analysis unit may be performed using a generative AI, or they may not. For example, the document analysis unit can input the candidate's project data into a generative AI and have the generative AI perform the skill depth assessment.

[0072] The document analysis unit can compare a candidate's self-assessment with their actual performance during document analysis and evaluate its reliability. For example, the document analysis unit can use a generating AI to compare a candidate's self-assessment with their actual performance data and evaluate its reliability. Furthermore, if a candidate's self-assessment is excessive, the generating AI can point out the discrepancy and evaluate its reliability. Additionally, if a candidate's self-assessment is underestimated, the generating AI can emphasize their actual performance and evaluate its reliability. For example, the document analysis unit can compare a candidate's self-assessment with their actual performance and evaluate its reliability. This allows the document analysis unit to evaluate reliability by comparing a candidate's self-assessment with their actual performance. Some or all of the above processing in the document analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the document analysis unit can input candidate self-assessment data and performance data into a generating AI and have the generating AI perform the reliability evaluation.

[0073] The document analysis unit can estimate the candidate's emotions and determine the order in which to evaluate the documents based on the estimated emotions. For example, if the candidate is nervous, the generating AI will determine the evaluation order considering their performance in a relaxed state. The document analysis unit can also determine the evaluation order based on the candidate's confidence if they are confident. Furthermore, if the candidate is stressed, the generating AI can determine the evaluation order to mitigate the effects of stress. For example, the document analysis unit estimates the candidate's emotions and determines the evaluation order based on the estimated emotions. This allows the document analysis unit to perform a more appropriate evaluation by determining the evaluation order based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the document analysis unit may be performed using or without a generating AI. For example, the document analysis unit can input candidate emotional data into a generating AI and have the AI ​​determine the evaluation order based on those emotional data.

[0074] The document analysis unit can analyze a candidate's social media activity during document analysis and supplement relevant skills and achievements. For example, the document analysis unit can analyze a candidate's social media activity and supplement relevant skills and achievements. This allows the document analysis unit to supplement relevant skills and achievements by analyzing a candidate's social media activity. Some or all of the above processing in the document analysis unit may be performed using or without a generative AI. For example, the document analysis unit can input the candidate's social media data into a generative AI and have the generative AI perform the supplementation of skills and achievements.

[0075] The document analysis unit can evaluate region-specific skills and experience by considering the candidate's geographical location information during document analysis. For example, if a candidate has experience in a specific region, the generating AI in the document analysis unit can evaluate that region-specific skill and experience. Furthermore, if a candidate has experience in a multinational corporation, the generating AI in the document analysis unit can evaluate that international skill and experience. Additionally, if a candidate has been involved in region-specific projects, the generating AI in the document analysis unit can evaluate that experience. For example, the document analysis unit evaluates region-specific skills and experience by considering the candidate's geographical location information. This allows the document analysis unit to evaluate region-specific skills and experience by considering the candidate's geographical location information. Some or all of the above processing in the document analysis unit may be performed using the generating AI, or not. For example, the document analysis unit can input the candidate's geographical location data into the generating AI and have the generating AI perform the evaluation of region-specific skills and experience.

[0076] The interview support unit can estimate a candidate's emotions and adjust the interview questions based on those emotions. For example, if a candidate is nervous, the interview support unit's generative AI can generate questions to help them relax. Conversely, if a candidate is confident, the generative AI can generate challenging questions. Furthermore, if a candidate is stressed, the generative AI can generate questions to alleviate that stress. For instance, the interview support unit estimates a candidate's emotions and adjusts the questions based on those emotions. This allows the interview support unit to ask more appropriate questions by adjusting them based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the interview support unit may be performed using or without a generative AI. For example, the interview support unit can input candidate emotion data into a generative AI and have the generative AI adjust the questions based on those emotions.

[0077] The interview support unit can generate optimal questions by referring to the candidate's past interview history during interview support. For example, the interview support unit can use a generating AI to analyze the content of questions the candidate has been asked in past interviews and generate optimal questions. The interview support unit can also use a generating AI to analyze the content of answers the candidate has given in past interviews and generate relevant questions. Furthermore, the interview support unit can use a generating AI to analyze the candidate's performance in past interviews and generate optimal questions. For example, the interview support unit can generate optimal questions by referring to the candidate's past interview history. In this way, the interview support unit can generate optimal questions by referring to the candidate's past interview history. Some or all of the above processes in the interview support unit may be performed using a generating AI, or they may not be performed using a generating AI. For example, the interview support unit can input the candidate's interview history data into a generating AI and have the generating AI perform the generation of optimal questions.

[0078] The interview support department can apply different question algorithms to candidates depending on their area of ​​expertise during interviews. For example, if a candidate is in the engineering field, the generative AI can generate technical questions. Similarly, if a candidate is in the marketing field, the generative AI can generate questions related to marketing strategies. Furthermore, if a candidate is in the design field, the generative AI can generate questions related to the design process. In short, the interview support department applies different question algorithms depending on the candidate's area of ​​expertise. This allows the interview support department to ask more appropriate questions by applying different question algorithms according to the candidate's area of ​​expertise. Some or all of the above processing in the interview support department may be performed using or without the generative AI. For example, the interview support department can input candidate area data into the generative AI and have the generative AI apply the question algorithms.

[0079] The interview support unit can estimate the candidate's emotions and adjust the order of interview questions based on the estimated emotions. For example, if the candidate is nervous, the generative AI can place questions designed to help them relax first. Similarly, if the candidate is confident, the generative AI can place challenging questions later in the interview. Furthermore, if the candidate is stressed, the generative AI can place questions designed to reduce stress first. For example, the interview support unit estimates the candidate's emotions and adjusts the order of questions based on those emotions. This allows the interview support unit to ask more appropriate questions by adjusting the order of questions based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the interview support unit may be performed using or without generative AI. For example, the interview support department can input candidate emotional data into a generating AI and have the AI ​​adjust the order of questions based on those emotions.

[0080] The interview support unit can evaluate the consistency of a candidate's answers and generate questions that point out inconsistencies during interviews. For example, the interview support unit can use a generating AI to compare a candidate's past and current answers and evaluate consistency. Furthermore, if there are inconsistencies in a candidate's answers, the generating AI can generate questions that highlight those inconsistencies. Additionally, if a candidate's answers are consistent, the generating AI can generate questions that emphasize that consistency. For example, the interview support unit can evaluate the consistency of a candidate's answers and generate questions that point out inconsistencies. This allows the interview support unit to perform a more accurate evaluation by assessing the consistency of a candidate's answers and pointing out inconsistencies. Some or all of the above processing in the interview support unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the interview support unit can input candidate answer data into a generating AI and have the generating AI perform consistency evaluation and inconsistency pointing.

[0081] The interview support unit can generate appropriate questions during interviews, taking into account the candidate's cultural background. For example, the interview support unit can use a generative AI to generate appropriate questions based on the candidate's cultural background. The interview support unit can also use a generative AI to generate culturally sensitive questions, taking into account the candidate's cultural background. Furthermore, the interview support unit can use a generative AI to generate questions that respect diversity, taking into account the candidate's cultural background. For example, the interview support unit generates appropriate questions, taking into account the candidate's cultural background. This enables the interview support unit to ask appropriate questions by considering the candidate's cultural background. Some or all of the above processing in the interview support unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the interview support unit can input the candidate's cultural background data into a generative AI and have the generative AI generate appropriate questions.

[0082] The response analysis unit can estimate the candidate's emotions and adjust the evaluation criteria for the responses based on the estimated emotions. For example, if the candidate is nervous, the response analysis unit can adjust the evaluation criteria so that the generating AI takes into account performance in a relaxed state. The response analysis unit can also have the generating AI evaluate the depth of skills based on the candidate's confidence if the candidate is confident. Furthermore, if the candidate is stressed, the response analysis unit can have the generating AI adjust the evaluation criteria to mitigate the effects of stress. For example, the response analysis unit estimates the candidate's emotions and adjusts the evaluation criteria based on the estimated emotions. This allows the response analysis unit to provide a more appropriate evaluation by adjusting the evaluation criteria based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response analysis unit may be performed using or without a generating AI. For example, the response analysis unit can input candidate emotional data into a generating AI, which can then adjust the evaluation criteria based on those emotional data.

[0083] The response analysis unit can analyze the detailed content of a candidate's responses and evaluate the depth of their skills during response analysis. For example, the response analysis unit can use a generating AI to analyze the candidate's responses in detail and evaluate the depth of their skills. The response analysis unit can also use a generating AI to analyze specific examples and data included in the candidate's responses and evaluate the depth of their skills. Furthermore, the response analysis unit can use a generating AI to evaluate relevant skills and experience based on the candidate's responses. For example, the response analysis unit can analyze the detailed content of a candidate's responses and evaluate the depth of their skills. In this way, the response analysis unit can accurately evaluate the depth of skills by analyzing the detailed content of a candidate's responses. Some or all of the above processing in the response analysis unit may be performed using a generating AI or not. For example, the response analysis unit can input candidate response data into a generating AI and have the generating AI perform the evaluation of the depth of skills.

[0084] The response analysis unit can compare the candidate's responses with past performance data to evaluate their reliability during response analysis. For example, the response analysis unit can use a generating AI to compare the candidate's responses with past performance data and evaluate their reliability. The response analysis unit can also use the generating AI to emphasize the reliability of a candidate's responses if they match past performance data. Furthermore, if a candidate's responses do not match past performance data, the generating AI can point out the discrepancies and evaluate the reliability. For example, the response analysis unit compares the candidate's responses with past performance data to evaluate their reliability. This allows the response analysis unit to perform a more accurate evaluation of the candidate's responses by comparing them with past performance data. Some or all of the above processing in the response analysis unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the response analysis unit can input the candidate's response data and past performance data into the generating AI and have the generating AI perform the reliability evaluation.

[0085] The response analysis unit can estimate the candidate's emotions and determine the order of evaluation based on the estimated candidate's emotions. For example, if the candidate is nervous, the response analysis unit will determine the evaluation order by considering the candidate's performance in a relaxed state. The response analysis unit can also determine the evaluation order based on the candidate's confidence if the candidate is confident. Furthermore, if the candidate is stressed, the response analysis unit can determine the evaluation order by having the generation AI mitigate the effects of stress. For example, the response analysis unit estimates the candidate's emotions and determines the evaluation order based on the estimated emotions. This allows the response analysis unit to perform more appropriate evaluations by determining the evaluation order based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response analysis unit may be performed using or without the generation AI. For example, the response analysis unit can input candidate emotional data into a generating AI, which can then perform the task of determining the evaluation order based on those emotional responses.

[0086] The response analysis unit can evaluate the consistency of a candidate's responses and point out inconsistencies during response analysis. For example, the response analysis unit can use a generating AI to compare a candidate's past and current responses and evaluate consistency. The response analysis unit can also use a generating AI to point out inconsistencies in a candidate's responses. Furthermore, if a candidate's responses are consistent, the generating AI can emphasize that consistency. For example, the response analysis unit evaluates the consistency of a candidate's responses and points out inconsistencies. This allows the response analysis unit to perform a more accurate evaluation by evaluating the consistency of a candidate's responses and pointing out inconsistencies. Some or all of the above processing in the response analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the response analysis unit can input candidate response data into a generating AI and have the generating AI perform consistency evaluation and point out inconsistencies.

[0087] The response analysis unit can perform appropriate evaluations by considering the candidate's cultural background during response analysis. For example, the response analysis unit can have the generating AI perform appropriate evaluations based on the candidate's cultural background. The response analysis unit can also have the generating AI perform culturally sensitive evaluations by considering the candidate's cultural background. Furthermore, the response analysis unit can have the generating AI perform evaluations that respect diversity based on the candidate's cultural background. For example, the response analysis unit can perform appropriate evaluations by considering the candidate's cultural background. This enables the response analysis unit to perform appropriate evaluations by considering the candidate's cultural background. Some or all of the above processing in the response analysis unit may be performed using the generating AI, or it may be performed without using the generating AI. For example, the response analysis unit can input candidate cultural background data into the generating AI and have the generating AI perform appropriate evaluations.

[0088] The hiring decision unit can estimate a candidate's emotions and adjust the hiring decision criteria based on the estimated emotions. For example, if a candidate is nervous, the hiring decision unit's generative AI can adjust the hiring decision criteria to consider their performance in a relaxed state. Furthermore, if a candidate is confident, the hiring decision unit's generative AI can adjust the hiring decision criteria based on that confidence. Additionally, if a candidate is stressed, the hiring decision unit's generative AI can adjust the hiring decision criteria to mitigate the effects of stress. For example, the hiring decision unit estimates a candidate's emotions and adjusts the hiring decision criteria based on those emotions. This allows the hiring decision unit to make more appropriate hiring decisions by adjusting the criteria based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the hiring decision unit may be performed using or without generative AI. For example, the hiring decision unit can input candidate emotional data into a generating AI and have the AI ​​adjust the decision criteria based on those emotional factors.

[0089] The hiring decision unit can make the optimal decision by comparing a candidate's past performance with the company's needs in detail when making a hiring decision. For example, the hiring decision unit can use a generating AI to compare a candidate's past performance data with the company's needs in detail and make the optimal hiring decision. The hiring decision unit can also use a generating AI to compare a candidate's skill set with the skills the company is looking for and make the optimal hiring decision. Furthermore, the hiring decision unit can use a generating AI to compare a candidate's past project experience with the company's current project needs and make the optimal hiring decision. For example, the hiring decision unit can use a generating AI to compare a candidate's past performance with the company's needs in detail and make the optimal decision. In this way, the hiring decision unit can make the optimal hiring decision by comparing a candidate's past performance with the company's needs in detail. Some or all of the above processing in the hiring decision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the hiring decision unit can input candidate performance data and company needs data into a generating AI and have the generating AI execute the optimal decision.

[0090] The hiring decision unit can evaluate a candidate's cultural fit by comparing it to the company's culture. For example, the hiring decision unit can use a generating AI to compare the candidate's cultural background with the company's culture and evaluate cultural fit. The hiring decision unit can also use a generating AI to compare the candidate's values ​​with the company's values ​​and evaluate cultural fit. Furthermore, the hiring decision unit can use a generating AI to compare the candidate's past workplace culture with the company's culture and evaluate cultural fit. For example, the hiring decision unit can use a generating AI to evaluate a candidate's cultural fit by comparing it to the company's culture. This allows the hiring decision unit to make more appropriate hiring decisions by comparing a candidate's cultural fit with the company's culture. Some or all of the above processing in the hiring decision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the hiring decision unit can input candidate cultural background data and company culture data into a generating AI and have the generating AI perform the evaluation of cultural fit.

[0091] The job offer decision unit can estimate a candidate's emotions and determine the priority of job offers based on the estimated emotions. For example, if a candidate is nervous, the generation AI will consider their performance in a relaxed state when determining the priority of job offers. Furthermore, if a candidate is confident, the generation AI can determine the priority of job offers based on that confidence. Additionally, if a candidate is stressed, the generation AI can determine the priority of job offers to mitigate the effects of that stress. For example, the job offer decision unit estimates a candidate's emotions and determines the priority of job offers based on those emotions. This allows the job offer decision unit to make more appropriate decisions by determining the priority of job offers based on the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the job offer decision unit may be performed using or without generation AI. For example, the hiring decision unit can input candidate emotional data into a generating AI and have the AI ​​perform priority decisions based on those emotions.

[0092] The hiring decision unit can evaluate region-specific skills and experience by considering the candidate's geographical location when making hiring decisions. For example, if a candidate has experience in a particular region, the hiring decision unit's generating AI can evaluate that region-specific skills and experience. Furthermore, if a candidate has experience in a multinational corporation, the generating AI can evaluate that international skills and experience. Additionally, if a candidate has been involved in region-specific projects, the generating AI can evaluate that experience. For example, the hiring decision unit evaluates region-specific skills and experience by considering the candidate's geographical location. This allows the hiring decision unit to evaluate region-specific skills and experience by considering the candidate's geographical location. Some or all of the above processing in the hiring decision unit may be performed using or without the generating AI. For example, the hiring decision unit can input the candidate's geographical location data into the generating AI and have the generating AI perform the evaluation of region-specific skills and experience.

[0093] The hiring decision unit can analyze a candidate's social media activity and supplement relevant skills and achievements when making a hiring decision. For example, the hiring decision unit analyzes a candidate's social media activity and supplements relevant skills and achievements. This allows the hiring decision unit to supplement relevant skills and achievements by analyzing a candidate's social media activity. Some or all of the above processing in the hiring decision unit may be performed using or without a generative AI. For example, the hiring decision unit can input a candidate's social media data into a generative AI and have the generative AI perform the supplementation of skills and achievements.

[0094] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0095] The recruitment support system can not only evaluate candidates' skills and aptitudes, but also assess their learning ability. For example, the document analysis unit can analyze a candidate's past learning history and self-study efforts to evaluate their learning ability. The interview support unit can generate questions that assess how candidates understand and apply new information. Furthermore, the response analysis unit can evaluate the candidate's learning ability from their answers, and the offer decision unit can make a decision on whether to offer a position considering this learning ability. In this way, the recruitment support system can assess a candidate's learning ability and determine their future growth potential.

[0096] The recruitment support system can also evaluate candidates' teamwork abilities. For example, the document analysis unit can analyze a candidate's role and contribution in past projects to assess their teamwork skills. The interview support unit can generate questions to evaluate a candidate's team experience and how they collaborate. Furthermore, the response analysis unit can evaluate a candidate's teamwork abilities from their answers, and the offer decision unit can make a decision on whether to offer a position, taking teamwork abilities into consideration. In this way, the recruitment support system can identify suitable personnel for the organization by evaluating candidates' teamwork abilities.

[0097] The recruitment support system can also evaluate candidates' leadership abilities. For example, the document analysis unit can analyze a candidate's past leadership experience and achievements to assess their leadership skills. The interview support unit can generate questions about the candidate's leadership style and leadership. Furthermore, the response analysis unit can evaluate the candidate's leadership abilities from their answers, and the offer decision unit can make a decision on whether to offer a position to a candidate, taking leadership abilities into consideration. In this way, the recruitment support system can identify future leadership candidates by evaluating their leadership abilities.

[0098] The recruitment support system can also evaluate candidates' problem-solving abilities. For example, the document analysis unit analyzes examples of problem-solving in a candidate's past projects to assess their problem-solving skills. The interview support unit generates questions related to the candidate's problem-solving abilities and can evaluate them through specific examples. Furthermore, the response analysis unit evaluates the candidate's problem-solving abilities from their answers, and the offer decision unit can make a decision on whether to offer a position, taking problem-solving abilities into consideration. In this way, the recruitment support system can assess a candidate's adaptability to practical work by evaluating their problem-solving abilities.

[0099] The recruitment support system can also evaluate candidates' creativity. For example, the document analysis unit analyzes creative efforts in a candidate's past projects and achievements to assess their creativity. The interview support unit generates questions about a candidate's creativity and can evaluate it through specific examples. Furthermore, the response analysis unit evaluates creativity from the candidate's answers, and the offer decision unit can make a decision on whether to offer a position considering creativity. In this way, the recruitment support system can identify individuals with innovative ideas by evaluating candidates' creativity.

[0100] The recruitment support system can estimate a candidate's emotions and provide interview feedback based on those emotions. For example, if a candidate is nervous, the interview support system can provide feedback to help them relax. It can also provide feedback to reinforce a candidate's confidence if they are confident. Furthermore, if a candidate is stressed, the interview support system can provide feedback to reduce that stress. This allows the interview support system to improve the quality of interviews by providing appropriate feedback based on the candidate's emotions.

[0101] The recruitment support system can estimate a candidate's emotions and adjust the interview process based on those estimates. For example, if the interview support system perceives a candidate as nervous, it will slow down the interview to help them relax. Conversely, if the candidate is confident, it can proceed more smoothly. Furthermore, if the interview support system perceives a candidate as stressed, it can adjust the interview process to alleviate that stress. This allows the interview support system to conduct more effective interviews by adjusting the process based on the candidate's emotions.

[0102] The recruitment support system can estimate a candidate's emotions and adjust interview evaluation criteria based on those emotions. For example, if a candidate is nervous, the interview support system can adjust the evaluation criteria to account for their performance in a relaxed state. It can also adjust the criteria based on a candidate's confidence if they are confident. Furthermore, if a candidate is stressed, the system can adjust the criteria to mitigate the effects of that stress. This allows the interview support system to provide more accurate evaluations by adjusting criteria based on the candidate's emotions.

[0103] The recruitment support system can estimate a candidate's emotions and adjust the way they notify the candidate of their job offer based on those emotions. For example, if a candidate is feeling nervous, the system will carefully notify them of the offer to help them relax. It can also respect a candidate's confidence when notifying them of their job offer. Furthermore, if a candidate is feeling stressed, the system can adjust the notification method to alleviate that stress. This allows the system to provide more appropriate job offers by adjusting the notification method based on the candidate's emotions.

[0104] The recruitment support system can estimate a candidate's emotions and provide follow-up support after an offer is made based on those estimated emotions. For example, if a candidate is nervous, the system can provide follow-up support to help them relax. If a candidate is confident, the system can also provide follow-up support to reinforce that confidence. Furthermore, if a candidate is stressed, the system can provide follow-up support to help reduce that stress. This allows the system to provide more appropriate support by tailoring post-offer follow-up to the candidate's emotions.

[0105] The following briefly describes the processing flow for example form 2.

[0106] Step 1: The document analysis department analyzes the candidate's documents. For example, it analyzes the contents of resumes and work histories to evaluate the candidate's skill set and past achievements. The document analysis department uses generative AI and employs text mining, keyword extraction, and document classification technologies to objectively evaluate the candidate's skills and suitability. Step 2: The Interview Support Department generates interview questions based on the results analyzed by the Document Analysis Department. Using a generation AI, it generates appropriate questions based on the candidate's skills and aptitude. It can also analyze the interview audio and video recordings and evaluate the candidate's facial expressions, tone of voice, and emotions using voice analysis technology, video analysis technology, and sentiment analysis technology. Step 3: The response analysis unit analyzes the candidate's answers based on the questions generated by the interview support unit. Using generation AI, the unit analyzes the candidate's answers using text analysis technology, sentiment analysis technology, and content consistency evaluation technology to assess their skills and suitability. Step 4: The Offer Decision Unit makes an offer decision based on the results analyzed by the Response Analysis Unit. Using a generation AI, it evaluates not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. A scoring system is used to evaluate the candidate and make an offer decision.

[0107] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0108] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0109] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0110] Each of the multiple elements described above, including the document analysis unit, interview support unit, answer analysis unit, and job offer decision unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the smart device 14 and analyzes the candidate's documents. The interview support unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates interview questions. The answer analysis unit is implemented by, for example, the control unit 46A of the smart device 14 and analyzes the candidate's answers. The job offer decision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and makes a decision on whether to offer a job. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0112] As shown in Figure 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.

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

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

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

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

[0117] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0118] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0119] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0120] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0122] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

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

[0124] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

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

[0126] Each of the multiple elements described above, including the document analysis unit, interview support unit, answer analysis unit, and job offer decision unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the candidate's documents. The interview support unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates interview questions. The answer analysis unit is implemented by, for example, the control unit 46A of the smart glasses 214 and analyzes the candidate's answers. The job offer decision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and makes a decision on whether to offer a job. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0128] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the document analysis unit, interview support unit, answer analysis unit, and job offer decision unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the candidate's documents. The interview support unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates interview questions. The answer analysis unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the candidate's answers. The job offer decision unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes a decision on whether to offer a job. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0144] As shown in Figure 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the 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 image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0151] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements described above, including the document analysis unit, interview support unit, answer analysis unit, and job offer decision unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the robot 414 and analyzes the candidate's documents. The interview support unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates interview questions. The answer analysis unit is implemented by, for example, the control unit 46A of the robot 414 and analyzes the candidate's answers. The job offer decision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and makes a decision on whether to offer a job. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0160] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0161] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0162] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0163] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0164] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0165] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0168] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0169] 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.

[0170] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0171] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0172] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0173] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0174] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0175] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0176] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0177] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0178] (Note 1) The document analysis department analyzes the candidates' documents, An interview support unit generates interview questions based on the results of the document analysis unit, The response analysis unit analyzes the candidate's answers based on the questions generated by the aforementioned interview support unit, The system includes a job offer decision unit that makes a job offer decision based on the results analyzed by the aforementioned response analysis unit. A system characterized by the following features. (Note 2) The aforementioned document analysis unit, We analyze the content of resumes and work histories to evaluate candidates' skill sets and past achievements. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned interview support department, The interview audio and video are analyzed to evaluate the candidate's facial expressions, tone of voice, and other factors. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned decision-making unit for job offers, We evaluate not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned document analysis unit, Estimate the candidate's sentiments and adjust the document evaluation criteria based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned document analysis unit, During the document analysis, a detailed analysis of the candidate's past projects and achievements is conducted to assess the depth of their skills. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned document analysis unit, During document analysis, the reliability of the candidate's self-assessment is evaluated by comparing it with their actual performance. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned document analysis unit, The system estimates the candidates' emotions and determines the order in which to evaluate the documents based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned document analysis unit, During document analysis, we analyze the candidate's social media activity to complement relevant skills and achievements. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned document analysis unit, During document analysis, we consider the candidate's geographical location to evaluate region-specific skills and experience. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned interview support department, The system estimates the candidate's emotions and adjusts the interview questions based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned interview support department, During interview support, the system generates optimal questions by referencing the candidate's past interview history. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned interview support department, When providing interview support, different question algorithms are applied depending on the candidate's area of ​​expertise. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned interview support department, The system estimates the candidate's emotions and adjusts the order of interview questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned interview support department, During interview support, we generate questions that assess the consistency of a candidate's answers and point out inconsistencies. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned interview support department, When providing interview support, consider the candidate's cultural background to generate appropriate questions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned response analysis unit, The system estimates the candidate's emotions and adjusts the evaluation criteria for responses based on the estimated candidate's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned response analysis unit, During response analysis, the detailed content of the candidates' answers is analyzed to assess the depth of their skills. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned response analysis unit, During response analysis, the reliability of candidates' responses is evaluated by comparing them with past performance. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned response analysis unit, The system estimates the candidates' emotions and determines the order in which to evaluate their responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned response analysis unit, During response analysis, the consistency of the candidates' responses is evaluated, and inconsistencies are pointed out. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned response analysis unit, When analyzing responses, consider the candidates' cultural backgrounds to ensure appropriate evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned decision-making unit for job offers, We estimate the candidate's emotions and adjust the criteria for making a hiring decision based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned decision-making unit for job offers, When making a hiring decision, we thoroughly compare the candidate's past performance with the company's needs to make the best decision. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned decision-making unit for job offers, When deciding whether to offer a job, we compare the candidate's cultural fit with the company's culture to assess their cultural compatibility. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned decision-making unit for job offers, The system estimates the candidates' emotions and determines the priority of job offers based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned decision-making unit for job offers, When making a hiring decision, we consider the candidate's geographical location and evaluate their region-specific skills and experience. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned decision-making unit for job offers, When making a hiring decision, we analyze the candidate's social media activity to complement their relevant skills and achievements. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The document analysis department analyzes the candidates' documents, An interview support unit generates interview questions based on the results of the document analysis unit, The response analysis unit analyzes the candidate's answers based on the questions generated by the aforementioned interview support unit, The system includes a job offer decision unit that makes a job offer decision based on the results analyzed by the aforementioned response analysis unit. A system characterized by the following features.

2. The aforementioned document analysis unit, We analyze the content of resumes and work histories to evaluate candidates' skill sets and past achievements. The system according to feature 1.

3. The aforementioned interview support department, The interview audio and video are analyzed to evaluate the candidate's facial expressions, tone of voice, and other factors. The system according to feature 1.

4. The aforementioned decision-making unit for job offers, We evaluate not only the candidate's skills and aptitude, but also whether they are a good fit for the company's needs and culture. The system according to feature 1.

5. The aforementioned document analysis unit, Estimate the candidate's sentiments and adjust the document evaluation criteria based on those estimated sentiments. The system according to feature 1.

6. The aforementioned document analysis unit, During the document analysis, a detailed analysis of the candidate's past projects and achievements is conducted to assess the depth of their skills. The system according to feature 1.

7. The aforementioned document analysis unit, During document analysis, the reliability of the candidate's self-assessment is evaluated by comparing it with their actual performance. The system according to feature 1.

8. The aforementioned document analysis unit, The system estimates the candidates' emotions and determines the order in which to evaluate the documents based on those estimated emotions. The system according to feature 1.

Images