system

Abstract

The system according to this embodiment aims to reduce costs in recruitment activities and prevent mismatches. [Solution] The system according to the embodiment comprises an analysis unit, a question generation unit, an interview unit, and a summarization unit. The analysis unit analyzes the information in the application form. The question generation unit generates questions based on the information analyzed by the analysis unit. The interview unit conducts an online interview using the questions generated by the question generation unit. The summarization unit summarizes the interview results obtained by the interview unit.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , ,

[0003] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, in the recruitment activity, it is necessary to read a large number of entry sheets and conduct multiple interviews, which is costly and there is a risk of mismatch.

[0005] The system according to the embodiment aims to reduce the cost in the recruitment activity and prevent mismatches.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a question generation unit, an interview unit, and a summarization unit. The analysis unit analyzes the information in the application form. The question generation unit generates questions based on the information analyzed by the analysis unit. The interview unit conducts an online interview using the questions generated by the question generation unit. The summarization unit summarizes the interview results obtained by the interview unit. [Effects of the Invention]

[0007] The system according to this embodiment can reduce costs in recruitment activities and prevent mismatches. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable 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 aims to reduce recruitment costs and prevent mismatches by introducing an AI interviewer using a generation AI and a voice generation AI as a preliminary interview in the recruitment process. This recruitment support system analyzes the application form and generates appropriate questions for the applicant. Next, the recruitment support system conducts an interview with the applicant using an online platform. At this time, the recruitment support system uses RAG to refer to company-specific information and past recruitment information and asks questions that it wants to confirm during the interview. The recruitment support system also conducts a knowledge test utilizing the vast knowledge of the AI. Since the applicant will think of and answer questions on the spot during the interview, it is possible to elicit their true feelings, which may differ from those expressed in the application form. Finally, the recruitment support system summarizes the interview results and provides the HR department with feedback materials that summarize points to ask in the first interview. This makes it possible to get to know the applicant in a short time and to streamline preparation for the next interview. By using generation AI, it becomes possible to analyze the applicant more logically and provide feedback. For example, the recruitment support system analyzes the applicant's career history, skills, and motivation in detail and extracts points that should be confirmed in the interview. For example, the system analyzes the applicant's role in specific projects and their skills. This allows it to generate appropriate questions for the applicant. Next, the recruitment support system conducts interviews with applicants using an online platform. During this process, the system uses RAG to refer to company-specific information and past recruitment data, asking questions to confirm key points. For example, it generates questions based on the skill sets the company requires and past recruitment criteria. This ensures that questions are tailored to the company's needs. Furthermore, the recruitment support system conducts knowledge tests. Leveraging the vast knowledge of AI, it generates questions to evaluate the applicant's expertise and skills. For example, it asks questions about specific technologies and industry trends. This allows for an objective assessment of the applicant's knowledge level. The interview results are summarized by the recruitment support system. Based on the information obtained from the interview, the system generates feedback materials summarizing the applicant's strengths and weaknesses, and points that should be asked in the first interview.This allows HR personnel to quickly understand candidates and streamline preparation for subsequent interviews. This system helps reduce recruitment costs and prevent mismatches. By having the recruitment support system conduct a preliminary interview, the effort of reviewing application forms and conducting multiple interviews is eliminated. Furthermore, because the recruitment support system evaluates objectively without being influenced by emotions, it also contributes to preventing mismatches. For example, even if a candidate is nervous, the recruitment support system can calmly ask questions and elicit the candidate's true feelings. This allows companies to efficiently recruit top talent. In short, the recruitment support system helps reduce recruitment costs and prevent mismatches.

[0029] The recruitment support system according to this embodiment comprises an analysis unit, a question generation unit, an interview unit, and a summarization unit. The analysis unit analyzes the information in the application form. For example, the analysis unit analyzes the applicant's career history, skills, and motivation for applying. For example, the analysis unit can use text analysis technology to analyze the content of the application form and extract the applicant's strengths and weaknesses. The analysis unit can also use data mining technology to analyze the applicant's past work history and skill set in detail. For example, the analysis unit can analyze the detailed roles in projects the applicant has been involved in in the past and extract specific results. The question generation unit generates questions based on the information analyzed by the analysis unit. For example, the question generation unit refers to company-specific information and past recruitment information and asks questions about points it wants to confirm in the interview. For example, the question generation unit can generate questions for applicants based on the company's vision and mission. The question generation unit can also refer to past recruitment criteria and interview questions and generate questions that meet the company's needs. For example, the question generation unit generates questions based on the skill set required by the company and past recruitment criteria. The interview unit conducts online interviews using questions generated by the question generation unit. The interview unit conducts interviews with applicants using, for example, an online platform. The interview unit can also conduct knowledge tests by leveraging the vast knowledge of AI. For example, the interview unit can ask questions about specific technologies or industry trends to objectively evaluate the applicant's knowledge level. The summarization unit summarizes the interview results obtained by the interview unit. For example, the summarization unit generates feedback materials based on the information obtained from the interview, summarizing the applicant's strengths and weaknesses and points to ask in the first interview. The summarization unit can summarize the interview results using, for example, text analysis technology and extract important information. The summarization unit can also summarize the interview results using AI and generate feedback materials. For example, based on the interview results, the summarization unit can analyze the applicant's strengths and weaknesses and propose specific areas for improvement. As a result, the recruitment support system according to this embodiment can reduce recruitment costs and prevent mismatches.Some or all of the above-described processes in the analysis unit, question generation unit, interview unit, and summarization unit may be performed using AI, for example, or without AI. For example, the analysis unit can input information from the application form into the AI ​​and have the AI ​​output the analysis results. The question generation unit can input the analysis results into the AI ​​and have the AI ​​generate questions. The interview unit can input the generated questions into the AI ​​and have the AI ​​conduct an online interview. The summarization unit can input the interview results into the AI ​​and have the AI ​​output a summary.

[0030] The analysis department analyzes the information in application forms. For example, it analyzes the applicant's background, skills, and motivation for applying. The analysis department can use text analysis technology to analyze the content of application forms and extract the applicant's strengths and weaknesses. Specifically, it uses natural language processing (NLP) technology to analyze the text data of application forms, extracting keywords and understanding the context. For example, it can analyze in detail the project experience and skill set described by the applicant and identify experience using specific technologies and tools. The analysis department can also use data mining technology to analyze in detail the applicant's past work history and skill set. For example, it can analyze the detailed role in projects the applicant has been involved in in the past and extract specific results. This makes it possible to objectively evaluate the applicant's achievements and abilities. Furthermore, the analysis department can use machine learning algorithms to cluster the applicant's data and identify similar applicant groups. This allows companies to quickly find the best candidates for specific positions. The analysis department utilizes these technologies to comprehensively analyze information from application forms and support companies' recruitment activities.

[0031] The question generation unit generates questions based on information analyzed by the analysis unit. For example, the question generation unit can refer to company-specific information and past recruitment information to ask questions that it wants to confirm during the interview. Specifically, it can generate questions for applicants based on the company's vision and mission. For example, it can generate questions related to the values ​​and culture that the company emphasizes to evaluate the applicant's suitability. The question generation unit can also refer to past recruitment criteria and interview questions to generate questions that meet the company's needs. For example, it can generate questions based on the skill set the company requires and past recruitment criteria. Furthermore, the question generation unit can generate questions using AI. Specifically, it can use a generation AI to input the analysis results as prompts and generate appropriate questions. For example, it can generate technical questions and behavioral questions based on the applicant's background and skills. As a result, the question generation unit can quickly and accurately generate questions that meet the company's needs, improving the quality of interviews.

[0032] The interview department conducts online interviews using questions generated by the question generation department. The interview department conducts interviews with applicants using online platforms, for example. The interview department can also conduct knowledge tests, for example, by leveraging the vast knowledge of AI. For example, the interview department can ask questions about specific technologies or industry trends to objectively evaluate the applicant's knowledge level. Furthermore, the interview department can use AI to support the interview process. Specifically, the AI ​​monitors the interview and suggests follow-up questions at appropriate times. The AI ​​can also analyze the applicant's facial expressions and tone of voice to detect emotions such as tension and anxiety. This allows the interviewer to understand the applicant's psychological state and conduct a more effective interview. In addition, the interview department can utilize the interview recording function to review the interview content later. This ensures transparency and fairness in the interview and allows for more accurate evaluation.

[0033] The summarization unit summarizes the interview results obtained by the interview unit. For example, based on the information obtained from the interview, the summarization unit generates feedback materials that summarize the applicant's strengths and weaknesses, and points to ask in the first interview. Specifically, it can summarize the interview results using text analysis technology and extract important information. For example, it can use natural language processing technology to convert the interview audio data into text and extract important statements and answers. The summarization unit can also use AI to summarize the interview results and generate feedback materials. Specifically, it can use a generation AI to input the interview results as prompts and generate a summary. For example, it can analyze the applicant's strengths and weaknesses and suggest specific areas for improvement. Furthermore, based on the interview results, the summarization unit can suggest points to ask and evaluate in the next interview. This allows interviewers to ask effective questions in the next interview and evaluate the applicant's suitability more accurately. Through these functions, the summarization unit improves the efficiency and accuracy of interviews and supports companies' recruitment activities.

[0034] The analysis unit can analyze the applicant's background, skills, and motivations. For example, the analysis unit can analyze the applicant's background in detail. For example, it can analyze the applicant's work history and educational background to extract the applicant's strengths and weaknesses. The analysis unit can also analyze the applicant's skills. For example, it can analyze the applicant's technical skills and soft skills to understand the applicant's skill set. The analysis unit can also analyze the applicant's motivations. For example, it can analyze the applicant's motivations using text analysis technology to uncover the applicant's true feelings. By analyzing the applicant's background, skills, and motivations in detail, it is possible to generate appropriate questions. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's background, skills, and motivations into AI and have the AI ​​output the analysis results.

[0035] The question generation unit can refer to company-specific information and past recruitment information to ask questions that it wants to confirm during the interview. For example, the question generation unit can refer to company-specific information. For example, it can refer to the company's vision, mission, current projects, etc., to generate questions for applicants. The question generation unit can also refer to past recruitment information. For example, it can refer to past interview questions and recruitment criteria to generate questions that meet the company's needs. In this way, by referring to company-specific information and past recruitment information, it is possible to ask questions that meet the company's needs. Some or all of the above processing in the question generation unit may be performed using AI, for example, or not using AI. For example, the question generation unit can input company-specific information and past recruitment information into AI and have the AI ​​generate questions.

[0036] The interview department can conduct interviews with applicants using an online platform. For example, the interview department can conduct interviews with applicants using an online platform. This allows interviews to be conducted regardless of location. Some or all of the above processes in the interview department may be performed using AI, or not. For example, the interview department can input the online platform into an AI and have the AI ​​conduct the online interview.

[0037] The interview department can leverage the vast knowledge of AI to conduct knowledge tests. For example, the interview department can ask questions about specific technologies or industry trends. For example, the interview department can generate questions to evaluate the applicant's expertise and skills, and objectively assess the applicant's knowledge level. In this way, by utilizing the vast knowledge of AI, the applicant's knowledge level can be objectively evaluated. Some or all of the above processes in the interview department may be performed using AI, or not. For example, the interview department can input knowledge tests into AI and have the AI ​​perform the knowledge evaluation.

[0038] The summarization unit can generate feedback materials based on information obtained from interviews, summarizing the applicant's strengths and weaknesses, and identifying points to ask in the first interview. For example, the summarization unit can summarize interview results using text analysis technology and extract important information. For instance, it can analyze the applicant's strengths and weaknesses and suggest specific areas for improvement. Furthermore, the summarization unit can use AI to summarize interview results and generate feedback materials. For example, it can analyze the applicant's strengths and weaknesses in detail based on the interview results and provide advice for the next interview. This streamlines preparation for the next interview by summarizing information obtained from the interview and generating feedback materials. Some or all of the above processing in the summarization unit may be performed using AI, or not. For example, the summarization unit can input interview results into AI and have the AI ​​output a summary.

[0039] The analysis unit can analyze an applicant's past work history in detail and extract their role and achievements in specific projects. For example, the analysis unit can analyze the detailed role an applicant has played in projects they have been involved in in the past. For example, the analysis unit can analyze the specific role and contribution an applicant played in a project. The analysis unit can also extract the specific results an applicant has achieved. For example, the analysis unit can analyze the results and deliverables an applicant has achieved in a project and evaluate their performance. The analysis unit can also analyze the technologies and tools an applicant has used to understand their skill set. For example, the analysis unit can analyze the technologies and tools an applicant has used in a project and evaluate their technical skills. This allows for a detailed analysis of an applicant's past work history to understand their specific role and achievements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input the applicant's work history data into an AI and have the AI ​​output the analysis results.

[0040] The analysis unit can analyze the applicant's social media activity to supplementally understand their motivations and interests. For example, the analysis unit can analyze the applicant's interests from their social media posts. For example, the analysis unit can analyze the content of the applicant's posts to understand their interests. The analysis unit can also analyze the applicant's followers and the accounts they follow to understand their network. For example, the analysis unit can analyze the attributes of the accounts the applicant follows and their followers to evaluate the applicant's network. The analysis unit can also analyze the frequency of the applicant's social media activity to evaluate their communication skills. For example, the analysis unit can analyze the frequency of the applicant's posts and the content of their comments to evaluate their communication skills. In this way, by analyzing the applicant's social media activity, their motivations and interests can be supplementally understood. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's social media data into AI and have the AI ​​output the analysis results.

[0041] The analysis unit can analyze the applicant's geographical location information and consider region-specific skills and experience. For example, the analysis unit can analyze region-specific skills based on the applicant's place of residence. For example, the analysis unit can analyze skills and experience related to the applicant's place of residence and evaluate the applicant's region-specific skills. The analysis unit can also analyze the characteristics of regions where the applicant has previously worked and evaluate their experience. For example, the analysis unit can analyze the characteristics of regions where the applicant has previously worked and evaluate the applicant's experience. The analysis unit can also evaluate region-specific industry knowledge based on the applicant's geographical location information. For example, the analysis unit can evaluate region-specific industry knowledge based on the applicant's geographical location information. In this way, by analyzing the applicant's geographical location information, region-specific skills and experience can be considered. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's geographical location information into AI and have the AI ​​output the analysis results.

[0042] The analysis unit can analyze applicants' online portfolios and blogs to evaluate additional skills and knowledge. For example, the analysis unit can analyze specific projects from applicants' online portfolios. For example, the analysis unit can analyze the details of projects posted by applicants in their online portfolios to evaluate their skills and knowledge. The analysis unit can also evaluate expertise from applicants' blog posts. For example, the analysis unit can analyze the content of applicants' blog posts to evaluate their expertise. The analysis unit can also analyze applicants' online activities to identify additional skill sets. For example, the analysis unit can analyze applicants' online activities to evaluate their skill sets. This allows for the evaluation of additional skills and knowledge by analyzing applicants' online portfolios and blogs. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input applicants' online portfolio and blog data into an AI and have the AI ​​output the analysis results.

[0043] The question generation unit can generate more in-depth questions by referring to the applicant's past answer history when generating questions. For example, the question generation unit can generate related in-depth questions based on the content of the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers and generate related questions. The question generation unit can also generate questions that delve into unresolved points from the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers, identify unresolved points, and generate questions based on them. The question generation unit can also analyze the applicant's past answer history and generate questions that point out inconsistencies. For example, the question generation unit can analyze the applicant's past answers, identify inconsistencies, and generate questions based on them. In this way, more in-depth questions can be generated by referring to the applicant's past answer history. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without using AI. For example, the question generation unit can input the applicant's past answer history into the AI ​​and generate questions from the AI.

[0044] The question generation unit can generate questions related to a company's current projects and challenges during the question generation process. For example, the question generation unit can generate specific questions related to a company's current projects. For example, the question generation unit can generate questions related to a company's ongoing projects to evaluate the suitability of applicants. The question generation unit can also generate questions asking for solutions to challenges facing a company. For example, the question generation unit can generate questions asking for solutions to challenges facing a company to evaluate the problem-solving abilities of applicants. The question generation unit can also generate questions related to a company's future plans to solicit applicants' opinions. For example, the question generation unit can generate questions related to a company's future plans to solicit applicants' opinions and suggestions. In this way, by generating questions related to a company's current projects and challenges, questions that meet the company's needs can be asked. Some or all of the above processing in the question generation unit may be performed using AI, for example, or not using AI. For example, the question generation unit can input information about a company's current projects and challenges into an AI and have the AI ​​generate questions.

[0045] The question generation unit can generate specialized questions based on the applicant's industry experience during question generation. For example, the question generation unit can generate questions that ask about specific expertise based on the applicant's industry experience. For example, the question generation unit can generate questions related to projects the applicant has been involved in in the past, thereby evaluating the applicant's expertise. The question generation unit can also generate questions about the latest trends based on the applicant's industry experience. For example, the question generation unit can generate questions about the latest industry trends based on the applicant's industry experience, thereby evaluating the applicant's knowledge. In this way, the applicant's expertise can be evaluated by generating specialized questions based on the applicant's industry experience. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the applicant's industry experience data into AI and have the AI ​​generate questions.

[0046] The question generation unit can generate questions related to the applicant's hobbies and interests, thereby helping them relax. For example, the question generation unit can generate questions related to the applicant's hobbies, helping them relax. The question generation unit can also generate relevant questions based on the applicant's interests. For example, the question generation unit can generate relevant questions based on the applicant's interests, helping them relax. The question generation unit can also generate relaxing questions based on the applicant's hobbies and interests. For example, the question generation unit can generate relaxing questions based on the applicant's hobbies and interests, helping the applicant relax. In this way, by generating questions related to the applicant's hobbies and interests, the applicant can relax. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the applicant's hobby and interest data into AI and have the AI ​​generate questions.

[0047] The interview department can analyze the applicant's nonverbal behavior during the interview to assess their level of nervousness and confidence. For example, the interview department can analyze the applicant's facial expressions to assess their level of nervousness. For example, the interview department can analyze changes in the applicant's facial expressions to assess their level of nervousness. The interview department can also analyze the applicant's posture to assess their level of confidence. For example, the interview department can analyze changes in the applicant's posture to assess their level of confidence. The interview department can also analyze the applicant's tone of voice to assess changes in their emotions. For example, the interview department can analyze changes in the applicant's tone of voice to assess changes in their emotions. In this way, by analyzing the applicant's nonverbal behavior, the interview department can assess their level of nervousness and confidence. Some or all of the above processing in the interview department may be performed using AI, for example, or not. For example, the interview department can input the applicant's nonverbal behavior data into AI and have the AI ​​output the analysis results.

[0048] The interview department can analyze the applicant's answers in real time during the interview and immediately generate follow-up questions. For example, the interview department can analyze the applicant's answers and generate relevant follow-up questions. The interview department can also generate follow-up questions that point out inconsistencies in the applicant's answers. For example, the interview department can analyze the applicant's answers, identify inconsistencies, and generate follow-up questions based on those inconsistencies. The interview department can also generate follow-up questions that delve deeper into the applicant's answers. For example, the interview department can analyze the applicant's answers and generate questions that delve deeper into the applicant's answers. This allows for the immediate generation of follow-up questions by analyzing the applicant's answers in real time. Some or all of the above processing in the interview department may be performed using AI, or not. For example, the interview department can input the applicant's answers into AI and have the AI ​​generate follow-up questions.

[0049] The interview department can refer to the applicant's past interview history during the interview to ask questions that do not overlap. For example, the interview department can analyze the applicant's past interview history and generate questions that do not overlap. The interview department can also generate new questions based on the applicant's past answers. For example, the interview department can analyze the applicant's past answers and generate new questions. The interview department can also refer to the applicant's past interview history and generate questions that delve into unresolved points. For example, the interview department can analyze the applicant's past interview history, identify unresolved points, and generate questions based on them. This allows the interview department to ask questions that do not overlap by referring to the applicant's past interview history. Some or all of the above processes in the interview department may be performed using AI, for example, or not. For example, the interview department can input the applicant's past interview history into AI and have the AI ​​generate questions.

[0050] The interview department can generate appropriate questions during interviews, taking into account the applicant's cultural background. For example, the interview department can analyze the applicant's cultural background and generate appropriate questions. The interview department can also generate relevant questions based on the applicant's cultural background. The interview department can also generate questions that help the applicant relax, taking their cultural background into consideration. This allows the interview department to generate appropriate questions by considering the applicant's cultural background. Some or all of the above processes in the interview department may be performed using AI, for example, or without AI. For example, the interview department can input the applicant's cultural background data into AI and have the AI ​​generate questions.

[0051] The summarization unit can evaluate the consistency of the applicant's answers and point out inconsistencies during the summarization process. For example, the summarization unit can analyze the content of the applicant's answers and evaluate their consistency. The summarization unit can also point out inconsistencies in the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify inconsistencies, and point them out. The summarization unit can also point out unresolved points based on the content of the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify unresolved points, and point them out. This allows the summarization unit to point out inconsistencies by evaluating the consistency of the applicant's answers. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0052] The summarization unit can analyze the applicant's strengths and weaknesses in detail during the summarization process and propose specific areas for improvement. For example, the summarization unit can analyze the applicant's answers to determine their strengths and weaknesses. The summarization unit can also highlight the applicant's strengths and propose specific areas for improvement. The summarization unit can also point out the applicant's weaknesses and provide specific advice for improvement. By analyzing the applicant's strengths and weaknesses in detail, the summarization unit can propose specific areas for improvement. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0053] The summarization unit can compare the applicant's responses with those of other applicants and perform a relative evaluation during the summarization process. For example, the summarization unit can compare the applicant's responses with those of other applicants and perform a relative evaluation. The summarization unit can also evaluate the applicant's strengths and weaknesses in comparison to those of other applicants. Furthermore, the summarization unit can clarify the differences between an applicant and other applicants based on their responses. For example, the summarization unit can analyze the applicant's responses and clarify the differences between them. This allows for a relative evaluation by comparing the applicant's responses with those of other applicants. Some or all of the above processing in the summarization unit may be performed using AI, or without AI. For example, the summarization unit can input the applicant's response data into AI and output the analysis results from the AI.

[0054] The summarization unit can evaluate the applicant's responses by comparing them to the skill set required by the company during the summarization process. For example, the summarization unit can evaluate the applicant's responses by comparing them to the skill set required by the company. For example, the summarization unit can evaluate the applicant's responses by comparing them to the skill set required by the company. The summarization unit can also evaluate the applicant's skill set based on the company's needs. For example, the summarization unit can evaluate the applicant's skill set based on the company's needs. The summarization unit can also evaluate the degree of agreement between the applicant's responses and the skill set required by the company. For example, the summarization unit can analyze the applicant's responses and evaluate the degree of agreement between them and the skill set required by the company. This allows for a more appropriate evaluation by comparing the applicant's responses with the skill set required by the company. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's response data into AI and have the AI ​​output the analysis results.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The analysis unit can analyze the applicant's social media activity to supplementally understand their motivations and interests. For example, the analysis unit can analyze the applicant's interests from their social media posts. For example, the analysis unit can analyze the content of the applicant's posts to understand their interests. The analysis unit can also analyze the applicant's followers and the accounts they follow to understand their network. For example, the analysis unit can analyze the attributes of the accounts the applicant follows and their followers to evaluate the applicant's network. The analysis unit can also analyze the frequency of the applicant's social media activity to evaluate their communication skills. For example, the analysis unit can analyze the frequency of the applicant's posts and the content of their comments to evaluate their communication skills. In this way, by analyzing the applicant's social media activity, their motivations and interests can be supplementally understood. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's social media data into AI and have the AI ​​output the analysis results.

[0057] The question generation unit can generate more in-depth questions by referring to the applicant's past answer history when generating questions. For example, the question generation unit can generate related in-depth questions based on the content of the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers and generate related questions. The question generation unit can also generate questions that delve into unresolved points from the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers, identify unresolved points, and generate questions based on them. The question generation unit can also analyze the applicant's past answer history and generate questions that point out inconsistencies. For example, the question generation unit can analyze the applicant's past answers, identify inconsistencies, and generate questions based on them. In this way, more in-depth questions can be generated by referring to the applicant's past answer history. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without using AI. For example, the question generation unit can input the applicant's past answer history into the AI ​​and generate questions from the AI.

[0058] The interview department can analyze the applicant's nonverbal behavior during the interview to assess their level of nervousness and confidence. For example, the interview department can analyze the applicant's facial expressions to assess their level of nervousness. For example, the interview department can analyze changes in the applicant's facial expressions to assess their level of nervousness. The interview department can also analyze the applicant's posture to assess their level of confidence. For example, the interview department can analyze changes in the applicant's posture to assess their level of confidence. The interview department can also analyze the applicant's tone of voice to assess changes in their emotions. For example, the interview department can analyze changes in the applicant's tone of voice to assess changes in their emotions. In this way, by analyzing the applicant's nonverbal behavior, the interview department can assess their level of nervousness and confidence. Some or all of the above processing in the interview department may be performed using AI, for example, or not. For example, the interview department can input the applicant's nonverbal behavior data into AI and have the AI ​​output the analysis results.

[0059] The summarization unit can evaluate the consistency of the applicant's answers and point out inconsistencies during the summarization process. For example, the summarization unit can analyze the content of the applicant's answers and evaluate their consistency. The summarization unit can also point out inconsistencies in the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify inconsistencies, and point them out. The summarization unit can also point out unresolved points based on the content of the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify unresolved points, and point them out. This allows the summarization unit to point out inconsistencies by evaluating the consistency of the applicant's answers. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0060] The question generation unit can generate questions related to a company's current projects and challenges during the question generation process. For example, the question generation unit can generate specific questions related to a company's current projects. For example, the question generation unit can generate questions related to a company's ongoing projects to evaluate the suitability of applicants. The question generation unit can also generate questions asking for solutions to challenges facing a company. For example, the question generation unit can generate questions asking for solutions to challenges facing a company to evaluate the problem-solving abilities of applicants. The question generation unit can also generate questions related to a company's future plans to solicit applicants' opinions. For example, the question generation unit can generate questions related to a company's future plans to solicit applicants' opinions and suggestions. In this way, by generating questions related to a company's current projects and challenges, questions that meet the company's needs can be asked. Some or all of the above processing in the question generation unit may be performed using AI, for example, or not using AI. For example, the question generation unit can input information about a company's current projects and challenges into an AI and have the AI ​​generate questions.

[0061] The summarization unit can analyze the applicant's strengths and weaknesses in detail during the summarization process and propose specific areas for improvement. For example, the summarization unit can analyze the applicant's answers to determine their strengths and weaknesses. The summarization unit can also highlight the applicant's strengths and propose specific areas for improvement. The summarization unit can also point out the applicant's weaknesses and provide specific advice for improvement. By analyzing the applicant's strengths and weaknesses in detail, the summarization unit can propose specific areas for improvement. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The analysis department analyzes the information in the application form. The analysis department analyzes the applicant's background, skills, and motivations, and uses text analysis and data mining techniques to extract the applicant's strengths and weaknesses. For example, it can analyze the detailed roles of projects the applicant has been involved in in the past and extract specific achievements. Step 2: The question generation unit generates questions based on the information analyzed by the analysis unit. The question generation unit refers to company-specific information and past recruitment information, and generates questions based on the company's vision and mission. It can also generate questions based on the skill sets the company requires and past recruitment criteria. Step 3: The interview team conducts online interviews using questions generated by the question generation team. Furthermore, leveraging the vast knowledge of the AI, knowledge tests can be conducted to objectively evaluate the applicant's knowledge level. Step 4: The summarization unit summarizes the interview results obtained by the interview unit. Based on the information obtained from the interview, the summarization unit generates feedback materials that summarize the applicant's strengths and weaknesses, and points to ask in the first interview. Text analysis technology and AI can be used to summarize the interview results and extract important information.

[0064] (Example of form 2) The recruitment support system according to an embodiment of the present invention is a system that aims to reduce recruitment costs and prevent mismatches by introducing an AI interviewer using a generation AI and a voice generation AI as a preliminary interview in the recruitment process. This recruitment support system analyzes the application form and generates appropriate questions for the applicant. Next, the recruitment support system conducts an interview with the applicant using an online platform. At this time, the recruitment support system uses RAG to refer to company-specific information and past recruitment information and asks questions that it wants to confirm during the interview. The recruitment support system also conducts a knowledge test utilizing the vast knowledge of the AI. Since the applicant will think of and answer questions on the spot during the interview, it is possible to elicit their true feelings, which may differ from those expressed in the application form. Finally, the recruitment support system summarizes the interview results and provides the HR department with feedback materials that summarize points to ask in the first interview. This makes it possible to get to know the applicant in a short time and to streamline preparation for the next interview. By using generation AI, it becomes possible to analyze the applicant more logically and provide feedback. For example, the recruitment support system analyzes the applicant's career history, skills, and motivation in detail and extracts points that should be confirmed in the interview. For example, the system analyzes the applicant's role in specific projects and their skills. This allows it to generate appropriate questions for the applicant. Next, the recruitment support system conducts interviews with applicants using an online platform. During this process, the system uses RAG to refer to company-specific information and past recruitment data, asking questions to confirm key points. For example, it generates questions based on the skill sets the company requires and past recruitment criteria. This ensures that questions are tailored to the company's needs. Furthermore, the recruitment support system conducts knowledge tests. Leveraging the vast knowledge of AI, it generates questions to evaluate the applicant's expertise and skills. For example, it asks questions about specific technologies and industry trends. This allows for an objective assessment of the applicant's knowledge level. The interview results are summarized by the recruitment support system. Based on the information obtained from the interview, the system generates feedback materials summarizing the applicant's strengths and weaknesses, and points that should be asked in the first interview.This allows HR personnel to quickly understand candidates and streamline preparation for subsequent interviews. This system helps reduce recruitment costs and prevent mismatches. By having the recruitment support system conduct a preliminary interview, the effort of reviewing application forms and conducting multiple interviews is eliminated. Furthermore, because the recruitment support system evaluates objectively without being influenced by emotions, it also contributes to preventing mismatches. For example, even if a candidate is nervous, the recruitment support system can calmly ask questions and elicit the candidate's true feelings. This allows companies to efficiently recruit top talent. In short, the recruitment support system helps reduce recruitment costs and prevent mismatches.

[0065] The recruitment support system according to this embodiment comprises an analysis unit, a question generation unit, an interview unit, and a summarization unit. The analysis unit analyzes the information in the application form. For example, the analysis unit analyzes the applicant's career history, skills, and motivation for applying. For example, the analysis unit can use text analysis technology to analyze the content of the application form and extract the applicant's strengths and weaknesses. The analysis unit can also use data mining technology to analyze the applicant's past work history and skill set in detail. For example, the analysis unit can analyze the detailed roles in projects the applicant has been involved in in the past and extract specific results. The question generation unit generates questions based on the information analyzed by the analysis unit. For example, the question generation unit refers to company-specific information and past recruitment information and asks questions about points it wants to confirm in the interview. For example, the question generation unit can generate questions for applicants based on the company's vision and mission. The question generation unit can also refer to past recruitment criteria and interview questions and generate questions that meet the company's needs. For example, the question generation unit generates questions based on the skill set required by the company and past recruitment criteria. The interview unit conducts online interviews using questions generated by the question generation unit. The interview unit conducts interviews with applicants using, for example, an online platform. The interview unit can also conduct knowledge tests by leveraging the vast knowledge of AI. For example, the interview unit can ask questions about specific technologies or industry trends to objectively evaluate the applicant's knowledge level. The summarization unit summarizes the interview results obtained by the interview unit. For example, the summarization unit generates feedback materials based on the information obtained from the interview, summarizing the applicant's strengths and weaknesses and points to ask in the first interview. The summarization unit can summarize the interview results using, for example, text analysis technology and extract important information. The summarization unit can also summarize the interview results using AI and generate feedback materials. For example, based on the interview results, the summarization unit can analyze the applicant's strengths and weaknesses and propose specific areas for improvement. As a result, the recruitment support system according to this embodiment can reduce recruitment costs and prevent mismatches.Some or all of the above-described processes in the analysis unit, question generation unit, interview unit, and summarization unit may be performed using AI, for example, or without AI. For example, the analysis unit can input information from the application form into the AI ​​and have the AI ​​output the analysis results. The question generation unit can input the analysis results into the AI ​​and have the AI ​​generate questions. The interview unit can input the generated questions into the AI ​​and have the AI ​​conduct an online interview. The summarization unit can input the interview results into the AI ​​and have the AI ​​output a summary.

[0066] The analysis department analyzes the information in application forms. For example, it analyzes the applicant's background, skills, and motivation for applying. The analysis department can use text analysis technology to analyze the content of application forms and extract the applicant's strengths and weaknesses. Specifically, it uses natural language processing (NLP) technology to analyze the text data of application forms, extracting keywords and understanding the context. For example, it can analyze in detail the project experience and skill set described by the applicant and identify experience using specific technologies and tools. The analysis department can also use data mining technology to analyze in detail the applicant's past work history and skill set. For example, it can analyze the detailed role in projects the applicant has been involved in in the past and extract specific results. This makes it possible to objectively evaluate the applicant's achievements and abilities. Furthermore, the analysis department can use machine learning algorithms to cluster the applicant's data and identify similar applicant groups. This allows companies to quickly find the best candidates for specific positions. The analysis department utilizes these technologies to comprehensively analyze information from application forms and support companies' recruitment activities.

[0067] The question generation unit generates questions based on information analyzed by the analysis unit. For example, the question generation unit can refer to company-specific information and past recruitment information to ask questions that it wants to confirm during the interview. Specifically, it can generate questions for applicants based on the company's vision and mission. For example, it can generate questions related to the values ​​and culture that the company emphasizes to evaluate the applicant's suitability. The question generation unit can also refer to past recruitment criteria and interview questions to generate questions that meet the company's needs. For example, it can generate questions based on the skill set the company requires and past recruitment criteria. Furthermore, the question generation unit can generate questions using AI. Specifically, it can use a generation AI to input the analysis results as prompts and generate appropriate questions. For example, it can generate technical questions and behavioral questions based on the applicant's background and skills. As a result, the question generation unit can quickly and accurately generate questions that meet the company's needs, improving the quality of interviews.

[0068] The interview department conducts online interviews using questions generated by the question generation department. The interview department conducts interviews with applicants using online platforms, for example. The interview department can also conduct knowledge tests, for example, by leveraging the vast knowledge of AI. For example, the interview department can ask questions about specific technologies or industry trends to objectively evaluate the applicant's knowledge level. Furthermore, the interview department can use AI to support the interview process. Specifically, the AI ​​monitors the interview and suggests follow-up questions at appropriate times. The AI ​​can also analyze the applicant's facial expressions and tone of voice to detect emotions such as tension and anxiety. This allows the interviewer to understand the applicant's psychological state and conduct a more effective interview. In addition, the interview department can utilize the interview recording function to review the interview content later. This ensures transparency and fairness in the interview and allows for more accurate evaluation.

[0069] The summarization unit summarizes the interview results obtained by the interview unit. For example, based on the information obtained from the interview, the summarization unit generates feedback materials that summarize the applicant's strengths and weaknesses, and points to ask in the first interview. Specifically, it can summarize the interview results using text analysis technology and extract important information. For example, it can use natural language processing technology to convert the interview audio data into text and extract important statements and answers. The summarization unit can also use AI to summarize the interview results and generate feedback materials. Specifically, it can use a generation AI to input the interview results as prompts and generate a summary. For example, it can analyze the applicant's strengths and weaknesses and suggest specific areas for improvement. Furthermore, based on the interview results, the summarization unit can suggest points to ask and evaluate in the next interview. This allows interviewers to ask effective questions in the next interview and evaluate the applicant's suitability more accurately. Through these functions, the summarization unit improves the efficiency and accuracy of interviews and supports companies' recruitment activities.

[0070] The analysis unit can analyze the applicant's background, skills, and motivations. For example, the analysis unit can analyze the applicant's background in detail. For example, it can analyze the applicant's work history and educational background to extract the applicant's strengths and weaknesses. The analysis unit can also analyze the applicant's skills. For example, it can analyze the applicant's technical skills and soft skills to understand the applicant's skill set. The analysis unit can also analyze the applicant's motivations. For example, it can analyze the applicant's motivations using text analysis technology to uncover the applicant's true feelings. By analyzing the applicant's background, skills, and motivations in detail, it is possible to generate appropriate questions. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's background, skills, and motivations into AI and have the AI ​​output the analysis results.

[0071] The question generation unit can refer to company-specific information and past recruitment information to ask questions that it wants to confirm during the interview. For example, the question generation unit can refer to company-specific information. For example, it can refer to the company's vision, mission, current projects, etc., to generate questions for applicants. The question generation unit can also refer to past recruitment information. For example, it can refer to past interview questions and recruitment criteria to generate questions that meet the company's needs. In this way, by referring to company-specific information and past recruitment information, it is possible to ask questions that meet the company's needs. Some or all of the above processing in the question generation unit may be performed using AI, for example, or not using AI. For example, the question generation unit can input company-specific information and past recruitment information into AI and have the AI ​​generate questions.

[0072] The interview department can conduct interviews with applicants using an online platform. For example, the interview department can conduct interviews with applicants using an online platform. This allows interviews to be conducted regardless of location. Some or all of the above processes in the interview department may be performed using AI, or not. For example, the interview department can input the online platform into an AI and have the AI ​​conduct the online interview.

[0073] The interview department can leverage the vast knowledge of AI to conduct knowledge tests. For example, the interview department can ask questions about specific technologies or industry trends. For example, the interview department can generate questions to evaluate the applicant's expertise and skills, and objectively assess the applicant's knowledge level. In this way, by utilizing the vast knowledge of AI, the applicant's knowledge level can be objectively evaluated. Some or all of the above processes in the interview department may be performed using AI, or not. For example, the interview department can input knowledge tests into AI and have the AI ​​perform the knowledge evaluation.

[0074] The summarization unit can generate feedback materials based on information obtained from interviews, summarizing the applicant's strengths and weaknesses, and identifying points to ask in the first interview. For example, the summarization unit can summarize interview results using text analysis technology and extract important information. For instance, it can analyze the applicant's strengths and weaknesses and suggest specific areas for improvement. Furthermore, the summarization unit can use AI to summarize interview results and generate feedback materials. For example, it can analyze the applicant's strengths and weaknesses in detail based on the interview results and provide advice for the next interview. This streamlines preparation for the next interview by summarizing information obtained from the interview and generating feedback materials. Some or all of the above processing in the summarization unit may be performed using AI, or not. For example, the summarization unit can input interview results into AI and have the AI ​​output a summary.

[0075] The analysis unit can estimate the applicant's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the applicant is nervous, the analysis unit can increase the accuracy of the analysis to extract more detailed information. For example, the analysis unit can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness. Also, if the applicant is relaxed, the analysis unit can adjust the accuracy of the analysis to grasp the overall trend. For example, the analysis unit can analyze the applicant's posture and gestures to assess the degree of relaxation. Furthermore, if the applicant is anxious, the analysis unit can adjust the accuracy of the analysis to produce results quickly. For example, the analysis unit can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety. This allows for the extraction of more accurate information by adjusting the accuracy of the analysis based on the applicant's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's emotional data into the AI ​​and have the AI ​​perform emotional estimation.

[0076] The analysis unit can analyze an applicant's past work history in detail and extract their role and achievements in specific projects. For example, the analysis unit can analyze the detailed role an applicant has played in projects they have been involved in in the past. For example, the analysis unit can analyze the specific role and contribution an applicant played in a project. The analysis unit can also extract the specific results an applicant has achieved. For example, the analysis unit can analyze the results and deliverables an applicant has achieved in a project and evaluate their performance. The analysis unit can also analyze the technologies and tools an applicant has used to understand their skill set. For example, the analysis unit can analyze the technologies and tools an applicant has used in a project and evaluate their technical skills. This allows for a detailed analysis of an applicant's past work history to understand their specific role and achievements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input the applicant's work history data into an AI and have the AI ​​output the analysis results.

[0077] The analysis unit can analyze the applicant's social media activity to supplementally understand their motivations and interests. For example, the analysis unit can analyze the applicant's interests from their social media posts. For example, the analysis unit can analyze the content of the applicant's posts to understand their interests. The analysis unit can also analyze the applicant's followers and the accounts they follow to understand their network. For example, the analysis unit can analyze the attributes of the accounts the applicant follows and their followers to evaluate the applicant's network. The analysis unit can also analyze the frequency of the applicant's social media activity to evaluate their communication skills. For example, the analysis unit can analyze the frequency of the applicant's posts and the content of their comments to evaluate their communication skills. In this way, by analyzing the applicant's social media activity, their motivations and interests can be supplementally understood. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's social media data into AI and have the AI ​​output the analysis results.

[0078] The analysis unit can estimate the applicant's emotions and prioritize the analysis results based on the estimated emotions. For example, if the applicant is nervous, the analysis unit will prioritize analyzing important information. For instance, it can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness. If the applicant is relaxed, the analysis unit can also analyze overall information in a balanced way. For example, it can analyze the applicant's posture and gestures to assess the degree of relaxation. Furthermore, if the applicant is anxious, the analysis unit can prioritize important information to produce results quickly. For example, it can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety. This allows for prioritizing the analysis results based on the applicant's emotions, thereby prioritizing the analysis of important information. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's emotional data into the AI ​​and have the AI ​​perform emotional estimation.

[0079] The analysis unit can analyze the applicant's geographical location information and consider region-specific skills and experience. For example, the analysis unit can analyze region-specific skills based on the applicant's place of residence. For example, the analysis unit can analyze skills and experience related to the applicant's place of residence and evaluate the applicant's region-specific skills. The analysis unit can also analyze the characteristics of regions where the applicant has previously worked and evaluate their experience. For example, the analysis unit can analyze the characteristics of regions where the applicant has previously worked and evaluate the applicant's experience. The analysis unit can also evaluate region-specific industry knowledge based on the applicant's geographical location information. For example, the analysis unit can evaluate region-specific industry knowledge based on the applicant's geographical location information. In this way, by analyzing the applicant's geographical location information, region-specific skills and experience can be considered. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's geographical location information into AI and have the AI ​​output the analysis results.

[0080] The analysis unit can analyze applicants' online portfolios and blogs to evaluate additional skills and knowledge. For example, the analysis unit can analyze specific projects from applicants' online portfolios. For example, the analysis unit can analyze the details of projects posted by applicants in their online portfolios to evaluate their skills and knowledge. The analysis unit can also evaluate expertise from applicants' blog posts. For example, the analysis unit can analyze the content of applicants' blog posts to evaluate their expertise. The analysis unit can also analyze applicants' online activities to identify additional skill sets. For example, the analysis unit can analyze applicants' online activities to evaluate their skill sets. This allows for the evaluation of additional skills and knowledge by analyzing applicants' online portfolios and blogs. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input applicants' online portfolio and blog data into an AI and have the AI ​​output the analysis results.

[0081] The question generation unit can estimate the applicant's emotions and adjust the difficulty of the questions based on the estimated emotions. For example, if the applicant is nervous, the question generation unit can start with easy questions and gradually increase the difficulty. For example, the question generation unit can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness. Also, if the applicant is relaxed, the question generation unit can proactively ask more difficult questions. For example, the question generation unit can analyze the applicant's posture and gestures to assess the degree of relaxation. Furthermore, if the applicant is anxious, the question generation unit can adjust the difficulty to ask questions that can be answered quickly. For example, the question generation unit can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety. In this way, by adjusting the difficulty of questions based on the applicant's emotions, more appropriate questions can be asked. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the applicant's emotional data into the AI ​​and have the AI ​​perform emotional estimation.

[0082] The question generation unit can generate more in-depth questions by referring to the applicant's past answer history when generating questions. For example, the question generation unit can generate related in-depth questions based on the content of the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers and generate related questions. The question generation unit can also generate questions that delve into unresolved points from the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers, identify unresolved points, and generate questions based on them. The question generation unit can also analyze the applicant's past answer history and generate questions that point out inconsistencies. For example, the question generation unit can analyze the applicant's past answers, identify inconsistencies, and generate questions based on them. In this way, more in-depth questions can be generated by referring to the applicant's past answer history. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without using AI. For example, the question generation unit can input the applicant's past answer history into the AI ​​and generate questions from the AI.

[0083] The question generation unit can generate questions related to a company's current projects and challenges during the question generation process. For example, the question generation unit can generate specific questions related to a company's current projects. For example, the question generation unit can generate questions related to a company's ongoing projects to evaluate the suitability of applicants. The question generation unit can also generate questions asking for solutions to challenges facing a company. For example, the question generation unit can generate questions asking for solutions to challenges facing a company to evaluate the problem-solving abilities of applicants. The question generation unit can also generate questions related to a company's future plans to solicit applicants' opinions. For example, the question generation unit can generate questions related to a company's future plans to solicit applicants' opinions and suggestions. In this way, by generating questions related to a company's current projects and challenges, questions that meet the company's needs can be asked. Some or all of the above processing in the question generation unit may be performed using AI, for example, or not using AI. For example, the question generation unit can input information about a company's current projects and challenges into an AI and have the AI ​​generate questions.

[0084] The question generation unit can estimate the applicant's emotions and adjust the order of questions based on the estimated emotions. For example, if the applicant is nervous, the question generation unit can start with easy questions and gradually increase the difficulty. For example, the question generation unit can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness. Also, if the applicant is relaxed, the question generation unit can proactively ask more difficult questions. For example, the question generation unit can analyze the applicant's posture and gestures to assess the degree of relaxation. Furthermore, if the applicant is anxious, the question generation unit can prioritize questions that can be answered quickly. For example, the question generation unit can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety. This allows for more appropriate questions to be asked by adjusting the order of questions based on the applicant's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the applicant's emotional data into the AI ​​and have the AI ​​perform emotional estimation.

[0085] The question generation unit can generate specialized questions based on the applicant's industry experience during question generation. For example, the question generation unit can generate questions that ask about specific expertise based on the applicant's industry experience. For example, the question generation unit can generate questions related to projects the applicant has been involved in in the past, thereby evaluating the applicant's expertise. The question generation unit can also generate questions about the latest trends based on the applicant's industry experience. For example, the question generation unit can generate questions about the latest industry trends based on the applicant's industry experience, thereby evaluating the applicant's knowledge. In this way, the applicant's expertise can be evaluated by generating specialized questions based on the applicant's industry experience. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the applicant's industry experience data into AI and have the AI ​​generate questions.

[0086] The question generation unit can generate questions related to the applicant's hobbies and interests, thereby helping them relax. For example, the question generation unit can generate questions related to the applicant's hobbies, helping them relax. The question generation unit can also generate relevant questions based on the applicant's interests. For example, the question generation unit can generate relevant questions based on the applicant's interests, helping them relax. The question generation unit can also generate relaxing questions based on the applicant's hobbies and interests. For example, the question generation unit can generate relaxing questions based on the applicant's hobbies and interests, helping the applicant relax. In this way, by generating questions related to the applicant's hobbies and interests, the applicant can relax. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the applicant's hobby and interest data into AI and have the AI ​​generate questions.

[0087] The interviewer can estimate the applicant's emotions and adjust the pace of the interview based on those estimates. For example, if the applicant is nervous, the interviewer can proceed at a slower pace. For instance, the interviewer can analyze the applicant's facial expressions and tone of voice to assess their level of nervousness. Conversely, if the applicant is relaxed, the interviewer can proceed at a normal pace. For instance, the interviewer can analyze the applicant's posture and gestures to assess their level of relaxation. Furthermore, if the applicant is anxious, the interviewer can proceed quickly. For instance, the interviewer can analyze the applicant's heart rate and skin electrical activity to assess their level of anxiety. By adjusting the pace of the interview based on the applicant's emotions, a more appropriate interview can be conducted. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, 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 department may be performed using AI, for example, or without AI. For example, the interview department may input the applicant's emotional data into AI and have AI perform emotional estimation.

[0088] The interview department can analyze the applicant's nonverbal behavior during the interview to assess their level of nervousness and confidence. For example, the interview department can analyze the applicant's facial expressions to assess their level of nervousness. For example, the interview department can analyze changes in the applicant's facial expressions to assess their level of nervousness. The interview department can also analyze the applicant's posture to assess their level of confidence. For example, the interview department can analyze changes in the applicant's posture to assess their level of confidence. The interview department can also analyze the applicant's tone of voice to assess changes in their emotions. For example, the interview department can analyze changes in the applicant's tone of voice to assess changes in their emotions. In this way, by analyzing the applicant's nonverbal behavior, the interview department can assess their level of nervousness and confidence. Some or all of the above processing in the interview department may be performed using AI, for example, or not. For example, the interview department can input the applicant's nonverbal behavior data into AI and have the AI ​​output the analysis results.

[0089] The interview department can analyze the applicant's answers in real time during the interview and immediately generate follow-up questions. For example, the interview department can analyze the applicant's answers and generate relevant follow-up questions. The interview department can also generate follow-up questions that point out inconsistencies in the applicant's answers. For example, the interview department can analyze the applicant's answers, identify inconsistencies, and generate follow-up questions based on those inconsistencies. The interview department can also generate follow-up questions that delve deeper into the applicant's answers. For example, the interview department can analyze the applicant's answers and generate questions that delve deeper into the applicant's answers. This allows for the immediate generation of follow-up questions by analyzing the applicant's answers in real time. Some or all of the above processing in the interview department may be performed using AI, or not. For example, the interview department can input the applicant's answers into AI and have the AI ​​generate follow-up questions.

[0090] The interviewer can estimate the applicant's emotions and adjust the interview atmosphere based on those estimates. For example, if the applicant is nervous, the interviewer can create a relaxed atmosphere. For instance, the interviewer can analyze the applicant's facial expressions and tone of voice to assess their level of nervousness and create a relaxed atmosphere. Alternatively, if the applicant is relaxed, the interviewer can conduct the interview in a normal atmosphere. For example, the interviewer can analyze the applicant's posture and gestures to assess their level of relaxation and conduct the interview in a normal atmosphere. Furthermore, if the applicant is anxious, the interviewer can conduct the interview quickly. For example, the interviewer can analyze the applicant's heart rate and skin electrical activity to assess their level of anxiety and conduct the interview quickly. This allows for more appropriate interviews by adjusting the interview atmosphere based on the applicant's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, 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 department may be performed using AI, for example, or without AI. For example, the interview department may input the applicant's emotional data into AI and have AI perform emotional estimation.

[0091] The interview department can refer to the applicant's past interview history during the interview to ask questions that do not overlap. For example, the interview department can analyze the applicant's past interview history and generate questions that do not overlap. The interview department can also generate new questions based on the applicant's past answers. For example, the interview department can analyze the applicant's past answers and generate new questions. The interview department can also refer to the applicant's past interview history and generate questions that delve into unresolved points. For example, the interview department can analyze the applicant's past interview history, identify unresolved points, and generate questions based on them. This allows the interview department to ask questions that do not overlap by referring to the applicant's past interview history. Some or all of the above processes in the interview department may be performed using AI, for example, or not. For example, the interview department can input the applicant's past interview history into AI and have the AI ​​generate questions.

[0092] The interview department can generate appropriate questions during interviews, taking into account the applicant's cultural background. For example, the interview department can analyze the applicant's cultural background and generate appropriate questions. The interview department can also generate relevant questions based on the applicant's cultural background. The interview department can also generate questions that help the applicant relax, taking their cultural background into consideration. This allows the interview department to generate appropriate questions by considering the applicant's cultural background. Some or all of the above processes in the interview department may be performed using AI, for example, or without AI. For example, the interview department can input the applicant's cultural background data into AI and have the AI ​​generate questions.

[0093] The summarization unit can estimate the applicant's emotions and adjust the way the summary is expressed based on those emotions. For example, if the applicant is nervous, the summarization unit can produce a calm summary. For instance, it can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness and produce a calm summary. Furthermore, if the applicant is relaxed, the summarization unit can produce a detailed summary. For example, it can analyze the applicant's posture and gestures to assess the degree of relaxation and produce a detailed summary. Also, if the applicant is anxious, the summarization unit can produce a quick, concise summary. For example, it can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety and produce a quick, concise summary. This allows for a more appropriate summary by adjusting the expression based on the applicant's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the summarization section may be performed using AI, or not using AI. For example, the summarization section may input applicant sentiment data into an AI and have the AI ​​perform sentiment estimation.

[0094] The summarization unit can evaluate the consistency of the applicant's answers and point out inconsistencies during the summarization process. For example, the summarization unit can analyze the content of the applicant's answers and evaluate their consistency. The summarization unit can also point out inconsistencies in the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify inconsistencies, and point them out. The summarization unit can also point out unresolved points based on the content of the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify unresolved points, and point them out. This allows the summarization unit to point out inconsistencies by evaluating the consistency of the applicant's answers. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0095] The summarization unit can analyze the applicant's strengths and weaknesses in detail during the summarization process and propose specific areas for improvement. For example, the summarization unit can analyze the applicant's answers to determine their strengths and weaknesses. The summarization unit can also highlight the applicant's strengths and propose specific areas for improvement. The summarization unit can also point out the applicant's weaknesses and provide specific advice for improvement. By analyzing the applicant's strengths and weaknesses in detail, the summarization unit can propose specific areas for improvement. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0096] The summarization unit can estimate the applicant's emotions and determine the priority of the summary based on the estimated emotions. For example, if the applicant is nervous, the summarization unit will prioritize summarizing important information. For instance, it can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness and prioritize summarizing important information. Furthermore, if the applicant is relaxed, the summarization unit can summarize the overall information in a balanced way. For example, it can analyze the applicant's posture and gestures to assess the degree of relaxation and summarize the overall information in a balanced way. Also, if the applicant is anxious, the summarization unit can prioritize information to quickly produce results. For example, it can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety and prioritize information to quickly produce results. This allows for prioritizing the summary based on the applicant's emotions, thereby prioritizing the summarization of important information. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the summarization section may be performed using AI, or not using AI. For example, the summarization section may input applicant sentiment data into an AI and have the AI ​​perform sentiment estimation.

[0097] The summarization unit can compare the applicant's responses with those of other applicants and perform a relative evaluation during the summarization process. For example, the summarization unit can compare the applicant's responses with those of other applicants and perform a relative evaluation. The summarization unit can also evaluate the applicant's strengths and weaknesses in comparison to those of other applicants. Furthermore, the summarization unit can clarify the differences between an applicant and other applicants based on their responses. For example, the summarization unit can analyze the applicant's responses and clarify the differences between them. This allows for a relative evaluation by comparing the applicant's responses with those of other applicants. Some or all of the above processing in the summarization unit may be performed using AI, or without AI. For example, the summarization unit can input the applicant's response data into AI and output the analysis results from the AI.

[0098] The summarization unit can evaluate the applicant's responses by comparing them to the skill set required by the company during the summarization process. For example, the summarization unit can evaluate the applicant's responses by comparing them to the skill set required by the company. For example, the summarization unit can evaluate the applicant's responses by comparing them to the skill set required by the company. The summarization unit can also evaluate the applicant's skill set based on the company's needs. For example, the summarization unit can evaluate the applicant's skill set based on the company's needs. The summarization unit can also evaluate the degree of agreement between the applicant's responses and the skill set required by the company. For example, the summarization unit can analyze the applicant's responses and evaluate the degree of agreement between them and the skill set required by the company. This allows for a more appropriate evaluation by comparing the applicant's responses with the skill set required by the company. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's response data into AI and have the AI ​​output the analysis results.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The analysis unit can analyze the applicant's social media activity to supplementally understand their motivations and interests. For example, the analysis unit can analyze the applicant's interests from their social media posts. For example, the analysis unit can analyze the content of the applicant's posts to understand their interests. The analysis unit can also analyze the applicant's followers and the accounts they follow to understand their network. For example, the analysis unit can analyze the attributes of the accounts the applicant follows and their followers to evaluate the applicant's network. The analysis unit can also analyze the frequency of the applicant's social media activity to evaluate their communication skills. For example, the analysis unit can analyze the frequency of the applicant's posts and the content of their comments to evaluate their communication skills. In this way, by analyzing the applicant's social media activity, their motivations and interests can be supplementally understood. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the applicant's social media data into AI and have the AI ​​output the analysis results.

[0101] The question generation unit can estimate the applicant's emotions and adjust the difficulty of the questions based on the estimated emotions. For example, if the applicant is nervous, the question generation unit can start with easy questions and gradually increase the difficulty. For example, the question generation unit can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness. Also, if the applicant is relaxed, the question generation unit can proactively ask more difficult questions. For example, the question generation unit can analyze the applicant's posture and gestures to assess the degree of relaxation. Furthermore, if the applicant is anxious, the question generation unit can adjust the difficulty to ask questions that can be answered quickly. For example, the question generation unit can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety. In this way, by adjusting the difficulty of questions based on the applicant's emotions, more appropriate questions can be asked. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the applicant's emotional data into the AI ​​and have the AI ​​perform emotional estimation.

[0102] The interviewer can estimate the applicant's emotions and adjust the pace of the interview based on those estimates. For example, if the applicant is nervous, the interviewer can proceed at a slower pace. For instance, the interviewer can analyze the applicant's facial expressions and tone of voice to assess their level of nervousness. Conversely, if the applicant is relaxed, the interviewer can proceed at a normal pace. For instance, the interviewer can analyze the applicant's posture and gestures to assess their level of relaxation. Furthermore, if the applicant is anxious, the interviewer can proceed quickly. For instance, the interviewer can analyze the applicant's heart rate and skin electrical activity to assess their level of anxiety. By adjusting the pace of the interview based on the applicant's emotions, a more appropriate interview can be conducted. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, 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 department may be performed using AI, for example, or without AI. For example, the interview department may input the applicant's emotional data into AI and have AI perform emotional estimation.

[0103] The summarization unit can estimate the applicant's emotions and adjust the way the summary is expressed based on those emotions. For example, if the applicant is nervous, the summarization unit can produce a calm summary. For instance, it can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness and produce a calm summary. Furthermore, if the applicant is relaxed, the summarization unit can produce a detailed summary. For example, it can analyze the applicant's posture and gestures to assess the degree of relaxation and produce a detailed summary. Also, if the applicant is anxious, the summarization unit can produce a quick, concise summary. For example, it can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety and produce a quick, concise summary. This allows for a more appropriate summary by adjusting the expression based on the applicant's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the summarization section may be performed using AI, or not using AI. For example, the summarization section may input applicant sentiment data into an AI and have the AI ​​perform sentiment estimation.

[0104] The question generation unit can generate more in-depth questions by referring to the applicant's past answer history when generating questions. For example, the question generation unit can generate related in-depth questions based on the content of the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers and generate related questions. The question generation unit can also generate questions that delve into unresolved points from the applicant's past answers. For example, the question generation unit can analyze the applicant's past answers, identify unresolved points, and generate questions based on them. The question generation unit can also analyze the applicant's past answer history and generate questions that point out inconsistencies. For example, the question generation unit can analyze the applicant's past answers, identify inconsistencies, and generate questions based on them. In this way, more in-depth questions can be generated by referring to the applicant's past answer history. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without using AI. For example, the question generation unit can input the applicant's past answer history into the AI ​​and generate questions from the AI.

[0105] The interview department can analyze the applicant's nonverbal behavior during the interview to assess their level of nervousness and confidence. For example, the interview department can analyze the applicant's facial expressions to assess their level of nervousness. For example, the interview department can analyze changes in the applicant's facial expressions to assess their level of nervousness. The interview department can also analyze the applicant's posture to assess their level of confidence. For example, the interview department can analyze changes in the applicant's posture to assess their level of confidence. The interview department can also analyze the applicant's tone of voice to assess changes in their emotions. For example, the interview department can analyze changes in the applicant's tone of voice to assess changes in their emotions. In this way, by analyzing the applicant's nonverbal behavior, the interview department can assess their level of nervousness and confidence. Some or all of the above processing in the interview department may be performed using AI, for example, or not. For example, the interview department can input the applicant's nonverbal behavior data into AI and have the AI ​​output the analysis results.

[0106] The summarization unit can evaluate the consistency of the applicant's answers and point out inconsistencies during the summarization process. For example, the summarization unit can analyze the content of the applicant's answers and evaluate their consistency. The summarization unit can also point out inconsistencies in the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify inconsistencies, and point them out. The summarization unit can also point out unresolved points based on the content of the applicant's answers. For example, the summarization unit can analyze the content of the applicant's answers, identify unresolved points, and point them out. This allows the summarization unit to point out inconsistencies by evaluating the consistency of the applicant's answers. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0107] The question generation unit can generate questions related to a company's current projects and challenges during the question generation process. For example, the question generation unit can generate specific questions related to a company's current projects. For example, the question generation unit can generate questions related to a company's ongoing projects to evaluate the suitability of applicants. The question generation unit can also generate questions asking for solutions to challenges facing a company. For example, the question generation unit can generate questions asking for solutions to challenges facing a company to evaluate the problem-solving abilities of applicants. The question generation unit can also generate questions related to a company's future plans to solicit applicants' opinions. For example, the question generation unit can generate questions related to a company's future plans to solicit applicants' opinions and suggestions. In this way, by generating questions related to a company's current projects and challenges, questions that meet the company's needs can be asked. Some or all of the above processing in the question generation unit may be performed using AI, for example, or not using AI. For example, the question generation unit can input information about a company's current projects and challenges into an AI and have the AI ​​generate questions.

[0108] The summarization unit can analyze the applicant's strengths and weaknesses in detail during the summarization process and propose specific areas for improvement. For example, the summarization unit can analyze the applicant's answers to determine their strengths and weaknesses. The summarization unit can also highlight the applicant's strengths and propose specific areas for improvement. The summarization unit can also point out the applicant's weaknesses and provide specific advice for improvement. By analyzing the applicant's strengths and weaknesses in detail, the summarization unit can propose specific areas for improvement. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the applicant's answer data into AI and have the AI ​​output the analysis results.

[0109] The summarization unit can estimate the applicant's emotions and determine the priority of the summary based on the estimated emotions. For example, if the applicant is nervous, the summarization unit will prioritize summarizing important information. For instance, it can analyze the applicant's facial expressions and tone of voice to assess the degree of nervousness and prioritize summarizing important information. Furthermore, if the applicant is relaxed, the summarization unit can summarize the overall information in a balanced way. For example, it can analyze the applicant's posture and gestures to assess the degree of relaxation and summarize the overall information in a balanced way. Also, if the applicant is anxious, the summarization unit can prioritize information to quickly produce results. For example, it can analyze the applicant's heart rate and skin electrical activity to assess the degree of anxiety and prioritize information to quickly produce results. This allows for prioritizing the summary based on the applicant's emotions, thereby prioritizing the summarization of important information. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the summarization section may be performed using AI, or not using AI. For example, the summarization section may input applicant sentiment data into an AI and have the AI ​​perform sentiment estimation.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The analysis department analyzes the information in the application form. The analysis department analyzes the applicant's background, skills, and motivations, and uses text analysis and data mining techniques to extract the applicant's strengths and weaknesses. For example, it can analyze the detailed roles of projects the applicant has been involved in in the past and extract specific achievements. Step 2: The question generation unit generates questions based on the information analyzed by the analysis unit. The question generation unit refers to company-specific information and past recruitment information, and generates questions based on the company's vision and mission. It can also generate questions based on the skill sets the company requires and past recruitment criteria. Step 3: The interview team conducts online interviews using questions generated by the question generation team. Furthermore, leveraging the vast knowledge of the AI, knowledge tests can be conducted to objectively evaluate the applicant's knowledge level. Step 4: The summarization unit summarizes the interview results obtained by the interview unit. Based on the information obtained from the interview, the summarization unit generates feedback materials that summarize the applicant's strengths and weaknesses, and points to ask in the first interview. Text analysis technology and AI can be used to summarize the interview results and extract important information.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] Each of the multiple elements described above, including the analysis unit, question generation unit, interview unit, and summarization unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit analyzes the information in the application form using the processor 46 of the smart device 14 and extracts the applicant's background, skills, and motivation for applying. The question generation unit generates questions based on the analysis results using the specific processing unit 290 of the data processing unit 12, for example, and refers to company-specific information and past recruitment information. The interview unit conducts interviews with applicants on an online platform using the control unit 46A of the smart device 14, for example, and conducts knowledge tests utilizing AI knowledge. The summarization unit summarizes the interview results using the specific processing unit 290 of the data processing unit 12, for example, and generates feedback materials. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] Each of the multiple elements described above, including the analysis unit, question generation unit, interview unit, and summarization unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit analyzes the information in the application form using the processor 46 of the smart glasses 214 and extracts the applicant's background, skills, motivation, etc. The question generation unit generates questions based on the analysis results using the specific processing unit 290 of the data processing unit 12, for example, and refers to company-specific information and past recruitment information. The interview unit conducts interviews with applicants on an online platform using the control unit 46A of the smart glasses 214, for example, and conducts knowledge tests utilizing AI knowledge. The summarization unit summarizes the interview results using the specific processing unit 290 of the data processing unit 12, for example, and generates feedback materials. 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.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] Each of the multiple elements described above, including the analysis unit, question generation unit, interview unit, and summarization unit, is implemented in at least one of the following: the headset terminal 314 and the data processing unit 12. For example, the analysis unit analyzes the information in the application form using the processor 46 of the headset terminal 314 and extracts the applicant's background, skills, and motivation for applying. The question generation unit generates questions based on the analysis results using the specific processing unit 290 of the data processing unit 12, for example, and refers to company-specific information and past recruitment information. The interview unit conducts interviews with applicants on an online platform using the control unit 46A of the headset terminal 314, for example, and conducts knowledge tests utilizing AI knowledge. The summarization unit summarizes the interview results using the specific processing unit 290 of the data processing unit 12, for example, and generates feedback materials. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the analysis unit, question generation unit, interview unit, and summarization unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit analyzes the information in the application form using the processor 46 of the robot 414 and extracts the applicant's background, skills, motivation, etc. The question generation unit generates questions based on the analysis results using, for example, the specific processing unit 290 of the data processing unit 12, and refers to company-specific information and past recruitment information. The interview unit conducts interviews with applicants on an online platform using, for example, the control unit 46A of the robot 414 and conducts knowledge tests utilizing AI knowledge. The summarization unit summarizes the interview results using, for example, the specific processing unit 290 of the data processing unit 12 and generates feedback materials. 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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."

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] (Note 1) The analysis unit analyzes the information from the application form, A question generation unit generates questions based on the information analyzed by the aforementioned analysis unit, An interview unit conducts an online interview using questions generated by the question generation unit, The system includes a summarization unit that summarizes the interview results obtained by the interview unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze the applicant's background, skills, and motivations for applying. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned question generation unit, Refer to company-specific information and past recruitment records, and ask questions to confirm points you want to verify during the interview. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned interview department, We conduct interviews with applicants using an online platform. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned interview department, The AI's vast knowledge is used to conduct knowledge tests. The system described in Appendix 1, characterized by the features described herein. (Note 6) The summary section above is, Based on the information gathered during the interview, a feedback document is generated summarizing the applicant's strengths and weaknesses, as well as points to ask in the first interview. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, The system estimates the applicant's emotions and adjusts the accuracy of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, We conduct a detailed analysis of the applicant's past work history and extract their roles and achievements in specific projects. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, Analyze applicants' social media activity to gain a complementary understanding of their motivations and interests. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system estimates the emotions of applicants and prioritizes the analysis results based on the estimated emotions of the applicants. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, We analyze the geographical location information of applicants and take into account region-specific skills and experience. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, We analyze applicants' online portfolios and blogs to assess their additional skills and knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned question generation unit, The system estimates the applicant's emotions and adjusts the difficulty of the questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned question generation unit, When generating questions, the system refers to the applicant's past answer history to generate more in-depth questions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned question generation unit, When generating questions, the system generates questions related to the company's current projects and challenges. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned question generation unit, The system estimates the applicant's emotions and adjusts the order of questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned question generation unit, When generating questions, specialized questions are generated based on the applicant's industry experience. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned question generation unit, When generating questions, the system creates questions related to the applicant's hobbies and interests to help them relax. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned interview department, The system estimates the applicant's emotions and adjusts the pace of the interview based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned interview department, During the interview, we analyze the applicant's nonverbal behavior to assess their level of nervousness and confidence. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned interview department, During interviews, the system analyzes applicants' responses in real time and immediately generates follow-up questions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned interview department, We estimate the applicant's emotions and adjust the interview atmosphere based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned interview department, During the interview, we will refer to the applicant's past interview history and ask questions that will not be repeated. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned interview department, During the interview, we generate appropriate questions that take into account the applicant's cultural background. The system described in Appendix 1, characterized by the features described herein. (Note 25) The summary section above is, Estimate the applicant's emotions and adjust the way the summary is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The summary section above is, During the summarization process, assess the consistency of the applicant's answers and point out any inconsistencies. The system described in Appendix 1, characterized by the features described herein. (Note 27) The summary section above is, When summarizing, conduct a detailed analysis of the applicant's strengths and weaknesses and propose specific areas for improvement. The system described in Appendix 1, characterized by the features described herein. (Note 28) The summary section above is, Estimate the applicant's emotions and determine the priority of the summary based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The summary section above is, During the summarization process, applicants' responses are compared with those of other applicants to provide a relative evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The summary section above is, During the summarization process, the applicant's answers are evaluated in comparison to the skill set required by the company. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0184] 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 analysis unit analyzes the information from the application form, A question generation unit generates questions based on the information analyzed by the aforementioned analysis unit, An interview unit conducts an online interview using questions generated by the question generation unit, The system includes a summarization unit that summarizes the interview results obtained by the interview unit. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze the applicant's background, skills, and motivations for applying. The system according to feature 1.

3. The aforementioned question generation unit, Refer to company-specific information and past recruitment records, and ask questions to confirm points you want to verify during the interview. The system according to feature 1.

4. The aforementioned interview department, We conduct interviews with applicants using an online platform. The system according to feature 1.

5. The aforementioned interview department, The vast knowledge possessed by AI will be used to conduct knowledge tests. The system according to feature 1.

6. The summary section above is, Based on the information gathered during the interview, a feedback document is generated summarizing the applicant's strengths and weaknesses, as well as points to ask in the first interview. The system according to feature 1.

7. The aforementioned analysis unit, The system estimates the applicant's emotions and adjusts the accuracy of the analysis based on the estimated emotions. The system according to feature 1.

8. The aforementioned analysis unit, We conduct a detailed analysis of the applicant's past work history and extract their roles and achievements in specific projects. The system according to feature 1.

9. The aforementioned analysis unit, Analyze applicants' social media activity to gain a complementary understanding of their motivations and interests. The system according to feature 1.

10. The aforementioned analysis unit, The system estimates the emotions of applicants and prioritizes the analysis results based on the estimated emotions of the applicants. The system according to feature 1.

Images