System

Abstract

A system is provided.SOLUTION: A system comprising: generation and AI means for interacting with a candidate; presenting means for presenting a question generated by the generation and AI means to the candidate; collecting means for collecting answers from the candidate; evaluating means for evaluating the answers collected by the collecting means; recording means for storing a result of the evaluation by the evaluating means; and recommending means for recommending an optimum second interviewer or place to the candidate.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional interview processes rely on the subjective judgment of interviewers, resulting in a lack of consistency and fairness in evaluation. Furthermore, interviews require a lot of time and human resources, making it difficult to identify the right candidates among a large number of candidates. The present invention aims to solve these problems and provide a means for realizing an efficient and fair hiring process. [Means for solving the problem]

[0005] This invention provides a system that includes a generation AI means for engaging in dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to candidates, and a collection means for collecting candidate response data. Furthermore, by providing an evaluation means for evaluating the collected response data and a recording means for accumulating the evaluation results, the system streamlines the interview process and achieves fair evaluation. Furthermore, by providing a recommendation means for recommending the most appropriate second interviewer and assignment based on the results, the system enables appropriate personnel placement.

[0006] A "generative AI means" is an artificial intelligence program that interacts with candidates and generates questions.

[0007] "Presentation Means" means an interface or device for presenting questions generated by the Generating AI Means to a candidate.

[0008] "Collection means" refers to a program or device for collecting candidate response data.

[0009] The "evaluation means" is a program for analyzing the response data collected by the collection means and evaluating the characteristics and skills of the candidates.

[0010] The "recording means" is a system for storing the evaluation results obtained by the evaluation means in a database.

[0011] A "recommendation tool" is a program or algorithm that recommends the most appropriate second interviewer or placement based on the evaluation results.

[0012] "Candidate" refers to an individual participating in the interview process.

[0013] "Response data" refers to information such as audio, text, or video provided by a candidate in response to a question. [Brief explanation of the drawings]

[0014] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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, a 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), and an APU (Accelerated Processing Unit).

[0018] 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.

[0019] 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.

[0020] 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), Bluetooth (registered trademark), etc.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] 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.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. The following describes an embodiment of the present invention.

[0036] System Configuration

[0037] 1. Generation AI means

[0038] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[0039] 2. Presentation means

[0040] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[0041] 3. Collection Method

[0042] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[0043] 4. Evaluation Methods

[0044] The server uses a generative AI model to analyze the collected response data, including speech recognition, sentiment analysis, and content analysis, to assess the candidate's thinking style, personality, and skill level.

[0045] 5. Recording Method

[0046] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be useful for future recruitment strategies and human resource management.

[0047] 6. Recommendations

[0048] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[0049] Specific examples

[0050] 1. The user starts the interview

[0051] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0052] 2. Generative AI presents questions

[0053] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[0054] 3. Users respond

[0055] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0056] 4. The server parses the answer

[0057] The server uses a generative AI model to analyze this voice data, which performs speech recognition and emotion analysis to assess the user's thinking style and personality.

[0058] 5. The server records the evaluation results

[0059] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[0060] 6. The server recommends candidates for second interviews and placements

[0061] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[0062] As described above, the embodiment of the present invention improves the efficiency and fairness of the conventional interview process, and realizes the selection and placement of appropriate personnel.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The user accesses a device (PC, smartphone, tablet) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[0066] Step 2:

[0067] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[0068] Step 3:

[0069] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[0070] Step 4:

[0071] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[0072] Step 5:

[0073] The server passes the received response data to the generative AI model and begins analysis. The analysis includes speech recognition, sentiment analysis, and content analysis. The generative AI model converts the user's response into text and analyzes the nuances of emotion and expression. Based on the analysis results, the user's thinking style, personality traits, and skill level are evaluated.

[0074] Step 6:

[0075] The server records the evaluation results provided by the generative AI model in a database, which can then be used for later re-evaluation and comparison with other candidates.

[0076] Step 7:

[0077] The server generates additional questions based on the initial evaluation results. A generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[0078] Step 8:

[0079] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 6 are then repeated.

[0080] Step 9:

[0081] The server aggregates all the evaluation data to create a comprehensive evaluation for the user. A generative AI model performs the integrated evaluation and generates a consistent final evaluation report.

[0082] Step 10:

[0083] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[0084] This is the specific process flow of the IntelliInterview System. This system utilizes generative AI to achieve an efficient and fair interview process.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] In today's interview process, it is difficult to fully evaluate a candidate's thinking style, personality, and the content of their responses. Furthermore, because the evaluation relies heavily on human subjectivity, there are issues with fairness and efficiency. Furthermore, it takes a lot of time and effort to identify the appropriate second interviewer and the candidate's assignment. There is a need for a method to solve these issues and realize an efficient and fair interview process.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting candidate response data in the form of audio, text, or video, an evaluation means for analyzing the response data collected by the collection means, a recording means for recording the results of the evaluation by the evaluation means in a database, a recommendation means for recommending the most suitable second interviewer or assignment for the candidate based on the evaluation results, an authentication means for starting an interactive session with an authenticated user, and a notification means for notifying an administrator of the analysis results. This makes it possible to objectively and efficiently evaluate the thinking style and personality of candidates and accurately suggest the most suitable interviewer and assignment.

[0090] A "generative AI means" is a means for generating questions for candidates using a generative AI model.

[0091] "Presentation Means" means a means by which questions generated by the Generative AI Means are presented to the Candidate in audio, text, or video format.

[0092] "Collection means" refers to a means for collecting candidate response data in audio, text, or video format, converting it into an appropriate format, and transmitting it to a server.

[0093] The "evaluation means" is a means for analyzing the response data collected by the collection means and evaluating the thinking style and personality traits of the candidate by performing voice recognition, emotion analysis, and content analysis.

[0094] The "recording means" is a means for recording the results of evaluation by the evaluation means in a database.

[0095] The "recommendation means" is a means for recommending the most suitable second interviewer or assignment for a candidate based on the evaluation results recorded by the recording means.

[0096] An "authentication means" is a means by which a user logs into a dedicated web or mobile app and confirms authentication information to initiate an interactive session with an authenticated user.

[0097] The "notification means" is a means for notifying the administrator of the analysis results and recommendation results.

[0098] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. Specific embodiments for implementing the present invention are described below.

[0099] The server runs a generative AI method to generate questions for the candidate. This generative AI method uses GPT-4 or an equivalent language model. The generated questions are designed to assess the candidate's thinking style and personality. For example, the generative AI may generate a question such as, "What is the most difficult project you have ever worked on?"

[0100] The generated questions are sent from the server to the terminal, which then presents them to the candidate. The questions can be presented in voice, text, or video format, allowing the candidate to choose the appropriate input method. Specifically, the terminal displays the questions using a web application using HTML5, CSS, and JavaScript.

[0101] Once the candidate enters their answers, the device collects the answer data, which is then sent to a server in an appropriate format, such as MP3 format, using a microphone and a framework such as React Native.

[0102] The server analyzes the collected response data using a generative AI model. This analysis includes speech recognition, sentiment analysis, and content analysis. Google Speech-to-Text API is used for speech recognition, and IBM Watson Tone Analyzer is used for sentiment analysis. This allows the candidate's thinking style, personality, and skill level to be evaluated.

[0103] The evaluation results are recorded in a database by the server using MySQL or PostgreSQL. This data can be used for future re-evaluations and comparisons with other candidates.

[0104] Based on the evaluation results, the server recommends the most suitable second interviewer and assignment for the candidate. For example, it may recommend assignment to the technical department leader or project management department. These recommendations are notified to the system administrator, who then uses the information to select the second interviewer and make appropriate assignment decisions.

[0105] Specific examples are shown below.

[0106] The user (candidate) starts the interview by logging in to a dedicated web app or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0107] The terminal presents the question received from the server to the user, for example, "What is the most difficult project you have ever undertaken?"

[0108] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0109] The server analyzes the voice data using a generative AI model, which provides results of speech recognition and sentiment analysis to assess the user's thinking style and personality.

[0110] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[0111] Based on the evaluation results, the server recommends that the employee be assigned to a technical department leader or project management department, and the recommendation is notified to the system administrator.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Divide the processing flow of this system's program into processing steps

[0114] Step 1: User authentication

[0115] Step 2: Question generation

[0116] Step 3: Question posing

[0117] Step 4: Collect responses

[0118] Step 5: Response analysis

[0119] Step 6: Evaluation Record

[0120] Step 7: Notification of recommended results

[0121] Explain each processing step in detail

[0122] Step 1: User authentication

[0123] The server authenticates users who access the server using a dedicated web app or mobile app. The user enters their username and password on the login screen. The server checks the information against the database, and if authentication is successful, it generates a session ID and returns it to the user. The input is user information, and the output is the authentication result and session ID. If authentication is successful, an interactive session begins.

[0124] Specific actions

[0125] 1. The user accesses the login screen and enters their username and password.

[0126] 2. The server checks the credentials against a database.

[0127] 3. If authentication is successful, the server generates a session ID and returns it to the user.

[0128] Step 2: Question generation

[0129] The server uses a generative AI model (e.g., GPT-4) to generate questions for the user, which are designed to assess the candidate's thinking style and personality. The input is the session ID, and the output is the generated questions.

[0130] Specific actions

[0131] 1. The server receives the session ID and runs the generative AI model.

[0132] 2. A generative AI model generates questions such as, "What is the most challenging project you have ever worked on?"

[0133] 3. A question is generated and stored on the server.

[0134] Step 3: Question posing

[0135] The generated question is sent from the server to the terminal, which then presents it to the user. The presentation can be in the form of voice, text, or video, and the user can choose the preferred input method. The input is the generated question, and the output is the presented question.

[0136] Specific actions

[0137] 1. The server sends the generated question to the terminal.

[0138] 2. The terminal presents the received question to the user (e.g., by displaying a text message).

[0139] 3. The user chooses the best input method (voice, text, or video).

[0140] Step 4: Collect responses

[0141] The user inputs answers to questions. The device collects the answer data and, in the case of voice input, converts it into an appropriate audio format (e.g., MP3) and sends it to the server. The input is the user's answer data, and the output is the collected answer data.

[0142] Specific actions

[0143] 1. The user speaks their response (e.g., "I worked on a large system migration project last year").

[0144] 2. The device collects the audio data and converts it into the appropriate format.

[0145] 3. The collected data is sent to the server.

[0146] Step 5: Response analysis

[0147] The server analyzes the collected response data using a generative AI model. The analysis includes speech recognition, sentiment analysis, and content analysis. The input is the collected response data, and the output is the analysis results.

[0148] Specific actions

[0149] 1. The server receives the collected response data and begins analysis using the generative AI model.

[0150] 2. Speech recognition (e.g., Google Speech-to-Text API) is performed.

[0151] 3. Sentiment analysis (e.g. IBM Watson Tone Analyzer) is performed and content analysis is carried out.

[0152] 4. The analysis results are obtained and the candidate's thinking style and personality are evaluated.

[0153] Step 6: Evaluation Record

[0154] The server records the analysis results in a database. The input is the analysis results, and the output is the evaluation data recorded in the database.

[0155] Specific actions

[0156] 1. The server receives the analysis results and accesses the database.

[0157] 2. The evaluation results are recorded in a database (e.g., MySQL, PostgreSQL).

[0158] 3. Confirmation of completion of recording will be made.

[0159] Step 7: Notification of recommended results

[0160] The server recommends the most suitable second interviewer and placement for the candidate based on the evaluation results. The recommended results are notified to the administrator. The input is the evaluation results, and the output is a notification of the recommended results.

[0161] Specific actions

[0162] 1. The server analyzes the evaluation results and determines the appropriate second interviewer and placement.

[0163] 2. Recommendations are generated and notified to the administrator.

[0164] 3. Administrators are notified and take necessary action.

[0165] The specific processing contents and operations of each step have been described above.

[0166] (Application example 1)

[0167] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0168] Conventional interview systems require a lot of time and effort when evaluating candidates, and can lack fairness. It is also difficult to accurately evaluate a candidate's characteristics and skills and determine the most appropriate position for the candidate. The present invention aims to solve these problems and provide a system for realizing an efficient and fair interview process.

[0169] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0170] In this invention, the server includes a recognition means for recognizing candidates, a generation AI means, a presentation means for presenting questions generated by the generation AI means, a voice collection means for collecting voice responses, a voice recognition means for converting the collected voice data into text, an evaluation means for evaluating the response data, an analysis means for performing sentiment analysis and text classification from the voice data, a data recording means for recording the evaluation results in an appropriate database, and a recommendation means for recommending the most suitable second interviewer or assignment for the candidate. This makes it possible to quickly and accurately evaluate the characteristics and skills of candidates and automatically recommend the most suitable assignment.

[0171] A "generative AI means" is an artificial intelligence means that automatically generates questions to engage in dialogue with candidates.

[0172] "Presentation means" refers to the means by which the generated questions are presented to the candidate, and may be in the form of audio, text, or video.

[0173] "Collection means" refers to the means used to collect candidate response data.

[0174] "Evaluation means" refers to means for evaluating collected response data, including sentiment analysis and content analysis.

[0175] The "recording means" is a means for accumulating the evaluation results, and records the evaluation results in a database.

[0176] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[0177] "Recognition means" refers to a means for recognizing candidates, such as by facial recognition, to identify candidates.

[0178] "Audio collection means" refers to a means for collecting candidates' audio responses to questions posed.

[0179] "Speech recognition means" refers to means for converting collected voice data into text.

[0180] "Analysis means" refers to means for performing sentiment analysis and text classification from audio data.

[0181] "Data recording means" means for recording the results of the evaluation in an appropriate database.

[0182] System Overview

[0183] This invention applies an interview system using generative AI to the recruitment of factory robots. This system includes a recognition means, a generative AI means, a presentation means, a voice collection means, a voice recognition means, an evaluation means, an analysis means, a data recording means, and a recommendation means. The specific implementation methods for each means, as well as the hardware and software required for them, are described below.

[0184] recognition means

[0185] The server uses a head-mounted display (HMD) with a built-in camera to recognize the candidate's face. For facial recognition, it uses the OpenCV library and the "haarcascade_frontalface_default.xml" model. This recognition method allows the candidate to automatically complete the login process.

[0186] Generation AI means

[0187] The server automatically generates questions to engage in dialogue with candidates using a generative AI model (e.g., GPT-3). The following is a concrete example of a prompt sentence for generating questions:

[0188] "To understand your role and responsibilities here, please tell us about a challenging project you have undertaken that has been relevant to your work."

[0189] Presentation means

[0190] The generated questions are presented to the candidate via the HMD in the form of audio, text, or video. The presentation means can present the questions in an appropriate manner depending on the candidate's selection.

[0191] Audio collection method

[0192] The candidate's voice responses are collected through the HMD's microphone, and the collected voice data is sent to the server in real time.

[0193] Voice recognition means

[0194] The server uses the Google Speech Recognition API to convert the voice data into text, which quickly transcribes the candidate's answers.

[0195] Evaluation and analysis tools

[0196] The server evaluates the textual responses and performs sentiment analysis and text classification using the "transformers" library. For example, sentiment analysis and text classification are performed for:

[0197] Emotion result: {"label": "POSITIVE", "score": 0.98}

[0198] Content result: {"label": "MANAGEMENT_SKILL", "score": 0.87}

[0199] Data Recording Means

[0200] The server records the results of the evaluation in an appropriate database. We use an SQLite database to store the results so that they can be used for later re-evaluation.

[0201] Recommendations

[0202] Based on the evaluation results, the server recommends the best second interviewer or placement for the candidate. For example, a notification recommending placement in a specific department at a factory may be sent to the manager.

[0203] These tools enable the present invention to quickly and accurately assess a candidate's characteristics and skills and automatically recommend the most suitable placement.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1:

[0206] The server performs facial recognition of the candidate. It uses the camera built into the HMD and the "haarcascade_frontalface_default.xml" model from the OpenCV library. The input is video data from the camera, and the output is the candidate's identification information. Specifically, the video data is processed in real time, and the facial features are compared with the database to complete the candidate's login.

[0207] Step 2:

[0208] The server generates questions using a generative AI model. The input is a prompt, an example of which is, "To understand your role and responsibilities here, please tell me about a challenging project in your related work." The output is a question to be presented to the candidate. Specifically, the generative AI (e.g., GPT-3) generates an appropriate question based on the prompt and outputs it in text format.

[0209] Step 3:

[0210] The device presents the generated questions to the candidate. The candidate can choose the presentation method from audio, text, or video format. The input is the generated question, and the output is the question presented to the candidate. Specifically, the HMD's display and speaker are used to present the question in the format selected by the candidate.

[0211] Step 4:

[0212] The user answers the questions by voice. The device collects the candidate's voice responses through the microphone built into the HMD. The input is the candidate's voice data, and the output is the collected voice file. Specifically, the microphone collects the voice and transmits it to the server in real time as digital voice data.

[0213] Step 5:

[0214] The server uses the Google Speech Recognition API to convert the voice data into text. The input is the collected voice data, and the output is the converted text data. Specifically, the API analyzes the voice data and converts the voice into text.

[0215] Step 6:

[0216] The server performs sentiment analysis and text classification using the "transformers" library to analyze text data. The input is the transformed text data, and the output is the sentiment analysis results and content classification results. Specifically, it extracts emotions and nuances from the text data and generates classification results.

[0217] Step 7:

[0218] The server records the analysis results in a database. The input is the sentiment analysis results and content classification results, and the output is the evaluation data stored in the database. Specifically, the evaluation data is stored in an SQLite database so that it can be used later for re-evaluation and comparison with other candidates.

[0219] Step 8:

[0220] The server recommends the most suitable second interviewer or assignment for the candidate based on the recorded evaluation data. The input is the recorded evaluation data, and the output is the recommendation result. Specifically, the server analyzes the evaluation data and automatically recommends the most appropriate assignment for the candidate (for example, a specific department in a factory). The recommendation result is notified to the administrator.

[0221] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0222] The present invention relates to an interview system called "IntelliInterview" that uses generative AI, and in particular, it combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. The following describes an embodiment of the present invention.

[0223] System Configuration

[0224] 1. Generation AI means

[0225] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[0226] 2. Presentation means

[0227] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[0228] 3. Emotion Engine

[0229] The server is equipped with an emotion engine for analyzing the user's response data. The emotion engine analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[0230] 4. Collection Method

[0231] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[0232] 5. Evaluation Methods

[0233] The server analyzes the collected response data using a generative AI model and an emotion engine. The emotion engine recognizes the user's emotions, and the generative AI model analyzes those emotions and the content of the responses to evaluate the user's thinking style, personality traits, and skill level.

[0234] 6. Recording Method

[0235] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be used for future recruitment strategies and human resource management.

[0236] 7. Recommendations

[0237] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[0238] Specific examples

[0239] 1. The user starts the interview

[0240] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0241] 2. Generative AI presents questions

[0242] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[0243] 3. Users respond

[0244] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0245] 4. The emotion engine analyzes the user's responses

[0246] The server analyzes the received voice data using an emotion engine, which analyzes the emotional tone in the voice and determines the emotional state of the user.

[0247] 5. Generative AI analyzes the answers

[0248] The server uses a generative AI model to analyze this voice data. This analysis involves voice recognition and content analysis, and evaluates the user's thinking style and personality. By taking into account the results of the emotion engine, a more accurate evaluation is possible.

[0249] 6. The server records the evaluation results

[0250] The evaluation results generated by the generative AI model and emotion engine are recorded in a database by the server, and this data can be used later for re-evaluation and comparison with other candidates.

[0251] 7. The server recommends candidates for second interviews and placements

[0252] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[0253] As described above, the embodiments of the present invention improve the efficiency and fairness of the conventional interview process, and realize the selection and placement of appropriate personnel. The introduction of the emotion engine provides deeper insights and makes it possible to understand the true characteristics of candidates.

[0254] The processing flow will be explained below.

[0255] Step 1:

[0256] The user accesses a device (PC, smartphone, tablet, etc.) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[0257] Step 2:

[0258] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[0259] Step 3:

[0260] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[0261] Step 4:

[0262] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[0263] Step 5:

[0264] The server passes the received response data to the generative AI model and emotion engine, which then analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[0265] Step 6:

[0266] The generative AI model takes into account the user's emotional state and analyzes the content of the voice and text data, which then assesses the user's thinking style, personality traits, and skill level.

[0267] Step 7:

[0268] The server records the evaluation results provided by the generative AI model and emotion engine in a database, which can then be used for later re-evaluation and comparison with other candidates.

[0269] Step 8:

[0270] The server generates additional questions based on the initial evaluation results. The generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[0271] Step 9:

[0272] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 7 are then repeated.

[0273] Step 10:

[0274] The server integrates all the evaluation data to create a comprehensive evaluation for the user. The generative AI model and emotion engine then perform the integrated evaluation to generate a consistent final evaluation report.

[0275] Step 11:

[0276] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[0277] The above is the specific processing flow of the intelligent interview system combined with an emotion engine. This system utilizes generative AI and an emotion engine to achieve detailed evaluation of candidates, including their emotional state, providing a fairer and more efficient interview process.

[0278] Example 2

[0279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0280] Conventional interview systems have difficulty taking into account emotional states and nuances of expression when evaluating candidates' thinking styles and personality traits. Furthermore, evaluations by human interviewers are prone to bias and risk lacking fairness. This makes it difficult to select and assign the right talent, impacting companies' recruitment strategies and human resource management.

[0281] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, and a collection means for collecting answer data from the candidates. This makes it possible to analyze the emotional state of the candidates and evaluate their thinking style and personality traits.

[0282] A "generative AI means" is a means that uses an AI model to generate questions to interact with a candidate.

[0283] The "presentation means" is a means for presenting the questions generated by the generation AI means to the candidate.

[0284] "Collection means" refers to the means used to collect candidate response data.

[0285] The "evaluation means" is a means for evaluating the response data collected by the collection means.

[0286] The "recording means" is a means for storing the results of evaluation by the evaluation means.

[0287] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[0288] "Emotion analysis means" is a means for analyzing the emotional state of a candidate.

[0289] The present invention relates to "IntelliInterview," an interview system that uses generative AI, and in particular, is a system that combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. An embodiment of the present invention is described in detail below.

[0290] Server Roles

[0291] The server is a key component of the present invention. The server executes a generative AI means to generate questions for dialogue with candidates. For example, the generative AI means uses GPT-4, a natural language generation model. The following prompt sentences are used to generate questions:

[0292] "Generate creative questions for candidates."

[0293] "Generate questions that ask candidates about difficult situations they've experienced in the past."

[0294] The questions generated by the generation AI means are sent to the terminal by the server. The server then analyzes the candidate's answer data using the emotion analysis means. This emotion analysis means analyzes the candidate's emotional state (e.g., joy, sadness, fear, anger, etc.) from the voice data and text data. For example, the emotion analysis tool of Azure Cognitive Services is used for emotion analysis.

[0295] The server integrates the analytical data obtained from the emotion analysis means and the generation AI means to generate a final evaluation result. The evaluation results are recorded in a database, allowing for future re-evaluation and comparison with other candidates. The server also recommends the most appropriate second interviewer and assignment based on the evaluation results.

[0296] Device Role

[0297] The terminal acts as an interface with the user. It presents the questions received from the server to the user. The presentation method can be text, audio, or video, and the user can choose according to their preference. For example, the generated question "What is the most difficult project you have ever worked on?" is presented to the user.

[0298] When the user enters an answer, the device collects the answer data, converts it into an appropriate data format, and sends it to the server. For example, if the answer is a voice response, the device converts the voice data into WAV or MP3 format and sends it.

[0299] User Roles

[0300] The user starts the interview by logging in to a dedicated web app or mobile app. First, the user enters their ID and password, and is authenticated by the server. If authentication is successful, the user receives questions from the server via their device.

[0301] Users enter answers to questions and send them to the server via their devices. This allows the system to collect data to evaluate the user's thinking style and personality traits. For example, a user might enter an answer like, "I was in charge of a project to introduce a new system last year..."

[0302] As described above, the interview system of the present invention combines generative AI and an emotion analysis engine to evaluate candidate aptitude with high accuracy and recommend optimal placement and second interviewers, thereby improving the efficiency and fairness of the conventional interview process.

[0303] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0304] Step 1:

[0305] The server executes the generative AI means to generate questions. The server passes a prompt (e.g., "Please generate a question to test the candidate's creativity") as input to a generative AI model (e.g., GPT-4). The generative AI model generates a question based on the prompt and outputs the question to the server.

[0306] Step 2:

[0307] The server sends the generated question to the terminal. The server converts the question, which is the output from the generation AI means, into a data format (e.g., text data) and sends it to the terminal. The terminal receives this question and proceeds to the next step.

[0308] Step 3:

[0309] The terminal presents the question to the user. The terminal outputs the question received from the server to the user in voice, text, or video format. For example, the terminal presents the question such as "What is the most difficult project you have ever undertaken?" to the user in voice format.

[0310] Step 4:

[0311] The user answers the question. The user responds to the question by voice, text, or video. For example, the user might say, "The biggest challenge I've ever faced was implementing a new system..."

[0312] Step 5:

[0313] The device collects the answer data and sends it to the server. The device converts the answer data entered by the user into an appropriate format (e.g., voice data into WAV format). After conversion, the device sends this data to the server.

[0314] Step 6:

[0315] The server analyzes the received response data using the emotion analysis means. The server passes input data (e.g., voice data) from the terminal to the emotion analysis means, which analyzes the emotional state (e.g., joy, sadness, fear, anger, etc.). The emotion analysis means outputs the analysis results to the server.

[0316] Step 7:

[0317] The server analyzes the responses using the generation AI. The server passes the output from the emotion analysis means (e.g., emotional state) and input data from the device (e.g., voice data) to the generation AI model. The generation AI model performs text analysis and evaluates the user's thinking style and personality traits from the responses. The evaluation results are output to the server.

[0318] Step 8:

[0319] The server records the evaluation results. The server combines the output data from the generative AI model and the sentiment analysis method to create evaluation data. This evaluation data is recorded in a database, allowing for future re-evaluation and comparison with other candidates.

[0320] Step 9:

[0321] The server notifies the recommended results. Based on the evaluation data, the server recommends the most suitable second interviewer and assignment. For example, it may recommend assignment to the technical department leader or project management department. The recommended results are notified to the manager.

[0322] (Application example 2)

[0323] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0324] Conventional self-driving vehicles lack a system that can evaluate the driver's emotional state and thinking style in real time and provide appropriate advice. As a result, driver fatigue and stress cannot be managed appropriately, resulting in problems with safety and comfort.

[0325] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0326] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting answer data from the candidates, an evaluation means for evaluating the answer data collected by the collection means, a recording means for accumulating the results of the evaluation by the evaluation means, a recommendation means for recommending a second interviewer or assignment that is optimal for the candidate, and a means for evaluating the emotions and thinking style of the driver of an autonomous vehicle in real time and providing appropriate advice. This makes it possible to evaluate the emotions and thinking style of the driver in real time and provide appropriate advice.

[0327] A "generative AI means" is an artificial intelligence system that generates questions and advice to engage in dialogue with a candidate (or driver).

[0328] The "presentation means" is a device that displays or audibly presents the questions or advice generated by the generation AI means to the candidate (or driver).

[0329] "Collection means" refers to a device or system for acquiring and storing candidate (or driver) response data.

[0330] The "evaluation means" refers to an algorithm or program for analyzing and evaluating the response data collected by the collection means.

[0331] A "recording means" is a device or system that stores the evaluated results in a database for later re-evaluation and comparison.

[0332] The "recommendation means" is a device or system for providing the candidate with the most suitable second interviewer or assignment, or appropriate advice for the driver, based on the evaluation results.

[0333] An "autonomous vehicle" is a vehicle that is equipped with the capability to drive autonomously with minimal driver intervention.

[0334] "Real-time assessment of emotions and thinking styles" refers to the process of instantly analyzing the driver's emotional state and thinking characteristics and making an assessment based on the current situation.

[0335] "Providing appropriate advice" means making the best suggestions to maintain a safe and comfortable driving environment based on the driver's emotions and thinking style.

[0336] This invention relates to a system that evaluates the driver's emotions and thinking style in real time and provides appropriate advice in autonomous vehicles. This system integrates a generative AI model and an emotion engine, aiming to improve safety and comfort.

[0337] System Configuration

[0338] 1. Generation AI means

[0339] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The generated questions are designed to assess the driver's emotions and thinking style.

[0340] 2. Presentation means

[0341] The device receives questions and advice from the server and presents them to the driver via the in-car display and voice system. For example, the device may ask, "How do you feel while driving?"

[0342] 3. Collection Method

[0343] The device collects the driver's voice responses via a microphone, converts them into an appropriate voice format, and sends them to a server. It also uses a camera to capture the driver's facial expressions for sentiment analysis.

[0344] 4. Evaluation Methods

[0345] The server analyzes the collected audio and video data using an emotion engine, which determines the driver's emotional state, and the generative AI model evaluates the driver's thinking style based on the responses and facial expressions.

[0346] 5. Recording Method

[0347] The evaluation results are stored in a database by the server and can be used later for re-evaluation, comparison with other drivers, and analysis of driving habits.

[0348] 6. Recommendations

[0349] The server then provides appropriate advice to the driver based on the evaluation results. For example, if the driver responds, "I'm a little tired," the system will suggest, "The next rest point is 5km away. Would you like to take a break?"

[0350] Hardware or software used

[0351] Hardware:

[0352] Microphone: Used to collect driver voice input.

[0353] Camera: Used to analyze the driver's facial expressions.

[0354] Display or audio system: Used to present questions and advice.

[0355] software:

[0356] SpeechRecognition: Used to convert speech to text.

[0357] OpenCV: Used to process camera footage.

[0358] Transformers (Hugging Face): Used for sentiment analysis using the BERT model.

[0359] Specific examples

[0360] Example prompt sentence:

[0361] The question posed is, "How do you feel about your recent work progress?"

[0362] If the driver answers, "I'm under pressure and a little tired," the system analyzes their emotions in real time and provides advice such as, "It's important to take enough rest. I recommend you take a coffee break in five minutes."

[0363] In this way, a system that combines a generative AI model and an emotion engine can evaluate the driver's state in real time in an autonomous vehicle and provide appropriate advice, thereby reducing driver fatigue and stress and improving safety.

[0364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0365] Step 1:

[0366] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The input is the driver's previous data and existing data in the system, and the output is the generated questions and advice. Based on the generated questions, the server creates prompt sentences to ask the driver.

[0367] Step 2:

[0368] The terminal presents the driver with questions and advice received from the server. The input is what the server produces, and the output is what the driver sees or hears on the display or audio system. For example, the question "How do you feel while driving?" is displayed on the display.

[0369] Step 3:

[0370] The user (driver) answers the presented questions by voice. The input is the question presented by the terminal, and the output is the driver's voice response. Drivers often respond by saying, "I'm a little tired today."

[0371] Step 4:

[0372] The terminal collects the driver's voice response through a microphone and converts it into an appropriate voice format. The input is the driver's voice data, and the output is the data converted into voice format. This voice data is then sent to the server.

[0373] Step 5:

[0374] The device uses a camera to capture the driver's facial expressions and collects the data in real time. The input is the camera image, and the output is facial expression data. This data is also sent to the server.

[0375] Step 6:

[0376] The server uses an emotion engine to analyze the collected audio and video data. The input is audio data and facial expression data, and the output is an analysis result that indicates the driver's emotional state. Specifically, it determines whether the driver feels "a little tired" by analyzing the tone of the voice and recognizing facial expressions.

[0377] Step 7:

[0378] The server uses a generative AI model to evaluate the driver's responses and emotional state. The input is the voice transcript and emotion analysis results, and the output is an assessment of the driver's thinking style and personality traits. For example, the driver may be assessed as "stressed."

[0379] Step 8:

[0380] The server stores the evaluation results in a database. The input is the evaluation results, and the output is the stored data, which can later be used for re-evaluation and comparison with other drivers.

[0381] Step 9:

[0382] Based on the evaluation results, the server generates appropriate advice for the driver and sends it to the terminal. The input is the evaluation result, and the output is the generated advice. For example, a suggestion might be generated: "The next rest point is 5 km away. Would you like to take a break?"

[0383] Step 10:

[0384] The terminal presents the advice received from the server to the driver. The input is the generated advice, and the output is the driver's behavior after receiving the advice. The driver is prompted to decide whether to take a break.

[0385] 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.

[0386] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0387] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0388] [Second embodiment]

[0389] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0390] 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.

[0391] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0392] 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.

[0393] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0394] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0395] 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.

[0396] 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.

[0397] 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 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.

[0398] 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.

[0399] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0400] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0401] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. The following describes an embodiment of the present invention.

[0402] System Configuration

[0403] 1. Generation AI means

[0404] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[0405] 2. Presentation means

[0406] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[0407] 3. Collection Method

[0408] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[0409] 4. Evaluation Methods

[0410] The server uses a generative AI model to analyze the collected response data, including speech recognition, sentiment analysis, and content analysis, to assess the candidate's thinking style, personality, and skill level.

[0411] 5. Recording Method

[0412] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be useful for future recruitment strategies and human resource management.

[0413] 6. Recommendations

[0414] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[0415] Specific examples

[0416] 1. The user starts the interview

[0417] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0418] 2. Generative AI presents questions

[0419] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[0420] 3. Users respond

[0421] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0422] 4. The server parses the answer

[0423] The server uses a generative AI model to analyze this voice data, which performs speech recognition and emotion analysis to assess the user's thinking style and personality.

[0424] 5. The server records the evaluation results

[0425] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[0426] 6. The server recommends candidates for second interviews and placements

[0427] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[0428] As described above, the embodiment of the present invention improves the efficiency and fairness of the conventional interview process, and realizes the selection and placement of appropriate personnel.

[0429] The processing flow will be explained below.

[0430] Step 1:

[0431] The user accesses a device (PC, smartphone, tablet) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[0432] Step 2:

[0433] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[0434] Step 3:

[0435] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[0436] Step 4:

[0437] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[0438] Step 5:

[0439] The server passes the received response data to the generative AI model and begins analysis. The analysis includes speech recognition, sentiment analysis, and content analysis. The generative AI model converts the user's response into text and analyzes the nuances of emotion and expression. Based on the analysis results, the user's thinking style, personality traits, and skill level are evaluated.

[0440] Step 6:

[0441] The server records the evaluation results provided by the generative AI model in a database, which can then be used for later re-evaluation and comparison with other candidates.

[0442] Step 7:

[0443] The server generates additional questions based on the initial evaluation results. A generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[0444] Step 8:

[0445] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 6 are then repeated.

[0446] Step 9:

[0447] The server aggregates all the evaluation data to create a comprehensive evaluation for the user. A generative AI model performs the integrated evaluation and generates a consistent final evaluation report.

[0448] Step 10:

[0449] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[0450] This is the specific process flow of the IntelliInterview System. This system utilizes generative AI to achieve an efficient and fair interview process.

[0451] Example 1

[0452] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0453] In today's interview process, it is difficult to fully evaluate a candidate's thinking style, personality, and the content of their responses. Furthermore, because the evaluation relies heavily on human subjectivity, there are issues with fairness and efficiency. Furthermore, it takes a lot of time and effort to identify the appropriate second interviewer and the candidate's assignment. There is a need for a method to solve these issues and realize an efficient and fair interview process.

[0454] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0455] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting candidate response data in the form of audio, text, or video, an evaluation means for analyzing the response data collected by the collection means, a recording means for recording the results of the evaluation by the evaluation means in a database, a recommendation means for recommending the most suitable second interviewer or assignment for the candidate based on the evaluation results, an authentication means for starting an interactive session with an authenticated user, and a notification means for notifying an administrator of the analysis results. This makes it possible to objectively and efficiently evaluate the thinking style and personality of candidates and accurately suggest the most suitable interviewer and assignment.

[0456] A "generative AI means" is a means for generating questions for candidates using a generative AI model.

[0457] "Presentation Means" means a means by which questions generated by the Generative AI Means are presented to the Candidate in audio, text, or video format.

[0458] "Collection means" refers to a means for collecting candidate response data in audio, text, or video format, converting it into an appropriate format, and transmitting it to a server.

[0459] The "evaluation means" is a means for analyzing the response data collected by the collection means and evaluating the thinking style and personality traits of the candidate by performing voice recognition, emotion analysis, and content analysis.

[0460] The "recording means" is a means for recording the results of evaluation by the evaluation means in a database.

[0461] The "recommendation means" is a means for recommending the most suitable second interviewer or assignment for a candidate based on the evaluation results recorded by the recording means.

[0462] An "authentication means" is a means by which a user logs into a dedicated web or mobile app and confirms authentication information to initiate an interactive session with an authenticated user.

[0463] The "notification means" is a means for notifying the administrator of the analysis results and recommendation results.

[0464] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. Specific embodiments for implementing the present invention are described below.

[0465] The server runs a generative AI method to generate questions for the candidate. This generative AI method uses GPT-4 or an equivalent language model. The generated questions are designed to assess the candidate's thinking style and personality. For example, the generative AI may generate a question such as, "What is the most difficult project you have ever worked on?"

[0466] The generated questions are sent from the server to the terminal, which then presents them to the candidate. The questions can be presented in voice, text, or video format, allowing the candidate to choose the appropriate input method. Specifically, the terminal displays the questions using a web application using HTML5, CSS, and JavaScript.

[0467] Once the candidate enters their answers, the device collects the answer data, which is then sent to a server in an appropriate format, such as MP3 format, using a microphone and a framework such as React Native.

[0468] The server analyzes the collected response data using a generative AI model. This analysis includes speech recognition, sentiment analysis, and content analysis. Google Speech-to-Text API is used for speech recognition, and IBM Watson Tone Analyzer is used for sentiment analysis. This allows the candidate's thinking style, personality, and skill level to be evaluated.

[0469] The evaluation results are recorded in a database by the server using MySQL or PostgreSQL. This data can be used for future re-evaluations and comparisons with other candidates.

[0470] Based on the evaluation results, the server recommends the most suitable second interviewer and assignment for the candidate. For example, it may recommend assignment to the technical department leader or project management department. These recommendations are notified to the system administrator, who then uses the information to select the second interviewer and make appropriate assignment decisions.

[0471] Specific examples are shown below.

[0472] The user (candidate) starts the interview by logging in to a dedicated web app or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0473] The terminal presents the question received from the server to the user, for example, "What is the most difficult project you have ever undertaken?"

[0474] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0475] The server analyzes the voice data using a generative AI model, which provides results of speech recognition and sentiment analysis to assess the user's thinking style and personality.

[0476] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[0477] Based on the evaluation results, the server recommends that the employee be assigned to a technical department leader or project management department, and the recommendation is notified to the system administrator.

[0478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0479] Divide the processing flow of this system's program into processing steps

[0480] Step 1: User authentication

[0481] Step 2: Question generation

[0482] Step 3: Question posing

[0483] Step 4: Collect responses

[0484] Step 5: Response analysis

[0485] Step 6: Evaluation Record

[0486] Step 7: Notification of recommended results

[0487] Explain each processing step in detail

[0488] Step 1: User authentication

[0489] The server authenticates users who access the server using a dedicated web app or mobile app. The user enters their username and password on the login screen. The server checks the information against the database, and if authentication is successful, it generates a session ID and returns it to the user. The input is user information, and the output is the authentication result and session ID. If authentication is successful, an interactive session begins.

[0490] Specific actions

[0491] 1. The user accesses the login screen and enters their username and password.

[0492] 2. The server checks the credentials against a database.

[0493] 3. If authentication is successful, the server generates a session ID and returns it to the user.

[0494] Step 2: Question generation

[0495] The server uses a generative AI model (e.g., GPT-4) to generate questions for the user, which are designed to assess the candidate's thinking style and personality. The input is the session ID, and the output is the generated questions.

[0496] Specific actions

[0497] 1. The server receives the session ID and runs the generative AI model.

[0498] 2. A generative AI model generates questions such as, "What is the most challenging project you have ever worked on?"

[0499] 3. A question is generated and stored on the server.

[0500] Step 3: Question posing

[0501] The generated question is sent from the server to the terminal, which then presents it to the user. The presentation can be in the form of voice, text, or video, and the user can choose the preferred input method. The input is the generated question, and the output is the presented question.

[0502] Specific actions

[0503] 1. The server sends the generated question to the terminal.

[0504] 2. The terminal presents the received question to the user (e.g., by displaying a text message).

[0505] 3. The user chooses the best input method (voice, text, or video).

[0506] Step 4: Collect responses

[0507] The user inputs answers to questions. The device collects the answer data and, in the case of voice input, converts it into an appropriate audio format (e.g., MP3) and sends it to the server. The input is the user's answer data, and the output is the collected answer data.

[0508] Specific actions

[0509] 1. The user speaks their response (e.g., "I worked on a large system migration project last year").

[0510] 2. The device collects the audio data and converts it into the appropriate format.

[0511] 3. The collected data is sent to the server.

[0512] Step 5: Response analysis

[0513] The server analyzes the collected response data using a generative AI model. The analysis includes speech recognition, sentiment analysis, and content analysis. The input is the collected response data, and the output is the analysis results.

[0514] Specific actions

[0515] 1. The server receives the collected response data and begins analysis using the generative AI model.

[0516] 2. Speech recognition (e.g., Google Speech-to-Text API) is performed.

[0517] 3. Sentiment analysis (e.g. IBM Watson Tone Analyzer) is performed and content analysis is carried out.

[0518] 4. The analysis results are obtained and the candidate's thinking style and personality are evaluated.

[0519] Step 6: Evaluation Record

[0520] The server records the analysis results in a database. The input is the analysis results, and the output is the evaluation data recorded in the database.

[0521] Specific actions

[0522] 1. The server receives the analysis results and accesses the database.

[0523] 2. The evaluation results are recorded in a database (e.g., MySQL, PostgreSQL).

[0524] 3. Confirmation of completion of recording will be made.

[0525] Step 7: Notification of recommended results

[0526] The server recommends the most suitable second interviewer and placement for the candidate based on the evaluation results. The recommended results are notified to the administrator. The input is the evaluation results, and the output is a notification of the recommended results.

[0527] Specific actions

[0528] 1. The server analyzes the evaluation results and determines the appropriate second interviewer and placement.

[0529] 2. Recommendations are generated and notified to the administrator.

[0530] 3. Administrators are notified and take necessary action.

[0531] The specific processing contents and operations of each step have been described above.

[0532] (Application example 1)

[0533] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0534] Conventional interview systems require a lot of time and effort when evaluating candidates, and can lack fairness. It is also difficult to accurately evaluate a candidate's characteristics and skills and determine the most appropriate position for the candidate. The present invention aims to solve these problems and provide a system for realizing an efficient and fair interview process.

[0535] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0536] In this invention, the server includes a recognition means for recognizing candidates, a generation AI means, a presentation means for presenting questions generated by the generation AI means, a voice collection means for collecting voice responses, a voice recognition means for converting the collected voice data into text, an evaluation means for evaluating the response data, an analysis means for performing sentiment analysis and text classification from the voice data, a data recording means for recording the evaluation results in an appropriate database, and a recommendation means for recommending the most suitable second interviewer or assignment for the candidate. This makes it possible to quickly and accurately evaluate the characteristics and skills of candidates and automatically recommend the most suitable assignment.

[0537] A "generative AI means" is an artificial intelligence means that automatically generates questions to engage in dialogue with candidates.

[0538] "Presentation means" refers to the means by which the generated questions are presented to the candidate, and may be in the form of audio, text, or video.

[0539] "Collection means" refers to the means used to collect candidate response data.

[0540] "Evaluation means" refers to means for evaluating collected response data, including sentiment analysis and content analysis.

[0541] The "recording means" is a means for accumulating the evaluation results, and records the evaluation results in a database.

[0542] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[0543] "Recognition means" refers to a means for recognizing candidates, such as by facial recognition, to identify candidates.

[0544] "Audio collection means" refers to a means for collecting candidates' audio responses to questions posed.

[0545] "Speech recognition means" refers to means for converting collected voice data into text.

[0546] "Analysis means" refers to means for performing sentiment analysis and text classification from audio data.

[0547] "Data recording means" means for recording the results of the evaluation in an appropriate database.

[0548] System Overview

[0549] This invention applies an interview system using generative AI to the recruitment of factory robots. This system includes a recognition means, a generative AI means, a presentation means, a voice collection means, a voice recognition means, an evaluation means, an analysis means, a data recording means, and a recommendation means. The specific implementation methods for each means, as well as the hardware and software required for them, are described below.

[0550] recognition means

[0551] The server uses a head-mounted display (HMD) with a built-in camera to recognize the candidate's face. For facial recognition, it uses the OpenCV library and the "haarcascade_frontalface_default.xml" model. This recognition method allows the candidate to automatically complete the login process.

[0552] Generation AI means

[0553] The server automatically generates questions to engage in dialogue with candidates using a generative AI model (e.g., GPT-3). The following is a concrete example of a prompt sentence for generating questions:

[0554] "To understand your role and responsibilities here, please tell us about a challenging project you have undertaken that has been relevant to your work."

[0555] Presentation means

[0556] The generated questions are presented to the candidate via the HMD in the form of audio, text, or video. The presentation means can present the questions in an appropriate manner depending on the candidate's selection.

[0557] Audio collection method

[0558] The candidate's voice responses are collected through the HMD's microphone, and the collected voice data is sent to the server in real time.

[0559] Voice recognition means

[0560] The server uses the Google Speech Recognition API to convert the voice data into text, which quickly transcribes the candidate's answers.

[0561] Evaluation and analysis tools

[0562] The server evaluates the textual responses and performs sentiment analysis and text classification using the "transformers" library. For example, sentiment analysis and text classification are performed for:

[0563] Emotion result: {"label": "POSITIVE", "score": 0.98}

[0564] Content result: {"label": "MANAGEMENT_SKILL", "score": 0.87}

[0565] Data Recording Means

[0566] The server records the results of the evaluation in an appropriate database. We use an SQLite database to store the results so that they can be used for later re-evaluation.

[0567] Recommendations

[0568] Based on the evaluation results, the server recommends the best second interviewer or placement for the candidate. For example, a notification recommending placement in a specific department at a factory may be sent to the manager.

[0569] These tools enable the present invention to quickly and accurately assess a candidate's characteristics and skills and automatically recommend the most suitable placement.

[0570] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0571] Step 1:

[0572] The server performs facial recognition of the candidate. It uses the camera built into the HMD and the "haarcascade_frontalface_default.xml" model from the OpenCV library. The input is video data from the camera, and the output is the candidate's identification information. Specifically, the video data is processed in real time, and the facial features are compared with the database to complete the candidate's login.

[0573] Step 2:

[0574] The server generates questions using a generative AI model. The input is a prompt, an example of which is, "To understand your role and responsibilities here, please tell me about a challenging project in your related work." The output is a question to be presented to the candidate. Specifically, the generative AI (e.g., GPT-3) generates an appropriate question based on the prompt and outputs it in text format.

[0575] Step 3:

[0576] The device presents the generated questions to the candidate. The candidate can choose the presentation method from audio, text, or video format. The input is the generated question, and the output is the question presented to the candidate. Specifically, the HMD's display and speaker are used to present the question in the format selected by the candidate.

[0577] Step 4:

[0578] The user answers the questions by voice. The device collects the candidate's voice responses through the microphone built into the HMD. The input is the candidate's voice data, and the output is the collected voice file. Specifically, the microphone collects the voice and transmits it to the server in real time as digital voice data.

[0579] Step 5:

[0580] The server uses the Google Speech Recognition API to convert the voice data into text. The input is the collected voice data, and the output is the converted text data. Specifically, the API analyzes the voice data and converts the voice into text.

[0581] Step 6:

[0582] The server performs sentiment analysis and text classification using the "transformers" library to analyze text data. The input is the transformed text data, and the output is the sentiment analysis results and content classification results. Specifically, it extracts emotions and nuances from the text data and generates classification results.

[0583] Step 7:

[0584] The server records the analysis results in a database. The input is the sentiment analysis results and content classification results, and the output is the evaluation data stored in the database. Specifically, the evaluation data is stored in an SQLite database so that it can be used later for re-evaluation and comparison with other candidates.

[0585] Step 8:

[0586] The server recommends the most suitable second interviewer or assignment for the candidate based on the recorded evaluation data. The input is the recorded evaluation data, and the output is the recommendation result. Specifically, the server analyzes the evaluation data and automatically recommends the most appropriate assignment for the candidate (for example, a specific department in a factory). The recommendation result is notified to the administrator.

[0587] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0588] The present invention relates to an interview system called "IntelliInterview" that uses generative AI, and in particular, it combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. The following describes an embodiment of the present invention.

[0589] System Configuration

[0590] 1. Generation AI means

[0591] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[0592] 2. Presentation means

[0593] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[0594] 3. Emotion Engine

[0595] The server is equipped with an emotion engine for analyzing the user's response data. The emotion engine analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[0596] 4. Collection Method

[0597] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[0598] 5. Evaluation Methods

[0599] The server analyzes the collected response data using a generative AI model and an emotion engine. The emotion engine recognizes the user's emotions, and the generative AI model analyzes those emotions and the content of the responses to evaluate the user's thinking style, personality traits, and skill level.

[0600] 6. Recording Method

[0601] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be used for future recruitment strategies and human resource management.

[0602] 7. Recommendations

[0603] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[0604] Specific examples

[0605] 1. The user starts the interview

[0606] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0607] 2. Generative AI presents questions

[0608] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[0609] 3. Users respond

[0610] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0611] 4. The emotion engine analyzes the user's responses

[0612] The server analyzes the received voice data using an emotion engine, which analyzes the emotional tone in the voice and determines the emotional state of the user.

[0613] 5. Generative AI analyzes the answers

[0614] The server uses a generative AI model to analyze this voice data. This analysis involves voice recognition and content analysis, and evaluates the user's thinking style and personality. By taking into account the results of the emotion engine, a more accurate evaluation is possible.

[0615] 6. The server records the evaluation results

[0616] The evaluation results generated by the generative AI model and emotion engine are recorded in a database by the server, and this data can be used later for re-evaluation and comparison with other candidates.

[0617] 7. The server recommends candidates for second interviews and placements

[0618] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[0619] As described above, the embodiments of the present invention improve the efficiency and fairness of the conventional interview process, and realize the selection and placement of appropriate personnel. The introduction of the emotion engine provides deeper insights and makes it possible to understand the true characteristics of candidates.

[0620] The processing flow will be explained below.

[0621] Step 1:

[0622] The user accesses a device (PC, smartphone, tablet, etc.) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[0623] Step 2:

[0624] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[0625] Step 3:

[0626] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[0627] Step 4:

[0628] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[0629] Step 5:

[0630] The server passes the received response data to the generative AI model and emotion engine, which then analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[0631] Step 6:

[0632] The generative AI model takes into account the user's emotional state and analyzes the content of the voice and text data, which then assesses the user's thinking style, personality traits, and skill level.

[0633] Step 7:

[0634] The server records the evaluation results provided by the generative AI model and emotion engine in a database, which can then be used for later re-evaluation and comparison with other candidates.

[0635] Step 8:

[0636] The server generates additional questions based on the initial evaluation results. The generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[0637] Step 9:

[0638] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 7 are then repeated.

[0639] Step 10:

[0640] The server integrates all the evaluation data to create a comprehensive evaluation for the user. The generative AI model and emotion engine then perform the integrated evaluation to generate a consistent final evaluation report.

[0641] Step 11:

[0642] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[0643] The above is the specific processing flow of the intelligent interview system combined with an emotion engine. This system utilizes generative AI and an emotion engine to achieve detailed evaluation of candidates, including their emotional state, providing a fairer and more efficient interview process.

[0644] Example 2

[0645] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0646] Conventional interview systems have difficulty taking into account emotional states and nuances of expression when evaluating candidates' thinking styles and personality traits. Furthermore, evaluations by human interviewers are prone to bias and risk lacking fairness. This makes it difficult to select and assign the right talent, impacting companies' recruitment strategies and human resource management.

[0647] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, and a collection means for collecting answer data from the candidates. This makes it possible to analyze the emotional state of the candidates and evaluate their thinking style and personality traits.

[0648] A "generative AI means" is a means that uses an AI model to generate questions to interact with a candidate.

[0649] The "presentation means" is a means for presenting the questions generated by the generation AI means to the candidate.

[0650] "Collection means" refers to the means used to collect candidate response data.

[0651] The "evaluation means" is a means for evaluating the response data collected by the collection means.

[0652] The "recording means" is a means for storing the results of evaluation by the evaluation means.

[0653] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[0654] "Emotion analysis means" is a means for analyzing the emotional state of a candidate.

[0655] The present invention relates to "IntelliInterview," an interview system that uses generative AI, and in particular, is a system that combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. An embodiment of the present invention is described in detail below.

[0656] Server Roles

[0657] The server is a key component of the present invention. The server executes a generative AI means to generate questions for dialogue with candidates. For example, the generative AI means uses GPT-4, a natural language generation model. The following prompt sentences are used to generate questions:

[0658] "Generate creative questions for candidates."

[0659] "Generate questions that ask candidates about difficult situations they've experienced in the past."

[0660] The questions generated by the generation AI means are sent to the terminal by the server. The server then analyzes the candidate's answer data using the emotion analysis means. This emotion analysis means analyzes the candidate's emotional state (e.g., joy, sadness, fear, anger, etc.) from the voice data and text data. For example, the emotion analysis tool of Azure Cognitive Services is used for emotion analysis.

[0661] The server integrates the analytical data obtained from the emotion analysis means and the generation AI means to generate a final evaluation result. The evaluation results are recorded in a database, allowing for future re-evaluation and comparison with other candidates. The server also recommends the most appropriate second interviewer and assignment based on the evaluation results.

[0662] Device Role

[0663] The terminal acts as an interface with the user. It presents the questions received from the server to the user. The presentation method can be text, audio, or video, and the user can choose according to their preference. For example, the generated question "What is the most difficult project you have ever worked on?" is presented to the user.

[0664] When the user enters an answer, the device collects the answer data, converts it into an appropriate data format, and sends it to the server. For example, if the answer is a voice response, the device converts the voice data into WAV or MP3 format and sends it.

[0665] User Roles

[0666] The user starts the interview by logging in to a dedicated web app or mobile app. First, the user enters their ID and password, and is authenticated by the server. If authentication is successful, the user receives questions from the server via their device.

[0667] Users enter answers to questions and send them to the server via their devices. This allows the system to collect data to evaluate the user's thinking style and personality traits. For example, a user might enter an answer like, "I was in charge of a project to introduce a new system last year..."

[0668] As described above, the interview system of the present invention combines generative AI and an emotion analysis engine to evaluate candidate aptitude with high accuracy and recommend optimal placement and second interviewers, thereby improving the efficiency and fairness of the conventional interview process.

[0669] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0670] Step 1:

[0671] The server executes the generative AI means to generate questions. The server passes a prompt (e.g., "Please generate a question to test the candidate's creativity") as input to a generative AI model (e.g., GPT-4). The generative AI model generates a question based on the prompt and outputs the question to the server.

[0672] Step 2:

[0673] The server sends the generated question to the terminal. The server converts the question, which is the output from the generation AI means, into a data format (e.g., text data) and sends it to the terminal. The terminal receives this question and proceeds to the next step.

[0674] Step 3:

[0675] The terminal presents the question to the user. The terminal outputs the question received from the server to the user in voice, text, or video format. For example, the terminal presents the question such as "What is the most difficult project you have ever undertaken?" to the user in voice format.

[0676] Step 4:

[0677] The user answers the question. The user responds to the question by voice, text, or video. For example, the user might say, "The biggest challenge I've ever faced was implementing a new system..."

[0678] Step 5:

[0679] The device collects the answer data and sends it to the server. The device converts the answer data entered by the user into an appropriate format (e.g., voice data into WAV format). After conversion, the device sends this data to the server.

[0680] Step 6:

[0681] The server analyzes the received response data using the emotion analysis means. The server passes input data (e.g., voice data) from the terminal to the emotion analysis means, which analyzes the emotional state (e.g., joy, sadness, fear, anger, etc.). The emotion analysis means outputs the analysis results to the server.

[0682] Step 7:

[0683] The server analyzes the responses using the generation AI. The server passes the output from the emotion analysis means (e.g., emotional state) and input data from the device (e.g., voice data) to the generation AI model. The generation AI model performs text analysis and evaluates the user's thinking style and personality traits from the responses. The evaluation results are output to the server.

[0684] Step 8:

[0685] The server records the evaluation results. The server combines the output data from the generative AI model and the sentiment analysis method to create evaluation data. This evaluation data is recorded in a database, allowing for future re-evaluation and comparison with other candidates.

[0686] Step 9:

[0687] The server notifies the recommended results. Based on the evaluation data, the server recommends the most suitable second interviewer and assignment. For example, it may recommend assignment to the technical department leader or project management department. The recommended results are notified to the manager.

[0688] (Application example 2)

[0689] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0690] Conventional self-driving vehicles lack a system that can evaluate the driver's emotional state and thinking style in real time and provide appropriate advice. As a result, driver fatigue and stress cannot be managed appropriately, resulting in problems with safety and comfort.

[0691] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0692] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting answer data from the candidates, an evaluation means for evaluating the answer data collected by the collection means, a recording means for accumulating the results of the evaluation by the evaluation means, a recommendation means for recommending a second interviewer or assignment that is optimal for the candidate, and a means for evaluating the emotions and thinking style of the driver of an autonomous vehicle in real time and providing appropriate advice. This makes it possible to evaluate the emotions and thinking style of the driver in real time and provide appropriate advice.

[0693] A "generative AI means" is an artificial intelligence system that generates questions and advice to engage in dialogue with a candidate (or driver).

[0694] The "presentation means" is a device that displays or audibly presents the questions or advice generated by the generation AI means to the candidate (or driver).

[0695] "Collection means" refers to a device or system for acquiring and storing candidate (or driver) response data.

[0696] The "evaluation means" refers to an algorithm or program for analyzing and evaluating the response data collected by the collection means.

[0697] A "recording means" is a device or system that stores the evaluated results in a database for later re-evaluation and comparison.

[0698] The "recommendation means" is a device or system for providing the candidate with the most suitable second interviewer or assignment, or appropriate advice for the driver, based on the evaluation results.

[0699] An "autonomous vehicle" is a vehicle that is equipped with the capability to drive autonomously with minimal driver intervention.

[0700] "Real-time assessment of emotions and thinking styles" refers to the process of instantly analyzing the driver's emotional state and thinking characteristics and making an assessment based on the current situation.

[0701] "Providing appropriate advice" means making the best suggestions to maintain a safe and comfortable driving environment based on the driver's emotions and thinking style.

[0702] This invention relates to a system that evaluates the driver's emotions and thinking style in real time and provides appropriate advice in autonomous vehicles. This system integrates a generative AI model and an emotion engine, aiming to improve safety and comfort.

[0703] System Configuration

[0704] 1. Generation AI means

[0705] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The generated questions are designed to assess the driver's emotions and thinking style.

[0706] 2. Presentation means

[0707] The device receives questions and advice from the server and presents them to the driver via the in-car display and voice system. For example, the device may ask, "How do you feel while driving?"

[0708] 3. Collection Method

[0709] The device collects the driver's voice responses via a microphone, converts them into an appropriate voice format, and sends them to a server. It also uses a camera to capture the driver's facial expressions for sentiment analysis.

[0710] 4. Evaluation Methods

[0711] The server analyzes the collected audio and video data using an emotion engine, which determines the driver's emotional state, and the generative AI model evaluates the driver's thinking style based on the responses and facial expressions.

[0712] 5. Recording Method

[0713] The evaluation results are stored in a database by the server and can be used later for re-evaluation, comparison with other drivers, and analysis of driving habits.

[0714] 6. Recommendations

[0715] The server then provides appropriate advice to the driver based on the evaluation results. For example, if the driver responds, "I'm a little tired," the system will suggest, "The next rest point is 5km away. Would you like to take a break?"

[0716] Hardware or software used

[0717] Hardware:

[0718] Microphone: Used to collect driver voice input.

[0719] Camera: Used to analyze the driver's facial expressions.

[0720] Display or audio system: Used to present questions and advice.

[0721] software:

[0722] SpeechRecognition: Used to convert speech to text.

[0723] OpenCV: Used to process camera footage.

[0724] Transformers (Hugging Face): Used for sentiment analysis using the BERT model.

[0725] Specific examples

[0726] Example prompt sentence:

[0727] The question posed is, "How do you feel about your recent work progress?"

[0728] If the driver answers, "I'm under pressure and a little tired," the system analyzes their emotions in real time and provides advice such as, "It's important to take enough rest. I recommend you take a coffee break in five minutes."

[0729] In this way, a system that combines a generative AI model and an emotion engine can evaluate the driver's state in real time in an autonomous vehicle and provide appropriate advice, thereby reducing driver fatigue and stress and improving safety.

[0730] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0731] Step 1:

[0732] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The input is the driver's previous data and existing data in the system, and the output is the generated questions and advice. Based on the generated questions, the server creates prompt sentences to ask the driver.

[0733] Step 2:

[0734] The terminal presents the driver with questions and advice received from the server. The input is what the server produces, and the output is what the driver sees or hears on the display or audio system. For example, the question "How do you feel while driving?" is displayed on the display.

[0735] Step 3:

[0736] The user (driver) answers the presented questions by voice. The input is the question presented by the terminal, and the output is the driver's voice response. Drivers often respond by saying, "I'm a little tired today."

[0737] Step 4:

[0738] The terminal collects the driver's voice response through a microphone and converts it into an appropriate voice format. The input is the driver's voice data, and the output is the data converted into voice format. This voice data is then sent to the server.

[0739] Step 5:

[0740] The device uses a camera to capture the driver's facial expressions and collects the data in real time. The input is the camera image, and the output is facial expression data. This data is also sent to the server.

[0741] Step 6:

[0742] The server uses an emotion engine to analyze the collected audio and video data. The input is audio data and facial expression data, and the output is an analysis result that indicates the driver's emotional state. Specifically, it determines whether the driver feels "a little tired" by analyzing the tone of the voice and recognizing facial expressions.

[0743] Step 7:

[0744] The server uses a generative AI model to evaluate the driver's responses and emotional state. The input is the voice transcript and emotion analysis results, and the output is an assessment of the driver's thinking style and personality traits. For example, the driver may be assessed as "stressed."

[0745] Step 8:

[0746] The server stores the evaluation results in a database. The input is the evaluation results, and the output is the stored data, which can later be used for re-evaluation and comparison with other drivers.

[0747] Step 9:

[0748] Based on the evaluation results, the server generates appropriate advice for the driver and sends it to the terminal. The input is the evaluation result, and the output is the generated advice. For example, a suggestion might be generated: "The next rest point is 5 km away. Would you like to take a break?"

[0749] Step 10:

[0750] The terminal presents the advice received from the server to the driver. The input is the generated advice, and the output is the driver's behavior after receiving the advice. The driver is prompted to decide whether to take a break.

[0751] 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.

[0752] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0753] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0754] [Third embodiment]

[0755] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0756] 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.

[0757] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0758] 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.

[0759] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0760] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0761] 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.

[0762] 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.

[0763] 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 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.

[0764] 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.

[0765] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0766] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0767] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. The following describes an embodiment of the present invention.

[0768] System Configuration

[0769] 1. Generation AI means

[0770] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[0771] 2. Presentation means

[0772] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[0773] 3. Collection Method

[0774] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[0775] 4. Evaluation Methods

[0776] The server uses a generative AI model to analyze the collected response data, including speech recognition, sentiment analysis, and content analysis, to assess the candidate's thinking style, personality, and skill level.

[0777] 5. Recording Method

[0778] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be useful for future recruitment strategies and human resource management.

[0779] 6. Recommendations

[0780] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[0781] Specific examples

[0782] 1. The user starts the interview

[0783] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0784] 2. Generative AI presents questions

[0785] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[0786] 3. Users respond

[0787] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0788] 4. The server parses the answer

[0789] The server uses a generative AI model to analyze this voice data, which performs speech recognition and emotion analysis to assess the user's thinking style and personality.

[0790] 5. The server records the evaluation results

[0791] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[0792] 6. The server recommends candidates for second interviews and placements

[0793] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[0794] As described above, the embodiment of the present invention improves the efficiency and fairness of the conventional interview process, and realizes the selection and placement of appropriate personnel.

[0795] The processing flow will be explained below.

[0796] Step 1:

[0797] The user accesses a device (PC, smartphone, tablet) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[0798] Step 2:

[0799] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[0800] Step 3:

[0801] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[0802] Step 4:

[0803] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[0804] Step 5:

[0805] The server passes the received response data to the generative AI model and begins analysis. The analysis includes speech recognition, sentiment analysis, and content analysis. The generative AI model converts the user's response into text and analyzes the nuances of emotion and expression. Based on the analysis results, the user's thinking style, personality traits, and skill level are evaluated.

[0806] Step 6:

[0807] The server records the evaluation results provided by the generative AI model in a database, which can then be used for later re-evaluation and comparison with other candidates.

[0808] Step 7:

[0809] The server generates additional questions based on the initial evaluation results. A generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[0810] Step 8:

[0811] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 6 are then repeated.

[0812] Step 9:

[0813] The server aggregates all the evaluation data to create a comprehensive evaluation for the user. A generative AI model performs the integrated evaluation and generates a consistent final evaluation report.

[0814] Step 10:

[0815] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[0816] This is the specific process flow of the IntelliInterview System. This system utilizes generative AI to achieve an efficient and fair interview process.

[0817] Example 1

[0818] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0819] In today's interview process, it is difficult to fully evaluate a candidate's thinking style, personality, and the content of their responses. Furthermore, because the evaluation relies heavily on human subjectivity, there are issues with fairness and efficiency. Furthermore, it takes a lot of time and effort to identify the appropriate second interviewer and the candidate's assignment. There is a need for a method to solve these issues and realize an efficient and fair interview process.

[0820] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0821] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting candidate response data in the form of audio, text, or video, an evaluation means for analyzing the response data collected by the collection means, a recording means for recording the results of the evaluation by the evaluation means in a database, a recommendation means for recommending the most suitable second interviewer or assignment for the candidate based on the evaluation results, an authentication means for starting an interactive session with an authenticated user, and a notification means for notifying an administrator of the analysis results. This makes it possible to objectively and efficiently evaluate the thinking style and personality of candidates and accurately suggest the most suitable interviewer and assignment.

[0822] A "generative AI means" is a means for generating questions for candidates using a generative AI model.

[0823] "Presentation Means" means a means by which questions generated by the Generative AI Means are presented to the Candidate in audio, text, or video format.

[0824] "Collection means" refers to a means for collecting candidate response data in audio, text, or video format, converting it into an appropriate format, and transmitting it to a server.

[0825] The "evaluation means" is a means for analyzing the response data collected by the collection means and evaluating the thinking style and personality traits of the candidate by performing voice recognition, emotion analysis, and content analysis.

[0826] The "recording means" is a means for recording the results of evaluation by the evaluation means in a database.

[0827] The "recommendation means" is a means for recommending the most suitable second interviewer or assignment for a candidate based on the evaluation results recorded by the recording means.

[0828] An "authentication means" is a means by which a user logs into a dedicated web or mobile app and confirms authentication information to initiate an interactive session with an authenticated user.

[0829] The "notification means" is a means for notifying the administrator of the analysis results and recommendation results.

[0830] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. Specific embodiments for implementing the present invention are described below.

[0831] The server runs a generative AI method to generate questions for the candidate. This generative AI method uses GPT-4 or an equivalent language model. The generated questions are designed to assess the candidate's thinking style and personality. For example, the generative AI may generate a question such as, "What is the most difficult project you have ever worked on?"

[0832] The generated questions are sent from the server to the terminal, which then presents them to the candidate. The questions can be presented in voice, text, or video format, allowing the candidate to choose the appropriate input method. Specifically, the terminal displays the questions using a web application using HTML5, CSS, and JavaScript.

[0833] Once the candidate enters their answers, the device collects the answer data, which is then sent to a server in an appropriate format, such as MP3 format, using a microphone and a framework such as React Native.

[0834] The server analyzes the collected response data using a generative AI model. This analysis includes speech recognition, sentiment analysis, and content analysis. Google Speech-to-Text API is used for speech recognition, and IBM Watson Tone Analyzer is used for sentiment analysis. This allows the candidate's thinking style, personality, and skill level to be evaluated.

[0835] The evaluation results are recorded in a database by the server using MySQL or PostgreSQL. This data can be used for future re-evaluations and comparisons with other candidates.

[0836] Based on the evaluation results, the server recommends the most suitable second interviewer and assignment for the candidate. For example, it may recommend assignment to the technical department leader or project management department. These recommendations are notified to the system administrator, who then uses the information to select the second interviewer and make appropriate assignment decisions.

[0837] Specific examples are shown below.

[0838] The user (candidate) starts the interview by logging in to a dedicated web app or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0839] The terminal presents the question received from the server to the user, for example, "What is the most difficult project you have ever undertaken?"

[0840] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0841] The server analyzes the voice data using a generative AI model, which provides results of speech recognition and sentiment analysis to assess the user's thinking style and personality.

[0842] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[0843] Based on the evaluation results, the server recommends that the employee be assigned to a technical department leader or project management department, and the recommendation is notified to the system administrator.

[0844] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0845] Divide the processing flow of this system's program into processing steps

[0846] Step 1: User authentication

[0847] Step 2: Question generation

[0848] Step 3: Question posing

[0849] Step 4: Collect responses

[0850] Step 5: Response analysis

[0851] Step 6: Evaluation Record

[0852] Step 7: Notification of recommended results

[0853] Explain each processing step in detail

[0854] Step 1: User authentication

[0855] The server authenticates users who access the server using a dedicated web app or mobile app. The user enters their username and password on the login screen. The server checks the information against the database, and if authentication is successful, it generates a session ID and returns it to the user. The input is user information, and the output is the authentication result and session ID. If authentication is successful, an interactive session begins.

[0856] Specific actions

[0857] 1. The user accesses the login screen and enters their username and password.

[0858] 2. The server checks the credentials against a database.

[0859] 3. If authentication is successful, the server generates a session ID and returns it to the user.

[0860] Step 2: Question generation

[0861] The server uses a generative AI model (e.g., GPT-4) to generate questions for the user, which are designed to assess the candidate's thinking style and personality. The input is the session ID, and the output is the generated questions.

[0862] Specific actions

[0863] 1. The server receives the session ID and runs the generative AI model.

[0864] 2. A generative AI model generates questions such as, "What is the most challenging project you have ever worked on?"

[0865] 3. A question is generated and stored on the server.

[0866] Step 3: Question posing

[0867] The generated question is sent from the server to the terminal, which then presents it to the user. The presentation can be in the form of voice, text, or video, and the user can choose the preferred input method. The input is the generated question, and the output is the presented question.

[0868] Specific actions

[0869] 1. The server sends the generated question to the terminal.

[0870] 2. The terminal presents the received question to the user (e.g., by displaying a text message).

[0871] 3. The user chooses the best input method (voice, text, or video).

[0872] Step 4: Collect responses

[0873] The user inputs answers to questions. The device collects the answer data and, in the case of voice input, converts it into an appropriate audio format (e.g., MP3) and sends it to the server. The input is the user's answer data, and the output is the collected answer data.

[0874] Specific actions

[0875] 1. The user speaks their response (e.g., "I worked on a large system migration project last year").

[0876] 2. The device collects the audio data and converts it into the appropriate format.

[0877] 3. The collected data is sent to the server.

[0878] Step 5: Response analysis

[0879] The server analyzes the collected response data using a generative AI model. The analysis includes speech recognition, sentiment analysis, and content analysis. The input is the collected response data, and the output is the analysis results.

[0880] Specific actions

[0881] 1. The server receives the collected response data and begins analysis using the generative AI model.

[0882] 2. Speech recognition (e.g., Google Speech-to-Text API) is performed.

[0883] 3. Sentiment analysis (e.g. IBM Watson Tone Analyzer) is performed and content analysis is carried out.

[0884] 4. The analysis results are obtained and the candidate's thinking style and personality are evaluated.

[0885] Step 6: Evaluation Record

[0886] The server records the analysis results in a database. The input is the analysis results, and the output is the evaluation data recorded in the database.

[0887] Specific actions

[0888] 1. The server receives the analysis results and accesses the database.

[0889] 2. The evaluation results are recorded in a database (e.g., MySQL, PostgreSQL).

[0890] 3. Confirmation of completion of recording will be made.

[0891] Step 7: Notification of recommended results

[0892] The server recommends the most suitable second interviewer and placement for the candidate based on the evaluation results. The recommended results are notified to the administrator. The input is the evaluation results, and the output is a notification of the recommended results.

[0893] Specific actions

[0894] 1. The server analyzes the evaluation results and determines the appropriate second interviewer and placement.

[0895] 2. Recommendations are generated and notified to the administrator.

[0896] 3. Administrators are notified and take necessary action.

[0897] The specific processing contents and operations of each step have been described above.

[0898] (Application example 1)

[0899] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0900] Conventional interview systems require a lot of time and effort when evaluating candidates, and can lack fairness. It is also difficult to accurately evaluate a candidate's characteristics and skills and determine the most appropriate position for the candidate. The present invention aims to solve these problems and provide a system for realizing an efficient and fair interview process.

[0901] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0902] In this invention, the server includes a recognition means for recognizing candidates, a generation AI means, a presentation means for presenting questions generated by the generation AI means, a voice collection means for collecting voice responses, a voice recognition means for converting the collected voice data into text, an evaluation means for evaluating the response data, an analysis means for performing sentiment analysis and text classification from the voice data, a data recording means for recording the evaluation results in an appropriate database, and a recommendation means for recommending the most suitable second interviewer or assignment for the candidate. This makes it possible to quickly and accurately evaluate the characteristics and skills of candidates and automatically recommend the most suitable assignment.

[0903] A "generative AI means" is an artificial intelligence means that automatically generates questions to engage in dialogue with candidates.

[0904] "Presentation means" refers to the means by which the generated questions are presented to the candidate, and may be in the form of audio, text, or video.

[0905] "Collection means" refers to the means used to collect candidate response data.

[0906] "Evaluation means" refers to means for evaluating collected response data, including sentiment analysis and content analysis.

[0907] The "recording means" is a means for accumulating the evaluation results, and records the evaluation results in a database.

[0908] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[0909] "Recognition means" refers to a means for recognizing candidates, such as by facial recognition, to identify candidates.

[0910] "Audio collection means" refers to a means for collecting candidates' audio responses to questions posed.

[0911] "Speech recognition means" refers to means for converting collected voice data into text.

[0912] "Analysis means" refers to means for performing sentiment analysis and text classification from audio data.

[0913] "Data recording means" means for recording the results of the evaluation in an appropriate database.

[0914] System Overview

[0915] This invention applies an interview system using generative AI to the recruitment of factory robots. This system includes a recognition means, a generative AI means, a presentation means, a voice collection means, a voice recognition means, an evaluation means, an analysis means, a data recording means, and a recommendation means. The specific implementation methods for each means, as well as the hardware and software required for them, are described below.

[0916] recognition means

[0917] The server uses a head-mounted display (HMD) with a built-in camera to recognize the candidate's face. For facial recognition, it uses the OpenCV library and the "haarcascade_frontalface_default.xml" model. This recognition method allows the candidate to automatically complete the login process.

[0918] Generation AI means

[0919] The server automatically generates questions to engage in dialogue with candidates using a generative AI model (e.g., GPT-3). The following is a concrete example of a prompt sentence for generating questions:

[0920] "To understand your role and responsibilities here, please tell us about a challenging project you have undertaken that has been relevant to your work."

[0921] Presentation means

[0922] The generated questions are presented to the candidate via the HMD in the form of audio, text, or video. The presentation means can present the questions in an appropriate manner depending on the candidate's selection.

[0923] Audio collection method

[0924] The candidate's voice responses are collected through the HMD's microphone, and the collected voice data is sent to the server in real time.

[0925] Voice recognition means

[0926] The server uses the Google Speech Recognition API to convert the voice data into text, which quickly transcribes the candidate's answers.

[0927] Evaluation and analysis tools

[0928] The server evaluates the textual responses and performs sentiment analysis and text classification using the "transformers" library. For example, sentiment analysis and text classification are performed for:

[0929] Emotion result: {"label": "POSITIVE", "score": 0.98}

[0930] Content result: {"label": "MANAGEMENT_SKILL", "score": 0.87}

[0931] Data Recording Means

[0932] The server records the results of the evaluation in an appropriate database. We use an SQLite database to store the results so that they can be used for later re-evaluation.

[0933] Recommendations

[0934] Based on the evaluation results, the server recommends the best second interviewer or placement for the candidate. For example, a notification recommending placement in a specific department at a factory may be sent to the manager.

[0935] These tools enable the present invention to quickly and accurately assess a candidate's characteristics and skills and automatically recommend the most suitable placement.

[0936] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0937] Step 1:

[0938] The server performs facial recognition of the candidate. It uses the camera built into the HMD and the "haarcascade_frontalface_default.xml" model from the OpenCV library. The input is video data from the camera, and the output is the candidate's identification information. Specifically, the video data is processed in real time, and the facial features are compared with the database to complete the candidate's login.

[0939] Step 2:

[0940] The server generates questions using a generative AI model. The input is a prompt, an example of which is, "To understand your role and responsibilities here, please tell me about a challenging project in your related work." The output is a question to be presented to the candidate. Specifically, the generative AI (e.g., GPT-3) generates an appropriate question based on the prompt and outputs it in text format.

[0941] Step 3:

[0942] The device presents the generated questions to the candidate. The candidate can choose the presentation method from audio, text, or video format. The input is the generated question, and the output is the question presented to the candidate. Specifically, the HMD's display and speaker are used to present the question in the format selected by the candidate.

[0943] Step 4:

[0944] The user answers the questions by voice. The device collects the candidate's voice responses through the microphone built into the HMD. The input is the candidate's voice data, and the output is the collected voice file. Specifically, the microphone collects the voice and transmits it to the server in real time as digital voice data.

[0945] Step 5:

[0946] The server uses the Google Speech Recognition API to convert the voice data into text. The input is the collected voice data, and the output is the converted text data. Specifically, the API analyzes the voice data and converts the voice into text.

[0947] Step 6:

[0948] The server performs sentiment analysis and text classification using the "transformers" library to analyze text data. The input is the transformed text data, and the output is the sentiment analysis results and content classification results. Specifically, it extracts emotions and nuances from the text data and generates classification results.

[0949] Step 7:

[0950] The server records the analysis results in a database. The input is the sentiment analysis results and content classification results, and the output is the evaluation data stored in the database. Specifically, the evaluation data is stored in an SQLite database so that it can be used later for re-evaluation and comparison with other candidates.

[0951] Step 8:

[0952] The server recommends the most suitable second interviewer or assignment for the candidate based on the recorded evaluation data. The input is the recorded evaluation data, and the output is the recommendation result. Specifically, the server analyzes the evaluation data and automatically recommends the most appropriate assignment for the candidate (for example, a specific department in a factory). The recommendation result is notified to the administrator.

[0953] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0954] The present invention relates to an interview system called "IntelliInterview" that uses generative AI, and in particular, it combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. The following describes an embodiment of the present invention.

[0955] System Configuration

[0956] 1. Generation AI means

[0957] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[0958] 2. Presentation means

[0959] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[0960] 3. Emotion Engine

[0961] The server is equipped with an emotion engine for analyzing the user's response data. The emotion engine analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[0962] 4. Collection Method

[0963] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[0964] 5. Evaluation Methods

[0965] The server analyzes the collected response data using a generative AI model and an emotion engine. The emotion engine recognizes the user's emotions, and the generative AI model analyzes those emotions and the content of the responses to evaluate the user's thinking style, personality traits, and skill level.

[0966] 6. Recording Method

[0967] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be used for future recruitment strategies and human resource management.

[0968] 7. Recommendations

[0969] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[0970] Specific examples

[0971] 1. The user starts the interview

[0972] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[0973] 2. Generative AI presents questions

[0974] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[0975] 3. Users respond

[0976] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[0977] 4. The emotion engine analyzes the user's responses

[0978] The server analyzes the received voice data using an emotion engine, which analyzes the emotional tone in the voice and determines the emotional state of the user.

[0979] 5. Generative AI analyzes the answers

[0980] The server uses a generative AI model to analyze this voice data. This analysis involves voice recognition and content analysis, and evaluates the user's thinking style and personality. By taking into account the results of the emotion engine, a more accurate evaluation is possible.

[0981] 6. The server records the evaluation results

[0982] The evaluation results generated by the generative AI model and emotion engine are recorded in a database by the server, and this data can be used later for re-evaluation and comparison with other candidates.

[0983] 7. The server recommends candidates for second interviews and placements

[0984] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[0985] As described above, the embodiments of the present invention improve the efficiency and fairness of the conventional interview process, and realize the selection and placement of appropriate personnel. The introduction of the emotion engine provides deeper insights and makes it possible to understand the true characteristics of candidates.

[0986] The processing flow will be explained below.

[0987] Step 1:

[0988] The user accesses a device (PC, smartphone, tablet, etc.) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[0989] Step 2:

[0990] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[0991] Step 3:

[0992] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[0993] Step 4:

[0994] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[0995] Step 5:

[0996] The server passes the received response data to the generative AI model and emotion engine, which then analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[0997] Step 6:

[0998] The generative AI model takes into account the user's emotional state and analyzes the content of the voice and text data, which then assesses the user's thinking style, personality traits, and skill level.

[0999] Step 7:

[1000] The server records the evaluation results provided by the generative AI model and emotion engine in a database, which can then be used for later re-evaluation and comparison with other candidates.

[1001] Step 8:

[1002] The server generates additional questions based on the initial evaluation results. The generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[1003] Step 9:

[1004] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 7 are then repeated.

[1005] Step 10:

[1006] The server integrates all the evaluation data to create a comprehensive evaluation for the user. The generative AI model and emotion engine then perform the integrated evaluation to generate a consistent final evaluation report.

[1007] Step 11:

[1008] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[1009] The above is the specific processing flow of the intelligent interview system combined with an emotion engine. This system utilizes generative AI and an emotion engine to achieve detailed evaluation of candidates, including their emotional state, providing a fairer and more efficient interview process.

[1010] Example 2

[1011] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1012] Conventional interview systems have difficulty taking into account emotional states and nuances of expression when evaluating candidates' thinking styles and personality traits. Furthermore, evaluations by human interviewers are prone to bias and risk lacking fairness. This makes it difficult to select and assign the right talent, impacting companies' recruitment strategies and human resource management.

[1013] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, and a collection means for collecting answer data from the candidates. This makes it possible to analyze the emotional state of the candidates and evaluate their thinking style and personality traits.

[1014] A "generative AI means" is a means that uses an AI model to generate questions to interact with a candidate.

[1015] The "presentation means" is a means for presenting the questions generated by the generation AI means to the candidate.

[1016] "Collection means" refers to the means used to collect candidate response data.

[1017] The "evaluation means" is a means for evaluating the response data collected by the collection means.

[1018] The "recording means" is a means for storing the results of evaluation by the evaluation means.

[1019] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[1020] "Emotion analysis means" is a means for analyzing the emotional state of a candidate.

[1021] The present invention relates to "IntelliInterview," an interview system that uses generative AI, and in particular, is a system that combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. An embodiment of the present invention is described in detail below.

[1022] Server Roles

[1023] The server is a key component of the present invention. The server executes a generative AI means to generate questions for dialogue with candidates. For example, the generative AI means uses GPT-4, a natural language generation model. The following prompt sentences are used to generate questions:

[1024] "Generate creative questions for candidates."

[1025] "Generate questions that ask candidates about difficult situations they've experienced in the past."

[1026] The questions generated by the generation AI means are sent to the terminal by the server. The server then analyzes the candidate's answer data using the emotion analysis means. This emotion analysis means analyzes the candidate's emotional state (e.g., joy, sadness, fear, anger, etc.) from the voice data and text data. For example, the emotion analysis tool of Azure Cognitive Services is used for emotion analysis.

[1027] The server integrates the analytical data obtained from the emotion analysis means and the generation AI means to generate a final evaluation result. The evaluation results are recorded in a database, allowing for future re-evaluation and comparison with other candidates. The server also recommends the most appropriate second interviewer and assignment based on the evaluation results.

[1028] Device Role

[1029] The terminal acts as an interface with the user. It presents the questions received from the server to the user. The presentation method can be text, audio, or video, and the user can choose according to their preference. For example, the generated question "What is the most difficult project you have ever worked on?" is presented to the user.

[1030] When the user enters an answer, the device collects the answer data, converts it into an appropriate data format, and sends it to the server. For example, if the answer is a voice response, the device converts the voice data into WAV or MP3 format and sends it.

[1031] User Roles

[1032] The user starts the interview by logging in to a dedicated web app or mobile app. First, the user enters their ID and password, and is authenticated by the server. If authentication is successful, the user receives questions from the server via their device.

[1033] Users enter answers to questions and send them to the server via their devices. This allows the system to collect data to evaluate the user's thinking style and personality traits. For example, a user might enter an answer like, "I was in charge of a project to introduce a new system last year..."

[1034] As described above, the interview system of the present invention combines generative AI and an emotion analysis engine to evaluate candidate aptitude with high accuracy and recommend optimal placement and second interviewers, thereby improving the efficiency and fairness of the conventional interview process.

[1035] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1036] Step 1:

[1037] The server executes the generative AI means to generate questions. The server passes a prompt (e.g., "Please generate a question to test the candidate's creativity") as input to a generative AI model (e.g., GPT-4). The generative AI model generates a question based on the prompt and outputs the question to the server.

[1038] Step 2:

[1039] The server sends the generated question to the terminal. The server converts the question, which is the output from the generation AI means, into a data format (e.g., text data) and sends it to the terminal. The terminal receives this question and proceeds to the next step.

[1040] Step 3:

[1041] The terminal presents the question to the user. The terminal outputs the question received from the server to the user in voice, text, or video format. For example, the terminal presents the question such as "What is the most difficult project you have ever undertaken?" to the user in voice format.

[1042] Step 4:

[1043] The user answers the question. The user responds to the question by voice, text, or video. For example, the user might say, "The biggest challenge I've ever faced was implementing a new system..."

[1044] Step 5:

[1045] The device collects the answer data and sends it to the server. The device converts the answer data entered by the user into an appropriate format (e.g., voice data into WAV format). After conversion, the device sends this data to the server.

[1046] Step 6:

[1047] The server analyzes the received response data using the emotion analysis means. The server passes input data (e.g., voice data) from the terminal to the emotion analysis means, which analyzes the emotional state (e.g., joy, sadness, fear, anger, etc.). The emotion analysis means outputs the analysis results to the server.

[1048] Step 7:

[1049] The server analyzes the responses using the generation AI. The server passes the output from the emotion analysis means (e.g., emotional state) and input data from the device (e.g., voice data) to the generation AI model. The generation AI model performs text analysis and evaluates the user's thinking style and personality traits from the responses. The evaluation results are output to the server.

[1050] Step 8:

[1051] The server records the evaluation results. The server combines the output data from the generative AI model and the sentiment analysis method to create evaluation data. This evaluation data is recorded in a database, allowing for future re-evaluation and comparison with other candidates.

[1052] Step 9:

[1053] The server notifies the recommended results. Based on the evaluation data, the server recommends the most suitable second interviewer and assignment. For example, it may recommend assignment to the technical department leader or project management department. The recommended results are notified to the manager.

[1054] (Application example 2)

[1055] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1056] Conventional self-driving vehicles lack a system that can evaluate the driver's emotional state and thinking style in real time and provide appropriate advice. As a result, driver fatigue and stress cannot be managed appropriately, resulting in problems with safety and comfort.

[1057] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1058] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting answer data from the candidates, an evaluation means for evaluating the answer data collected by the collection means, a recording means for accumulating the results of the evaluation by the evaluation means, a recommendation means for recommending a second interviewer or assignment that is optimal for the candidate, and a means for evaluating the emotions and thinking style of the driver of an autonomous vehicle in real time and providing appropriate advice. This makes it possible to evaluate the emotions and thinking style of the driver in real time and provide appropriate advice.

[1059] A "generative AI means" is an artificial intelligence system that generates questions and advice to engage in dialogue with a candidate (or driver).

[1060] The "presentation means" is a device that displays or audibly presents the questions or advice generated by the generation AI means to the candidate (or driver).

[1061] "Collection means" refers to a device or system for acquiring and storing candidate (or driver) response data.

[1062] The "evaluation means" refers to an algorithm or program for analyzing and evaluating the response data collected by the collection means.

[1063] A "recording means" is a device or system that stores the evaluated results in a database for later re-evaluation and comparison.

[1064] The "recommendation means" is a device or system for providing the candidate with the most suitable second interviewer or assignment, or appropriate advice for the driver, based on the evaluation results.

[1065] An "autonomous vehicle" is a vehicle that is equipped with the capability to drive autonomously with minimal driver intervention.

[1066] "Real-time assessment of emotions and thinking styles" refers to the process of instantly analyzing the driver's emotional state and thinking characteristics and making an assessment based on the current situation.

[1067] "Providing appropriate advice" means making the best suggestions to maintain a safe and comfortable driving environment based on the driver's emotions and thinking style.

[1068] This invention relates to a system that evaluates the driver's emotions and thinking style in real time and provides appropriate advice in autonomous vehicles. This system integrates a generative AI model and an emotion engine, aiming to improve safety and comfort.

[1069] System Configuration

[1070] 1. Generation AI means

[1071] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The generated questions are designed to assess the driver's emotions and thinking style.

[1072] 2. Presentation means

[1073] The device receives questions and advice from the server and presents them to the driver via the in-car display and voice system. For example, the device may ask, "How do you feel while driving?"

[1074] 3. Collection Method

[1075] The device collects the driver's voice responses via a microphone, converts them into an appropriate voice format, and sends them to a server. It also uses a camera to capture the driver's facial expressions for sentiment analysis.

[1076] 4. Evaluation Methods

[1077] The server analyzes the collected audio and video data using an emotion engine, which determines the driver's emotional state, and the generative AI model evaluates the driver's thinking style based on the responses and facial expressions.

[1078] 5. Recording Method

[1079] The evaluation results are stored in a database by the server and can be used later for re-evaluation, comparison with other drivers, and analysis of driving habits.

[1080] 6. Recommendations

[1081] The server then provides appropriate advice to the driver based on the evaluation results. For example, if the driver responds, "I'm a little tired," the system will suggest, "The next rest point is 5km away. Would you like to take a break?"

[1082] Hardware or software used

[1083] Hardware:

[1084] Microphone: Used to collect driver voice input.

[1085] Camera: Used to analyze the driver's facial expressions.

[1086] Display or audio system: Used to present questions and advice.

[1087] software:

[1088] SpeechRecognition: Used to convert speech to text.

[1089] OpenCV: Used to process camera footage.

[1090] Transformers (Hugging Face): Used for sentiment analysis using the BERT model.

[1091] Specific examples

[1092] Example prompt sentence:

[1093] The question posed is, "How do you feel about your recent work progress?"

[1094] If the driver answers, "I'm under pressure and a little tired," the system analyzes their emotions in real time and provides advice such as, "It's important to take enough rest. I recommend you take a coffee break in five minutes."

[1095] In this way, a system that combines a generative AI model and an emotion engine can evaluate the driver's state in real time in an autonomous vehicle and provide appropriate advice, thereby reducing driver fatigue and stress and improving safety.

[1096] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1097] Step 1:

[1098] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The input is the driver's previous data and existing data in the system, and the output is the generated questions and advice. Based on the generated questions, the server creates prompt sentences to ask the driver.

[1099] Step 2:

[1100] The terminal presents the driver with questions and advice received from the server. The input is what the server produces, and the output is what the driver sees or hears on the display or audio system. For example, the question "How do you feel while driving?" is displayed on the display.

[1101] Step 3:

[1102] The user (driver) answers the presented questions by voice. The input is the question presented by the terminal, and the output is the driver's voice response. Drivers often respond by saying, "I'm a little tired today."

[1103] Step 4:

[1104] The terminal collects the driver's voice response through a microphone and converts it into an appropriate voice format. The input is the driver's voice data, and the output is the data converted into voice format. This voice data is then sent to the server.

[1105] Step 5:

[1106] The device uses a camera to capture the driver's facial expressions and collects the data in real time. The input is the camera image, and the output is facial expression data. This data is also sent to the server.

[1107] Step 6:

[1108] The server uses an emotion engine to analyze the collected audio and video data. The input is audio data and facial expression data, and the output is an analysis result that indicates the driver's emotional state. Specifically, it determines whether the driver feels "a little tired" by analyzing the tone of the voice and recognizing facial expressions.

[1109] Step 7:

[1110] The server uses a generative AI model to evaluate the driver's responses and emotional state. The input is the voice transcript and emotion analysis results, and the output is an assessment of the driver's thinking style and personality traits. For example, the driver may be assessed as "stressed."

[1111] Step 8:

[1112] The server stores the evaluation results in a database. The input is the evaluation results, and the output is the stored data, which can later be used for re-evaluation and comparison with other drivers.

[1113] Step 9:

[1114] Based on the evaluation results, the server generates appropriate advice for the driver and sends it to the terminal. The input is the evaluation result, and the output is the generated advice. For example, a suggestion might be generated: "The next rest point is 5 km away. Would you like to take a break?"

[1115] Step 10:

[1116] The terminal presents the advice received from the server to the driver. The input is the generated advice, and the output is the driver's behavior after receiving the advice. The driver is prompted to decide whether to take a break.

[1117] 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.

[1118] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[1119] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1120] [Fourth embodiment]

[1121] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1122] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1124] 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.

[1125] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1126] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1127] 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.

[1128] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1129] 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.

[1130] 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 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.

[1131] 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.

[1132] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1133] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1134] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. The following describes an embodiment of the present invention.

[1135] System Configuration

[1136] 1. Generation AI means

[1137] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[1138] 2. Presentation means

[1139] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[1140] 3. Collection Method

[1141] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[1142] 4. Evaluation Methods

[1143] The server uses a generative AI model to analyze the collected response data, including speech recognition, sentiment analysis, and content analysis, to assess the candidate's thinking style, personality, and skill level.

[1144] 5. Recording Method

[1145] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be useful for future recruitment strategies and human resource management.

[1146] 6. Recommendations

[1147] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[1148] Specific examples

[1149] 1. The user starts the interview

[1150] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[1151] 2. Generative AI presents questions

[1152] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[1153] 3. Users respond

[1154] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[1155] 4. The server parses the answer

[1156] The server uses a generative AI model to analyze this voice data, which performs speech recognition and emotion analysis to assess the user's thinking style and personality.

[1157] 5. The server records the evaluation results

[1158] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[1159] 6. The server recommends candidates for second interviews and placements

[1160] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[1161] As described above, the embodiment of the present invention improves the efficiency and fairness of the conventional interview process, and realizes the selection and placement of appropriate personnel.

[1162] The processing flow will be explained below.

[1163] Step 1:

[1164] The user accesses a device (PC, smartphone, tablet) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[1165] Step 2:

[1166] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[1167] Step 3:

[1168] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[1169] Step 4:

[1170] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[1171] Step 5:

[1172] The server passes the received response data to the generative AI model and begins analysis. The analysis includes speech recognition, sentiment analysis, and content analysis. The generative AI model converts the user's response into text and analyzes the nuances of emotion and expression. Based on the analysis results, the user's thinking style, personality traits, and skill level are evaluated.

[1173] Step 6:

[1174] The server records the evaluation results provided by the generative AI model in a database, which can then be used for later re-evaluation and comparison with other candidates.

[1175] Step 7:

[1176] The server generates additional questions based on the initial evaluation results. A generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[1177] Step 8:

[1178] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 6 are then repeated.

[1179] Step 9:

[1180] The server aggregates all the evaluation data to create a comprehensive evaluation for the user. A generative AI model performs the integrated evaluation and generates a consistent final evaluation report.

[1181] Step 10:

[1182] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[1183] This is the specific process flow of the IntelliInterview System. This system utilizes generative AI to achieve an efficient and fair interview process.

[1184] Example 1

[1185] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1186] In today's interview process, it is difficult to fully evaluate a candidate's thinking style, personality, and the content of their responses. Furthermore, because the evaluation relies heavily on human subjectivity, there are issues with fairness and efficiency. Furthermore, it takes a lot of time and effort to identify the appropriate second interviewer and the candidate's assignment. There is a need for a method to solve these issues and realize an efficient and fair interview process.

[1187] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1188] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting candidate response data in the form of audio, text, or video, an evaluation means for analyzing the response data collected by the collection means, a recording means for recording the results of the evaluation by the evaluation means in a database, a recommendation means for recommending the most suitable second interviewer or assignment for the candidate based on the evaluation results, an authentication means for starting an interactive session with an authenticated user, and a notification means for notifying an administrator of the analysis results. This makes it possible to objectively and efficiently evaluate the thinking style and personality of candidates and accurately suggest the most suitable interviewer and assignment.

[1189] A "generative AI means" is a means for generating questions for candidates using a generative AI model.

[1190] "Presentation Means" means a means by which questions generated by the Generative AI Means are presented to the Candidate in audio, text, or video format.

[1191] "Collection means" refers to a means for collecting candidate response data in audio, text, or video format, converting it into an appropriate format, and transmitting it to a server.

[1192] The "evaluation means" is a means for analyzing the response data collected by the collection means and evaluating the thinking style and personality traits of the candidate by performing voice recognition, emotion analysis, and content analysis.

[1193] The "recording means" is a means for recording the results of evaluation by the evaluation means in a database.

[1194] The "recommendation means" is a means for recommending the most suitable second interviewer or assignment for a candidate based on the evaluation results recorded by the recording means.

[1195] An "authentication means" is a means by which a user logs into a dedicated web or mobile app and confirms authentication information to initiate an interactive session with an authenticated user.

[1196] The "notification means" is a means for notifying the administrator of the analysis results and recommendation results.

[1197] The present invention relates to an interview system called "IntelliInterview" that uses generative AI. This system evaluates a candidate's thinking style, personality, facial expressions, and tone of voice in their responses, and recommends the most suitable second interviewer and assignment. Specific embodiments for implementing the present invention are described below.

[1198] The server runs a generative AI method to generate questions for the candidate. This generative AI method uses GPT-4 or an equivalent language model. The generated questions are designed to assess the candidate's thinking style and personality. For example, the generative AI may generate a question such as, "What is the most difficult project you have ever worked on?"

[1199] The generated questions are sent from the server to the terminal, which then presents them to the candidate. The questions can be presented in voice, text, or video format, allowing the candidate to choose the appropriate input method. Specifically, the terminal displays the questions using a web application using HTML5, CSS, and JavaScript.

[1200] Once the candidate enters their answers, the device collects the answer data, which is then sent to a server in an appropriate format, such as MP3 format, using a microphone and a framework such as React Native.

[1201] The server analyzes the collected response data using a generative AI model. This analysis includes speech recognition, sentiment analysis, and content analysis. Google Speech-to-Text API is used for speech recognition, and IBM Watson Tone Analyzer is used for sentiment analysis. This allows the candidate's thinking style, personality, and skill level to be evaluated.

[1202] The evaluation results are recorded in a database by the server using MySQL or PostgreSQL. This data can be used for future re-evaluations and comparisons with other candidates.

[1203] Based on the evaluation results, the server recommends the most suitable second interviewer and assignment for the candidate. For example, it may recommend assignment to the technical department leader or project management department. These recommendations are notified to the system administrator, who then uses the information to select the second interviewer and make appropriate assignment decisions.

[1204] Specific examples are shown below.

[1205] The user (candidate) starts the interview by logging in to a dedicated web app or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[1206] The terminal presents the question received from the server to the user, for example, "What is the most difficult project you have ever undertaken?"

[1207] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[1208] The server analyzes the voice data using a generative AI model, which provides results of speech recognition and sentiment analysis to assess the user's thinking style and personality.

[1209] The evaluation results generated by the generative AI model are recorded in a database by the server, and this data can be used later for reassessment and comparison with other candidates.

[1210] Based on the evaluation results, the server recommends that the employee be assigned to a technical department leader or project management department, and the recommendation is notified to the system administrator.

[1211] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1212] Divide the processing flow of this system's program into processing steps

[1213] Step 1: User authentication

[1214] Step 2: Question generation

[1215] Step 3: Question posing

[1216] Step 4: Collect responses

[1217] Step 5: Response analysis

[1218] Step 6: Evaluation Record

[1219] Step 7: Notification of recommended results

[1220] Explain each processing step in detail

[1221] Step 1: User authentication

[1222] The server authenticates users who access the server using a dedicated web app or mobile app. The user enters their username and password on the login screen. The server checks the information against the database, and if authentication is successful, it generates a session ID and returns it to the user. The input is user information, and the output is the authentication result and session ID. If authentication is successful, an interactive session begins.

[1223] Specific actions

[1224] 1. The user accesses the login screen and enters their username and password.

[1225] 2. The server checks the credentials against a database.

[1226] 3. If authentication is successful, the server generates a session ID and returns it to the user.

[1227] Step 2: Question generation

[1228] The server uses a generative AI model (e.g., GPT-4) to generate questions for the user, which are designed to assess the candidate's thinking style and personality. The input is the session ID, and the output is the generated questions.

[1229] Specific actions

[1230] 1. The server receives the session ID and runs the generative AI model.

[1231] 2. A generative AI model generates questions such as, "What is the most challenging project you have ever worked on?"

[1232] 3. A question is generated and stored on the server.

[1233] Step 3: Question posing

[1234] The generated question is sent from the server to the terminal, which then presents it to the user. The presentation can be in the form of voice, text, or video, and the user can choose the preferred input method. The input is the generated question, and the output is the presented question.

[1235] Specific actions

[1236] 1. The server sends the generated question to the terminal.

[1237] 2. The terminal presents the received question to the user (e.g., by displaying a text message).

[1238] 3. The user chooses the best input method (voice, text, or video).

[1239] Step 4: Collect responses

[1240] The user inputs answers to questions. The device collects the answer data and, in the case of voice input, converts it into an appropriate audio format (e.g., MP3) and sends it to the server. The input is the user's answer data, and the output is the collected answer data.

[1241] Specific actions

[1242] 1. The user speaks their response (e.g., "I worked on a large system migration project last year").

[1243] 2. The device collects the audio data and converts it into the appropriate format.

[1244] 3. The collected data is sent to the server.

[1245] Step 5: Response analysis

[1246] The server analyzes the collected response data using a generative AI model. The analysis includes speech recognition, sentiment analysis, and content analysis. The input is the collected response data, and the output is the analysis results.

[1247] Specific actions

[1248] 1. The server receives the collected response data and begins analysis using the generative AI model.

[1249] 2. Speech recognition (e.g., Google Speech-to-Text API) is performed.

[1250] 3. Sentiment analysis (e.g. IBM Watson Tone Analyzer) is performed and content analysis is carried out.

[1251] 4. The analysis results are obtained and the candidate's thinking style and personality are evaluated.

[1252] Step 6: Evaluation Record

[1253] The server records the analysis results in a database. The input is the analysis results, and the output is the evaluation data recorded in the database.

[1254] Specific actions

[1255] 1. The server receives the analysis results and accesses the database.

[1256] 2. The evaluation results are recorded in a database (e.g., MySQL, PostgreSQL).

[1257] 3. Confirmation of completion of recording will be made.

[1258] Step 7: Notification of recommended results

[1259] The server recommends the most suitable second interviewer and placement for the candidate based on the evaluation results. The recommended results are notified to the administrator. The input is the evaluation results, and the output is a notification of the recommended results.

[1260] Specific actions

[1261] 1. The server analyzes the evaluation results and determines the appropriate second interviewer and placement.

[1262] 2. Recommendations are generated and notified to the administrator.

[1263] 3. Administrators are notified and take necessary action.

[1264] The specific processing contents and operations of each step have been described above.

[1265] (Application example 1)

[1266] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1267] Conventional interview systems require a lot of time and effort when evaluating candidates, and can lack fairness. It is also difficult to accurately evaluate a candidate's characteristics and skills and determine the most appropriate position for the candidate. The present invention aims to solve these problems and provide a system for realizing an efficient and fair interview process.

[1268] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1269] In this invention, the server includes a recognition means for recognizing candidates, a generation AI means, a presentation means for presenting questions generated by the generation AI means, a voice collection means for collecting voice responses, a voice recognition means for converting the collected voice data into text, an evaluation means for evaluating the response data, an analysis means for performing sentiment analysis and text classification from the voice data, a data recording means for recording the evaluation results in an appropriate database, and a recommendation means for recommending the most suitable second interviewer or assignment for the candidate. This makes it possible to quickly and accurately evaluate the characteristics and skills of candidates and automatically recommend the most suitable assignment.

[1270] A "generative AI means" is an artificial intelligence means that automatically generates questions to engage in dialogue with candidates.

[1271] "Presentation means" refers to the means by which the generated questions are presented to the candidate, and may be in the form of audio, text, or video.

[1272] "Collection means" refers to the means used to collect candidate response data.

[1273] "Evaluation means" refers to means for evaluating collected response data, including sentiment analysis and content analysis.

[1274] The "recording means" is a means for accumulating the evaluation results, and records the evaluation results in a database.

[1275] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[1276] "Recognition means" refers to a means for recognizing candidates, such as by facial recognition, to identify candidates.

[1277] "Audio collection means" refers to a means for collecting candidates' audio responses to questions posed.

[1278] "Speech recognition means" refers to means for converting collected voice data into text.

[1279] "Analysis means" refers to means for performing sentiment analysis and text classification from audio data.

[1280] "Data recording means" means for recording the results of the evaluation in an appropriate database.

[1281] System Overview

[1282] This invention applies an interview system using generative AI to the recruitment of factory robots. This system includes a recognition means, a generative AI means, a presentation means, a voice collection means, a voice recognition means, an evaluation means, an analysis means, a data recording means, and a recommendation means. The specific implementation methods for each means, as well as the hardware and software required for them, are described below.

[1283] recognition means

[1284] The server uses a head-mounted display (HMD) with a built-in camera to recognize the candidate's face. For facial recognition, it uses the OpenCV library and the "haarcascade_frontalface_default.xml" model. This recognition method allows the candidate to automatically complete the login process.

[1285] Generation AI means

[1286] The server automatically generates questions to engage in dialogue with candidates using a generative AI model (e.g., GPT-3). The following is a concrete example of a prompt sentence for generating questions:

[1287] "To understand your role and responsibilities here, please tell us about a challenging project you have undertaken that has been relevant to your work."

[1288] Presentation means

[1289] The generated questions are presented to the candidate via the HMD in the form of audio, text, or video. The presentation means can present the questions in an appropriate manner depending on the candidate's selection.

[1290] Audio collection method

[1291] The candidate's voice responses are collected through the HMD's microphone, and the collected voice data is sent to the server in real time.

[1292] Voice recognition means

[1293] The server uses the Google Speech Recognition API to convert the voice data into text, which quickly transcribes the candidate's answers.

[1294] Evaluation and analysis tools

[1295] The server evaluates the textual responses and performs sentiment analysis and text classification using the "transformers" library. For example, sentiment analysis and text classification are performed for:

[1296] Emotion result: {"label": "POSITIVE", "score": 0.98}

[1297] Content result: {"label": "MANAGEMENT_SKILL", "score": 0.87}

[1298] Data Recording Means

[1299] The server records the results of the evaluation in an appropriate database. We use an SQLite database to store the results so that they can be used for later re-evaluation.

[1300] Recommendations

[1301] Based on the evaluation results, the server recommends the best second interviewer or placement for the candidate. For example, a notification recommending placement in a specific department at a factory may be sent to the manager.

[1302] These tools enable the present invention to quickly and accurately assess a candidate's characteristics and skills and automatically recommend the most suitable placement.

[1303] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1304] Step 1:

[1305] The server performs facial recognition of the candidate. It uses the camera built into the HMD and the "haarcascade_frontalface_default.xml" model from the OpenCV library. The input is video data from the camera, and the output is the candidate's identification information. Specifically, the video data is processed in real time, and the facial features are compared with the database to complete the candidate's login.

[1306] Step 2:

[1307] The server generates questions using a generative AI model. The input is a prompt, an example of which is, "To understand your role and responsibilities here, please tell me about a challenging project in your related work." The output is a question to be presented to the candidate. Specifically, the generative AI (e.g., GPT-3) generates an appropriate question based on the prompt and outputs it in text format.

[1308] Step 3:

[1309] The device presents the generated questions to the candidate. The candidate can choose the presentation method from audio, text, or video format. The input is the generated question, and the output is the question presented to the candidate. Specifically, the HMD's display and speaker are used to present the question in the format selected by the candidate.

[1310] Step 4:

[1311] The user answers the questions by voice. The device collects the candidate's voice responses through the microphone built into the HMD. The input is the candidate's voice data, and the output is the collected voice file. Specifically, the microphone collects the voice and transmits it to the server in real time as digital voice data.

[1312] Step 5:

[1313] The server uses the Google Speech Recognition API to convert the voice data into text. The input is the collected voice data, and the output is the converted text data. Specifically, the API analyzes the voice data and converts the voice into text.

[1314] Step 6:

[1315] The server performs sentiment analysis and text classification using the "transformers" library to analyze text data. The input is the transformed text data, and the output is the sentiment analysis results and content classification results. Specifically, it extracts emotions and nuances from the text data and generates classification results.

[1316] Step 7:

[1317] The server records the analysis results in a database. The input is the sentiment analysis results and content classification results, and the output is the evaluation data stored in the database. Specifically, the evaluation data is stored in an SQLite database so that it can be used later for re-evaluation and comparison with other candidates.

[1318] Step 8:

[1319] The server recommends the most suitable second interviewer or assignment for the candidate based on the recorded evaluation data. The input is the recorded evaluation data, and the output is the recommendation result. Specifically, the server analyzes the evaluation data and automatically recommends the most appropriate assignment for the candidate (for example, a specific department in a factory). The recommendation result is notified to the administrator.

[1320] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1321] The present invention relates to an interview system called "IntelliInterview" that uses generative AI, and in particular, it combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. The following describes an embodiment of the present invention.

[1322] System Configuration

[1323] 1. Generation AI means

[1324] The server runs a generative AI program to generate questions to interact with candidates, which are designed to assess their thinking style and personality.

[1325] 2. Presentation means

[1326] The terminal receives questions from the server and presents them to the user (candidate). The questions can be presented in audio, text, or video format, and the user can choose the appropriate input method.

[1327] 3. Emotion Engine

[1328] The server is equipped with an emotion engine for analyzing the user's response data. The emotion engine analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[1329] 4. Collection Method

[1330] When the user enters an answer, the device collects the answer data, converts the collected data into an appropriate format, and sends it to the server. For example, voice data is converted into an appropriate voice format.

[1331] 5. Evaluation Methods

[1332] The server analyzes the collected response data using a generative AI model and an emotion engine. The emotion engine recognizes the user's emotions, and the generative AI model analyzes those emotions and the content of the responses to evaluate the user's thinking style, personality traits, and skill level.

[1333] 6. Recording Method

[1334] The server records the evaluation results in a database. This data can be used later for re-evaluation and comparison with other candidates. The recorded evaluation data can be used for future recruitment strategies and human resource management.

[1335] 7. Recommendations

[1336] Based on the evaluation results, the server recommends the best person for the second interview and the appropriate position for the candidate. For example, it may recommend a technical department leader or a project management department. The recommended results are then notified to the manager.

[1337] Specific examples

[1338] 1. The user starts the interview

[1339] The user begins the interview by logging in to a dedicated web or mobile app. The server authenticates the user, and if the login is successful, the interactive session begins.

[1340] 2. Generative AI presents questions

[1341] The device presents the user with questions received from the server. For example, the generative AI generates a question like, "What is the most difficult project you have ever undertaken?"

[1342] 3. Users respond

[1343] The user responds by voice input, saying, "I was in charge of a large-scale system migration project last year..." The device collects this voice data, converts it into an appropriate voice format, and sends it to the server.

[1344] 4. The emotion engine analyzes the user's responses

[1345] The server analyzes the received voice data using an emotion engine, which analyzes the emotional tone in the voice and determines the emotional state of the user.

[1346] 5. Generative AI analyzes the answers

[1347] The server uses a generative AI model to analyze this voice data. This analysis involves voice recognition and content analysis, and evaluates the user's thinking style and personality. By taking into account the results of the emotion engine, a more accurate evaluation is possible.

[1348] 6. The server records the evaluation results

[1349] The evaluation results generated by the generative AI model and emotion engine are recorded in a database by the server, and this data can be used later for re-evaluation and comparison with other candidates.

[1350] 7. The server recommends candidates for second interviews and placements

[1351] Based on the evaluation results, the server recommends, for example, assigning the candidate to a technical department leader or project management department, and notifies the system administrator of the recommendation.

[1352] As described above, the embodiments of the present invention improve the efficiency and fairness of the conventional interview process, and realize the selection and placement of appropriate personnel. The introduction of the emotion engine provides deeper insights and makes it possible to understand the true characteristics of candidates.

[1353] The processing flow will be explained below.

[1354] Step 1:

[1355] The user accesses a device (PC, smartphone, tablet, etc.) and launches the IntelliInterview System web app or mobile app. The user enters their login information and performs authentication. The server verifies the user's authentication information, and if authentication is successful, transitions the user to the interview session.

[1356] Step 2:

[1357] The server runs a generative AI program to generate initial questions for dialogue with candidates. The generated questions are designed to assess the user's thinking style and personality. The server then sends the initial questions to the terminal.

[1358] Step 3:

[1359] The terminal presents the initial question received from the server to the user in voice, text, or video format, and the user answers the presented question in voice, text, or video format.

[1360] Step 4:

[1361] The user inputs the answer, and the device collects the answer data. For example, in the case of voice input, the device collects the user's voice data and converts it into an appropriate audio format (e.g., WAV, MP3). The device then sends the converted data to the server.

[1362] Step 5:

[1363] The server passes the received response data to the generative AI model and emotion engine, which then analyzes the voice, text, and video data to recognize the user's emotional state (e.g., joy, sadness, fear, anger, etc.).

[1364] Step 6:

[1365] The generative AI model takes into account the user's emotional state and analyzes the content of the voice and text data, which then assesses the user's thinking style, personality traits, and skill level.

[1366] Step 7:

[1367] The server records the evaluation results provided by the generative AI model and emotion engine in a database, which can then be used for later re-evaluation and comparison with other candidates.

[1368] Step 8:

[1369] The server generates additional questions based on the initial evaluation results. The generative AI program designs and generates questions for the user to gain further insight. The server then sends the generated questions to the device.

[1370] Step 9:

[1371] The device presents the user with additional questions received from the server. The user again answers in voice, text, or video format. The device collects the answer data and sends it back to the server. Steps 4 to 7 are then repeated.

[1372] Step 10:

[1373] The server integrates all the evaluation data to create a comprehensive evaluation for the user. The generative AI model and emotion engine then perform the integrated evaluation to generate a consistent final evaluation report.

[1374] Step 11:

[1375] Based on the final evaluation results, the server recommends the best candidate for the second interview and the appropriate assignment for the candidate. The recommendation results are notified to the system administrator or person in charge. For example, based on the evaluation results, it may be recommended that the candidate be assigned to the technical department leader or project management department.

[1376] The above is the specific processing flow of the intelligent interview system combined with an emotion engine. This system utilizes generative AI and an emotion engine to achieve detailed evaluation of candidates, including their emotional state, providing a fairer and more efficient interview process.

[1377] Example 2

[1378] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1379] Conventional interview systems have difficulty taking into account emotional states and nuances of expression when evaluating candidates' thinking styles and personality traits. Furthermore, evaluations by human interviewers are prone to bias and risk lacking fairness. This makes it difficult to select and assign the right talent, impacting companies' recruitment strategies and human resource management.

[1380] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, and a collection means for collecting answer data from the candidates. This makes it possible to analyze the emotional state of the candidates and evaluate their thinking style and personality traits.

[1381] A "generative AI means" is a means that uses an AI model to generate questions to interact with a candidate.

[1382] The "presentation means" is a means for presenting the questions generated by the generation AI means to the candidate.

[1383] "Collection means" refers to the means used to collect candidate response data.

[1384] The "evaluation means" is a means for evaluating the response data collected by the collection means.

[1385] The "recording means" is a means for storing the results of evaluation by the evaluation means.

[1386] "Recommendation measures" are measures for recommending the most suitable second interviewer or placement for a candidate.

[1387] "Emotion analysis means" is a means for analyzing the emotional state of a candidate.

[1388] The present invention relates to "IntelliInterview," an interview system that uses generative AI, and in particular, is a system that combines an emotion engine that recognizes the user's emotions. This system uses the emotion engine to evaluate the candidate's thinking style, personality, and emotions, and recommends the most appropriate second interviewer and assignment. An embodiment of the present invention is described in detail below.

[1389] Server Roles

[1390] The server is a key component of the present invention. The server executes a generative AI means to generate questions for dialogue with candidates. For example, the generative AI means uses GPT-4, a natural language generation model. The following prompt sentences are used to generate questions:

[1391] "Generate creative questions for candidates."

[1392] "Generate questions that ask candidates about difficult situations they've experienced in the past."

[1393] The questions generated by the generation AI means are sent to the terminal by the server. The server then analyzes the candidate's answer data using the emotion analysis means. This emotion analysis means analyzes the candidate's emotional state (e.g., joy, sadness, fear, anger, etc.) from the voice data and text data. For example, the emotion analysis tool of Azure Cognitive Services is used for emotion analysis.

[1394] The server integrates the analytical data obtained from the emotion analysis means and the generation AI means to generate a final evaluation result. The evaluation results are recorded in a database, allowing for future re-evaluation and comparison with other candidates. The server also recommends the most appropriate second interviewer and assignment based on the evaluation results.

[1395] Device Role

[1396] The terminal acts as an interface with the user. It presents the questions received from the server to the user. The presentation method can be text, audio, or video, and the user can choose according to their preference. For example, the generated question "What is the most difficult project you have ever worked on?" is presented to the user.

[1397] When the user enters an answer, the device collects the answer data, converts it into an appropriate data format, and sends it to the server. For example, if the answer is a voice response, the device converts the voice data into WAV or MP3 format and sends it.

[1398] User Roles

[1399] The user starts the interview by logging in to a dedicated web app or mobile app. First, the user enters their ID and password, and is authenticated by the server. If authentication is successful, the user receives questions from the server via their device.

[1400] Users enter answers to questions and send them to the server via their devices. This allows the system to collect data to evaluate the user's thinking style and personality traits. For example, a user might enter an answer like, "I was in charge of a project to introduce a new system last year..."

[1401] As described above, the interview system of the present invention combines generative AI and an emotion analysis engine to evaluate candidate aptitude with high accuracy and recommend optimal placement and second interviewers, thereby improving the efficiency and fairness of the conventional interview process.

[1402] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1403] Step 1:

[1404] The server executes the generative AI means to generate questions. The server passes a prompt (e.g., "Please generate a question to test the candidate's creativity") as input to a generative AI model (e.g., GPT-4). The generative AI model generates a question based on the prompt and outputs the question to the server.

[1405] Step 2:

[1406] The server sends the generated question to the terminal. The server converts the question, which is the output from the generation AI means, into a data format (e.g., text data) and sends it to the terminal. The terminal receives this question and proceeds to the next step.

[1407] Step 3:

[1408] The terminal presents the question to the user. The terminal outputs the question received from the server to the user in voice, text, or video format. For example, the terminal presents the question such as "What is the most difficult project you have ever undertaken?" to the user in voice format.

[1409] Step 4:

[1410] The user answers the question. The user responds to the question by voice, text, or video. For example, the user might say, "The biggest challenge I've ever faced was implementing a new system..."

[1411] Step 5:

[1412] The device collects the answer data and sends it to the server. The device converts the answer data entered by the user into an appropriate format (e.g., voice data into WAV format). After conversion, the device sends this data to the server.

[1413] Step 6:

[1414] The server analyzes the received response data using the emotion analysis means. The server passes input data (e.g., voice data) from the terminal to the emotion analysis means, which analyzes the emotional state (e.g., joy, sadness, fear, anger, etc.). The emotion analysis means outputs the analysis results to the server.

[1415] Step 7:

[1416] The server analyzes the responses using the generation AI. The server passes the output from the emotion analysis means (e.g., emotional state) and input data from the device (e.g., voice data) to the generation AI model. The generation AI model performs text analysis and evaluates the user's thinking style and personality traits from the responses. The evaluation results are output to the server.

[1417] Step 8:

[1418] The server records the evaluation results. The server combines the output data from the generative AI model and the sentiment analysis method to create evaluation data. This evaluation data is recorded in a database, allowing for future re-evaluation and comparison with other candidates.

[1419] Step 9:

[1420] The server notifies the recommended results. Based on the evaluation data, the server recommends the most suitable second interviewer and assignment. For example, it may recommend assignment to the technical department leader or project management department. The recommended results are notified to the manager.

[1421] (Application example 2)

[1422] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1423] Conventional self-driving vehicles lack a system that can evaluate the driver's emotional state and thinking style in real time and provide appropriate advice. As a result, driver fatigue and stress cannot be managed appropriately, resulting in problems with safety and comfort.

[1424] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1425] In this invention, the server includes a generation AI means for engaging in a dialogue with candidates, a presentation means for presenting questions generated by the generation AI means to the candidates, a collection means for collecting answer data from the candidates, an evaluation means for evaluating the answer data collected by the collection means, a recording means for accumulating the results of the evaluation by the evaluation means, a recommendation means for recommending a second interviewer or assignment that is optimal for the candidate, and a means for evaluating the emotions and thinking style of the driver of an autonomous vehicle in real time and providing appropriate advice. This makes it possible to evaluate the emotions and thinking style of the driver in real time and provide appropriate advice.

[1426] A "generative AI means" is an artificial intelligence system that generates questions and advice to engage in dialogue with a candidate (or driver).

[1427] The "presentation means" is a device that displays or audibly presents the questions or advice generated by the generation AI means to the candidate (or driver).

[1428] "Collection means" refers to a device or system for acquiring and storing candidate (or driver) response data.

[1429] The "evaluation means" refers to an algorithm or program for analyzing and evaluating the response data collected by the collection means.

[1430] A "recording means" is a device or system that stores the evaluated results in a database for later re-evaluation and comparison.

[1431] The "recommendation means" is a device or system for providing the candidate with the most suitable second interviewer or assignment, or appropriate advice for the driver, based on the evaluation results.

[1432] An "autonomous vehicle" is a vehicle that is equipped with the capability to drive autonomously with minimal driver intervention.

[1433] "Real-time assessment of emotions and thinking styles" refers to the process of instantly analyzing the driver's emotional state and thinking characteristics and making an assessment based on the current situation.

[1434] "Providing appropriate advice" means making the best suggestions to maintain a safe and comfortable driving environment based on the driver's emotions and thinking style.

[1435] This invention relates to a system that evaluates the driver's emotions and thinking style in real time and provides appropriate advice in autonomous vehicles. This system integrates a generative AI model and an emotion engine, aiming to improve safety and comfort.

[1436] System Configuration

[1437] 1. Generation AI means

[1438] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The generated questions are designed to assess the driver's emotions and thinking style.

[1439] 2. Presentation means

[1440] The device receives questions and advice from the server and presents them to the driver via the in-car display and voice system. For example, the device may ask, "How do you feel while driving?"

[1441] 3. Collection Method

[1442] The device collects the driver's voice responses via a microphone, converts them into an appropriate voice format, and sends them to a server. It also uses a camera to capture the driver's facial expressions for sentiment analysis.

[1443] 4. Evaluation Methods

[1444] The server analyzes the collected audio and video data using an emotion engine, which determines the driver's emotional state, and the generative AI model evaluates the driver's thinking style based on the responses and facial expressions.

[1445] 5. Recording Method

[1446] The evaluation results are stored in a database by the server and can be used later for re-evaluation, comparison with other drivers, and analysis of driving habits.

[1447] 6. Recommendations

[1448] The server then provides appropriate advice to the driver based on the evaluation results. For example, if the driver responds, "I'm a little tired," the system will suggest, "The next rest point is 5km away. Would you like to take a break?"

[1449] Hardware or software used

[1450] Hardware:

[1451] Microphone: Used to collect driver voice input.

[1452] Camera: Used to analyze the driver's facial expressions.

[1453] Display or audio system: Used to present questions and advice.

[1454] software:

[1455] SpeechRecognition: Used to convert speech to text.

[1456] OpenCV: Used to process camera footage.

[1457] Transformers (Hugging Face): Used for sentiment analysis using the BERT model.

[1458] Specific examples

[1459] Example prompt sentence:

[1460] The question posed is, "How do you feel about your recent work progress?"

[1461] If the driver answers, "I'm under pressure and a little tired," the system analyzes their emotions in real time and provides advice such as, "It's important to take enough rest. I recommend you take a coffee break in five minutes."

[1462] In this way, a system that combines a generative AI model and an emotion engine can evaluate the driver's state in real time in an autonomous vehicle and provide appropriate advice, thereby reducing driver fatigue and stress and improving safety.

[1463] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1464] Step 1:

[1465] The server runs a generative AI program to generate questions and advice for dialogue with the driver. The input is the driver's previous data and existing data in the system, and the output is the generated questions and advice. Based on the generated questions, the server creates prompt sentences to ask the driver.

[1466] Step 2:

[1467] The terminal presents the driver with questions and advice received from the server. The input is what the server produces, and the output is what the driver sees or hears on the display or audio system. For example, the question "How do you feel while driving?" is displayed on the display.

[1468] Step 3:

[1469] The user (driver) answers the presented questions by voice. The input is the question presented by the terminal, and the output is the driver's voice response. Drivers often respond by saying, "I'm a little tired today."

[1470] Step 4:

[1471] The terminal collects the driver's voice response through a microphone and converts it into an appropriate voice format. The input is the driver's voice data, and the output is the data converted into voice format. This voice data is then sent to the server.

[1472] Step 5:

[1473] The device uses a camera to capture the driver's facial expressions and collects the data in real time. The input is the camera image, and the output is facial expression data. This data is also sent to the server.

[1474] Step 6:

[1475] The server uses an emotion engine to analyze the collected audio and video data. The input is audio data and facial expression data, and the output is an analysis result that indicates the driver's emotional state. Specifically, it determines whether the driver feels "a little tired" by analyzing the tone of the voice and recognizing facial expressions.

[1476] Step 7:

[1477] The server uses a generative AI model to evaluate the driver's responses and emotional state. The input is the voice transcript and emotion analysis results, and the output is an assessment of the driver's thinking style and personality traits. For example, the driver may be assessed as "stressed."

[1478] Step 8:

[1479] The server stores the evaluation results in a database. The input is the evaluation results, and the output is the stored data, which can later be used for re-evaluation and comparison with other drivers.

[1480] Step 9:

[1481] Based on the evaluation results, the server generates appropriate advice for the driver and sends it to the terminal. The input is the evaluation result, and the output is the generated advice. For example, a suggestion might be generated: "The next rest point is 5 km away. Would you like to take a break?"

[1482] Step 10:

[1483] The terminal presents the advice received from the server to the driver. The input is the generated advice, and the output is the driver's behavior after receiving the advice. The driver is prompted to decide whether to take a break.

[1484] 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.

[1485] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[1486] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1487] 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.

[1488] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1489] 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.

[1490] 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).

[1491] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1492] 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."

[1493] 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.

[1494] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1495] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1500] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] The following is further disclosed regarding the above embodiment.

[1506] (Claim 1)

[1507] a generative AI means for interacting with candidates;

[1508] a presentation means for presenting the questions generated by the generation AI means to the candidate;

[1509] a collection means for collecting candidate response data;

[1510] evaluation means for evaluating the response data collected by the collection means;

[1511] a recording means for storing the results of the evaluation by the evaluation means;

[1512] Recommendations for the best second interviewer or placement for the candidate;

[1513] A system including:

[1514] (Claim 2)

[1515] Provide a means for collecting candidate response data in audio, text, or video format;

[1516] 10. The system of claim 1.

[1517] (Claim 3)

[1518] The generating AI means comprises means for analyzing the candidate's emotions and expression nuances and for evaluating their thinking style and personality traits;

[1519] 10. The system of claim 1.

[1520] "Example 1"

[1521] (Claim 1)

[1522] a generative AI means for interacting with candidates;

[1523] a presentation means for presenting the questions generated by the generation AI means to the candidate;

[1524] a collection means for collecting candidate response data in audio, text, or video format;

[1525] evaluation means for analyzing the response data collected by the collection means;

[1526] a recording means for recording the results of the evaluation by the evaluation means in a database;

[1527] Recommendation measures to recommend the best second interviewer or placement for the candidate based on the evaluation results;

[1528] authentication means for initiating an interactive session with an authenticated user;

[1529] a notification means for notifying an administrator of the analysis results;

[1530] A system including:

[1531] (Claim 2)

[1532] means for evaluating the candidate's response data by means of speech recognition, sentiment analysis, and content analysis;

[1533] 10. The system of claim 1.

[1534] (Claim 3)

[1535] The generating AI means generates questions based on the prompt sentence and includes means for evaluating the user's thinking style and personality traits.

[1536] 10. The system of claim 1.

[1537] "Application Example 1"

[1538] (Claim 1)

[1539] a generative AI means for interacting with candidates;

[1540] a presentation means for presenting the questions generated by the generation AI means to the candidate;

[1541] a collection means for collecting candidate response data;

[1542] evaluation means for evaluating the response data collected by the collection means;

[1543] a recording means for storing the results of the evaluation by the evaluation means;

[1544] Recommendations for the best second interviewer or placement for the candidate;

[1545] recognition means for recognizing candidates;

[1546] a voice collecting means for collecting voice responses to the questions presented by the presenting means;

[1547] a voice recognition means for converting the voice data collected by the voice collection means into text;

[1548] analysis means for performing sentiment analysis and text classification from the speech data by the evaluation means;

[1549] data recording means for recording the results of the candidate's evaluation in an appropriate database;

[1550] A system including:

[1551] (Claim 2)

[1552] providing a means for collecting candidate response data in audio, text, or video format;

[1553] 10. The system of claim 1.

[1554] (Claim 3)

[1555] The generating AI means comprises means for analyzing the candidate's emotions and expression nuances and for evaluating their thinking style and personality traits;

[1556] 10. The system of claim 1.

[1557] "Example 2: Combining Emotion Engines"

[1558] (Claim 1)

[1559] a generative AI means for interacting with candidates;

[1560] a presentation means for presenting the questions generated by the generation AI means to the candidate;

[1561] a collection means for collecting candidate response data;

[1562] evaluation means for evaluating the response data collected by the collection means;

[1563] a recording means for storing the results of the evaluation by the evaluation means;

[1564] Recommendations for the best second interviewer or placement for the candidate;

[1565] emotion analysis means for analyzing the emotional state of the candidate;

[1566] A system including:

[1567] (Claim 2)

[1568] 10. The system of claim 1, comprising means for collecting candidate response data in the form of audio, text, or video.

[1569] (Claim 3)

[1570] 10. The system of claim 1, wherein the generative AI means comprises means for analyzing the candidate's emotions and expressive nuances and assessing their thinking style and personality traits.

[1571] "Application example 2 when combining emotion engines"

[1572] (Claim 1)

[1573] a generative AI means for interacting with candidates;

[1574] a presentation means for presenting the questions generated by the generation AI means to the candidate;

[1575] a collection means for collecting candidate response data;

[1576] evaluation means for evaluating the response data collected by the collection means;

[1577] a recording means for storing the results of the evaluation by the evaluation means;

[1578] Recommendations for the best second interviewer or placement for the candidate;

[1579] A means for evaluating the emotions and thinking style of drivers in autonomous vehicles in real time and providing appropriate advice;

[1580] A system including:

[1581] (Claim 2)

[1582] 10. The system of claim 1, comprising means for collecting candidate response data in the form of audio, text, or video.

[1583] (Claim 3)

[1584] 10. The system of claim 1, wherein the generative AI means comprises means for analyzing the candidate's emotions and expressive nuances and assessing their thinking style and personality traits. [Explanation of symbols]

[1585] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a generative AI means for interacting with candidates; a presentation means for presenting the questions generated by the generation AI means to the candidate; a collection means for collecting candidate response data; evaluation means for evaluating the response data collected by the collection means; a recording means for storing the results of the evaluation by the evaluation means; Recommendations for the best second interviewer or placement for the candidate; A system including:

2. Provide a means for collecting candidate response data in audio, text, or video format; The system of claim 1 .

3. The generating AI means comprises means for analyzing the candidate's emotions and expression nuances and for evaluating their thinking style and personality traits; The system of claim 1 .

Images