System

Abstract

To provide a system capable of efficiently selecting a candidate for the second interview and considering placement by analyzing the dialogue data of the candidate.SOLUTION: The system in an embodiment includes a collection unit, an analysis unit, a selection unit, and an assignment unit. The collection unit collects dialogue data with a candidate. The analysis unit analyzes the dialogue data collected by the collection unit. The selection unit selects a second interviewee based on the analysis results obtained by the analysis unit. The assignment unit considers where to assign based on the regional characteristics of the candidate selected by the selection unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not efficiently select second interviewers or consider assignment destinations based on candidates' dialogue data, so there is room for improvement.

[0005] The system according to the embodiment aims to analyze dialogue data of candidates and efficiently select candidates for a second interview and consider assignment destinations. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a selection unit, and an assignment unit. The collection unit collects dialogue data with candidates. The analysis unit analyzes the dialogue data collected by the collection unit. The selection unit selects a second interviewer based on the analysis results obtained by the analysis unit. The assignment unit considers assignment destinations based on the regional characteristics of the candidates selected by the selection unit. Effect of the Invention

[0007] The system according to the embodiment can analyze dialogue data of candidates and efficiently select second interviewees and consider assignment destinations. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The employment interview support system according to the embodiment of the present invention is a system that utilizes a generation AI to make employment interviews more efficient and analyze the thinking type and personality of candidates. In this system, the generation AI collects and analyzes dialogue data with the candidates to evaluate the thinking type and personality of the candidates. Based on the evaluation results, the second interviewer is selected and the assignment destination based on the regionality is considered. This makes the recruitment process more efficient and makes it possible to accurately evaluate the compatibility and aptitude of the candidates. For example, the contents and answers spoken by the candidates during the interview are recorded in detail, and the generation AI analyzes the data. Based on the analysis results, candidates with thinking types and personalities suitable for a specific position are selected and the optimal assignment destination is proposed. This mechanism strengthens the company's human resource strategy and improves the success rate of recruitment. As a result, the employment interview support system can automatically collect and analyze dialogue data of candidates, select appropriate candidates, and propose the optimal assignment destination.

[0029] The employment interview support system according to the embodiment includes a collection unit, an analysis unit, a selection unit, and an assignment unit. The collection unit collects dialogue data with the candidate. The dialogue data with the candidate includes, for example, voice data, text data, video data, etc., but is not limited to such examples. The collection unit, for example, records in detail the contents of what the candidate said during the interview and the answers he or she answered. For example, the collection unit collects data when the candidate introduces himself or herself or answers a specific question. The analysis unit uses a generation AI to analyze the dialogue data collected by the collection unit. The analysis is performed, for example, by a method such as natural language processing, emotion analysis, keyword extraction, etc., but is not limited to such examples. For example, the analysis unit analyzes the contents of the candidate's remarks, the choice of words, the characteristics of the way he or she speaks, etc., and evaluates the candidate's thinking type and personality. The selection unit selects a second interviewer based on the analysis result obtained by the analysis unit. The selection is performed, for example, according to a scoring system or evaluation criteria, but is not limited to such examples. For example, the selection unit selects a candidate with a thinking type and personality suitable for a specific position. The allocation department proposes an optimal assignment destination based on the regional characteristics of the candidate selected by the selection department. The assignment destination proposal is made based on criteria such as, for example, place of residence, place of work, and commuting time, but is not limited to such examples. For example, the allocation department selects a candidate suitable for work in a specific region based on the candidate's personality and thinking type, and assigns the candidate to that region. In this way, the recruitment interview support system according to the embodiment can automatically collect and analyze conversation data of candidates, select appropriate candidates, and propose optimal assignment destinations.

[0030] The collection unit collects dialogue data with the candidate. The dialogue data with the candidate includes, but is not limited to, voice data, text data, video data, and the like. The collection unit, for example, records in detail the contents and answers that the candidate spoke during the interview. Specifically, the collection unit uses a high-precision microphone and camera to collect the voice and video of the candidate in real time. The voice data records in detail the contents of the candidate's remarks, tone of voice, speaking speed, and the like, and the text data converts the voice into text using voice recognition technology. The video data includes non-verbal information such as the candidate's facial expressions, gestures, and posture. These data are continuously collected throughout the entire interview process and stored in a central database. Furthermore, the collection unit not only collects data when the candidate introduces himself or herself or answers specific questions, but also simultaneously records the questions and reactions of the interviewer. This makes it possible to grasp the overall flow and context of the dialogue. The collection unit centrally manages these data and makes them accessible to the analysis unit and selection unit. In addition, the collection unit adjusts the frequency and accuracy of data collection, allowing for flexible responses according to specific situations and conditions. For example, if the answer to a particular question is important, the data for that part can be set to be collected with high accuracy, allowing the collection unit to collect data efficiently and effectively, improving the performance of the entire system.

[0031] The analysis unit uses the generation AI to analyze the dialogue data collected by the collection unit. The analysis is performed by, for example, natural language processing, emotion analysis, keyword extraction, and other methods, but is not limited to these examples. Specifically, the natural language processing technology is used to analyze the content of the candidate's remarks and understand the context and intent. In emotion analysis, changes in emotions are detected from the candidate's tone of voice and facial expressions, and the degree of stress and tension is evaluated. In keyword extraction, important keywords and phrases are extracted from the candidate's remarks and specific skills and experience are evaluated. The generation AI integrates these analysis results and evaluates the candidate's thinking type and personality. For example, the content of the candidate's remarks, choice of words, and speaking characteristics are analyzed to evaluate characteristics such as logical thinking, creativity, and cooperativeness. Furthermore, the analysis unit builds a model to predict the suitability of the candidate based on past interview data and successful hiring cases. This allows the analysis unit to quickly and accurately analyze the collected data and evaluate the characteristics and suitability of the candidate. The analysis unit provides these analysis results to the selection unit, which is useful for selecting second interviewers. In addition, the analysis unit can continuously learn the analysis results and improve the analysis accuracy. This enables the analysis unit to not only grasp the situation in real time, but also handle long-term risk management and anomaly detection, improving the reliability and safety of the entire system.

[0032] The selection unit selects candidates for the second interview based on the analysis results obtained by the analysis unit. The selection is performed, for example, according to a scoring system or evaluation criteria, but is not limited to such examples. Specifically, a score is given to each candidate based on information such as the candidate's thinking type, personality, and skill set provided by the analysis unit. The scoring system emphasizes the skills and characteristics required for a specific position and evaluates the candidates based on that. For example, for a position requiring leadership, a high score is given to a candidate with high leadership skills and communication skills. The selection unit selects the most suitable candidate based on these scores. In addition, the selection unit can flexibly set the evaluation criteria. For example, the evaluation criteria are customized according to the needs of a specific project or team, and the most suitable candidate is selected. Furthermore, the selection unit evaluates the aptitude and potential of the candidate based on the analysis results, and makes the selection taking into consideration the future growth potential. This allows the selection unit to select an appropriate candidate not only from a short-term need but also from a long-term perspective. The selection unit provides the selection results to the assignment unit, which helps in proposing the most suitable assignment. This enables the selection unit to efficiently and effectively select second interviewers, improving the performance of the entire system.

[0033] The allocation department proposes the most suitable place of assignment based on the regional characteristics of the candidate selected by the selection department. The proposal of the place of assignment is made based on criteria such as, for example, place of residence, place of work, and commuting time, but is not limited to such examples. Specifically, the optimal place of work is proposed based on the candidate's place of residence information, taking into consideration the commuting time and transportation means. For example, if the candidate lives in an urban area, the commuting time can be shortened and work efficiency can be improved by assigning the candidate to an office or project in the urban area. In addition, the allocation department selects candidates suitable for work in a specific area based on the candidate's personality and thinking type, and assigns them to that area. For example, a candidate with high cooperativeness is assigned to a project where teamwork is emphasized, and a candidate with high expertise is assigned to a project where individual skills are emphasized. Furthermore, the allocation department can propose the most suitable place of assignment taking into consideration the candidate's wishes and career plan. For example, if a candidate wishes to gain experience in a specific field, the candidate's career growth is supported by assigning him / her to a project or team related to that field. Based on this information, the Assignment Department can propose optimal assignment destinations and improve candidate satisfaction and work efficiency. This allows the Assignment Department to assign candidates efficiently and effectively, improving the performance of the entire system.

[0034] The collection unit can record in detail the contents or answers spoken by the candidate during the interview. Methods of recording in detail include, for example, recording, transcribing, adding metadata, and the like, but are not limited to such examples. For example, the collection unit records the contents spoken by the candidate during the interview using a high-precision recording device and saves the audio data. The collection unit can also convert the recorded audio data into text data using transcription software. Furthermore, the collection unit can add metadata to the collected dialogue data and record attribute information of the data. For example, the collection unit adds metadata such as the date and time of the dialogue, the location, and basic information of the candidate to the dialogue data. This allows the collection unit to record in detail the contents and answers spoken by the candidate during the interview, improving the accuracy of the analysis. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the dialogue data of the candidate into the generation AI, and the generation AI can automatically record the dialogue data in detail.

[0035] The analysis unit can analyze the contents of the candidate's remarks, the choice of words, and the characteristics of the way of speaking to evaluate the thinking type and personality. The analysis unit, for example, analyzes the contents of the candidate's remarks. Methods of analyzing the contents of the remarks include, for example, keyword extraction, context analysis, and the like, but are not limited to such examples. The analysis unit, for example, extracts important keywords from the contents of the candidate's remarks and analyzes the frequency and relevance of the keywords. The analysis unit can also analyze the context of the contents of the candidate's remarks to evaluate the intention and meaning of the remarks. Furthermore, the analysis unit analyzes the choice of words of the candidate. Methods of analyzing the choice of words include, for example, the frequency of positive / negative words, the use of technical terms, and the like, but are not limited to such examples. The analysis unit, for example, analyzes the frequency of positive and negative words included in the remarks of the candidate to evaluate the emotions and attitudes of the candidate. The analysis unit can also analyze the frequency of technical terms used by the candidate to evaluate the expertise and skills of the candidate. Furthermore, the analysis unit analyzes the characteristics of the way the candidate speaks. Methods for analyzing the characteristics of speaking style include, for example, speech speed, intonation, pauses, etc., but are not limited to such examples. For example, the analysis unit analyzes the speech speed of the candidate to evaluate the rhythm and tempo of the speech. The analysis unit can also analyze the intonation of the candidate's remarks to evaluate the way of expressing emotions and emphasizing them. In this way, the analysis unit can analyze the contents of the candidate's remarks, the choice of words, and the characteristics of the speaking style, and evaluate the thinking type and personality. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit inputs the dialogue data of the candidate into the generation AI, and the generation AI can automatically analyze the contents of the remarks, the choice of words, and the characteristics of the speaking style.

[0036] The selection unit can select candidates having a thinking type or personality suitable for a specific position. The selection unit selects candidates suitable for a specific position, for example, based on the analysis results obtained by the analysis unit. Selection criteria include, for example, a scoring system and evaluation criteria, but are not limited to such examples. The selection unit selects candidates suitable for a specific position, for example, based on the candidate's thinking type or personality. For example, the selection unit selects candidates having a logical thinking type suitable for a sales position. The selection unit can also select candidates having specialized knowledge suitable for a technical position. Furthermore, the selection unit can also select candidates having leadership skills suitable for a managerial position. This allows the selection unit to select candidates having a thinking type or personality suitable for a specific position, improving the success rate of recruitment. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit inputs the analysis results obtained by the analysis unit into the generation AI, and the generation AI can automatically select a candidate suitable for a specific position.

[0037] The assignment department can propose an appropriate assignment based on the personality or thinking type of the candidate. The assignment department proposes an optimal assignment based on, for example, the personality and thinking type of the candidate selected by the selection department. The criteria for suggesting an assignment include, for example, department, project, work location, etc., but are not limited to such examples. The assignment department selects a candidate suitable for work in a specific area based on, for example, the personality and thinking type of the candidate, and assigns the candidate to that area. For example, if the candidate has a sociable personality, the assignment department can assign the candidate to a sales position or customer support position. In addition, if the candidate has a logical thinking type, the assignment department can assign the candidate to a technical position or data analysis position. Furthermore, the assignment department can propose a flexible working style such as remote work or flextime based on the personality and thinking type of the candidate. This allows the assignment department to propose an optimal assignment based on the personality and thinking type of the candidate, thereby strengthening the company's human resource strategy. A part or all of the above-mentioned processing in the assignment department may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the placement department can input data on a candidate's personality and thinking type into the generation AI, which can then automatically suggest the most suitable placement.

[0038] The collection unit can analyze the past interview history of the candidate and select an appropriate collection method. The collection unit, for example, analyzes the past interview history of the candidate. The method of analyzing the past interview history includes, for example, the number of interviews, the content of questions, and the evaluation results, but is not limited to such examples. For example, the collection unit prioritizes and collects question formats that the candidate has preferred in the past. The collection unit can also collect questions while avoiding questions that the candidate was weak at in the past. Furthermore, the collection unit can select the most effective collection timing from the past interview history of the candidate. In this way, the collection unit can select the optimal collection method by analyzing the past interview history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the past interview history data of the candidate to the generation AI, and the generation AI can automatically select the optimal collection method.

[0039] The collection unit can filter the dialogue data based on the candidate's current work experience and skill set when collecting the dialogue data. The collection unit, for example, filters the dialogue data based on the candidate's current work experience and skill set. Filtering criteria include, for example, the type of job, years of experience, and achievements, but are not limited to such examples. The collection unit, for example, prioritizes and collects questions related to the candidate's current work experience. The collection unit can also collect related dialogue data based on the candidate's skill set. Furthermore, the collection unit can filter unnecessary data based on the candidate's work experience and skill set. This allows the collection unit to collect related dialogue data based on the candidate's work experience and skill set. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit inputs data on the candidate's work experience and skill set into the generation AI, and the generation AI can automatically perform filtering.

[0040] The collection unit can collect highly relevant data preferentially based on the geographical location information of the candidate when collecting the dialogue data. The collection unit, for example, collects dialogue data taking into account the geographical location information of the candidate. Methods of considering the geographical location information include, for example, addresses, GPS data, area codes, and the like, but are not limited to such examples. The collection unit, for example, prioritizes questions specific to a region based on the geographical location of the candidate. The collection unit can also preferentially collect work experience related to the geographical location of the candidate. Furthermore, the collection unit can also collect related company information based on the geographical location of the candidate. In this way, the collection unit can collect highly relevant data by considering the geographical location information of the candidate. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the geographical location information of the candidate to the generation AI, and the generation AI can automatically collect highly relevant data preferentially.

[0041] The collection unit can analyze the candidate's social media activity and collect related data when collecting the dialogue data. The collection unit, for example, analyzes the candidate's social media activity. Methods for analyzing social media activity include, but are not limited to, for example, the content of posts, the number of followers, and the engagement rate. The collection unit, for example, collects questions reflecting interests from the candidate's social media activity. The collection unit can also collect related work experience based on the candidate's social media activity. Furthermore, the collection unit can analyze the candidate's social media activity and collect data for evaluating aptitude. In this way, the collection unit can collect related data by analyzing the candidate's social media activity. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the candidate's social media activity data into the generation AI, and the generation AI can automatically collect related data.

[0042] The analysis unit can adjust the level of detail of the analysis based on the importance of the candidate's statement during the analysis. The analysis unit, for example, evaluates the importance of the candidate's statement. Methods for evaluating the importance of the statement include, for example, the frequency of keywords and the importance of the context, but are not limited to such examples. The analysis unit, for example, extracts important keywords from the content of the candidate's statement and evaluates the frequency and relevance of the keywords. The analysis unit can also analyze the context of the content of the candidate's statement and evaluate the intention and meaning of the statement. The analysis unit adjusts the level of detail of the analysis based on the importance of the statement. Adjustments to the level of detail include, for example, the depth of analysis and the granularity of information, but are not limited to such examples. For example, the analysis unit performs a detailed analysis on important statements. Furthermore, the analysis unit can perform a simplified analysis on general statements. Furthermore, the analysis unit can also adjust the depth of the analysis according to the importance of the candidate's statement. As a result, the analysis unit can perform a more accurate analysis by adjusting the level of detail of the analysis according to the importance of the candidate's statement. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs the candidate's utterance data into the generation AI, and the generation AI automatically evaluates the importance of the utterance and adjusts the level of detail of the analysis.

[0043] The analysis unit can apply different analysis algorithms depending on the job category of the candidate during the analysis. The analysis unit, for example, identifies the job category of the candidate. Methods for identifying the job category include, for example, the type of job, years of experience, and achievements, but are not limited to such examples. The analysis unit, for example, analyzes the job history of the candidate to identify the job category. In addition, the analysis unit applies different analysis algorithms depending on the job category of the candidate. Methods for applying the analysis algorithm include, for example, machine learning algorithms and statistical analysis algorithms, but are not limited to such examples. For example, the analysis unit applies an analysis algorithm that emphasizes technical skills to candidates for technical positions. In addition, the analysis unit can apply an analysis algorithm that emphasizes communication skills to candidates for sales positions. Furthermore, the analysis unit can also apply an analysis algorithm that emphasizes leadership skills to candidates for managerial positions. This allows the analysis unit to perform more appropriate analysis by applying an analysis algorithm according to the job category of the candidate. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input a candidate's job category data into the generation AI, which can then automatically apply an appropriate analysis algorithm.

[0044] The analysis unit can determine the priority of the analysis based on the interview time of the candidate at the time of analysis. The analysis unit, for example, identifies the interview time of the candidate. The method of identifying the interview time includes, for example, the interview date, the application period, the selection stage, etc., but is not limited to such examples. The analysis unit, for example, identifies the interview date of the candidate and prioritizes the analysis of the most recent interview data. The analysis unit can also identify the application period of the candidate and prioritize the analysis of data within the application period. Furthermore, the analysis unit can also identify the selection stage of the candidate and adjust the order of analysis based on the selection stage. As a result, the analysis unit can determine the priority of the analysis based on the interview time of the candidate, thereby enabling efficient analysis. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the interview time data of the candidate to the generation AI, and the generation AI can automatically determine the priority of the analysis.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the candidate during analysis. The analysis unit, for example, evaluates the relevance of the candidate. The method of evaluating the relevance includes, for example, job relevance, skill relevance, and the like, but is not limited to such examples. The analysis unit, for example, analyzes highly relevant data by giving priority to the work experience of the candidate. The analysis unit can also analyze highly relevant data by giving priority to the skill set of the candidate. Furthermore, the analysis unit can also analyze highly relevant data by giving priority to the work aptitude of the candidate. The analysis unit adjusts the order of analysis based on the relevance. The adjustment of the order includes, for example, priority order, importance, and the like, but is not limited to such examples. The analysis unit, for example, analyzes highly relevant data by giving priority to the work experience of the candidate. The analysis unit can also analyze highly relevant data by giving priority to the skill set of the candidate. Furthermore, the analysis unit can also analyze highly relevant data by giving priority to the work aptitude of the candidate. As a result, the analysis unit adjusts the order of analysis based on the relevance of the candidate, thereby enabling efficient analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs the candidate's relevance data into the generation AI, and the generation AI can automatically adjust the order of analysis.

[0046] The selection unit can improve the accuracy of selection by considering the interrelationships of the candidates at the time of selection. The selection unit, for example, evaluates the interrelationships of the candidates. The method of evaluating the interrelationships includes, for example, the history of joint projects, mutual evaluation, etc., but is not limited to such examples. The selection unit, for example, analyzes the interrelationships between the candidates and evaluates the aptitude for teamwork. The selection unit can also select by considering the past cooperative relationships of the candidates. Furthermore, the selection unit can also propose an optimal team composition based on the interrelationships of the candidates. As a result, the selection unit improves the accuracy of selection by considering the interrelationships of the candidates. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit inputs the interrelationship data of the candidates into the generation AI, and the generation AI automatically evaluates the interrelationships, thereby improving the accuracy of selection.

[0047] The selection unit can make a selection by taking into consideration the attribute information of the candidate. The selection unit, for example, evaluates the attribute information of the candidate. The evaluation method of the attribute information includes, for example, age, gender, and educational background, but is not limited to such examples. The selection unit makes a selection by taking into consideration, for example, the age and gender of the candidate. The selection unit can also make a selection by taking into consideration the educational background and work history of the candidate. Furthermore, the selection unit can also make a selection by taking into consideration the skill set and qualifications of the candidate. In this way, the selection unit can select a more suitable candidate by taking into consideration the attribute information of the candidate. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input attribute information data of the candidate into the generation AI, and the generation AI can automatically evaluate the attribute information and make a selection.

[0048] The selection unit can make a selection taking into consideration the geographic distribution of the candidates. The selection unit, for example, evaluates the geographic distribution of the candidates. The evaluation method of the geographic distribution includes, for example, the place of residence, the place of work, and the commuting time, but is not limited to such examples. The selection unit, for example, proposes an optimal place of work based on the place of residence of the candidate. In addition, the selection unit can optimize the team composition by taking into consideration the geographic distribution of the candidates. Furthermore, the selection unit can also evaluate the suitability of remote work based on the geographic distribution of the candidates. In this way, the selection unit can select a more appropriate candidate by taking into consideration the geographic distribution of the candidates. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the geographic distribution data of the candidates into the generation AI, and the generation AI can automatically evaluate the geographic distribution and make the selection.

[0049] The selection unit can improve the accuracy of the selection by referring to the candidate's related literature at the time of selection. The selection unit, for example, refers to the candidate's related literature. The method of referring to the related literature includes, but is not limited to, academic papers, technical reports, industry news, and the like. The selection unit, for example, refers to the candidate's research papers to evaluate the candidate's expertise. The selection unit can also evaluate the candidate's practical experience by referring to the candidate's past project reports. Furthermore, the selection unit can also analyze the candidate's related literature and collect data for evaluating aptitude. As a result, the selection unit improves the accuracy of the selection by referring to the candidate's related literature. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the selection unit inputs the candidate's related literature data into the generation AI, and the generation AI automatically refers to the related literature, thereby improving the accuracy of the selection.

[0050] The assignment department can select the most suitable assignment destination by analyzing the candidate's past work history at the time of assignment. The assignment department, for example, analyzes the candidate's past work history. The method of analyzing the past work history includes, for example, the type of work, years of experience, and achievements, but is not limited to such examples. The assignment department, for example, proposes a related assignment destination based on the candidate's past work history. The assignment department can also analyze the candidate's work history and select the most suitable assignment destination. Furthermore, the assignment department can also propose a highly suitable assignment destination based on the candidate's past work history. In this way, the assignment department can select the most suitable assignment destination by analyzing the candidate's past work history. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the assignment department can input the candidate's past work history data into the generation AI, and the generation AI can automatically select the most suitable assignment destination.

[0051] The assignment department can customize the means of the assignment destination based on the candidate's current living situation at the time of assignment. The assignment department, for example, evaluates the candidate's current living situation. The evaluation method of the living situation includes, for example, family composition, commuting time, living environment, etc., but is not limited to such examples. For example, if the candidate needs to live in a specific area due to family circumstances, the assignment department assigns the candidate to that area. In addition, if the candidate wishes to work remotely, the assignment department can propose an assignment destination that allows remote work. Furthermore, the assignment department can also propose an assignment destination that takes commuting time into consideration based on the candidate's living situation. As a result, the assignment department can propose a more appropriate assignment destination by customizing the assignment destination based on the candidate's living situation. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the assignment department can input the candidate's living situation data into the generation AI, and the generation AI can automatically customize the means of the assignment destination.

[0052] The assignment department can select the optimal assignment destination by considering the geographical location information of the candidate at the time of assignment. The assignment department, for example, evaluates the geographical location information of the candidate. The evaluation method of the geographical location information includes, for example, an address, GPS data, a region code, etc., but is not limited to such examples. The assignment department, for example, proposes the optimal work location based on the candidate's place of residence. In addition, the assignment department can select an assignment destination that minimizes commuting time by considering the geographical location information of the candidate. Furthermore, the assignment department can also evaluate the suitability of remote work based on the geographical location information of the candidate. In this way, the assignment department can select the optimal assignment destination by considering the geographical location information of the candidate. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the assignment department can input the geographical location information data of the candidate into the generation AI, and the generation AI can automatically select the optimal assignment destination.

[0053] At the time of assignment, the assignment department can analyze the social media activity of the candidate and propose a means of assignment. The assignment department, for example, analyzes the social media activity of the candidate. Methods of analyzing social media activity include, for example, but are not limited to, the content of posts, the number of followers, and the engagement rate. The assignment department, for example, proposes an assignment that reflects the candidate's interests from the social media activity of the candidate. The assignment department can also propose an assignment that takes into account the candidate's related work experience based on the candidate's social media activity. Furthermore, the assignment department can also analyze the candidate's social media activity and propose an assignment to evaluate the candidate's aptitude. In this way, the assignment department can propose a more appropriate assignment by analyzing the candidate's social media activity. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the assignment department can input the candidate's social media activity data into the generation AI, and the generation AI can automatically propose a means of assignment.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] When collecting dialogue data of a candidate, the collection unit can filter the dialogue data based on the candidate's past work history and skill set. For example, questions related to the candidate's current work experience are preferentially collected. In addition, relevant dialogue data can be collected based on the candidate's skill set. Furthermore, unnecessary data can be filtered based on the candidate's work experience and skill set. This allows the collection unit to collect relevant dialogue data based on the candidate's work experience and skill set.

[0056] The collection unit can analyze the past interview history of the candidate and select an appropriate collection method. For example, the collection unit can prioritize the question formats that the candidate preferred in the past. It can also collect questions that the candidate had difficulty with in the past, avoiding them. Furthermore, it can select the most effective collection timing from the candidate's past interview history. In this way, the collection unit can select the optimal collection method by analyzing the past interview history.

[0057] The analysis unit can adjust the level of detail of the analysis based on the importance of the candidate's statements. For example, important keywords can be extracted from the candidate's statements and the frequency and relevance of those keywords can be evaluated. The context of the candidate's statements can also be analyzed to evaluate the intention and meaning of the statements. A detailed analysis can be performed for important statements, and a simplified analysis can be performed for general statements. This allows the analysis unit to perform more accurate analysis by adjusting the level of detail of the analysis according to the importance of the candidate's statements.

[0058] The selection unit can improve the accuracy of selection by taking into account the interrelationships between the candidates when making a selection. For example, the interrelationships between the candidates can be analyzed to evaluate the suitability for teamwork. Also, the selection unit can take into account the past cooperative relationships between the candidates. Furthermore, the selection unit can propose an optimal team composition based on the interrelationships between the candidates. In this way, the selection unit can improve the accuracy of selection by taking into account the interrelationships between the candidates.

[0059] At the time of assignment, the assignment department can select the most suitable assignment destination by analyzing the candidate's past work history. For example, a related assignment destination can be suggested based on the candidate's past work history. Also, the assignment department can analyze the candidate's work history and select the most suitable assignment destination. Furthermore, it can suggest a highly suitable assignment destination based on the candidate's past work history. In this way, the assignment department can select the most suitable assignment destination by analyzing the candidate's past work history.

[0060] At the time of assignment, the assignment department can customize the means of assignment based on the candidate's current living situation. For example, if a candidate needs to live in a specific area due to family circumstances, the candidate will be assigned to that area. Also, if the candidate wishes to work remotely, an assignment that allows remote work can be suggested. Furthermore, an assignment that takes into account the candidate's commuting time can be suggested based on the candidate's living situation. This allows the assignment department to suggest a more appropriate assignment by customizing the assignment based on the candidate's living situation.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The collection department collects conversation data with the candidate. The conversation data includes voice data, text data, video data, etc. For example, the contents and answers that the candidate spoke during the interview are recorded in detail. The collection department collects data when the candidate introduces himself or herself and answers specific questions. Step 2: The analysis unit uses the generation AI to analyze the dialogue data collected by the collection unit. The analysis is carried out using methods such as natural language processing, sentiment analysis, and keyword extraction. For example, the analysis unit analyzes the content of the candidate's remarks, their choice of words, and speaking characteristics to evaluate their thinking type and personality. Step 3: The selection department selects candidates for the second interview based on the analysis results obtained by the analysis department. The selection is done according to a scoring system or evaluation criteria. For example, the selection department selects candidates who have the thinking type or personality suitable for a particular position. Step 4: The placement department proposes the most suitable placement based on the regional characteristics of the candidates selected by the selection department. The placement proposal is based on criteria such as place of residence, place of work, and commute time. For example, the placement department selects candidates who are suitable for work in a particular region based on the candidate's personality and thinking type, and assigns them to that region.

[0063] (Example 2) The employment interview support system according to the embodiment of the present invention is a system that utilizes a generation AI to make employment interviews more efficient and analyze the thinking type and personality of candidates. In this system, the generation AI collects and analyzes dialogue data with the candidates to evaluate the thinking type and personality of the candidates. Based on the evaluation results, the second interviewer is selected and the assignment destination based on the regionality is considered. This makes the recruitment process more efficient and makes it possible to accurately evaluate the compatibility and aptitude of the candidates. For example, the contents and answers spoken by the candidates during the interview are recorded in detail, and the generation AI analyzes the data. Based on the analysis results, candidates with thinking types and personalities suitable for a specific position are selected and the optimal assignment destination is proposed. This mechanism strengthens the company's human resource strategy and improves the success rate of recruitment. As a result, the employment interview support system can automatically collect and analyze dialogue data of candidates, select appropriate candidates, and propose the optimal assignment destination.

[0064] The employment interview support system according to the embodiment includes a collection unit, an analysis unit, a selection unit, and an assignment unit. The collection unit collects dialogue data with the candidate. The dialogue data with the candidate includes, for example, voice data, text data, video data, etc., but is not limited to such examples. The collection unit, for example, records in detail the contents of what the candidate said during the interview and the answers he or she answered. For example, the collection unit collects data when the candidate introduces himself or herself or answers a specific question. The analysis unit uses a generation AI to analyze the dialogue data collected by the collection unit. The analysis is performed, for example, by a method such as natural language processing, emotion analysis, keyword extraction, etc., but is not limited to such examples. For example, the analysis unit analyzes the contents of the candidate's remarks, the choice of words, the characteristics of the way he or she speaks, etc., and evaluates the candidate's thinking type and personality. The selection unit selects a second interviewer based on the analysis result obtained by the analysis unit. The selection is performed, for example, according to a scoring system or evaluation criteria, but is not limited to such examples. For example, the selection unit selects a candidate with a thinking type and personality suitable for a specific position. The allocation department proposes an optimal assignment destination based on the regional characteristics of the candidate selected by the selection department. The assignment destination proposal is made based on criteria such as, for example, place of residence, place of work, and commuting time, but is not limited to such examples. For example, the allocation department selects a candidate suitable for work in a specific region based on the candidate's personality and thinking type, and assigns the candidate to that region. In this way, the recruitment interview support system according to the embodiment can automatically collect and analyze conversation data of candidates, select appropriate candidates, and propose optimal assignment destinations.

[0065] The collection unit collects dialogue data with the candidate. The dialogue data with the candidate includes, but is not limited to, voice data, text data, video data, and the like. The collection unit, for example, records in detail the contents and answers that the candidate spoke during the interview. Specifically, the collection unit uses a high-precision microphone and camera to collect the voice and video of the candidate in real time. The voice data records in detail the contents of the candidate's remarks, tone of voice, speaking speed, and the like, and the text data converts the voice into text using voice recognition technology. The video data includes non-verbal information such as the candidate's facial expressions, gestures, and posture. These data are continuously collected throughout the entire interview process and stored in a central database. Furthermore, the collection unit not only collects data when the candidate introduces himself or herself or answers specific questions, but also simultaneously records the questions and reactions of the interviewer. This makes it possible to grasp the overall flow and context of the dialogue. The collection unit centrally manages these data and makes them accessible to the analysis unit and selection unit. In addition, the collection unit adjusts the frequency and accuracy of data collection, allowing for flexible responses according to specific situations and conditions. For example, if the answer to a particular question is important, the data for that part can be set to be collected with high accuracy, allowing the collection unit to collect data efficiently and effectively, improving the performance of the entire system.

[0066] The analysis unit uses the generation AI to analyze the dialogue data collected by the collection unit. The analysis is performed by, for example, natural language processing, emotion analysis, keyword extraction, and other methods, but is not limited to these examples. Specifically, the natural language processing technology is used to analyze the content of the candidate's remarks and understand the context and intent. In emotion analysis, changes in emotions are detected from the candidate's tone of voice and facial expressions, and the degree of stress and tension is evaluated. In keyword extraction, important keywords and phrases are extracted from the candidate's remarks and specific skills and experience are evaluated. The generation AI integrates these analysis results and evaluates the candidate's thinking type and personality. For example, the content of the candidate's remarks, choice of words, and speaking characteristics are analyzed to evaluate characteristics such as logical thinking, creativity, and cooperativeness. Furthermore, the analysis unit builds a model to predict the suitability of the candidate based on past interview data and successful hiring cases. This allows the analysis unit to quickly and accurately analyze the collected data and evaluate the characteristics and suitability of the candidate. The analysis unit provides these analysis results to the selection unit, which is useful for selecting second interviewers. In addition, the analysis unit can continuously learn the analysis results and improve the analysis accuracy. This enables the analysis unit to not only grasp the situation in real time, but also handle long-term risk management and anomaly detection, improving the reliability and safety of the entire system.

[0067] The selection unit selects candidates for the second interview based on the analysis results obtained by the analysis unit. The selection is performed, for example, according to a scoring system or evaluation criteria, but is not limited to such examples. Specifically, a score is given to each candidate based on information such as the candidate's thinking type, personality, and skill set provided by the analysis unit. The scoring system emphasizes the skills and characteristics required for a specific position and evaluates the candidates based on that. For example, for a position requiring leadership, a high score is given to a candidate with high leadership skills and communication skills. The selection unit selects the most suitable candidate based on these scores. In addition, the selection unit can flexibly set the evaluation criteria. For example, the evaluation criteria are customized according to the needs of a specific project or team, and the most suitable candidate is selected. Furthermore, the selection unit evaluates the aptitude and potential of the candidate based on the analysis results, and makes the selection taking into consideration the future growth potential. This allows the selection unit to select an appropriate candidate not only from a short-term need but also from a long-term perspective. The selection unit provides the selection results to the assignment unit, which helps in proposing the most suitable assignment. This enables the selection unit to efficiently and effectively select second interviewers, improving the performance of the entire system.

[0068] The allocation department proposes the most suitable place of assignment based on the regional characteristics of the candidate selected by the selection department. The proposal of the place of assignment is made based on criteria such as, for example, place of residence, place of work, and commuting time, but is not limited to such examples. Specifically, the optimal place of work is proposed based on the candidate's place of residence information, taking into consideration the commuting time and transportation means. For example, if the candidate lives in an urban area, the commuting time can be shortened and work efficiency can be improved by assigning the candidate to an office or project in the urban area. In addition, the allocation department selects candidates suitable for work in a specific area based on the candidate's personality and thinking type, and assigns them to that area. For example, a candidate with high cooperativeness is assigned to a project where teamwork is emphasized, and a candidate with high expertise is assigned to a project where individual skills are emphasized. Furthermore, the allocation department can propose the most suitable place of assignment taking into consideration the candidate's wishes and career plan. For example, if a candidate wishes to gain experience in a specific field, the candidate's career growth is supported by assigning him / her to a project or team related to that field. Based on this information, the Assignment Department can propose optimal assignment destinations and improve candidate satisfaction and work efficiency. This allows the Assignment Department to assign candidates efficiently and effectively, improving the performance of the entire system.

[0069] The collection unit can record in detail the contents or answers spoken by the candidate during the interview. Methods of recording in detail include, for example, recording, transcribing, adding metadata, and the like, but are not limited to such examples. For example, the collection unit records the contents spoken by the candidate during the interview using a high-precision recording device and saves the audio data. The collection unit can also convert the recorded audio data into text data using transcription software. Furthermore, the collection unit can add metadata to the collected dialogue data and record attribute information of the data. For example, the collection unit adds metadata such as the date and time of the dialogue, the location, and basic information of the candidate to the dialogue data. This allows the collection unit to record in detail the contents and answers spoken by the candidate during the interview, improving the accuracy of the analysis. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the dialogue data of the candidate into the generation AI, and the generation AI can automatically record the dialogue data in detail.

[0070] The analysis unit can analyze the contents of the candidate's remarks, the choice of words, and the characteristics of the way of speaking to evaluate the thinking type and personality. The analysis unit, for example, analyzes the contents of the candidate's remarks. Methods of analyzing the contents of the remarks include, for example, keyword extraction, context analysis, and the like, but are not limited to such examples. The analysis unit, for example, extracts important keywords from the contents of the candidate's remarks and analyzes the frequency and relevance of the keywords. The analysis unit can also analyze the context of the contents of the candidate's remarks to evaluate the intention and meaning of the remarks. Furthermore, the analysis unit analyzes the choice of words of the candidate. Methods of analyzing the choice of words include, for example, the frequency of positive / negative words, the use of technical terms, and the like, but are not limited to such examples. The analysis unit, for example, analyzes the frequency of positive and negative words included in the remarks of the candidate to evaluate the emotions and attitudes of the candidate. The analysis unit can also analyze the frequency of technical terms used by the candidate to evaluate the expertise and skills of the candidate. Furthermore, the analysis unit analyzes the characteristics of the way the candidate speaks. Methods for analyzing the characteristics of speaking style include, for example, speech speed, intonation, pauses, etc., but are not limited to such examples. For example, the analysis unit analyzes the speech speed of the candidate to evaluate the rhythm and tempo of the speech. The analysis unit can also analyze the intonation of the candidate's remarks to evaluate the way of expressing emotions and emphasizing them. In this way, the analysis unit can analyze the contents of the candidate's remarks, the choice of words, and the characteristics of the speaking style, and evaluate the thinking type and personality. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit inputs the dialogue data of the candidate into the generation AI, and the generation AI can automatically analyze the contents of the remarks, the choice of words, and the characteristics of the speaking style.

[0071] The selection unit can select candidates having a thinking type or personality suitable for a specific position. The selection unit selects candidates suitable for a specific position, for example, based on the analysis results obtained by the analysis unit. Selection criteria include, for example, a scoring system and evaluation criteria, but are not limited to such examples. The selection unit selects candidates suitable for a specific position, for example, based on the candidate's thinking type or personality. For example, the selection unit selects candidates having a logical thinking type suitable for a sales position. The selection unit can also select candidates having specialized knowledge suitable for a technical position. Furthermore, the selection unit can also select candidates having leadership skills suitable for a managerial position. This allows the selection unit to select candidates having a thinking type or personality suitable for a specific position, improving the success rate of recruitment. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit inputs the analysis results obtained by the analysis unit into the generation AI, and the generation AI can automatically select a candidate suitable for a specific position.

[0072] The assignment department can propose an appropriate assignment based on the personality or thinking type of the candidate. The assignment department proposes an optimal assignment based on, for example, the personality and thinking type of the candidate selected by the selection department. The criteria for suggesting an assignment include, for example, department, project, work location, etc., but are not limited to such examples. The assignment department selects a candidate suitable for work in a specific area based on, for example, the personality and thinking type of the candidate, and assigns the candidate to that area. For example, if the candidate has a sociable personality, the assignment department can assign the candidate to a sales position or customer support position. In addition, if the candidate has a logical thinking type, the assignment department can assign the candidate to a technical position or data analysis position. Furthermore, the assignment department can propose a flexible working style such as remote work or flextime based on the personality and thinking type of the candidate. This allows the assignment department to propose an optimal assignment based on the personality and thinking type of the candidate, thereby strengthening the company's human resource strategy. A part or all of the above-mentioned processing in the assignment department may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the placement department can input data on a candidate's personality and thinking type into the generation AI, which can then automatically suggest the most suitable placement.

[0073] The collection unit can estimate the emotion of the candidate and adjust the collection timing of the dialogue data based on the estimated emotion. The collection unit, for example, estimates the emotion of the candidate. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. The collection unit, for example, takes a picture of the candidate's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The collection unit can also record the candidate's voice and estimate the emotion using a voice analysis technology. Furthermore, the collection unit can also perform text analysis of the contents of the candidate's remarks and estimate the emotion. The collection unit adjusts the collection timing of the dialogue data based on the estimated emotion. The collection timing adjustment method includes, for example, real-time analysis, pre-setting, etc., but is not limited to such examples. For example, when the candidate is nervous, the collection unit collects the dialogue data after setting aside time for the candidate to relax. Furthermore, when the candidate is relaxed, the collection unit can immediately start collecting the dialogue data. Furthermore, when the candidate is excited, the collection unit can wait until the candidate calms down before collecting the dialogue data. This allows the collection unit to collect more natural dialogue data by adjusting the collection timing according to the candidate's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit inputs the candidate's emotion data into the generation AI, and the generation AI can automatically adjust the collection timing.

[0074] The collection unit can analyze the past interview history of the candidate and select an appropriate collection method. The collection unit, for example, analyzes the past interview history of the candidate. The method of analyzing the past interview history includes, for example, the number of interviews, the content of questions, and the evaluation results, but is not limited to such examples. For example, the collection unit prioritizes and collects question formats that the candidate has preferred in the past. The collection unit can also collect questions while avoiding questions that the candidate was weak at in the past. Furthermore, the collection unit can select the most effective collection timing from the past interview history of the candidate. In this way, the collection unit can select the optimal collection method by analyzing the past interview history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the past interview history data of the candidate to the generation AI, and the generation AI can automatically select the optimal collection method.

[0075] The collection unit can filter the dialogue data based on the candidate's current work experience and skill set when collecting the dialogue data. The collection unit, for example, filters the dialogue data based on the candidate's current work experience and skill set. Filtering criteria include, for example, the type of job, years of experience, and achievements, but are not limited to such examples. The collection unit, for example, prioritizes and collects questions related to the candidate's current work experience. The collection unit can also collect related dialogue data based on the candidate's skill set. Furthermore, the collection unit can filter unnecessary data based on the candidate's work experience and skill set. This allows the collection unit to collect related dialogue data based on the candidate's work experience and skill set. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit inputs data on the candidate's work experience and skill set into the generation AI, and the generation AI can automatically perform filtering.

[0076] The collection unit can estimate the candidate's emotion and determine the priority of the dialogue data to be collected based on the estimated emotion. The collection unit, for example, estimates the candidate's emotion. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. The collection unit, for example, takes a picture of the candidate's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The collection unit can also record the candidate's voice and estimate the emotion using a voice analysis technology. Furthermore, the collection unit can also perform text analysis of the candidate's remarks and estimate the emotion. The collection unit determines the priority of the dialogue data to be collected based on the estimated emotion. The priority determination method includes, for example, importance score, urgency, etc., but is not limited to such examples. For example, if the candidate is nervous, the collection unit prioritizes questions to relax the candidate. Furthermore, if the candidate is relaxed, the collection unit can prioritize in-depth questions. Furthermore, if the candidate is excited, the collection unit can prioritize questions to calm the candidate. This allows the collection unit to collect more appropriate data by determining the priority of dialogue data according to the emotions of the candidates. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit inputs the candidate's emotion data into the generation AI, and the generation AI can automatically determine the priority of the dialogue data.

[0077] The collection unit can collect highly relevant data preferentially based on the geographical location information of the candidate when collecting the dialogue data. The collection unit, for example, collects dialogue data taking into account the geographical location information of the candidate. Methods of considering the geographical location information include, for example, addresses, GPS data, area codes, and the like, but are not limited to such examples. The collection unit, for example, prioritizes questions specific to a region based on the geographical location of the candidate. The collection unit can also preferentially collect work experience related to the geographical location of the candidate. Furthermore, the collection unit can also collect related company information based on the geographical location of the candidate. In this way, the collection unit can collect highly relevant data by considering the geographical location information of the candidate. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the geographical location information of the candidate to the generation AI, and the generation AI can automatically collect highly relevant data preferentially.

[0078] The collection unit can analyze the candidate's social media activity and collect related data when collecting the dialogue data. The collection unit, for example, analyzes the candidate's social media activity. Methods for analyzing social media activity include, but are not limited to, for example, the content of posts, the number of followers, and the engagement rate. The collection unit, for example, collects questions reflecting interests from the candidate's social media activity. The collection unit can also collect related work experience based on the candidate's social media activity. Furthermore, the collection unit can analyze the candidate's social media activity and collect data for evaluating aptitude. In this way, the collection unit can collect related data by analyzing the candidate's social media activity. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the candidate's social media activity data into the generation AI, and the generation AI can automatically collect related data.

[0079] The analysis unit can estimate the candidate's emotion and adjust the expression method of the analysis based on the estimated emotion. The analysis unit, for example, estimates the candidate's emotion. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. The analysis unit, for example, takes a picture of the candidate's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The analysis unit can also record the candidate's voice and estimate the emotion using voice analysis technology. Furthermore, the analysis unit can perform text analysis of the candidate's remarks and estimate the emotion. The analysis unit adjusts the expression method of the analysis based on the estimated emotion. The adjustment of the expression method includes, for example, the use of language, tone, level of detail, etc., but is not limited to such examples. For example, when the candidate is nervous, the analysis unit provides a simple and highly visible analysis result. Furthermore, when the candidate is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, when the candidate is excited, the analysis unit can provide a visually stimulating analysis result. This allows the analysis unit to provide more appropriate analysis results by adjusting the way the analysis is expressed according to the candidate's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs the candidate's emotion data into the generation AI, and the generation AI can automatically adjust the way the analysis is expressed.

[0080] The analysis unit can adjust the level of detail of the analysis based on the importance of the candidate's statement during the analysis. The analysis unit, for example, evaluates the importance of the candidate's statement. Methods for evaluating the importance of the statement include, for example, the frequency of keywords and the importance of the context, but are not limited to such examples. The analysis unit, for example, extracts important keywords from the content of the candidate's statement and evaluates the frequency and relevance of the keywords. The analysis unit can also analyze the context of the content of the candidate's statement and evaluate the intention and meaning of the statement. The analysis unit adjusts the level of detail of the analysis based on the importance of the statement. Adjustments to the level of detail include, for example, the depth of analysis and the granularity of information, but are not limited to such examples. For example, the analysis unit performs a detailed analysis on important statements. Furthermore, the analysis unit can perform a simplified analysis on general statements. Furthermore, the analysis unit can also adjust the depth of the analysis according to the importance of the candidate's statement. As a result, the analysis unit can perform a more accurate analysis by adjusting the level of detail of the analysis according to the importance of the candidate's statement. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs the candidate's utterance data into the generation AI, and the generation AI automatically evaluates the importance of the utterance and adjusts the level of detail of the analysis.

[0081] The analysis unit can apply different analysis algorithms depending on the job category of the candidate during the analysis. The analysis unit, for example, identifies the job category of the candidate. Methods for identifying the job category include, for example, the type of job, years of experience, and achievements, but are not limited to such examples. The analysis unit, for example, analyzes the job history of the candidate to identify the job category. In addition, the analysis unit applies different analysis algorithms depending on the job category of the candidate. Methods for applying the analysis algorithm include, for example, machine learning algorithms and statistical analysis algorithms, but are not limited to such examples. For example, the analysis unit applies an analysis algorithm that emphasizes technical skills to candidates for technical positions. In addition, the analysis unit can apply an analysis algorithm that emphasizes communication skills to candidates for sales positions. Furthermore, the analysis unit can also apply an analysis algorithm that emphasizes leadership skills to candidates for managerial positions. This allows the analysis unit to perform more appropriate analysis by applying an analysis algorithm according to the job category of the candidate. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input a candidate's job category data into the generation AI, which can then automatically apply an appropriate analysis algorithm.

[0082] The analysis unit can estimate the candidate's emotion and adjust the length of the analysis based on the estimated emotion. The analysis unit, for example, estimates the candidate's emotion. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. The analysis unit, for example, takes a picture of the candidate's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The analysis unit can also record the candidate's voice and estimate the emotion using voice analysis technology. Furthermore, the analysis unit can perform text analysis of the candidate's remarks and estimate the emotion. The analysis unit adjusts the length of the analysis based on the estimated emotion. The adjustment of the length of the analysis includes, for example, the analysis time, the level of detail of the information, etc., but is not limited to such examples. For example, when the candidate is in a hurry, the analysis unit performs a short and to the point analysis. Furthermore, when the candidate is relaxed, the analysis unit can perform a detailed analysis. Furthermore, when the candidate is excited, the analysis unit can perform a visually stimulating analysis. In this way, the analysis unit can provide a more appropriate analysis result by adjusting the length of the analysis according to the candidate's emotion. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs the candidate's emotion data into the generation AI, and the generation AI can automatically adjust the length of the analysis.

[0083] The analysis unit can determine the priority of the analysis based on the interview time of the candidate at the time of analysis. The analysis unit, for example, identifies the interview time of the candidate. The method of identifying the interview time includes, for example, the interview date, the application period, the selection stage, etc., but is not limited to such examples. The analysis unit, for example, identifies the interview date of the candidate and prioritizes the analysis of the most recent interview data. The analysis unit can also identify the application period of the candidate and prioritize the analysis of data within the application period. Furthermore, the analysis unit can also identify the selection stage of the candidate and adjust the order of analysis based on the selection stage. As a result, the analysis unit can determine the priority of the analysis based on the interview time of the candidate, thereby enabling efficient analysis. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the interview time data of the candidate to the generation AI, and the generation AI can automatically determine the priority of the analysis.

[0084] The analysis unit can adjust the order of analysis based on the relevance of the candidate during analysis. The analysis unit, for example, evaluates the relevance of the candidate. The method of evaluating the relevance includes, for example, job relevance, skill relevance, and the like, but is not limited to such examples. The analysis unit, for example, analyzes highly relevant data by giving priority to the work experience of the candidate. The analysis unit can also analyze highly relevant data by giving priority to the skill set of the candidate. Furthermore, the analysis unit can also analyze highly relevant data by giving priority to the work aptitude of the candidate. The analysis unit adjusts the order of analysis based on the relevance. The adjustment of the order includes, for example, priority order, importance, and the like, but is not limited to such examples. The analysis unit, for example, analyzes highly relevant data by giving priority to the work experience of the candidate. The analysis unit can also analyze highly relevant data by giving priority to the skill set of the candidate. Furthermore, the analysis unit can also analyze highly relevant data by giving priority to the work aptitude of the candidate. Thereby, the analysis unit adjusts the order of analysis based on the relevance of the candidate, thereby enabling efficient analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs the candidate's relevance data into the generation AI, and the generation AI can automatically adjust the order of analysis.

[0085] The selection unit can estimate the emotion of the candidate and adjust the selection criteria based on the estimated emotion. The selection unit, for example, estimates the emotion of the candidate. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. For example, the selection unit captures the facial expression of the candidate with a camera and estimates the emotion using an emotion estimation algorithm. The selection unit can also record the candidate's voice and estimate the emotion using a voice analysis technology. Furthermore, the selection unit can perform text analysis of the contents of the candidate's remarks and estimate the emotion. The selection unit adjusts the selection criteria based on the estimated emotion. The adjustment of the selection criteria includes, for example, evaluation criteria, scoring systems, etc., but is not limited to such examples. For example, when the candidate is nervous, the selection unit emphasizes evaluation in a relaxed state. Furthermore, when the candidate is relaxed, the selection unit can apply normal evaluation criteria. Furthermore, when the candidate is excited, the selection unit can also emphasize evaluation in a calm state. In this way, the selection unit can select a more suitable candidate by adjusting the selection criteria according to the candidate's emotion. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the selection unit inputs emotion data of candidates to the generation AI, and the generation AI can automatically adjust the selection criteria.

[0086] The selection unit can improve the accuracy of selection by considering the interrelationships of the candidates at the time of selection. The selection unit, for example, evaluates the interrelationships of the candidates. The method of evaluating the interrelationships includes, for example, the history of joint projects, mutual evaluation, etc., but is not limited to such examples. The selection unit, for example, analyzes the interrelationships between the candidates and evaluates the aptitude for teamwork. The selection unit can also select by considering the past cooperative relationships of the candidates. Furthermore, the selection unit can also propose an optimal team composition based on the interrelationships of the candidates. As a result, the selection unit improves the accuracy of selection by considering the interrelationships of the candidates. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit inputs the interrelationship data of the candidates into the generation AI, and the generation AI automatically evaluates the interrelationships, thereby improving the accuracy of selection.

[0087] The selection unit can make a selection by taking into consideration the attribute information of the candidate. The selection unit, for example, evaluates the attribute information of the candidate. The evaluation method of the attribute information includes, for example, age, gender, and educational background, but is not limited to such examples. The selection unit makes a selection by taking into consideration, for example, the age and gender of the candidate. The selection unit can also make a selection by taking into consideration the educational background and work history of the candidate. Furthermore, the selection unit can also make a selection by taking into consideration the skill set and qualifications of the candidate. In this way, the selection unit can select a more suitable candidate by taking into consideration the attribute information of the candidate. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input attribute information data of the candidate into the generation AI, and the generation AI can automatically evaluate the attribute information and make a selection.

[0088] The selection unit can estimate the emotion of the candidate and adjust the order of displaying the selection results based on the estimated emotion. The selection unit, for example, estimates the emotion of the candidate. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. For example, the selection unit captures the facial expression of the candidate with a camera and estimates the emotion using an emotion estimation algorithm. The selection unit can also record the candidate's voice and estimate the emotion using a voice analysis technology. Furthermore, the selection unit can also perform text analysis of the contents of the candidate's remarks and estimate the emotion. The selection unit adjusts the order of displaying the selection results based on the estimated emotion. The adjustment of the display order includes, for example, priority and importance, but is not limited to such examples. For example, when the candidate is nervous, the selection unit prioritizes and displays the evaluation results in a relaxed state. Furthermore, when the candidate is relaxed, the selection unit can display the normal evaluation results. Furthermore, when the candidate is excited, the selection unit can also prioritize and display the evaluation results in a calm state. This allows the selection unit to provide more appropriate results by adjusting the order in which the selection results are displayed according to the emotions of the candidates. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the selection unit can input emotion data of the candidates into the generation AI, and adjust the order in which the generation AI automatically displays the selection results.

[0089] The selection unit can make a selection taking into consideration the geographic distribution of the candidates. The selection unit, for example, evaluates the geographic distribution of the candidates. The evaluation method of the geographic distribution includes, for example, the place of residence, the place of work, and the commuting time, but is not limited to such examples. The selection unit, for example, proposes an optimal place of work based on the place of residence of the candidate. In addition, the selection unit can optimize the team composition by taking into consideration the geographic distribution of the candidates. Furthermore, the selection unit can also evaluate the suitability of remote work based on the geographic distribution of the candidates. In this way, the selection unit can select a more appropriate candidate by taking into consideration the geographic distribution of the candidates. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the geographic distribution data of the candidates into the generation AI, and the generation AI can automatically evaluate the geographic distribution and make the selection.

[0090] The selection unit can improve the accuracy of the selection by referring to the candidate's related literature at the time of selection. The selection unit, for example, refers to the candidate's related literature. The method of referring to the related literature includes, but is not limited to, academic papers, technical reports, industry news, and the like. The selection unit, for example, refers to the candidate's research papers to evaluate the candidate's expertise. The selection unit can also evaluate the candidate's practical experience by referring to the candidate's past project reports. Furthermore, the selection unit can also analyze the candidate's related literature and collect data for evaluating aptitude. As a result, the selection unit improves the accuracy of the selection by referring to the candidate's related literature. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the selection unit inputs the candidate's related literature data into the generation AI, and the generation AI automatically refers to the related literature, thereby improving the accuracy of the selection.

[0091] The assignment department can estimate the emotion of the candidate and adjust the assignment proposal method based on the estimated emotion. The assignment department, for example, estimates the emotion of the candidate. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. The assignment department, for example, takes a picture of the candidate's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The assignment department can also record the candidate's voice and estimate the emotion using a voice analysis technology. Furthermore, the assignment department can also perform text analysis of the candidate's remarks and estimate the emotion. The assignment department adjusts the assignment proposal method based on the estimated emotion. The adjustment of the proposal method includes, for example, the timing of the proposal, the level of detail of the proposal content, etc., but is not limited to such examples. For example, when the candidate is nervous, the assignment department proposes an assignment in a relaxed state. Furthermore, when the candidate is relaxed, the assignment department can propose a normal assignment. Furthermore, when the candidate is excited, the assignment department can also propose an assignment in a calm state. This allows the assignment department to suggest more appropriate assignments by adjusting the method of suggesting assignments according to the candidate's emotions. Estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the assignment department may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the assignment department can input emotion data of the candidate into the generation AI, which can automatically adjust the method of suggesting assignments.

[0092] The assignment department can select the most suitable assignment destination by analyzing the candidate's past work history at the time of assignment. The assignment department, for example, analyzes the candidate's past work history. The method of analyzing the past work history includes, for example, the type of work, years of experience, and achievements, but is not limited to such examples. The assignment department, for example, proposes a related assignment destination based on the candidate's past work history. The assignment department can also analyze the candidate's work history and select the most suitable assignment destination. Furthermore, the assignment department can also propose a highly suitable assignment destination based on the candidate's past work history. In this way, the assignment department can select the most suitable assignment destination by analyzing the candidate's past work history. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the assignment department can input the candidate's past work history data into the generation AI, and the generation AI can automatically select the most suitable assignment destination.

[0093] The assignment department can customize the means of the assignment destination based on the candidate's current living situation at the time of assignment. The assignment department, for example, evaluates the candidate's current living situation. The evaluation method of the living situation includes, for example, family composition, commuting time, living environment, etc., but is not limited to such examples. For example, if the candidate needs to live in a specific area due to family circumstances, the assignment department assigns the candidate to that area. In addition, if the candidate wishes to work remotely, the assignment department can propose an assignment destination that allows remote work. Furthermore, the assignment department can also propose an assignment destination that takes commuting time into consideration based on the candidate's living situation. As a result, the assignment department can propose a more appropriate assignment destination by customizing the assignment destination based on the candidate's living situation. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the assignment department can input the candidate's living situation data into the generation AI, and the generation AI can automatically customize the means of the assignment destination.

[0094] The assignment department can estimate the emotion of the candidate and determine the priority of the assignment destination based on the estimated emotion. The assignment department, for example, estimates the emotion of the candidate. The emotion estimation method includes, for example, facial expression analysis, voice analysis, text analysis, etc., but is not limited to such examples. The assignment department, for example, takes a picture of the candidate's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The assignment department can also record the candidate's voice and estimate the emotion using a voice analysis technology. Furthermore, the assignment department can also perform text analysis of the contents of the candidate's remarks and estimate the emotion. The assignment department determines the priority of the assignment destination based on the estimated emotion. The determination of the priority includes, for example, an importance score, an urgency, etc., but is not limited to such examples. For example, when the candidate is nervous, the assignment department prioritizes the assignment destination in a relaxed state. Furthermore, when the candidate is relaxed, the assignment department can prioritize a normal assignment destination. Furthermore, when the candidate is excited, the assignment department can prioritize the assignment destination in a calm state. This allows the assignment department to propose more appropriate assignments by determining the priority of assignments according to the candidate's emotions. Estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the assignment department may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the assignment department can input emotion data of the candidate into the generation AI, and the generation AI can automatically determine the priority of assignments.

[0095] The assignment department can select the optimal assignment destination by considering the geographical location information of the candidate at the time of assignment. The assignment department, for example, evaluates the geographical location information of the candidate. The evaluation method of the geographical location information includes, for example, an address, GPS data, a region code, etc., but is not limited to such examples. The assignment department, for example, proposes the optimal work location based on the candidate's place of residence. In addition, the assignment department can select an assignment destination that minimizes commuting time by considering the geographical location information of the candidate. Furthermore, the assignment department can also evaluate the suitability of remote work based on the geographical location information of the candidate. In this way, the assignment department can select the optimal assignment destination by considering the geographical location information of the candidate. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the assignment department can input the geographical location information data of the candidate into the generation AI, and the generation AI can automatically select the optimal assignment destination.

[0096] At the time of assignment, the assignment department can analyze the social media activity of the candidate and propose a means of assignment. The assignment department, for example, analyzes the social media activity of the candidate. Methods of analyzing social media activity include, for example, but are not limited to, the content of posts, the number of followers, and the engagement rate. The assignment department, for example, proposes an assignment that reflects the candidate's interests from the social media activity of the candidate. The assignment department can also propose an assignment that takes into account the candidate's related work experience based on the candidate's social media activity. Furthermore, the assignment department can also analyze the candidate's social media activity and propose an assignment to evaluate the candidate's aptitude. In this way, the assignment department can propose a more appropriate assignment by analyzing the candidate's social media activity. Part or all of the above-mentioned processing in the assignment department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the assignment department can input the candidate's social media activity data into the generation AI, and the generation AI can automatically propose a means of assignment.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] When collecting dialogue data of a candidate, the collection unit can filter the dialogue data based on the candidate's past work history and skill set. For example, questions related to the candidate's current work experience are preferentially collected. In addition, relevant dialogue data can be collected based on the candidate's skill set. Furthermore, unnecessary data can be filtered based on the candidate's work experience and skill set. This allows the collection unit to collect relevant dialogue data based on the candidate's work experience and skill set.

[0099] The collection unit can estimate the emotions of the candidate and adjust the timing of collection of dialogue data based on the estimated emotions. For example, if the candidate is nervous, the conversation data is collected after allowing time for the candidate to relax. Also, if the candidate is relaxed, the collection of dialogue data can start immediately. Furthermore, if the candidate is excited, the collection unit can wait until the candidate calms down before collecting the conversation data. In this way, the collection unit can collect more natural conversation data by adjusting the collection timing according to the candidate's emotions.

[0100] When analyzing the content of a candidate's remarks, choice of words, and characteristics of the way the candidate speaks, the analysis unit can estimate the candidate's emotions and adjust the way the analysis is presented based on the estimated emotions. For example, if the candidate is nervous, a simple and highly visible analysis result can be provided. If the candidate is relaxed, a detailed analysis result can be provided. Furthermore, if the candidate is excited, a visually stimulating analysis result can be provided. This allows the analysis unit to provide more appropriate analysis results by adjusting the way the analysis is presented according to the candidate's emotions.

[0101] When selecting candidates with a thinking type or personality suitable for a particular position, the selection unit can estimate the emotions of the candidates and adjust the selection criteria based on the estimated emotions. For example, if the candidate is nervous, emphasis can be placed on evaluation in a relaxed state. Also, if the candidate is relaxed, normal evaluation criteria can be applied. Furthermore, if the candidate is excited, emphasis can be placed on evaluation in a calm state. In this way, the selection unit can select more suitable candidates by adjusting the selection criteria according to the emotions of the candidates.

[0102] When suggesting an appropriate assignment based on the candidate's personality and thinking type, the assignment department can estimate the candidate's emotions and adjust the method of suggesting the assignment based on the estimated emotions. For example, if the candidate is nervous, an assignment in a relaxed state can be suggested. Also, if the candidate is relaxed, a normal assignment can be suggested. Furthermore, if the candidate is excited, an assignment in a calm state can also be suggested. In this way, the assignment department can suggest a more appropriate assignment by adjusting the method of suggesting the assignment according to the candidate's emotions.

[0103] The collection unit can analyze the past interview history of the candidate and select an appropriate collection method. For example, the collection unit can prioritize the question formats that the candidate preferred in the past. It can also collect questions that the candidate had difficulty with in the past, avoiding them. Furthermore, it can select the most effective collection timing from the candidate's past interview history. In this way, the collection unit can select the optimal collection method by analyzing the past interview history.

[0104] The analysis unit can adjust the level of detail of the analysis based on the importance of the candidate's statements. For example, important keywords can be extracted from the candidate's statements and the frequency and relevance of those keywords can be evaluated. The context of the candidate's statements can also be analyzed to evaluate the intention and meaning of the statements. A detailed analysis can be performed for important statements, and a simplified analysis can be performed for general statements. This allows the analysis unit to perform more accurate analysis by adjusting the level of detail of the analysis according to the importance of the candidate's statements.

[0105] The selection unit can improve the accuracy of selection by taking into account the interrelationships between the candidates when making a selection. For example, the interrelationships between the candidates can be analyzed to evaluate the suitability for teamwork. Also, the selection unit can take into account the past cooperative relationships between the candidates. Furthermore, the selection unit can propose an optimal team composition based on the interrelationships between the candidates. In this way, the selection unit can improve the accuracy of selection by taking into account the interrelationships between the candidates.

[0106] At the time of assignment, the assignment department can select the most suitable assignment destination by analyzing the candidate's past work history. For example, a related assignment destination can be suggested based on the candidate's past work history. Also, the assignment department can analyze the candidate's work history and select the most suitable assignment destination. Furthermore, it can suggest a highly suitable assignment destination based on the candidate's past work history. In this way, the assignment department can select the most suitable assignment destination by analyzing the candidate's past work history.

[0107] At the time of assignment, the assignment department can customize the means of assignment based on the candidate's current living situation. For example, if a candidate needs to live in a specific area due to family circumstances, the candidate will be assigned to that area. Also, if the candidate wishes to work remotely, an assignment that allows remote work can be suggested. Furthermore, an assignment that takes into account the candidate's commuting time can be suggested based on the candidate's living situation. This allows the assignment department to suggest a more appropriate assignment by customizing the assignment based on the candidate's living situation.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The collection department collects conversation data with the candidate. The conversation data includes voice data, text data, video data, etc. For example, the contents and answers that the candidate spoke during the interview are recorded in detail. The collection department collects data when the candidate introduces himself or herself and answers specific questions. Step 2: The analysis unit uses the generation AI to analyze the dialogue data collected by the collection unit. The analysis is carried out using methods such as natural language processing, sentiment analysis, and keyword extraction. For example, the analysis unit analyzes the content of the candidate's remarks, their choice of words, and speaking characteristics to evaluate their thinking type and personality. Step 3: The selection department selects candidates for the second interview based on the analysis results obtained by the analysis department. The selection is done according to a scoring system or evaluation criteria. For example, the selection department selects candidates who have the thinking type or personality suitable for a particular position. Step 4: The placement department proposes the most suitable placement based on the regional characteristics of the candidates selected by the selection department. The placement proposal is based on criteria such as place of residence, place of work, and commute time. For example, the placement department selects candidates who are suitable for work in a particular region based on the candidate's personality and thinking type, and assigns them to that region.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements including the collection unit, analysis unit, selection unit, and assignment unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects dialogue data of the candidates using the camera 42 and microphone 38B of the smart device 14, and records the data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected dialogue data using the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects a second interviewer based on the analysis result. The assignment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes an optimal assignment destination based on the regionality of the selected candidate. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0121] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements including the above-mentioned collection unit, analysis unit, selection unit, and assignment unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects dialogue data of the candidates using the camera 42 and microphone 238 of the smart glasses 214, and records the data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected dialogue data using the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects a second interviewer based on the analysis result. The assignment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes an optimal assignment destination based on the regionality of the selected candidate. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0137] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0138] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements including the above-mentioned collection unit, analysis unit, selection unit, and assignment unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects dialogue data of the candidate using the camera 42 and microphone 238 of the headset type terminal 314, and records the data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected dialogue data using the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects a second interviewer based on the analysis result. The assignment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes the optimal assignment destination based on the regionality of the selected candidate. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] Each of the multiple elements including the above-mentioned collection unit, analysis unit, selection unit, and assignment unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects dialogue data of the candidate using the camera 42 and microphone 238 of the robot 414, and records the data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected dialogue data using the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects a second interviewer based on the analysis result. The assignment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes an optimal assignment destination based on the regionality of the selected candidate. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0164] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0171] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0172] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0173] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0176] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 1) A collection unit that collects dialogue data with candidates; an analysis unit that analyzes the dialogue data collected by the collection unit; A selection unit that selects second interviewees based on the analysis results obtained by the analysis unit; An assignment department that considers assignment destinations based on the regional characteristics of the candidates selected by the selection department. A system characterized by: (Appendix 2) The collecting unit includes: Keep a detailed record of what the candidate said or answered during the interview 2. The system of claim 1, (Appendix 3) The analysis unit is Analyze the content of a candidate's statements, their choice of words, and the characteristics of their speaking style to evaluate their thinking style and personality 2. The system of claim 1, (Appendix 4) The selection unit is Select candidates with the right thinking style or personality for a particular position 2. The system of claim 1, (Appendix 5) The allocation department includes: Suggest suitable placements based on candidates' personality or thinking type 2. The system of claim 1, (Appendix 6) The collecting unit includes: Estimate the candidate's emotions and adjust the timing of conversation data collection based on the estimated emotions. 2. The system of claim 1, (Appendix 7) The collecting unit includes: Analyze past interview history of candidates and choose the appropriate collection method 2. The system of claim 1, (Appendix 8) The collecting unit includes: Filter based on candidates' current work experience or skill set 2. The system of claim 1, (Appendix 9) The collecting unit includes: Estimate the candidate's emotions and prioritize the conversation data to be collected based on the estimated emotions. 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting conversation data, prioritize collection of relevant data based on the candidate's geographic location 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting interaction data, analyze candidates' social media activity to gather more relevant data 2. The system of claim 1, (Appendix 12) The analysis unit is Infer the candidate's sentiment and adjust the presentation of the analysis based on the inferred sentiment 2. The system of claim 1, (Appendix 13) The analysis unit is During analysis, adjust the level of detail based on the importance of what the candidate said 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, apply different analysis algorithms depending on the candidate's job category 2. The system of claim 1, (Appendix 15) The analysis unit is Estimate the candidate's sentiment and adjust the length of the analysis based on the estimated sentiment 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, prioritize analysis based on when candidates are interviewed 2. The system of claim 1, (Appendix 17) The analysis unit is During parsing, adjust the order of parsing based on candidate relevance 2. The system of claim 1, (Appendix 18) The selection unit is Infer candidates' emotions and adjust selection criteria based on the inferred emotions 2. The system of claim 1, (Appendix 19) The selection unit is Improve accuracy of selection by considering the interrelationships of candidates during selection 2. The system of claim 1, (Appendix 20) The selection unit is When selecting candidates, consider their attribute information. 2. The system of claim 1, (Appendix 21) The selection unit is Infer the sentiment of the candidates and adjust the order in which the selection results are displayed based on the inferred sentiment 2. The system of claim 1, (Appendix 22) The selection unit is At the time of selection, the geographical distribution of candidates will be taken into consideration. 2. The system of claim 1, (Appendix 23) The selection unit is When selecting candidates, refer to their related literature to improve the accuracy of the selection process. 2. The system of claim 1, (Appendix 24) The allocation department includes: Infer candidate sentiment and adjust placement suggestions based on the inferred sentiment 2. The system of claim 1, (Appendix 25) The allocation department includes: At the time of placement, analyze the candidate's past work history to select the most suitable placement 2. The system of claim 1, (Appendix 26) The allocation department includes: During placement, customize placement avenues based on the candidate's current life situation 2. The system of claim 1, (Appendix 27) The allocation department includes: Infer candidates' emotions and prioritize placements based on the inferred emotions 2. The system of claim 1, (Appendix 28) The allocation department includes: During placement, the geographic location of the candidate is taken into consideration to select the most suitable placement. 2. The system of claim 1, (Appendix 29) The allocation department includes: At the time of placement, analyze the candidates' social media activity to suggest placement avenues 2. The system of claim 1, [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects dialogue data with candidates; an analysis unit that analyzes the dialogue data collected by the collection unit; A selection unit that selects second interviewees based on the analysis results obtained by the analysis unit; An assignment department that considers assignment destinations based on the regional characteristics of the candidates selected by the selection department. A system characterized by:

2. The collecting unit includes: Keep a detailed record of what the candidate said or answered during the interview 2. The system of claim 1 .

3. The analysis unit is Analyze the content of a candidate's statements, their choice of words, and the characteristics of their speaking style to evaluate their thinking style and personality 2. The system of claim 1 .

4. The selection unit is Select candidates with the right thinking style or personality for a particular position 2. The system of claim 1 .

5. The allocation department includes: Suggest suitable placements based on candidates' personality or thinking type 2. The system of claim 1 .

6. The collecting unit includes: Estimate the candidate's emotions and adjust the timing of conversation data collection based on the estimated emotions.

2. The system of claim 1 .

7. The collecting unit includes: Analyze past interview history of candidates and choose the appropriate collection method 2. The system of claim 1 .

8. The collecting unit includes: Filter based on candidates' current work experience or skill set 2. The system of claim 1 .

Images