system

Abstract

The system according to this embodiment aims to accurately understand a candidate's thinking style, personality, strengths, and characteristics, and to consider appropriate placements and roles. [Solution] The system according to the embodiment comprises an analysis unit, an evaluation unit, a selection unit, an assignment unit, and a recording unit. The analysis unit analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The evaluation unit evaluates the candidate's strengths and characteristics based on the results analyzed by the analysis unit. The selection unit selects appropriate second interviewers based on the evaluation results obtained by the evaluation unit. The assignment unit considers the optimal assignment location and role according to the candidate's personality and skills based on the evaluation results obtained by the evaluation unit. The recording unit records the conversation with the candidate and saves it as data that can be re-evaluated and compared later.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to accurately grasp the thinking style, personality, strengths and characteristics of candidates in an interview and consider appropriate assignment destinations and roles.

[0005] The system according to the embodiment aims to accurately grasp the thinking style, personality, strengths and characteristics of candidates and consider appropriate assignment destinations and roles.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an evaluation unit, a selection unit, an assignment unit, and a recording unit. The analysis unit analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The evaluation unit evaluates the candidate's strengths and characteristics based on the results analyzed by the analysis unit. The selection unit selects appropriate second interviewers based on the evaluation results obtained by the evaluation unit. The assignment unit considers the optimal assignment location and role according to the candidate's personality and skills based on the evaluation results obtained by the evaluation unit. The recording unit records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. [Effects of the Invention]

[0007] The system according to this embodiment can accurately grasp a candidate's thinking style, personality, strengths, and characteristics, and consider appropriate placements and roles. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An interview system according to an embodiment of the present invention is an interview system using an AI agent. This interview system can analyze a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, determine their authenticity, and make accurate evaluations. This allows for accurate understanding of a candidate's strengths and characteristics, enabling not only the selection of appropriate second-round interviewers but also consideration of the optimal placement and role. For example, the interview system can identify the most suitable position within the organization, maximize potential, and assess compatibility and synergy with existing employees, based on the candidate's personality and skills. The greatest advantage of this idea is that it allows for dialogue with candidates without being constrained by time or location. Candidates can proceed with the dialogue at their own pace and make effective use of their time. Furthermore, the interview system records the dialogue with the candidate, allowing for later re-evaluation and comparison. This enables interviewers to review the information and make more appropriate decisions. Moreover, the dialogue conducted by the interview system is consistent and objective. Candidates can receive a fair evaluation and are less susceptible to subjective bias. Such objective evaluation leads to a fairer recruitment process. The interview system consists of the following steps: First, the candidate begins a dialogue with the AI ​​agent. The AI ​​agent analyzes the candidate's thinking style, personality, facial expressions, and tone of voice to determine the truthfulness of their responses. Next, based on the analysis, the AI ​​agent evaluates the candidate's strengths and characteristics and selects appropriate second interviewers. It also considers the optimal placement and role based on the candidate's personality and skills. Finally, the AI ​​agent records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. This streamlines the recruitment process and improves the assessment of candidate suitability. By selecting the best talent and placing them in the appropriate roles and departments, organizations can build effective teams and improve overall organizational performance. Thus, the interview system analyzes the candidate's thinking style, personality, facial expressions, and tone of voice to evaluate their strengths and characteristics, selects appropriate second interviewers, considers the optimal placement and role, and records the conversation, enabling streamlining the recruitment process and improving candidate suitability.

[0029] The interview system according to this embodiment comprises an analysis unit, an evaluation unit, a selection unit, an assignment unit, and a recording unit. The analysis unit analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The analysis unit may, for example, use AI to analyze the candidate's thinking style. The analysis unit may also, for example, use AI to analyze the candidate's personality. The analysis unit may also, for example, use AI to analyze the candidate's facial expressions and tone of voice in their responses. The evaluation unit evaluates the candidate's strengths and characteristics based on the results analyzed by the analysis unit. The evaluation unit may, for example, use AI to evaluate the candidate's strengths. The evaluation unit may also, for example, use AI to evaluate the candidate's characteristics. The evaluation unit may also, for example, use AI to comprehensively evaluate the candidate's strengths and characteristics. The selection unit selects an appropriate second interviewer based on the evaluation results obtained by the evaluation unit. The selection unit may, for example, use AI to select an appropriate second interviewer. The selection unit may also, for example, use AI to select a second interviewer based on the candidate's evaluation results. The selection unit may also, for example, use AI to analyze the candidate's evaluation results and select the optimal second interviewer. The Placement Department considers the optimal placement and role for each candidate based on their personality and skills, using evaluation results obtained by the Evaluation Department. The Placement Department may, for example, use AI to consider placements that match each candidate's personality. The Placement Department may also, for example, use AI to consider roles that match each candidate's skills. The Placement Department may also, for example, use AI to comprehensively evaluate each candidate's personality and skills and consider the optimal placement and role. The Recording Department records conversations with candidates and saves them as data that can be re-evaluated and compared later. The Recording Department may, for example, use AI to record conversations with candidates. The Recording Department may also, for example, use AI to save conversation data with candidates. The Recording Department may also, for example, use AI to analyze conversation data with candidates and save it as data that can be re-evaluated and compared. As a result, the interview system according to the embodiment can analyze a candidate's thinking style and personality, facial expressions and tone of voice in their responses, evaluate their strengths and characteristics, select appropriate second interviewers, consider the optimal placement and role, and record conversations, thereby improving the efficiency of the recruitment process and enhancing the assessment of candidates' suitability.

[0030] The analysis unit analyzes candidates' thinking styles, personalities, facial expressions, and tone of voice during their responses. For example, the analysis unit uses AI to analyze candidates' thinking styles. Specifically, it uses natural language processing technology to analyze how candidates develop their arguments and what their problem-solving approaches are during interviews. The AI ​​analyzes the candidates' statements in real time and classifies their thinking styles, such as logical thinking, creative thinking, and intuitive thinking. It also uses algorithms based on psychological models to analyze candidates' personalities. For example, it analyzes candidates' language use and expressions to evaluate the Big Five personality traits (extraversion, agreeableness, conscientiousness, emotional stability, and openness). Furthermore, it combines image recognition technology and voice analysis technology to analyze candidates' facial expressions and tone of voice during their responses. It detects changes in facial expressions from video footage captured by a camera and analyzes changes in voice tone and pitch from audio data collected by a microphone. This allows the analysis unit to assess the candidate's emotional state and their level of confidence in their answers. The analysis unit integrates this data to create an overall profile of the candidate. This allows the analysis unit to comprehensively understand the candidate's thinking style, personality, and emotional state, and provide the information necessary for the next evaluation step.

[0031] The evaluation department assesses candidates' strengths and characteristics based on the results analyzed by the analytics department. For example, the evaluation department uses AI to evaluate candidates' strengths. Specifically, it uses algorithms to comprehensively evaluate candidates' skill sets, experience, and personality traits based on data provided by the analytics department. The AI ​​analyzes candidates' past performance, resume content, and interview statements to identify areas where candidates excel. For example, it sets evaluation criteria such as technical skills, leadership abilities, and communication skills, and assigns scores to each criterion. It also uses psychological evaluation models to assess candidates' characteristics. For example, it evaluates candidates' cooperativeness, stress tolerance, and problem-solving abilities to determine the environment in which they perform best. The evaluation department integrates these evaluation results to create a comprehensive evaluation report of the candidate. This report includes recommendations for the candidate's strengths and characteristics, as well as suitable job roles and positions. This allows the evaluation department to accurately assess candidates' strengths and characteristics and provide the information necessary for the next selection step.

[0032] The selection department selects appropriate second interviewers based on the evaluation results obtained by the evaluation department. The selection department may, for example, use AI to select appropriate second interviewers. Specifically, it uses an algorithm to select the most suitable second interviewer for each candidate, based on the evaluation report provided by the evaluation department. The AI ​​analyzes the candidate's evaluation results and identifies the interviewer best suited to the candidate's characteristics and skills. For example, for a candidate with strong technical skills, a technical expert will be selected as the interviewer, and for a candidate with strong leadership abilities, an interviewer with extensive management experience will be selected. The AI ​​also evaluates the interviewer's suitability and performance based on their past evaluation data and feedback, selecting the most suitable interviewer. Based on this data, the selection department selects the most suitable second interviewer for each candidate and adjusts the interview schedule. This allows the selection department to quickly and accurately select appropriate second interviewers based on the candidate's evaluation results, thereby streamlining the interview process.

[0033] The Placement Department considers the most suitable placement and role for each candidate based on their personality and skills, using evaluation results obtained by the Evaluation Department. For example, the Placement Department may use AI to consider placements that match a candidate's personality. Specifically, it uses an algorithm to identify the most suitable placement and role for a candidate based on the evaluation report provided by the Evaluation Department. The AI ​​analyzes the candidate's personality traits and skill set to determine which department or team the candidate can perform best in. For example, a candidate with high collaborative skills might be placed in a project that emphasizes teamwork, while a candidate with high technical skills might be placed in a specialized technical department. The AI ​​also evaluates the candidate's suitability based on past placement and performance data and recommends the most suitable placement and role. Based on this data, the Placement Department considers the most suitable placement and role for each candidate and makes a placement decision. This allows the Placement Department to quickly and accurately determine the most suitable placement and role for each candidate, thereby improving the overall performance of the organization.

[0034] The Records Department records conversations with candidates and stores the data for later review and comparison. For example, the Records Department uses AI to record conversations with candidates. Specifically, it collects audio and video data during interviews in real time and analyzes and stores this data using AI. The AI ​​uses speech recognition technology to transcribe the interview content into text and extracts important keywords and phrases. It also analyzes the candidate's facial expressions and gestures from the video data to record their emotional state and reactions. This allows the Records Department to create detailed records of conversations with candidates and store them as data for later review and comparison. Furthermore, the Records Department centrally manages this data and can collaborate with other departments and systems as needed. For example, recorded data is stored on a cloud server and made accessible to the evaluation and selection departments. The Records Department also sets data retention periods and access permissions to ensure data security. This allows the Records Department to improve the transparency and reliability of the recruitment process by meticulously recording conversations with candidates and storing the data for later review and comparison.

[0035] The facial expression analysis unit can analyze the candidate's facial expressions and tone of voice. The facial expression analysis unit can, for example, use AI to analyze the candidate's facial expressions. The facial expression analysis unit can also, for example, use AI to analyze the candidate's tone of voice. The facial expression analysis unit can also, for example, use AI to comprehensively analyze the candidate's facial expressions and tone of voice. This allows the facial expression analysis unit to make a more accurate evaluation by analyzing the candidate's facial expressions and tone of voice. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generating AI, or it may be performed without a generating AI. For example, the facial expression analysis unit can input the candidate's facial expression data into a generating AI and have the generating AI perform the facial expression analysis.

[0036] The truth / false determination unit can determine the truth or falsity of an answer. The truth / false determination unit can, for example, use AI to determine the truth or falsity of an answer. The truth / false determination unit can, for example, use AI to analyze the content of an answer and determine its truth or falsity. The truth / false determination unit can, for example, use AI to analyze the consistency of an answer and determine its truth or falsity. This allows the truth / false determination unit to make more accurate evaluations by determining the truth or falsity of an answer. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generating AI, or without a generating AI. For example, the truth / false determination unit can input candidate answer data into a generating AI and have the generating AI perform the determination of the truth or falsity of the answer.

[0037] The criteria setting unit can set evaluation criteria for assessing a candidate's strengths and characteristics. The criteria setting unit can, for example, use AI to set evaluation criteria. The criteria setting unit can also, for example, use AI to set criteria for assessing a candidate's strengths. The criteria setting unit can also, for example, use AI to set criteria for assessing a candidate's characteristics. This improves the consistency and objectivity of the evaluation by allowing the criteria setting unit to set evaluation criteria. Some or all of the above-described processes in the criteria setting unit may be performed, for example, using a generative AI, or without using a generative AI. For example, the criteria setting unit can input candidate evaluation criteria into a generative AI and have the generative AI perform the setting of evaluation criteria.

[0038] The assignment criteria setting unit can set assignment criteria to consider the optimal assignment location and role according to the candidate's personality and skills. The assignment criteria setting unit can, for example, use AI to set assignment criteria. The assignment criteria setting unit can also, for example, use AI to set assignment criteria according to the candidate's personality. The assignment criteria setting unit can also, for example, use AI to set assignment criteria according to the candidate's skills. As a result, by setting assignment criteria, the assignment criteria setting unit can make it possible to assign candidates to positions that match their aptitudes. Some or all of the above-described processes in the assignment criteria setting unit may be performed, for example, using a generating AI, or without using a generating AI. For example, the assignment criteria setting unit can input the candidate's assignment criteria into a generating AI and have the generating AI perform the setting of the assignment criteria.

[0039] The analysis unit can analyze a candidate's past interview history and select the optimal analysis method. For example, the analysis unit can refer to data from interviews the candidate has had in the past and ask similar questions. For example, the analysis unit can focus on questions related to specific skills based on the candidate's past interview history. For example, the analysis unit can analyze the candidate's past interview history and add new questions to improve the accuracy of the analysis. This allows the optimal analysis method to be selected by analyzing the candidate's past interview history. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the candidate's past interview data into a generative AI and have the generative AI select the optimal analysis method.

[0040] The analysis unit can filter candidates based on their current situation and areas of interest during analysis. For example, the analysis unit may prioritize questions related to the candidate's current job. The analysis unit may also add relevant questions based on the candidate's areas of interest. The analysis unit may also select appropriate questions based on the candidate's current situation. This allows for a more appropriate analysis by filtering based on the candidate's current situation and areas of interest. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input data on the candidate's current situation and areas of interest into a generative AI and have the generative AI perform the filtering.

[0041] The analysis unit can prioritize the analysis of highly relevant data by considering the candidate's geographical location information during the analysis. For example, the analysis unit can prioritize region-related questions based on the candidate's geographical location information. The analysis unit can also prioritize the analysis of relevant data by considering the candidate's geographical location information. For example, the analysis unit can perform analysis according to the characteristics of the region based on the candidate's geographical location information. This allows for the prioritization of highly relevant data by considering the candidate's geographical location information. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the candidate's geographical location information into a generative AI and have the generative AI perform the analysis of highly relevant data.

[0042] The analysis unit can analyze a candidate's social media activity and analyze related data during the analysis. For example, the analysis unit can analyze a candidate's social media activity and add related questions. The analysis unit can also improve the accuracy of the analysis based on the candidate's social media activity. For example, the analysis unit can analyze a candidate's social media activity and prioritize the analysis of related data. This allows for the analysis of related data by analyzing a candidate's social media activity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input data on a candidate's social media activity into a generative AI and have the generative AI perform the analysis of the related data.

[0043] The evaluation unit can adjust the level of detail in the evaluation based on the candidate's importance during the evaluation process. For example, the evaluation unit will conduct a detailed evaluation if the candidate is applying for an important position. For example, the evaluation unit may conduct a concise evaluation if the candidate is applying for a general position. The evaluation unit can also adjust the level of detail in the evaluation according to the candidate's importance. This allows for a more appropriate evaluation by adjusting the level of detail in the evaluation based on the candidate's importance. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the evaluation.

[0044] The evaluation unit can apply different evaluation algorithms depending on the candidate's category during the evaluation process. For example, if a candidate is applying for a technical position, the evaluation unit will apply an evaluation algorithm that emphasizes technical skills. For example, if a candidate is applying for a management position, the evaluation unit may also apply an evaluation algorithm that emphasizes leadership skills. The evaluation unit can also select an appropriate evaluation algorithm depending on the candidate's category. This allows for more appropriate evaluations by applying different evaluation algorithms depending on the candidate's category. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate category data into a generative AI and have the generative AI execute the application of the evaluation algorithm.

[0045] The evaluation unit can determine the priority of evaluations based on the timing of candidate submissions during the evaluation process. For example, the evaluation unit may prioritize evaluations of candidates who submit early. The evaluation unit may also perform evaluations quickly if a candidate is close to the submission deadline. The evaluation unit can also determine the priority of evaluations based on the timing of candidate submissions. This allows for more efficient evaluations by determining the priority of evaluations based on the timing of candidate submissions. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate submission timing data into a generative AI and have the generative AI determine the priority of evaluations.

[0046] The evaluation unit can adjust the order of evaluations based on the relevance of candidates during the evaluation process. For example, the evaluation unit may prioritize evaluating candidates who possess relevant skills. The evaluation unit may also prioritize evaluating candidates who possess relevant experience. The evaluation unit can also adjust the order of evaluations based on the relevance of candidates. This allows for more appropriate evaluations by adjusting the order of evaluations based on the relevance of candidates. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate relevance data into a generative AI and have the generative AI perform the adjustment of the evaluation order.

[0047] The selection unit can improve the accuracy of its selection process by considering the interrelationships of candidates. For example, the selection unit can evaluate how well candidates can cooperate with other candidates. The selection unit can also analyze the interrelationships of candidates to make the optimal selection. The selection unit can also improve the accuracy of its selection process based on the interrelationships of candidates. This improves the accuracy of the selection process by considering the interrelationships of candidates. Some or all of the above-described processes in the selection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the selection unit can input candidate interrelationship data into a generative AI and have the generative AI perform the task of improving the accuracy of the selection process.

[0048] The selection unit can make selections while considering the candidate's attribute information. For example, the selection unit can make selections based on the candidate's skill set. The selection unit can also make selections based on the candidate's experience. The selection unit can also make optimal selections based on the candidate's attribute information. This makes it possible to make more appropriate selections by considering the candidate's attribute information. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the selection unit can input the candidate's attribute information into a generative AI and have the generative AI perform the selection.

[0049] The selection unit can perform selections while considering the geographical distribution of candidates. For example, the selection unit can perform region-related selections based on the geographical distribution of candidates. The selection unit can also perform optimal selections while considering the geographical distribution of candidates. For example, the selection unit can perform selections according to regional characteristics based on the geographical distribution of candidates. This makes it possible to perform more appropriate selections by considering the geographical distribution of candidates. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the selection unit can input candidate geographical distribution data into a generative AI and have the generative AI perform the selection.

[0050] The selection unit can improve the accuracy of its selection process by referring to relevant literature for each candidate. For example, the selection unit can improve the accuracy of its selection by referring to relevant literature for each candidate. The selection unit can also make the optimal selection based on relevant literature for each candidate. The selection unit can also improve the accuracy of its selection by analyzing relevant literature for each candidate. This improves the accuracy of the selection process by referring to relevant literature for each candidate. Some or all of the above-described processes in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input candidate relevant literature data into a generative AI and have the generative AI perform the task of improving the accuracy of the selection.

[0051] The placement department can analyze a candidate's past placement history to select the optimal placement method at the time of placement. For example, the placement department can refer to a candidate's past placement history and select a similar placement method. For example, the placement department can focus on placement methods related to specific skills based on a candidate's past placement history. For example, the placement department can analyze a candidate's past placement history to select the optimal placement method. This allows for the selection of the optimal placement method by analyzing a candidate's past placement history. Some or all of the above processes in the placement department may be performed using, for example, a generative AI, or not using a generative AI. For example, the placement department can input a candidate's past placement history data into a generative AI and have the generative AI select the optimal placement method.

[0052] The placement department can customize the placement method based on the candidate's current situation at the time of placement. For example, the placement department may prioritize placement methods related to the candidate's current duties. The placement department may also select an appropriate placement method according to the candidate's current situation. The placement department may also customize the placement method based on the candidate's current situation. This allows for more appropriate placement by customizing the placement method based on the candidate's current situation. Some or all of the above processes in the placement department may be performed using, for example, a generative AI, or not using a generative AI. For example, the placement department may input the candidate's current situation data into a generative AI and have the generative AI perform the customization of the placement method.

[0053] The assignment department can select the optimal assignment method when assigning candidates, taking into account their geographical location information. For example, the assignment department may prioritize assignment methods related to a region based on the candidate's geographical location information. The assignment department may also select the optimal assignment method by considering the candidate's geographical location information. For example, the assignment department may select an assignment method that is appropriate to the characteristics of a region based on the candidate's geographical location information. This makes it possible to assign candidates more appropriately by considering their geographical location information. Some or all of the above processing in the assignment department may be performed using, for example, a generative AI, or without using a generative AI. For example, the assignment department may input the candidate's geographical location data into a generative AI and have the generative AI select the optimal assignment method.

[0054] The placement department can analyze a candidate's social media activity and propose placement methods at the time of placement. For example, the placement department can analyze a candidate's social media activity and propose relevant placement methods. The placement department can also propose the optimal placement method based on a candidate's social media activity. The placement department can also analyze a candidate's social media activity and propose placement methods. This allows for the proposal of more appropriate placement methods by analyzing a candidate's social media activity. Some or all of the above processing in the placement department may be performed using, for example, generative AI, or without generative AI. For example, the placement department can input candidate social media activity data into a generative AI and have the generative AI propose placement methods.

[0055] The recording unit can optimize its recording algorithm by referring to past recording data during recording. For example, the recording unit can refer to past recording data and use a similar recording algorithm. For example, the recording unit can optimize the recording algorithm for a specific skill based on past recording data. For example, the recording unit can analyze past recording data and optimize the recording algorithm. This allows the recording algorithm to be optimized by referring to past recording data. Some or all of the above processes in the recording unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the recording unit can input past recording data into a generative AI and have the generative AI perform the optimization of the recording algorithm.

[0056] The recording unit can weight the recorded data based on the candidate's submission timing during recording. For example, the recording unit may give a higher weight if the candidate submits early. The recording unit may also give a lower weight if the candidate is close to the submission deadline. The recording unit can also weight the recorded data based on the candidate's submission timing. This allows for more appropriate recording by weighting the recorded data based on the candidate's submission timing. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input candidate submission timing data into a generative AI and have the generative AI perform the weighting of the recorded data.

[0057] The facial expression analysis unit can select the optimal analysis method by referring to the candidate's past facial expression data during facial expression analysis. For example, the facial expression analysis unit can refer to the candidate's past facial expression data and use a similar analysis method. For example, the facial expression analysis unit can optimize the analysis method for a specific skill based on the candidate's past facial expression data. For example, the facial expression analysis unit can analyze the candidate's past facial expression data and select the optimal analysis method. This allows the optimal analysis method to be selected by referring to the candidate's past facial expression data. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression analysis unit can input the candidate's past facial expression data into a generative AI and have the generative AI select the optimal analysis method.

[0058] The facial expression analysis unit can customize the analysis methods based on the candidate's current situation during facial expression analysis. For example, the facial expression analysis unit may prioritize facial expression analysis related to the candidate's current job. The facial expression analysis unit may also select appropriate facial expression analysis methods according to the candidate's current situation. The facial expression analysis unit may also customize the facial expression analysis methods based on the candidate's current situation. This allows for more appropriate facial expression analysis by customizing the analysis methods based on the candidate's current situation. Some or all of the above-described processes in the facial expression analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the facial expression analysis unit can input the candidate's current situation data into a generating AI and have the generating AI perform the customization of the analysis methods.

[0059] The facial expression analysis unit can select the optimal analysis method by considering the candidate's geographical location information during facial expression analysis. For example, the facial expression analysis unit may prioritize facial expression analysis related to the region based on the candidate's geographical location information. The facial expression analysis unit can also select the optimal facial expression analysis method by considering the candidate's geographical location information. For example, the facial expression analysis unit may select a facial expression analysis method that is appropriate to the characteristics of the region based on the candidate's geographical location information. This allows for the selection of the optimal facial expression analysis method by considering the candidate's geographical location information. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the facial expression analysis unit can input the candidate's geographical location information data into a generative AI and have the generative AI select the optimal facial expression analysis method.

[0060] The facial expression analysis unit can analyze a candidate's social media activity and propose analysis methods during facial expression analysis. For example, the facial expression analysis unit can analyze a candidate's social media activity and propose relevant facial expression analysis methods. The facial expression analysis unit can also propose the optimal facial expression analysis method based on a candidate's social media activity. The facial expression analysis unit can also analyze a candidate's social media activity and propose facial expression analysis methods. This allows the optimal analysis method to be proposed by analyzing a candidate's social media activity. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression analysis unit can input candidate social media activity data into a generative AI and have the generative AI execute the proposal of analysis methods.

[0061] The truth / false determination unit can select the optimal determination method by referring to the candidate's past response data when determining truth / falseness. For example, the truth / false determination unit can refer to the candidate's past response data and use a similar determination method. For example, the truth / false determination unit can optimize the determination method for a specific skill based on the candidate's past response data. For example, the truth / false determination unit can analyze the candidate's past response data and select the optimal determination method. This allows the optimal determination method to be selected by referring to the candidate's past response data. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without a generative AI. For example, the truth / false determination unit can input the candidate's past response data into a generative AI and have the generative AI select the optimal determination method.

[0062] The truth / false determination unit can customize its judgment methods based on the candidate's current situation when making a truth / false determination. For example, the truth / false determination unit may prioritize truth / false determinations related to the candidate's current duties. The truth / false determination unit can also select appropriate truth / false determination methods according to the candidate's current situation. The truth / false determination unit can also customize its judgment methods based on the candidate's current situation. This allows for more appropriate truth / false determinations by customizing the judgment methods based on the candidate's current situation. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without a generative AI. For example, the truth / false determination unit can input the candidate's current situation data into a generative AI and have the generative AI perform the customization of the judgment methods.

[0063] The truth / false determination unit can select the optimal determination method by considering the candidate's geographical location information when determining truth / falseness. For example, the truth / false determination unit can prioritize truth / false determinations related to a region based on the candidate's geographical location information. The truth / false determination unit can also select the optimal truth / false determination method by considering the candidate's geographical location information. For example, the truth / false determination unit can select a truth / false determination method that is appropriate to the characteristics of the region based on the candidate's geographical location information. This allows the optimal determination method to be selected by considering the candidate's geographical location information. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the truth / false determination unit can input the candidate's geographical location information data into a generative AI and have the generative AI select the optimal determination method.

[0064] The truth / false determination unit can analyze the candidate's social media activity and propose a means of determination when making a truth / false determination. For example, the truth / false determination unit can analyze the candidate's social media activity and propose relevant means of truth / false determination. The truth / false determination unit can also propose the optimal means of truth / false determination based on the candidate's social media activity. The truth / false determination unit can also analyze the candidate's social media activity and propose a means of truth / false determination. This allows the optimal means of determination to be proposed by analyzing the candidate's social media activity. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without a generative AI. For example, the truth / false determination unit can input the candidate's social media activity data into a generative AI and have the generative AI execute the proposal of means of determination.

[0065] The criteria setting unit can optimize the criteria algorithm by referring to past evaluation data when setting criteria. For example, the criteria setting unit can refer to past evaluation data and use a similar criteria algorithm. For example, the criteria setting unit can optimize the criteria algorithm for a specific skill from past evaluation data. For example, the criteria setting unit can analyze past evaluation data and optimize the criteria algorithm. This allows the criteria algorithm to be optimized by referring to past evaluation data. Some or all of the above processing in the criteria setting unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the criteria setting unit can input past evaluation data into a generative AI and have the generative AI perform the optimization of the criteria algorithm.

[0066] The criteria setting unit can weight the criteria data based on the candidate's submission timing when setting the criteria. For example, the criteria setting unit may give a higher weight if the candidate submits early. For example, the criteria setting unit may also give a lower weight if the candidate is close to the submission deadline. The criteria setting unit can also weight the criteria data based on the candidate's submission timing. This allows for more appropriate criteria setting by weighting the criteria data based on the candidate's submission timing. Some or all of the above processing in the criteria setting unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the criteria setting unit can input candidate submission timing data into a generating AI and have the generating AI perform the weighting of the criteria data.

[0067] The assignment criteria setting unit can optimize the criteria algorithm by referring to past assignment data when setting assignment criteria. For example, the assignment criteria setting unit can refer to past assignment data and use a similar criteria algorithm. For example, the assignment criteria setting unit can optimize the criteria algorithm for specific skills from past assignment data. For example, the assignment criteria setting unit can analyze past assignment data and optimize the criteria algorithm. This allows the criteria algorithm to be optimized by referring to past assignment data. Some or all of the above processing in the assignment criteria setting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assignment criteria setting unit can input past assignment data into a generative AI and have the generative AI perform the optimization of the criteria algorithm.

[0068] The assignment criteria setting unit can weight the criteria data based on the candidate's submission timing when setting assignment criteria. For example, the assignment criteria setting unit may give a higher weight if the candidate submits early. For example, the assignment criteria setting unit may also give a lower weight if the candidate is close to the submission deadline. The assignment criteria setting unit can also weight the criteria data based on the candidate's submission timing. This makes it possible to set more appropriate assignment criteria by weighting the criteria data based on the candidate's submission timing. Some or all of the above processing in the assignment criteria setting unit may be performed using, for example, a generation AI, or without a generation AI. For example, the assignment criteria setting unit can input candidate submission timing data into a generation AI and have the generation AI perform the weighting of the criteria data.

[0069] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0070] The analysis unit can analyze a candidate's past work history and identify skills and experience relevant to their current job. For example, the analysis unit can refer to a candidate's past work history and extract relevant skills. The analysis unit can also, for example, ask questions based on specific experiences derived from a candidate's past work history. By analyzing a candidate's past work history and identifying skills and experience relevant to their current job, the analysis unit can perform a more accurate analysis.

[0071] The selection department can analyze a candidate's past project history and select appropriate second interviewers. For example, the selection department can refer to a candidate's past project history and select second interviewers based on relevant projects. For example, the selection department can also select second interviewers based on specific skills from a candidate's past project history. By analyzing a candidate's past project history and selecting appropriate second interviewers, the selection department can make more accurate selections.

[0072] The recording unit can analyze a candidate's past interview data and optimize the recording method. For example, the recording unit can refer to a candidate's past interview data and use a similar recording method. For example, the recording unit can also optimize the recording method for specific skills based on a candidate's past interview data. By analyzing a candidate's past interview data and optimizing the recording method, for example, the recording unit can achieve more accurate records.

[0073] The evaluation department can analyze a candidate's past evaluation data and optimize the evaluation criteria. For example, the evaluation department can refer to a candidate's past evaluation data and use similar evaluation criteria. For example, the evaluation department can also optimize evaluation criteria for specific skills based on a candidate's past evaluation data. By analyzing a candidate's past evaluation data and optimizing the evaluation criteria, the evaluation department can enable more accurate evaluations.

[0074] The placement department can analyze a candidate's past placement data and optimize placement methods. For example, the placement department can refer to a candidate's past placement data and use similar placement methods. For example, the placement department can also optimize placement methods for specific skills based on a candidate's past placement data. By analyzing a candidate's past placement data and optimizing placement methods, the placement department can achieve more accurate placements.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The analysis unit analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. For example, AI can be used to analyze the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. Step 2: The evaluation unit assesses the candidate's strengths and characteristics based on the results analyzed by the analysis unit. For example, AI can be used to assess the candidate's strengths and characteristics. Step 3: The selection unit selects appropriate second interviewers based on the evaluation results obtained by the evaluation unit. For example, AI can be used to select appropriate second interviewers. Step 4: The Placement Department considers the most suitable placement and role for each candidate based on their personality and skills, using the evaluation results obtained by the Evaluation Department. For example, AI can be used to comprehensively evaluate a candidate's personality and skills and consider the most suitable placement and role. Step 5: The recording unit records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. For example, AI can be used to save the conversation data with the candidate and save it as data that can be re-evaluated and compared later.

[0077] (Example of form 2) An interview system according to an embodiment of the present invention is an interview system using an AI agent. This interview system can analyze a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, determine their authenticity, and make accurate evaluations. This allows for accurate understanding of a candidate's strengths and characteristics, enabling not only the selection of appropriate second-round interviewers but also consideration of the optimal placement and role. For example, the interview system can identify the most suitable position within the organization, maximize potential, and assess compatibility and synergy with existing employees, based on the candidate's personality and skills. The greatest advantage of this idea is that it allows for dialogue with candidates without being constrained by time or location. Candidates can proceed with the dialogue at their own pace and make effective use of their time. Furthermore, the interview system records the dialogue with the candidate, allowing for later re-evaluation and comparison. This enables interviewers to review the information and make more appropriate decisions. Moreover, the dialogue conducted by the interview system is consistent and objective. Candidates can receive a fair evaluation and are less susceptible to subjective bias. Such objective evaluation leads to a fairer recruitment process. The interview system consists of the following steps: First, the candidate begins a dialogue with the AI ​​agent. The AI ​​agent analyzes the candidate's thinking style, personality, facial expressions, and tone of voice to determine the truthfulness of their responses. Next, based on the analysis, the AI ​​agent evaluates the candidate's strengths and characteristics and selects appropriate second interviewers. It also considers the optimal placement and role based on the candidate's personality and skills. Finally, the AI ​​agent records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. This streamlines the recruitment process and improves the assessment of candidate suitability. By selecting the best talent and placing them in the appropriate roles and departments, organizations can build effective teams and improve overall organizational performance. Thus, the interview system analyzes the candidate's thinking style, personality, facial expressions, and tone of voice to evaluate their strengths and characteristics, selects appropriate second interviewers, considers the optimal placement and role, and records the conversation, enabling streamlining the recruitment process and improving candidate suitability.

[0078] The interview system according to this embodiment comprises an analysis unit, an evaluation unit, a selection unit, an assignment unit, and a recording unit. The analysis unit analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The analysis unit may, for example, use AI to analyze the candidate's thinking style. The analysis unit may also, for example, use AI to analyze the candidate's personality. The analysis unit may also, for example, use AI to analyze the candidate's facial expressions and tone of voice in their responses. The evaluation unit evaluates the candidate's strengths and characteristics based on the results analyzed by the analysis unit. The evaluation unit may, for example, use AI to evaluate the candidate's strengths. The evaluation unit may also, for example, use AI to evaluate the candidate's characteristics. The evaluation unit may also, for example, use AI to comprehensively evaluate the candidate's strengths and characteristics. The selection unit selects an appropriate second interviewer based on the evaluation results obtained by the evaluation unit. The selection unit may, for example, use AI to select an appropriate second interviewer. The selection unit may also, for example, use AI to select a second interviewer based on the candidate's evaluation results. The selection unit may also, for example, use AI to analyze the candidate's evaluation results and select the optimal second interviewer. The Placement Department considers the optimal placement and role for each candidate based on their personality and skills, using evaluation results obtained by the Evaluation Department. The Placement Department may, for example, use AI to consider placements that match each candidate's personality. The Placement Department may also, for example, use AI to consider roles that match each candidate's skills. The Placement Department may also, for example, use AI to comprehensively evaluate each candidate's personality and skills and consider the optimal placement and role. The Recording Department records conversations with candidates and saves them as data that can be re-evaluated and compared later. The Recording Department may, for example, use AI to record conversations with candidates. The Recording Department may also, for example, use AI to save conversation data with candidates. The Recording Department may also, for example, use AI to analyze conversation data with candidates and save it as data that can be re-evaluated and compared. As a result, the interview system according to the embodiment can analyze a candidate's thinking style and personality, facial expressions and tone of voice in their responses, evaluate their strengths and characteristics, select appropriate second interviewers, consider the optimal placement and role, and record conversations, thereby improving the efficiency of the recruitment process and enhancing the assessment of candidates' suitability.

[0079] The analysis unit analyzes candidates' thinking styles, personalities, facial expressions, and tone of voice during their responses. For example, the analysis unit uses AI to analyze candidates' thinking styles. Specifically, it uses natural language processing technology to analyze how candidates develop their arguments and what their problem-solving approaches are during interviews. The AI ​​analyzes the candidates' statements in real time and classifies their thinking styles, such as logical thinking, creative thinking, and intuitive thinking. It also uses algorithms based on psychological models to analyze candidates' personalities. For example, it analyzes candidates' language use and expressions to evaluate the Big Five personality traits (extraversion, agreeableness, conscientiousness, emotional stability, and openness). Furthermore, it combines image recognition technology and voice analysis technology to analyze candidates' facial expressions and tone of voice during their responses. It detects changes in facial expressions from video footage captured by a camera and analyzes changes in voice tone and pitch from audio data collected by a microphone. This allows the analysis unit to assess the candidate's emotional state and their level of confidence in their answers. The analysis unit integrates this data to create an overall profile of the candidate. This allows the analysis unit to comprehensively understand the candidate's thinking style, personality, and emotional state, and provide the information necessary for the next evaluation step.

[0080] The evaluation department assesses candidates' strengths and characteristics based on the results analyzed by the analytics department. For example, the evaluation department uses AI to evaluate candidates' strengths. Specifically, it uses algorithms to comprehensively evaluate candidates' skill sets, experience, and personality traits based on data provided by the analytics department. The AI ​​analyzes candidates' past performance, resume content, and interview statements to identify areas where candidates excel. For example, it sets evaluation criteria such as technical skills, leadership abilities, and communication skills, and assigns scores to each criterion. It also uses psychological evaluation models to assess candidates' characteristics. For example, it evaluates candidates' cooperativeness, stress tolerance, and problem-solving abilities to determine the environment in which they perform best. The evaluation department integrates these evaluation results to create a comprehensive evaluation report of the candidate. This report includes recommendations for the candidate's strengths and characteristics, as well as suitable job roles and positions. This allows the evaluation department to accurately assess candidates' strengths and characteristics and provide the information necessary for the next selection step.

[0081] The selection department selects appropriate second interviewers based on the evaluation results obtained by the evaluation department. The selection department may, for example, use AI to select appropriate second interviewers. Specifically, it uses an algorithm to select the most suitable second interviewer for each candidate, based on the evaluation report provided by the evaluation department. The AI ​​analyzes the candidate's evaluation results and identifies the interviewer best suited to the candidate's characteristics and skills. For example, for a candidate with strong technical skills, a technical expert will be selected as the interviewer, and for a candidate with strong leadership abilities, an interviewer with extensive management experience will be selected. The AI ​​also evaluates the interviewer's suitability and performance based on their past evaluation data and feedback, selecting the most suitable interviewer. Based on this data, the selection department selects the most suitable second interviewer for each candidate and adjusts the interview schedule. This allows the selection department to quickly and accurately select appropriate second interviewers based on the candidate's evaluation results, thereby streamlining the interview process.

[0082] The Placement Department considers the most suitable placement and role for each candidate based on their personality and skills, using evaluation results obtained by the Evaluation Department. For example, the Placement Department may use AI to consider placements that match a candidate's personality. Specifically, it uses an algorithm to identify the most suitable placement and role for a candidate based on the evaluation report provided by the Evaluation Department. The AI ​​analyzes the candidate's personality traits and skill set to determine which department or team the candidate can perform best in. For example, a candidate with high collaborative skills might be placed in a project that emphasizes teamwork, while a candidate with high technical skills might be placed in a specialized technical department. The AI ​​also evaluates the candidate's suitability based on past placement and performance data and recommends the most suitable placement and role. Based on this data, the Placement Department considers the most suitable placement and role for each candidate and makes a placement decision. This allows the Placement Department to quickly and accurately determine the most suitable placement and role for each candidate, thereby improving the overall performance of the organization.

[0083] The Records Department records conversations with candidates and stores the data for later review and comparison. For example, the Records Department uses AI to record conversations with candidates. Specifically, it collects audio and video data during interviews in real time and analyzes and stores this data using AI. The AI ​​uses speech recognition technology to transcribe the interview content into text and extracts important keywords and phrases. It also analyzes the candidate's facial expressions and gestures from the video data to record their emotional state and reactions. This allows the Records Department to create detailed records of conversations with candidates and store them as data for later review and comparison. Furthermore, the Records Department centrally manages this data and can collaborate with other departments and systems as needed. For example, recorded data is stored on a cloud server and made accessible to the evaluation and selection departments. The Records Department also sets data retention periods and access permissions to ensure data security. This allows the Records Department to improve the transparency and reliability of the recruitment process by meticulously recording conversations with candidates and storing the data for later review and comparison.

[0084] The facial expression analysis unit can analyze the candidate's facial expressions and tone of voice. The facial expression analysis unit can, for example, use AI to analyze the candidate's facial expressions. The facial expression analysis unit can also, for example, use AI to analyze the candidate's tone of voice. The facial expression analysis unit can also, for example, use AI to comprehensively analyze the candidate's facial expressions and tone of voice. This allows the facial expression analysis unit to make a more accurate evaluation by analyzing the candidate's facial expressions and tone of voice. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generating AI, or it may be performed without a generating AI. For example, the facial expression analysis unit can input the candidate's facial expression data into a generating AI and have the generating AI perform the facial expression analysis.

[0085] The truth / false determination unit can determine the truth or falsity of an answer. The truth / false determination unit can, for example, use AI to determine the truth or falsity of an answer. The truth / false determination unit can, for example, use AI to analyze the content of an answer and determine its truth or falsity. The truth / false determination unit can, for example, use AI to analyze the consistency of an answer and determine its truth or falsity. This allows the truth / false determination unit to make more accurate evaluations by determining the truth or falsity of an answer. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generating AI, or without a generating AI. For example, the truth / false determination unit can input candidate answer data into a generating AI and have the generating AI perform the determination of the truth or falsity of the answer.

[0086] The criteria setting unit can set evaluation criteria for assessing a candidate's strengths and characteristics. The criteria setting unit can, for example, use AI to set evaluation criteria. The criteria setting unit can also, for example, use AI to set criteria for assessing a candidate's strengths. The criteria setting unit can also, for example, use AI to set criteria for assessing a candidate's characteristics. This improves the consistency and objectivity of the evaluation by allowing the criteria setting unit to set evaluation criteria. Some or all of the above-described processes in the criteria setting unit may be performed, for example, using a generative AI, or without using a generative AI. For example, the criteria setting unit can input candidate evaluation criteria into a generative AI and have the generative AI perform the setting of evaluation criteria.

[0087] The assignment criteria setting unit can set assignment criteria to consider the optimal assignment location and role according to the candidate's personality and skills. The assignment criteria setting unit can, for example, use AI to set assignment criteria. The assignment criteria setting unit can also, for example, use AI to set assignment criteria according to the candidate's personality. The assignment criteria setting unit can also, for example, use AI to set assignment criteria according to the candidate's skills. As a result, by setting assignment criteria, the assignment criteria setting unit can make it possible to assign candidates to positions that match their aptitudes. Some or all of the above-described processes in the assignment criteria setting unit may be performed, for example, using a generating AI, or without using a generating AI. For example, the assignment criteria setting unit can input the candidate's assignment criteria into a generating AI and have the generating AI perform the setting of the assignment criteria.

[0088] The analysis unit can estimate the candidate's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the candidate is nervous, the analysis unit can improve the accuracy of the analysis by having the AI ​​ask additional questions to help the candidate relax. If the candidate is relaxed, the analysis unit can ask more detailed questions to perform a deeper analysis. If the candidate is in a hurry, the analysis unit can ask concise questions to perform a quick analysis. This allows for a more accurate analysis by adjusting the accuracy of the analysis according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0089] The analysis unit can analyze a candidate's past interview history and select the optimal analysis method. For example, the analysis unit can refer to data from interviews the candidate has had in the past and ask similar questions. For example, the analysis unit can focus on questions related to specific skills based on the candidate's past interview history. For example, the analysis unit can analyze the candidate's past interview history and add new questions to improve the accuracy of the analysis. This allows the optimal analysis method to be selected by analyzing the candidate's past interview history. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the candidate's past interview data into a generative AI and have the generative AI select the optimal analysis method.

[0090] The analysis unit can filter candidates based on their current situation and areas of interest during analysis. For example, the analysis unit may prioritize questions related to the candidate's current job. The analysis unit may also add relevant questions based on the candidate's areas of interest. The analysis unit may also select appropriate questions based on the candidate's current situation. This allows for a more appropriate analysis by filtering based on the candidate's current situation and areas of interest. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input data on the candidate's current situation and areas of interest into a generative AI and have the generative AI perform the filtering.

[0091] The analysis unit can estimate the candidate's emotions and prioritize the analysis results based on the estimated emotions. For example, if the candidate is nervous, the analysis unit will prioritize displaying analysis results that promote relaxation. For example, if the candidate is relaxed, the analysis unit may also prioritize displaying detailed analysis results. For example, if the candidate is in a hurry, the analysis unit may also prioritize displaying concise analysis results. By prioritizing the analysis results according to the candidate's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0092] The analysis unit can prioritize the analysis of highly relevant data by considering the candidate's geographical location information during the analysis. For example, the analysis unit can prioritize region-related questions based on the candidate's geographical location information. The analysis unit can also prioritize the analysis of relevant data by considering the candidate's geographical location information. For example, the analysis unit can perform analysis according to the characteristics of the region based on the candidate's geographical location information. This allows for the prioritization of highly relevant data by considering the candidate's geographical location information. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the candidate's geographical location information into a generative AI and have the generative AI perform the analysis of highly relevant data.

[0093] The analysis unit can analyze a candidate's social media activity and analyze related data during the analysis. For example, the analysis unit can analyze a candidate's social media activity and add related questions. The analysis unit can also improve the accuracy of the analysis based on the candidate's social media activity. For example, the analysis unit can analyze a candidate's social media activity and prioritize the analysis of related data. This allows for the analysis of related data by analyzing a candidate's social media activity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input data on a candidate's social media activity into a generative AI and have the generative AI perform the analysis of the related data.

[0094] The evaluation unit can estimate the candidate's emotions and adjust the expression of the evaluation based on the estimated emotions. For example, if the candidate is nervous, the evaluation unit may use evaluation expressions to help them relax. For example, if the candidate is relaxed, the evaluation unit may use detailed evaluation expressions. For example, if the candidate is in a hurry, the evaluation unit may use concise evaluation expressions. This allows for a more appropriate evaluation by adjusting the expression of the evaluation according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the evaluation unit may be performed using AI, for example, or not using AI. For example, the evaluation unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0095] The evaluation unit can adjust the level of detail in the evaluation based on the candidate's importance during the evaluation process. For example, the evaluation unit will conduct a detailed evaluation if the candidate is applying for an important position. For example, the evaluation unit may conduct a concise evaluation if the candidate is applying for a general position. The evaluation unit can also adjust the level of detail in the evaluation according to the candidate's importance. This allows for a more appropriate evaluation by adjusting the level of detail in the evaluation based on the candidate's importance. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the evaluation.

[0096] The evaluation unit can apply different evaluation algorithms depending on the candidate's category during the evaluation process. For example, if a candidate is applying for a technical position, the evaluation unit will apply an evaluation algorithm that emphasizes technical skills. For example, if a candidate is applying for a management position, the evaluation unit may also apply an evaluation algorithm that emphasizes leadership skills. The evaluation unit can also select an appropriate evaluation algorithm depending on the candidate's category. This allows for more appropriate evaluations by applying different evaluation algorithms depending on the candidate's category. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate category data into a generative AI and have the generative AI execute the application of the evaluation algorithm.

[0097] The evaluation unit can estimate the candidate's emotions and adjust the length of the evaluation based on the estimated emotions. For example, if the candidate is nervous, the evaluation unit may give a short evaluation. For example, if the candidate is relaxed, the evaluation unit may give a detailed evaluation. For example, if the candidate is in a hurry, the evaluation unit may give a concise evaluation. By adjusting the length of the evaluation according to the candidate's emotions, a more appropriate evaluation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the evaluation unit may be performed using AI, for example, or not using AI. For example, the evaluation unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0098] The evaluation unit can determine the priority of evaluations based on the timing of candidate submissions during the evaluation process. For example, the evaluation unit may prioritize evaluations of candidates who submit early. The evaluation unit may also perform evaluations quickly if a candidate is close to the submission deadline. The evaluation unit can also determine the priority of evaluations based on the timing of candidate submissions. This allows for more efficient evaluations by determining the priority of evaluations based on the timing of candidate submissions. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate submission timing data into a generative AI and have the generative AI determine the priority of evaluations.

[0099] The evaluation unit can adjust the order of evaluations based on the relevance of candidates during the evaluation process. For example, the evaluation unit may prioritize evaluating candidates who possess relevant skills. The evaluation unit may also prioritize evaluating candidates who possess relevant experience. The evaluation unit can also adjust the order of evaluations based on the relevance of candidates. This allows for more appropriate evaluations by adjusting the order of evaluations based on the relevance of candidates. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input candidate relevance data into a generative AI and have the generative AI perform the adjustment of the evaluation order.

[0100] The selection unit can estimate the candidate's emotions and adjust the selection criteria based on the estimated emotions. For example, if the candidate is nervous, the selection unit may use criteria to help them relax. If the candidate is relaxed, the selection unit may also use detailed criteria. If the candidate is in a hurry, the selection unit may also use concise criteria. This allows for more appropriate selection by adjusting the selection criteria according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit may input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0101] The selection unit can improve the accuracy of its selection process by considering the interrelationships of candidates. For example, the selection unit can evaluate how well candidates can cooperate with other candidates. The selection unit can also analyze the interrelationships of candidates to make the optimal selection. The selection unit can also improve the accuracy of its selection process based on the interrelationships of candidates. This improves the accuracy of the selection process by considering the interrelationships of candidates. Some or all of the above-described processes in the selection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the selection unit can input candidate interrelationship data into a generative AI and have the generative AI perform the task of improving the accuracy of the selection process.

[0102] The selection unit can make selections while considering the candidate's attribute information. For example, the selection unit can make selections based on the candidate's skill set. The selection unit can also make selections based on the candidate's experience. The selection unit can also make optimal selections based on the candidate's attribute information. This makes it possible to make more appropriate selections by considering the candidate's attribute information. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the selection unit can input the candidate's attribute information into a generative AI and have the generative AI perform the selection.

[0103] The selection unit can estimate the candidate's emotions and adjust the order in which the selection results are displayed based on the estimated candidate's emotions. For example, if the candidate is nervous, the selection unit may prioritize displaying results that promote relaxation. For example, if the candidate is relaxed, the selection unit may also prioritize displaying detailed results. For example, if the candidate is in a hurry, the selection unit may also prioritize displaying concise results. This allows for more appropriate result display by adjusting the order in which the selection results are displayed according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0104] The selection unit can perform selections while considering the geographical distribution of candidates. For example, the selection unit can perform region-related selections based on the geographical distribution of candidates. The selection unit can also perform optimal selections while considering the geographical distribution of candidates. For example, the selection unit can perform selections according to regional characteristics based on the geographical distribution of candidates. This makes it possible to perform more appropriate selections by considering the geographical distribution of candidates. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the selection unit can input candidate geographical distribution data into a generative AI and have the generative AI perform the selection.

[0105] The selection unit can improve the accuracy of its selection process by referring to relevant literature for each candidate. For example, the selection unit can improve the accuracy of its selection by referring to relevant literature for each candidate. The selection unit can also make the optimal selection based on relevant literature for each candidate. The selection unit can also improve the accuracy of its selection by analyzing relevant literature for each candidate. This improves the accuracy of the selection process by referring to relevant literature for each candidate. Some or all of the above-described processes in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input candidate relevant literature data into a generative AI and have the generative AI perform the task of improving the accuracy of the selection.

[0106] The placement unit can estimate a candidate's emotions and adjust the placement method based on the estimated emotions. For example, if a candidate is nervous, the placement unit may use a placement method designed to help them relax. If a candidate is relaxed, the placement unit may also use a more detailed placement method. If a candidate is in a hurry, the placement unit may also use a more concise placement method. By adjusting the placement method according to the candidate's emotions, more appropriate placements become possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the placement unit may be performed using AI or not. For example, the placement unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0107] The placement department can analyze a candidate's past placement history to select the optimal placement method at the time of placement. For example, the placement department can refer to a candidate's past placement history and select a similar placement method. For example, the placement department can focus on placement methods related to specific skills based on a candidate's past placement history. For example, the placement department can analyze a candidate's past placement history to select the optimal placement method. This allows for the selection of the optimal placement method by analyzing a candidate's past placement history. Some or all of the above processes in the placement department may be performed using, for example, a generative AI, or not using a generative AI. For example, the placement department can input a candidate's past placement history data into a generative AI and have the generative AI select the optimal placement method.

[0108] The placement department can customize the placement method based on the candidate's current situation at the time of placement. For example, the placement department may prioritize placement methods related to the candidate's current duties. The placement department may also select an appropriate placement method according to the candidate's current situation. The placement department may also customize the placement method based on the candidate's current situation. This allows for more appropriate placement by customizing the placement method based on the candidate's current situation. Some or all of the above processes in the placement department may be performed using, for example, a generative AI, or not using a generative AI. For example, the placement department may input the candidate's current situation data into a generative AI and have the generative AI perform the customization of the placement method.

[0109] The assignment unit can estimate a candidate's emotions and determine assignment priorities based on the estimated emotions. For example, if a candidate is nervous, the assignment unit may prioritize assignments that help them relax. If a candidate is relaxed, the assignment unit may also prioritize detailed assignments. If a candidate is in a hurry, the assignment unit may also prioritize concise assignments. This allows for more appropriate assignments by prioritizing assignments according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assignment unit may be performed using AI or not. For example, the assignment unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0110] The assignment department can select the optimal assignment method when assigning candidates, taking into account their geographical location information. For example, the assignment department may prioritize assignment methods related to a region based on the candidate's geographical location information. The assignment department may also select the optimal assignment method by considering the candidate's geographical location information. For example, the assignment department may select an assignment method that is appropriate to the characteristics of a region based on the candidate's geographical location information. This makes it possible to assign candidates more appropriately by considering their geographical location information. Some or all of the above processing in the assignment department may be performed using, for example, a generative AI, or without using a generative AI. For example, the assignment department may input the candidate's geographical location data into a generative AI and have the generative AI select the optimal assignment method.

[0111] The placement department can analyze a candidate's social media activity and propose placement methods at the time of placement. For example, the placement department can analyze a candidate's social media activity and propose relevant placement methods. The placement department can also propose the optimal placement method based on a candidate's social media activity. The placement department can also analyze a candidate's social media activity and propose placement methods. This allows for the proposal of more appropriate placement methods by analyzing a candidate's social media activity. Some or all of the above processing in the placement department may be performed using, for example, generative AI, or without generative AI. For example, the placement department can input candidate social media activity data into a generative AI and have the generative AI propose placement methods.

[0112] The recording unit can estimate the candidate's emotions and select recording data based on the estimated emotions. For example, if the candidate is nervous, the recording unit may prioritize selecting recording data that helps them relax. For example, if the candidate is relaxed, the recording unit may prioritize selecting detailed recording data. For example, if the candidate is in a hurry, the recording unit may prioritize selecting concise recording data. This allows for more appropriate recording by selecting recording data according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI or not using AI. For example, the recording unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0113] The recording unit can optimize its recording algorithm by referring to past recording data during recording. For example, the recording unit can refer to past recording data and use a similar recording algorithm. For example, the recording unit can optimize the recording algorithm for a specific skill based on past recording data. For example, the recording unit can analyze past recording data and optimize the recording algorithm. This allows the recording algorithm to be optimized by referring to past recording data. Some or all of the above processes in the recording unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the recording unit can input past recording data into a generative AI and have the generative AI perform the optimization of the recording algorithm.

[0114] The recording unit can estimate the candidate's emotions and adjust the recording frequency based on the estimated emotions. For example, if the candidate is nervous, the recording unit will record frequently. For example, if the candidate is relaxed, the recording unit may also record in detail. For example, if the candidate is in a hurry, the recording unit may also record concisely. By adjusting the recording frequency according to the candidate's emotions, more appropriate recording becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the recording unit may be performed using AI, for example, or not using AI. For example, the recording unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0115] The recording unit can weight the recorded data based on the candidate's submission timing during recording. For example, the recording unit may give a higher weight if the candidate submits early. The recording unit may also give a lower weight if the candidate is close to the submission deadline. The recording unit can also weight the recorded data based on the candidate's submission timing. This allows for more appropriate recording by weighting the recorded data based on the candidate's submission timing. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input candidate submission timing data into a generative AI and have the generative AI perform the weighting of the recorded data.

[0116] The facial expression analysis unit can estimate the candidate's emotions and adjust the accuracy of the facial expression analysis based on the estimated emotions. For example, if the candidate is nervous, the facial expression analysis unit can perform facial expression analysis to help them relax. For example, if the candidate is relaxed, the facial expression analysis unit can also perform a detailed facial expression analysis. For example, if the candidate is in a hurry, the facial expression analysis unit can also perform a concise facial expression analysis. By adjusting the accuracy of the facial expression analysis according to the candidate's emotions, more accurate facial expression analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, for example, 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 processing in the facial expression analysis unit may be performed using AI, for example, or without using AI. For example, the facial expression analysis unit can input the candidate's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0117] The facial expression analysis unit can select the optimal analysis method by referring to the candidate's past facial expression data during facial expression analysis. For example, the facial expression analysis unit can refer to the candidate's past facial expression data and use a similar analysis method. For example, the facial expression analysis unit can optimize the analysis method for a specific skill based on the candidate's past facial expression data. For example, the facial expression analysis unit can analyze the candidate's past facial expression data and select the optimal analysis method. This allows the optimal analysis method to be selected by referring to the candidate's past facial expression data. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression analysis unit can input the candidate's past facial expression data into a generative AI and have the generative AI select the optimal analysis method.

[0118] The facial expression analysis unit can customize the analysis methods based on the candidate's current situation during facial expression analysis. For example, the facial expression analysis unit may prioritize facial expression analysis related to the candidate's current job. The facial expression analysis unit may also select appropriate facial expression analysis methods according to the candidate's current situation. The facial expression analysis unit may also customize the facial expression analysis methods based on the candidate's current situation. This allows for more appropriate facial expression analysis by customizing the analysis methods based on the candidate's current situation. Some or all of the above-described processes in the facial expression analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the facial expression analysis unit can input the candidate's current situation data into a generating AI and have the generating AI perform the customization of the analysis methods.

[0119] The facial expression analysis unit can estimate the candidate's emotions and determine the priority of facial expression analysis based on the estimated emotions. For example, if the candidate is nervous, the facial expression analysis unit may prioritize facial expression analysis to promote relaxation. For example, if the candidate is relaxed, the facial expression analysis unit may also prioritize detailed facial expression analysis. For example, if the candidate is in a hurry, the facial expression analysis unit may also prioritize concise facial expression analysis. This allows for more appropriate facial expression analysis by determining the priority of facial expression analysis according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, for example, 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 processing in the facial expression analysis unit may be performed using AI, for example, or without AI. For example, the facial expression analysis unit can input the candidate's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0120] The facial expression analysis unit can select the optimal analysis method by considering the candidate's geographical location information during facial expression analysis. For example, the facial expression analysis unit may prioritize facial expression analysis related to the region based on the candidate's geographical location information. The facial expression analysis unit can also select the optimal facial expression analysis method by considering the candidate's geographical location information. For example, the facial expression analysis unit may select a facial expression analysis method that is appropriate to the characteristics of the region based on the candidate's geographical location information. This allows for the selection of the optimal facial expression analysis method by considering the candidate's geographical location information. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the facial expression analysis unit can input the candidate's geographical location information data into a generative AI and have the generative AI select the optimal facial expression analysis method.

[0121] The facial expression analysis unit can analyze a candidate's social media activity and propose analysis methods during facial expression analysis. For example, the facial expression analysis unit can analyze a candidate's social media activity and propose relevant facial expression analysis methods. The facial expression analysis unit can also propose the optimal facial expression analysis method based on a candidate's social media activity. The facial expression analysis unit can also analyze a candidate's social media activity and propose facial expression analysis methods. This allows the optimal analysis method to be proposed by analyzing a candidate's social media activity. Some or all of the above processing in the facial expression analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression analysis unit can input candidate social media activity data into a generative AI and have the generative AI execute the proposal of analysis methods.

[0122] The truth / false determination unit can estimate the candidate's emotions and adjust the accuracy of its truth / false determination based on the estimated candidate's emotions. For example, if the candidate is nervous, the truth / false determination unit can make a truth / false determination to help them relax. For example, if the candidate is relaxed, the truth / false determination unit can also make a detailed truth / false determination. For example, if the candidate is in a hurry, the truth / false determination unit can also make a concise truth / false determination. By adjusting the accuracy of the truth / false determination according to the candidate's emotions, more accurate truth / false determination becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, for example, 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 processing in the truth / false determination unit may be performed using AI, for example, or without AI. For example, the truth / false determination unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0123] The truth / false determination unit can select the optimal determination method by referring to the candidate's past response data when determining truth / falseness. For example, the truth / false determination unit can refer to the candidate's past response data and use a similar determination method. For example, the truth / false determination unit can optimize the determination method for a specific skill based on the candidate's past response data. For example, the truth / false determination unit can analyze the candidate's past response data and select the optimal determination method. This allows the optimal determination method to be selected by referring to the candidate's past response data. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without a generative AI. For example, the truth / false determination unit can input the candidate's past response data into a generative AI and have the generative AI select the optimal determination method.

[0124] The truth / false determination unit can customize its judgment methods based on the candidate's current situation when making a truth / false determination. For example, the truth / false determination unit may prioritize truth / false determinations related to the candidate's current duties. The truth / false determination unit can also select appropriate truth / false determination methods according to the candidate's current situation. The truth / false determination unit can also customize its judgment methods based on the candidate's current situation. This allows for more appropriate truth / false determinations by customizing the judgment methods based on the candidate's current situation. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without a generative AI. For example, the truth / false determination unit can input the candidate's current situation data into a generative AI and have the generative AI perform the customization of the judgment methods.

[0125] The truth / false determination unit can estimate the candidate's emotions and determine the priority of truth / false determinations based on the estimated candidate's emotions. For example, if the candidate is nervous, the truth / false determination unit may prioritize truth / false determinations that help the candidate relax. For example, if the candidate is relaxed, the truth / false determination unit may also prioritize detailed truth / false determinations. For example, if the candidate is in a hurry, the truth / false determination unit may also prioritize concise truth / false determinations. This allows for more appropriate truth / false determinations by determining the priority of truth / false determinations according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the truth / false determination unit may be performed using AI, for example, or without AI. For example, the truth / false determination unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0126] The truth / false determination unit can select the optimal determination method by considering the candidate's geographical location information when determining truth / falseness. For example, the truth / false determination unit can prioritize truth / false determinations related to a region based on the candidate's geographical location information. The truth / false determination unit can also select the optimal truth / false determination method by considering the candidate's geographical location information. For example, the truth / false determination unit can select a truth / false determination method that is appropriate to the characteristics of the region based on the candidate's geographical location information. This allows the optimal determination method to be selected by considering the candidate's geographical location information. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the truth / false determination unit can input the candidate's geographical location information data into a generative AI and have the generative AI select the optimal determination method.

[0127] The truth / false determination unit can analyze the candidate's social media activity and propose a means of determination when making a truth / false determination. For example, the truth / false determination unit can analyze the candidate's social media activity and propose relevant means of truth / false determination. The truth / false determination unit can also propose the optimal means of truth / false determination based on the candidate's social media activity. The truth / false determination unit can also analyze the candidate's social media activity and propose a means of truth / false determination. This allows the optimal means of determination to be proposed by analyzing the candidate's social media activity. Some or all of the above processing in the truth / false determination unit may be performed using, for example, a generative AI, or without a generative AI. For example, the truth / false determination unit can input the candidate's social media activity data into a generative AI and have the generative AI execute the proposal of means of determination.

[0128] The criteria setting unit can estimate a candidate's emotions and set evaluation criteria based on the estimated emotions. For example, if a candidate is nervous, the criteria setting unit can set evaluation criteria to help them relax. For example, if a candidate is relaxed, the criteria setting unit can also set detailed evaluation criteria. For example, if a candidate is in a hurry, the criteria setting unit can also set concise evaluation criteria. This allows for more appropriate evaluation by setting evaluation criteria according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the criteria setting unit may be performed using AI, for example, or without AI. For example, the criteria setting unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0129] The criteria setting unit can optimize the criteria algorithm by referring to past evaluation data when setting criteria. For example, the criteria setting unit can refer to past evaluation data and use a similar criteria algorithm. For example, the criteria setting unit can optimize the criteria algorithm for a specific skill from past evaluation data. For example, the criteria setting unit can analyze past evaluation data and optimize the criteria algorithm. This allows the criteria algorithm to be optimized by referring to past evaluation data. Some or all of the above processing in the criteria setting unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the criteria setting unit can input past evaluation data into a generative AI and have the generative AI perform the optimization of the criteria algorithm.

[0130] The criteria setting unit can estimate the candidate's emotions and adjust the frequency of criteria setting based on the estimated candidate's emotions. For example, the criteria setting unit may set criteria frequently if the candidate is nervous. For example, the criteria setting unit may set detailed criteria if the candidate is relaxed. For example, the criteria setting unit may set concise criteria if the candidate is in a hurry. By adjusting the frequency of criteria setting according to the candidate's emotions, more appropriate criteria setting becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the criteria setting unit may be performed using AI, for example, or without AI. For example, the criteria setting unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0131] The criteria setting unit can weight the criteria data based on the candidate's submission timing when setting the criteria. For example, the criteria setting unit may give a higher weight if the candidate submits early. For example, the criteria setting unit may also give a lower weight if the candidate is close to the submission deadline. The criteria setting unit can also weight the criteria data based on the candidate's submission timing. This allows for more appropriate criteria setting by weighting the criteria data based on the candidate's submission timing. Some or all of the above processing in the criteria setting unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the criteria setting unit can input candidate submission timing data into a generating AI and have the generating AI perform the weighting of the criteria data.

[0132] The assignment criteria setting unit can estimate a candidate's emotions and set assignment criteria based on the estimated emotions. For example, if a candidate is nervous, the assignment criteria setting unit can set assignment criteria to help them relax. For example, if a candidate is relaxed, the assignment criteria setting unit can also set detailed assignment criteria. For example, if a candidate is in a hurry, the assignment criteria setting unit can also set concise assignment criteria. This allows for more appropriate assignments by setting assignment criteria according to the candidate's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the assignment criteria setting unit may be performed using AI, for example, or without AI. For example, the assignment criteria setting unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0133] The assignment criteria setting unit can optimize the criteria algorithm by referring to past assignment data when setting assignment criteria. For example, the assignment criteria setting unit can refer to past assignment data and use a similar criteria algorithm. For example, the assignment criteria setting unit can optimize the criteria algorithm for specific skills from past assignment data. For example, the assignment criteria setting unit can analyze past assignment data and optimize the criteria algorithm. This allows the criteria algorithm to be optimized by referring to past assignment data. Some or all of the above processing in the assignment criteria setting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assignment criteria setting unit can input past assignment data into a generative AI and have the generative AI perform the optimization of the criteria algorithm.

[0134] The assignment criteria setting unit can estimate a candidate's emotions and adjust the frequency of assignment criteria setting based on the estimated emotions. For example, if a candidate is nervous, the assignment criteria setting unit may set assignment criteria frequently. For example, if a candidate is relaxed, the assignment criteria setting unit may also set detailed assignment criteria. For example, if a candidate is in a hurry, the assignment criteria setting unit may also set concise assignment criteria. By adjusting the frequency of assignment criteria setting according to the candidate's emotions, more appropriate assignment criteria setting becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, 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 processing in the assignment criteria setting unit may be performed using AI, for example, or without AI. For example, the assignment criteria setting unit can input candidate emotion data into a generative AI and have the generative AI perform emotion estimation.

[0135] The assignment criteria setting unit can weight the criteria data based on the candidate's submission timing when setting assignment criteria. For example, the assignment criteria setting unit may give a higher weight if the candidate submits early. For example, the assignment criteria setting unit may also give a lower weight if the candidate is close to the submission deadline. The assignment criteria setting unit can also weight the criteria data based on the candidate's submission timing. This makes it possible to set more appropriate assignment criteria by weighting the criteria data based on the candidate's submission timing. Some or all of the above processing in the assignment criteria setting unit may be performed using, for example, a generation AI, or without a generation AI. For example, the assignment criteria setting unit can input candidate submission timing data into a generation AI and have the generation AI perform the weighting of the criteria data.

[0136] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0137] The analysis unit can analyze a candidate's past work history and identify skills and experience relevant to their current job. For example, the analysis unit can refer to a candidate's past work history and extract relevant skills. The analysis unit can also, for example, ask questions based on specific experiences derived from a candidate's past work history. By analyzing a candidate's past work history and identifying skills and experience relevant to their current job, the analysis unit can perform a more accurate analysis.

[0138] The evaluation unit can estimate the candidate's emotions and adjust the evaluation feedback based on those emotions. For example, if the candidate is nervous, the evaluation unit can provide feedback to help them relax. If the candidate is relaxed, the evaluation unit can also provide detailed feedback. If the candidate is in a hurry, the evaluation unit can also provide concise feedback. By adjusting the evaluation feedback according to the candidate's emotions, a more appropriate evaluation becomes possible.

[0139] The selection department can analyze a candidate's past project history and select appropriate second interviewers. For example, the selection department can refer to a candidate's past project history and select second interviewers based on relevant projects. For example, the selection department can also select second interviewers based on specific skills from a candidate's past project history. By analyzing a candidate's past project history and selecting appropriate second interviewers, the selection department can make more accurate selections.

[0140] The placement department can estimate a candidate's emotions and adjust the timing of their placement based on those emotions. For example, if a candidate is nervous, the department can set a placement timing to help them relax. If a candidate is relaxed, the department can also set a more detailed placement timing. If a candidate is in a hurry, the department can also set a more concise placement timing. By adjusting the placement timing according to the candidate's emotions, more appropriate placements become possible.

[0141] The recording unit can analyze a candidate's past interview data and optimize the recording method. For example, the recording unit can refer to a candidate's past interview data and use a similar recording method. For example, the recording unit can also optimize the recording method for specific skills based on a candidate's past interview data. By analyzing a candidate's past interview data and optimizing the recording method, for example, the recording unit can achieve more accurate records.

[0142] The analysis unit can estimate the candidate's emotions and adjust the analysis speed based on the estimated emotions. For example, if the candidate is nervous, the analysis unit can slow down the analysis speed to help them relax. If the candidate is relaxed, the analysis unit can also speed up the analysis speed to perform a more detailed analysis. If the candidate is in a hurry, the analysis unit can also adjust the speed to perform a more concise analysis. By adjusting the analysis speed according to the candidate's emotions, a more accurate analysis becomes possible.

[0143] The evaluation department can analyze a candidate's past evaluation data and optimize the evaluation criteria. For example, the evaluation department can refer to a candidate's past evaluation data and use similar evaluation criteria. For example, the evaluation department can also optimize evaluation criteria for specific skills based on a candidate's past evaluation data. By analyzing a candidate's past evaluation data and optimizing the evaluation criteria, the evaluation department can enable more accurate evaluations.

[0144] The selection process can estimate the candidate's emotions and adjust the selection criteria based on those estimates. For example, if a candidate is nervous, the selection process can use criteria to help them relax. If a candidate is relaxed, the selection process can also use detailed criteria. If a candidate is in a hurry, the selection process can also use concise criteria. By adjusting the selection criteria according to the candidate's emotions, a more appropriate selection becomes possible.

[0145] The placement department can analyze a candidate's past placement data and optimize placement methods. For example, the placement department can refer to a candidate's past placement data and use similar placement methods. For example, the placement department can also optimize placement methods for specific skills based on a candidate's past placement data. By analyzing a candidate's past placement data and optimizing placement methods, the placement department can achieve more accurate placements.

[0146] The recording unit can estimate the candidate's emotions and adjust the recording method based on the estimated emotions. For example, if the candidate is nervous, the recording unit will use a recording method to help them relax. For example, if the candidate is relaxed, the recording unit may use a detailed recording method. For example, if the candidate is in a hurry, the recording unit may use a concise recording method. This allows for more appropriate recording by adjusting the recording method according to the candidate's emotions.

[0147] The following briefly describes the processing flow for example form 2.

[0148] Step 1: The analysis unit analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. For example, AI can be used to analyze the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. Step 2: The evaluation unit assesses the candidate's strengths and characteristics based on the results analyzed by the analysis unit. For example, AI can be used to assess the candidate's strengths and characteristics. Step 3: The selection unit selects appropriate second interviewers based on the evaluation results obtained by the evaluation unit. For example, AI can be used to select appropriate second interviewers. Step 4: The Placement Department considers the most suitable placement and role for each candidate based on their personality and skills, using the evaluation results obtained by the Evaluation Department. For example, AI can be used to comprehensively evaluate a candidate's personality and skills and consider the most suitable placement and role. Step 5: The recording unit records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. For example, AI can be used to save the conversation data with the candidate and save it as data that can be re-evaluated and compared later.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0151] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the analysis unit, evaluation unit, selection unit, assignment unit, recording unit, facial expression analysis unit, truth / false determination unit, standard setting unit, and assignment standard setting unit, is implemented by, for example, at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 and analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The evaluation unit is implemented by, for example, the identification processing unit 290 of the data processing device 12 and evaluates the candidate's strengths and characteristics based on the analysis results. The selection unit is implemented by, for example, the control unit 46A of the smart device 14 and selects an appropriate second interviewer based on the evaluation results. The assignment unit is implemented by, for example, the identification processing unit 290 of the data processing device 12 and considers the optimal assignment location and role according to the candidate's personality and skills. The recording unit is implemented by, for example, the control unit 46A of the smart device 14 and records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. The facial expression analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the candidate's facial expressions and tone of voice. The truth / false determination unit is implemented, for example, by the control unit 46A of the smart device 14, and determines the truth or falsity of the answer. The standard setting unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and sets evaluation criteria. The assignment criteria setting unit is implemented, for example, by the control unit 46A of the smart device 14, and sets assignment criteria according to the candidate's personality and skills. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0153] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0154] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0156] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

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

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0163] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] Each of the multiple elements described above, including the analysis unit, evaluation unit, selection unit, assignment unit, recording unit, facial expression analysis unit, truth / false judgment unit, standard setting unit, and assignment standard setting unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The evaluation unit is implemented by, for example, the identification processing unit 290 of the data processing device 12 and evaluates the candidate's strengths and characteristics based on the analysis results. The selection unit is implemented by, for example, the control unit 46A of the smart glasses 214 and selects an appropriate second interviewer based on the evaluation results. The assignment unit is implemented by, for example, the identification processing unit 290 of the data processing device 12 and considers the optimal assignment location and role according to the candidate's personality and skills. The recording unit is implemented by, for example, the control unit 46A of the smart glasses 214 and records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. The facial expression analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the candidate's facial expressions and tone of voice. The truthfulness determination unit is implemented, for example, by the control unit 46A of the smart glasses 214, and determines the truthfulness of the answers. The standard setting unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and sets evaluation criteria. The assignment criteria setting unit is implemented, for example, by the control unit 46A of the smart glasses 214, and sets assignment criteria according to the candidate's personality and skills. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0169] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0170] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0172] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0176] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0177] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0178] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0179] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0180] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0181] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0182] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0183] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0184] Each of the multiple elements described above, including the analysis unit, evaluation unit, selection unit, assignment unit, recording unit, facial expression analysis unit, truth / false judgment unit, standard setting unit, and assignment standard setting unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The evaluation unit is implemented by, for example, the identification processing unit 290 of the data processing device 12 and evaluates the candidate's strengths and characteristics based on the analysis results. The selection unit is implemented by, for example, the control unit 46A of the headset terminal 314 and selects an appropriate second interviewer based on the evaluation results. The assignment unit is implemented by, for example, the identification processing unit 290 of the data processing device 12 and considers the optimal assignment location and role according to the candidate's personality and skills. The recording unit is implemented by, for example, the control unit 46A of the headset terminal 314 and records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. The facial expression analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the candidate's facial expressions and tone of voice. The truthfulness determination unit is implemented, for example, by the control unit 46A of the headset terminal 314, and determines the truthfulness of the answers. The standard setting unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and sets evaluation criteria. The assignment criteria setting unit is implemented, for example, by the control unit 46A of the headset terminal 314, and sets assignment criteria according to the candidate's personality and skills. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0185] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0186] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0187] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0188] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0189] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0191] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0192] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0193] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0194] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0195] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0196] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0197] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0198] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0199] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0200] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0201] Each of the multiple elements described above, including the analysis unit, evaluation unit, selection unit, assignment unit, recording unit, facial expression analysis unit, truth / false determination unit, standard setting unit, and assignment standard setting unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 and analyzes the candidate's thinking style, personality, facial expressions, and tone of voice in their responses. The evaluation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and evaluates the candidate's strengths and characteristics based on the analysis results. The selection unit is implemented by, for example, the control unit 46A of the robot 414 and selects an appropriate second interviewer based on the evaluation results. The assignment unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and considers the optimal assignment location and role according to the candidate's personality and skills. The recording unit is implemented by, for example, the control unit 46A of the robot 414 and records the conversation with the candidate and saves it as data that can be re-evaluated and compared later. The facial expression analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the candidate's facial expressions and tone of voice. The truth / false determination unit is implemented, for example, by the control unit 46A of the robot 414, and determines the truth or falsity of the answer. The standard setting unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and sets evaluation criteria. The assignment criteria setting unit is implemented, for example, by the control unit 46A of the robot 414, and sets assignment criteria according to the candidate's personality and skills. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0202] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0203] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0204] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0205] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0206] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0207] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0208] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0209] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0210] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0211] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0212] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0213] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0214] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0215] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0216] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0217] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0218] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0219] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0220] (Note 1) The analysis unit analyzes the candidate's thinking style and personality, as well as their facial expressions and tone of voice when answering questions. An evaluation unit that evaluates the candidate's strengths and characteristics based on the results of the analysis performed by the aforementioned analysis unit, A selection unit selects appropriate second interviewers based on the evaluation results obtained by the aforementioned evaluation unit, Based on the evaluation results obtained by the aforementioned evaluation department, the placement department considers the most suitable placement and role for each candidate according to their individuality and skills. It includes a recording unit that records conversations with candidates and saves them as data that can be re-evaluated and compared later. A system characterized by the following features. (Note 2) It is equipped with a facial expression analysis unit that analyzes the candidate's facial expressions and tone of voice. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a truth / false determination unit to determine the truth or falsity of the answer. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a criteria setting unit for establishing evaluation criteria to assess the strengths and characteristics of candidates. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a placement criteria setting unit that sets placement criteria to consider the most suitable placement and role for each candidate based on their individuality and skills. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, The system estimates the candidates' emotions and adjusts the accuracy of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, Analyze the candidate's past interview history and select the most suitable analysis method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, During the analysis, filtering is performed based on the candidates' current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, The system estimates the candidates' emotions and prioritizes the analysis results based on the estimated emotions of the candidates. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, During analysis, the system prioritizes analyzing highly relevant data, taking into account the candidates' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, During the analysis, the candidate's social media activity is analyzed, and relevant data is analyzed. The system described in Appendix 1, characterized by the features described herein. (Note 12) The evaluation unit, The system estimates the candidate's emotions and adjusts the way evaluations are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The evaluation unit, During the evaluation process, adjust the level of detail based on the importance of the candidate. The system described in Appendix 1, characterized by the features described herein. (Note 14) The evaluation unit, During evaluation, different evaluation algorithms are applied depending on the candidate's category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The evaluation unit, Estimate the candidate's sentiment and adjust the length of the evaluation based on the estimated candidate's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The evaluation unit, During the evaluation process, priority will be determined based on the timing of candidate submissions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The evaluation unit, During the evaluation process, the order of evaluations will be adjusted based on the relevance of the candidates. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned selection unit is The system estimates the candidates' sentiments and adjusts the selection criteria based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned selection unit is When selecting candidates, consider their interrelationships to improve the accuracy of the selection process. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned selection unit is When making a selection, the candidate's attribute information will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned selection unit is The system estimates the candidates' sentiments and adjusts the order in which the selection results are displayed based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned selection unit is The selection process takes into account the geographical distribution of the candidates. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned selection unit is During the selection process, we refer to relevant literature for each candidate to improve the accuracy of the selection. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned assignment unit is, The system estimates the candidates' emotions and adjusts the assignment method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned assignment unit is, When assigning a candidate, their past assignment history is analyzed to select the most suitable assignment method. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned assignment unit is, When assigning a position, customize the assignment method based on the candidate's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned assignment unit is, The system estimates the candidates' emotions and determines placement priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned assignment unit is, When assigning candidates, the most suitable assignment method will be selected, taking into account the candidate's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned assignment unit is, When assigning candidates to positions, we analyze their social media activity and propose placement methods. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned recording unit is The system estimates the candidates' emotions and selects the recording data based on the estimated emotions of the candidates. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned recording unit is During recording, the recording algorithm is optimized by referring to past recording data. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned recording unit is The system estimates the candidate's sentiment and adjusts the frequency of recordings based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned recording unit is During recording, the recorded data is weighted based on when the candidate submitted their application. The system described in Appendix 1, characterized by the features described herein. (Note 34) The facial expression analysis unit, The system estimates the candidate's emotions and adjusts the accuracy of facial expression analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The facial expression analysis unit, During facial expression analysis, the optimal analysis method is selected by referring to the candidate's past facial expression data. The system described in Appendix 1, characterized by the features described herein. (Note 36) The facial expression analysis unit, During facial expression analysis, the analysis method is customized based on the candidate's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 37) The facial expression analysis unit, The system estimates the candidate's emotions and determines the priority of facial expression analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The facial expression analysis unit, When analyzing facial expressions, the optimal analysis method is selected by considering the candidate's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 39) The facial expression analysis unit, When analyzing facial expressions, we analyze candidates' social media activity and propose methods for analysis. The system described in Appendix 1, characterized by the features described herein. (Note 40) The truth / false determination unit is, The system estimates the candidate's sentiment and adjusts the accuracy of the truthfulness judgment based on the estimated candidate's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 41) The truth / false determination unit is, When determining truthfulness, the system selects the most appropriate method by referring to the candidate's past response data. The system described in Appendix 1, characterized by the features described herein. (Note 42) The truth / false determination unit is, Customize the means of judgment based on the current situation of the candidate when making a true / false judgment The system according to appended note 1, characterized in that (Appended note 43) The true / false judgment unit Estimate the emotions of the candidate and determine the priority order of true / false judgment based on the estimated emotions of the candidate The system according to appended note 1, characterized in that (Appended note 44) The true / false judgment unit Select an optimal judgment method considering the geographical location information of the candidate when making a true / false judgment The system according to appended note 1, characterized in that (Appended note 45) The true / false judgment unit Analyze the social media activities of the candidate when making a true / false judgment and propose means of judgment The system according to appended note 1, characterized in that (Appended note 46) The reference setting unit Estimate the emotions of the candidate and set evaluation criteria based on the estimated emotions of the candidate The system according to appended note 1, characterized in that (Appended note 47) The reference setting unit Optimize the reference algorithm by referring to past evaluation data when setting the reference The system according to appended note 1, characterized in that (Appended note 48) The reference setting unit Estimate the emotions of the candidate and adjust the frequency of reference setting based on the estimated emotions of the candidate The system according to appended note 1, characterized in that (Appended note 49) The reference setting unit Perform weighting of reference data based on the submission time of the candidate when setting the reference The system according to appended note 1, characterized in that (Appended note 50) The assignment reference setting unit The system estimates the candidates' emotions and sets placement criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 51) The aforementioned assignment criteria setting unit is: When setting assignment criteria, the criteria algorithm is optimized by referring to past assignment data. The system described in Appendix 1, characterized by the features described herein. (Note 52) The aforementioned assignment criteria setting unit is: Estimate the candidate's emotions and adjust the frequency of setting placement criteria based on the estimated candidate emotions. The system described in Appendix 1, characterized by the features described herein. (Note 53) The aforementioned assignment criteria setting unit is: When setting assignment criteria, the criteria data is weighted based on when the candidates submitted their data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0221] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes the candidate's thinking style and personality, as well as their facial expressions and tone of voice when answering questions. An evaluation unit that evaluates the candidate's strengths and characteristics based on the results of the analysis performed by the aforementioned analysis unit, A selection unit selects appropriate second interviewers based on the evaluation results obtained by the aforementioned evaluation unit, Based on the evaluation results obtained by the aforementioned evaluation department, the placement department considers the most suitable placement and role for each candidate according to their individuality and skills. It includes a recording unit that records conversations with candidates and saves them as data that can be re-evaluated and compared later. A system characterized by the following features.

2. It is equipped with a facial expression analysis unit that analyzes the candidate's facial expressions and tone of voice. The system according to feature 1.

3. It includes a truth / false determination unit to determine the truth or falsity of the answer. The system according to feature 1.

4. It includes a criteria setting unit for establishing evaluation criteria to assess the strengths and characteristics of candidates. The system according to feature 1.

5. It includes a placement criteria setting unit that sets placement criteria to consider the most suitable placement and role for each candidate based on their individuality and skills. The system according to feature 1.

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

7. The aforementioned analysis unit, Analyze the candidate's past interview history and select the most suitable analysis method. The system according to feature 1.

8. The aforementioned analysis unit, During the analysis, filtering is performed based on the candidates' current situation and areas of interest. The system according to feature 1.

Images