System

Abstract

To provide a system that automatically selects excellent personnel.SOLUTION: A system according to an embodiment comprises a reception unit, an analysis unit, an evaluation unit, a calculation unit, and a selection unit. The reception unit accepts responses from candidates. The analysis unit analyzes the responses received by the reception unit. The evaluation unit evaluates the responses analyzed by the analysis unit. The calculation unit computes a score based on the evaluation result from the evaluation unit. The selection unit selects excellent personnel based on the score computed by the calculation 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, there is a risk of overlooking talented candidates because interviewers' standards and personal opinions are subject to change when hiring.

[0005] The system according to the embodiment aims to automatically select talented personnel. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, an evaluation unit, a calculation unit, and a selection unit. The reception unit receives answers from candidates. The analysis unit analyzes the answers received by the reception unit. The evaluation unit evaluates the answers analyzed by the analysis unit. The calculation unit calculates a score based on the result of the evaluation by the evaluation unit. The selection unit selects excellent personnel based on the score calculated by the calculation unit. Effect of the Invention

[0007] The system according to the embodiment can automatically select talented personnel. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The recruiting system according to the embodiment of the present invention is a system that uses a generating AI to automate the question and answer session for recruiting and secure excellent talent. This recruiting system starts with a candidate taking an online interview. The candidate answers questions presented by the generating AI. The generating AI analyzes and evaluates the candidate's answers in real time. The evaluation criteria are based on pre-set skills, experience, aptitude, etc. Next, the generating AI comprehensively evaluates the candidate's answers and calculates a score. This score is an objective evaluation of the candidate's aptitude and skills, and can eliminate the interviewer's personal opinion and fluctuations in standards. Furthermore, the generating AI automatically selects excellent talent based on the candidate's score. The selected candidate can proceed to the next selection step. This system can reduce the cost of recruiting and ensure the securing of excellent talent. For example, when a candidate answers the question "What are your strengths?", the generating AI analyzes the answer and evaluates the candidate's strengths. In addition, the generating AI also analyzes the answer to the question "What projects have you participated in in the past?" and evaluates the candidate's experience and skills. In this way, a Q&A system using generative AI can eliminate the interviewer's personal opinions and fluctuations in standards, and can objectively evaluate talented personnel. This makes recruitment more efficient and reduces costs, making it possible to secure talented personnel. This allows the recruitment system to reliably secure talented personnel.

[0029] The human resource recruitment system according to the embodiment includes a reception unit, an analysis unit, an evaluation unit, a calculation unit, and a selection unit. The reception unit receives the answers of the candidates. The answers of the candidates include, for example, text format, audio format, video format, and the like, but are not limited to such examples. The reception unit answers questions presented by the generation AI, for example, when the candidates take an online interview. The analysis unit analyzes the answers received by the reception unit. The analysis unit analyzes the answers of the candidates, for example, using natural language processing technology. The analysis unit can also analyze the emotions of the candidates using emotion analysis technology. For example, the analysis unit analyzes the content, wording, facial expression, tone of voice, and the like of the answers of the candidates. The evaluation unit evaluates the answers analyzed by the analysis unit. The evaluation unit performs evaluation, for example, based on skills, experience, aptitude, and the like set in advance. For example, the evaluation unit performs skill evaluation, aptitude evaluation, experience evaluation, and the like of the candidates. The calculation unit calculates a score based on the results of evaluation by the evaluation unit. The calculation unit calculates the score using, for example, a points system, a ranking system, weighting, or other methods. The selection unit selects excellent personnel based on the score calculated by the calculation unit. The selection unit selects excellent personnel based on, for example, a score threshold or a specific skill set. In this way, the personnel recruitment system according to the embodiment can automatically analyze and evaluate the answers of the candidates, calculate the scores, and select excellent personnel.

[0030] The reception unit receives the answers of the candidates. The answers of the candidates include, for example, text format, audio format, video format, etc., but are not limited to such examples. The reception unit answers questions presented by the generation AI, for example, when the candidate takes an online interview. Specifically, the reception unit receives the answers from the candidates through a web interface or a mobile application. The text format answers are sentences entered by the candidate using a keyboard, and the audio format answers are audio data recorded by the candidate through a microphone. The video format answers are video data recorded by the candidate using a camera, including audio. The reception unit receives these data in real time and stores them in a database. Furthermore, the reception unit appropriately classifies the answer data of the candidates and prepares them so that the analysis unit can efficiently process them. For example, the text data is stored as a character string, the audio data is stored as an audio file, and the video data is stored as a video file. As a result, the reception unit centrally manages answer data in various formats and realizes smooth data provision to the analysis unit. The reception unit also has the function of checking the quality of the candidates' response data and filtering out incomplete or noisy data, allowing the analysis unit to perform analysis based on high-quality data, improving the accuracy and reliability of the entire system.

[0031] The analysis unit analyzes the answers received by the reception unit. The analysis unit analyzes the answers of the candidates using, for example, natural language processing technology. The analysis unit can also analyze the emotions of the candidates using emotion analysis technology. Specifically, the analysis unit uses natural language processing technology to analyze the answers in text format to understand the intentions and contents of the candidates. For example, morphological analysis is performed to analyze grammatical structures and extract keywords and phrases. Furthermore, emotion analysis technology is used to identify the emotions contained in the answers of the candidates. For example, positive emotions, negative emotions, neutral emotions, and the like are classified. For answers in audio format, speech recognition technology is used to convert them into text, and then natural language processing technology is applied. Furthermore, tone, pitch, speed, and the like of the voice are analyzed from the audio data to evaluate the emotions and tension of the candidates. For answers in video format, image recognition technology is used to analyze facial expressions and gestures to evaluate the emotions and attitudes of the candidates. For example, emotions such as joy, surprise, anger, and sadness are identified from facial expressions, and confidence and tension are evaluated from gestures. This allows the analysis unit to analyze the answers of the candidates from multiple angles and extract detailed information. Additionally, the analytics department can compare and analyze candidates' responses with past data and case studies to identify patterns and trends, providing a basis for more accurate assessment of candidates' skills and aptitude.

[0032] The evaluation unit evaluates the answers analyzed by the analysis unit. The evaluation unit performs the evaluation based on, for example, preset skills, experience, aptitude, and the like. Specifically, the evaluation unit performs skill evaluation, aptitude evaluation, experience evaluation, and the like of the candidates based on the data provided by the analysis unit. In the skill evaluation, the technical skills and expertise of the candidates are evaluated, and in the aptitude evaluation, the personality and behavioral characteristics of the candidates are evaluated. In the experience evaluation, the candidate's past work experience and achievements are evaluated. The evaluation unit performs a comprehensive evaluation of the candidates based on these evaluation criteria. For example, in the skill evaluation, programming skills and problem-solving ability are evaluated, and in the aptitude evaluation, leadership and teamwork aptitude are evaluated. In the experience evaluation, past project success cases and achievements are evaluated. The evaluation unit integrates these evaluation results and calculates the overall evaluation of the candidates. Furthermore, the evaluation unit can flexibly adjust the evaluation criteria. For example, the weighting of the evaluation criteria can be changed depending on a specific job type or position. This allows the evaluation unit to perform evaluation according to the characteristics and aptitude of each candidate and provide basic data for selecting the most suitable personnel.

[0033] The calculation unit calculates a score based on the results of the evaluation by the evaluation unit. The calculation unit calculates the score using, for example, a point system, a rank system, weighting, or other methods. Specifically, the calculation unit assigns points to each evaluation item based on the evaluation results provided by the evaluation unit, and calculates a total score. In the point system, a certain number of points is assigned to each evaluation item, and the total score is the total score. In the rank system, a rank is assigned to each evaluation item, and a total score is calculated based on the rank. In the weighting system, different weights are set for each evaluation item, and a total score is calculated based on the weights. For example, a high weight is set for skill evaluation, a medium weight is set for aptitude evaluation, and a low weight is set for experience evaluation. This allows the calculation unit to calculate a score according to the characteristics and aptitude of each candidate. Furthermore, the calculation unit can flexibly adjust the score calculation method. For example, the score calculation method can be changed according to a specific job type or position. This allows the calculation unit to calculate an optimal score according to the characteristics and aptitude of each candidate, and provide basic data for the selection unit to select excellent personnel.

[0034] The selection unit selects excellent human resources based on the scores calculated by the calculation unit. The selection unit selects excellent human resources based on, for example, a score threshold or a specific skill set. Specifically, the selection unit compares the overall evaluations of each candidate based on the scores provided by the calculation unit and selects the most excellent human resources. A score threshold is set, and candidates exceeding the threshold are selected as excellent human resources. Candidates with a specific skill set can also be preferentially selected. For example, candidates who are familiar with a specific programming language or technology are preferentially selected. Furthermore, the selection unit can flexibly adjust the selection criteria. For example, the selection criteria can be changed depending on a specific project or team. This allows the selection unit to select the most suitable human resources for each project or team. The selection unit manages the selection results and keeps records to ensure the transparency and fairness of the recruitment process. This allows the selection unit to efficiently and effectively select excellent human resources and contribute to the growth and development of the company.

[0035] The analysis unit can analyze at least one of the contents, the language, the facial expression, and the tone of the candidate's answer. The analysis unit, for example, analyzes the contents of the candidate's answer. For example, the analysis unit uses natural language processing technology to analyze the contents of the candidate's answer. The analysis unit can also analyze the candidate's language. For example, the analysis unit analyzes the use of honorific language and the use of technical terms. Furthermore, the analysis unit can analyze the candidate's facial expression. For example, the analysis unit uses face recognition technology to analyze the candidate's facial expression. The analysis unit can also analyze the candidate's tone of voice. For example, the analysis unit uses voice analysis technology to analyze the candidate's tone of voice. This allows the analysis unit to analyze the contents, the language, the facial expression, the tone of voice, and the like of the candidate's answer, thereby enabling a more detailed evaluation. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the candidate's answer data to the generation AI and cause the generation AI to execute the analysis of the contents, the language, the facial expression, and the tone of voice of the answer.

[0036] The model unit includes a model unit, and the model unit can use a model that has learned past interview data and industry best practices. The model unit uses, for example, a model that has learned past interview data. Past interview data includes, for example, text data, voice data, video data, etc., but is not limited to such examples. For example, the model unit learns the answer patterns of candidates based on past interview data. The model unit can also use a model that has learned industry best practices. Industry best practices include, for example, success stories and standard evaluation criteria, but are not limited to such examples. For example, the model unit optimizes the evaluation criteria based on industry best practices. As a result, the model unit uses a model that has learned past interview data and industry best practices, thereby improving the accuracy of the evaluation. Part or all of the above-mentioned processing in the model unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the model unit can input past interview data to the generation AI and cause the generation AI to execute model learning.

[0037] The evaluation unit can perform the evaluation based on at least one of the skills, experience, and aptitude set in advance. The evaluation unit performs the evaluation based on the skills set in advance, for example. The skills include, for example, technical skills and soft skills, but are not limited to such examples. For example, the evaluation unit evaluates the technical skills of the candidate. The evaluation unit can also perform the evaluation based on the experience set in advance. The experience includes, for example, work experience and project experience, but are not limited to such examples. For example, the evaluation unit evaluates the work experience of the candidate. Furthermore, the evaluation unit can perform the evaluation based on the aptitude set in advance. The aptitude includes, for example, psychological tests and aptitude tests, but are not limited to such examples. For example, the evaluation unit evaluates the aptitude of the candidate. As a result, the evaluation unit can perform an objective evaluation by performing the evaluation based on the skills, experience, aptitude, and the like set in advance. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the evaluation unit can input data on the skills, experience, and aptitude of the candidate to the generation AI and cause the generation AI to execute the evaluation.

[0038] The calculation unit can calculate a score based on the evaluation result. For example, the calculation unit calculates a score using a points system based on the evaluation result. The points system includes, for example, a method of assigning a score in the range of 0 to 100 points, but is not limited to such an example. For example, the calculation unit calculates a score in the range of 0 to 100 points based on the evaluation result. The calculation unit can also calculate a score using a rank system based on the evaluation result. The rank system includes, for example, a method of assigning an evaluation from A to F, but is not limited to such an example. For example, the calculation unit calculates an evaluation from A to F based on the evaluation result. Furthermore, the calculation unit can also calculate a score by weighting based on the evaluation result. The weighting includes, for example, a method of assigning a different weight to each evaluation item, but is not limited to such an example. For example, the calculation unit calculates a score by assigning a high weight to technical skills. As a result, the calculation unit can objectively evaluate the aptitude and skills of the candidate by calculating a score based on the evaluation result. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the calculation unit can input evaluation result data to the generation AI and cause the generation AI to calculate a score.

[0039] The selection unit can select excellent talent based on the score. The selection unit selects excellent talent based on, for example, a score threshold. The score threshold includes, for example, a method of selecting a candidate with a score of 80 points or more as an excellent talent, but is not limited to such an example. For example, the selection unit selects a candidate with a score of 80 points or more as an excellent talent. The selection unit can also select excellent talent based on a specific skill set. The specific skill set includes, for example, programming skills and project management skills, but is not limited to such an example. For example, the selection unit selects a candidate with programming skills as an excellent talent. In this way, the selection unit can eliminate the interviewer's personal opinion and fluctuation in standards by selecting excellent talent based on the score. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input score data into the generation AI and cause the generation AI to select excellent talent.

[0040] The reception unit can analyze the past interview history of the candidate and select the optimal question. The reception unit, for example, analyzes the past interview history of the candidate. The past interview history includes, for example, the number of interviews, the question content, the evaluation result, and the like, but is not limited to such examples. For example, the reception unit avoids questions that the candidate had difficulty answering in the past and selects questions from a different angle. The reception unit can also present questions that the candidate was good at in the past again to bring out the strengths of the candidate. Furthermore, the reception unit can select questions related to unanswered fields from the past interview history of the candidate. In this way, the reception unit can select more appropriate questions and bring out the strengths of the candidate by analyzing the past interview history of the candidate. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the past interview history data of the candidate to the generation AI and cause the generation AI to select the optimal question.

[0041] The reception unit can customize the questions based on the candidate's current job and field of interest when presenting the questions. The reception unit customizes the questions based on the candidate's current job, for example. The current job includes, for example, job content, job title, and scope of work, but is not limited to such examples. For example, the reception unit presents specific questions related to the candidate's current job. The reception unit can also customize the questions based on the candidate's field of interest. The field of interest includes, for example, past projects and research themes, but is not limited to such examples. For example, the reception unit selects questions that interest the candidate based on the candidate's field of interest. Furthermore, the reception unit can also customize the questions based on the candidate's work experience. The work experience includes, for example, practical experience and project experience, but is not limited to such examples. For example, the reception unit presents questions that are in line with practical work based on the candidate's work experience. As a result, the reception unit can present more specific and relevant questions by customizing the questions based on the candidate's current job and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception department can input data about the candidate's job duties and areas of interest into the generation AI and have the generation AI customize the questions.

[0042] When presenting a question, the reception unit can preferentially present a highly relevant question in consideration of the geographical location information of the candidate. The reception unit presents a question, for example, in consideration of the geographical location information of the candidate. The geographical location information includes, for example, GPS data and address information, but is not limited to such examples. For example, the reception unit presents a question regarding a problem specific to the region based on the geographical location of the candidate. The reception unit can also select a question regarding an industry trend related to the geographical location of the candidate. Furthermore, the reception unit can present a question regarding a culture or custom of the region based on the geographical location of the candidate. Thereby, the reception unit can ask a question regarding a problem or trend specific to the region by presenting a question in consideration of the geographical location information of the candidate. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the candidate to the generation AI and cause the generation AI to select a highly relevant question.

[0043] The reception unit can analyze the social media activity of the candidate and present a related question when presenting a question. The reception unit, for example, analyzes the social media activity of the candidate. The social media activity includes, for example, the content of posts, the number of followers, and engagement, but is not limited to such examples. For example, the reception unit selects an interesting question based on the content of the candidate's social media activities. The reception unit can also present questions related to the candidate's social media comments and posts. Furthermore, the reception unit can select a related question based on the candidate's followers and areas of interest in social media. In this way, the reception unit can ask a question based on the candidate's areas of interest and activity content by analyzing the candidate's social media activities. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the candidate's social media activity data to the generation AI and cause the generation AI to select a related question.

[0044] The analysis unit can improve the accuracy of the analysis when analyzing the answer by taking into account the candidate's past work experience and skill set. The analysis unit performs the analysis by taking into account, for example, the candidate's past work experience. The past work experience includes, for example, the job content, the job title, the scope of work, etc., but is not limited to such examples. For example, the analysis unit performs the analysis by emphasizing related skills based on the candidate's work experience. The analysis unit can also perform the analysis by taking into account the candidate's skill set. The skill set includes, for example, technical skills and soft skills, but is not limited to such examples. For example, the analysis unit evaluates the technical accuracy of the answer based on the candidate's skill set. Furthermore, the analysis unit can also evaluate the practical applicability of the answer by referring to the candidate's past work experience. As a result, the analysis unit improves the accuracy of the analysis by taking into account the candidate's past work experience and skill set. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the candidate's work experience and skill set to the generation AI and cause the generation AI to execute the improvement of the accuracy of the analysis.

[0045] The analysis unit can apply an algorithm for evaluating the consistency of the candidate's answers when analyzing the answers. The analysis unit applies, for example, an algorithm for evaluating the consistency of the candidate's answers. The algorithm includes, for example, a machine learning algorithm and a rule-based algorithm, but is not limited to such examples. For example, the analysis unit applies an algorithm for evaluating whether the candidate's answers are consistent. In addition, the analysis unit can also apply an algorithm for identifying the inconsistency when the candidate's answers are inconsistent. Furthermore, the analysis unit can also apply an algorithm for evaluating the consistency of the candidate's answers and reflecting it in the score. In this way, the analysis unit can evaluate the consistency of the candidate's answers, thereby enabling more accurate analysis. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the candidate's answer data to the generation AI and cause the generation AI to execute the evaluation of consistency.

[0046] The analysis unit can perform the analysis while considering the geographical background of the candidate when analyzing the answer. The analysis unit performs the analysis while considering, for example, the geographical background of the candidate. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the analysis unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The analysis unit can also perform the analysis based on industry trends related to the geographical background of the candidate. Furthermore, the analysis unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This enables the analysis unit to analyze problems and trends specific to the region by considering the geographical background of the candidate. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to execute the analysis.

[0047] The analysis unit can improve the accuracy of the analysis when analyzing the answer by referring to the candidate's related literature and past projects. The analysis unit performs the analysis by referring to, for example, the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the analysis unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The analysis unit can also perform the analysis by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the analysis unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the analysis unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the analysis unit improves the accuracy of the analysis by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the analysis.

[0048] The evaluation unit can improve the accuracy of the evaluation by considering the candidate's past performance and project results at the time of evaluation. The evaluation unit performs the evaluation by considering, for example, the candidate's past performance. The past performance includes, for example, project results and the degree of achievement of work, but is not limited to such examples. For example, the evaluation unit evaluates the candidate by emphasizing related skills based on the candidate's past performance. The evaluation unit can also perform the evaluation by considering the candidate's project results. The project results include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the evaluation unit evaluates the practical applicability of the answer based on the candidate's project results. Furthermore, the evaluation unit can also improve the accuracy of the evaluation by referring to the candidate's past performance and project results. As a result, the evaluation unit improves the accuracy of the evaluation by considering the candidate's past performance and project results. Part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input data on the candidate's past performance and project results to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0049] The evaluation unit can compare the quality and quantity of the answers of the candidates during the evaluation. The evaluation unit, for example, emphasizes the quality of the answers of the candidates and performs the evaluation. The quality of the answers includes, for example, the accuracy of the content and logical consistency, but is not limited to such examples. For example, the evaluation unit emphasizes the quality of the answers of the candidates and highly evaluates detailed answers. The evaluation unit can also emphasize the quantity of the answers of the candidates and perform the evaluation. The quantity of the answers includes, for example, the number of characters of the answers and the number of answers, but is not limited to such examples. For example, the evaluation unit emphasizes the quantity of the answers of the candidates and highly evaluates answers that provide a lot of information. Furthermore, the evaluation unit can comprehensively evaluate the quality and quantity of the answers of the candidates and highly evaluate balanced answers. As a result, the evaluation unit can comprehensively evaluate the quality and quantity of the answers of the candidates, thereby enabling a balanced evaluation. Part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the answer data of the candidates to the generation AI and cause the generation AI to execute the evaluation of the quality and quantity.

[0050] The evaluation unit can perform the evaluation while taking into consideration the geographical background of the candidate. The evaluation unit performs the evaluation while taking into consideration the geographical background of the candidate, for example. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the evaluation unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The evaluation unit can also perform the evaluation based on industry trends related to the geographical background of the candidate. Furthermore, the evaluation unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This enables the evaluation unit to evaluate problems and trends specific to the region by taking into consideration the geographical background of the candidate. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to execute the evaluation.

[0051] The evaluation unit can improve the accuracy of the evaluation by referring to the candidate's related literature and past projects at the time of evaluation. The evaluation unit performs the evaluation by referring to, for example, the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the evaluation unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The evaluation unit can also perform the evaluation by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the evaluation unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the evaluation unit can also evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the evaluation unit improves the accuracy of the evaluation by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0052] The calculation unit can improve the accuracy of the score by considering the candidate's past performance and project results when calculating the score. The calculation unit, for example, calculates the score by considering the candidate's past performance. The past performance includes, for example, project results and the degree of task achievement, but is not limited to such examples. For example, the calculation unit calculates the score by emphasizing related skills based on the candidate's past performance. The calculation unit can also calculate the score by considering the candidate's project results. The project results include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the calculation unit evaluates the practical applicability of the answer based on the candidate's project results. Furthermore, the calculation unit can improve the accuracy of the score by referring to the candidate's past performance and project results. As a result, the calculation unit improves the accuracy of the score by considering the candidate's past performance and project results. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input data on the candidate's past performance and project results to the generation AI and cause the generation AI to execute the improvement of the accuracy of the score.

[0053] The calculation unit can calculate the score by comparing the quality and quantity of the candidate's answer when calculating the score. The calculation unit, for example, calculates the score by placing emphasis on the quality of the candidate's answer. The quality of the answer includes, for example, the accuracy of the content and logical consistency, but is not limited to such examples. For example, the calculation unit places emphasis on the quality of the candidate's answer and highly values ​​detailed answers. The calculation unit can also calculate the score by placing emphasis on the quantity of the candidate's answer. The quantity of the answer includes, for example, the number of characters of the answer and the number of answers, but is not limited to such examples. For example, the calculation unit places emphasis on the quantity of the candidate's answer and highly values ​​answers that provide a lot of information. Furthermore, the calculation unit can comprehensively evaluate the quality and quantity of the candidate's answer and highly value balanced answers. As a result, the calculation unit can comprehensively evaluate the quality and quantity of the candidate's answer to calculate a balanced score. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the candidate's answer data to the generation AI and cause the generation AI to execute the evaluation of the quality and quantity.

[0054] The calculation unit can calculate the score taking into consideration the geographical background of the candidate when calculating the score. The calculation unit calculates the score taking into consideration, for example, the geographical background of the candidate. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the calculation unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The calculation unit can also calculate the score based on industry trends related to the geographical background of the candidate. Furthermore, the calculation unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This makes it possible for the calculation unit to calculate the score regarding problems and trends specific to the region by taking into consideration the geographical background of the candidate. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the calculation unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to calculate the score.

[0055] The calculation unit can improve the accuracy of the score by referring to the candidate's related literature and past projects when calculating the score. The calculation unit, for example, calculates the score by referring to the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the calculation unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The calculation unit can also calculate the score by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the calculation unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the calculation unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the calculation unit improves the accuracy of the score by referring to the candidate's related literature and past projects. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the score.

[0056] The selection unit can improve the accuracy of the selection by considering the past performance and project results of the candidate at the time of selection. The selection unit, for example, makes the selection by considering the past performance of the candidate. The past performance includes, for example, project results and the degree of achievement of the work, but is not limited to such examples. For example, the selection unit selects with emphasis on related skills based on the past performance of the candidate. The selection unit can also make the selection by considering the project results of the candidate. The project results include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the selection unit evaluates the practical applicability of the answer based on the project results of the candidate. Furthermore, the selection unit can improve the accuracy of the selection by referring to the past performance and project results of the candidate. As a result, the selection unit improves the accuracy of the selection by considering the past performance and project results of the candidate. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input data on the past performance and project results of the candidate to the generation AI and cause the generation AI to execute the improvement of the accuracy of the selection.

[0057] The selection unit can make a selection by comparing the quality and quantity of the answers of the candidates. The selection unit, for example, makes a selection by placing emphasis on the quality of the answers of the candidates. The quality of the answers includes, for example, the accuracy of the content and logical consistency, but is not limited to such examples. For example, the selection unit places emphasis on the quality of the answers of the candidates and highly values ​​detailed answers. The selection unit can also make a selection by placing emphasis on the quantity of the answers of the candidates. The quantity of the answers includes, for example, the number of characters of the answers and the number of answers, but is not limited to such examples. For example, the selection unit places emphasis on the quantity of the answers of the candidates and highly values ​​answers that provide a lot of information. Furthermore, the selection unit can comprehensively evaluate the quality and quantity of the answers of the candidates and highly value balanced answers. As a result, the selection unit can comprehensively evaluate the quality and quantity of the answers of the candidates, thereby making it possible to make a balanced selection. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the answer data of the candidates to the generation AI and cause the generation AI to execute the evaluation of the quality and quantity.

[0058] The selection unit can make a selection taking into consideration the geographical background of the candidate. The selection unit makes a selection taking into consideration, for example, the geographical background of the candidate. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the selection unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The selection unit can also make a selection based on industry trends related to the geographical background of the candidate. Furthermore, the selection unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This allows the selection unit to make a selection regarding problems and trends specific to the region by taking into consideration the geographical background of the candidate. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to execute the selection.

[0059] The selection unit can improve the accuracy of the selection by referring to the candidate's related literature and past projects at the time of selection. The selection unit, for example, makes the selection by referring to the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the selection unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The selection unit can also make the selection by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the selection unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the selection unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the selection unit improves the accuracy of the selection by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the selection.

[0060] The model unit can improve the accuracy of the model by referring to past interview data when learning the model. The model unit, for example, learns the model by referring to past interview data. The past interview data includes, for example, text data, audio data, video data, etc., but is not limited to such examples. For example, the model unit learns the answer patterns of the candidates based on the past interview data. The model unit can also optimize the evaluation criteria by referring to the past interview data. Furthermore, the model unit can also improve the prediction accuracy of the model based on the past interview data. As a result, the model unit improves the accuracy of the model by referring to the past interview data. Part or all of the above-mentioned processing in the model unit may be performed, for example, using AI, or may be performed without using AI. For example, the model unit can input past interview data to the generation AI and cause the generation AI to execute model learning.

[0061] The model unit can optimize the model by incorporating industry best practices when learning the model. The model unit, for example, incorporates industry best practices to learn the model. Industry best practices include, but are not limited to, success stories and standard evaluation criteria. For example, the model unit optimizes the evaluation criteria based on industry best practices. The model unit can also select learning data for the model by referring to industry best practices. Furthermore, the model unit can also improve the prediction accuracy of the model by incorporating industry best practices. As a result, the model unit improves the accuracy of the model by incorporating industry best practices. A part or all of the above-mentioned processing in the model unit may be performed, for example, using AI, or may be performed without using AI. For example, the model unit can input industry best practices into the generation AI and cause the generation AI to execute model learning.

[0062] The model unit can select learning data in consideration of the geographical background of the candidate when learning the model. The model unit selects learning data in consideration of the geographical background of the candidate, for example. The geographical background includes, but is not limited to, problems and trends specific to the region. For example, the model unit selects learning data with emphasis on answers regarding problems specific to the region based on the geographical background of the candidate. The model unit can also select learning data based on industry trends related to the geographical background of the candidate. Furthermore, the model unit can also select learning data with emphasis on answers regarding the culture and customs of the region based on the geographical background of the candidate. This enables the model unit to learn about problems and trends specific to the region by considering the geographical background of the candidate. Part or all of the above-mentioned processing in the model unit may be performed, for example, using AI, or may be performed without using AI. For example, the model unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to select the learning data.

[0063] The model unit can improve the accuracy of the model by referring to the candidate's related literature and past projects when learning the model. The model unit, for example, learns the model by referring to the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the model unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The model unit can also learn the model by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the model unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the model unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the model unit improves the accuracy of the model by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the model unit may be performed using, for example, AI, or may be performed without using AI. For example, the model unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the model.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] In addition to the content of the candidate's answers, the analysis unit can also analyze the candidate's non-verbal behavior. For example, the analysis unit can analyze the candidate's gestures and posture to evaluate the candidate's confidence and sincerity. The analysis unit can also analyze the candidate's eye movements to evaluate the candidate's concentration and interest in the questions. Furthermore, the analysis unit can analyze the speed and pauses of the candidate's answers to evaluate the candidate's thought process and stress level. This allows the analysis unit to perform a more multifaceted evaluation by analyzing the candidate's non-verbal behavior.

[0066] The analysis unit can take into account the cultural background of the candidate when analyzing the content of the candidate's answers. For example, the analysis unit interprets the answers by taking into account the cultural characteristics of the candidate's country or region of origin. The analysis unit can also take into account the candidate's native language and language habits, and reflect differences in language usage and expressions in the evaluation. Furthermore, the analysis unit can take into account the candidate's religion and values, and accurately understand the intentions and meanings behind the answers. This allows the analysis unit to make a fair and accurate evaluation by taking into account the candidate's cultural background.

[0067] In addition to the candidate's response data, the Model Department can use the candidate's social media activity as learning data. For example, the Model Department can analyze the candidate's social media posting content, number of followers, and engagement rate to evaluate the candidate's communication skills and influence. The Model Department can also learn the candidate's social media activity patterns and understand the candidate's interests and concerns. Furthermore, the Model Department can evaluate the candidate's values ​​and beliefs based on the candidate's comments and actions on social media. This allows the Model Department to use the candidate's social media activity as learning data, enabling a more comprehensive evaluation.

[0068] In addition to the quality of the candidate's answers, the assessment department can evaluate the candidate's creativity. For example, the assessment department can evaluate the originality and innovation of the ideas and solutions presented by the candidate. The assessment department can also evaluate the originality of the candidate's approach to projects and challenges that he or she has worked on in the past. Furthermore, the assessment department can evaluate the flexible thinking and new perspectives that the candidate showed during the interview. This allows the assessment department to find innovative talent by evaluating the candidates' creativity.

[0069] The calculation unit can evaluate the consistency of the candidate's answers when calculating the candidate's score. For example, the calculation unit can evaluate whether the candidate gives consistent answers to different questions. The calculation unit can also evaluate whether the candidate's answers are consistent with the contents of past interviews and resumes. Furthermore, the calculation unit can evaluate whether the candidate's answers are logically consistent. In this way, the calculation unit can calculate a highly reliable score by evaluating the consistency of the candidate's answers.

[0070] The process flow of the first embodiment will be briefly described below.

[0071] Step 1: The reception unit receives the candidate's answer. The candidate's answer may be in text format, audio format, video format, or the like, but is not limited to such examples. For example, when the candidate takes an online interview, the reception unit answers the questions presented by the generation AI. Step 2: The analysis unit analyzes the answers received by the reception unit. For example, the analysis unit analyzes the answers of the candidates using natural language processing technology. The analysis unit can also analyze the emotions of the candidates using emotion analysis technology. For example, the analysis unit analyzes the content, wording, facial expressions, tone of voice, etc. of the candidates' answers. Step 3: The evaluation unit evaluates the answers analyzed by the analysis unit. The evaluation unit performs evaluation based on, for example, preset skills, experience, aptitude, etc. For example, the evaluation unit performs skill evaluation, aptitude evaluation, experience evaluation, etc. of the candidate. Step 4: The calculation unit calculates a score based on the results of the evaluation by the evaluation unit. The calculation unit calculates the score using a method such as a points system, a ranking system, or a weighting system. Step 5: The selection unit selects talented individuals based on the scores calculated by the calculation unit. The selection unit selects talented individuals based on, for example, a score threshold or a specific skill set.

[0072] (Example 2) The recruiting system according to the embodiment of the present invention is a system that uses a generating AI to automate the question and answer session for recruiting and secure excellent talent. This recruiting system starts with a candidate taking an online interview. The candidate answers questions presented by the generating AI. The generating AI analyzes and evaluates the candidate's answers in real time. The evaluation criteria are based on pre-set skills, experience, aptitude, etc. Next, the generating AI comprehensively evaluates the candidate's answers and calculates a score. This score is an objective evaluation of the candidate's aptitude and skills, and can eliminate the interviewer's personal opinion and fluctuations in standards. Furthermore, the generating AI automatically selects excellent talent based on the candidate's score. The selected candidate can proceed to the next selection step. This system can reduce the cost of recruiting and ensure the securing of excellent talent. For example, when a candidate answers the question "What are your strengths?", the generating AI analyzes the answer and evaluates the candidate's strengths. In addition, the generating AI also analyzes the answer to the question "What projects have you participated in in the past?" and evaluates the candidate's experience and skills. In this way, a Q&A system using generative AI can eliminate the interviewer's personal opinions and fluctuations in standards, and can objectively evaluate talented personnel. This makes recruitment more efficient and reduces costs, making it possible to secure talented personnel. This allows the recruitment system to reliably secure talented personnel.

[0073] The human resource recruitment system according to the embodiment includes a reception unit, an analysis unit, an evaluation unit, a calculation unit, and a selection unit. The reception unit receives the answers of the candidates. The answers of the candidates include, for example, text format, audio format, video format, and the like, but are not limited to such examples. The reception unit answers questions presented by the generation AI, for example, when the candidates take an online interview. The analysis unit analyzes the answers received by the reception unit. The analysis unit analyzes the answers of the candidates, for example, using natural language processing technology. The analysis unit can also analyze the emotions of the candidates using emotion analysis technology. For example, the analysis unit analyzes the content, wording, facial expression, tone of voice, and the like of the answers of the candidates. The evaluation unit evaluates the answers analyzed by the analysis unit. The evaluation unit performs evaluation, for example, based on skills, experience, aptitude, and the like set in advance. For example, the evaluation unit performs skill evaluation, aptitude evaluation, experience evaluation, and the like of the candidates. The calculation unit calculates a score based on the results of evaluation by the evaluation unit. The calculation unit calculates the score using, for example, a points system, a ranking system, weighting, or other methods. The selection unit selects excellent personnel based on the score calculated by the calculation unit. The selection unit selects excellent personnel based on, for example, a score threshold or a specific skill set. In this way, the personnel recruitment system according to the embodiment can automatically analyze and evaluate the answers of the candidates, calculate the scores, and select excellent personnel.

[0074] The reception unit receives the answers of the candidates. The answers of the candidates include, for example, text format, audio format, video format, etc., but are not limited to such examples. The reception unit answers questions presented by the generation AI, for example, when the candidate takes an online interview. Specifically, the reception unit receives the answers from the candidates through a web interface or a mobile application. The text format answers are sentences entered by the candidate using a keyboard, and the audio format answers are audio data recorded by the candidate through a microphone. The video format answers are video data recorded by the candidate using a camera, including audio. The reception unit receives these data in real time and stores them in a database. Furthermore, the reception unit appropriately classifies the answer data of the candidates and prepares them so that the analysis unit can efficiently process them. For example, the text data is stored as a character string, the audio data is stored as an audio file, and the video data is stored as a video file. As a result, the reception unit centrally manages answer data in various formats and realizes smooth data provision to the analysis unit. The reception unit also has the function of checking the quality of the candidates' response data and filtering out incomplete or noisy data, allowing the analysis unit to perform analysis based on high-quality data, improving the accuracy and reliability of the entire system.

[0075] The analysis unit analyzes the answers received by the reception unit. The analysis unit analyzes the answers of the candidates using, for example, natural language processing technology. The analysis unit can also analyze the emotions of the candidates using emotion analysis technology. Specifically, the analysis unit uses natural language processing technology to analyze the answers in text format to understand the intentions and contents of the candidates. For example, morphological analysis is performed to analyze grammatical structures and extract keywords and phrases. Furthermore, emotion analysis technology is used to identify the emotions contained in the answers of the candidates. For example, positive emotions, negative emotions, neutral emotions, and the like are classified. For answers in audio format, speech recognition technology is used to convert them into text, and then natural language processing technology is applied. Furthermore, tone, pitch, speed, and the like of the voice are analyzed from the audio data to evaluate the emotions and tension of the candidates. For answers in video format, image recognition technology is used to analyze facial expressions and gestures to evaluate the emotions and attitudes of the candidates. For example, emotions such as joy, surprise, anger, and sadness are identified from facial expressions, and confidence and tension are evaluated from gestures. This allows the analysis unit to analyze the answers of the candidates from multiple angles and extract detailed information. Additionally, the analytics department can compare and analyze candidates' responses with past data and case studies to identify patterns and trends, providing a basis for more accurate assessment of candidates' skills and aptitude.

[0076] The evaluation unit evaluates the answers analyzed by the analysis unit. The evaluation unit performs the evaluation based on, for example, preset skills, experience, aptitude, and the like. Specifically, the evaluation unit performs skill evaluation, aptitude evaluation, experience evaluation, and the like of the candidates based on the data provided by the analysis unit. In the skill evaluation, the technical skills and expertise of the candidates are evaluated, and in the aptitude evaluation, the personality and behavioral characteristics of the candidates are evaluated. In the experience evaluation, the candidate's past work experience and achievements are evaluated. The evaluation unit performs a comprehensive evaluation of the candidates based on these evaluation criteria. For example, in the skill evaluation, programming skills and problem-solving ability are evaluated, and in the aptitude evaluation, leadership and teamwork aptitude are evaluated. In the experience evaluation, past project success cases and achievements are evaluated. The evaluation unit integrates these evaluation results and calculates the overall evaluation of the candidates. Furthermore, the evaluation unit can flexibly adjust the evaluation criteria. For example, the weighting of the evaluation criteria can be changed depending on a specific job type or position. This allows the evaluation unit to perform evaluation according to the characteristics and aptitude of each candidate and provide basic data for selecting the most suitable personnel.

[0077] The calculation unit calculates a score based on the results of the evaluation by the evaluation unit. The calculation unit calculates the score using, for example, a point system, a rank system, weighting, or other methods. Specifically, the calculation unit assigns points to each evaluation item based on the evaluation results provided by the evaluation unit, and calculates a total score. In the point system, a certain number of points is assigned to each evaluation item, and the total score is the total score. In the rank system, a rank is assigned to each evaluation item, and a total score is calculated based on the rank. In the weighting system, different weights are set for each evaluation item, and a total score is calculated based on the weights. For example, a high weight is set for skill evaluation, a medium weight is set for aptitude evaluation, and a low weight is set for experience evaluation. This allows the calculation unit to calculate a score according to the characteristics and aptitude of each candidate. Furthermore, the calculation unit can flexibly adjust the score calculation method. For example, the score calculation method can be changed according to a specific job type or position. This allows the calculation unit to calculate an optimal score according to the characteristics and aptitude of each candidate, and provide basic data for the selection unit to select excellent personnel.

[0078] The selection unit selects excellent human resources based on the scores calculated by the calculation unit. The selection unit selects excellent human resources based on, for example, a score threshold or a specific skill set. Specifically, the selection unit compares the overall evaluations of each candidate based on the scores provided by the calculation unit and selects the most excellent human resources. A score threshold is set, and candidates exceeding the threshold are selected as excellent human resources. Candidates with a specific skill set can also be preferentially selected. For example, candidates who are familiar with a specific programming language or technology are preferentially selected. Furthermore, the selection unit can flexibly adjust the selection criteria. For example, the selection criteria can be changed depending on a specific project or team. This allows the selection unit to select the most suitable human resources for each project or team. The selection unit manages the selection results and keeps records to ensure the transparency and fairness of the recruitment process. This allows the selection unit to efficiently and effectively select excellent human resources and contribute to the growth and development of the company.

[0079] The analysis unit can analyze at least one of the contents, the language, the facial expression, and the tone of the candidate's answer. The analysis unit, for example, analyzes the contents of the candidate's answer. For example, the analysis unit uses natural language processing technology to analyze the contents of the candidate's answer. The analysis unit can also analyze the candidate's language. For example, the analysis unit analyzes the use of honorific language and the use of technical terms. Furthermore, the analysis unit can analyze the candidate's facial expression. For example, the analysis unit uses face recognition technology to analyze the candidate's facial expression. The analysis unit can also analyze the candidate's tone of voice. For example, the analysis unit uses voice analysis technology to analyze the candidate's tone of voice. This allows the analysis unit to analyze the contents, the language, the facial expression, the tone of voice, and the like of the candidate's answer, thereby enabling a more detailed evaluation. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the candidate's answer data to the generation AI and cause the generation AI to execute the analysis of the contents, the language, the facial expression, and the tone of voice of the answer.

[0080] The model unit includes a model unit, and the model unit can use a model that has learned past interview data and industry best practices. The model unit uses, for example, a model that has learned past interview data. Past interview data includes, for example, text data, voice data, video data, etc., but is not limited to such examples. For example, the model unit learns the answer patterns of candidates based on past interview data. The model unit can also use a model that has learned industry best practices. Industry best practices include, for example, success stories and standard evaluation criteria, but are not limited to such examples. For example, the model unit optimizes the evaluation criteria based on industry best practices. As a result, the model unit uses a model that has learned past interview data and industry best practices, thereby improving the accuracy of the evaluation. Part or all of the above-mentioned processing in the model unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the model unit can input past interview data to the generation AI and cause the generation AI to execute model learning.

[0081] The evaluation unit can perform the evaluation based on at least one of the skills, experience, and aptitude set in advance. The evaluation unit performs the evaluation based on the skills set in advance, for example. The skills include, for example, technical skills and soft skills, but are not limited to such examples. For example, the evaluation unit evaluates the technical skills of the candidate. The evaluation unit can also perform the evaluation based on the experience set in advance. The experience includes, for example, work experience and project experience, but are not limited to such examples. For example, the evaluation unit evaluates the work experience of the candidate. Furthermore, the evaluation unit can perform the evaluation based on the aptitude set in advance. The aptitude includes, for example, psychological tests and aptitude tests, but are not limited to such examples. For example, the evaluation unit evaluates the aptitude of the candidate. As a result, the evaluation unit can perform an objective evaluation by performing the evaluation based on the skills, experience, aptitude, and the like set in advance. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the evaluation unit can input data on the skills, experience, and aptitude of the candidate to the generation AI and cause the generation AI to execute the evaluation.

[0082] The calculation unit can calculate a score based on the evaluation result. For example, the calculation unit calculates a score using a points system based on the evaluation result. The points system includes, for example, a method of assigning a score in the range of 0 to 100 points, but is not limited to such an example. For example, the calculation unit calculates a score in the range of 0 to 100 points based on the evaluation result. The calculation unit can also calculate a score using a rank system based on the evaluation result. The rank system includes, for example, a method of assigning an evaluation from A to F, but is not limited to such an example. For example, the calculation unit calculates an evaluation from A to F based on the evaluation result. Furthermore, the calculation unit can also calculate a score by weighting based on the evaluation result. The weighting includes, for example, a method of assigning a different weight to each evaluation item, but is not limited to such an example. For example, the calculation unit calculates a score by assigning a high weight to technical skills. As a result, the calculation unit can objectively evaluate the aptitude and skills of the candidate by calculating a score based on the evaluation result. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the calculation unit can input evaluation result data to the generation AI and cause the generation AI to calculate a score.

[0083] The selection unit can select excellent talent based on the score. The selection unit selects excellent talent based on, for example, a score threshold. The score threshold includes, for example, a method of selecting a candidate with a score of 80 points or more as an excellent talent, but is not limited to such an example. For example, the selection unit selects a candidate with a score of 80 points or more as an excellent talent. The selection unit can also select excellent talent based on a specific skill set. The specific skill set includes, for example, programming skills and project management skills, but is not limited to such an example. For example, the selection unit selects a candidate with programming skills as an excellent talent. In this way, the selection unit can eliminate the interviewer's personal opinion and fluctuation in standards by selecting excellent talent based on the score. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input score data into the generation AI and cause the generation AI to select excellent talent.

[0084] The reception unit can estimate the candidate's emotion and adjust the order of questions based on the estimated candidate's emotion. The reception unit, for example, estimates the candidate's emotion. The estimation of emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the reception unit estimates the emotion using facial expression data of the candidate captured by a camera. The reception unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the reception unit adjusts the order of questions based on the estimated candidate's emotion. For example, if the candidate is nervous, the reception unit starts with easy questions to relax the candidate. Also, if the candidate is relaxed, more difficult questions can be presented early. Furthermore, if the candidate is impatient, important questions can be postponed and questions to calm the candidate down can be asked first. In this way, the reception unit can promote relaxation of the candidate and elicit more accurate answers by adjusting the order of questions based on the candidate's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input facial expression data and voice data of the candidate to the generation AI and cause the generation AI to estimate the emotion.

[0085] The reception unit can analyze the past interview history of the candidate and select the optimal question. The reception unit, for example, analyzes the past interview history of the candidate. The past interview history includes, for example, the number of interviews, the question content, the evaluation result, and the like, but is not limited to such examples. For example, the reception unit avoids questions that the candidate had difficulty answering in the past and selects questions from a different angle. The reception unit can also present questions that the candidate was good at in the past again to bring out the strengths of the candidate. Furthermore, the reception unit can select questions related to unanswered fields from the past interview history of the candidate. In this way, the reception unit can select more appropriate questions and bring out the strengths of the candidate by analyzing the past interview history of the candidate. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the past interview history data of the candidate to the generation AI and cause the generation AI to select the optimal question.

[0086] The reception unit can customize the questions based on the candidate's current job and field of interest when presenting the questions. The reception unit customizes the questions based on the candidate's current job, for example. The current job includes, for example, job content, job title, and scope of work, but is not limited to such examples. For example, the reception unit presents specific questions related to the candidate's current job. The reception unit can also customize the questions based on the candidate's field of interest. The field of interest includes, for example, past projects and research themes, but is not limited to such examples. For example, the reception unit selects questions that interest the candidate based on the candidate's field of interest. Furthermore, the reception unit can also customize the questions based on the candidate's work experience. The work experience includes, for example, practical experience and project experience, but is not limited to such examples. For example, the reception unit presents questions that are in line with practical work based on the candidate's work experience. As a result, the reception unit can present more specific and relevant questions by customizing the questions based on the candidate's current job and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception department can input data about the candidate's job duties and areas of interest into the generation AI and have the generation AI customize the questions.

[0087] The reception unit can estimate the candidate's emotions and adjust the difficulty of the questions based on the estimated candidate's emotions. The reception unit, for example, estimates the candidate's emotions. The estimation of emotions includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the reception unit estimates the emotions using facial expression data of the candidate captured by a camera. The reception unit can also estimate the emotions using voice data of the candidate recorded by a microphone. Next, the reception unit adjusts the difficulty of the questions based on the estimated candidate's emotions. For example, if the candidate is nervous, the difficulty is gradually increased starting with easy questions. Also, if the candidate is relaxed, a more difficult question can be presented early. Furthermore, if the candidate is impatient, more questions with a lower difficulty level can be asked to calm the candidate down. In this way, the reception unit can promote relaxation of the candidate and elicit more accurate answers by adjusting the difficulty of the questions based on the candidate's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit may input facial expression data and voice data of the candidate to the generation AI and cause the generation AI to estimate emotions.

[0088] When presenting a question, the reception unit can preferentially present a highly relevant question in consideration of the geographical location information of the candidate. The reception unit presents a question, for example, in consideration of the geographical location information of the candidate. The geographical location information includes, for example, GPS data and address information, but is not limited to such examples. For example, the reception unit presents a question regarding a problem specific to the region based on the geographical location of the candidate. The reception unit can also select a question regarding an industry trend related to the geographical location of the candidate. Furthermore, the reception unit can present a question regarding a culture or custom of the region based on the geographical location of the candidate. Thereby, the reception unit can ask a question regarding a problem or trend specific to the region by presenting a question in consideration of the geographical location information of the candidate. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the candidate to the generation AI and cause the generation AI to select a highly relevant question.

[0089] The reception unit can analyze the social media activity of the candidate and present a related question when presenting a question. The reception unit, for example, analyzes the social media activity of the candidate. The social media activity includes, for example, the content of posts, the number of followers, and engagement, but is not limited to such examples. For example, the reception unit selects an interesting question based on the content of the candidate's social media activities. The reception unit can also present questions related to the candidate's social media comments and posts. Furthermore, the reception unit can select a related question based on the candidate's followers and areas of interest in social media. In this way, the reception unit can ask a question based on the candidate's areas of interest and activity content by analyzing the candidate's social media activities. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the candidate's social media activity data to the generation AI and cause the generation AI to select a related question.

[0090] The analysis unit can estimate the candidate's emotions and adjust the answer analysis method based on the estimated candidate's emotions. The analysis unit, for example, estimates the candidate's emotions. The estimation of emotions includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the analysis unit estimates emotions using facial expression data of the candidate captured by a camera. The analysis unit can also estimate emotions using voice data of the candidate recorded by a microphone. Next, the analysis unit adjusts the answer analysis method based on the estimated candidate's emotions. For example, if the candidate is nervous, the content of the answer is emphasized and errors in expression are overlooked. In addition, if the candidate is relaxed, the details and specificity of the answer can be emphasized. Furthermore, if the candidate is impatient, the consistency of the answer can be emphasized and even a short answer can be evaluated. This allows the analysis unit to adjust the answer analysis method based on the candidate's emotions, making it possible to perform more accurate analysis. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and adjust the analysis method.

[0091] The analysis unit can improve the accuracy of the analysis when analyzing the answer by taking into account the candidate's past work experience and skill set. The analysis unit performs the analysis by taking into account, for example, the candidate's past work experience. The past work experience includes, for example, the job content, the job title, the scope of work, etc., but is not limited to such examples. For example, the analysis unit performs the analysis by emphasizing related skills based on the candidate's work experience. The analysis unit can also perform the analysis by taking into account the candidate's skill set. The skill set includes, for example, technical skills and soft skills, but is not limited to such examples. For example, the analysis unit evaluates the technical accuracy of the answer based on the candidate's skill set. Furthermore, the analysis unit can also evaluate the practical applicability of the answer by referring to the candidate's past work experience. As a result, the analysis unit improves the accuracy of the analysis by taking into account the candidate's past work experience and skill set. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the candidate's work experience and skill set to the generation AI and cause the generation AI to execute the improvement of the accuracy of the analysis.

[0092] The analysis unit can apply an algorithm for evaluating the consistency of the candidate's answers when analyzing the answers. The analysis unit applies, for example, an algorithm for evaluating the consistency of the candidate's answers. The algorithm includes, for example, a machine learning algorithm and a rule-based algorithm, but is not limited to such examples. For example, the analysis unit applies an algorithm for evaluating whether the candidate's answers are consistent. In addition, the analysis unit can also apply an algorithm for identifying the inconsistency when the candidate's answers are inconsistent. Furthermore, the analysis unit can also apply an algorithm for evaluating the consistency of the candidate's answers and reflecting it in the score. In this way, the analysis unit can evaluate the consistency of the candidate's answers, thereby enabling more accurate analysis. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the candidate's answer data to the generation AI and cause the generation AI to execute the evaluation of consistency.

[0093] The analysis unit can estimate the candidate's emotion and adjust the display method of the analysis result based on the estimated candidate's emotion. The analysis unit, for example, estimates the candidate's emotion. The estimation of emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the analysis unit estimates the emotion using facial expression data of the candidate captured by a camera. The analysis unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the analysis unit adjusts the display method of the analysis result based on the estimated emotion of the candidate. For example, if the candidate is nervous, a simple and highly visible display method is provided. Also, if the candidate is relaxed, a display method including detailed information can be provided. Furthermore, if the candidate is impatient, a display method that focuses on the main points can be provided. As a result, the analysis unit adjusts the display method of the analysis result based on the candidate's emotion, thereby enabling a display that is easy for the candidate to see. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and adjust the display method.

[0094] The analysis unit can perform the analysis while considering the geographical background of the candidate when analyzing the answer. The analysis unit performs the analysis while considering, for example, the geographical background of the candidate. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the analysis unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The analysis unit can also perform the analysis based on industry trends related to the geographical background of the candidate. Furthermore, the analysis unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This enables the analysis unit to analyze problems and trends specific to the region by considering the geographical background of the candidate. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to execute the analysis.

[0095] The analysis unit can improve the accuracy of the analysis when analyzing the answer by referring to the candidate's related literature and past projects. The analysis unit performs the analysis by referring to, for example, the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the analysis unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The analysis unit can also perform the analysis by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the analysis unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the analysis unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the analysis unit improves the accuracy of the analysis by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the analysis.

[0096] The evaluation unit can estimate the candidate's emotion and adjust the evaluation criteria based on the estimated candidate's emotion. The evaluation unit, for example, estimates the candidate's emotion. The estimation of emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the evaluation unit estimates the emotion using facial expression data of the candidate captured by a camera. The evaluation unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the evaluation unit adjusts the evaluation criteria based on the estimated candidate's emotion. For example, if the candidate is nervous, the content of the answer is emphasized and errors in expression are neglected. In addition, if the candidate is relaxed, the detail and concreteness of the answer can be emphasized. Furthermore, if the candidate is impatient, the consistency of the answer can be emphasized and even a short answer can be evaluated. This allows the evaluation unit to adjust the evaluation criteria based on the candidate's emotion, enabling more accurate evaluation. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processes in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and adjust the evaluation criteria.

[0097] The evaluation unit can improve the accuracy of the evaluation by considering the candidate's past performance and project results at the time of evaluation. The evaluation unit performs the evaluation by considering, for example, the candidate's past performance. The past performance includes, for example, project results and the degree of achievement of work, but is not limited to such examples. For example, the evaluation unit evaluates the candidate by emphasizing related skills based on the candidate's past performance. The evaluation unit can also perform the evaluation by considering the candidate's project results. The project results include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the evaluation unit evaluates the practical applicability of the answer based on the candidate's project results. Furthermore, the evaluation unit can also improve the accuracy of the evaluation by referring to the candidate's past performance and project results. As a result, the evaluation unit improves the accuracy of the evaluation by considering the candidate's past performance and project results. Part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input data on the candidate's past performance and project results to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0098] The evaluation unit can compare the quality and quantity of the answers of the candidates during the evaluation. The evaluation unit, for example, emphasizes the quality of the answers of the candidates and performs the evaluation. The quality of the answers includes, for example, the accuracy of the content and logical consistency, but is not limited to such examples. For example, the evaluation unit emphasizes the quality of the answers of the candidates and highly evaluates detailed answers. The evaluation unit can also emphasize the quantity of the answers of the candidates and perform the evaluation. The quantity of the answers includes, for example, the number of characters of the answers and the number of answers, but is not limited to such examples. For example, the evaluation unit emphasizes the quantity of the answers of the candidates and highly evaluates answers that provide a lot of information. Furthermore, the evaluation unit can comprehensively evaluate the quality and quantity of the answers of the candidates and highly evaluate balanced answers. As a result, the evaluation unit can comprehensively evaluate the quality and quantity of the answers of the candidates, thereby enabling a balanced evaluation. Part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the answer data of the candidates to the generation AI and cause the generation AI to execute the evaluation of the quality and quantity.

[0099] The evaluation unit can estimate the emotion of the candidate and adjust the display method of the evaluation result based on the estimated emotion of the candidate. The evaluation unit, for example, estimates the emotion of the candidate. The estimation of the emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the evaluation unit estimates the emotion using facial expression data of the candidate captured by a camera. The evaluation unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the evaluation unit adjusts the display method of the evaluation result based on the estimated emotion of the candidate. For example, if the candidate is nervous, a simple and highly visible display method is provided. Also, if the candidate is relaxed, a display method including detailed information can be provided. Furthermore, if the candidate is impatient, a display method that focuses on the main points can be provided. As a result, the evaluation unit adjusts the display method of the evaluation result based on the emotion of the candidate, thereby enabling a display that is easy for the candidate to see. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and adjust the display method.

[0100] The evaluation unit can perform the evaluation while taking into consideration the geographical background of the candidate. The evaluation unit performs the evaluation while taking into consideration the geographical background of the candidate, for example. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the evaluation unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The evaluation unit can also perform the evaluation based on industry trends related to the geographical background of the candidate. Furthermore, the evaluation unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This enables the evaluation unit to evaluate problems and trends specific to the region by taking into consideration the geographical background of the candidate. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to execute the evaluation.

[0101] The evaluation unit can improve the accuracy of the evaluation by referring to the candidate's related literature and past projects at the time of evaluation. The evaluation unit performs the evaluation by referring to, for example, the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the evaluation unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The evaluation unit can also perform the evaluation by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the evaluation unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the evaluation unit can also evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the evaluation unit improves the accuracy of the evaluation by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0102] The calculation unit can estimate the candidate's emotion and adjust the score calculation method based on the estimated candidate's emotion. The calculation unit, for example, estimates the candidate's emotion. The estimation of emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the calculation unit estimates the emotion using facial expression data of the candidate captured by a camera. The calculation unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the calculation unit adjusts the score calculation method based on the estimated candidate's emotion. For example, if the candidate is nervous, the content of the answer is emphasized and errors in expression are neglected. In addition, if the candidate is relaxed, the detail and specificity of the answer can be emphasized. Furthermore, if the candidate is impatient, the consistency of the answer can be emphasized and even a short answer can be evaluated. As a result, the calculation unit can adjust the score calculation method based on the candidate's emotion, thereby enabling more accurate score calculation. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the calculation unit may be performed, for example, using AI, or may be performed without using AI. For example, the calculation unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and adjust the score calculation method.

[0103] The calculation unit can improve the accuracy of the score by considering the candidate's past performance and project results when calculating the score. The calculation unit, for example, calculates the score by considering the candidate's past performance. The past performance includes, for example, project results and the degree of task achievement, but is not limited to such examples. For example, the calculation unit calculates the score by emphasizing related skills based on the candidate's past performance. The calculation unit can also calculate the score by considering the candidate's project results. The project results include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the calculation unit evaluates the practical applicability of the answer based on the candidate's project results. Furthermore, the calculation unit can improve the accuracy of the score by referring to the candidate's past performance and project results. As a result, the calculation unit improves the accuracy of the score by considering the candidate's past performance and project results. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input data on the candidate's past performance and project results to the generation AI and cause the generation AI to execute the improvement of the accuracy of the score.

[0104] The calculation unit can calculate the score by comparing the quality and quantity of the candidate's answer when calculating the score. The calculation unit, for example, calculates the score by placing emphasis on the quality of the candidate's answer. The quality of the answer includes, for example, the accuracy of the content and logical consistency, but is not limited to such examples. For example, the calculation unit places emphasis on the quality of the candidate's answer and highly values ​​detailed answers. The calculation unit can also calculate the score by placing emphasis on the quantity of the candidate's answer. The quantity of the answer includes, for example, the number of characters of the answer and the number of answers, but is not limited to such examples. For example, the calculation unit places emphasis on the quantity of the candidate's answer and highly values ​​answers that provide a lot of information. Furthermore, the calculation unit can comprehensively evaluate the quality and quantity of the candidate's answer and highly value balanced answers. As a result, the calculation unit can comprehensively evaluate the quality and quantity of the candidate's answer to calculate a balanced score. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the candidate's answer data to the generation AI and cause the generation AI to execute the evaluation of the quality and quantity.

[0105] The calculation unit can estimate the emotion of the candidate and adjust the display method of the score based on the estimated emotion of the candidate. The calculation unit, for example, estimates the emotion of the candidate. The estimation of the emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the calculation unit estimates the emotion using facial expression data of the candidate captured by a camera. The calculation unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the calculation unit adjusts the display method of the score based on the estimated emotion of the candidate. For example, if the candidate is nervous, a simple and highly visible display method is provided. Also, if the candidate is relaxed, a display method including detailed information can be provided. Furthermore, if the candidate is impatient, a display method that focuses on the main points can be provided. As a result, the calculation unit adjusts the display method of the score based on the emotion of the candidate, thereby enabling a display that is easy for the candidate to see. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and adjust the display method.

[0106] The calculation unit can calculate the score taking into consideration the geographical background of the candidate when calculating the score. The calculation unit calculates the score taking into consideration, for example, the geographical background of the candidate. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the calculation unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The calculation unit can also calculate the score based on industry trends related to the geographical background of the candidate. Furthermore, the calculation unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This makes it possible for the calculation unit to calculate the score regarding problems and trends specific to the region by taking into consideration the geographical background of the candidate. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the calculation unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to calculate the score.

[0107] The calculation unit can improve the accuracy of the score by referring to the candidate's related literature and past projects when calculating the score. The calculation unit, for example, calculates the score by referring to the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the calculation unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The calculation unit can also calculate the score by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the calculation unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the calculation unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the calculation unit improves the accuracy of the score by referring to the candidate's related literature and past projects. A part or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the score.

[0108] The selection unit can estimate the emotion of the candidate and adjust the selection criteria based on the estimated emotion of the candidate. The selection unit, for example, estimates the emotion of the candidate. The estimation of emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the selection unit estimates the emotion using facial expression data of the candidate captured by a camera. The selection unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the selection unit adjusts the selection criteria based on the estimated emotion of the candidate. For example, if the candidate is nervous, the content of the answer is emphasized and mistakes in expression are neglected. In addition, if the candidate is relaxed, the detail and concreteness of the answer can be emphasized. Furthermore, if the candidate is impatient, the consistency of the answer can be emphasized and even a short answer can be evaluated. This allows the selection unit to adjust the selection criteria based on the emotion of the candidate, thereby enabling more accurate selection. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processes in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input facial expression data and voice data of the candidates to the generation AI, and cause the generation AI to estimate emotions and adjust the selection criteria.

[0109] The selection unit can improve the accuracy of the selection by considering the past performance and project results of the candidate at the time of selection. The selection unit, for example, makes the selection by considering the past performance of the candidate. The past performance includes, for example, project results and the degree of achievement of the work, but is not limited to such examples. For example, the selection unit selects with emphasis on related skills based on the past performance of the candidate. The selection unit can also make the selection by considering the project results of the candidate. The project results include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the selection unit evaluates the practical applicability of the answer based on the project results of the candidate. Furthermore, the selection unit can improve the accuracy of the selection by referring to the past performance and project results of the candidate. As a result, the selection unit improves the accuracy of the selection by considering the past performance and project results of the candidate. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input data on the past performance and project results of the candidate to the generation AI and cause the generation AI to execute the improvement of the accuracy of the selection.

[0110] The selection unit can make a selection by comparing the quality and quantity of the answers of the candidates. The selection unit, for example, makes a selection by placing emphasis on the quality of the answers of the candidates. The quality of the answers includes, for example, the accuracy of the content and logical consistency, but is not limited to such examples. For example, the selection unit places emphasis on the quality of the answers of the candidates and highly values ​​detailed answers. The selection unit can also make a selection by placing emphasis on the quantity of the answers of the candidates. The quantity of the answers includes, for example, the number of characters of the answers and the number of answers, but is not limited to such examples. For example, the selection unit places emphasis on the quantity of the answers of the candidates and highly values ​​answers that provide a lot of information. Furthermore, the selection unit can comprehensively evaluate the quality and quantity of the answers of the candidates and highly value balanced answers. As a result, the selection unit can comprehensively evaluate the quality and quantity of the answers of the candidates, thereby making it possible to make a balanced selection. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the answer data of the candidates to the generation AI and cause the generation AI to execute the evaluation of the quality and quantity.

[0111] The selection unit can estimate the emotion of the candidate and adjust the display method of the selection result based on the estimated emotion of the candidate. The selection unit, for example, estimates the emotion of the candidate. The estimation of the emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the selection unit estimates the emotion using facial expression data of the candidate captured by a camera. The selection unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the selection unit adjusts the display method of the selection result based on the estimated emotion of the candidate. For example, if the candidate is nervous, a simple and highly visible display method is provided. Also, if the candidate is relaxed, a display method including detailed information can be provided. Furthermore, if the candidate is impatient, a display method that focuses on the main points can be provided. As a result, the selection unit adjusts the display method of the selection result based on the emotion of the candidate, thereby enabling a display that is easy for the candidate to see. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input facial expression data and voice data of the candidates to the generation AI, and cause the generation AI to estimate emotions and adjust the display method.

[0112] The selection unit can make a selection taking into consideration the geographical background of the candidate. The selection unit makes a selection taking into consideration, for example, the geographical background of the candidate. The geographical background includes, for example, problems and trends specific to the region, but is not limited to such examples. For example, the selection unit emphasizes answers regarding problems specific to the region based on the geographical background of the candidate. The selection unit can also make a selection based on industry trends related to the geographical background of the candidate. Furthermore, the selection unit can evaluate answers regarding the culture and customs of the region based on the geographical background of the candidate. This allows the selection unit to make a selection regarding problems and trends specific to the region by taking into consideration the geographical background of the candidate. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to execute the selection.

[0113] The selection unit can improve the accuracy of the selection by referring to the candidate's related literature and past projects at the time of selection. The selection unit, for example, makes the selection by referring to the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the selection unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The selection unit can also make the selection by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the selection unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the selection unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the selection unit improves the accuracy of the selection by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the selection.

[0114] The model unit can estimate the candidate's emotion and select learning data of the model based on the estimated candidate's emotion. The model unit, for example, estimates the candidate's emotion. The estimation of emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the model unit estimates the emotion using facial expression data of the candidate captured by a camera. The model unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the model unit selects learning data of the model based on the estimated emotion of the candidate. For example, if the candidate is nervous, the learning data is selected with emphasis on answers in a relaxed state. Also, if the candidate is relaxed, the learning data can be selected with emphasis on detailed answers. Furthermore, if the candidate is impatient, the learning data can be selected with emphasis on consistent answers. As a result, the model unit can select the learning data of the model based on the candidate's emotion, thereby enabling more accurate model learning. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the model unit may be performed using, for example, AI, or may be performed without using AI. For example, the model unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and select learning data.

[0115] The model unit can improve the accuracy of the model by referring to past interview data when learning the model. The model unit, for example, learns the model by referring to past interview data. The past interview data includes, for example, text data, audio data, video data, etc., but is not limited to such examples. For example, the model unit learns the answer patterns of the candidates based on the past interview data. The model unit can also optimize the evaluation criteria by referring to the past interview data. Furthermore, the model unit can also improve the prediction accuracy of the model based on the past interview data. As a result, the model unit improves the accuracy of the model by referring to the past interview data. Part or all of the above-mentioned processing in the model unit may be performed, for example, using AI, or may be performed without using AI. For example, the model unit can input past interview data to the generation AI and cause the generation AI to execute model learning.

[0116] The model unit can optimize the model by incorporating industry best practices when learning the model. The model unit, for example, incorporates industry best practices to learn the model. Industry best practices include, but are not limited to, success stories and standard evaluation criteria. For example, the model unit optimizes the evaluation criteria based on industry best practices. The model unit can also select learning data for the model by referring to industry best practices. Furthermore, the model unit can also improve the prediction accuracy of the model by incorporating industry best practices. As a result, the model unit improves the accuracy of the model by incorporating industry best practices. A part or all of the above-mentioned processing in the model unit may be performed, for example, using AI, or may be performed without using AI. For example, the model unit can input industry best practices into the generation AI and cause the generation AI to execute model learning.

[0117] The model unit can estimate the candidate's emotion and adjust the learning frequency of the model based on the estimated candidate's emotion. The model unit, for example, estimates the candidate's emotion. The estimation of emotion includes, for example, techniques such as facial expression analysis and voice analysis, but is not limited to such examples. For example, the model unit estimates the emotion using facial expression data of the candidate captured by a camera. The model unit can also estimate the emotion using voice data of the candidate recorded by a microphone. Next, the model unit adjusts the learning frequency of the model based on the estimated emotion of the candidate. For example, if the candidate is nervous, the learning frequency can be adjusted by placing emphasis on answers given in a relaxed state. In addition, if the candidate is relaxed, the learning frequency can also be adjusted by placing emphasis on detailed answers. Furthermore, if the candidate is impatient, the learning frequency can also be adjusted by placing emphasis on consistent answers. As a result, the model unit adjusts the learning frequency of the model based on the candidate's emotion, thereby enabling more accurate model learning. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the model unit may be performed using, for example, AI, or may be performed without using AI. For example, the model unit may input facial expression data and voice data of the candidate to the generation AI, and cause the generation AI to estimate emotions and adjust the learning frequency.

[0118] The model unit can select learning data in consideration of the geographical background of the candidate when learning the model. The model unit selects learning data in consideration of the geographical background of the candidate, for example. The geographical background includes, but is not limited to, problems and trends specific to the region. For example, the model unit selects learning data with emphasis on answers regarding problems specific to the region based on the geographical background of the candidate. The model unit can also select learning data based on industry trends related to the geographical background of the candidate. Furthermore, the model unit can also select learning data with emphasis on answers regarding the culture and customs of the region based on the geographical background of the candidate. This enables the model unit to learn about problems and trends specific to the region by considering the geographical background of the candidate. Part or all of the above-mentioned processing in the model unit may be performed, for example, using AI, or may be performed without using AI. For example, the model unit can input the geographical background data of the candidate to the generation AI and cause the generation AI to select the learning data.

[0119] The model unit can improve the accuracy of the model by referring to the candidate's related literature and past projects when learning the model. The model unit, for example, learns the model by referring to the candidate's related literature. The related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the model unit evaluates the accuracy of the answer by referring to the related literature mentioned by the candidate. The model unit can also learn the model by referring to the candidate's past projects. The past projects include, for example, project deliverables and evaluation results, but are not limited to such examples. For example, the model unit evaluates the practical applicability of the answer by referring to the candidate's past projects. Furthermore, the model unit can evaluate the depth and detail of the answer based on the candidate's related literature and projects. As a result, the model unit improves the accuracy of the model by referring to the candidate's related literature and past projects. Part or all of the above-mentioned processing in the model unit may be performed using, for example, AI, or may be performed without using AI. For example, the model unit can input the candidate's related literature and data of past projects into the generation AI and cause the generation AI to execute the improvement of the accuracy of the model.

[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] In addition to the content of the candidate's answers, the analysis unit can also analyze the candidate's non-verbal behavior. For example, the analysis unit can analyze the candidate's gestures and posture to evaluate the candidate's confidence and sincerity. The analysis unit can also analyze the candidate's eye movements to evaluate the candidate's concentration and interest in the questions. Furthermore, the analysis unit can analyze the speed and pauses of the candidate's answers to evaluate the candidate's thought process and stress level. This allows the analysis unit to perform a more multifaceted evaluation by analyzing the candidate's non-verbal behavior.

[0122] The analysis unit can take into account the cultural background of the candidate when analyzing the content of the candidate's answers. For example, the analysis unit interprets the answers by taking into account the cultural characteristics of the candidate's country or region of origin. The analysis unit can also take into account the candidate's native language and language habits, and reflect differences in language usage and expressions in the evaluation. Furthermore, the analysis unit can take into account the candidate's religion and values, and accurately understand the intentions and meanings behind the answers. This allows the analysis unit to make a fair and accurate evaluation by taking into account the candidate's cultural background.

[0123] In addition to the candidate's response data, the Model Department can use the candidate's social media activity as learning data. For example, the Model Department can analyze the candidate's social media posting content, number of followers, and engagement rate to evaluate the candidate's communication skills and influence. The Model Department can also learn the candidate's social media activity patterns and understand the candidate's interests and concerns. Furthermore, the Model Department can evaluate the candidate's values ​​and beliefs based on the candidate's comments and actions on social media. This allows the Model Department to use the candidate's social media activity as learning data, enabling a more comprehensive evaluation.

[0124] In addition to the quality of the candidate's answers, the assessment department can evaluate the candidate's creativity. For example, the assessment department can evaluate the originality and innovation of the ideas and solutions presented by the candidate. The assessment department can also evaluate the originality of the candidate's approach to projects and challenges that he or she has worked on in the past. Furthermore, the assessment department can evaluate the flexible thinking and new perspectives that the candidate showed during the interview. This allows the assessment department to find innovative talent by evaluating the candidates' creativity.

[0125] The calculation unit can evaluate the consistency of the candidate's answers when calculating the candidate's score. For example, the calculation unit can evaluate whether the candidate gives consistent answers to different questions. The calculation unit can also evaluate whether the candidate's answers are consistent with the contents of past interviews and resumes. Furthermore, the calculation unit can evaluate whether the candidate's answers are logically consistent. In this way, the calculation unit can calculate a highly reliable score by evaluating the consistency of the candidate's answers.

[0126] The reception department can estimate the candidate's emotions and adjust the speed of the interview based on the estimated emotions of the candidate. For example, if the candidate is nervous, the interview can be slowed down to allow the candidate to relax. Also, if the candidate is relaxed, the interview can be sped up to make the interview more efficient. Furthermore, if the candidate is impatient, the interview can be temporarily stopped to give the candidate time to calm down. In this way, the reception department can maximize the candidate's performance by adjusting the speed of the interview based on the candidate's emotions.

[0127] The analysis unit can estimate the candidate's emotions and adjust the answer analysis method based on the estimated candidate's emotions. For example, if the candidate is nervous, the content of the answer can be emphasized and mistakes in expression can be overlooked. Also, if the candidate is relaxed, the detail and specificity of the answer can be emphasized. Furthermore, if the candidate is in a hurry, the consistency of the answer can be emphasized and even short answers can be evaluated. This allows the analysis unit to adjust the answer analysis method based on the candidate's emotions, making it possible to perform more accurate analysis.

[0128] The evaluation unit can estimate the candidate's emotions and adjust the evaluation criteria based on the estimated emotions of the candidate. For example, if the candidate is nervous, the evaluation unit can emphasize the content of the answer and downplay mistakes in expression. If the candidate is relaxed, the evaluation unit can emphasize the detail and specificity of the answer. Furthermore, if the candidate is in a hurry, the evaluation unit can emphasize the consistency of the answer and evaluate even short answers. This allows the evaluation unit to perform more accurate evaluation by adjusting the evaluation criteria based on the candidate's emotions.

[0129] The calculation unit can estimate the emotions of the candidate and adjust the score calculation method based on the estimated emotions of the candidate. For example, if the candidate is nervous, the content of the answer can be emphasized and mistakes in expression can be overlooked. Also, if the candidate is relaxed, the detail and specificity of the answer can be emphasized. Furthermore, if the candidate is in a hurry, the consistency of the answer can be emphasized and even short answers can be evaluated. In this way, the calculation unit can adjust the score calculation method based on the emotions of the candidate to calculate the score more accurately.

[0130] The selection unit can estimate the emotions of the candidates and adjust the selection criteria based on the estimated emotions of the candidates. For example, if the candidate is nervous, the selection unit can emphasize the content of the answer and disregard mistakes in expression. Also, if the candidate is relaxed, the selection unit can emphasize the detail and specificity of the answer. Furthermore, if the candidate is in a hurry, the selection unit can emphasize the consistency of the answer and evaluate even short answers. This allows the selection unit to make more accurate selections by adjusting the selection criteria based on the emotions of the candidates.

[0131] The process flow of the second embodiment will be briefly described below.

[0132] Step 1: The reception unit receives the candidate's answer. The candidate's answer may be in text format, audio format, video format, or the like, but is not limited to such examples. For example, when the candidate takes an online interview, the reception unit answers the questions presented by the generation AI. Step 2: The analysis unit analyzes the answers received by the reception unit. For example, the analysis unit analyzes the answers of the candidates using natural language processing technology. The analysis unit can also analyze the emotions of the candidates using emotion analysis technology. For example, the analysis unit analyzes the content, wording, facial expressions, tone of voice, etc. of the candidates' answers. Step 3: The evaluation unit evaluates the answers analyzed by the analysis unit. The evaluation unit performs evaluation based on, for example, preset skills, experience, aptitude, etc. For example, the evaluation unit performs skill evaluation, aptitude evaluation, experience evaluation, etc. of the candidate. Step 4: The calculation unit calculates a score based on the results of the evaluation by the evaluation unit. The calculation unit calculates the score using a method such as a points system, a ranking system, or a weighting system. Step 5: The selection unit selects talented individuals based on the scores calculated by the calculation unit. The selection unit selects talented individuals based on, for example, a score threshold or a specific skill set.

[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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0135] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements including the above-mentioned reception unit, analysis unit, evaluation unit, calculation unit, selection unit, and model unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives the answers of the candidates. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the answers of the candidates. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the analyzed answers. The calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a score based on the evaluation result. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects excellent personnel based on the calculated score. The model unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a model that has learned past interview data and industry best practices. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes 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, the RAM 30, and the 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 the voice according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average 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 performed in a secure state.

[0144] Fig. 4 shows an example of 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements including the above-mentioned reception unit, analysis unit, evaluation unit, calculation unit, selection unit, and model unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives the answers of the candidates. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the answers of the candidates. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the analyzed answers. The calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a score based on the evaluation result. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects excellent personnel based on the calculated score. The model unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a model that has learned past interview data and industry best practices. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes 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, the RAM 30, and the 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 the voice according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average 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 performed 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0163] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) 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 voice indicating a user input for 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.

[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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0168] Each of the multiple elements including the above-mentioned reception unit, analysis unit, evaluation unit, calculation unit, selection unit, and model unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives the answers of the candidates. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the answers of the candidates. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the analyzed answers. The calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a score based on the evaluation result. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects excellent personnel based on the calculated score. The model unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a model that has learned past interview data and industry best practices. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes 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, a 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, the RAM 30, and the 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 the voice according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of 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 performed in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0180] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) 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 a voice indicating a user input for 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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] Each of the multiple elements including the above-mentioned reception unit, analysis unit, evaluation unit, calculation unit, selection unit, and model unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives the answers of the candidates. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the answers of the candidates. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the analyzed answers. The calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a score based on the evaluation result. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects excellent personnel based on the calculated score. The model unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a model that has learned past interview data and industry best practices. The correspondence between each unit and the device and control unit is not limited to the above-mentioned example, and various changes are possible.

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

[0187] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in 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 of emotion map 400 and usually 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 inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

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

[0192] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," 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 Universal Serial Bus (USB) 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] In addition, 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 upon 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] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0198] The hardware resource that executes the specific process may be one of these various processors, or may be 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 configuration using one 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 configuration using a processor that realizes the functions of the 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, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

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

[0202] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

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

[0204] (Appendix 1) a reception unit for receiving answers from candidates; an analysis unit that analyzes the answer received by the reception unit; an evaluation unit that evaluates the answer analyzed by the analysis unit; A calculation unit that calculates a score based on a result of the evaluation by the evaluation unit; A selection unit that selects excellent personnel based on the score calculated by the calculation unit. A system characterized by: (Appendix 2) The analysis unit analyzes at least one of the content, the wording, the facial expression, and the tone of the candidate's answer. 2. The system of claim 1, (Appendix 3) Equipped with a model section, The modeling department uses models that have been trained using past interview data and industry best practices. 2. The system of claim 1, (Appendix 4) The evaluation unit performs evaluation based on at least one of preset skills, experience, and aptitude. 2. The system of claim 1, (Appendix 5) The calculation unit is Calculate a score based on the evaluation results 2. The system of claim 1, (Appendix 6) The selection unit is Select top talent based on scores 2. The system of claim 1, (Appendix 7) The reception unit is Estimate candidate sentiment and adjust question order based on estimated candidate sentiment 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the candidate's past interview history and select the most appropriate questions 2. The system of claim 1, (Appendix 9) The reception unit is Customize questions based on the candidate's current job role and interests 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the candidate's sentiment and adjust the difficulty of questions based on the estimated candidate's sentiment 2. The system of claim 1, (Appendix 11) The reception unit is When presenting questions, the system takes into account the candidate's geographic location to prioritize the most relevant questions 2. The system of claim 1, (Appendix 12) The reception unit is When presenting questions, analyze candidates' social media activity and present relevant questions 2. The system of claim 1, (Appendix 13) The analysis unit is Inferring candidate sentiment and adjusting answer analysis based on the inferred candidate sentiment 2. The system of claim 1, (Appendix 14) The analysis unit is When analyzing responses, the accuracy of the analysis can be improved by taking into account the candidate's past work experience and skill set. 2. The system of claim 1, (Appendix 15) The analysis unit is During answer analysis, we apply algorithms to evaluate the consistency of the candidate's answers. 2. The system of claim 1, (Appendix 16) The analysis unit is Estimate candidate sentiment and adjust how analysis results are displayed based on the estimated candidate sentiment 2. The system of claim 1, (Appendix 17) The analysis unit is When analyzing responses, consider the geographical background of the candidates. 2. The system of claim 1, (Appendix 18) The analysis unit is When analyzing answers, we refer to the candidate's related literature and past projects to improve the accuracy of the analysis. 2. The system of claim 1, (Appendix 19) The evaluation unit is Inferring the candidate's sentiment and adjusting the evaluation criteria based on the inferred candidate's sentiment 2. The system of claim 1, (Appendix 20) The evaluation unit is Improve the accuracy of evaluation by considering candidates' past performance and project results during evaluation 2. The system of claim 1, (Appendix 21) The evaluation unit is During the assessment, the quality and quantity of the candidates' answers are compared and assessed. 2. The system of claim 1, (Appendix 22) The evaluation unit is Inferring the candidate's sentiment and adjusting how the assessment results are presented based on the inferred candidate's sentiment 2. The system of claim 1, (Appendix 23) The evaluation unit is During the evaluation, the geographical background of the candidates will be taken into consideration. 2. The system of claim 1, (Appendix 24) The evaluation unit is During the evaluation, we refer to the candidate's relevant literature and past projects to improve the accuracy of the evaluation. 2. The system of claim 1, (Appendix 25) The calculation unit is Inferring candidate sentiment and adjusting the scoring methodology based on the estimated candidate sentiment 2. The system of claim 1, (Appendix 26) The calculation unit is Improve the accuracy of the score by considering the candidate's past performance and project results when calculating the score 2. The system of claim 1, (Appendix 27) The calculation unit is When calculating the score, the quality and quantity of the candidate's answers are compared to calculate the score. 2. The system of claim 1, (Appendix 28) The calculation unit is Estimate candidate sentiment and adjust how the score is displayed based on the estimated candidate sentiment 2. The system of claim 1, (Appendix 29) The calculation unit is The geographical location of the candidate is taken into account when calculating the score. 2. The system of claim 1, (Appendix 30) The calculation unit is When calculating the score, we refer to the candidate's related literature and past projects to improve the accuracy of the score. 2. The system of claim 1, (Appendix 31) The selection unit is Estimate the sentiment of candidates and adjust selection criteria based on the estimated sentiment of candidates 2. The system of claim 1, (Appendix 32) The selection unit is Improve the accuracy of selection by considering candidates' past performance and project results during selection. 2. The system of claim 1, (Appendix 33) The selection unit is At the time of selection, the selection will be made by comparing the quality and quantity of the candidates' answers. 2. The system of claim 1, (Appendix 34) The selection unit is Inferring candidate sentiment and adjusting how selection results are presented based on the inferred candidate sentiment 2. The system of claim 1, (Appendix 35) The selection unit is At the time of selection, the geographical background of the candidates will be taken into consideration. 2. The system of claim 1, (Appendix 36) The selection unit is When selecting candidates, we refer to their related literature and past projects to improve the accuracy of our selection process. 2. The system of claim 1, (Appendix 37) The model unit includes: Estimate the candidate's emotions and select model training data based on the estimated candidate's emotions. 3. The system of claim 2, (Appendix 38) The model unit includes: When training a model, refer to past interview data to improve the model's accuracy. 3. The system of claim 2, (Appendix 39) The model unit includes: Incorporate industry best practices into model training to optimize your models 3. The system of claim 2, (Appendix 40) The model unit includes: Estimate the candidate's sentiment and adjust the model's training frequency based on the estimated candidate's sentiment 3. The system of claim 2, (Appendix 41) The model unit includes: When training the model, the training data is selected taking into account the geographical background of the candidates. 3. The system of claim 2, (Appendix 42) The model unit includes: When training the model, refer to the candidate's related literature and past projects to improve the model's accuracy. 3. The system of claim 2, [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 reception unit for receiving answers from candidates; an analysis unit that analyzes the answer received by the reception unit; an evaluation unit that evaluates the answer analyzed by the analysis unit; A calculation unit that calculates a score based on a result of the evaluation by the evaluation unit; A selection unit that selects excellent personnel based on the score calculated by the calculation unit. A system characterized by:

2. The analysis unit analyzes at least one of the content, the wording, the facial expression, and the tone of the candidate's answer.

2. The system of claim 1 .

3. Equipped with a model section, The modeling department uses models that have been trained using past interview data and industry best practices.

2. The system of claim 1 .

4. The evaluation unit performs evaluation based on at least one of preset skills, experience, and aptitude.

2. The system of claim 1 .

5. The reception unit is Estimate candidate sentiment and adjust question order based on estimated candidate sentiment 2. The system of claim 1 .

6. The reception unit is Analyze the candidate's past interview history and select the most appropriate questions 2. The system of claim 1 .

7. The reception unit is Customize questions based on the candidate's current job role and interests 2. The system of claim 1 .

Images