System

Abstract

An object of a system according to an embodiment is to reduce variations in evaluations of interviews and to draw attention to non-verbal elements.SOLUTION: A system includes a transcription unit, an evaluation unit, and a notable shift unit. The transcription unit converts the voice data of the interview into text data. The evaluation unit evaluates the text data converted by the transcription unit on the basis of a company's evaluation standard. The attention shift unit makes the interviewer pay attention to the non-verbal element based on the evaluation by the evaluation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional techniques, there is a risk that interview evaluations may vary depending on the interviewer.

[0005] The system according to the embodiment aims to reduce variability in the evaluation of interviews and draw attention to non-verbal factors. [Means for solving the problem]

[0006] The system according to the embodiment includes a transcription unit, an evaluation unit, and an attention shifting unit. The transcription unit converts audio data from an interview into text data. The evaluation unit evaluates the text data converted by the transcription unit based on the company's own evaluation criteria. The attention shifting unit directs the interviewer's attention to non-verbal elements based on the evaluation by the evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment can reduce the variability in the evaluation of interviews and draw attention to non-verbal factors. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's 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 read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The evaluation system according to an embodiment of the present invention transcribes interviews and quantifies evaluations based on the company's evaluation standards by reading in the transcripts. This allows interviewers and human resources personnel to focus on the facial expressions and behavior of the interviewee rather than the content of the conversation, reducing the variability in evaluations of the content of the conversation depending on the interviewer.

[0029] The evaluation system according to the embodiment includes a transcription unit, an evaluation unit, and an attention shifting unit. The transcription unit converts interview audio data into text data. For example, the audio data is input into a generation AI and transcribed using speech recognition technology. The transcription unit can also transcribe audio data in real time. For example, the audio data is input into a generation AI in real time and transcribed immediately. The evaluation unit evaluates the text data converted by the transcription unit based on the company's evaluation criteria. For example, the generation AI analyzes the text data and assigns scores to evaluation items such as "initiative," "leadership," and "problem-solving ability." The evaluation unit can also estimate emotions based on the interviewer's answers and reflect the emotional intensity in the evaluation. For example, the generation AI analyzes the interviewer's emotional state using an emotion estimation algorithm and reflects the intensity in the evaluation. The attention shifting unit directs the interviewer's attention to non-verbal elements based on the evaluation by the evaluation unit. For example, the attention shifting unit analyzes the interviewer's facial expressions and gestures and provides feedback to the interviewer. The attention shifting unit can also automatically highlight points that the interviewer should pay attention to, supporting the progress of the interview. For example, if the interviewer is talking about an important point, that part will be highlighted. As a result, the evaluation system according to the embodiment allows the interviewer to focus on non-verbal elements, enabling a more comprehensive evaluation and reducing variation in evaluation. For example, the quality of the interview improves when the interviewer pays attention to the facial expressions and behavior of the interviewee. Furthermore, the evaluation of the conversation content by the generation AI ensures fairness in the evaluation.

[0030] The transcription unit can analyze video data as well as audio data from interviews and convert facial expressions and gestures into text data. For example, the transcription unit inputs video data from an interview into a generation AI and analyzes the interviewer's facial expressions using a facial expression recognition algorithm. For example, if the interviewer is smiling while speaking, that facial expression is converted into text data as a "smile." The transcription unit can also analyze video data from an interview and convert the interviewer's gestures into text data. For example, if the interviewer is explaining by moving their hands, those gestures are converted into text data as "hand movements." In this way, by converting the interviewer's facial expressions and gestures into text data, it becomes easier for the interviewer to grasp non-verbal elements.

[0031] The transcription unit can transcribe the interview audio data in real time so that the interviewer can check it on the spot. For example, the transcription unit inputs the interview audio data into a generative AI in real time and immediately transcribes it using speech recognition technology. For example, the interviewer's answers are displayed as text data in real time. The transcription unit can also provide an interface that allows the interviewer to check the real-time transcribed data on the spot. For example, the transcription unit can allow the interviewer to check the real-time transcribed data on a screen. This allows the interviewer to check the transcribed data in real time, which makes the interview proceed more smoothly.

[0032] When transcribing an interview, the transcription department can automatically translate it into different languages, making it usable by multinational companies. For example, the transcription department inputs the audio data of an interview into a generative AI, transcribes it using speech recognition technology, and simultaneously automatically translates it into different languages. For example, the content of an interview in Japanese is translated into English. The transcription department can also provide an interface that allows interviewers to check the text data that has been automatically translated into different languages. For example, the transcription department can allow interviewers to check the text data translated into different languages ​​on a screen. This allows automatic translation into different languages ​​to be usable by multinational companies.

[0033] The transcription department can add a function that analyzes interview audio data and automatically highlights specific keywords and phrases. For example, the transcription department inputs interview audio data into a generation AI and transcribes it using speech recognition technology, while automatically highlighting specific keywords and phrases. For example, it highlights important keywords such as "leadership" and "problem solving." The transcription department can also set criteria for highlighting specific keywords and phrases. For example, it can highlight keywords based on frequency of appearance or importance. This allows interviewers to instantly confirm important information by automatically highlighting specific keywords and phrases.

[0034] When evaluating the content of the conversation, the evaluation unit can compare it with past interview data to detect trends and patterns. For example, the evaluation unit inputs the interviewer's answers into the generation AI and compares it with past interview data to detect trends and patterns. For example, it extracts the characteristics of answers that are highly rated for "leadership" from past interview data. The evaluation unit can also set criteria for detecting trends and patterns. For example, it analyzes trends based on changes over time or frequency. This allows it to detect trends and patterns by comparing it with past interview data, improving the accuracy of the evaluation.

[0035] The evaluation department can develop an algorithm that analyzes the interviewer's answers and automatically extracts latent skills and abilities. For example, the evaluation department could input the interviewer's answers into a generation AI and develop an algorithm that automatically extracts latent skills and abilities using natural language processing technology. For example, skills such as "leadership" and "problem-solving ability" could be extracted. The evaluation department can also set criteria for extracting latent skills and abilities. For example, skills could be extracted based on keywords and phrases in the answers. This allows for a more comprehensive evaluation by automatically extracting the interviewer's latent skills and abilities.

[0036] The evaluation department can customize the evaluation of the conversation content to match the standards of different industries and job types, increasing versatility. For example, the evaluation department inputs the interviewer's responses into the generation AI and customizes the evaluation to match the standards of different industries and job types. For example, different evaluation standards can be set for technical jobs and sales jobs. The evaluation department can also develop algorithms that perform evaluations based on the standards of different industries and job types. For example, evaluation items and standards can be set for each industry and evaluations are made based on those. This increases versatility by customizing the evaluation to match the standards of different industries and job types.

[0037] The evaluation unit can visualize the interviewer's answers and display the evaluation results in graphs and charts. For example, the evaluation unit inputs the interviewer's answers into a generation AI and visualizes the evaluation results. For example, the score for each evaluation item can be displayed in a bar graph or pie chart. The evaluation unit can also set criteria for visualizing the evaluation results. For example, it can select the graph format based on the importance of the evaluation item. In this way, visualizing the evaluation results makes it easier for interviewers to intuitively understand the evaluation results.

[0038] The evaluation unit can visualize the interviewer's answers and display the evaluation results in graphs and charts. For example, the evaluation unit inputs the interviewer's answers into a generation AI and visualizes the evaluation results. For example, the score for each evaluation item can be displayed in a bar graph or pie chart. The evaluation unit can also set criteria for visualizing the evaluation results. For example, it can select the graph format based on the importance of the evaluation item. In this way, visualizing the evaluation results makes it easier for interviewers to intuitively understand the evaluation results.

[0039] The attention shifting unit can develop a system that analyzes non-verbal elements that interviewers should pay attention to in real time and provides feedback to the interviewers. For example, the attention shifting unit inputs interview video data into a generative AI and analyzes non-verbal elements in real time. For example, it analyzes the interviewer's facial expressions and gestures and provides feedback to the interviewer. The attention shifting unit can also set criteria for analyzing non-verbal elements. For example, it performs analysis based on changes in facial expressions and the frequency of gestures. This allows the quality of interviews to be improved by analyzing non-verbal elements that interviewers should pay attention to in real time and providing feedback.

[0040] The attention shifting unit can incorporate an algorithm that analyzes the facial expressions and behavior of the interviewer and detects specific behavioral patterns. For example, the attention shifting unit inputs video data from an interview into the generation AI and analyzes the interviewer's facial expressions using a facial expression recognition algorithm. For example, if the interviewer is smiling while speaking, the expression is recorded as a "smile." The attention shifting unit can also analyze the interviewer's behavior and detect specific behavioral patterns. For example, it can record repeated actions performed by the interviewer as a "specific behavioral pattern." This allows the interviewer to gain a deeper understanding of the interviewer's behavior by analyzing the interviewer's facial expressions and behavior and detecting specific behavioral patterns.

[0041] The attention shifting unit can provide tools that automatically highlight points that interviewers should pay attention to and support the progress of the interview. For example, the attention shifting unit inputs interview video data into generative AI and develops an algorithm that automatically highlights points that interviewers should pay attention to. For example, if the interviewer is talking about an important point, that part will be highlighted. The attention shifting unit can also provide tools that support the progress of the interview. For example, it provides an interface that allows interviewers to check points that they should pay attention to in real time. This will automatically highlight points that interviewers should pay attention to, making the interview progress more smoothly.

[0042] The Attention Shifting Unit can customize the points that interviewers should focus on to suit the standards of different cultures and regions. For example, the Attention Shifting Unit inputs interview video data into a generative AI and customizes the points to focus on to suit the standards of different cultures and regions. For example, politeness in Japanese culture is added to the evaluation criteria. The Attention Shifting Unit can also set points to focus on based on the standards of different cultures and regions. For example, evaluations are made based on the culture and standards of each country and region. This allows the points to be customized to suit the standards of different cultures and regions, making it usable in global companies.

[0043] The attention shifting unit can develop an interface that visualizes and displays in real time the points that interviewers should pay attention to. For example, the attention shifting unit inputs interview video data into a generation AI and develops an algorithm that visualizes the points that should be noted. For example, it displays the interviewer's facial expressions and gestures in graphs and charts. The attention shifting unit can also provide an interface that displays the points that should be noted in real time. For example, it provides a screen that allows interviewers to check the points that should be noted in real time. This makes it easier for interviewers to check on the spot by visualizing and displaying the points that should be noted in real time.

[0044] The evaluation department can add a function to analyze the evaluation history of interviewers and check the consistency of evaluations. For example, the evaluation department inputs the evaluation history of interviewers into the generation AI and develops an algorithm to check the consistency of evaluations. For example, it analyzes whether the evaluations for the same evaluation items are consistent. The evaluation department can also set criteria for checking the consistency of evaluations. For example, it evaluates consistency based on the variability and fluctuations in evaluations. In this way, by analyzing the evaluation history of interviewers and checking the consistency, it is possible to reduce the variability in evaluations.

[0045] The evaluation department can standardize the evaluation criteria of interviewers and build a system in which the generation AI performs evaluations based on those criteria. For example, the evaluation department standardizes the evaluation criteria of interviewers and inputs those criteria into the generation AI. For example, it sets evaluation items such as "initiative," "leadership," and "problem-solving ability." The evaluation department can also develop an algorithm that performs evaluations based on standardized evaluation criteria. For example, it performs evaluations based on standardized evaluation items and evaluation methods. This standardizes the evaluation criteria and allows the generation AI to perform evaluations based on those standards, reducing variation in evaluations.

[0046] The evaluation department can automatically generate feedback on interviewer evaluations and correct evaluation variance in real time. For example, the evaluation department inputs interviewer evaluation data into a generation AI and develops an algorithm that automatically generates feedback on evaluations. For example, it detects evaluation variance and suggests points for correction. The evaluation department can also set criteria for correcting evaluation variance in real time. For example, it makes corrections based on fluctuations and consistency in evaluations. In this way, evaluation variance can be reduced by automatically generating feedback on evaluations and correcting it in real time.

[0047] The evaluation department can develop an algorithm that integrates the evaluations of different interviewers and generates an overall evaluation to reduce variability in evaluations. For example, the evaluation department inputs evaluation data from different interviewers into a generation AI and develops an algorithm that generates an overall evaluation. For example, the evaluations of multiple interviewers are integrated and an average score is calculated. The evaluation department can also set criteria for integrating evaluations. For example, the evaluation department performs an overall evaluation based on the integration of evaluation data or the integration of evaluation results. In this way, the evaluations of different interviewers are integrated and an overall evaluation is generated, thereby reducing variability in evaluations.

[0048] The evaluation department can provide a dashboard that visualizes the interviewer's evaluations and enables the variance in evaluations to be confirmed at a glance. For example, the evaluation department inputs the interviewer's evaluation data into a generation AI and develops an algorithm that visualizes the variance in evaluations. For example, the evaluation department displays the evaluation scores in a graph or chart. The evaluation department can also provide a dashboard for checking the variance in evaluations. For example, it provides a screen that enables the fluctuations and consistency of the evaluation scores to be confirmed at a glance. In this way, by visualizing the evaluations and checking them on the dashboard, the variance in evaluations can be understood at a glance.

[0049] The evaluation department can use generative AI to automatically learn their company's evaluation criteria and optimize the evaluation process. For example, the evaluation department inputs their company's evaluation criteria into the generative AI and develops an algorithm that automatically learns them. For example, they set evaluation items such as "initiative," "leadership," and "problem-solving ability." The evaluation department can also set criteria for optimizing the evaluation process. For example, they can optimize based on the importance of evaluation items and evaluation methods. This allows the system to automatically learn their company's evaluation criteria and optimize the evaluation process, improving the consistency of evaluations.

[0050] The evaluation department can develop an algorithm that evaluates an interviewer's skills and abilities in detail based on the company's evaluation criteria. For example, the evaluation department inputs the company's evaluation criteria into a generation AI and develops an algorithm that evaluates an interviewer's skills and abilities in detail. For example, the evaluation department can set evaluation items such as "technical knowledge" and "communication skills." The evaluation department can also set criteria for evaluating skills and abilities in detail. For example, the evaluation can be based on a more detailed breakdown of evaluation items and a more refined evaluation method. This enables a more appropriate personnel evaluation by evaluating skills and abilities in detail based on the company's evaluation criteria.

[0051] The evaluation department can build a system in which it periodically reviews its own evaluation criteria and the generation AI performs evaluations based on the latest criteria. The evaluation department, for example, periodically reviews its own evaluation criteria and inputs the latest criteria into the generation AI. For example, it updates the evaluation items in response to changes in the industry or the needs of the company. The evaluation department can also set the frequency and method for reviewing the evaluation criteria. For example, it updates the evaluation criteria every six months or annually. This improves the accuracy of evaluations by periodically reviewing the evaluation criteria and performing evaluations based on the latest criteria.

[0052] The evaluation department can apply its company's evaluation criteria to different industries and job types, increasing versatility. For example, the evaluation department inputs its company's evaluation criteria into a generation AI and develops an algorithm that applies them to different industries and job types. For example, different evaluation criteria can be set for technical positions and sales positions. The evaluation department can also set criteria to be applied to different industries and job types. For example, evaluations are conducted based on evaluation items and standards for each industry. This increases versatility by applying the company's evaluation criteria to different industries and job types.

[0053] The evaluation department can provide tools that visualize their company's evaluation criteria and enable an intuitive understanding of the evaluation process. For example, the evaluation department inputs their company's evaluation criteria into a generation AI and develops an algorithm to visualize them. For example, the evaluation department can display the scores for each evaluation item in a bar graph or pie chart. The evaluation department can also provide tools that enable an intuitive understanding of the evaluation process. For example, it can provide an interface that visually displays the importance of evaluation items and the evaluation method. This improves the efficiency of evaluation by visualizing the evaluation criteria and enabling an intuitive understanding of the evaluation process.

[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] The evaluation unit can add a function to analyze the content of interviewer's answers and check the consistency of the answers. For example, if an interviewer gives contradictory answers to different questions, the function can detect the contradiction and notify the interviewer. The evaluation unit can also set criteria for checking the consistency of answers. For example, the function can evaluate consistency based on the degree of agreement of specific keywords or phrases. This allows for more reliable evaluation by checking the consistency of interviewer's answers.

[0056] The evaluation department can add a function to analyze the content of interviewers' answers and evaluate the originality of the answers. For example, if an interviewer offers a unique perspective or idea rather than a general answer, that originality can be reflected in the evaluation. The evaluation department can also set criteria for evaluating the originality of answers. For example, the evaluation can be based on the creativity and novelty of the answers. This makes it easier to find creative talent by reflecting the originality of the interviewer in the evaluation.

[0057] The evaluation department can add a function that analyzes the content of interviewer's answers and evaluates the specificity of the answers. For example, if the interviewer answers using specific examples or data, that specificity will be reflected in the evaluation. The evaluation department can also set criteria for evaluating the specificity of answers. For example, the evaluation will be based on the number of specific examples and the level of detail. In this way, by reflecting the specificity of the interviewer in the evaluation, it will be easier to find personnel with high practical skills.

[0058] The evaluation department can add a function to analyze the content of the interviewer's answers and evaluate the logic of the answers. For example, if the interviewer answers with a logical structure, that logic can be reflected in the evaluation. The evaluation department can also set criteria for evaluating the logic of answers. For example, the evaluation can be based on the logical structure and clarity of causal relationships. In this way, by reflecting the interviewer's logic in the evaluation, it becomes easier to find people with strong logical thinking skills.

[0059] The evaluation department can add a function that analyzes the content of interviewees' answers and evaluates the adaptability of the answers. For example, it can evaluate whether the interviewee can flexibly respond to different situations and challenges. The evaluation department can also set criteria for evaluating the adaptability of answers. For example, it can evaluate based on the flexibility and adaptability of answers to different scenarios. This makes it easier to find people who are resilient to change by reflecting the adaptability of the interviewee in the evaluation.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The transcription department converts the interview audio data into text data. For example, the interview audio data is input into the generation AI, which then transcribes it using speech recognition technology. The transcription department can also transcribe audio data in real time. For example, the interview audio data is input into the generation AI in real time, which then transcribes it instantly. Step 2: The evaluation department evaluates the text data converted by the transcription department based on the company's evaluation criteria. For example, the generation AI analyzes the text data and assigns scores to evaluation items such as "action," "leadership," and "problem-solving ability." The evaluation department can also estimate the emotions expressed by the interviewer's answers and reflect the emotional intensity in the evaluation. For example, the generation AI uses an emotion estimation algorithm to analyze the interviewer's emotional state and reflect that intensity in the evaluation. Step 3: The attention shifting unit directs the interviewer's attention to non-verbal elements based on the evaluation by the evaluation unit. For example, it analyzes the interviewer's facial expressions and gestures and provides feedback to the interviewer. The attention shifting unit can also automatically highlight points that the interviewer should pay attention to, supporting the progress of the interview. For example, if the interviewer is talking about an important point, it will highlight that part.

[0062] (Example 2) The evaluation system according to an embodiment of the present invention transcribes interviews and quantifies evaluations based on the company's evaluation standards by reading in the transcripts. This allows interviewers and human resources personnel to focus on the facial expressions and behavior of the interviewee rather than the content of the conversation, reducing the variability in evaluations of the content of the conversation depending on the interviewer.

[0063] The evaluation system according to the embodiment includes a transcription unit, an evaluation unit, and an attention shifting unit. The transcription unit converts interview audio data into text data. For example, the audio data is input into a generation AI and transcribed using speech recognition technology. The transcription unit can also transcribe audio data in real time. For example, the audio data is input into a generation AI in real time and transcribed immediately. The evaluation unit evaluates the text data converted by the transcription unit based on the company's evaluation criteria. For example, the generation AI analyzes the text data and assigns scores to evaluation items such as "initiative," "leadership," and "problem-solving ability." The evaluation unit can also estimate emotions based on the interviewer's answers and reflect the emotional intensity in the evaluation. For example, the generation AI analyzes the interviewer's emotional state using an emotion estimation algorithm and reflects the intensity in the evaluation. The attention shifting unit directs the interviewer's attention to non-verbal elements based on the evaluation by the evaluation unit. For example, the attention shifting unit analyzes the interviewer's facial expressions and gestures and provides feedback to the interviewer. The attention shifting unit can also automatically highlight points that the interviewer should pay attention to, supporting the progress of the interview. For example, if the interviewer is talking about an important point, that part will be highlighted. As a result, the evaluation system according to the embodiment allows the interviewer to focus on non-verbal elements, enabling a more comprehensive evaluation and reducing variation in evaluation. For example, the quality of the interview improves when the interviewer pays attention to the facial expressions and behavior of the interviewee. Furthermore, the evaluation of the conversation content by the generation AI ensures fairness in the evaluation.

[0064] The transcription unit can estimate emotions from the interview audio data and add the interviewer's emotional state to the text data. For example, the transcription unit inputs the interview audio data into a generation AI and analyzes the interviewer's emotional state using an emotion estimation algorithm. For example, if the interviewer is nervous, the transcription unit adds that emotional state to the text data as "nervous." The transcription unit can also analyze the interview audio data and display the interviewer's emotional state in real time. For example, if the interviewer is speaking with confidence, the transcription unit displays that emotional state as "confident" in real time. By adding the interviewer's emotional state to the text data, it becomes easier for the interviewer to understand the interviewer's emotions.

[0065] The transcription unit can analyze video data as well as audio data from interviews and convert facial expressions and gestures into text data. For example, the transcription unit inputs video data from an interview into a generation AI and analyzes the interviewer's facial expressions using a facial expression recognition algorithm. For example, if the interviewer is smiling while speaking, that facial expression is converted into text data as a "smile." The transcription unit can also analyze video data from an interview and convert the interviewer's gestures into text data. For example, if the interviewer is explaining by moving their hands, those gestures are converted into text data as "hand movements." In this way, by converting the interviewer's facial expressions and gestures into text data, it becomes easier for the interviewer to grasp non-verbal elements.

[0066] The transcription unit can transcribe the interview audio data in real time so that the interviewer can check it on the spot. For example, the transcription unit inputs the interview audio data into a generative AI in real time and immediately transcribes it using speech recognition technology. For example, the interviewer's answers are displayed as text data in real time. The transcription unit can also provide an interface that allows the interviewer to check the real-time transcribed data on the spot. For example, the transcription unit can allow the interviewer to check the real-time transcribed data on a screen. This allows the interviewer to check the transcribed data in real time, which makes the interview proceed more smoothly.

[0067] When transcribing an interview, the transcription department can automatically translate it into different languages, making it usable by multinational companies. For example, the transcription department inputs the audio data of an interview into a generative AI, transcribes it using speech recognition technology, and simultaneously automatically translates it into different languages. For example, the content of an interview in Japanese is translated into English. The transcription department can also provide an interface that allows interviewers to check the text data that has been automatically translated into different languages. For example, the transcription department can allow interviewers to check the text data translated into different languages ​​on a screen. This allows automatic translation into different languages ​​to be usable by multinational companies.

[0068] The transcription department can add a function that analyzes interview audio data and automatically highlights specific keywords and phrases. For example, the transcription department inputs interview audio data into a generation AI and transcribes it using speech recognition technology, while automatically highlighting specific keywords and phrases. For example, it highlights important keywords such as "leadership" and "problem solving." The transcription department can also set criteria for highlighting specific keywords and phrases. For example, it can highlight keywords based on frequency of appearance or importance. This allows interviewers to instantly confirm important information by automatically highlighting specific keywords and phrases.

[0069] The transcription unit can use an emotion estimation function to display the interviewer's emotional state in real time, allowing the interviewer to respond on the spot. For example, the transcription unit inputs interview audio data into a generation AI and uses an emotion estimation algorithm to analyze the interviewer's emotional state in real time. For example, if the interviewer is nervous, the transcription unit can display the emotional state as "nervous" in real time. The transcription unit can also provide an interface that displays the interviewer's emotional state in real time. For example, the interface can allow the interviewer to check the interviewer's emotional state on a screen in real time. This allows the interviewer to respond appropriately on the spot by displaying the interviewer's emotional state in real time.

[0070] The evaluation unit can estimate the emotions of the interviewer's answers and reflect the emotional intensity in the evaluation. For example, the evaluation unit inputs the interviewer's answers into a generation AI and analyzes the emotional intensity using an emotion estimation algorithm. For example, if the interviewer speaks passionately, the emotional intensity is reflected in the evaluation as "Passion (Intensity: 8)." The evaluation unit can also set criteria for reflecting emotional intensity in the evaluation. For example, the evaluation is based on the strength and type of emotion. This allows the interviewer's emotional intensity to be reflected in the evaluation, making it possible to make a more comprehensive evaluation.

[0071] When evaluating the content of the conversation, the evaluation unit can compare it with past interview data to detect trends and patterns. For example, the evaluation unit inputs the interviewer's answers into the generation AI and compares it with past interview data to detect trends and patterns. For example, it extracts the characteristics of answers that are highly rated for "leadership" from past interview data. The evaluation unit can also set criteria for detecting trends and patterns. For example, it analyzes trends based on changes over time or frequency. This allows it to detect trends and patterns by comparing it with past interview data, improving the accuracy of the evaluation.

[0072] The evaluation department can develop an algorithm that analyzes the interviewer's answers and automatically extracts latent skills and abilities. For example, the evaluation department could input the interviewer's answers into a generation AI and develop an algorithm that automatically extracts latent skills and abilities using natural language processing technology. For example, skills such as "leadership" and "problem-solving ability" could be extracted. The evaluation department can also set criteria for extracting latent skills and abilities. For example, skills could be extracted based on keywords and phrases in the answers. This allows for a more comprehensive evaluation by automatically extracting the interviewer's latent skills and abilities.

[0073] The evaluation department can customize the evaluation of the conversation content to match the standards of different industries and job types, increasing versatility. For example, the evaluation department inputs the interviewer's responses into the generation AI and customizes the evaluation to match the standards of different industries and job types. For example, different evaluation standards can be set for technical jobs and sales jobs. The evaluation department can also develop algorithms that perform evaluations based on the standards of different industries and job types. For example, evaluation items and standards can be set for each industry and evaluations are made based on those. This increases versatility by customizing the evaluation to match the standards of different industries and job types.

[0074] The evaluation unit can visualize the interviewer's answers and display the evaluation results in graphs and charts. For example, the evaluation unit inputs the interviewer's answers into a generation AI and visualizes the evaluation results. For example, the score for each evaluation item can be displayed in a bar graph or pie chart. The evaluation unit can also set criteria for visualizing the evaluation results. For example, it can select the graph format based on the importance of the evaluation item. In this way, visualizing the evaluation results makes it easier for interviewers to intuitively understand the evaluation results.

[0075] The evaluation unit can visualize the interviewer's answers and display the evaluation results in graphs and charts. For example, the evaluation unit inputs the interviewer's answers into a generation AI and visualizes the evaluation results. For example, the score for each evaluation item can be displayed in a bar graph or pie chart. The evaluation unit can also set criteria for visualizing the evaluation results. For example, it can select the graph format based on the importance of the evaluation item. In this way, visualizing the evaluation results makes it easier for interviewers to intuitively understand the evaluation results.

[0076] The evaluation unit can use the emotion estimation function to collect the interviewer's emotional reactions to the interviewer's answers and reflect them in the evaluation. For example, the evaluation unit inputs the interviewer's answers into the generation AI and uses the emotion estimation algorithm to collect the interviewer's emotional reactions. For example, if the interviewer is surprised by the interviewer's answers, the evaluation unit records this emotional reaction as "surprise." The evaluation unit can also set criteria for reflecting the interviewer's emotional reactions in the evaluation. For example, the evaluation can be based on the type and intensity of emotion. This allows the interviewer's emotional reactions to be reflected in the evaluation, making it possible to perform a more comprehensive evaluation.

[0077] The attention shifting unit can develop a system that analyzes non-verbal elements that interviewers should pay attention to in real time and provides feedback to the interviewers. For example, the attention shifting unit inputs interview video data into a generative AI and analyzes non-verbal elements in real time. For example, it analyzes the interviewer's facial expressions and gestures and provides feedback to the interviewer. The attention shifting unit can also set criteria for analyzing non-verbal elements. For example, it performs analysis based on changes in facial expressions and the frequency of gestures. This allows the quality of interviews to be improved by analyzing non-verbal elements that interviewers should pay attention to in real time and providing feedback.

[0078] The attention shifting unit can incorporate an algorithm that analyzes the facial expressions and behavior of the interviewer and detects specific behavioral patterns. For example, the attention shifting unit inputs video data from an interview into the generation AI and analyzes the interviewer's facial expressions using a facial expression recognition algorithm. For example, if the interviewer is smiling while speaking, the expression is recorded as a "smile." The attention shifting unit can also analyze the interviewer's behavior and detect specific behavioral patterns. For example, it can record repeated actions performed by the interviewer as a "specific behavioral pattern." This allows the interviewer to gain a deeper understanding of the interviewer's behavior by analyzing the interviewer's facial expressions and behavior and detecting specific behavioral patterns.

[0079] The attention shifting unit can provide tools that automatically highlight points that interviewers should pay attention to and support the progress of the interview. For example, the attention shifting unit inputs interview video data into generative AI and develops an algorithm that automatically highlights points that interviewers should pay attention to. For example, if the interviewer is talking about an important point, that part will be highlighted. The attention shifting unit can also provide tools that support the progress of the interview. For example, it provides an interface that allows interviewers to check points that they should pay attention to in real time. This will automatically highlight points that interviewers should pay attention to, making the interview progress more smoothly.

[0080] The Attention Shifting Unit can customize the points that interviewers should focus on to suit the standards of different cultures and regions. For example, the Attention Shifting Unit inputs interview video data into a generative AI and customizes the points to focus on to suit the standards of different cultures and regions. For example, politeness in Japanese culture is added to the evaluation criteria. The Attention Shifting Unit can also set points to focus on based on the standards of different cultures and regions. For example, evaluations are made based on the culture and standards of each country and region. This allows the points to be customized to suit the standards of different cultures and regions, making it usable in global companies.

[0081] The attention shifting unit can develop an interface that visualizes and displays in real time the points that interviewers should pay attention to. For example, the attention shifting unit inputs interview video data into a generation AI and develops an algorithm that visualizes the points that should be noted. For example, it displays the interviewer's facial expressions and gestures in graphs and charts. The attention shifting unit can also provide an interface that displays the points that should be noted in real time. For example, it provides a screen that allows interviewers to check the points that should be noted in real time. This makes it easier for interviewers to check on the spot by visualizing and displaying the points that should be noted in real time.

[0082] The attention shifting unit can use the emotion estimation function to evaluate points that the interviewer should pay attention to from an emotional perspective and provide feedback. For example, the attention shifting unit inputs interview video data into the generation AI and analyzes the interviewer's emotional state using an emotion estimation algorithm. For example, if the interviewer is nervous, the emotional state is recorded as "tension." The attention shifting unit can also evaluate points that the interviewer should pay attention to from an emotional perspective and provide feedback. For example, it can suggest appropriate responses to the interviewer based on the interviewer's emotional state. This makes it easier for the interviewer to understand the interviewer's emotional state by evaluating from an emotional perspective and providing feedback.

[0083] The evaluation department can add a function to analyze the evaluation history of interviewers and check the consistency of evaluations. For example, the evaluation department inputs the evaluation history of interviewers into the generation AI and develops an algorithm to check the consistency of evaluations. For example, it analyzes whether the evaluations for the same evaluation items are consistent. The evaluation department can also set criteria for checking the consistency of evaluations. For example, it evaluates consistency based on the variability and fluctuations in evaluations. In this way, by analyzing the evaluation history of interviewers and checking the consistency, it is possible to reduce the variability in evaluations.

[0084] The evaluation department can standardize the evaluation criteria of interviewers and build a system in which the generation AI performs evaluations based on those criteria. For example, the evaluation department standardizes the evaluation criteria of interviewers and inputs those criteria into the generation AI. For example, it sets evaluation items such as "initiative," "leadership," and "problem-solving ability." The evaluation department can also develop an algorithm that performs evaluations based on standardized evaluation criteria. For example, it performs evaluations based on standardized evaluation items and evaluation methods. This standardizes the evaluation criteria and allows the generation AI to perform evaluations based on those standards, reducing variation in evaluations.

[0085] The evaluation department can automatically generate feedback on interviewer evaluations and correct evaluation variance in real time. For example, the evaluation department inputs interviewer evaluation data into a generation AI and develops an algorithm that automatically generates feedback on evaluations. For example, it detects evaluation variance and suggests points for correction. The evaluation department can also set criteria for correcting evaluation variance in real time. For example, it makes corrections based on fluctuations and consistency in evaluations. In this way, evaluation variance can be reduced by automatically generating feedback on evaluations and correcting it in real time.

[0086] The evaluation department can develop an algorithm that integrates the evaluations of different interviewers and generates an overall evaluation to reduce variability in evaluations. For example, the evaluation department inputs evaluation data from different interviewers into a generation AI and develops an algorithm that generates an overall evaluation. For example, the evaluations of multiple interviewers are integrated and an average score is calculated. The evaluation department can also set criteria for integrating evaluations. For example, the evaluation department performs an overall evaluation based on the integration of evaluation data or the integration of evaluation results. In this way, the evaluations of different interviewers are integrated and an overall evaluation is generated, thereby reducing variability in evaluations.

[0087] The evaluation department can provide a dashboard that visualizes the interviewer's evaluations and enables the variance in evaluations to be confirmed at a glance. For example, the evaluation department inputs the interviewer's evaluation data into a generation AI and develops an algorithm that visualizes the variance in evaluations. For example, the evaluation department displays the evaluation scores in a graph or chart. The evaluation department can also provide a dashboard for checking the variance in evaluations. For example, it provides a screen that enables the fluctuations and consistency of the evaluation scores to be confirmed at a glance. In this way, by visualizing the evaluations and checking them on the dashboard, the variance in evaluations can be understood at a glance.

[0088] The evaluation unit can use the emotion estimation function to reflect the interviewer's emotional state in the evaluation, thereby reducing variability in the evaluation. For example, the evaluation unit inputs the interviewer's emotional state into the generation AI and reflects it in the evaluation using an emotion estimation algorithm. For example, if the interviewer is nervous, the evaluation unit reflects that emotional state as "tension" in the evaluation. The evaluation unit can also set criteria for reflecting the interviewer's emotional state in the evaluation. For example, the evaluation is made based on the type and intensity of emotion. In this way, by reflecting the interviewer's emotional state in the evaluation, variability in the evaluation can be reduced.

[0089] The evaluation department can use generative AI to automatically learn their company's evaluation criteria and optimize the evaluation process. For example, the evaluation department inputs their company's evaluation criteria into the generative AI and develops an algorithm that automatically learns them. For example, they set evaluation items such as "initiative," "leadership," and "problem-solving ability." The evaluation department can also set criteria for optimizing the evaluation process. For example, they can optimize based on the importance of evaluation items and evaluation methods. This allows the system to automatically learn their company's evaluation criteria and optimize the evaluation process, improving the consistency of evaluations.

[0090] The evaluation department can develop an algorithm that evaluates an interviewer's skills and abilities in detail based on the company's evaluation criteria. For example, the evaluation department inputs the company's evaluation criteria into a generation AI and develops an algorithm that evaluates an interviewer's skills and abilities in detail. For example, the evaluation department can set evaluation items such as "technical knowledge" and "communication skills." The evaluation department can also set criteria for evaluating skills and abilities in detail. For example, the evaluation can be based on a more detailed breakdown of evaluation items and a more refined evaluation method. This enables a more appropriate personnel evaluation by evaluating skills and abilities in detail based on the company's evaluation criteria.

[0091] The evaluation department can build a system in which it periodically reviews its own evaluation criteria and the generation AI performs evaluations based on the latest criteria. The evaluation department, for example, periodically reviews its own evaluation criteria and inputs the latest criteria into the generation AI. For example, it updates the evaluation items in response to changes in the industry or the needs of the company. The evaluation department can also set the frequency and method for reviewing the evaluation criteria. For example, it updates the evaluation criteria every six months or annually. This improves the accuracy of evaluations by periodically reviewing the evaluation criteria and performing evaluations based on the latest criteria.

[0092] The evaluation department can apply its company's evaluation criteria to different industries and job types, increasing versatility. For example, the evaluation department inputs its company's evaluation criteria into a generation AI and develops an algorithm that applies them to different industries and job types. For example, different evaluation criteria can be set for technical positions and sales positions. The evaluation department can also set criteria to be applied to different industries and job types. For example, evaluations are conducted based on evaluation items and standards for each industry. This increases versatility by applying the company's evaluation criteria to different industries and job types.

[0093] The evaluation department can provide tools that visualize their company's evaluation criteria and enable an intuitive understanding of the evaluation process. For example, the evaluation department inputs their company's evaluation criteria into a generation AI and develops an algorithm to visualize them. For example, the evaluation department can display the scores for each evaluation item in a bar graph or pie chart. The evaluation department can also provide tools that enable an intuitive understanding of the evaluation process. For example, it can provide an interface that visually displays the importance of evaluation items and the evaluation method. This improves the efficiency of evaluation by visualizing the evaluation criteria and enabling an intuitive understanding of the evaluation process.

[0094] The evaluation unit can use the emotion estimation function to collect users' emotional responses to evaluation results based on their own evaluation criteria, and use the collected data to improve the evaluation criteria. For example, the evaluation unit inputs the evaluation results based on their own evaluation criteria into the generation AI and uses an emotion estimation algorithm to collect users' emotional responses. For example, the evaluation unit records the user's emotional state regarding the evaluation results as "satisfied" or "dissatisfied." The evaluation unit can also set criteria for collecting users' emotional responses. For example, the evaluation unit collects emotional responses based on facial expression analysis or voice analysis. This allows the evaluation accuracy to be improved by collecting users' emotional responses and using them to improve the evaluation criteria.

[0095] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0096] The evaluation unit can add a function to analyze the content of interviewer's answers and check the consistency of the answers. For example, if an interviewer gives contradictory answers to different questions, the function can detect the contradiction and notify the interviewer. The evaluation unit can also set criteria for checking the consistency of answers. For example, the function can evaluate consistency based on the degree of agreement of specific keywords or phrases. This allows for more reliable evaluation by checking the consistency of interviewer's answers.

[0097] The evaluation department can add a function to analyze the content of interviewers' answers and evaluate the originality of the answers. For example, if an interviewer offers a unique perspective or idea rather than a general answer, that originality can be reflected in the evaluation. The evaluation department can also set criteria for evaluating the originality of answers. For example, the evaluation can be based on the creativity and novelty of the answers. This makes it easier to find creative talent by reflecting the originality of the interviewer in the evaluation.

[0098] The evaluation department can add a function that analyzes the content of interviewer's answers and evaluates the specificity of the answers. For example, if the interviewer answers using specific examples or data, that specificity will be reflected in the evaluation. The evaluation department can also set criteria for evaluating the specificity of answers. For example, the evaluation will be based on the number of specific examples and the level of detail. In this way, by reflecting the specificity of the interviewer in the evaluation, it will be easier to find personnel with high practical skills.

[0099] The evaluation department can add a function to analyze the content of the interviewer's answers and evaluate the logic of the answers. For example, if the interviewer answers with a logical structure, that logic can be reflected in the evaluation. The evaluation department can also set criteria for evaluating the logic of answers. For example, the evaluation can be based on the logical structure and clarity of causal relationships. In this way, by reflecting the interviewer's logic in the evaluation, it becomes easier to find people with strong logical thinking skills.

[0100] The evaluation department can add a function that analyzes the content of interviewees' answers and evaluates the adaptability of the answers. For example, it can evaluate whether the interviewee can flexibly respond to different situations and challenges. The evaluation department can also set criteria for evaluating the adaptability of answers. For example, it can evaluate based on the flexibility and adaptability of answers to different scenarios. This makes it easier to find people who are resilient to change by reflecting the adaptability of the interviewee in the evaluation.

[0101] The evaluation unit can estimate the emotions of the interviewer's answers and reflect the emotional intensity in the evaluation. For example, if the interviewer is speaking passionately, the emotional intensity can be reflected in the evaluation as "Passion (Intensity: 8)." The evaluation unit can also set criteria for reflecting emotional intensity in the evaluation. For example, the evaluation can be based on the strength and type of emotion. This allows the emotional intensity of the interviewer to be reflected in the evaluation, making it possible to make a more comprehensive evaluation.

[0102] The evaluation unit can analyze the content of the interviewer's answers and use the emotion estimation function to display the interviewer's emotional state in real time. For example, if the interviewer is nervous, the emotional state is displayed as "nervous" in real time. The evaluation unit can also provide an interface that displays the interviewer's emotional state in real time. For example, it allows the interviewer to check the interviewer's emotional state on the screen in real time. This allows the interviewer to take appropriate action on the spot by displaying the interviewer's emotional state in real time.

[0103] The evaluation unit can analyze the interviewer's answers and use the emotion estimation function to collect the interviewer's emotional reactions and reflect them in the evaluation. For example, if the interviewer is surprised, the emotional reaction is recorded as "surprise." The evaluation unit can also set criteria for reflecting the interviewer's emotional reactions in the evaluation. For example, the evaluation can be based on the type and intensity of emotion. This allows the interviewer's emotional reactions to be reflected in the evaluation, making it possible to make a more comprehensive evaluation.

[0104] The evaluation unit can analyze the content of the interviewer's answers and use the emotion estimation function to collect the interviewer's emotional reactions and reflect them in the evaluation. For example, if the interviewer is surprised by the interviewer's answers, the emotional reaction can be recorded as "surprise." The evaluation unit can also set criteria for reflecting the interviewer's emotional reactions in the evaluation. For example, the evaluation can be based on the type and intensity of emotion. This allows the interviewer's emotional reactions to be reflected in the evaluation, making it possible to make a more comprehensive evaluation.

[0105] The evaluation unit analyzes the interviewer's responses and uses the emotion estimation function to visualize the interviewer's emotional state and reflect it in the evaluation. For example, if the interviewer is nervous, the emotional state is displayed as "tension" in a graph or chart. The evaluation unit can also set criteria for visualizing the interviewer's emotional state. For example, visualization is performed based on the strength or type of emotion. This allows the interviewer's emotional state to be visualized and reflected in the evaluation, making it possible to make a more comprehensive evaluation.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The transcription department converts the interview audio data into text data. For example, the interview audio data is input into the generation AI, which then transcribes it using speech recognition technology. The transcription department can also transcribe audio data in real time. For example, the interview audio data is input into the generation AI in real time, which then transcribes it instantly. Step 2: The evaluation department evaluates the text data converted by the transcription department based on the company's evaluation criteria. For example, the generation AI analyzes the text data and assigns scores to evaluation items such as "action," "leadership," and "problem-solving ability." The evaluation department can also estimate the emotions expressed by the interviewer's answers and reflect the emotional intensity in the evaluation. For example, the generation AI uses an emotion estimation algorithm to analyze the interviewer's emotional state and reflect that intensity in the evaluation. Step 3: The attention shifting unit directs the interviewer's attention to non-verbal elements based on the evaluation by the evaluation unit. For example, it analyzes the interviewer's facial expressions and gestures and provides feedback to the interviewer. The attention shifting unit can also automatically highlight points that the interviewer should pay attention to, supporting the progress of the interview. For example, if the interviewer is talking about an important point, it will highlight that part.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 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.

[0113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] 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.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] 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.

[0120] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0121] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 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.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] 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.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] 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.

[0134] 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.

[0135] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] 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.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0149] 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.

[0150] 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.

[0151] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0152] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0158] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0159] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0160] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0161] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0162] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0163] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0164] 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.

[0165] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0166] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0167] 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.

[0168] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0169] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0170] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0171] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0172] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0173] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0174] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0175] 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 transcription department that converts the interview audio data into text data; an evaluation unit that evaluates the text data converted by the transcription unit based on its own company's evaluation standards; A system comprising: an attention shifting unit that directs the interviewer to focus on non-verbal elements based on the evaluation by the evaluation unit.

2. The transcription unit The system according to claim 1, wherein when transcribing an interview, the system automatically translates the interview into the different languages, making the interview available to multinational companies.

3. The evaluation unit 2. The system according to claim 1, wherein an emotion estimation is performed on the content of the interviewer's answers, and the emotional intensity is reflected in the evaluation.

4. The attention shifting unit The system according to claim 1, characterized in that a system is developed that analyzes the non-verbal elements that the interviewer should pay attention to in real time and provides feedback to the interviewer.

5. The transcription unit 2. The system according to claim 1, wherein emotion estimation is performed from audio data of an interview, and the emotional state of the interviewer is added to the text data.

Images