System

Abstract

An object of the system according to the embodiment is to efficiently analyze contents of a resume and evaluate skills and experience of a candidate.SOLUTION: A system according to an embodiment includes a preprocessing unit, a generation unit, an evaluation unit, a question generation unit, and a response evaluation unit. The preprocessing unit preprocesses the text of the resume. The generation unit analyzes the text preprocessed by the preprocessing unit, extracts information, and generates a summary. The evaluation unit analyzes the contents of the resume based on the summary generated by the generation unit, and evaluates the skill and experience of the candidate. The question generation unit generates a question based on the information evaluated by the evaluation unit, and makes the question to the candidate. The response evaluation unit evaluates a response of the candidate to the question generated by the question generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the drawback of making it difficult to efficiently analyze resume content and evaluate candidates' skills and experience.

[0005] The system according to the embodiment aims to efficiently analyze the contents of resumes and evaluate the skills and experience of candidates. [Means for solving the problem]

[0006] The system according to the embodiment includes a preprocessing unit, a generation unit, an evaluation unit, a question generation unit, and a response evaluation unit. The preprocessing unit preprocesses the resume text. The generation unit analyzes the text preprocessed by the preprocessing unit, extracts information, and generates a summary. The evaluation unit analyzes the content of the resume based on the summary generated by the generation unit and evaluates the skills and experience of the candidate. The question generation unit generates questions based on the information evaluated by the evaluation unit and asks the questions to the candidate. The response evaluation unit evaluates the candidate's responses to the questions posed by the question generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently analyze the contents of a resume and evaluate the skills and experience of a candidate. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A recruitment support system according to an embodiment of the present invention is a system that uses a generation AI to summarize and analyze resumes and a digital human to conduct first interviews. The recruitment support system inputs the resume text into the generation AI, which then analyzes the input resume and generates a summary. Based on the generated summary, the generation AI analyzes the resume content and evaluates the candidate's skills and experience. Furthermore, the digital human conducts a first interview and evaluates the candidate's responses. For example, the recruitment support system inputs the text data of a resume submitted by a candidate into the generation AI. This ensures that the generation AI can properly analyze the resume regardless of its format or content. Next, the recruitment support system uses the generation AI to analyze each section of the resume (e.g., educational background, work history, skills, etc.) and extracts important information to generate a summary. For example, the generation AI outputs the candidate's highest level of education, most recent work history, and key skills as a summary. Next, the recruitment support system evaluates the candidate's skill set and depth of experience based on the summarized information. For example, the generation AI evaluates skills in a specific programming language or project management experience. Next, in the recruitment support system, a digital human asks candidates questions based on the questions generated by the generative AI. The candidate's responses are evaluated in real time by the digital human. For example, the candidate's communication skills and problem-solving ability are evaluated. This allows the recruitment support system to realize an efficient and objective recruitment process. By using generative AI to summarize and analyze resumes and having digital humans conduct first interviews, the recruitment support system reduces the burden on recruiters and allows for consistent candidate evaluation. For example, this makes it possible to quickly select the most suitable candidate from a large number of applicants.

[0029] The recruitment support system according to the embodiment includes a preprocessing unit, a generation unit, an evaluation unit, a questioning unit, and a response evaluation unit. The preprocessing unit preprocesses the resume text. For example, the preprocessing unit preprocesses the text data so that it can be appropriately analyzed regardless of the format or content of the resume. The preprocessing unit performs processes such as text normalization, noise removal, and tokenization. The generation unit uses a generation AI to analyze the text preprocessed by the preprocessing unit, extract important information, and generate a summary. For example, the generation unit analyzes each section of the resume (e.g., educational background, work history, skills, etc.) and extracts important information to generate a summary. The generation unit outputs, for example, the candidate's highest educational background, most recent work history, and key skills as a summary. The evaluation unit analyzes the content of the resume based on the summary generated by the generation unit and evaluates the candidate's skills and experience. For example, the evaluation unit evaluates the candidate's skill set and depth of experience based on the summarized information. For example, the evaluation unit evaluates, for example, skills in a specific programming language, project management experience, etc. The questioning unit generates questions based on the information evaluated by the evaluation unit and asks the candidates. The questioning unit generates appropriate questions using, for example, a generation AI based on the candidate's skills and experience. The questioning unit generates specific questions based on, for example, the candidate's skills and experience. The response evaluation unit evaluates the candidate's responses to the questions posed by the questioning unit. The response evaluation unit evaluates, for example, the candidate's communication skills and problem-solving ability. The response evaluation unit evaluates, for example, the candidate's communication skills and problem-solving ability based on the content of the candidate's responses. As a result, the recruitment support system according to the embodiment realizes an efficient and objective recruitment process by preprocessing resume text, generating and evaluating summaries, asking questions, and evaluating responses.

[0030] The preprocessing unit can preprocess the text data so that it can be analyzed regardless of the format or content of the resume. The preprocessing unit performs processes such as text normalization, noise removal, and tokenization. The preprocessing unit can, for example, remove unnecessary line breaks and spaces from the resume text data. The preprocessing unit can also automatically correct typos and omissions from the resume text data. Furthermore, the preprocessing unit can remove unnecessary formatting information from the resume text data and convert it into a format that is easy to analyze. In this way, by preprocessing the text data so that it can be properly analyzed regardless of the resume format or content, analysis accuracy is improved.

[0031] The generation unit can analyze each section of the resume, extract important information, and generate a summary. For example, the generation unit analyzes each section of the resume (e.g., educational background, work history, skills, etc.), extracts important information, and generates a summary. The generation unit outputs, for example, the candidate's highest educational background, most recent work history, and main skills as a summary. The generation unit can also use a generation AI to analyze the contents of the resume, extract important information, and generate a summary. For example, the generation AI receives a prompt such as "Please summarize the main points of this resume," and extracts the main points of the resume to create a summary. This improves the accuracy of the summary by analyzing each section of the resume and extracting important information to generate a summary.

[0032] The evaluation unit can evaluate the candidate's skill set and experience based on the summarized information. For example, the evaluation unit evaluates the candidate's skill set and depth of experience based on the summarized information. For example, the evaluation unit evaluates skills in a specific programming language or project management experience. The evaluation unit can also use a generative AI to evaluate the candidate's skill set and depth of experience based on the summarized information. For example, the evaluation unit uses a generative AI to analyze the summarized information and evaluate the candidate's skill set and depth of experience. This improves the accuracy of the evaluation by evaluating the candidate's skill set and depth of experience based on the summarized information.

[0033] The question unit allows the generation AI to generate appropriate questions based on the candidate's skills and experience. For example, the question unit generates appropriate questions based on the candidate's skills and experience. The question unit generates specific questions based on the candidate's skills and experience. The question unit can also use the generation AI to generate appropriate questions based on the candidate's skills and experience. For example, the question unit receives a prompt from the generation AI asking, "What questions should be asked of this candidate?" and generates questions based on the candidate's skills and experience. This allows the generation AI to generate appropriate questions based on the candidate's skills and experience, thereby improving the accuracy of questions.

[0034] The response evaluation unit can evaluate the candidate's communication skills and problem-solving ability. The response evaluation unit evaluates, for example, the candidate's communication skills and problem-solving ability. The response evaluation unit can evaluate, for example, the candidate's communication skills and problem-solving ability based on the content of the candidate's response. The response evaluation unit can also use a generation AI to evaluate the candidate's communication skills and problem-solving ability based on the content of the candidate's response. For example, the response evaluation unit uses a generation AI to analyze the content of the candidate's response and evaluate the candidate's communication skills and problem-solving ability. This improves the accuracy of the evaluation by evaluating the candidate's communication skills and problem-solving ability.

[0035] The preprocessing unit can automatically detect differences in language and format of resumes and select the optimal preprocessing method. For example, the preprocessing unit automatically detects differences in language and format of resumes and selects the optimal preprocessing method. For example, if the resume is written in English, the preprocessing unit performs preprocessing that is compatible with the English-specific format. Furthermore, if the resume is submitted in PDF format, the preprocessing unit can extract text and convert it into an analyzable format. Furthermore, if the resume is submitted handwritten, the preprocessing unit can convert it into text data using handwriting recognition technology. In this way, the accuracy of preprocessing is improved by automatically detecting differences in language and format of resumes and selecting the optimal preprocessing method.

[0036] The preprocessing unit can perform preprocessing to emphasize specific sections according to the content of the resume. For example, the preprocessing unit performs preprocessing to emphasize specific sections according to the content of the resume. For example, if the education section is important, the preprocessing unit can perform preprocessing by emphasizing information related to education. Furthermore, if the work history section is important, the preprocessing unit can perform preprocessing by emphasizing information related to work history. Furthermore, if the skills section is important, the preprocessing unit can perform preprocessing by emphasizing information related to skills. In this way, by performing preprocessing to emphasize specific sections according to the content of the resume, the accuracy of the preprocessing is improved.

[0037] The preprocessing unit can perform filtering to remove noise from the resume text data and improve analysis accuracy. The preprocessing unit, for example, performs filtering to remove noise from the resume text data and improve analysis accuracy. The preprocessing unit, for example, removes unnecessary line breaks and spaces from the resume text data. The preprocessing unit can also automatically correct typos and omissions from the resume text data. The preprocessing unit can also remove unnecessary formatting information from the resume text data and convert it into a format that is easier to analyze. In this way, filtering to remove noise from the resume text data and improve analysis accuracy improves the accuracy of preprocessing.

[0038] The preprocessing unit can preprocess the resume text data to adjust it according to different industries and job types. For example, the preprocessing unit performs preprocessing to customize the resume text data according to different industries and job types. For example, the preprocessing unit can emphasize programming skills and project experience in a resume for the IT industry. The preprocessing unit can also emphasize medical qualifications and clinical experience in a resume for the medical industry. The preprocessing unit can also emphasize teaching qualifications and teaching experience in a resume for the education industry. In this way, the accuracy of the preprocessing is improved by performing preprocessing to customize the resume text data according to different industries and job types.

[0039] The preprocessing unit can optimize preprocessing by comparing the resume text data with past application histories. The preprocessing unit, for example, optimizes preprocessing by comparing the resume text data with past application histories. The preprocessing unit, for example, compares the resume text data with past application histories and removes duplicate information. The preprocessing unit can also extract important information from past application histories and perform preprocessing. The preprocessing unit can also emphasize the most recent information by comparing the resume text data with past application histories. In this way, optimizing preprocessing by comparing the resume text data with past application histories improves the accuracy of preprocessing.

[0040] The preprocessing unit can preprocess the resume text data based on the candidate's geographical background. For example, the preprocessing unit preprocesses the resume text data based on the candidate's geographical background. For example, the preprocessing unit highlights information about local companies and schools based on the candidate's place of residence. The preprocessing unit can also highlight region-specific skills and experience based on the candidate's geographical background. The preprocessing unit can also highlight information related to the local job market based on the candidate's geographical background. In this way, by preprocessing the resume text data based on the candidate's geographical background, the accuracy of the preprocessing is improved.

[0041] The generation unit can analyze each section of the resume and adjust the level of detail of the summary based on its importance. For example, the generation unit analyzes each section of the resume and adjusts the level of detail of the summary based on its importance. For example, if the education section is important, the generation unit generates a detailed summary related to the education section. Also, if the work history section is important, the generation unit can generate a detailed summary related to the work history section. Also, if the skills section is important, the generation unit can generate a detailed summary related to the skills section. In this way, by analyzing each section of the resume and adjusting the level of detail of the summary based on its importance, the accuracy of the summary is improved.

[0042] The generation unit can use different summarization algorithms depending on the content of the resume. For example, the generation unit applies different summarization algorithms depending on the content of the resume. For example, the generation unit applies a summarization algorithm specialized for educational background to a resume with a lot of educational background information. The generation unit can also apply a summarization algorithm specialized for work history to a resume with a lot of work history information. The generation unit can also apply a summarization algorithm specialized for skills to a resume with a lot of skills information. In this way, by applying different summarization algorithms depending on the content of the resume, the accuracy of the summary is improved.

[0043] The generation unit can improve the accuracy of the summary by referring to past summary results of the resume. The generation unit, for example, improves the accuracy of the summary by referring to past summary results of the resume. The generation unit, for example, applies an algorithm that improves the accuracy of the summary based on the past summary results. The generation unit can also improve the accuracy of the summary by extracting important information from the past summary results. The generation unit can also analyze the past summary results and reflect feedback to improve the accuracy of the summary. In this way, the accuracy of the summary is improved by referring to the past summary results of the resume.

[0044] The generation unit can determine the priority of summaries based on the time of submission of the resume. The generation unit determines the priority of summaries based on, for example, the time of submission of the resume. The generation unit, for example, prioritizes summarizing the most recent resume. The generation unit can also summarize resumes that were submitted earlier later. The generation unit can also adjust the order of summaries based on the time of submission. In this way, by determining the priority of summaries based on the time of submission of the resume, the accuracy of summaries is improved.

[0045] The generation unit can change the order of summaries based on the relevance of the resumes. The generation unit, for example, adjusts the order of summaries based on the relevance of the resumes. The generation unit, for example, prioritizes summarizing highly relevant resumes. The generation unit can also postpone summarizing less relevant resumes. The generation unit can also adjust the order of summaries based on the relevance. In this way, adjusting the order of summaries based on the relevance of the resumes improves the accuracy of the summaries.

[0046] The generation unit can adjust the use of technical terms in the resume according to the expertise level of the candidate. For example, the generation unit adjusts the use of technical terms in the resume according to the expertise level of the candidate. For example, the generation unit generates a summary that uses a lot of technical terms for a candidate with high expertise. The generation unit can also generate a summary that uses less technical terms for a candidate with low expertise. The generation unit can also adjust the use of technical terms according to the expertise level. In this way, by adjusting the use of technical terms in the resume according to the expertise level of the candidate, the accuracy of the summary is improved.

[0047] The evaluation unit can evaluate the candidate's skill set and depth of experience in detail based on the summarized information. The evaluation unit, for example, evaluates the candidate's skill set and depth of experience in detail based on the summarized information. The evaluation unit, for example, evaluates the candidate's programming skills in detail from the summarized information. The evaluation unit can also evaluate the candidate's project management experience in detail from the summarized information. The evaluation unit can also evaluate the candidate's communication skills in detail from the summarized information. In this way, the accuracy of the evaluation is improved by evaluating the candidate's skill set and depth of experience in detail based on the summarized information.

[0048] The evaluation unit can use different evaluation algorithms depending on the content of the resume. For example, the evaluation unit applies different evaluation algorithms depending on the content of the resume. For example, if programming skills are important, the evaluation unit applies an evaluation algorithm specialized for programming skills. Furthermore, if project management experience is important, the evaluation unit can also apply an evaluation algorithm specialized for project management. Furthermore, if communication skills are important, the evaluation unit can also apply an evaluation algorithm specialized for communication skills. In this way, by applying different evaluation algorithms depending on the content of the resume, the accuracy of the evaluation is improved.

[0049] The evaluation unit can improve the accuracy of the evaluation by referring to past evaluation results. The evaluation unit, for example, improves the accuracy of the evaluation by referring to past evaluation results. The evaluation unit, for example, applies an algorithm that improves the accuracy of the evaluation based on the past evaluation results. The evaluation unit can also improve the accuracy of the evaluation by extracting important information from the past evaluation results. The evaluation unit can also analyze the past evaluation results and reflect feedback to improve the accuracy of the evaluation. In this way, the accuracy of the evaluation is improved by referring to the past evaluation results.

[0050] The evaluation unit can weight the evaluation based on the time of submission of the resume. The evaluation unit weights the evaluation based on, for example, the time of submission of the resume. The evaluation unit, for example, prioritizes evaluation of the most recent resume. The evaluation unit can also postpone evaluation of resumes that were submitted earlier. The evaluation unit can also adjust the weight of the evaluation based on the time of submission. In this way, weighting the evaluation based on the time of submission of the resume improves the accuracy of the evaluation.

[0051] The evaluation unit can change the order of evaluation based on the relevance of the resumes. The evaluation unit, for example, adjusts the order of evaluation based on the relevance of the resumes. The evaluation unit, for example, prioritizes evaluation of highly relevant resumes. The evaluation unit can also postpone evaluation of less relevant resumes. The evaluation unit can also adjust the order of evaluation based on the relevance. In this way, adjusting the order of evaluation based on the relevance of the resumes improves the accuracy of the evaluation.

[0052] The evaluation unit can adjust the use of technical terms in the resume according to the candidate's level of expertise. The evaluation unit, for example, adjusts the use of technical terms in the resume according to the candidate's level of expertise. For example, the evaluation unit may perform an evaluation that uses more technical terms for a candidate with high expertise. The evaluation unit may also perform an evaluation that uses less technical terms for a candidate with low expertise. The evaluation unit may also adjust the use of technical terms according to the candidate's level of expertise. In this way, the accuracy of the evaluation is improved by adjusting the use of technical terms in the resume according to the candidate's level of expertise.

[0053] The questioning unit can adjust the level of detail of the questions based on the skills and experience of the candidate. The questioning unit adjusts the level of detail of the questions based on, for example, the skills and experience of the candidate. For example, the questioning unit asks detailed questions to candidates with high skills. The questioning unit can also ask concise questions to candidates with low skills. The questioning unit can also ask questions that include specific examples to candidates with a lot of experience. In this way, adjusting the level of detail of the questions based on the skills and experience of the candidate improves the accuracy of the questions.

[0054] The questioning unit can use different questioning algorithms depending on the content of the candidate's resume. For example, the questioning unit applies different questioning algorithms depending on the content of the candidate's resume. For example, if programming skills are important, the questioning unit applies a questioning algorithm specialized for programming. Furthermore, if project management experience is important, the questioning unit can also apply a questioning algorithm specialized for project management. Furthermore, if communication skills are important, the questioning unit can also apply a questioning algorithm specialized for communication. In this way, by applying different questioning algorithms depending on the content of the candidate's resume, the accuracy of the questions is improved.

[0055] The questioning unit can improve the accuracy of questions by referring to past question results. The questioning unit, for example, improves the accuracy of questions by referring to past question results. The questioning unit, for example, applies an algorithm that improves the accuracy of questions based on past question results. The questioning unit can also improve the accuracy of questions by extracting important information from past question results. The questioning unit can also analyze past question results and reflect feedback to improve the accuracy of questions. In this way, the accuracy of questions is improved by referring to past question results.

[0056] The questioning unit can determine the priority of questions based on the time of submission of the questions. The questioning unit determines the priority of questions based on, for example, the time of submission of the questions. The questioning unit, for example, prioritizes the most recent questions. The questioning unit can also postpone questions that were submitted earlier. The questioning unit can also adjust the order of questions based on the time of submission. In this way, by determining the priority of questions based on the time of submission of the questions, the accuracy of the questions is improved.

[0057] The questioning unit can change the order of questions based on the relevance of the questions. For example, the questioning unit adjusts the order of questions based on the relevance of the questions. For example, the questioning unit prioritizes highly relevant questions. Furthermore, the questioning unit can also postpone asking less relevant questions. Furthermore, the questioning unit can adjust the order of questions based on the relevance. In this way, adjusting the order of questions based on the relevance of the questions improves the accuracy of the questions.

[0058] The questioning unit can adjust the use of technical terms in the questions according to the expertise level of the candidate. For example, the questioning unit adjusts the use of technical terms in the questions according to the expertise level of the candidate. For example, the questioning unit asks questions that use a lot of technical terms to candidates with high expertise. The questioning unit can also ask questions that use less technical terms to candidates with low expertise. The questioning unit can also adjust the use of technical terms according to the expertise level. In this way, by adjusting the use of technical terms in the questions according to the expertise level of the candidate, the accuracy of the questions is improved.

[0059] The response evaluation unit can analyze the content of the candidate's response in detail and evaluate their communication skills and problem-solving ability. The response evaluation unit, for example, analyzes the content of the candidate's response in detail and evaluates their communication skills, problem-solving ability, etc. The response evaluation unit can evaluate their communication skills and problem-solving ability based on the content of the candidate's response. The response evaluation unit can also use a generation AI to evaluate their communication skills and problem-solving ability based on the content of the candidate's response. For example, the response evaluation unit uses a generation AI to analyze the content of the candidate's response and evaluate their communication skills and problem-solving ability. In this way, by analyzing the content of the candidate's response in detail, the evaluation of their communication skills and problem-solving ability is improved.

[0060] The response evaluation unit can use different evaluation algorithms depending on the content of the response. For example, the response evaluation unit applies different evaluation algorithms depending on the content of the response. For example, if communication skills are important, the response evaluation unit applies an evaluation algorithm specialized for communication. Furthermore, if problem-solving ability is important, the response evaluation unit can also apply an evaluation algorithm specialized for problem solving. Furthermore, if leadership skills are important, the response evaluation unit can also apply an evaluation algorithm specialized for leadership. In this way, by applying different evaluation algorithms depending on the content of the response, the accuracy of the evaluation is improved.

[0061] The response evaluation unit can improve the accuracy of the evaluation by referring to past response evaluation results. The response evaluation unit improves the accuracy of the evaluation by referring to, for example, past response evaluation results. The response evaluation unit applies an algorithm that improves the accuracy of the evaluation based on, for example, past response evaluation results. The response evaluation unit can also improve the accuracy of the evaluation by extracting important information from past response evaluation results. The response evaluation unit can also analyze past response evaluation results and reflect feedback to improve the accuracy of the evaluation. In this way, the accuracy of the evaluation is improved by referring to past response evaluation results.

[0062] The response evaluation unit can weight the evaluation based on the time of submission of the response. The response evaluation unit weights the evaluation based on, for example, the time of submission of the response. The response evaluation unit, for example, prioritizes evaluation of the most recent response. The response evaluation unit can also evaluate responses that were submitted earlier later. The response evaluation unit can also adjust the weighting of the evaluation based on the time of submission. Thus, weighting the evaluation based on the time of submission of the response improves the accuracy of the evaluation.

[0063] The response evaluation unit can change the order of evaluation based on the relevance of the responses. The response evaluation unit, for example, adjusts the order of evaluation based on the relevance of the responses. For example, the response evaluation unit prioritizes evaluation of highly relevant responses. The response evaluation unit can also postpone evaluation of less relevant responses. The response evaluation unit can also adjust the order of evaluation based on the relevance. In this way, adjusting the order of evaluation based on the relevance of the responses improves the accuracy of the evaluation.

[0064] The response evaluation unit can adjust the use of technical terms in the response according to the expertise level of the candidate. The response evaluation unit, for example, adjusts the use of technical terms in the response according to the expertise level of the candidate. For example, the response evaluation unit performs an evaluation that uses more technical terms for a candidate with high expertise. The response evaluation unit can also perform an evaluation that uses less technical terms for a candidate with low expertise. The response evaluation unit can also adjust the use of technical terms according to the expertise level. In this way, by adjusting the use of technical terms in the response according to the expertise level of the candidate, the accuracy of the evaluation is improved.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The evaluation department can propose an appropriate training plan based on the candidate's skills and experience. For example, the evaluation department can analyze the candidate's skill set and, if a specific skill is lacking, propose a training plan to improve that skill. The evaluation department can also propose a career path based on the candidate's experience. Furthermore, the evaluation department can introduce an appropriate mentor based on the candidate's skills and experience. In this way, the evaluation department can support the candidate's growth by proposing an appropriate training plan, career path, and mentor based on the candidate's skills and experience.

[0067] The questioning department can adjust the content of the questions by referring to the candidate's past interview results. For example, the questioning department can avoid questions that the candidate found difficult in past interviews. The questioning department can also increase the number of questions related to areas in which the candidate was strong in past interviews. Furthermore, the questioning department can ask questions to check the candidate's growth based on the past interview results. In this way, the questioning department can realize more effective interviews by adjusting the content of the questions by referring to the candidate's past interview results.

[0068] The response evaluation unit can provide appropriate feedback based on the content of the candidate's response. For example, the response evaluation unit can provide feedback on the candidate's communication skills. The response evaluation unit can also provide feedback on the candidate's problem-solving ability. Furthermore, the response evaluation unit can provide feedback pointing out areas for improvement and strengths based on the content of the candidate's response. In this way, the response evaluation unit can support the candidate's growth by providing appropriate feedback based on the content of the candidate's response.

[0069] The preprocessing unit can customize the resume text data based on the candidate's work history. For example, if the candidate has extensive experience in the IT industry, the preprocessing unit can emphasize IT-related skills and project experience. In addition, if the candidate has extensive experience in the medical industry, the preprocessing unit can emphasize medical qualifications and clinical experience. Furthermore, if the candidate has extensive experience in the education industry, the preprocessing unit can emphasize teaching qualifications and teaching experience. In this way, the preprocessing unit can customize the resume text data based on the candidate's work history, thereby improving the accuracy of preprocessing.

[0070] The generation unit can evaluate the suitability of a candidate based on the content of the resume. For example, the generation unit can evaluate whether the candidate is suitable for a specific job based on the content of the resume. The generation unit can also evaluate whether the candidate has a specific skill set based on the content of the resume. Furthermore, the generation unit can evaluate whether the candidate has extensive experience in a specific industry based on the content of the resume. In this way, the generation unit can select an appropriate candidate by evaluating the suitability of the candidate based on the content of the resume.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The preprocessing section preprocesses the resume text. For example, the preprocessing section preprocesses the text data so that it can be analyzed appropriately regardless of the format or content of the resume. Specifically, it performs processes such as text normalization, noise removal, and tokenization. Step 2: The generator analyzes the preprocessed text, extracts important information, and generates a summary. For example, the generator analyzes each section of a resume (educational history, work history, skills, etc.) and outputs a summary of the candidate's highest level of education, most recent work history, key skills, etc. Step 3: The evaluation unit analyzes the resume content based on the summary generated by the generation unit and evaluates the candidate's skills and experience. For example, the evaluation unit evaluates specific programming language skills or project management experience based on the summarized information. Step 4: The questioning unit generates questions based on the information evaluated by the evaluation unit and asks the candidates. For example, the questioning unit uses a generation AI to generate appropriate questions based on the candidate's skills and experience. Step 5: The response evaluation section evaluates the candidate's responses to the questions posed by the questioning section. The response evaluation section evaluates, for example, the candidate's communication skills, problem-solving ability, etc.

[0073] (Example 2) A recruitment support system according to an embodiment of the present invention is a system that uses a generation AI to summarize and analyze resumes and a digital human to conduct first interviews. The recruitment support system inputs the resume text into the generation AI, which then analyzes the input resume and generates a summary. Based on the generated summary, the generation AI analyzes the resume content and evaluates the candidate's skills and experience. Furthermore, the digital human conducts a first interview and evaluates the candidate's responses. For example, the recruitment support system inputs the text data of a resume submitted by a candidate into the generation AI. This ensures that the generation AI can properly analyze the resume regardless of its format or content. Next, the recruitment support system uses the generation AI to analyze each section of the resume (e.g., educational background, work history, skills, etc.) and extracts important information to generate a summary. For example, the generation AI outputs the candidate's highest level of education, most recent work history, and key skills as a summary. Next, the recruitment support system evaluates the candidate's skill set and depth of experience based on the summarized information. For example, the generation AI evaluates skills in a specific programming language or project management experience. Next, in the recruitment support system, a digital human asks candidates questions based on the questions generated by the generative AI. The candidate's responses are evaluated in real time by the digital human. For example, the candidate's communication skills and problem-solving ability are evaluated. This allows the recruitment support system to realize an efficient and objective recruitment process. By using generative AI to summarize and analyze resumes and having digital humans conduct first interviews, the recruitment support system reduces the burden on recruiters and allows for consistent candidate evaluation. For example, this makes it possible to quickly select the most suitable candidate from a large number of applicants.

[0074] The recruitment support system according to the embodiment includes a preprocessing unit, a generation unit, an evaluation unit, a questioning unit, and a response evaluation unit. The preprocessing unit preprocesses the resume text. For example, the preprocessing unit preprocesses the text data so that it can be appropriately analyzed regardless of the format or content of the resume. The preprocessing unit performs processes such as text normalization, noise removal, and tokenization. The generation unit uses a generation AI to analyze the text preprocessed by the preprocessing unit, extract important information, and generate a summary. For example, the generation unit analyzes each section of the resume (e.g., educational background, work history, skills, etc.) and extracts important information to generate a summary. The generation unit outputs, for example, the candidate's highest educational background, most recent work history, and key skills as a summary. The evaluation unit analyzes the content of the resume based on the summary generated by the generation unit and evaluates the candidate's skills and experience. For example, the evaluation unit evaluates the candidate's skill set and depth of experience based on the summarized information. For example, the evaluation unit evaluates, for example, skills in a specific programming language, project management experience, etc. The questioning unit generates questions based on the information evaluated by the evaluation unit and asks the candidates. The questioning unit generates appropriate questions using, for example, a generation AI based on the candidate's skills and experience. The questioning unit generates specific questions based on, for example, the candidate's skills and experience. The response evaluation unit evaluates the candidate's responses to the questions posed by the questioning unit. The response evaluation unit evaluates, for example, the candidate's communication skills and problem-solving ability. The response evaluation unit evaluates, for example, the candidate's communication skills and problem-solving ability based on the content of the candidate's responses. As a result, the recruitment support system according to the embodiment realizes an efficient and objective recruitment process by preprocessing resume text, generating and evaluating summaries, asking questions, and evaluating responses.

[0075] The preprocessing unit can preprocess the text data so that it can be analyzed regardless of the format or content of the resume. The preprocessing unit performs processes such as text normalization, noise removal, and tokenization. The preprocessing unit can, for example, remove unnecessary line breaks and spaces from the resume text data. The preprocessing unit can also automatically correct typos and omissions from the resume text data. Furthermore, the preprocessing unit can remove unnecessary formatting information from the resume text data and convert it into a format that is easy to analyze. In this way, by preprocessing the text data so that it can be properly analyzed regardless of the resume format or content, analysis accuracy is improved.

[0076] The generation unit can analyze each section of the resume, extract important information, and generate a summary. For example, the generation unit analyzes each section of the resume (e.g., educational background, work history, skills, etc.), extracts important information, and generates a summary. The generation unit outputs, for example, the candidate's highest educational background, most recent work history, and main skills as a summary. The generation unit can also use a generation AI to analyze the contents of the resume, extract important information, and generate a summary. For example, the generation AI receives a prompt such as "Please summarize the main points of this resume," and extracts the main points of the resume to create a summary. This improves the accuracy of the summary by analyzing each section of the resume and extracting important information to generate a summary.

[0077] The evaluation unit can evaluate the candidate's skill set and experience based on the summarized information. For example, the evaluation unit evaluates the candidate's skill set and depth of experience based on the summarized information. For example, the evaluation unit evaluates skills in a specific programming language or project management experience. The evaluation unit can also use a generative AI to evaluate the candidate's skill set and depth of experience based on the summarized information. For example, the evaluation unit uses a generative AI to analyze the summarized information and evaluate the candidate's skill set and depth of experience. This improves the accuracy of the evaluation by evaluating the candidate's skill set and depth of experience based on the summarized information.

[0078] The question unit allows the generation AI to generate appropriate questions based on the candidate's skills and experience. For example, the question unit generates appropriate questions based on the candidate's skills and experience. The question unit generates specific questions based on the candidate's skills and experience. The question unit can also use the generation AI to generate appropriate questions based on the candidate's skills and experience. For example, the question unit receives a prompt from the generation AI asking, "What questions should be asked of this candidate?" and generates questions based on the candidate's skills and experience. This allows the generation AI to generate appropriate questions based on the candidate's skills and experience, thereby improving the accuracy of questions.

[0079] The response evaluation unit can evaluate the candidate's communication skills and problem-solving ability. The response evaluation unit evaluates, for example, the candidate's communication skills and problem-solving ability. The response evaluation unit can evaluate, for example, the candidate's communication skills and problem-solving ability based on the content of the candidate's response. The response evaluation unit can also use a generation AI to evaluate the candidate's communication skills and problem-solving ability based on the content of the candidate's response. For example, the response evaluation unit uses a generation AI to analyze the content of the candidate's response and evaluate the candidate's communication skills and problem-solving ability. This improves the accuracy of the evaluation by evaluating the candidate's communication skills and problem-solving ability.

[0080] The preprocessing unit can estimate the user's emotions and adjust the preprocessing method based on the estimated user emotions. For example, the preprocessing unit can estimate the user's emotions and adjust the preprocessing method based on the estimated user emotions. For example, if the user is feeling stressed, the preprocessing unit can simplify the preprocessing procedure and perform analysis quickly. Furthermore, if the user is relaxed, the preprocessing unit can perform detailed preprocessing to improve accuracy. Furthermore, if the user is in a hurry, the preprocessing unit can perform preprocessing by focusing on the most important information. This improves the accuracy of preprocessing by adjusting the preprocessing method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0081] The preprocessing unit can automatically detect differences in language and format of resumes and select the optimal preprocessing method. For example, the preprocessing unit automatically detects differences in language and format of resumes and selects the optimal preprocessing method. For example, if the resume is written in English, the preprocessing unit performs preprocessing that is compatible with the English-specific format. Furthermore, if the resume is submitted in PDF format, the preprocessing unit can extract text and convert it into an analyzable format. Furthermore, if the resume is submitted handwritten, the preprocessing unit can convert it into text data using handwriting recognition technology. In this way, the accuracy of preprocessing is improved by automatically detecting differences in language and format of resumes and selecting the optimal preprocessing method.

[0082] The preprocessing unit can perform preprocessing to emphasize specific sections according to the content of the resume. For example, the preprocessing unit performs preprocessing to emphasize specific sections according to the content of the resume. For example, if the education section is important, the preprocessing unit can perform preprocessing by emphasizing information related to education. Furthermore, if the work history section is important, the preprocessing unit can perform preprocessing by emphasizing information related to work history. Furthermore, if the skills section is important, the preprocessing unit can perform preprocessing by emphasizing information related to skills. In this way, by performing preprocessing to emphasize specific sections according to the content of the resume, the accuracy of the preprocessing is improved.

[0083] The preprocessing unit can perform filtering to remove noise from the resume text data and improve analysis accuracy. The preprocessing unit, for example, performs filtering to remove noise from the resume text data and improve analysis accuracy. The preprocessing unit, for example, removes unnecessary line breaks and spaces from the resume text data. The preprocessing unit can also automatically correct typos and omissions from the resume text data. The preprocessing unit can also remove unnecessary formatting information from the resume text data and convert it into a format that is easier to analyze. In this way, filtering to remove noise from the resume text data and improve analysis accuracy improves the accuracy of preprocessing.

[0084] The preprocessing unit can estimate the user's emotions and determine the priority of preprocessing based on the estimated user emotions. For example, the preprocessing unit estimates the user's emotions and determines the priority of preprocessing based on the estimated user emotions. For example, if the user is feeling stressed, the preprocessing unit prioritizes preprocessing of important information. The preprocessing unit can also perform overall preprocessing when the user is relaxed. The preprocessing unit can also quickly preprocess the most important information when the user is in a hurry. This improves the accuracy of preprocessing by determining the priority of preprocessing based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0085] The preprocessing unit can preprocess the resume text data to adjust it according to different industries and job types. For example, the preprocessing unit performs preprocessing to customize the resume text data according to different industries and job types. For example, the preprocessing unit can emphasize programming skills and project experience in a resume for the IT industry. The preprocessing unit can also emphasize medical qualifications and clinical experience in a resume for the medical industry. The preprocessing unit can also emphasize teaching qualifications and teaching experience in a resume for the education industry. In this way, the accuracy of the preprocessing is improved by performing preprocessing to customize the resume text data according to different industries and job types.

[0086] The preprocessing unit can optimize preprocessing by comparing the resume text data with past application histories. The preprocessing unit, for example, optimizes preprocessing by comparing the resume text data with past application histories. The preprocessing unit, for example, compares the resume text data with past application histories and removes duplicate information. The preprocessing unit can also extract important information from past application histories and perform preprocessing. The preprocessing unit can also emphasize the most recent information by comparing the resume text data with past application histories. In this way, optimizing preprocessing by comparing the resume text data with past application histories improves the accuracy of preprocessing.

[0087] The preprocessing unit can preprocess the resume text data based on the candidate's geographical background. For example, the preprocessing unit preprocesses the resume text data based on the candidate's geographical background. For example, the preprocessing unit highlights information about local companies and schools based on the candidate's place of residence. The preprocessing unit can also highlight region-specific skills and experience based on the candidate's geographical background. The preprocessing unit can also highlight information related to the local job market based on the candidate's geographical background. In this way, by preprocessing the resume text data based on the candidate's geographical background, the accuracy of the preprocessing is improved.

[0088] The generation unit can estimate the user's emotion and change the summary presentation method based on the estimated user emotion. For example, the generation unit can estimate the user's emotion and adjust the summary presentation method based on the estimated user emotion. For example, the generation unit can generate a detailed summary when the user is relaxed. The generation unit can also generate a concise summary when the user is in a hurry. The generation unit can also generate a summary that highlights only important information when the user is stressed. This improves the accuracy of the summary by adjusting the summary presentation method based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] The generation unit can analyze each section of the resume and adjust the level of detail of the summary based on its importance. For example, the generation unit analyzes each section of the resume and adjusts the level of detail of the summary based on its importance. For example, if the education section is important, the generation unit generates a detailed summary related to the education section. Also, if the work history section is important, the generation unit can generate a detailed summary related to the work history section. Also, if the skills section is important, the generation unit can generate a detailed summary related to the skills section. In this way, by analyzing each section of the resume and adjusting the level of detail of the summary based on its importance, the accuracy of the summary is improved.

[0090] The generation unit can use different summarization algorithms depending on the content of the resume. For example, the generation unit applies different summarization algorithms depending on the content of the resume. For example, the generation unit applies a summarization algorithm specialized for educational background to a resume with a lot of educational background information. The generation unit can also apply a summarization algorithm specialized for work history to a resume with a lot of work history information. The generation unit can also apply a summarization algorithm specialized for skills to a resume with a lot of skills information. In this way, by applying different summarization algorithms depending on the content of the resume, the accuracy of the summary is improved.

[0091] The generation unit can improve the accuracy of the summary by referring to past summary results of the resume. The generation unit, for example, improves the accuracy of the summary by referring to past summary results of the resume. The generation unit, for example, applies an algorithm that improves the accuracy of the summary based on the past summary results. The generation unit can also improve the accuracy of the summary by extracting important information from the past summary results. The generation unit can also analyze the past summary results and reflect feedback to improve the accuracy of the summary. In this way, the accuracy of the summary is improved by referring to the past summary results of the resume.

[0092] The generation unit can estimate the user's emotion and change the length of the summary based on the estimated user emotion. For example, the generation unit can estimate the user's emotion and adjust the length of the summary based on the estimated user emotion. For example, if the user is in a hurry, the generation unit can generate a short summary that covers the main points. If the user is relaxed, the generation unit can also generate a longer summary that includes detailed explanations. If the user is stressed, the generation unit can also generate a short summary that includes only important information. This improves the accuracy of the summary by adjusting the length of the summary based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] The generation unit can determine the priority of summaries based on the time of submission of the resume. The generation unit determines the priority of summaries based on, for example, the time of submission of the resume. The generation unit, for example, prioritizes summarizing the most recent resume. The generation unit can also summarize resumes that were submitted earlier later. The generation unit can also adjust the order of summaries based on the time of submission. In this way, by determining the priority of summaries based on the time of submission of the resume, the accuracy of summaries is improved.

[0094] The generation unit can change the order of summaries based on the relevance of the resumes. The generation unit, for example, adjusts the order of summaries based on the relevance of the resumes. The generation unit, for example, prioritizes summarizing highly relevant resumes. The generation unit can also postpone summarizing less relevant resumes. The generation unit can also adjust the order of summaries based on the relevance. In this way, adjusting the order of summaries based on the relevance of the resumes improves the accuracy of the summaries.

[0095] The generation unit can adjust the use of technical terms in the resume according to the expertise level of the candidate. For example, the generation unit adjusts the use of technical terms in the resume according to the expertise level of the candidate. For example, the generation unit generates a summary that uses a lot of technical terms for a candidate with high expertise. The generation unit can also generate a summary that uses less technical terms for a candidate with low expertise. The generation unit can also adjust the use of technical terms according to the expertise level. In this way, by adjusting the use of technical terms in the resume according to the expertise level of the candidate, the accuracy of the summary is improved.

[0096] The evaluation unit can estimate the user's emotions and change the evaluation criteria based on the estimated user emotions. For example, the evaluation unit estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions. For example, the evaluation unit applies detailed evaluation criteria when the user is relaxed. The evaluation unit can also apply simple evaluation criteria when the user is in a hurry. The evaluation unit can also apply only important evaluation criteria when the user is stressed. This improves the accuracy of the evaluation by adjusting the evaluation criteria based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The evaluation unit can evaluate the candidate's skill set and depth of experience in detail based on the summarized information. The evaluation unit, for example, evaluates the candidate's skill set and depth of experience in detail based on the summarized information. The evaluation unit, for example, evaluates the candidate's programming skills in detail from the summarized information. The evaluation unit can also evaluate the candidate's project management experience in detail from the summarized information. The evaluation unit can also evaluate the candidate's communication skills in detail from the summarized information. In this way, the accuracy of the evaluation is improved by evaluating the candidate's skill set and depth of experience in detail based on the summarized information.

[0098] The evaluation unit can use different evaluation algorithms depending on the content of the resume. For example, the evaluation unit applies different evaluation algorithms depending on the content of the resume. For example, if programming skills are important, the evaluation unit applies an evaluation algorithm specialized for programming skills. Furthermore, if project management experience is important, the evaluation unit can also apply an evaluation algorithm specialized for project management. Furthermore, if communication skills are important, the evaluation unit can also apply an evaluation algorithm specialized for communication skills. In this way, by applying different evaluation algorithms depending on the content of the resume, the accuracy of the evaluation is improved.

[0099] The evaluation unit can improve the accuracy of the evaluation by referring to past evaluation results. The evaluation unit, for example, improves the accuracy of the evaluation by referring to past evaluation results. The evaluation unit, for example, applies an algorithm that improves the accuracy of the evaluation based on the past evaluation results. The evaluation unit can also improve the accuracy of the evaluation by extracting important information from the past evaluation results. The evaluation unit can also analyze the past evaluation results and reflect feedback to improve the accuracy of the evaluation. In this way, the accuracy of the evaluation is improved by referring to the past evaluation results.

[0100] The evaluation unit can estimate the user's emotions and set the priority of the evaluations based on the estimated user emotions. For example, the evaluation unit estimates the user's emotions and determines the priority of the evaluations based on the estimated user emotions. For example, if the user is relaxed, the evaluation unit can prioritize an overall evaluation. If the user is in a hurry, the evaluation unit can also prioritize evaluations of important skills and experiences. If the user is stressed, the evaluation unit can also prioritize concise evaluations. This improves the accuracy of the evaluations by determining the priority of the evaluations based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] The evaluation unit can weight the evaluation based on the time of submission of the resume. The evaluation unit weights the evaluation based on, for example, the time of submission of the resume. The evaluation unit, for example, prioritizes evaluation of the most recent resume. The evaluation unit can also postpone evaluation of resumes that were submitted earlier. The evaluation unit can also adjust the weight of the evaluation based on the time of submission. In this way, weighting the evaluation based on the time of submission of the resume improves the accuracy of the evaluation.

[0102] The evaluation unit can change the order of evaluation based on the relevance of the resumes. The evaluation unit, for example, adjusts the order of evaluation based on the relevance of the resumes. The evaluation unit, for example, prioritizes evaluation of highly relevant resumes. The evaluation unit can also postpone evaluation of less relevant resumes. The evaluation unit can also adjust the order of evaluation based on the relevance. In this way, adjusting the order of evaluation based on the relevance of the resumes improves the accuracy of the evaluation.

[0103] The evaluation unit can adjust the use of technical terms in the resume according to the candidate's level of expertise. The evaluation unit, for example, adjusts the use of technical terms in the resume according to the candidate's level of expertise. For example, the evaluation unit may perform an evaluation that uses more technical terms for a candidate with high expertise. The evaluation unit may also perform an evaluation that uses less technical terms for a candidate with low expertise. The evaluation unit may also adjust the use of technical terms according to the candidate's level of expertise. In this way, the accuracy of the evaluation is improved by adjusting the use of technical terms in the resume according to the candidate's level of expertise.

[0104] The questioning unit can estimate the user's emotions and change the way the question is phrased based on the estimated user's emotions. For example, the questioning unit estimates the user's emotions and adjusts the way the question is phrased based on the estimated user's emotions. For example, the questioning unit asks detailed questions when the user is relaxed. Furthermore, the questioning unit can ask concise questions when the user is in a hurry. Furthermore, the questioning unit can ask questions that include only important information when the user is stressed. This improves the accuracy of the questions by adjusting the way the question is phrased based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0105] The questioning unit can adjust the level of detail of the questions based on the skills and experience of the candidate. The questioning unit adjusts the level of detail of the questions based on, for example, the skills and experience of the candidate. For example, the questioning unit asks detailed questions to candidates with high skills. The questioning unit can also ask concise questions to candidates with low skills. The questioning unit can also ask questions that include specific examples to candidates with a lot of experience. In this way, adjusting the level of detail of the questions based on the skills and experience of the candidate improves the accuracy of the questions.

[0106] The questioning unit can use different questioning algorithms depending on the content of the candidate's resume. For example, the questioning unit applies different questioning algorithms depending on the content of the candidate's resume. For example, if programming skills are important, the questioning unit applies a questioning algorithm specialized for programming. Furthermore, if project management experience is important, the questioning unit can also apply a questioning algorithm specialized for project management. Furthermore, if communication skills are important, the questioning unit can also apply a questioning algorithm specialized for communication. In this way, by applying different questioning algorithms depending on the content of the candidate's resume, the accuracy of the questions is improved.

[0107] The questioning unit can improve the accuracy of questions by referring to past question results. The questioning unit, for example, improves the accuracy of questions by referring to past question results. The questioning unit, for example, applies an algorithm that improves the accuracy of questions based on past question results. The questioning unit can also improve the accuracy of questions by extracting important information from past question results. The questioning unit can also analyze past question results and reflect feedback to improve the accuracy of questions. In this way, the accuracy of questions is improved by referring to past question results.

[0108] The questioning unit can estimate the user's emotions and change the length of the questions based on the estimated user emotions. For example, the questioning unit estimates the user's emotions and adjusts the length of the questions based on the estimated user emotions. For example, if the user is in a hurry, the questioning unit can ask short, to-the-point questions. If the user is relaxed, the questioning unit can also ask longer questions that include detailed explanations. If the user is stressed, the questioning unit can also ask short questions that include only important information. This improves the accuracy of the questions by adjusting the length of the questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0109] The questioning unit can determine the priority of questions based on the time of submission of the questions. The questioning unit determines the priority of questions based on, for example, the time of submission of the questions. The questioning unit, for example, prioritizes the most recent questions. The questioning unit can also postpone questions that were submitted earlier. The questioning unit can also adjust the order of questions based on the time of submission. In this way, by determining the priority of questions based on the time of submission of the questions, the accuracy of the questions is improved.

[0110] The questioning unit can change the order of questions based on the relevance of the questions. For example, the questioning unit adjusts the order of questions based on the relevance of the questions. For example, the questioning unit prioritizes highly relevant questions. Furthermore, the questioning unit can also postpone asking less relevant questions. Furthermore, the questioning unit can adjust the order of questions based on the relevance. In this way, adjusting the order of questions based on the relevance of the questions improves the accuracy of the questions.

[0111] The questioning unit can adjust the use of technical terms in the questions according to the expertise level of the candidate. For example, the questioning unit adjusts the use of technical terms in the questions according to the expertise level of the candidate. For example, the questioning unit asks questions that use a lot of technical terms to candidates with high expertise. The questioning unit can also ask questions that use less technical terms to candidates with low expertise. The questioning unit can also adjust the use of technical terms according to the expertise level. In this way, by adjusting the use of technical terms in the questions according to the expertise level of the candidate, the accuracy of the questions is improved.

[0112] The response evaluation unit can estimate the user's emotions and change the response evaluation criteria based on the estimated user emotions. For example, the response evaluation unit can estimate the user's emotions and adjust the response evaluation criteria based on the estimated user emotions. For example, the response evaluation unit can apply detailed evaluation criteria when the user is relaxed. The response evaluation unit can also apply simple evaluation criteria when the user is in a hurry. The response evaluation unit can also apply only important evaluation criteria when the user is stressed. This improves the accuracy of the evaluation by adjusting the response evaluation criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0113] The response evaluation unit can analyze the content of the candidate's response in detail and evaluate their communication skills and problem-solving ability. The response evaluation unit, for example, analyzes the content of the candidate's response in detail and evaluates their communication skills, problem-solving ability, etc. The response evaluation unit can evaluate their communication skills and problem-solving ability based on the content of the candidate's response. The response evaluation unit can also use a generation AI to evaluate their communication skills and problem-solving ability based on the content of the candidate's response. For example, the response evaluation unit uses a generation AI to analyze the content of the candidate's response and evaluate their communication skills and problem-solving ability. In this way, by analyzing the content of the candidate's response in detail, the evaluation of their communication skills and problem-solving ability is improved.

[0114] The response evaluation unit can use different evaluation algorithms depending on the content of the response. For example, the response evaluation unit applies different evaluation algorithms depending on the content of the response. For example, if communication skills are important, the response evaluation unit applies an evaluation algorithm specialized for communication. Furthermore, if problem-solving ability is important, the response evaluation unit can also apply an evaluation algorithm specialized for problem solving. Furthermore, if leadership skills are important, the response evaluation unit can also apply an evaluation algorithm specialized for leadership. In this way, by applying different evaluation algorithms depending on the content of the response, the accuracy of the evaluation is improved.

[0115] The response evaluation unit can improve the accuracy of the evaluation by referring to past response evaluation results. The response evaluation unit improves the accuracy of the evaluation by referring to, for example, past response evaluation results. The response evaluation unit applies an algorithm that improves the accuracy of the evaluation based on, for example, past response evaluation results. The response evaluation unit can also improve the accuracy of the evaluation by extracting important information from past response evaluation results. The response evaluation unit can also analyze past response evaluation results and reflect feedback to improve the accuracy of the evaluation. In this way, the accuracy of the evaluation is improved by referring to past response evaluation results.

[0116] The response evaluation unit can estimate the user's emotions and prioritize the response evaluations based on the estimated user emotions. For example, the response evaluation unit estimates the user's emotions and prioritizes the response evaluations based on the estimated user emotions. For example, if the user is relaxed, the response evaluation unit prioritizes an overall evaluation. If the user is in a hurry, the response evaluation unit can also prioritize evaluations of important skills and experiences. If the user is stressed, the response evaluation unit can also prioritize concise evaluations. This improves the accuracy of the evaluations by prioritizing the response evaluations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0117] The response evaluation unit can weight the evaluation based on the time of submission of the response. The response evaluation unit weights the evaluation based on, for example, the time of submission of the response. The response evaluation unit, for example, prioritizes evaluation of the most recent response. The response evaluation unit can also evaluate responses that were submitted earlier later. The response evaluation unit can also adjust the weighting of the evaluation based on the time of submission. Thus, weighting the evaluation based on the time of submission of the response improves the accuracy of the evaluation.

[0118] The response evaluation unit can change the order of evaluation based on the relevance of the responses. The response evaluation unit, for example, adjusts the order of evaluation based on the relevance of the responses. For example, the response evaluation unit prioritizes evaluation of highly relevant responses. The response evaluation unit can also postpone evaluation of less relevant responses. The response evaluation unit can also adjust the order of evaluation based on the relevance. In this way, adjusting the order of evaluation based on the relevance of the responses improves the accuracy of the evaluation.

[0119] The response evaluation unit can adjust the use of technical terms in the response according to the expertise level of the candidate. The response evaluation unit, for example, adjusts the use of technical terms in the response according to the expertise level of the candidate. For example, the response evaluation unit performs an evaluation that uses more technical terms for a candidate with high expertise. The response evaluation unit can also perform an evaluation that uses less technical terms for a candidate with low expertise. The response evaluation unit can also adjust the use of technical terms according to the expertise level. In this way, by adjusting the use of technical terms in the response according to the expertise level of the candidate, the accuracy of the evaluation is improved. === Hard Collateral 1-1 === Each of the multiple elements, including the preprocessing unit, generation unit, evaluation unit, questioning unit, and response evaluation unit, described above, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the preprocessing unit is implemented by the control unit 46A of the smart device 14 and preprocesses resume text data. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the preprocessed text and generates a summary. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the candidate's skills and experience based on the generated summary. The questioning unit is implemented, for example, by the control unit 46A of the smart device 14 and generates questions based on the evaluated information and asks the candidate the questions. The response evaluation unit is implemented, for example, by the control unit 46A of the smart device 14 and evaluates the candidate's responses. === Hard Collateral 1-2 === Each of the multiple elements, including the preprocessing unit, generation unit, evaluation unit, questioning unit, and response evaluation unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the preprocessing unit is implemented by the control unit 46A of the smart glasses 214 and preprocesses resume text data. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the preprocessed text and generates a summary. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the candidate's skills and experience based on the generated summary. The questioning unit is implemented, for example, by the control unit 46A of the smart glasses 214 and generates questions based on the evaluated information and asks the candidate the questions. The response evaluation unit is implemented, for example, by the control unit 46A of the smart glasses 214 and evaluates the candidate's responses. === Hard Collateral 1-3 === Each of the multiple elements, including the preprocessing unit, generation unit, evaluation unit, questioning unit, and response evaluation unit, described above, is implemented, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the preprocessing unit is implemented by the control unit 46A of the headset type terminal 314 and preprocesses text data of the resume. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the preprocessed text and generates a summary. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the candidate's skills and experience based on the generated summary. The questioning unit is implemented, for example, by the control unit 46A of the headset type terminal 314 and generates questions based on the evaluated information and asks the candidate the questions. The response evaluation unit is implemented, for example, by the control unit 46A of the headset type terminal 314 and evaluates the candidate's responses. === Hard Collateral 1-4 === Each of the multiple elements, including the preprocessing unit, generation unit, evaluation unit, questioning unit, and response evaluation unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the preprocessing unit is realized by the control unit 46A of the robot 414 and preprocesses text data of a resume. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the preprocessed text and generates a summary. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the skills and experience of a candidate based on the generated summary. The questioning unit is realized, for example, by the control unit 46A of the robot 414 and generates questions based on the evaluated information and asks the candidate. The response evaluation unit is realized, for example, by the control unit 46A of the robot 414 and evaluates the candidate's responses.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The evaluation department can propose an appropriate training plan based on the candidate's skills and experience. For example, the evaluation department can analyze the candidate's skill set and, if a specific skill is lacking, propose a training plan to improve that skill. The evaluation department can also propose a career path based on the candidate's experience. Furthermore, the evaluation department can introduce an appropriate mentor based on the candidate's skills and experience. In this way, the evaluation department can support the candidate's growth by proposing an appropriate training plan, career path, and mentor based on the candidate's skills and experience.

[0122] The questioning department can adjust the content of the questions by referring to the candidate's past interview results. For example, the questioning department can avoid questions that the candidate found difficult in past interviews. The questioning department can also increase the number of questions related to areas in which the candidate was strong in past interviews. Furthermore, the questioning department can ask questions to check the candidate's growth based on the past interview results. In this way, the questioning department can realize more effective interviews by adjusting the content of the questions by referring to the candidate's past interview results.

[0123] The response evaluation unit can provide appropriate feedback based on the content of the candidate's response. For example, the response evaluation unit can provide feedback on the candidate's communication skills. The response evaluation unit can also provide feedback on the candidate's problem-solving ability. Furthermore, the response evaluation unit can provide feedback pointing out areas for improvement and strengths based on the content of the candidate's response. In this way, the response evaluation unit can support the candidate's growth by providing appropriate feedback based on the content of the candidate's response.

[0124] The preprocessing unit can customize the resume text data based on the candidate's work history. For example, if the candidate has extensive experience in the IT industry, the preprocessing unit can emphasize IT-related skills and project experience. In addition, if the candidate has extensive experience in the medical industry, the preprocessing unit can emphasize medical qualifications and clinical experience. Furthermore, if the candidate has extensive experience in the education industry, the preprocessing unit can emphasize teaching qualifications and teaching experience. In this way, the preprocessing unit can customize the resume text data based on the candidate's work history, thereby improving the accuracy of preprocessing.

[0125] The generation unit can evaluate the suitability of a candidate based on the content of the resume. For example, the generation unit can evaluate whether the candidate is suitable for a specific job based on the content of the resume. The generation unit can also evaluate whether the candidate has a specific skill set based on the content of the resume. Furthermore, the generation unit can evaluate whether the candidate has extensive experience in a specific industry based on the content of the resume. In this way, the generation unit can select an appropriate candidate by evaluating the suitability of the candidate based on the content of the resume.

[0126] The evaluation unit can estimate the user's emotions and provide evaluation feedback based on the estimated user's emotions. For example, the evaluation unit can provide detailed feedback when the user is relaxed. The evaluation unit can also provide brief feedback when the user is in a hurry. Furthermore, the evaluation unit can prioritize providing positive feedback when the user is feeling stressed. In this way, the evaluation unit can improve user satisfaction by providing evaluation feedback based on the user's emotions.

[0127] The questioning unit can estimate the user's emotions and adjust the difficulty of the questions based on the estimated user's emotions. For example, the questioning unit can ask more difficult questions when the user is relaxed. The questioning unit can also ask easier questions when the user is in a hurry. Furthermore, the questioning unit can prioritize questions that are easier for the user to answer when the user is feeling stressed. In this way, the questioning unit can reduce the burden on the user by adjusting the difficulty of the questions based on the user's emotions.

[0128] The response evaluation unit can estimate the user's emotions and provide response evaluation feedback based on the estimated user's emotions. For example, the response evaluation unit can provide detailed feedback when the user is relaxed. The response evaluation unit can also provide concise feedback when the user is in a hurry. Furthermore, the response evaluation unit can prioritize providing positive feedback when the user is feeling stressed. In this way, the response evaluation unit can improve user satisfaction by providing response evaluation feedback based on the user's emotions.

[0129] The preprocessing unit can estimate the user's emotion and adjust the preprocessing procedure based on the estimated user's emotion. For example, the preprocessing unit can perform detailed preprocessing when the user is relaxed. The preprocessing unit can also perform simplified preprocessing when the user is in a hurry. Furthermore, the preprocessing unit can perform preprocessing by focusing on the most important information when the user is feeling stressed. In this way, the preprocessing unit can adjust the preprocessing procedure based on the user's emotion, thereby improving the accuracy of the preprocessing.

[0130] The generation unit can estimate the user's emotion and adjust the content of the summary based on the estimated user's emotion. For example, the generation unit can generate a detailed summary when the user is relaxed. The generation unit can also generate a concise summary when the user is in a hurry. Furthermore, the generation unit can generate a summary that highlights only important information when the user is stressed. In this way, the generation unit can adjust the content of the summary based on the user's emotion, thereby improving the accuracy of the summary.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The preprocessing section preprocesses the resume text. For example, the preprocessing section preprocesses the text data so that it can be analyzed appropriately regardless of the format or content of the resume. Specifically, it performs processes such as text normalization, noise removal, and tokenization. Step 2: The generator analyzes the preprocessed text, extracts important information, and generates a summary. For example, the generator analyzes each section of a resume (educational history, work history, skills, etc.) and outputs a summary of the candidate's highest level of education, most recent work history, key skills, etc. Step 3: The evaluation unit analyzes the resume content based on the summary generated by the generation unit and evaluates the candidate's skills and experience. For example, the evaluation unit evaluates specific programming language skills or project management experience based on the summarized information. Step 4: The questioning unit generates questions based on the information evaluated by the evaluation unit and asks the candidates. For example, the questioning unit uses a generation AI to generate appropriate questions based on the candidate's skills and experience. Step 5: The response evaluation section evaluates the candidate's responses to the questions posed by the questioning section. The response evaluation section evaluates, for example, the candidate's communication skills, problem-solving ability, etc.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] 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.

[0196] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0197] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0198] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0202] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0204] [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a preprocessing unit that preprocesses the resume text; a generation unit that analyzes the text preprocessed by the preprocessing unit, extracts information, and generates a summary; an evaluation unit that analyzes the content of the resume based on the summary generated by the generation unit and evaluates the skills and experience of the candidate; a questioning unit that generates questions based on the information evaluated by the above unit and asks the questions to the candidates; a response evaluation unit that evaluates the candidate's responses to the questions posed by the unit A system characterized by:

2. The pre-treatment unit Preprocess text data so that it can be analyzed regardless of resume format or content 2. The system of claim 1.

3. The generation unit Parse each section of a resume, extract key information, and generate a summary 2. The system of claim 1.

4. The evaluation unit Evaluate candidate skillsets and experience based on summarized information 2. The system of claim 1.

5. The interrogation unit Generative AI generates appropriate questions based on the candidate's skills and experience 2. The system of claim 1.

6. The response evaluation unit Evaluate candidates' communication and problem-solving skills 2. The system of claim 1.

7. The pre-treatment unit Estimate the user's emotions and change the preprocessing method based on the estimated user emotions.

2. The system of claim 1.

8. The pre-treatment unit Automatically detects differences in language and formatting of resumes and selects the most appropriate pre-processing method 2. The system of claim 1.

Images