System

Abstract

A system is provided.SOLUTION: A system, comprising: means for a user to input login information; means for a server to authenticate the login information of the user; means for the server to generate a question list based on application positions of the user; means for the user to input answers to the question list; means for the server to pass the user's answers to a generating AI for evaluation; means for the server to store evaluation results of the generating AI in a database; and means for the server to notify the user of the evaluation results.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] The problem with the traditional recruitment process is that it relies heavily on the interviewer's personal opinions and subjectivity, making recruitment standards unstable. This creates the risk of missing out on talented candidates or creating mismatches, which can undermine the efficiency and fairness of recruitment. Furthermore, recruitment is costly, and this burden can become particularly heavy for large companies. It is necessary to resolve these issues and introduce quantitative and efficient recruitment standards. [Means for solving the problem]

[0005] The present invention is a system that includes a means for a user to input login information, a means for a server to authenticate the user's login information, a means for the server to generate a list of questions based on the position the user is applying for, a means for the user to input answers to the list of questions, a means for the server to pass the user's answers to a generation AI for evaluation, a means for the server to store the evaluation results by the generation AI in a database, a means for the server to notify the user of the evaluation results, and a means for the server to integrate all interview data and generate a report to be provided to the final interviewer. This system eliminates interviewer subjectivity and enables evaluation based on unified quantitative standards. As a result, it is possible to streamline the hiring process, reduce costs, and even conduct fair personnel evaluations.

[0006] "User information" refers to information that includes a user's identification information, application-related data, and authentication information.

[0007] A "server" is a computing system that receives, processes, stores, and communicates with other devices and systems.

[0008] "Login information" refers to information used to authenticate a user, such as a user ID and password.

[0009] A "question list" is a set of questions to ask a user that is generated based on the position the user is applying for.

[0010] "Generative AI" is a system that uses artificial intelligence technology to evaluate user answers.

[0011] "Evaluation results" refers to the scores and feedback calculated after the generation AI analyzes the user's answers.

[0012] A "database" is a system for organizing, storing, and managing data efficiently and securely.

[0013] A "final interviewer" is the person who makes the final decision in the interview process.

[0014] A "report" is a document that consolidates the data obtained throughout the interview process and is provided to the final interviewer. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a human resource recruitment evaluation system that uses generative AI. This system automates the entire interview process and eliminates the subjectivity of interviewers by conducting quantitative evaluations, thereby reducing the risk of mismatch and improving the efficiency of recruitment.

[0037] System Overview

[0038] 1. User login

[0039] The terminal displays a login screen to the user, and the user enters their ID and password.

[0040] The server receives the login information and checks it against the data stored in the database.

[0041] After successful authentication, the server generates a session ID and sends it back to the terminal.

[0042] 2. Question list generation and presentation

[0043] The server generates an appropriate list of questions based on the user's applied position information.

[0044] The terminal displays the generated list of questions to the user.

[0045] 3. Enter and submit your answers

[0046] The user inputs answers to the questions and presses the send button.

[0047] The terminal transmits the inputted answer to the server.

[0048] 4. Evaluation by generative AI

[0049] The server passes the received answer to the generative AI model.

[0050] The generative AI analyzes the answers based on past learning data and calculates a score for each question.

[0051] The server stores the evaluation results of the generated AI in a database.

[0052] 5. Notification of evaluation results

[0053] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0054] The terminal displays the evaluation results to the user.

[0055] 6. Integration of final interview data

[0056] The server consolidates all process data and generates a report for the final interviewer.

[0057] The server sends the report to the terminal of the final interviewer.

[0058] Specific examples

[0059] 1. User login

[0060] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[0061] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[0062] The terminal retains the received session ID for the user and displays the dashboard.

[0063] 2. Question list generation and presentation

[0064] The server recognizes that the user is applying for a position as a "Software Engineer."

[0065] The server generates a list of questions for software engineers and sends it to the terminal.

[0066] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[0067] 3. Enter and submit your answers

[0068] The user enters an answer to the question and presses the submit button. For example, the user enters "I have been involved in developing web applications in the past..."

[0069] The device sends the response in JSON format to the server.

[0070] 4. Evaluation by generative AI

[0071] The server inputs the received answers into the generation AI.

[0072] The generating AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100."

[0073] The server stores the generated scores in a database.

[0074] 5. Notification of evaluation results

[0075] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0076] The device displays to the user, "Your rating score is 85 / 100."

[0077] 6. Integration of final interview data

[0078] The server consolidates all interview process data and generates a report for the final interview page.

[0079] The server sends the report to the terminal of the final interviewer.

[0080] This system automates all steps from user application to evaluation, enabling efficient and fair recruitment.

[0081] The processing flow will be explained below.

[0082] Step 1:

[0083] The user enters their ID and password on the login screen and clicks the "Login" button.

[0084] Step 2:

[0085] The device sends the entered ID and password to the server.

[0086] Step 3:

[0087] The server checks the received ID and password against the user information in the database.

[0088] Step 4:

[0089] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[0090] Step 5:

[0091] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[0092] Step 6:

[0093] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[0094] Step 7:

[0095] The server sends the generated question list to the terminal.

[0096] Step 8:

[0097] The terminal displays the received list of questions to the user, allowing the user to input answers.

[0098] Step 9:

[0099] The user enters answers to each question and clicks the submit button.

[0100] Step 10:

[0101] The device sends the user's answer in JSON format to the server.

[0102] Step 11:

[0103] The server validates the response it receives to ensure there is no missing or incorrect data.

[0104] Step 12:

[0105] The server passes the verified answer data to the generative AI model.

[0106] Step 13:

[0107] The generative AI analyzes the answers it receives and calculates a score for each question.

[0108] Step 14:

[0109] The generated AI returns the calculated score to the server.

[0110] Step 15:

[0111] The server stores the scores received from the generated AI in a database.

[0112] Step 16:

[0113] The server converts the saved score data into a format that can be notified to the user and transmits it to the terminal.

[0114] Step 17:

[0115] The device displays the evaluation result to the user, for example, "Your overall score is 85 / 100."

[0116] Step 18:

[0117] The server consolidates all interview process data to generate a report for the final interview.

[0118] Step 19:

[0119] The server sends the generated report to the terminal of the final interviewer.

[0120] Step 20:

[0121] The final interviewer will make the final decision based on the report provided.

[0122] Example 1

[0123] 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."

[0124] Conventional recruitment evaluation systems have the problem that the interviewer's subjectivity is easily involved, making it difficult to achieve fair evaluations. Furthermore, the interview process is conducted manually, which reduces recruitment efficiency and increases the risk of mismatches. Furthermore, the management of applicant responses and notification of evaluation results are not centralized, making the entire process cumbersome.

[0125] 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.

[0126] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; a means for the terminal to display a login screen to the user and prompt the user to input an ID and password; a means for the server to generate a session ID and send it back to the terminal if authentication is successful; and a means for the server to send the answers entered by the user to the server in JSON format. This enables automation of the interview process, fair evaluation, and efficient management.

[0127] A "user" is an individual or organization that uses the system, and is primarily responsible for entering login information and answering questions on the questionnaire.

[0128] A "terminal" is a device operated by a user, and is used to display a login screen and a list of questions and to send answers to a server.

[0129] The "server" is the central control device of the system, and is a device that authenticates user login information, generates a list of questions, evaluates answers, notifies users of the evaluation results, and integrates data.

[0130] "Login information" refers to authentication information for a user to access a system, and is usually composed of a user ID and password.

[0131] A "session ID" is a unique identifier generated by the server when a user logs in to the system, and is used to manage the login session.

[0132] A "question list" is a set of questions generated by the server based on the user's application for a position, and used to evaluate the user's skills and experience.

[0133] "Generative AI" is an artificial intelligence model that analyzes user responses and provides quantitative evaluations.

[0134] "Database" means a data management system for the server to store assessment results and other interview process data.

[0135] A "report" is a document that is generated by the server by integrating all interview data and provided to the final interviewer, and includes the user's evaluation results and the like.

[0136] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight data exchange format for concisely expressing data structures, and is primarily used to exchange data between servers and terminals.

[0137] This invention is a human resource recruitment evaluation system that uses a generative AI model. This system automates the entire interview process and eliminates the subjectivity of interviewers by performing quantitative evaluations, thereby reducing the risk of mismatch and improving recruitment efficiency. Below, we will explain in detail each element that makes up this system.

[0138] System configuration

[0139] This system operates through the mutual cooperation of three entities: the server, the terminal, and the user.

[0140] Server: The central control unit of the system, which performs major processes such as login authentication, question list generation, calculation and storage of evaluation results, and data integration.

[0141] Terminal: A device operated by the user that presents a list of questions, allows users to input answers, and displays evaluation results.

[0142] User: An applicant who uses the system and is the entity that enters login information and answers the questionnaire.

[0143] This system uses the following technical elements:

[0144] Generative AI model: An artificial intelligence model that analyzes input answers and makes a quantitative evaluation.

[0145] Database: Data storage for saving assessment results and interview process data.

[0146] Hardware and Software Configuration

[0147] 1. Login Process

[0148] The terminal displays a login screen to the user, and the user enters their ID and password. The terminal sends this to the server, which collates it with the information stored in the database. If the collation is successful, the server generates a session ID and sends it back to the terminal. Using this session ID, the user can access the system.

[0149] 2. Question list generation and presentation

[0150] The server retrieves the user's application position information from the database and generates a list of questions based on the information, which is then sent to the terminal and displayed to the user.

[0151] 3. Enter and submit your answers

[0152] The user enters answers to the questions and presses the submit button. The terminal sends the answers in JSON format to the server. For example, in response to the question "Tell us about your past project experience," the user enters "I have been in charge of developing web applications in the past."

[0153] 4. Evaluation Process

[0154] The server passes the received answer to the generative AI model for analysis. The generative AI model calculates a score for the user's answer based on past learning data. For example, a score of "Project management skills: 80 / 100" may be generated. The server stores this evaluation result in a database.

[0155] 5. Notification of evaluation results

[0156] The server converts the evaluation results into a format suitable for the user and sends it to the terminal. The terminal displays the results to the user. For example, it displays "Your evaluation score is 85 / 100."

[0157] 6. Integration of final interview data

[0158] The server aggregates all interview data and generates a report for the final interviewer, which is sent to the final interviewer's terminal.

[0159] Specific examples

[0160] Example prompt sentence:

[0161] "Tell me about your past project experience."

[0162] "What skills can you best contribute to this position?"

[0163] Tell us about your experience as a team leader.

[0164] Using these technologies and processes, the system automates all steps from users' applications to evaluations, enabling efficient and fair recruitment.

[0165] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0166] Step 1: User Login

[0167] 1. The device displays a login screen to the user.

[0168] Input: User ID and password

[0169] Output: Display of input form

[0170] Specific behavior: The device renders the HTML of the login screen and displays it to the user.

[0171] 2. The user enters their ID and password and presses the "Login" button.

[0172] Input: User ID (e.g., "user123") and password (e.g., "password123")

[0173] Output: Authentication request from device to server

[0174] Specific Action: The user enters data into the input fields and clicks the submit button.

[0175] 3. The device sends the login information entered by the user to the server.

[0176] Input: User ID and password

[0177] Output: Authentication request to the server (JSON format)

[0178] Specific operation: The device sends login information in JSON format to the server.

[0179] 4. The server checks the received login information against its database.

[0180] Input: Login information (user ID and password)

[0181] Output: Authentication result (success or failure)

[0182] Specific operation: The server queries the database to check whether the entered user ID and password match.

[0183] 5. If authentication is successful, the server generates a session ID and sends it back to the terminal.

[0184] Input: Authentication successful

[0185] Output: Session ID (e.g. "abc123")

[0186] Specific operation: The server generates a session ID and sends it to the terminal.

[0187] 6. The device retains the received session ID and displays the dashboard.

[0188] Input: Session ID

[0189] Output: Dashboard screen

[0190] Specific operation: The device saves the session ID in local storage and displays the user dashboard.

[0191] Step 2: Generate and present a list of questions

[0192] 1. The server retrieves the user's application position information from the database.

[0193] Input: User ID

[0194] Output: Position information (e.g. "Software Engineer")

[0195] Specific operation: The server queries the database to obtain information about the user's applied position.

[0196] 2. The server generates a list of questions based on the position applied for.

[0197] Input: Position information

[0198] Output: Question list (e.g. "Tell me about your past project experience")

[0199] Specific operation: The server dynamically generates a list of questions from a question template according to the position being applied for.

[0200] 3. The server sends the generated question list to the terminal.

[0201] Input: Question List

[0202] Output: Data sent to the terminal (JSON format)

[0203] Specific operation: The server sends the generated question list to the terminal in JSON format.

[0204] 4. The terminal displays the received list of questions to the user.

[0205] Input: Question List

[0206] Output: Question list screen

[0207] Specific operation: The terminal renders the question list in HTML format and displays it to the user.

[0208] Step 3: Enter and submit your answers

[0209] 1. The user enters answers to the questions and presses the submit button.

[0210] Input: Answer (e.g., "I have worked on web application development in the past")

[0211] Output: Input data to the terminal

[0212] Specific action: The user enters an answer to a question in the text field and clicks the submit button.

[0213] 2. The device sends the entered answer in JSON format to the server.

[0214] Input: Answer content (JSON format)

[0215] Output: Data sent to the server

[0216] Specific operation: The device converts the response into JSON format and sends it to the server.

[0217] Step 4: Evaluation by generative AI

[0218] 1. The server inputs the received answers into a generative AI model.

[0219] Input: Answer (e.g., "I have worked on web application development in the past")

[0220] Output: Input data to a generative AI model

[0221] Specific operation: The server passes the answer data to the generative AI model.

[0222] 2. The generative AI analyzes the answers and calculates a score for each question.

[0223] Input: Answer

[0224] Output: Score (e.g. "Project Management Skills: 80 / 100")

[0225] Specific operation: The generative AI model analyzes the answers and calculates an evaluation score based on the training data.

[0226] 3. The server stores the generated scores in a database.

[0227] Input: Score

[0228] Output: Data saved to database

[0229] Specific operation: The server saves the score data in a database.

[0230] Step 5: Notification of evaluation results

[0231] 1. The server converts the evaluation results into a format that can be notified to the user.

[0232] Input: Score

[0233] Output: Notification data (e.g. "Your rating score is 85 / 100")

[0234] Specific operation: The server converts the score data into a format that can be notified to the user.

[0235] 2. The server sends the converted evaluation results to the terminal.

[0236] Input: Notification data

[0237] Output: Data sent to the terminal

[0238] Specific operation: The server sends notification data in JSON format to the device.

[0239] 3. The device displays the evaluation results to the user.

[0240] Input: Notification data

[0241] Output: Evaluation result screen

[0242] Specific operation: The device renders the notification data in HTML format and displays it to the user.

[0243] Step 6: Consolidating the final interview data

[0244] 1. The server aggregates all the interview data.

[0245] Input: Interview process data

[0246] Output: Integrated data

[0247] Specific operation: The server analyzes multiple interview data sets and creates a single integrated dataset.

[0248] 2. The server generates a report for the final interviewer.

[0249] Input: Integrated data

[0250] Output: Report (e.g. "Comprehensive report of user rating scores")

[0251] Specific operation: The server generates a report for the final interviewer based on the integrated data.

[0252] 3. The server sends the generated report to the terminal of the final interviewer.

[0253] Input: Report

[0254] Output: Report data sent to the terminal

[0255] Specific operation: The server sends the report in JSON format to the terminal and displays it on the terminal of the final interviewer.

[0256] The above is the specific flow of program processing in the present invention.

[0257] (Application example 1)

[0258] 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."

[0259] Conventional methods for evaluating the skills of factory workers require a lot of time and effort, and are heavily influenced by the evaluator's subjectivity, resulting in problems with the fairness and efficiency of the evaluation. In particular, artificial bias in evaluations and a lack of consistency in evaluation criteria hinder worker motivation and appropriate personnel allocation. This makes it difficult to design training plans and determine optimal personnel allocation.

[0260] 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.

[0261] In this invention, the server includes a means for a user to input login information, a means for the server to authenticate the user's login information, a means for the server to generate a list of questions based on the user's role, a means for the user to input answers to the list of questions, a means for the server to pass the user's answers to a generative AI model for evaluation, a means for the server to store the evaluation results by the generative AI model in a database, a means for the server to notify the user of the evaluation results, and a means for the server to integrate all evaluation data and generate a report to be provided to a manager. This enables efficient and fair evaluation of the skills of workers in a factory, enabling appropriate personnel allocation and the creation of training plans.

[0262] A "user" is a worker or operator who has access to the system, enters answers to a questionnaire, and is evaluated.

[0263] "Login information" refers to the authentication information required for a user to access a system, and is usually composed of a user ID and password.

[0264] "Server" refers to a device or software that processes and manages data for the entire system.

[0265] A "question list" is a set of questions for skill evaluation that is created by the server based on the user's role and work responsibilities.

[0266] A "generative AI model" is an artificial intelligence model that analyzes user responses based on past learning data and generates quantitative evaluation results.

[0267] "Database" means a digital data storage device for storing all evaluation data and login information for the System.

[0268] "Evaluation results" refer to scores such as skills and work efficiency calculated by the generative AI model by analyzing the user's responses.

[0269] A "report" is a written or digital document that the server generates to consolidate all evaluation data and provide to an administrator.

[0270] "Authentication" is the process by which a server receives a user's login information and verifies the user's legitimacy by checking it against information in a database.

[0271] "JSON format" is a structured data format for exchanging user responses, and is an abbreviation for JavaScript Object Notation.

[0272] This invention is an efficient and fair evaluation system that improves on the conventional method of evaluating the skills of factory workers. The system begins with the user entering login information, which is authenticated by the server, and then evaluates the user's skills using a generative AI model. The evaluation results are stored in a database and provided to managers as a report.

[0273] The server uses Flask (a Python web framework) to authenticate the login information of workers and operators when they access the system. This login information mainly consists of a user ID and password. If authentication is successful, the server generates a session ID and sends it to the user's terminal.

[0274] The server then generates a questionnaire based on the logged-in user's role and responsibilities, tailored to the user's specific tasks and skill set, and displays the questionnaire on a smartphone, tablet, or other device.

[0275] When a user enters answers into the question list, the answers are sent to the server in JSON format. The server then passes the received answers to the generative AI model, which analyzes them based on past learning data. As a result of the analysis, a score is calculated based on the user's skills, work efficiency, etc.

[0276] The generated evaluation results are stored in a database, and the server notifies the user. The evaluation result notification allows users to check their own skill evaluation and use it for future training and self-improvement. The server also consolidates all evaluation data to generate a report and provides it to managers. This allows managers to understand the skill status of their workers and design appropriate personnel assignments and training plans.

[0277] A specific example of this system is shown below.

[0278] Specific examples

[0279] 1. Log in:

[0280] The user enters "user123" and "password123" on the tablet and presses the login button.

[0281] The server authenticates the login information, generates a session ID "session_1234", and sends it to the terminal.

[0282] 2. Generate a list of questions:

[0283] The server recognizes the user's role as a "parts assembler" and generates an appropriate list of questions.

[0284] For example, questions such as "Tell us about your work environment recently" and "What was the most difficult task you had in the past week?" will be displayed.

[0285] 3. Enter and submit your answers:

[0286] The user answers the questions by typing "The working environment was comfortable" and "The most difficult task during the week was assembling the cooling device," and then presses the send button.

[0287] The device sends the entered answer in JSON format to the server.

[0288] 4. Generative AI evaluation:

[0289] The server analyzes the answers it receives using a generative AI model to generate scores such as "Skill evaluation: 90 / 100, work efficiency: 85 / 100."

[0290] 5. Notification of evaluation results:

[0291] The server sends the evaluation results to the terminal and displays to the user, "Your evaluation scores are skill rating 90 / 100 and work efficiency 85 / 100."

[0292] 6. Generate the final report:

[0293] The server consolidates all the evaluation data and generates reports for administrators, who can use these reports to design appropriate training plans.

[0294] This system will enable efficient and fair evaluation of the skills of workers within factories, leading to appropriate staffing and training.

[0295] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0296] Step 1:

[0297] The server authenticates the user's login information. The user enters their user ID and password into the login screen on a device such as a tablet and submits it. The server receives the submitted information and compares it with the information in its database. If authentication is successful, the server generates a session ID and submits it to the user's device. This session ID is used to identify the user in subsequent processes.

[0298] Input: User ID, Password

[0299] Output: Session ID

[0300] Step 2:

[0301] The server generates a questionnaire based on the role of the logged-in user. After the user is properly authenticated, the server retrieves the user's role (e.g., parts assembly worker) from the database. Then, it generates a questionnaire appropriate for the user's role and sends it to the terminal. The user's terminal displays this questionnaire.

[0302] Input: Session ID, User Role

[0303] Output: Question list

[0304] Step 3:

[0305] The user enters answers to the presented list of questions and sends them from the device to the server. The user enters answers to the questions using a tablet or smartphone and presses the send button. The device sends the entered answers in JSON format to the server.

[0306] Input: Question list, user answers

[0307] Output: JSON formatted response data

[0308] Step 4:

[0309] The server passes the received answers to the generative AI model for evaluation. The server inputs the JSON-formatted answer data received from the user into the generative AI model and requests analysis. The generative AI model analyzes the user's answers based on past learning data and calculates scores for skill and work efficiency.

[0310] Input: JSON formatted response data

[0311] Output: Evaluation score (e.g., skill rating 90 / 100, work efficiency 85 / 100)

[0312] Step 5:

[0313] The server saves the evaluation results from the generative AI model in a database and notifies the user. The generated evaluation results are saved in a database by the server. The server then sends the evaluation results to the user's device, where the user can check the displayed score.

[0314] Input: Rating score

[0315] Output: Notify user, save to database

[0316] Step 6:

[0317] The server consolidates all the evaluation data and generates a report to be provided to the manager. The server aggregates and consolidates the evaluation data of multiple users. It then generates a report that allows the manager to grasp the overall status of workers in the factory and sends it to the manager's terminal. The manager can use this report to optimize training plans and personnel deployment.

[0318] Input: A set of evaluation data

[0319] Output: Report for administrator

[0320] 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.

[0321] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system authenticates the user's login information, generates a list of questions based on the position being applied for, and analyzes the user's answers and emotions. The analysis results are stored in a database as evaluation results and reflected in a report provided to the final interviewer.

[0322] System Overview

[0323] 1. User login

[0324] The terminal displays a login screen to the user, and the user enters their ID and password.

[0325] The server receives the login information and checks it against a database.

[0326] After successful authentication, the server generates a session ID and sends it back to the terminal.

[0327] 2. Question list generation and presentation

[0328] The server generates a list of questions based on the user's applied position information.

[0329] The terminal displays the generated list of questions to the user.

[0330] 3. Enter and submit answers and emotion data

[0331] The user enters answers into the question list and presses the submit button.

[0332] The device sends the input answer and emotion data to the server.

[0333] 4. Evaluation using generative AI and emotion engine

[0334] The server passes the received answer to the generation AI.

[0335] The emotion engine analyzes the emotions from the voice and text of the user's responses.

[0336] The generating AI evaluates the answers and analyzed emotional data and calculates a score.

[0337] The server stores the evaluation results from the generation AI and emotion engine in a database.

[0338] 5. Notification of evaluation results

[0339] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0340] The terminal displays the evaluation results to the user.

[0341] 6. Integration of final interview data

[0342] The server consolidates all process data and generates a report for the final interviewer.

[0343] The server sends the report to the terminal of the final interviewer.

[0344] Specific examples

[0345] 1. User login

[0346] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[0347] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[0348] The terminal retains the received session ID and displays the dashboard.

[0349] 2. Question list generation and presentation

[0350] The server recognizes that the user is applying for a position as a "Software Engineer."

[0351] The server generates a list of questions for software engineers and sends it to the terminal.

[0352] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[0353] 3. Enter and submit answers and emotion data

[0354] The user answers the question by saying, "I have worked on developing web applications in the past..."

[0355] The emotion engine analyzes the user's voice and text and generates emotion data.

[0356] The device sends the user's answers and emotion data in JSON format to the server.

[0357] 4. Evaluation using generative AI and emotion engine

[0358] The server inputs the answers and emotional data into the generation AI.

[0359] The generating AI analyzes the answers and generates a score such as "Project management skills: 80 / 100."

[0360] The emotion engine passes the analyzed emotion data to the generation AI.

[0361] The server stores the generated scores and emotion data in a database.

[0362] 5. Notification of evaluation results

[0363] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0364] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[0365] 6. Integration of final interview data

[0366] The server consolidates all interview process data and generates a report for the final interview page.

[0367] The server sends the report to the terminal of the final interviewer.

[0368] This system achieves more accurate and fair evaluation of personnel by combining the user's responses with their emotions.

[0369] The processing flow will be explained below.

[0370] Step 1:

[0371] The user enters their ID and password on the login screen and clicks the "Login" button.

[0372] Step 2:

[0373] The device sends the entered ID and password to the server.

[0374] Step 3:

[0375] The server checks the received ID and password against the user information in the database.

[0376] Step 4:

[0377] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[0378] Step 5:

[0379] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[0380] Step 6:

[0381] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[0382] Step 7:

[0383] The server sends the generated question list to the terminal.

[0384] Step 8:

[0385] The terminal displays the received list of questions to the user, allowing the user to input answers.

[0386] Step 9:

[0387] The user enters answers to each question and clicks the submit button.

[0388] Step 10:

[0389] When the user inputs something, the emotion engine analyzes the audio and video to detect the user's emotional state.

[0390] Step 11:

[0391] The emotion engine generates emotion analysis data and transmits the data to the server.

[0392] Step 12:

[0393] The device sends the user's answer in JSON format to the server.

[0394] Step 13:

[0395] The server receives the response data and emotion data and validates both data to check for missing or inappropriate data.

[0396] Step 14:

[0397] The server passes verified response data and emotion data to the generative AI model.

[0398] Step 15:

[0399] The generative AI analyzes the answers it receives and calculates a score for each question.

[0400] Step 16:

[0401] The generative AI calculates an overall score or rating that takes emotional data into account.

[0402] Step 17:

[0403] The generated AI returns the calculated score to the server.

[0404] Step 18:

[0405] The server stores the scores and sentiment analysis data received from the generation AI in a database.

[0406] Step 19:

[0407] The server converts the evaluation results (score and emotion analysis results) into a format that can be notified to the user and sends them to the terminal.

[0408] Step 20:

[0409] The device will display the evaluation results to the user, such as "Your overall score is 85 / 100. Sentiment analysis has confirmed this is a reliable answer."

[0410] Step 21:

[0411] The server consolidates all interview process data (answer data, emotion data, scores, etc.) and generates a report for the final interviewer.

[0412] Step 22:

[0413] The server sends the generated report to the terminal of the final interviewer.

[0414] Step 23:

[0415] The final interviewer will make the final decision based on the report provided.

[0416] Example 2

[0417] 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."

[0418] In conventional recruitment processes, evaluation criteria are often subjective, resulting in unfair screening. Furthermore, the burden on interviewers is heavy, making efficient talent evaluation difficult. Furthermore, evaluations rarely incorporate emotional data, increasing the likelihood of overlooking an applicant's true personality and potential. The present invention aims to solve these problems and achieve fair and efficient talent evaluation.

[0419] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for the user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a question list based on the user's applied position; a means for the user to input answers to the question list; a means for the terminal to acquire the user's answers and emotion data and transmit them to the server; a means for the server to pass the user's answers to the generation AI for evaluation; a means for the server to pass the user's emotion data acquired from the emotion engine to the generation AI; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; and a means for the server to integrate all interview data and generate a report to be provided to the final interviewer. This enables accurate and fair personnel evaluation based on the user's answers and emotions, thereby improving the efficiency and fairness of the hiring process.

[0420] "User" refers to a person who uses the system to log in and enter answers to a list of questions.

[0421] "Server" refers to the computer system that authenticates user login information, generates the question list, analyzes responses and emotional data, stores the evaluation results, and generates a report for the final interviewer.

[0422] "Terminal" refers to a device through which a user accesses the system, enters login information, displays a list of questions, and enters and submits answers.

[0423] "Login Information" refers to the ID and password entered by a User to access the System.

[0424] "Authentication" refers to the process by which a server checks a user's login information against a database to determine whether access is permitted.

[0425] "Applied position" refers to information about the job type or position for which the user is applying.

[0426] A "question list" refers to a set of questions that a user must answer based on the position they are applying for.

[0427] "Answer" refers to the text or audio content that a user enters in response to a list of questions.

[0428] "Emotion data" refers to information about the psychological state and emotions analyzed by the emotion engine from the user's responses.

[0429] "Generative AI" refers to an artificial intelligence model that evaluates and generates a score based on user responses and emotional data.

[0430] "Evaluation results" refers to the score or evaluation calculated based on the user's answers and emotional data analyzed by the generation AI.

[0431] "Database" refers to a data storage system for storing assessment results and other user information.

[0432] "Report" refers to a document that consolidates all interview data and provides it to the final interviewer.

[0433] "Emotion engine" refers to software or algorithms that analyze emotions from a user's voice or text and generate emotion data.

[0434] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system begins when a user enters login information and the server authenticates it. The server then generates a list of questions based on the position the user is applying for, and the terminal displays this to the user. The user enters answers to the list of questions, and the terminal sends the answers and emotion data to the server. The server uses generative AI to evaluate the user's answers and emotion data and stores the results in a database. Finally, the server integrates all the evaluation data and generates a report to be provided to the final interviewer.

[0435] Hardware and software used

[0436] Device: A device operated by a user, such as a PC, tablet, or smartphone

[0437] Server: A hosting environment that includes a web server such as Apache or Nginx, and a database such as MySQL or PostgreSQL.

[0438] Generative AI models: Advanced natural language processing models such as GPT-4

[0439] Emotion engine: Emotion analysis software such as IBM Watson Emotion Analysis

[0440] Program processing

[0441] 1. User login authentication

[0442] The terminal displays a login screen to the user, and the user enters their ID and password.

[0443] The server receives the login information, checks it against a database, and if authentication is successful, generates a session ID and sends it back to the terminal.

[0444] 2. Generating and presenting a list of questions

[0445] The server generates a list of questions based on the user's application information for the position. For example, it generates a list of questions for a software engineer.

[0446] The terminal displays the generated list of questions to the user, for example, "Tell me about your past project experience."

[0447] 3. Enter and submit answers and emotion data

[0448] The user answers the questions and presses the submit button. For example, they enter a specific answer such as "I have worked on developing web applications in the past..."

[0449] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[0450] The device sends the user's answers and emotion data in JSON format to the server.

[0451] 4. Evaluation using generative AI and emotion engine

[0452] The server passes the received answers and emotion data to the generation AI, using, for example, GPT-4.

[0453] The generating AI analyzes the answers and generates a score of "Project management skills: 80 / 100."

[0454] The emotion data analyzed by the emotion engine is passed to the generative AI and incorporated as part of the evaluation.

[0455] The server stores the generated scores and emotion data in a database.

[0456] 5. Notification of evaluation results

[0457] The server converts the evaluation results into a format that can be communicated to the user and sends them to the terminal.

[0458] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[0459] 6. Integration of final interview data

[0460] The server consolidates all process data and generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[0461] The server sends the report to the terminal of the final interviewer.

[0462] Prompt Sentence Examples

[0463] The following prompt sentences are fed into the generative AI model to evaluate the user's responses and emotional data:

[0464] Please rate based on the following answers and sentiment data: Answer: "I have worked on web application development in the past." Sentiment data: "Positive, enthusiastic."

[0465] This system combines user responses with emotional data to make evaluations, enabling more accurate and fairer personnel evaluations.

[0466] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0467] Step 1:

[0468] Displaying the login screen and user authentication

[0469] The device displays a login screen, which includes fields for entering your ID and password.

[0470] The user enters their ID and password and clicks the "Login" button.

[0471] The terminal sends the entered ID and password to the server. The input data includes credential information for authentication.

[0472] The server checks the received ID and password against the database, and if they match, generates a session ID. It performs database operations for the check and generates a session ID.

[0473] The server sends the generated session ID to the terminal and also includes a success message.

[0474] The device receives the session ID and displays the dashboard.

[0475] Step 2:

[0476] Generate and present questionnaires

[0477] The server retrieves the user's application information, which is retrieved from the database at login time.

[0478] The server generates a list of questions based on a specific job application, for example, a list of questions for a software engineer, using a generative AI model.

[0479] The server sends the generated question list to the terminal.

[0480] The terminal displays the received question list to the user. For example, a specific example of the question is "Tell us about your past project experience."

[0481] Step 3:

[0482] Enter and submit answers and emotion data

[0483] The user inputs answers to the list of questions. For example, the user inputs a specific answer such as "I have been involved in developing web applications in the past."

[0484] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[0485] The device sends the user's answer and the generated emotion data in JSON format to the server. The input data includes the user's answer text and emotion analysis data.

[0486] The server parses the received JSON data and prepares it for use in the next step.

[0487] Step 4:

[0488] Evaluation by generative AI and emotion engine

[0489] The server inputs the received answers and sentiment data into a generative AI, for example, using a natural language processing model such as GPT-4.

[0490] The generative AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100." The input to the generative AI model is the user's answers and emotional data.

[0491] The emotion engine passes the analyzed emotion data to the generation AI, which takes this into consideration when making an evaluation.

[0492] The server stores the generated scores and emotion data in a database. The output data includes the evaluation scores and emotion data.

[0493] Step 5:

[0494] Notification of evaluation results

[0495] The server converts the evaluation results into a format that can be notified to the user. The server generates evaluation results and formats them in a format that is easy for the user to understand.

[0496] The server transmits the evaluation results to the terminal.

[0497] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[0498] Step 6:

[0499] Integration of final interview data

[0500] The server aggregates all interview process data, including each user's answers, emotional data, and the evaluation results of the generative AI.

[0501] The server generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[0502] The server sends the report to the terminal of the final interviewer.

[0503] (Application example 2)

[0504] 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."

[0505] The traditional recruitment process involves a lot of manual work and relies heavily on the interviewer's subjectivity, making it difficult to achieve fair and efficient evaluations. It is also difficult to properly analyze the applicant's emotions during the interview and reflect them in the evaluation. In particular, when interviewers are not always present at the factory, the interview itself becomes difficult and inefficient. There is a need for a system that can solve these issues.

[0506] 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.

[0507] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the emotion engine to analyze emotion data based on the user's answers; a means for the server to store the evaluation results by the generation AI and the emotion engine in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; and a means for the robot assistant to present questions for the job interview and collect voice responses from the applicant. This enables fair and efficient personnel evaluation, and makes it possible to achieve an efficient interview process even when an interviewer is not present, particularly in job interviews at factories, etc.

[0508] A "user" is a person who uses this system to log in and input answers to the position they are applying for.

[0509] A "server" is a computer device that processes and manages information, stores data entered by users and evaluation results in a database, and notifies users of such data.

[0510] "Login Information" means authentication information such as ID and password required for a User to access the System.

[0511] "Applied position" is information about the type of job or position for which the user is applying.

[0512] A "question list" is a set of questions generated based on the position being applied for, which are presented to the applicant during the interview.

[0513] "Generative AI" is an artificial intelligence technology that analyzes user responses and generates evaluations.

[0514] "Evaluation results" are data on user responses analyzed by the generative AI and emotion engine, including evaluation scores and comments.

[0515] An "emotion engine" is a technology that analyzes emotions based on user responses and extracts emotional data from voice and text.

[0516] The "database" is an information management system for storing evaluation results and interview data.

[0517] A "robot assistant" is an artificial intelligence-equipped device that has the ability to pose questions during job interviews and collect applicants' voice responses.

[0518] The "final interviewer" is the person whose role it is to make the final hiring decision based on all interview data.

[0519] "Interview data" refers to all information related to the interview, such as the user's answers, emotional data, and evaluation results.

[0520] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient personnel evaluation. This system can support efficient interview processes, especially in recruitment interviews at factories, even when interviewers are not present.

[0521] System Program

[0522] User Login

[0523] The user enters their ID and password on the login screen, and the server authenticates this login information. After successful authentication, the server generates a session ID and sends it to the user's device.

[0524] Question list generation and presentation

[0525] The server generates a list of questions based on the user's applied position information, and the list of questions is presented to the user via the user terminal or robot assistant.

[0526] Collecting response and sentiment data

[0527] When a user answers a question by typing or speaking, the robot assistant collects the voice data and the emotion engine analyzes the emotion from the voice data.

[0528] Evaluation by generative AI and emotion engine

[0529] The server passes the user's response data and emotion data to the AI ​​generator to generate an evaluation. The generated evaluation score and emotion data are stored in a database.

[0530] Notification of evaluation results

[0531] The server converts the evaluation results into a format suitable for the user and sends them to the user's terminal, where they are displayed.

[0532] Integration of final interview data

[0533] The server aggregates all the interview data and generates a report to be provided to the final interviewer, who then sends the report to his / her terminal.

[0534] Hardware and Software

[0535] EmotionEngine: Software for analyzing emotions in voice and text data

[0536] EvaluationModel: Evaluation model using generative AI

[0537] Robot assistants: AI-powered devices that pose questions and collect spoken responses

[0538] Server: A computer device that processes and manages information, stores evaluation results in a database, and sends notifications.

[0539] Specific examples

[0540] When a user applies for a software engineer position, the server follows this sequence:

[0541] 1. The server generates questions for software engineers, such as "Tell me about your past project experience."

[0542] 2. The user types or speaks the answer, "I have worked on developing web applications in the past..."

[0543] 3. The emotion engine analyzes the voice data and generates emotion data.

[0544] 4. The server and the generation AI work together to evaluate the user's technical skills and emotions and generate a score such as "Project management skills: 80 / 100."

[0545] 5. The server converts the evaluation results into a different format and notifies the user device, "Your evaluation score is 85 / 100. Reliable emotional expression was observed."

[0546] Prompt Sentence Examples

[0547] "I'm applying for a factory machine operator position. Please generate a list of questions for this position."

[0548] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0549] Step 1:

[0550] The user enters their login information.

[0551] Input: The user enters the ID and password.

[0552] Operation: The user's device displays the login screen, and the user enters their ID and password.

[0553] Output: Login information is sent from the user terminal to the server.

[0554] Step 2:

[0555] The server authenticates the user's login information.

[0556] Input: The server receives the user's ID and password.

[0557] How it works: The server checks the database and verifies the login information.

[0558] Output: When authentication is successful, the server generates a session ID and sends it to the user's device.

[0559] Step 3:

[0560] The server generates a list of questions based on the position the user is applying for.

[0561] Input: User's application information for the position.

[0562] Operation: The server references the database and creates a list of questions corresponding to the position being applied for.

[0563] Output: The generated question list is sent to the user terminal or robot assistant.

[0564] Step 4:

[0565] The user enters answers into the questionnaire.

[0566] Input: Question list sent from the server.

[0567] Action: The user types in or speaks a response.

[0568] Output: The user device or robot assistant collects the answers and sends them to the server.

[0569] Step 5:

[0570] The server passes the user's answers to the generation AI for evaluation.

[0571] Input: User response data.

[0572] How it works: The server passes the user's text response to the generative AI model for analysis.

[0573] Output: The ratings generated by the generation AI are sent back to the server.

[0574] Step 6:

[0575] The emotion engine analyzes the emotion data based on the user's responses.

[0576] Input: User's voice response data.

[0577] How it works: The emotion engine analyzes the voice data and generates emotion data.

[0578] Output: The analyzed emotion data is sent to the server.

[0579] Step 7:

[0580] The server stores the evaluation results from the generation AI and emotion engine in a database.

[0581] Input: Evaluation data from generative AI and emotion data from emotion engine.

[0582] Operation: The server integrates and stores the rating data and emotion data in a database.

[0583] Output: A database entry containing the evaluation results and emotion data.

[0584] Step 8:

[0585] The server notifies the user of the evaluation results.

[0586] Input: Evaluation results stored in a database.

[0587] Operation: The server converts the evaluation results into a notification format and sends them to the user terminal.

[0588] Output: The user is notified of the evaluation results.

[0589] Step 9:

[0590] The server consolidates all the interview data and generates a report that is provided to the final interviewer.

[0591] Input: All interview data.

[0592] How it works: The server analyzes the data and creates a report for the final interviewer.

[0593] Output: The generated report is sent to the terminal of the final interviewer.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] [Second embodiment]

[0598] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0599] 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.

[0600] 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).

[0601] 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.

[0602] 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.

[0603] 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).

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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."

[0610] This invention is a human resource recruitment evaluation system that uses generative AI. This system automates the entire interview process and eliminates the subjectivity of interviewers by conducting quantitative evaluations, thereby reducing the risk of mismatch and improving the efficiency of recruitment.

[0611] System Overview

[0612] 1. User login

[0613] The terminal displays a login screen to the user, and the user enters their ID and password.

[0614] The server receives the login information and checks it against the data stored in the database.

[0615] After successful authentication, the server generates a session ID and sends it back to the terminal.

[0616] 2. Question list generation and presentation

[0617] The server generates an appropriate list of questions based on the user's applied position information.

[0618] The terminal displays the generated list of questions to the user.

[0619] 3. Enter and submit your answers

[0620] The user inputs answers to the questions and presses the send button.

[0621] The terminal transmits the inputted answer to the server.

[0622] 4. Evaluation by generative AI

[0623] The server passes the received answer to the generative AI model.

[0624] The generative AI analyzes the answers based on past learning data and calculates a score for each question.

[0625] The server stores the evaluation results of the generated AI in a database.

[0626] 5. Notification of evaluation results

[0627] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0628] The terminal displays the evaluation results to the user.

[0629] 6. Integration of final interview data

[0630] The server consolidates all process data and generates a report for the final interviewer.

[0631] The server sends the report to the terminal of the final interviewer.

[0632] Specific examples

[0633] 1. User login

[0634] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[0635] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[0636] The terminal retains the received session ID for the user and displays the dashboard.

[0637] 2. Question list generation and presentation

[0638] The server recognizes that the user is applying for a position as a "Software Engineer."

[0639] The server generates a list of questions for software engineers and sends it to the terminal.

[0640] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[0641] 3. Enter and submit your answers

[0642] The user enters an answer to the question and presses the submit button. For example, the user enters "I have been involved in developing web applications in the past..."

[0643] The device sends the response in JSON format to the server.

[0644] 4. Evaluation by generative AI

[0645] The server inputs the received answers into the generation AI.

[0646] The generating AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100."

[0647] The server stores the generated scores in a database.

[0648] 5. Notification of evaluation results

[0649] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0650] The device displays to the user, "Your rating score is 85 / 100."

[0651] 6. Integration of final interview data

[0652] The server consolidates all interview process data and generates a report for the final interview page.

[0653] The server sends the report to the terminal of the final interviewer.

[0654] This system automates all steps from user application to evaluation, enabling efficient and fair recruitment.

[0655] The processing flow will be explained below.

[0656] Step 1:

[0657] The user enters their ID and password on the login screen and clicks the "Login" button.

[0658] Step 2:

[0659] The device sends the entered ID and password to the server.

[0660] Step 3:

[0661] The server checks the received ID and password against the user information in the database.

[0662] Step 4:

[0663] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[0664] Step 5:

[0665] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[0666] Step 6:

[0667] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[0668] Step 7:

[0669] The server sends the generated question list to the terminal.

[0670] Step 8:

[0671] The terminal displays the received list of questions to the user, allowing the user to input answers.

[0672] Step 9:

[0673] The user enters answers to each question and clicks the submit button.

[0674] Step 10:

[0675] The device sends the user's answer in JSON format to the server.

[0676] Step 11:

[0677] The server validates the response it receives to ensure there is no missing or incorrect data.

[0678] Step 12:

[0679] The server passes the verified answer data to the generative AI model.

[0680] Step 13:

[0681] The generative AI analyzes the answers it receives and calculates a score for each question.

[0682] Step 14:

[0683] The generated AI returns the calculated score to the server.

[0684] Step 15:

[0685] The server stores the scores received from the generated AI in a database.

[0686] Step 16:

[0687] The server converts the saved score data into a format that can be notified to the user and transmits it to the terminal.

[0688] Step 17:

[0689] The device displays the evaluation result to the user, for example, "Your overall score is 85 / 100."

[0690] Step 18:

[0691] The server consolidates all interview process data to generate a report for the final interview.

[0692] Step 19:

[0693] The server sends the generated report to the terminal of the final interviewer.

[0694] Step 20:

[0695] The final interviewer will make the final decision based on the report provided.

[0696] Example 1

[0697] 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."

[0698] Conventional recruitment evaluation systems have the problem that the interviewer's subjectivity is easily involved, making it difficult to achieve fair evaluations. Furthermore, the interview process is conducted manually, which reduces recruitment efficiency and increases the risk of mismatches. Furthermore, the management of applicant responses and notification of evaluation results are not centralized, making the entire process cumbersome.

[0699] 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.

[0700] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; a means for the terminal to display a login screen to the user and prompt the user to input an ID and password; a means for the server to generate a session ID and send it back to the terminal if authentication is successful; and a means for the server to send the answers entered by the user to the server in JSON format. This enables automation of the interview process, fair evaluation, and efficient management.

[0701] A "user" is an individual or organization that uses the system, and is primarily responsible for entering login information and answering questions on the questionnaire.

[0702] A "terminal" is a device operated by a user, and is used to display a login screen and a list of questions and to send answers to a server.

[0703] The "server" is the central control device of the system, and is a device that authenticates user login information, generates a list of questions, evaluates answers, notifies users of the evaluation results, and integrates data.

[0704] "Login information" refers to authentication information for a user to access a system, and is usually composed of a user ID and password.

[0705] A "session ID" is a unique identifier generated by the server when a user logs in to the system, and is used to manage the login session.

[0706] A "question list" is a set of questions generated by the server based on the user's application for a position, and used to evaluate the user's skills and experience.

[0707] "Generative AI" is an artificial intelligence model that analyzes user responses and provides quantitative evaluations.

[0708] "Database" means a data management system for the server to store assessment results and other interview process data.

[0709] A "report" is a document that is generated by the server by integrating all interview data and provided to the final interviewer, and includes the user's evaluation results and the like.

[0710] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight data exchange format for concisely expressing data structures, and is primarily used to exchange data between servers and terminals.

[0711] This invention is a human resource recruitment evaluation system that uses a generative AI model. This system automates the entire interview process and eliminates the subjectivity of interviewers by performing quantitative evaluations, thereby reducing the risk of mismatch and improving recruitment efficiency. Below, we will explain in detail each element that makes up this system.

[0712] System configuration

[0713] This system operates through the mutual cooperation of three entities: the server, the terminal, and the user.

[0714] Server: The central control unit of the system, which performs major processes such as login authentication, question list generation, calculation and storage of evaluation results, and data integration.

[0715] Terminal: A device operated by the user that presents a list of questions, allows users to input answers, and displays evaluation results.

[0716] User: An applicant who uses the system and is the entity that enters login information and answers the questionnaire.

[0717] This system uses the following technical elements:

[0718] Generative AI model: An artificial intelligence model that analyzes input answers and makes a quantitative evaluation.

[0719] Database: Data storage for saving assessment results and interview process data.

[0720] Hardware and Software Configuration

[0721] 1. Login Process

[0722] The terminal displays a login screen to the user, and the user enters their ID and password. The terminal sends this to the server, which collates it with the information stored in the database. If the collation is successful, the server generates a session ID and sends it back to the terminal. Using this session ID, the user can access the system.

[0723] 2. Question list generation and presentation

[0724] The server retrieves the user's application position information from the database and generates a list of questions based on the information, which is then sent to the terminal and displayed to the user.

[0725] 3. Enter and submit your answers

[0726] The user enters answers to the questions and presses the submit button. The terminal sends the answers in JSON format to the server. For example, in response to the question "Tell us about your past project experience," the user enters "I have been in charge of developing web applications in the past."

[0727] 4. Evaluation Process

[0728] The server passes the received answer to the generative AI model for analysis. The generative AI model calculates a score for the user's answer based on past learning data. For example, a score of "Project management skills: 80 / 100" may be generated. The server stores this evaluation result in a database.

[0729] 5. Notification of evaluation results

[0730] The server converts the evaluation results into a format suitable for the user and sends it to the terminal. The terminal displays the results to the user. For example, it displays "Your evaluation score is 85 / 100."

[0731] 6. Integration of final interview data

[0732] The server aggregates all interview data and generates a report for the final interviewer, which is sent to the final interviewer's terminal.

[0733] Specific examples

[0734] Example prompt sentence:

[0735] "Tell me about your past project experience."

[0736] "What skills can you best contribute to this position?"

[0737] Tell us about your experience as a team leader.

[0738] Using these technologies and processes, the system automates all steps from users' applications to evaluations, enabling efficient and fair recruitment.

[0739] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0740] Step 1: User Login

[0741] 1. The device displays a login screen to the user.

[0742] Input: User ID and password

[0743] Output: Display of input form

[0744] Specific behavior: The device renders the HTML of the login screen and displays it to the user.

[0745] 2. The user enters their ID and password and presses the "Login" button.

[0746] Input: User ID (e.g., "user123") and password (e.g., "password123")

[0747] Output: Authentication request from device to server

[0748] Specific Action: The user enters data into the input fields and clicks the submit button.

[0749] 3. The device sends the login information entered by the user to the server.

[0750] Input: User ID and password

[0751] Output: Authentication request to the server (JSON format)

[0752] Specific operation: The device sends login information in JSON format to the server.

[0753] 4. The server checks the received login information against its database.

[0754] Input: Login information (user ID and password)

[0755] Output: Authentication result (success or failure)

[0756] Specific operation: The server queries the database to check whether the entered user ID and password match.

[0757] 5. If authentication is successful, the server generates a session ID and sends it back to the terminal.

[0758] Input: Authentication successful

[0759] Output: Session ID (e.g. "abc123")

[0760] Specific operation: The server generates a session ID and sends it to the terminal.

[0761] 6. The device retains the received session ID and displays the dashboard.

[0762] Input: Session ID

[0763] Output: Dashboard screen

[0764] Specific operation: The device saves the session ID in local storage and displays the user dashboard.

[0765] Step 2: Generate and present a list of questions

[0766] 1. The server retrieves the user's application position information from the database.

[0767] Input: User ID

[0768] Output: Position information (e.g. "Software Engineer")

[0769] Specific operation: The server queries the database to obtain information about the user's applied position.

[0770] 2. The server generates a list of questions based on the position applied for.

[0771] Input: Position information

[0772] Output: Question list (e.g. "Tell me about your past project experience")

[0773] Specific operation: The server dynamically generates a list of questions from a question template according to the position being applied for.

[0774] 3. The server sends the generated question list to the terminal.

[0775] Input: Question List

[0776] Output: Data sent to the terminal (JSON format)

[0777] Specific operation: The server sends the generated question list to the terminal in JSON format.

[0778] 4. The terminal displays the received list of questions to the user.

[0779] Input: Question List

[0780] Output: Question list screen

[0781] Specific operation: The terminal renders the question list in HTML format and displays it to the user.

[0782] Step 3: Enter and submit your answers

[0783] 1. The user enters answers to the questions and presses the submit button.

[0784] Input: Answer (e.g., "I have worked on web application development in the past")

[0785] Output: Input data to the terminal

[0786] Specific action: The user enters an answer to a question in the text field and clicks the submit button.

[0787] 2. The device sends the entered answer in JSON format to the server.

[0788] Input: Answer content (JSON format)

[0789] Output: Data sent to the server

[0790] Specific operation: The device converts the response into JSON format and sends it to the server.

[0791] Step 4: Evaluation by generative AI

[0792] 1. The server inputs the received answers into a generative AI model.

[0793] Input: Answer (e.g., "I have worked on web application development in the past")

[0794] Output: Input data to a generative AI model

[0795] Specific operation: The server passes the answer data to the generative AI model.

[0796] 2. The generative AI analyzes the answers and calculates a score for each question.

[0797] Input: Answer

[0798] Output: Score (e.g. "Project Management Skills: 80 / 100")

[0799] Specific operation: The generative AI model analyzes the answers and calculates an evaluation score based on the training data.

[0800] 3. The server stores the generated scores in a database.

[0801] Input: Score

[0802] Output: Data saved to database

[0803] Specific operation: The server saves the score data in a database.

[0804] Step 5: Notification of evaluation results

[0805] 1. The server converts the evaluation results into a format that can be notified to the user.

[0806] Input: Score

[0807] Output: Notification data (e.g. "Your rating score is 85 / 100")

[0808] Specific operation: The server converts the score data into a format that can be notified to the user.

[0809] 2. The server sends the converted evaluation results to the terminal.

[0810] Input: Notification data

[0811] Output: Data sent to the terminal

[0812] Specific operation: The server sends notification data in JSON format to the device.

[0813] 3. The device displays the evaluation results to the user.

[0814] Input: Notification data

[0815] Output: Evaluation result screen

[0816] Specific operation: The device renders the notification data in HTML format and displays it to the user.

[0817] Step 6: Consolidating the final interview data

[0818] 1. The server aggregates all the interview data.

[0819] Input: Interview process data

[0820] Output: Integrated data

[0821] Specific operation: The server analyzes multiple interview data sets and creates a single integrated dataset.

[0822] 2. The server generates a report for the final interviewer.

[0823] Input: Integrated data

[0824] Output: Report (e.g. "Comprehensive report of user rating scores")

[0825] Specific operation: The server generates a report for the final interviewer based on the integrated data.

[0826] 3. The server sends the generated report to the terminal of the final interviewer.

[0827] Input: Report

[0828] Output: Report data sent to the terminal

[0829] Specific operation: The server sends the report in JSON format to the terminal and displays it on the terminal of the final interviewer.

[0830] The above is the specific flow of program processing in the present invention.

[0831] (Application example 1)

[0832] 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."

[0833] Conventional methods for evaluating the skills of factory workers require a lot of time and effort, and are heavily influenced by the evaluator's subjectivity, resulting in problems with the fairness and efficiency of the evaluation. In particular, artificial bias in evaluations and a lack of consistency in evaluation criteria hinder worker motivation and appropriate personnel allocation. This makes it difficult to design training plans and determine optimal personnel allocation.

[0834] 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.

[0835] In this invention, the server includes a means for a user to input login information, a means for the server to authenticate the user's login information, a means for the server to generate a list of questions based on the user's role, a means for the user to input answers to the list of questions, a means for the server to pass the user's answers to a generative AI model for evaluation, a means for the server to store the evaluation results by the generative AI model in a database, a means for the server to notify the user of the evaluation results, and a means for the server to integrate all evaluation data and generate a report to be provided to a manager. This enables efficient and fair evaluation of the skills of workers in a factory, enabling appropriate personnel allocation and the creation of training plans.

[0836] A "user" is a worker or operator who has access to the system, enters answers to a questionnaire, and is evaluated.

[0837] "Login information" refers to the authentication information required for a user to access a system, and is usually composed of a user ID and password.

[0838] "Server" refers to a device or software that processes and manages data for the entire system.

[0839] A "question list" is a set of questions for skill evaluation that is created by the server based on the user's role and work responsibilities.

[0840] A "generative AI model" is an artificial intelligence model that analyzes user responses based on past learning data and generates quantitative evaluation results.

[0841] "Database" means a digital data storage device for storing all evaluation data and login information for the System.

[0842] "Evaluation results" refer to scores such as skills and work efficiency calculated by the generative AI model by analyzing the user's responses.

[0843] A "report" is a written or digital document that the server generates to consolidate all evaluation data and provide to an administrator.

[0844] "Authentication" is the process by which a server receives a user's login information and verifies the user's legitimacy by checking it against information in a database.

[0845] "JSON format" is a structured data format for exchanging user responses, and is an abbreviation for JavaScript Object Notation.

[0846] This invention is an efficient and fair evaluation system that improves on the conventional method of evaluating the skills of factory workers. The system begins with the user entering login information, which is authenticated by the server, and then evaluates the user's skills using a generative AI model. The evaluation results are stored in a database and provided to managers as a report.

[0847] The server uses Flask (a Python web framework) to authenticate the login information of workers and operators when they access the system. This login information mainly consists of a user ID and password. If authentication is successful, the server generates a session ID and sends it to the user's terminal.

[0848] The server then generates a questionnaire based on the logged-in user's role and responsibilities, tailored to the user's specific tasks and skill set, and displays the questionnaire on a smartphone, tablet, or other device.

[0849] When a user enters answers into the question list, the answers are sent to the server in JSON format. The server then passes the received answers to the generative AI model, which analyzes them based on past learning data. As a result of the analysis, a score is calculated based on the user's skills, work efficiency, etc.

[0850] The generated evaluation results are stored in a database, and the server notifies the user. The evaluation result notification allows users to check their own skill evaluation and use it for future training and self-improvement. The server also consolidates all evaluation data to generate a report and provides it to managers. This allows managers to understand the skill status of their workers and design appropriate personnel assignments and training plans.

[0851] A specific example of this system is shown below.

[0852] Specific examples

[0853] 1. Log in:

[0854] The user enters "user123" and "password123" on the tablet and presses the login button.

[0855] The server authenticates the login information, generates a session ID "session_1234", and sends it to the terminal.

[0856] 2. Generate a list of questions:

[0857] The server recognizes the user's role as a "parts assembler" and generates an appropriate list of questions.

[0858] For example, questions such as "Tell us about your work environment recently" and "What was the most difficult task you had in the past week?" will be displayed.

[0859] 3. Enter and submit your answers:

[0860] The user answers the questions by typing "The working environment was comfortable" and "The most difficult task during the week was assembling the cooling device," and then presses the send button.

[0861] The device sends the entered answer in JSON format to the server.

[0862] 4. Generative AI evaluation:

[0863] The server analyzes the answers it receives using a generative AI model to generate scores such as "Skill evaluation: 90 / 100, work efficiency: 85 / 100."

[0864] 5. Notification of evaluation results:

[0865] The server sends the evaluation results to the terminal and displays to the user, "Your evaluation scores are skill rating 90 / 100 and work efficiency 85 / 100."

[0866] 6. Generate the final report:

[0867] The server consolidates all the evaluation data and generates reports for administrators, who can use these reports to design appropriate training plans.

[0868] This system will enable efficient and fair evaluation of the skills of workers within factories, leading to appropriate staffing and training.

[0869] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0870] Step 1:

[0871] The server authenticates the user's login information. The user enters their user ID and password into the login screen on a device such as a tablet and submits it. The server receives the submitted information and compares it with the information in its database. If authentication is successful, the server generates a session ID and submits it to the user's device. This session ID is used to identify the user in subsequent processes.

[0872] Input: User ID, Password

[0873] Output: Session ID

[0874] Step 2:

[0875] The server generates a questionnaire based on the role of the logged-in user. After the user is properly authenticated, the server retrieves the user's role (e.g., parts assembly worker) from the database. Then, it generates a questionnaire appropriate for the user's role and sends it to the terminal. The user's terminal displays this questionnaire.

[0876] Input: Session ID, User Role

[0877] Output: Question list

[0878] Step 3:

[0879] The user enters answers to the presented list of questions and sends them from the device to the server. The user enters answers to the questions using a tablet or smartphone and presses the send button. The device sends the entered answers in JSON format to the server.

[0880] Input: Question list, user answers

[0881] Output: JSON formatted response data

[0882] Step 4:

[0883] The server passes the received answers to the generative AI model for evaluation. The server inputs the JSON-formatted answer data received from the user into the generative AI model and requests analysis. The generative AI model analyzes the user's answers based on past learning data and calculates scores for skill and work efficiency.

[0884] Input: JSON formatted response data

[0885] Output: Evaluation score (e.g., skill rating 90 / 100, work efficiency 85 / 100)

[0886] Step 5:

[0887] The server saves the evaluation results from the generative AI model in a database and notifies the user. The generated evaluation results are saved in a database by the server. The server then sends the evaluation results to the user's device, where the user can check the displayed score.

[0888] Input: Rating score

[0889] Output: Notify user, save to database

[0890] Step 6:

[0891] The server consolidates all the evaluation data and generates a report to be provided to the manager. The server aggregates and consolidates the evaluation data of multiple users. It then generates a report that allows the manager to grasp the overall status of workers in the factory and sends it to the manager's terminal. The manager can use this report to optimize training plans and personnel deployment.

[0892] Input: A set of evaluation data

[0893] Output: Report for administrator

[0894] 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.

[0895] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system authenticates the user's login information, generates a list of questions based on the position being applied for, and analyzes the user's answers and emotions. The analysis results are stored in a database as evaluation results and reflected in a report provided to the final interviewer.

[0896] System Overview

[0897] 1. User login

[0898] The terminal displays a login screen to the user, and the user enters their ID and password.

[0899] The server receives the login information and checks it against a database.

[0900] After successful authentication, the server generates a session ID and sends it back to the terminal.

[0901] 2. Question list generation and presentation

[0902] The server generates a list of questions based on the user's applied position information.

[0903] The terminal displays the generated list of questions to the user.

[0904] 3. Enter and submit answers and emotion data

[0905] The user enters answers into the question list and presses the submit button.

[0906] The device sends the input answer and emotion data to the server.

[0907] 4. Evaluation using generative AI and emotion engine

[0908] The server passes the received answer to the generation AI.

[0909] The emotion engine analyzes the emotions from the voice and text of the user's responses.

[0910] The generating AI evaluates the answers and analyzed emotional data and calculates a score.

[0911] The server stores the evaluation results from the generation AI and emotion engine in a database.

[0912] 5. Notification of evaluation results

[0913] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0914] The terminal displays the evaluation results to the user.

[0915] 6. Integration of final interview data

[0916] The server consolidates all process data and generates a report for the final interviewer.

[0917] The server sends the report to the terminal of the final interviewer.

[0918] Specific examples

[0919] 1. User login

[0920] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[0921] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[0922] The terminal retains the received session ID and displays the dashboard.

[0923] 2. Question list generation and presentation

[0924] The server recognizes that the user is applying for a position as a "Software Engineer."

[0925] The server generates a list of questions for software engineers and sends it to the terminal.

[0926] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[0927] 3. Enter and submit answers and emotion data

[0928] The user answers the question by saying, "I have worked on developing web applications in the past..."

[0929] The emotion engine analyzes the user's voice and text and generates emotion data.

[0930] The device sends the user's answers and emotion data in JSON format to the server.

[0931] 4. Evaluation using generative AI and emotion engine

[0932] The server inputs the answers and emotional data into the generation AI.

[0933] The generating AI analyzes the answers and generates a score such as "Project management skills: 80 / 100."

[0934] The emotion engine passes the analyzed emotion data to the generation AI.

[0935] The server stores the generated scores and emotion data in a database.

[0936] 5. Notification of evaluation results

[0937] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[0938] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[0939] 6. Integration of final interview data

[0940] The server consolidates all interview process data and generates a report for the final interview page.

[0941] The server sends the report to the terminal of the final interviewer.

[0942] This system achieves more accurate and fair evaluation of personnel by combining the user's responses with their emotions.

[0943] The processing flow will be explained below.

[0944] Step 1:

[0945] The user enters their ID and password on the login screen and clicks the "Login" button.

[0946] Step 2:

[0947] The device sends the entered ID and password to the server.

[0948] Step 3:

[0949] The server checks the received ID and password against the user information in the database.

[0950] Step 4:

[0951] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[0952] Step 5:

[0953] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[0954] Step 6:

[0955] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[0956] Step 7:

[0957] The server sends the generated question list to the terminal.

[0958] Step 8:

[0959] The terminal displays the received list of questions to the user, allowing the user to input answers.

[0960] Step 9:

[0961] The user enters answers to each question and clicks the submit button.

[0962] Step 10:

[0963] When the user inputs something, the emotion engine analyzes the audio and video to detect the user's emotional state.

[0964] Step 11:

[0965] The emotion engine generates emotion analysis data and transmits the data to the server.

[0966] Step 12:

[0967] The device sends the user's answer in JSON format to the server.

[0968] Step 13:

[0969] The server receives the response data and emotion data and validates both data to check for missing or inappropriate data.

[0970] Step 14:

[0971] The server passes verified response data and emotion data to the generative AI model.

[0972] Step 15:

[0973] The generative AI analyzes the answers it receives and calculates a score for each question.

[0974] Step 16:

[0975] The generative AI calculates an overall score or rating that takes emotional data into account.

[0976] Step 17:

[0977] The generated AI returns the calculated score to the server.

[0978] Step 18:

[0979] The server stores the scores and sentiment analysis data received from the generation AI in a database.

[0980] Step 19:

[0981] The server converts the evaluation results (score and emotion analysis results) into a format that can be notified to the user and sends them to the terminal.

[0982] Step 20:

[0983] The device will display the evaluation results to the user, such as "Your overall score is 85 / 100. Sentiment analysis has confirmed this is a reliable answer."

[0984] Step 21:

[0985] The server consolidates all interview process data (answer data, emotion data, scores, etc.) and generates a report for the final interviewer.

[0986] Step 22:

[0987] The server sends the generated report to the terminal of the final interviewer.

[0988] Step 23:

[0989] The final interviewer will make the final decision based on the report provided.

[0990] Example 2

[0991] 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."

[0992] In conventional recruitment processes, evaluation criteria are often subjective, resulting in unfair screening. Furthermore, the burden on interviewers is heavy, making efficient talent evaluation difficult. Furthermore, evaluations rarely incorporate emotional data, increasing the likelihood of overlooking an applicant's true personality and potential. The present invention aims to solve these problems and achieve fair and efficient talent evaluation.

[0993] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for the user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a question list based on the user's applied position; a means for the user to input answers to the question list; a means for the terminal to acquire the user's answers and emotion data and transmit them to the server; a means for the server to pass the user's answers to the generation AI for evaluation; a means for the server to pass the user's emotion data acquired from the emotion engine to the generation AI; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; and a means for the server to integrate all interview data and generate a report to be provided to the final interviewer. This enables accurate and fair personnel evaluation based on the user's answers and emotions, thereby improving the efficiency and fairness of the hiring process.

[0994] "User" refers to a person who uses the system to log in and enter answers to a list of questions.

[0995] "Server" refers to the computer system that authenticates user login information, generates the question list, analyzes responses and emotional data, stores the evaluation results, and generates a report for the final interviewer.

[0996] "Terminal" refers to a device through which a user accesses the system, enters login information, displays a list of questions, and enters and submits answers.

[0997] "Login Information" refers to the ID and password entered by a User to access the System.

[0998] "Authentication" refers to the process by which a server checks a user's login information against a database to determine whether access is permitted.

[0999] "Applied position" refers to information about the job type or position for which the user is applying.

[1000] A "question list" refers to a set of questions that a user must answer based on the position they are applying for.

[1001] "Answer" refers to the text or audio content that a user enters in response to a list of questions.

[1002] "Emotion data" refers to information about the psychological state and emotions analyzed by the emotion engine from the user's responses.

[1003] "Generative AI" refers to an artificial intelligence model that evaluates and generates a score based on user responses and emotional data.

[1004] "Evaluation results" refers to the score or evaluation calculated based on the user's answers and emotional data analyzed by the generation AI.

[1005] "Database" refers to a data storage system for storing assessment results and other user information.

[1006] "Report" refers to a document that consolidates all interview data and provides it to the final interviewer.

[1007] "Emotion engine" refers to software or algorithms that analyze emotions from a user's voice or text and generate emotion data.

[1008] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system begins when a user enters login information and the server authenticates it. The server then generates a list of questions based on the position the user is applying for, and the terminal displays this to the user. The user enters answers to the list of questions, and the terminal sends the answers and emotion data to the server. The server uses generative AI to evaluate the user's answers and emotion data and stores the results in a database. Finally, the server integrates all the evaluation data and generates a report to be provided to the final interviewer.

[1009] Hardware and software used

[1010] Device: A device operated by a user, such as a PC, tablet, or smartphone

[1011] Server: A hosting environment that includes a web server such as Apache or Nginx, and a database such as MySQL or PostgreSQL.

[1012] Generative AI models: Advanced natural language processing models such as GPT-4

[1013] Emotion engine: Emotion analysis software such as IBM Watson Emotion Analysis

[1014] Program processing

[1015] 1. User login authentication

[1016] The terminal displays a login screen to the user, and the user enters their ID and password.

[1017] The server receives the login information, checks it against a database, and if authentication is successful, generates a session ID and sends it back to the terminal.

[1018] 2. Generating and presenting a list of questions

[1019] The server generates a list of questions based on the user's application information for the position. For example, it generates a list of questions for a software engineer.

[1020] The terminal displays the generated list of questions to the user, for example, "Tell me about your past project experience."

[1021] 3. Enter and submit answers and emotion data

[1022] The user answers the questions and presses the submit button. For example, they enter a specific answer such as "I have worked on developing web applications in the past..."

[1023] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[1024] The device sends the user's answers and emotion data in JSON format to the server.

[1025] 4. Evaluation using generative AI and emotion engine

[1026] The server passes the received answers and emotion data to the generation AI, using, for example, GPT-4.

[1027] The generating AI analyzes the answers and generates a score of "Project management skills: 80 / 100."

[1028] The emotion data analyzed by the emotion engine is passed to the generative AI and incorporated as part of the evaluation.

[1029] The server stores the generated scores and emotion data in a database.

[1030] 5. Notification of evaluation results

[1031] The server converts the evaluation results into a format that can be communicated to the user and sends them to the terminal.

[1032] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[1033] 6. Integration of final interview data

[1034] The server consolidates all process data and generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[1035] The server sends the report to the terminal of the final interviewer.

[1036] Prompt Sentence Examples

[1037] The following prompt sentences are fed into the generative AI model to evaluate the user's responses and emotional data:

[1038] Please rate based on the following answers and sentiment data: Answer: "I have worked on web application development in the past." Sentiment data: "Positive, enthusiastic."

[1039] This system combines user responses with emotional data to make evaluations, enabling more accurate and fairer personnel evaluations.

[1040] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1041] Step 1:

[1042] Displaying the login screen and user authentication

[1043] The device displays a login screen, which includes fields for entering your ID and password.

[1044] The user enters their ID and password and clicks the "Login" button.

[1045] The terminal sends the entered ID and password to the server. The input data includes credential information for authentication.

[1046] The server checks the received ID and password against the database, and if they match, generates a session ID. It performs database operations for the check and generates a session ID.

[1047] The server sends the generated session ID to the terminal and also includes a success message.

[1048] The device receives the session ID and displays the dashboard.

[1049] Step 2:

[1050] Generate and present questionnaires

[1051] The server retrieves the user's application information, which is retrieved from the database at login time.

[1052] The server generates a list of questions based on a specific job application, for example, a list of questions for a software engineer, using a generative AI model.

[1053] The server sends the generated question list to the terminal.

[1054] The terminal displays the received question list to the user. For example, a specific example of the question is "Tell us about your past project experience."

[1055] Step 3:

[1056] Enter and submit answers and emotion data

[1057] The user inputs answers to the list of questions. For example, the user inputs a specific answer such as "I have been involved in developing web applications in the past."

[1058] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[1059] The device sends the user's answer and the generated emotion data in JSON format to the server. The input data includes the user's answer text and emotion analysis data.

[1060] The server parses the received JSON data and prepares it for use in the next step.

[1061] Step 4:

[1062] Evaluation by generative AI and emotion engine

[1063] The server inputs the received answers and sentiment data into a generative AI, for example, using a natural language processing model such as GPT-4.

[1064] The generative AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100." The input to the generative AI model is the user's answers and emotional data.

[1065] The emotion engine passes the analyzed emotion data to the generation AI, which takes this into consideration when making an evaluation.

[1066] The server stores the generated scores and emotion data in a database. The output data includes the evaluation scores and emotion data.

[1067] Step 5:

[1068] Notification of evaluation results

[1069] The server converts the evaluation results into a format that can be notified to the user. The server generates evaluation results and formats them in a format that is easy for the user to understand.

[1070] The server transmits the evaluation results to the terminal.

[1071] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[1072] Step 6:

[1073] Integration of final interview data

[1074] The server aggregates all interview process data, including each user's answers, emotional data, and the evaluation results of the generative AI.

[1075] The server generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[1076] The server sends the report to the terminal of the final interviewer.

[1077] (Application example 2)

[1078] 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."

[1079] The traditional recruitment process involves a lot of manual work and relies heavily on the interviewer's subjectivity, making it difficult to achieve fair and efficient evaluations. It is also difficult to properly analyze the applicant's emotions during the interview and reflect them in the evaluation. In particular, when interviewers are not always present at the factory, the interview itself becomes difficult and inefficient. There is a need for a system that can solve these issues.

[1080] 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.

[1081] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the emotion engine to analyze emotion data based on the user's answers; a means for the server to store the evaluation results by the generation AI and the emotion engine in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; and a means for the robot assistant to present questions for the job interview and collect voice responses from the applicant. This enables fair and efficient personnel evaluation, and makes it possible to achieve an efficient interview process even when an interviewer is not present, particularly in job interviews at factories, etc.

[1082] A "user" is a person who uses this system to log in and input answers to the position they are applying for.

[1083] A "server" is a computer device that processes and manages information, stores data entered by users and evaluation results in a database, and notifies users of such data.

[1084] "Login Information" means authentication information such as ID and password required for a User to access the System.

[1085] "Applied position" is information about the type of job or position for which the user is applying.

[1086] A "question list" is a set of questions generated based on the position being applied for, which are presented to the applicant during the interview.

[1087] "Generative AI" is an artificial intelligence technology that analyzes user responses and generates evaluations.

[1088] "Evaluation results" are data on user responses analyzed by the generative AI and emotion engine, including evaluation scores and comments.

[1089] An "emotion engine" is a technology that analyzes emotions based on user responses and extracts emotional data from voice and text.

[1090] The "database" is an information management system for storing evaluation results and interview data.

[1091] A "robot assistant" is an artificial intelligence-equipped device that has the ability to pose questions during job interviews and collect applicants' voice responses.

[1092] The "final interviewer" is the person whose role it is to make the final hiring decision based on all interview data.

[1093] "Interview data" refers to all information related to the interview, such as the user's answers, emotional data, and evaluation results.

[1094] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient personnel evaluation. This system can support efficient interview processes, especially in recruitment interviews at factories, even when interviewers are not present.

[1095] System Program

[1096] User Login

[1097] The user enters their ID and password on the login screen, and the server authenticates this login information. After successful authentication, the server generates a session ID and sends it to the user's device.

[1098] Question list generation and presentation

[1099] The server generates a list of questions based on the user's applied position information, and the list of questions is presented to the user via the user terminal or robot assistant.

[1100] Collecting response and sentiment data

[1101] When a user answers a question by typing or speaking, the robot assistant collects the voice data and the emotion engine analyzes the emotion from the voice data.

[1102] Evaluation by generative AI and emotion engine

[1103] The server passes the user's response data and emotion data to the AI ​​generator to generate an evaluation. The generated evaluation score and emotion data are stored in a database.

[1104] Notification of evaluation results

[1105] The server converts the evaluation results into a format suitable for the user and sends them to the user's terminal, where they are displayed.

[1106] Integration of final interview data

[1107] The server aggregates all the interview data and generates a report to be provided to the final interviewer, who then sends the report to his / her terminal.

[1108] Hardware and Software

[1109] EmotionEngine: Software for analyzing emotions in voice and text data

[1110] EvaluationModel: Evaluation model using generative AI

[1111] Robot assistants: AI-powered devices that pose questions and collect spoken responses

[1112] Server: A computer device that processes and manages information, stores evaluation results in a database, and sends notifications.

[1113] Specific examples

[1114] When a user applies for a software engineer position, the server follows this sequence:

[1115] 1. The server generates questions for software engineers, such as "Tell me about your past project experience."

[1116] 2. The user types or speaks the answer, "I have worked on developing web applications in the past..."

[1117] 3. The emotion engine analyzes the voice data and generates emotion data.

[1118] 4. The server and the generation AI work together to evaluate the user's technical skills and emotions and generate a score such as "Project management skills: 80 / 100."

[1119] 5. The server converts the evaluation results into a different format and notifies the user device, "Your evaluation score is 85 / 100. Reliable emotional expression was observed."

[1120] Prompt Sentence Examples

[1121] "I'm applying for a factory machine operator position. Please generate a list of questions for this position."

[1122] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1123] Step 1:

[1124] The user enters their login information.

[1125] Input: The user enters the ID and password.

[1126] Operation: The user's device displays the login screen, and the user enters their ID and password.

[1127] Output: Login information is sent from the user terminal to the server.

[1128] Step 2:

[1129] The server authenticates the user's login information.

[1130] Input: The server receives the user's ID and password.

[1131] How it works: The server checks the database and verifies the login information.

[1132] Output: When authentication is successful, the server generates a session ID and sends it to the user's device.

[1133] Step 3:

[1134] The server generates a list of questions based on the position the user is applying for.

[1135] Input: User's application information for the position.

[1136] Operation: The server references the database and creates a list of questions corresponding to the position being applied for.

[1137] Output: The generated question list is sent to the user terminal or robot assistant.

[1138] Step 4:

[1139] The user enters answers into the questionnaire.

[1140] Input: Question list sent from the server.

[1141] Action: The user types in or speaks a response.

[1142] Output: The user device or robot assistant collects the answers and sends them to the server.

[1143] Step 5:

[1144] The server passes the user's answers to the generation AI for evaluation.

[1145] Input: User response data.

[1146] How it works: The server passes the user's text response to the generative AI model for analysis.

[1147] Output: The ratings generated by the generation AI are sent back to the server.

[1148] Step 6:

[1149] The emotion engine analyzes the emotion data based on the user's responses.

[1150] Input: User's voice response data.

[1151] How it works: The emotion engine analyzes the voice data and generates emotion data.

[1152] Output: The analyzed emotion data is sent to the server.

[1153] Step 7:

[1154] The server stores the evaluation results from the generation AI and emotion engine in a database.

[1155] Input: Evaluation data from generative AI and emotion data from emotion engine.

[1156] Operation: The server integrates and stores the rating data and emotion data in a database.

[1157] Output: A database entry containing the evaluation results and emotion data.

[1158] Step 8:

[1159] The server notifies the user of the evaluation results.

[1160] Input: Evaluation results stored in a database.

[1161] Operation: The server converts the evaluation results into a notification format and sends them to the user terminal.

[1162] Output: The user is notified of the evaluation results.

[1163] Step 9:

[1164] The server consolidates all the interview data and generates a report that is provided to the final interviewer.

[1165] Input: All interview data.

[1166] How it works: The server analyzes the data and creates a report for the final interviewer.

[1167] Output: The generated report is sent to the terminal of the final interviewer.

[1168] 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.

[1169] 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.

[1170] 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.

[1171] [Third embodiment]

[1172] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1173] 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.

[1174] 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).

[1175] 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.

[1176] 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.

[1177] 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).

[1178] 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.

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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."

[1184] This invention is a human resource recruitment evaluation system that uses generative AI. This system automates the entire interview process and eliminates the subjectivity of interviewers by conducting quantitative evaluations, thereby reducing the risk of mismatch and improving the efficiency of recruitment.

[1185] System Overview

[1186] 1. User login

[1187] The terminal displays a login screen to the user, and the user enters their ID and password.

[1188] The server receives the login information and checks it against the data stored in the database.

[1189] After successful authentication, the server generates a session ID and sends it back to the terminal.

[1190] 2. Question list generation and presentation

[1191] The server generates an appropriate list of questions based on the user's applied position information.

[1192] The terminal displays the generated list of questions to the user.

[1193] 3. Enter and submit your answers

[1194] The user inputs answers to the questions and presses the send button.

[1195] The terminal transmits the inputted answer to the server.

[1196] 4. Evaluation by generative AI

[1197] The server passes the received answer to the generative AI model.

[1198] The generative AI analyzes the answers based on past learning data and calculates a score for each question.

[1199] The server stores the evaluation results of the generated AI in a database.

[1200] 5. Notification of evaluation results

[1201] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[1202] The terminal displays the evaluation results to the user.

[1203] 6. Integration of final interview data

[1204] The server consolidates all process data and generates a report for the final interviewer.

[1205] The server sends the report to the terminal of the final interviewer.

[1206] Specific examples

[1207] 1. User login

[1208] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[1209] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[1210] The terminal retains the received session ID for the user and displays the dashboard.

[1211] 2. Question list generation and presentation

[1212] The server recognizes that the user is applying for a position as a "Software Engineer."

[1213] The server generates a list of questions for software engineers and sends it to the terminal.

[1214] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[1215] 3. Enter and submit your answers

[1216] The user enters an answer to the question and presses the submit button. For example, the user enters "I have been involved in developing web applications in the past..."

[1217] The device sends the response in JSON format to the server.

[1218] 4. Evaluation by generative AI

[1219] The server inputs the received answers into the generation AI.

[1220] The generating AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100."

[1221] The server stores the generated scores in a database.

[1222] 5. Notification of evaluation results

[1223] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[1224] The device displays to the user, "Your rating score is 85 / 100."

[1225] 6. Integration of final interview data

[1226] The server consolidates all interview process data and generates a report for the final interview page.

[1227] The server sends the report to the terminal of the final interviewer.

[1228] This system automates all steps from user application to evaluation, enabling efficient and fair recruitment.

[1229] The processing flow will be explained below.

[1230] Step 1:

[1231] The user enters their ID and password on the login screen and clicks the "Login" button.

[1232] Step 2:

[1233] The device sends the entered ID and password to the server.

[1234] Step 3:

[1235] The server checks the received ID and password against the user information in the database.

[1236] Step 4:

[1237] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[1238] Step 5:

[1239] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[1240] Step 6:

[1241] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[1242] Step 7:

[1243] The server sends the generated question list to the terminal.

[1244] Step 8:

[1245] The terminal displays the received list of questions to the user, allowing the user to input answers.

[1246] Step 9:

[1247] The user enters answers to each question and clicks the submit button.

[1248] Step 10:

[1249] The device sends the user's answer in JSON format to the server.

[1250] Step 11:

[1251] The server validates the response it receives to ensure there is no missing or incorrect data.

[1252] Step 12:

[1253] The server passes the verified answer data to the generative AI model.

[1254] Step 13:

[1255] The generative AI analyzes the answers it receives and calculates a score for each question.

[1256] Step 14:

[1257] The generated AI returns the calculated score to the server.

[1258] Step 15:

[1259] The server stores the scores received from the generated AI in a database.

[1260] Step 16:

[1261] The server converts the saved score data into a format that can be notified to the user and transmits it to the terminal.

[1262] Step 17:

[1263] The device displays the evaluation result to the user, for example, "Your overall score is 85 / 100."

[1264] Step 18:

[1265] The server consolidates all interview process data to generate a report for the final interview.

[1266] Step 19:

[1267] The server sends the generated report to the terminal of the final interviewer.

[1268] Step 20:

[1269] The final interviewer will make the final decision based on the report provided.

[1270] Example 1

[1271] 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."

[1272] Conventional recruitment evaluation systems have the problem that the interviewer's subjectivity is easily involved, making it difficult to achieve fair evaluations. Furthermore, the interview process is conducted manually, which reduces recruitment efficiency and increases the risk of mismatches. Furthermore, the management of applicant responses and notification of evaluation results are not centralized, making the entire process cumbersome.

[1273] 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.

[1274] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; a means for the terminal to display a login screen to the user and prompt the user to input an ID and password; a means for the server to generate a session ID and send it back to the terminal if authentication is successful; and a means for the server to send the answers entered by the user to the server in JSON format. This enables automation of the interview process, fair evaluation, and efficient management.

[1275] A "user" is an individual or organization that uses the system, and is primarily responsible for entering login information and answering questions on the questionnaire.

[1276] A "terminal" is a device operated by a user, and is used to display a login screen and a list of questions and to send answers to a server.

[1277] The "server" is the central control device of the system, and is a device that authenticates user login information, generates a list of questions, evaluates answers, notifies users of the evaluation results, and integrates data.

[1278] "Login information" refers to authentication information for a user to access a system, and is usually composed of a user ID and password.

[1279] A "session ID" is a unique identifier generated by the server when a user logs in to the system, and is used to manage the login session.

[1280] A "question list" is a set of questions generated by the server based on the user's application for a position, and used to evaluate the user's skills and experience.

[1281] "Generative AI" is an artificial intelligence model that analyzes user responses and provides quantitative evaluations.

[1282] "Database" means a data management system for the server to store assessment results and other interview process data.

[1283] A "report" is a document that is generated by the server by integrating all interview data and provided to the final interviewer, and includes the user's evaluation results and the like.

[1284] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight data exchange format for concisely expressing data structures, and is primarily used to exchange data between servers and terminals.

[1285] This invention is a human resource recruitment evaluation system that uses a generative AI model. This system automates the entire interview process and eliminates the subjectivity of interviewers by performing quantitative evaluations, thereby reducing the risk of mismatch and improving recruitment efficiency. Below, we will explain in detail each element that makes up this system.

[1286] System configuration

[1287] This system operates through the mutual cooperation of three entities: the server, the terminal, and the user.

[1288] Server: The central control unit of the system, which performs major processes such as login authentication, question list generation, calculation and storage of evaluation results, and data integration.

[1289] Terminal: A device operated by the user that presents a list of questions, allows users to input answers, and displays evaluation results.

[1290] User: An applicant who uses the system and is the entity that enters login information and answers the questionnaire.

[1291] This system uses the following technical elements:

[1292] Generative AI model: An artificial intelligence model that analyzes input answers and makes a quantitative evaluation.

[1293] Database: Data storage for saving assessment results and interview process data.

[1294] Hardware and Software Configuration

[1295] 1. Login Process

[1296] The terminal displays a login screen to the user, and the user enters their ID and password. The terminal sends this to the server, which collates it with the information stored in the database. If the collation is successful, the server generates a session ID and sends it back to the terminal. Using this session ID, the user can access the system.

[1297] 2. Question list generation and presentation

[1298] The server retrieves the user's application position information from the database and generates a list of questions based on the information, which is then sent to the terminal and displayed to the user.

[1299] 3. Enter and submit your answers

[1300] The user enters answers to the questions and presses the submit button. The terminal sends the answers in JSON format to the server. For example, in response to the question "Tell us about your past project experience," the user enters "I have been in charge of developing web applications in the past."

[1301] 4. Evaluation Process

[1302] The server passes the received answer to the generative AI model for analysis. The generative AI model calculates a score for the user's answer based on past learning data. For example, a score of "Project management skills: 80 / 100" may be generated. The server stores this evaluation result in a database.

[1303] 5. Notification of evaluation results

[1304] The server converts the evaluation results into a format suitable for the user and sends it to the terminal. The terminal displays the results to the user. For example, it displays "Your evaluation score is 85 / 100."

[1305] 6. Integration of final interview data

[1306] The server aggregates all interview data and generates a report for the final interviewer, which is sent to the final interviewer's terminal.

[1307] Specific examples

[1308] Example prompt sentence:

[1309] "Tell me about your past project experience."

[1310] "What skills can you best contribute to this position?"

[1311] Tell us about your experience as a team leader.

[1312] Using these technologies and processes, the system automates all steps from users' applications to evaluations, enabling efficient and fair recruitment.

[1313] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1314] Step 1: User Login

[1315] 1. The device displays a login screen to the user.

[1316] Input: User ID and password

[1317] Output: Display of input form

[1318] Specific behavior: The device renders the HTML of the login screen and displays it to the user.

[1319] 2. The user enters their ID and password and presses the "Login" button.

[1320] Input: User ID (e.g., "user123") and password (e.g., "password123")

[1321] Output: Authentication request from device to server

[1322] Specific Action: The user enters data into the input fields and clicks the submit button.

[1323] 3. The device sends the login information entered by the user to the server.

[1324] Input: User ID and password

[1325] Output: Authentication request to the server (JSON format)

[1326] Specific operation: The device sends login information in JSON format to the server.

[1327] 4. The server checks the received login information against its database.

[1328] Input: Login information (user ID and password)

[1329] Output: Authentication result (success or failure)

[1330] Specific operation: The server queries the database to check whether the entered user ID and password match.

[1331] 5. If authentication is successful, the server generates a session ID and sends it back to the terminal.

[1332] Input: Authentication successful

[1333] Output: Session ID (e.g. "abc123")

[1334] Specific operation: The server generates a session ID and sends it to the terminal.

[1335] 6. The device retains the received session ID and displays the dashboard.

[1336] Input: Session ID

[1337] Output: Dashboard screen

[1338] Specific operation: The device saves the session ID in local storage and displays the user dashboard.

[1339] Step 2: Generate and present a list of questions

[1340] 1. The server retrieves the user's application position information from the database.

[1341] Input: User ID

[1342] Output: Position information (e.g. "Software Engineer")

[1343] Specific operation: The server queries the database to obtain information about the user's applied position.

[1344] 2. The server generates a list of questions based on the position applied for.

[1345] Input: Position information

[1346] Output: Question list (e.g. "Tell me about your past project experience")

[1347] Specific operation: The server dynamically generates a list of questions from a question template according to the position being applied for.

[1348] 3. The server sends the generated question list to the terminal.

[1349] Input: Question List

[1350] Output: Data sent to the terminal (JSON format)

[1351] Specific operation: The server sends the generated question list to the terminal in JSON format.

[1352] 4. The terminal displays the received list of questions to the user.

[1353] Input: Question List

[1354] Output: Question list screen

[1355] Specific operation: The terminal renders the question list in HTML format and displays it to the user.

[1356] Step 3: Enter and submit your answers

[1357] 1. The user enters answers to the questions and presses the submit button.

[1358] Input: Answer (e.g., "I have worked on web application development in the past")

[1359] Output: Input data to the terminal

[1360] Specific action: The user enters an answer to a question in the text field and clicks the submit button.

[1361] 2. The device sends the entered answer in JSON format to the server.

[1362] Input: Answer content (JSON format)

[1363] Output: Data sent to the server

[1364] Specific operation: The device converts the response into JSON format and sends it to the server.

[1365] Step 4: Evaluation by generative AI

[1366] 1. The server inputs the received answers into a generative AI model.

[1367] Input: Answer (e.g., "I have worked on web application development in the past")

[1368] Output: Input data to a generative AI model

[1369] Specific operation: The server passes the answer data to the generative AI model.

[1370] 2. The generative AI analyzes the answers and calculates a score for each question.

[1371] Input: Answer

[1372] Output: Score (e.g. "Project Management Skills: 80 / 100")

[1373] Specific operation: The generative AI model analyzes the answers and calculates an evaluation score based on the training data.

[1374] 3. The server stores the generated scores in a database.

[1375] Input: Score

[1376] Output: Data saved to database

[1377] Specific operation: The server saves the score data in a database.

[1378] Step 5: Notification of evaluation results

[1379] 1. The server converts the evaluation results into a format that can be notified to the user.

[1380] Input: Score

[1381] Output: Notification data (e.g. "Your rating score is 85 / 100")

[1382] Specific operation: The server converts the score data into a format that can be notified to the user.

[1383] 2. The server sends the converted evaluation results to the terminal.

[1384] Input: Notification data

[1385] Output: Data sent to the terminal

[1386] Specific operation: The server sends notification data in JSON format to the device.

[1387] 3. The device displays the evaluation results to the user.

[1388] Input: Notification data

[1389] Output: Evaluation result screen

[1390] Specific operation: The device renders the notification data in HTML format and displays it to the user.

[1391] Step 6: Consolidating the final interview data

[1392] 1. The server aggregates all the interview data.

[1393] Input: Interview process data

[1394] Output: Integrated data

[1395] Specific operation: The server analyzes multiple interview data sets and creates a single integrated dataset.

[1396] 2. The server generates a report for the final interviewer.

[1397] Input: Integrated data

[1398] Output: Report (e.g. "Comprehensive report of user rating scores")

[1399] Specific operation: The server generates a report for the final interviewer based on the integrated data.

[1400] 3. The server sends the generated report to the terminal of the final interviewer.

[1401] Input: Report

[1402] Output: Report data sent to the terminal

[1403] Specific operation: The server sends the report in JSON format to the terminal and displays it on the terminal of the final interviewer.

[1404] The above is the specific flow of program processing in the present invention.

[1405] (Application example 1)

[1406] 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."

[1407] Conventional methods for evaluating the skills of factory workers require a lot of time and effort, and are heavily influenced by the evaluator's subjectivity, resulting in problems with the fairness and efficiency of the evaluation. In particular, artificial bias in evaluations and a lack of consistency in evaluation criteria hinder worker motivation and appropriate personnel allocation. This makes it difficult to design training plans and determine optimal personnel allocation.

[1408] 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.

[1409] In this invention, the server includes a means for a user to input login information, a means for the server to authenticate the user's login information, a means for the server to generate a list of questions based on the user's role, a means for the user to input answers to the list of questions, a means for the server to pass the user's answers to a generative AI model for evaluation, a means for the server to store the evaluation results by the generative AI model in a database, a means for the server to notify the user of the evaluation results, and a means for the server to integrate all evaluation data and generate a report to be provided to a manager. This enables efficient and fair evaluation of the skills of workers in a factory, enabling appropriate personnel allocation and the creation of training plans.

[1410] A "user" is a worker or operator who has access to the system, enters answers to a questionnaire, and is evaluated.

[1411] "Login information" refers to the authentication information required for a user to access a system, and is usually composed of a user ID and password.

[1412] "Server" refers to a device or software that processes and manages data for the entire system.

[1413] A "question list" is a set of questions for skill evaluation that is created by the server based on the user's role and work responsibilities.

[1414] A "generative AI model" is an artificial intelligence model that analyzes user responses based on past learning data and generates quantitative evaluation results.

[1415] "Database" means a digital data storage device for storing all evaluation data and login information for the System.

[1416] "Evaluation results" refer to scores such as skills and work efficiency calculated by the generative AI model by analyzing the user's responses.

[1417] A "report" is a written or digital document that the server generates to consolidate all evaluation data and provide to an administrator.

[1418] "Authentication" is the process by which a server receives a user's login information and verifies the user's legitimacy by checking it against information in a database.

[1419] "JSON format" is a structured data format for exchanging user responses, and is an abbreviation for JavaScript Object Notation.

[1420] This invention is an efficient and fair evaluation system that improves on the conventional method of evaluating the skills of factory workers. The system begins with the user entering login information, which is authenticated by the server, and then evaluates the user's skills using a generative AI model. The evaluation results are stored in a database and provided to managers as a report.

[1421] The server uses Flask (a Python web framework) to authenticate the login information of workers and operators when they access the system. This login information mainly consists of a user ID and password. If authentication is successful, the server generates a session ID and sends it to the user's terminal.

[1422] The server then generates a questionnaire based on the logged-in user's role and responsibilities, tailored to the user's specific tasks and skill set, and displays the questionnaire on a smartphone, tablet, or other device.

[1423] When a user enters answers into the question list, the answers are sent to the server in JSON format. The server then passes the received answers to the generative AI model, which analyzes them based on past learning data. As a result of the analysis, a score is calculated based on the user's skills, work efficiency, etc.

[1424] The generated evaluation results are stored in a database, and the server notifies the user. The evaluation result notification allows users to check their own skill evaluation and use it for future training and self-improvement. The server also consolidates all evaluation data to generate a report and provides it to managers. This allows managers to understand the skill status of their workers and design appropriate personnel assignments and training plans.

[1425] A specific example of this system is shown below.

[1426] Specific examples

[1427] 1. Log in:

[1428] The user enters "user123" and "password123" on the tablet and presses the login button.

[1429] The server authenticates the login information, generates a session ID "session_1234", and sends it to the terminal.

[1430] 2. Generate a list of questions:

[1431] The server recognizes the user's role as a "parts assembler" and generates an appropriate list of questions.

[1432] For example, questions such as "Tell us about your work environment recently" and "What was the most difficult task you had in the past week?" will be displayed.

[1433] 3. Enter and submit your answers:

[1434] The user answers the questions by typing "The working environment was comfortable" and "The most difficult task during the week was assembling the cooling device," and then presses the send button.

[1435] The device sends the entered answer in JSON format to the server.

[1436] 4. Generative AI evaluation:

[1437] The server analyzes the answers it receives using a generative AI model to generate scores such as "Skill evaluation: 90 / 100, work efficiency: 85 / 100."

[1438] 5. Notification of evaluation results:

[1439] The server sends the evaluation results to the terminal and displays to the user, "Your evaluation scores are skill rating 90 / 100 and work efficiency 85 / 100."

[1440] 6. Generate the final report:

[1441] The server consolidates all the evaluation data and generates reports for administrators, who can use these reports to design appropriate training plans.

[1442] This system will enable efficient and fair evaluation of the skills of workers within factories, leading to appropriate staffing and training.

[1443] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1444] Step 1:

[1445] The server authenticates the user's login information. The user enters their user ID and password into the login screen on a device such as a tablet and submits it. The server receives the submitted information and compares it with the information in its database. If authentication is successful, the server generates a session ID and submits it to the user's device. This session ID is used to identify the user in subsequent processes.

[1446] Input: User ID, Password

[1447] Output: Session ID

[1448] Step 2:

[1449] The server generates a questionnaire based on the role of the logged-in user. After the user is properly authenticated, the server retrieves the user's role (e.g., parts assembly worker) from the database. Then, it generates a questionnaire appropriate for the user's role and sends it to the terminal. The user's terminal displays this questionnaire.

[1450] Input: Session ID, User Role

[1451] Output: Question list

[1452] Step 3:

[1453] The user enters answers to the presented list of questions and sends them from the device to the server. The user enters answers to the questions using a tablet or smartphone and presses the send button. The device sends the entered answers in JSON format to the server.

[1454] Input: Question list, user answers

[1455] Output: JSON formatted response data

[1456] Step 4:

[1457] The server passes the received answers to the generative AI model for evaluation. The server inputs the JSON-formatted answer data received from the user into the generative AI model and requests analysis. The generative AI model analyzes the user's answers based on past learning data and calculates scores for skill and work efficiency.

[1458] Input: JSON formatted response data

[1459] Output: Evaluation score (e.g., skill rating 90 / 100, work efficiency 85 / 100)

[1460] Step 5:

[1461] The server saves the evaluation results from the generative AI model in a database and notifies the user. The generated evaluation results are saved in a database by the server. The server then sends the evaluation results to the user's device, where the user can check the displayed score.

[1462] Input: Rating score

[1463] Output: Notify user, save to database

[1464] Step 6:

[1465] The server consolidates all the evaluation data and generates a report to be provided to the manager. The server aggregates and consolidates the evaluation data of multiple users. It then generates a report that allows the manager to grasp the overall status of workers in the factory and sends it to the manager's terminal. The manager can use this report to optimize training plans and personnel deployment.

[1466] Input: A set of evaluation data

[1467] Output: Report for administrator

[1468] 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.

[1469] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system authenticates the user's login information, generates a list of questions based on the position being applied for, and analyzes the user's answers and emotions. The analysis results are stored in a database as evaluation results and reflected in a report provided to the final interviewer.

[1470] System Overview

[1471] 1. User login

[1472] The terminal displays a login screen to the user, and the user enters their ID and password.

[1473] The server receives the login information and checks it against a database.

[1474] After successful authentication, the server generates a session ID and sends it back to the terminal.

[1475] 2. Question list generation and presentation

[1476] The server generates a list of questions based on the user's applied position information.

[1477] The terminal displays the generated list of questions to the user.

[1478] 3. Enter and submit answers and emotion data

[1479] The user enters answers into the question list and presses the submit button.

[1480] The device sends the input answer and emotion data to the server.

[1481] 4. Evaluation using generative AI and emotion engine

[1482] The server passes the received answer to the generation AI.

[1483] The emotion engine analyzes the emotions from the voice and text of the user's responses.

[1484] The generating AI evaluates the answers and analyzed emotional data and calculates a score.

[1485] The server stores the evaluation results from the generation AI and emotion engine in a database.

[1486] 5. Notification of evaluation results

[1487] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[1488] The terminal displays the evaluation results to the user.

[1489] 6. Integration of final interview data

[1490] The server consolidates all process data and generates a report for the final interviewer.

[1491] The server sends the report to the terminal of the final interviewer.

[1492] Specific examples

[1493] 1. User login

[1494] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[1495] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[1496] The terminal retains the received session ID and displays the dashboard.

[1497] 2. Question list generation and presentation

[1498] The server recognizes that the user is applying for a position as a "Software Engineer."

[1499] The server generates a list of questions for software engineers and sends it to the terminal.

[1500] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[1501] 3. Enter and submit answers and emotion data

[1502] The user answers the question by saying, "I have worked on developing web applications in the past..."

[1503] The emotion engine analyzes the user's voice and text and generates emotion data.

[1504] The device sends the user's answers and emotion data in JSON format to the server.

[1505] 4. Evaluation using generative AI and emotion engine

[1506] The server inputs the answers and emotional data into the generation AI.

[1507] The generating AI analyzes the answers and generates a score such as "Project management skills: 80 / 100."

[1508] The emotion engine passes the analyzed emotion data to the generation AI.

[1509] The server stores the generated scores and emotion data in a database.

[1510] 5. Notification of evaluation results

[1511] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[1512] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[1513] 6. Integration of final interview data

[1514] The server consolidates all interview process data and generates a report for the final interview page.

[1515] The server sends the report to the terminal of the final interviewer.

[1516] This system achieves more accurate and fair evaluation of personnel by combining the user's responses with their emotions.

[1517] The processing flow will be explained below.

[1518] Step 1:

[1519] The user enters their ID and password on the login screen and clicks the "Login" button.

[1520] Step 2:

[1521] The device sends the entered ID and password to the server.

[1522] Step 3:

[1523] The server checks the received ID and password against the user information in the database.

[1524] Step 4:

[1525] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[1526] Step 5:

[1527] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[1528] Step 6:

[1529] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[1530] Step 7:

[1531] The server sends the generated question list to the terminal.

[1532] Step 8:

[1533] The terminal displays the received list of questions to the user, allowing the user to input answers.

[1534] Step 9:

[1535] The user enters answers to each question and clicks the submit button.

[1536] Step 10:

[1537] When the user inputs something, the emotion engine analyzes the audio and video to detect the user's emotional state.

[1538] Step 11:

[1539] The emotion engine generates emotion analysis data and transmits the data to the server.

[1540] Step 12:

[1541] The device sends the user's answer in JSON format to the server.

[1542] Step 13:

[1543] The server receives the response data and emotion data and validates both data to check for missing or inappropriate data.

[1544] Step 14:

[1545] The server passes verified response data and emotion data to the generative AI model.

[1546] Step 15:

[1547] The generative AI analyzes the answers it receives and calculates a score for each question.

[1548] Step 16:

[1549] The generative AI calculates an overall score or rating that takes emotional data into account.

[1550] Step 17:

[1551] The generated AI returns the calculated score to the server.

[1552] Step 18:

[1553] The server stores the scores and sentiment analysis data received from the generation AI in a database.

[1554] Step 19:

[1555] The server converts the evaluation results (score and emotion analysis results) into a format that can be notified to the user and sends them to the terminal.

[1556] Step 20:

[1557] The device will display the evaluation results to the user, such as "Your overall score is 85 / 100. Sentiment analysis has confirmed this is a reliable answer."

[1558] Step 21:

[1559] The server consolidates all interview process data (answer data, emotion data, scores, etc.) and generates a report for the final interviewer.

[1560] Step 22:

[1561] The server sends the generated report to the terminal of the final interviewer.

[1562] Step 23:

[1563] The final interviewer will make the final decision based on the report provided.

[1564] Example 2

[1565] 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."

[1566] In conventional recruitment processes, evaluation criteria are often subjective, resulting in unfair screening. Furthermore, the burden on interviewers is heavy, making efficient talent evaluation difficult. Furthermore, evaluations rarely incorporate emotional data, increasing the likelihood of overlooking an applicant's true personality and potential. The present invention aims to solve these problems and achieve fair and efficient talent evaluation.

[1567] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for the user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a question list based on the user's applied position; a means for the user to input answers to the question list; a means for the terminal to acquire the user's answers and emotion data and transmit them to the server; a means for the server to pass the user's answers to the generation AI for evaluation; a means for the server to pass the user's emotion data acquired from the emotion engine to the generation AI; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; and a means for the server to integrate all interview data and generate a report to be provided to the final interviewer. This enables accurate and fair personnel evaluation based on the user's answers and emotions, thereby improving the efficiency and fairness of the hiring process.

[1568] "User" refers to a person who uses the system to log in and enter answers to a list of questions.

[1569] "Server" refers to the computer system that authenticates user login information, generates the question list, analyzes responses and emotional data, stores the evaluation results, and generates a report for the final interviewer.

[1570] "Terminal" refers to a device through which a user accesses the system, enters login information, displays a list of questions, and enters and submits answers.

[1571] "Login Information" refers to the ID and password entered by a User to access the System.

[1572] "Authentication" refers to the process by which a server checks a user's login information against a database to determine whether access is permitted.

[1573] "Applied position" refers to information about the job type or position for which the user is applying.

[1574] A "question list" refers to a set of questions that a user must answer based on the position they are applying for.

[1575] "Answer" refers to the text or audio content that a user enters in response to a list of questions.

[1576] "Emotion data" refers to information about the psychological state and emotions analyzed by the emotion engine from the user's responses.

[1577] "Generative AI" refers to an artificial intelligence model that evaluates and generates a score based on user responses and emotional data.

[1578] "Evaluation results" refers to the score or evaluation calculated based on the user's answers and emotional data analyzed by the generation AI.

[1579] "Database" refers to a data storage system for storing assessment results and other user information.

[1580] "Report" refers to a document that consolidates all interview data and provides it to the final interviewer.

[1581] "Emotion engine" refers to software or algorithms that analyze emotions from a user's voice or text and generate emotion data.

[1582] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system begins when a user enters login information and the server authenticates it. The server then generates a list of questions based on the position the user is applying for, and the terminal displays this to the user. The user enters answers to the list of questions, and the terminal sends the answers and emotion data to the server. The server uses generative AI to evaluate the user's answers and emotion data and stores the results in a database. Finally, the server integrates all the evaluation data and generates a report to be provided to the final interviewer.

[1583] Hardware and software used

[1584] Device: A device operated by a user, such as a PC, tablet, or smartphone

[1585] Server: A hosting environment that includes a web server such as Apache or Nginx, and a database such as MySQL or PostgreSQL.

[1586] Generative AI models: Advanced natural language processing models such as GPT-4

[1587] Emotion engine: Emotion analysis software such as IBM Watson Emotion Analysis

[1588] Program processing

[1589] 1. User login authentication

[1590] The terminal displays a login screen to the user, and the user enters their ID and password.

[1591] The server receives the login information, checks it against a database, and if authentication is successful, generates a session ID and sends it back to the terminal.

[1592] 2. Generating and presenting a list of questions

[1593] The server generates a list of questions based on the user's application information for the position. For example, it generates a list of questions for a software engineer.

[1594] The terminal displays the generated list of questions to the user, for example, "Tell me about your past project experience."

[1595] 3. Enter and submit answers and emotion data

[1596] The user answers the questions and presses the submit button. For example, they enter a specific answer such as "I have worked on developing web applications in the past..."

[1597] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[1598] The device sends the user's answers and emotion data in JSON format to the server.

[1599] 4. Evaluation using generative AI and emotion engine

[1600] The server passes the received answers and emotion data to the generation AI, using, for example, GPT-4.

[1601] The generating AI analyzes the answers and generates a score of "Project management skills: 80 / 100."

[1602] The emotion data analyzed by the emotion engine is passed to the generative AI and incorporated as part of the evaluation.

[1603] The server stores the generated scores and emotion data in a database.

[1604] 5. Notification of evaluation results

[1605] The server converts the evaluation results into a format that can be communicated to the user and sends them to the terminal.

[1606] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[1607] 6. Integration of final interview data

[1608] The server consolidates all process data and generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[1609] The server sends the report to the terminal of the final interviewer.

[1610] Prompt Sentence Examples

[1611] The following prompt sentences are fed into the generative AI model to evaluate the user's responses and emotional data:

[1612] Please rate based on the following answers and sentiment data: Answer: "I have worked on web application development in the past." Sentiment data: "Positive, enthusiastic."

[1613] This system combines user responses with emotional data to make evaluations, enabling more accurate and fairer personnel evaluations.

[1614] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1615] Step 1:

[1616] Displaying the login screen and user authentication

[1617] The device displays a login screen, which includes fields for entering your ID and password.

[1618] The user enters their ID and password and clicks the "Login" button.

[1619] The terminal sends the entered ID and password to the server. The input data includes credential information for authentication.

[1620] The server checks the received ID and password against the database, and if they match, generates a session ID. It performs database operations for the check and generates a session ID.

[1621] The server sends the generated session ID to the terminal and also includes a success message.

[1622] The device receives the session ID and displays the dashboard.

[1623] Step 2:

[1624] Generate and present questionnaires

[1625] The server retrieves the user's application information, which is retrieved from the database at login time.

[1626] The server generates a list of questions based on a specific job application, for example, a list of questions for a software engineer, using a generative AI model.

[1627] The server sends the generated question list to the terminal.

[1628] The terminal displays the received question list to the user. For example, a specific example of the question is "Tell us about your past project experience."

[1629] Step 3:

[1630] Enter and submit answers and emotion data

[1631] The user inputs answers to the list of questions. For example, the user inputs a specific answer such as "I have been involved in developing web applications in the past."

[1632] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[1633] The device sends the user's answer and the generated emotion data in JSON format to the server. The input data includes the user's answer text and emotion analysis data.

[1634] The server parses the received JSON data and prepares it for use in the next step.

[1635] Step 4:

[1636] Evaluation by generative AI and emotion engine

[1637] The server inputs the received answers and sentiment data into a generative AI, for example, using a natural language processing model such as GPT-4.

[1638] The generative AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100." The input to the generative AI model is the user's answers and emotional data.

[1639] The emotion engine passes the analyzed emotion data to the generation AI, which takes this into consideration when making an evaluation.

[1640] The server stores the generated scores and emotion data in a database. The output data includes the evaluation scores and emotion data.

[1641] Step 5:

[1642] Notification of evaluation results

[1643] The server converts the evaluation results into a format that can be notified to the user. The server generates evaluation results and formats them in a format that is easy for the user to understand.

[1644] The server transmits the evaluation results to the terminal.

[1645] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[1646] Step 6:

[1647] Integration of final interview data

[1648] The server aggregates all interview process data, including each user's answers, emotional data, and the evaluation results of the generative AI.

[1649] The server generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[1650] The server sends the report to the terminal of the final interviewer.

[1651] (Application example 2)

[1652] 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."

[1653] The traditional recruitment process involves a lot of manual work and relies heavily on the interviewer's subjectivity, making it difficult to achieve fair and efficient evaluations. It is also difficult to properly analyze the applicant's emotions during the interview and reflect them in the evaluation. In particular, when interviewers are not always present at the factory, the interview itself becomes difficult and inefficient. There is a need for a system that can solve these issues.

[1654] 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.

[1655] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the emotion engine to analyze emotion data based on the user's answers; a means for the server to store the evaluation results by the generation AI and the emotion engine in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; and a means for the robot assistant to present questions for the job interview and collect voice responses from the applicant. This enables fair and efficient personnel evaluation, and makes it possible to achieve an efficient interview process even when an interviewer is not present, particularly in job interviews at factories, etc.

[1656] A "user" is a person who uses this system to log in and input answers to the position they are applying for.

[1657] A "server" is a computer device that processes and manages information, stores data entered by users and evaluation results in a database, and notifies users of such data.

[1658] "Login Information" means authentication information such as ID and password required for a User to access the System.

[1659] "Applied position" is information about the type of job or position for which the user is applying.

[1660] A "question list" is a set of questions generated based on the position being applied for, which are presented to the applicant during the interview.

[1661] "Generative AI" is an artificial intelligence technology that analyzes user responses and generates evaluations.

[1662] "Evaluation results" are data on user responses analyzed by the generative AI and emotion engine, including evaluation scores and comments.

[1663] An "emotion engine" is a technology that analyzes emotions based on user responses and extracts emotional data from voice and text.

[1664] The "database" is an information management system for storing evaluation results and interview data.

[1665] A "robot assistant" is an artificial intelligence-equipped device that has the ability to pose questions during job interviews and collect applicants' voice responses.

[1666] The "final interviewer" is the person whose role it is to make the final hiring decision based on all interview data.

[1667] "Interview data" refers to all information related to the interview, such as the user's answers, emotional data, and evaluation results.

[1668] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient personnel evaluation. This system can support efficient interview processes, especially in recruitment interviews at factories, even when interviewers are not present.

[1669] System Program

[1670] User Login

[1671] The user enters their ID and password on the login screen, and the server authenticates this login information. After successful authentication, the server generates a session ID and sends it to the user's device.

[1672] Question list generation and presentation

[1673] The server generates a list of questions based on the user's applied position information, and the list of questions is presented to the user via the user terminal or robot assistant.

[1674] Collecting response and sentiment data

[1675] When a user answers a question by typing or speaking, the robot assistant collects the voice data and the emotion engine analyzes the emotion from the voice data.

[1676] Evaluation by generative AI and emotion engine

[1677] The server passes the user's response data and emotion data to the AI ​​generator to generate an evaluation. The generated evaluation score and emotion data are stored in a database.

[1678] Notification of evaluation results

[1679] The server converts the evaluation results into a format suitable for the user and sends them to the user's terminal, where they are displayed.

[1680] Integration of final interview data

[1681] The server aggregates all the interview data and generates a report to be provided to the final interviewer, who then sends the report to his / her terminal.

[1682] Hardware and Software

[1683] EmotionEngine: Software for analyzing emotions in voice and text data

[1684] EvaluationModel: Evaluation model using generative AI

[1685] Robot assistants: AI-powered devices that pose questions and collect spoken responses

[1686] Server: A computer device that processes and manages information, stores evaluation results in a database, and sends notifications.

[1687] Specific examples

[1688] When a user applies for a software engineer position, the server follows this sequence:

[1689] 1. The server generates questions for software engineers, such as "Tell me about your past project experience."

[1690] 2. The user types or speaks the answer, "I have worked on developing web applications in the past..."

[1691] 3. The emotion engine analyzes the voice data and generates emotion data.

[1692] 4. The server and the generation AI work together to evaluate the user's technical skills and emotions and generate a score such as "Project management skills: 80 / 100."

[1693] 5. The server converts the evaluation results into a different format and notifies the user device, "Your evaluation score is 85 / 100. Reliable emotional expression was observed."

[1694] Prompt Sentence Examples

[1695] "I'm applying for a factory machine operator position. Please generate a list of questions for this position."

[1696] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1697] Step 1:

[1698] The user enters their login information.

[1699] Input: The user enters the ID and password.

[1700] Operation: The user's device displays the login screen, and the user enters their ID and password.

[1701] Output: Login information is sent from the user terminal to the server.

[1702] Step 2:

[1703] The server authenticates the user's login information.

[1704] Input: The server receives the user's ID and password.

[1705] How it works: The server checks the database and verifies the login information.

[1706] Output: When authentication is successful, the server generates a session ID and sends it to the user's device.

[1707] Step 3:

[1708] The server generates a list of questions based on the position the user is applying for.

[1709] Input: User's application information for the position.

[1710] Operation: The server references the database and creates a list of questions corresponding to the position being applied for.

[1711] Output: The generated question list is sent to the user terminal or robot assistant.

[1712] Step 4:

[1713] The user enters answers into the questionnaire.

[1714] Input: Question list sent from the server.

[1715] Action: The user types in or speaks a response.

[1716] Output: The user device or robot assistant collects the answers and sends them to the server.

[1717] Step 5:

[1718] The server passes the user's answers to the generation AI for evaluation.

[1719] Input: User response data.

[1720] How it works: The server passes the user's text response to the generative AI model for analysis.

[1721] Output: The ratings generated by the generation AI are sent back to the server.

[1722] Step 6:

[1723] The emotion engine analyzes the emotion data based on the user's responses.

[1724] Input: User's voice response data.

[1725] How it works: The emotion engine analyzes the voice data and generates emotion data.

[1726] Output: The analyzed emotion data is sent to the server.

[1727] Step 7:

[1728] The server stores the evaluation results from the generation AI and emotion engine in a database.

[1729] Input: Evaluation data from generative AI and emotion data from emotion engine.

[1730] Operation: The server integrates and stores the rating data and emotion data in a database.

[1731] Output: A database entry containing the evaluation results and emotion data.

[1732] Step 8:

[1733] The server notifies the user of the evaluation results.

[1734] Input: Evaluation results stored in a database.

[1735] Operation: The server converts the evaluation results into a notification format and sends them to the user terminal.

[1736] Output: The user is notified of the evaluation results.

[1737] Step 9:

[1738] The server consolidates all the interview data and generates a report that is provided to the final interviewer.

[1739] Input: All interview data.

[1740] How it works: The server analyzes the data and creates a report for the final interviewer.

[1741] Output: The generated report is sent to the terminal of the final interviewer.

[1742] 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.

[1743] 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.

[1744] 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.

[1745] [Fourth embodiment]

[1746] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1747] 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.

[1748] 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).

[1749] 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.

[1750] 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.

[1751] 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).

[1752] 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.

[1753] 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.

[1754] 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.

[1755] 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.

[1756] 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.

[1757] 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.

[1758] 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."

[1759] This invention is a human resource recruitment evaluation system that uses generative AI. This system automates the entire interview process and eliminates the subjectivity of interviewers by conducting quantitative evaluations, thereby reducing the risk of mismatch and improving the efficiency of recruitment.

[1760] System Overview

[1761] 1. User login

[1762] The terminal displays a login screen to the user, and the user enters their ID and password.

[1763] The server receives the login information and checks it against the data stored in the database.

[1764] After successful authentication, the server generates a session ID and sends it back to the terminal.

[1765] 2. Question list generation and presentation

[1766] The server generates an appropriate list of questions based on the user's applied position information.

[1767] The terminal displays the generated list of questions to the user.

[1768] 3. Enter and submit your answers

[1769] The user inputs answers to the questions and presses the send button.

[1770] The terminal transmits the inputted answer to the server.

[1771] 4. Evaluation by generative AI

[1772] The server passes the received answer to the generative AI model.

[1773] The generative AI analyzes the answers based on past learning data and calculates a score for each question.

[1774] The server stores the evaluation results of the generated AI in a database.

[1775] 5. Notification of evaluation results

[1776] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[1777] The terminal displays the evaluation results to the user.

[1778] 6. Integration of final interview data

[1779] The server consolidates all process data and generates a report for the final interviewer.

[1780] The server sends the report to the terminal of the final interviewer.

[1781] Specific examples

[1782] 1. User login

[1783] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[1784] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[1785] The terminal retains the received session ID for the user and displays the dashboard.

[1786] 2. Question list generation and presentation

[1787] The server recognizes that the user is applying for a position as a "Software Engineer."

[1788] The server generates a list of questions for software engineers and sends it to the terminal.

[1789] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[1790] 3. Enter and submit your answers

[1791] The user enters an answer to the question and presses the submit button. For example, the user enters "I have been involved in developing web applications in the past..."

[1792] The device sends the response in JSON format to the server.

[1793] 4. Evaluation by generative AI

[1794] The server inputs the received answers into the generation AI.

[1795] The generating AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100."

[1796] The server stores the generated scores in a database.

[1797] 5. Notification of evaluation results

[1798] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[1799] The device displays to the user, "Your rating score is 85 / 100."

[1800] 6. Integration of final interview data

[1801] The server consolidates all interview process data and generates a report for the final interview page.

[1802] The server sends the report to the terminal of the final interviewer.

[1803] This system automates all steps from user application to evaluation, enabling efficient and fair recruitment.

[1804] The processing flow will be explained below.

[1805] Step 1:

[1806] The user enters their ID and password on the login screen and clicks the "Login" button.

[1807] Step 2:

[1808] The device sends the entered ID and password to the server.

[1809] Step 3:

[1810] The server checks the received ID and password against the user information in the database.

[1811] Step 4:

[1812] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[1813] Step 5:

[1814] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[1815] Step 6:

[1816] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[1817] Step 7:

[1818] The server sends the generated question list to the terminal.

[1819] Step 8:

[1820] The terminal displays the received list of questions to the user, allowing the user to input answers.

[1821] Step 9:

[1822] The user enters answers to each question and clicks the submit button.

[1823] Step 10:

[1824] The device sends the user's answer in JSON format to the server.

[1825] Step 11:

[1826] The server validates the response it receives to ensure there is no missing or incorrect data.

[1827] Step 12:

[1828] The server passes the verified answer data to the generative AI model.

[1829] Step 13:

[1830] The generative AI analyzes the answers it receives and calculates a score for each question.

[1831] Step 14:

[1832] The generated AI returns the calculated score to the server.

[1833] Step 15:

[1834] The server stores the scores received from the generated AI in a database.

[1835] Step 16:

[1836] The server converts the saved score data into a format that can be notified to the user and transmits it to the terminal.

[1837] Step 17:

[1838] The device displays the evaluation result to the user, for example, "Your overall score is 85 / 100."

[1839] Step 18:

[1840] The server consolidates all interview process data to generate a report for the final interview.

[1841] Step 19:

[1842] The server sends the generated report to the terminal of the final interviewer.

[1843] Step 20:

[1844] The final interviewer will make the final decision based on the report provided.

[1845] Example 1

[1846] 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."

[1847] Conventional recruitment evaluation systems have the problem that the interviewer's subjectivity is easily involved, making it difficult to achieve fair evaluations. Furthermore, the interview process is conducted manually, which reduces recruitment efficiency and increases the risk of mismatches. Furthermore, the management of applicant responses and notification of evaluation results are not centralized, making the entire process cumbersome.

[1848] 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.

[1849] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; a means for the terminal to display a login screen to the user and prompt the user to input an ID and password; a means for the server to generate a session ID and send it back to the terminal if authentication is successful; and a means for the server to send the answers entered by the user to the server in JSON format. This enables automation of the interview process, fair evaluation, and efficient management.

[1850] A "user" is an individual or organization that uses the system, and is primarily responsible for entering login information and answering questions on the questionnaire.

[1851] A "terminal" is a device operated by a user, and is used to display a login screen and a list of questions and to send answers to a server.

[1852] The "server" is the central control device of the system, and is a device that authenticates user login information, generates a list of questions, evaluates answers, notifies users of the evaluation results, and integrates data.

[1853] "Login information" refers to authentication information for a user to access a system, and is usually composed of a user ID and password.

[1854] A "session ID" is a unique identifier generated by the server when a user logs in to the system, and is used to manage the login session.

[1855] A "question list" is a set of questions generated by the server based on the user's application for a position, and used to evaluate the user's skills and experience.

[1856] "Generative AI" is an artificial intelligence model that analyzes user responses and provides quantitative evaluations.

[1857] "Database" means a data management system for the server to store assessment results and other interview process data.

[1858] A "report" is a document that is generated by the server by integrating all interview data and provided to the final interviewer, and includes the user's evaluation results and the like.

[1859] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight data exchange format for concisely expressing data structures, and is primarily used to exchange data between servers and terminals.

[1860] This invention is a human resource recruitment evaluation system that uses a generative AI model. This system automates the entire interview process and eliminates the subjectivity of interviewers by performing quantitative evaluations, thereby reducing the risk of mismatch and improving recruitment efficiency. Below, we will explain in detail each element that makes up this system.

[1861] System configuration

[1862] This system operates through the mutual cooperation of three entities: the server, the terminal, and the user.

[1863] Server: The central control unit of the system, which performs major processes such as login authentication, question list generation, calculation and storage of evaluation results, and data integration.

[1864] Terminal: A device operated by the user that presents a list of questions, allows users to input answers, and displays evaluation results.

[1865] User: An applicant who uses the system and is the entity that enters login information and answers the questionnaire.

[1866] This system uses the following technical elements:

[1867] Generative AI model: An artificial intelligence model that analyzes input answers and makes a quantitative evaluation.

[1868] Database: Data storage for saving assessment results and interview process data.

[1869] Hardware and Software Configuration

[1870] 1. Login Process

[1871] The terminal displays a login screen to the user, and the user enters their ID and password. The terminal sends this to the server, which collates it with the information stored in the database. If the collation is successful, the server generates a session ID and sends it back to the terminal. Using this session ID, the user can access the system.

[1872] 2. Question list generation and presentation

[1873] The server retrieves the user's application position information from the database and generates a list of questions based on the information, which is then sent to the terminal and displayed to the user.

[1874] 3. Enter and submit your answers

[1875] The user enters answers to the questions and presses the submit button. The terminal sends the answers in JSON format to the server. For example, in response to the question "Tell us about your past project experience," the user enters "I have been in charge of developing web applications in the past."

[1876] 4. Evaluation Process

[1877] The server passes the received answer to the generative AI model for analysis. The generative AI model calculates a score for the user's answer based on past learning data. For example, a score of "Project management skills: 80 / 100" may be generated. The server stores this evaluation result in a database.

[1878] 5. Notification of evaluation results

[1879] The server converts the evaluation results into a format suitable for the user and sends it to the terminal. The terminal displays the results to the user. For example, it displays "Your evaluation score is 85 / 100."

[1880] 6. Integration of final interview data

[1881] The server aggregates all interview data and generates a report for the final interviewer, which is sent to the final interviewer's terminal.

[1882] Specific examples

[1883] Example prompt sentence:

[1884] "Tell me about your past project experience."

[1885] "What skills can you best contribute to this position?"

[1886] Tell us about your experience as a team leader.

[1887] Using these technologies and processes, the system automates all steps from users' applications to evaluations, enabling efficient and fair recruitment.

[1888] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1889] Step 1: User Login

[1890] 1. The device displays a login screen to the user.

[1891] Input: User ID and password

[1892] Output: Display of input form

[1893] Specific behavior: The device renders the HTML of the login screen and displays it to the user.

[1894] 2. The user enters their ID and password and presses the "Login" button.

[1895] Input: User ID (e.g., "user123") and password (e.g., "password123")

[1896] Output: Authentication request from device to server

[1897] Specific Action: The user enters data into the input fields and clicks the submit button.

[1898] 3. The device sends the login information entered by the user to the server.

[1899] Input: User ID and password

[1900] Output: Authentication request to the server (JSON format)

[1901] Specific operation: The device sends login information in JSON format to the server.

[1902] 4. The server checks the received login information against its database.

[1903] Input: Login information (user ID and password)

[1904] Output: Authentication result (success or failure)

[1905] Specific operation: The server queries the database to check whether the entered user ID and password match.

[1906] 5. If authentication is successful, the server generates a session ID and sends it back to the terminal.

[1907] Input: Authentication successful

[1908] Output: Session ID (e.g. "abc123")

[1909] Specific operation: The server generates a session ID and sends it to the terminal.

[1910] 6. The device retains the received session ID and displays the dashboard.

[1911] Input: Session ID

[1912] Output: Dashboard screen

[1913] Specific operation: The device saves the session ID in local storage and displays the user dashboard.

[1914] Step 2: Generate and present a list of questions

[1915] 1. The server retrieves the user's application position information from the database.

[1916] Input: User ID

[1917] Output: Position information (e.g. "Software Engineer")

[1918] Specific operation: The server queries the database to obtain information about the user's applied position.

[1919] 2. The server generates a list of questions based on the position applied for.

[1920] Input: Position information

[1921] Output: Question list (e.g. "Tell me about your past project experience")

[1922] Specific operation: The server dynamically generates a list of questions from a question template according to the position being applied for.

[1923] 3. The server sends the generated question list to the terminal.

[1924] Input: Question List

[1925] Output: Data sent to the terminal (JSON format)

[1926] Specific operation: The server sends the generated question list to the terminal in JSON format.

[1927] 4. The terminal displays the received list of questions to the user.

[1928] Input: Question List

[1929] Output: Question list screen

[1930] Specific operation: The terminal renders the question list in HTML format and displays it to the user.

[1931] Step 3: Enter and submit your answers

[1932] 1. The user enters answers to the questions and presses the submit button.

[1933] Input: Answer (e.g., "I have worked on web application development in the past")

[1934] Output: Input data to the terminal

[1935] Specific action: The user enters an answer to a question in the text field and clicks the submit button.

[1936] 2. The device sends the entered answer in JSON format to the server.

[1937] Input: Answer content (JSON format)

[1938] Output: Data sent to the server

[1939] Specific operation: The device converts the response into JSON format and sends it to the server.

[1940] Step 4: Evaluation by generative AI

[1941] 1. The server inputs the received answers into a generative AI model.

[1942] Input: Answer (e.g., "I have worked on web application development in the past")

[1943] Output: Input data to a generative AI model

[1944] Specific operation: The server passes the answer data to the generative AI model.

[1945] 2. The generative AI analyzes the answers and calculates a score for each question.

[1946] Input: Answer

[1947] Output: Score (e.g. "Project Management Skills: 80 / 100")

[1948] Specific operation: The generative AI model analyzes the answers and calculates an evaluation score based on the training data.

[1949] 3. The server stores the generated scores in a database.

[1950] Input: Score

[1951] Output: Data saved to database

[1952] Specific operation: The server saves the score data in a database.

[1953] Step 5: Notification of evaluation results

[1954] 1. The server converts the evaluation results into a format that can be notified to the user.

[1955] Input: Score

[1956] Output: Notification data (e.g. "Your rating score is 85 / 100")

[1957] Specific operation: The server converts the score data into a format that can be notified to the user.

[1958] 2. The server sends the converted evaluation results to the terminal.

[1959] Input: Notification data

[1960] Output: Data sent to the terminal

[1961] Specific operation: The server sends notification data in JSON format to the device.

[1962] 3. The device displays the evaluation results to the user.

[1963] Input: Notification data

[1964] Output: Evaluation result screen

[1965] Specific operation: The device renders the notification data in HTML format and displays it to the user.

[1966] Step 6: Consolidating the final interview data

[1967] 1. The server aggregates all the interview data.

[1968] Input: Interview process data

[1969] Output: Integrated data

[1970] Specific operation: The server analyzes multiple interview data sets and creates a single integrated dataset.

[1971] 2. The server generates a report for the final interviewer.

[1972] Input: Integrated data

[1973] Output: Report (e.g. "Comprehensive report of user rating scores")

[1974] Specific operation: The server generates a report for the final interviewer based on the integrated data.

[1975] 3. The server sends the generated report to the terminal of the final interviewer.

[1976] Input: Report

[1977] Output: Report data sent to the terminal

[1978] Specific operation: The server sends the report in JSON format to the terminal and displays it on the terminal of the final interviewer.

[1979] The above is the specific flow of program processing in the present invention.

[1980] (Application example 1)

[1981] 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."

[1982] Conventional methods for evaluating the skills of factory workers require a lot of time and effort, and are heavily influenced by the evaluator's subjectivity, resulting in problems with the fairness and efficiency of the evaluation. In particular, artificial bias in evaluations and a lack of consistency in evaluation criteria hinder worker motivation and appropriate personnel allocation. This makes it difficult to design training plans and determine optimal personnel allocation.

[1983] 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.

[1984] In this invention, the server includes a means for a user to input login information, a means for the server to authenticate the user's login information, a means for the server to generate a list of questions based on the user's role, a means for the user to input answers to the list of questions, a means for the server to pass the user's answers to a generative AI model for evaluation, a means for the server to store the evaluation results by the generative AI model in a database, a means for the server to notify the user of the evaluation results, and a means for the server to integrate all evaluation data and generate a report to be provided to a manager. This enables efficient and fair evaluation of the skills of workers in a factory, enabling appropriate personnel allocation and the creation of training plans.

[1985] A "user" is a worker or operator who has access to the system, enters answers to a questionnaire, and is evaluated.

[1986] "Login information" refers to the authentication information required for a user to access a system, and is usually composed of a user ID and password.

[1987] "Server" refers to a device or software that processes and manages data for the entire system.

[1988] A "question list" is a set of questions for skill evaluation that is created by the server based on the user's role and work responsibilities.

[1989] A "generative AI model" is an artificial intelligence model that analyzes user responses based on past learning data and generates quantitative evaluation results.

[1990] "Database" means a digital data storage device for storing all evaluation data and login information for the System.

[1991] "Evaluation results" refer to scores such as skills and work efficiency calculated by the generative AI model by analyzing the user's responses.

[1992] A "report" is a written or digital document that the server generates to consolidate all evaluation data and provide to an administrator.

[1993] "Authentication" is the process by which a server receives a user's login information and verifies the user's legitimacy by checking it against information in a database.

[1994] "JSON format" is a structured data format for exchanging user responses, and is an abbreviation for JavaScript Object Notation.

[1995] This invention is an efficient and fair evaluation system that improves on the conventional method of evaluating the skills of factory workers. The system begins with the user entering login information, which is authenticated by the server, and then evaluates the user's skills using a generative AI model. The evaluation results are stored in a database and provided to managers as a report.

[1996] The server uses Flask (a Python web framework) to authenticate the login information of workers and operators when they access the system. This login information mainly consists of a user ID and password. If authentication is successful, the server generates a session ID and sends it to the user's terminal.

[1997] The server then generates a questionnaire based on the logged-in user's role and responsibilities, tailored to the user's specific tasks and skill set, and displays the questionnaire on a smartphone, tablet, or other device.

[1998] When a user enters answers into the question list, the answers are sent to the server in JSON format. The server then passes the received answers to the generative AI model, which analyzes them based on past learning data. As a result of the analysis, a score is calculated based on the user's skills, work efficiency, etc.

[1999] The generated evaluation results are stored in a database, and the server notifies the user. The evaluation result notification allows users to check their own skill evaluation and use it for future training and self-improvement. The server also consolidates all evaluation data to generate a report and provides it to managers. This allows managers to understand the skill status of their workers and design appropriate personnel assignments and training plans.

[2000] A specific example of this system is shown below.

[2001] Specific examples

[2002] 1. Log in:

[2003] The user enters "user123" and "password123" on the tablet and presses the login button.

[2004] The server authenticates the login information, generates a session ID "session_1234", and sends it to the terminal.

[2005] 2. Generate a list of questions:

[2006] The server recognizes the user's role as a "parts assembler" and generates an appropriate list of questions.

[2007] For example, questions such as "Tell us about your work environment recently" and "What was the most difficult task you had in the past week?" will be displayed.

[2008] 3. Enter and submit your answers:

[2009] The user answers the questions by typing "The working environment was comfortable" and "The most difficult task during the week was assembling the cooling device," and then presses the send button.

[2010] The device sends the entered answer in JSON format to the server.

[2011] 4. Generative AI evaluation:

[2012] The server analyzes the answers it receives using a generative AI model to generate scores such as "Skill evaluation: 90 / 100, work efficiency: 85 / 100."

[2013] 5. Notification of evaluation results:

[2014] The server sends the evaluation results to the terminal and displays to the user, "Your evaluation scores are skill rating 90 / 100 and work efficiency 85 / 100."

[2015] 6. Generate the final report:

[2016] The server consolidates all the evaluation data and generates reports for administrators, who can use these reports to design appropriate training plans.

[2017] This system will enable efficient and fair evaluation of the skills of workers within factories, leading to appropriate staffing and training.

[2018] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2019] Step 1:

[2020] The server authenticates the user's login information. The user enters their user ID and password into the login screen on a device such as a tablet and submits it. The server receives the submitted information and compares it with the information in its database. If authentication is successful, the server generates a session ID and submits it to the user's device. This session ID is used to identify the user in subsequent processes.

[2021] Input: User ID, Password

[2022] Output: Session ID

[2023] Step 2:

[2024] The server generates a questionnaire based on the role of the logged-in user. After the user is properly authenticated, the server retrieves the user's role (e.g., parts assembly worker) from the database. Then, it generates a questionnaire appropriate for the user's role and sends it to the terminal. The user's terminal displays this questionnaire.

[2025] Input: Session ID, User Role

[2026] Output: Question list

[2027] Step 3:

[2028] The user enters answers to the presented list of questions and sends them from the device to the server. The user enters answers to the questions using a tablet or smartphone and presses the send button. The device sends the entered answers in JSON format to the server.

[2029] Input: Question list, user answers

[2030] Output: JSON formatted response data

[2031] Step 4:

[2032] The server passes the received answers to the generative AI model for evaluation. The server inputs the JSON-formatted answer data received from the user into the generative AI model and requests analysis. The generative AI model analyzes the user's answers based on past learning data and calculates scores for skill and work efficiency.

[2033] Input: JSON formatted response data

[2034] Output: Evaluation score (e.g., skill rating 90 / 100, work efficiency 85 / 100)

[2035] Step 5:

[2036] The server saves the evaluation results from the generative AI model in a database and notifies the user. The generated evaluation results are saved in a database by the server. The server then sends the evaluation results to the user's device, where the user can check the displayed score.

[2037] Input: Rating score

[2038] Output: Notify user, save to database

[2039] Step 6:

[2040] The server consolidates all the evaluation data and generates a report to be provided to the manager. The server aggregates and consolidates the evaluation data of multiple users. It then generates a report that allows the manager to grasp the overall status of workers in the factory and sends it to the manager's terminal. The manager can use this report to optimize training plans and personnel deployment.

[2041] Input: A set of evaluation data

[2042] Output: Report for administrator

[2043] 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.

[2044] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system authenticates the user's login information, generates a list of questions based on the position being applied for, and analyzes the user's answers and emotions. The analysis results are stored in a database as evaluation results and reflected in a report provided to the final interviewer.

[2045] System Overview

[2046] 1. User login

[2047] The terminal displays a login screen to the user, and the user enters their ID and password.

[2048] The server receives the login information and checks it against a database.

[2049] After successful authentication, the server generates a session ID and sends it back to the terminal.

[2050] 2. Question list generation and presentation

[2051] The server generates a list of questions based on the user's applied position information.

[2052] The terminal displays the generated list of questions to the user.

[2053] 3. Enter and submit answers and emotion data

[2054] The user enters answers into the question list and presses the submit button.

[2055] The device sends the input answer and emotion data to the server.

[2056] 4. Evaluation using generative AI and emotion engine

[2057] The server passes the received answer to the generation AI.

[2058] The emotion engine analyzes the emotions from the voice and text of the user's responses.

[2059] The generating AI evaluates the answers and analyzed emotional data and calculates a score.

[2060] The server stores the evaluation results from the generation AI and emotion engine in a database.

[2061] 5. Notification of evaluation results

[2062] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[2063] The terminal displays the evaluation results to the user.

[2064] 6. Integration of final interview data

[2065] The server consolidates all process data and generates a report for the final interviewer.

[2066] The server sends the report to the terminal of the final interviewer.

[2067] Specific examples

[2068] 1. User login

[2069] The user enters "user123" and "password" on the login screen and presses the "Login" button.

[2070] The server checks the received ID and password against a database, and if they match, generates a session ID and sends it to the terminal.

[2071] The terminal retains the received session ID and displays the dashboard.

[2072] 2. Question list generation and presentation

[2073] The server recognizes that the user is applying for a position as a "Software Engineer."

[2074] The server generates a list of questions for software engineers and sends it to the terminal.

[2075] The terminal displays the received list of questions to the user, for example, "Tell us about your past project experience."

[2076] 3. Enter and submit answers and emotion data

[2077] The user answers the question by saying, "I have worked on developing web applications in the past..."

[2078] The emotion engine analyzes the user's voice and text and generates emotion data.

[2079] The device sends the user's answers and emotion data in JSON format to the server.

[2080] 4. Evaluation using generative AI and emotion engine

[2081] The server inputs the answers and emotional data into the generation AI.

[2082] The generating AI analyzes the answers and generates a score such as "Project management skills: 80 / 100."

[2083] The emotion engine passes the analyzed emotion data to the generation AI.

[2084] The server stores the generated scores and emotion data in a database.

[2085] 5. Notification of evaluation results

[2086] The server converts the evaluation results into a format that can be notified to the user and sends it to the terminal.

[2087] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[2088] 6. Integration of final interview data

[2089] The server consolidates all interview process data and generates a report for the final interview page.

[2090] The server sends the report to the terminal of the final interviewer.

[2091] This system achieves more accurate and fair evaluation of personnel by combining the user's responses with their emotions.

[2092] The processing flow will be explained below.

[2093] Step 1:

[2094] The user enters their ID and password on the login screen and clicks the "Login" button.

[2095] Step 2:

[2096] The device sends the entered ID and password to the server.

[2097] Step 3:

[2098] The server checks the received ID and password against the user information in the database.

[2099] Step 4:

[2100] If the login information is correct, the server generates a session ID and sends it back to the terminal. If it is incorrect, it generates an error message and sends it back to the terminal.

[2101] Step 5:

[2102] The terminal receives the session ID and displays the dashboard screen to the user. If an error message is received, the error content is displayed on the login screen.

[2103] Step 6:

[2104] The server recognizes the position the user is applying for and generates an appropriate list of questions based on that.

[2105] Step 7:

[2106] The server sends the generated question list to the terminal.

[2107] Step 8:

[2108] The terminal displays the received list of questions to the user, allowing the user to input answers.

[2109] Step 9:

[2110] The user enters answers to each question and clicks the submit button.

[2111] Step 10:

[2112] When the user inputs something, the emotion engine analyzes the audio and video to detect the user's emotional state.

[2113] Step 11:

[2114] The emotion engine generates emotion analysis data and transmits the data to the server.

[2115] Step 12:

[2116] The device sends the user's answer in JSON format to the server.

[2117] Step 13:

[2118] The server receives the response data and emotion data and validates both data to check for missing or inappropriate data.

[2119] Step 14:

[2120] The server passes verified response data and emotion data to the generative AI model.

[2121] Step 15:

[2122] The generative AI analyzes the answers it receives and calculates a score for each question.

[2123] Step 16:

[2124] The generative AI calculates an overall score or rating that takes emotional data into account.

[2125] Step 17:

[2126] The generated AI returns the calculated score to the server.

[2127] Step 18:

[2128] The server stores the scores and sentiment analysis data received from the generation AI in a database.

[2129] Step 19:

[2130] The server converts the evaluation results (score and emotion analysis results) into a format that can be notified to the user and sends them to the terminal.

[2131] Step 20:

[2132] The device will display the evaluation results to the user, such as "Your overall score is 85 / 100. Sentiment analysis has confirmed this is a reliable answer."

[2133] Step 21:

[2134] The server consolidates all interview process data (answer data, emotion data, scores, etc.) and generates a report for the final interviewer.

[2135] Step 22:

[2136] The server sends the generated report to the terminal of the final interviewer.

[2137] Step 23:

[2138] The final interviewer will make the final decision based on the report provided.

[2139] Example 2

[2140] 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."

[2141] In conventional recruitment processes, evaluation criteria are often subjective, resulting in unfair screening. Furthermore, the burden on interviewers is heavy, making efficient talent evaluation difficult. Furthermore, evaluations rarely incorporate emotional data, increasing the likelihood of overlooking an applicant's true personality and potential. The present invention aims to solve these problems and achieve fair and efficient talent evaluation.

[2142] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for the user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a question list based on the user's applied position; a means for the user to input answers to the question list; a means for the terminal to acquire the user's answers and emotion data and transmit them to the server; a means for the server to pass the user's answers to the generation AI for evaluation; a means for the server to pass the user's emotion data acquired from the emotion engine to the generation AI; a means for the server to store the evaluation results by the generation AI in a database; a means for the server to notify the user of the evaluation results; and a means for the server to integrate all interview data and generate a report to be provided to the final interviewer. This enables accurate and fair personnel evaluation based on the user's answers and emotions, thereby improving the efficiency and fairness of the hiring process.

[2143] "User" refers to a person who uses the system to log in and enter answers to a list of questions.

[2144] "Server" refers to the computer system that authenticates user login information, generates the question list, analyzes responses and emotional data, stores the evaluation results, and generates a report for the final interviewer.

[2145] "Terminal" refers to a device through which a user accesses the system, enters login information, displays a list of questions, and enters and submits answers.

[2146] "Login Information" refers to the ID and password entered by a User to access the System.

[2147] "Authentication" refers to the process by which a server checks a user's login information against a database to determine whether access is permitted.

[2148] "Applied position" refers to information about the job type or position for which the user is applying.

[2149] A "question list" refers to a set of questions that a user must answer based on the position they are applying for.

[2150] "Answer" refers to the text or audio content that a user enters in response to a list of questions.

[2151] "Emotion data" refers to information about the psychological state and emotions analyzed by the emotion engine from the user's responses.

[2152] "Generative AI" refers to an artificial intelligence model that evaluates and generates a score based on user responses and emotional data.

[2153] "Evaluation results" refers to the score or evaluation calculated based on the user's answers and emotional data analyzed by the generation AI.

[2154] "Database" refers to a data storage system for storing assessment results and other user information.

[2155] "Report" refers to a document that consolidates all interview data and provides it to the final interviewer.

[2156] "Emotion engine" refers to software or algorithms that analyze emotions from a user's voice or text and generate emotion data.

[2157] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient talent evaluation. The system begins when a user enters login information and the server authenticates it. The server then generates a list of questions based on the position the user is applying for, and the terminal displays this to the user. The user enters answers to the list of questions, and the terminal sends the answers and emotion data to the server. The server uses generative AI to evaluate the user's answers and emotion data and stores the results in a database. Finally, the server integrates all the evaluation data and generates a report to be provided to the final interviewer.

[2158] Hardware and software used

[2159] Device: A device operated by a user, such as a PC, tablet, or smartphone

[2160] Server: A hosting environment that includes a web server such as Apache or Nginx, and a database such as MySQL or PostgreSQL.

[2161] Generative AI models: Advanced natural language processing models such as GPT-4

[2162] Emotion engine: Emotion analysis software such as IBM Watson Emotion Analysis

[2163] Program processing

[2164] 1. User login authentication

[2165] The terminal displays a login screen to the user, and the user enters their ID and password.

[2166] The server receives the login information, checks it against a database, and if authentication is successful, generates a session ID and sends it back to the terminal.

[2167] 2. Generating and presenting a list of questions

[2168] The server generates a list of questions based on the user's application information for the position. For example, it generates a list of questions for a software engineer.

[2169] The terminal displays the generated list of questions to the user, for example, "Tell me about your past project experience."

[2170] 3. Enter and submit answers and emotion data

[2171] The user answers the questions and presses the submit button. For example, they enter a specific answer such as "I have worked on developing web applications in the past..."

[2172] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[2173] The device sends the user's answers and emotion data in JSON format to the server.

[2174] 4. Evaluation using generative AI and emotion engine

[2175] The server passes the received answers and emotion data to the generation AI, using, for example, GPT-4.

[2176] The generating AI analyzes the answers and generates a score of "Project management skills: 80 / 100."

[2177] The emotion data analyzed by the emotion engine is passed to the generative AI and incorporated as part of the evaluation.

[2178] The server stores the generated scores and emotion data in a database.

[2179] 5. Notification of evaluation results

[2180] The server converts the evaluation results into a format that can be communicated to the user and sends them to the terminal.

[2181] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[2182] 6. Integration of final interview data

[2183] The server consolidates all process data and generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[2184] The server sends the report to the terminal of the final interviewer.

[2185] Prompt Sentence Examples

[2186] The following prompt sentences are fed into the generative AI model to evaluate the user's responses and emotional data:

[2187] Please rate based on the following answers and sentiment data: Answer: "I have worked on web application development in the past." Sentiment data: "Positive, enthusiastic."

[2188] This system combines user responses with emotional data to make evaluations, enabling more accurate and fairer personnel evaluations.

[2189] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2190] Step 1:

[2191] Displaying the login screen and user authentication

[2192] The device displays a login screen, which includes fields for entering your ID and password.

[2193] The user enters their ID and password and clicks the "Login" button.

[2194] The terminal sends the entered ID and password to the server. The input data includes credential information for authentication.

[2195] The server checks the received ID and password against the database, and if they match, generates a session ID. It performs database operations for the check and generates a session ID.

[2196] The server sends the generated session ID to the terminal and also includes a success message.

[2197] The device receives the session ID and displays the dashboard.

[2198] Step 2:

[2199] Generate and present questionnaires

[2200] The server retrieves the user's application information, which is retrieved from the database at login time.

[2201] The server generates a list of questions based on a specific job application, for example, a list of questions for a software engineer, using a generative AI model.

[2202] The server sends the generated question list to the terminal.

[2203] The terminal displays the received question list to the user. For example, a specific example of the question is "Tell us about your past project experience."

[2204] Step 3:

[2205] Enter and submit answers and emotion data

[2206] The user inputs answers to the list of questions. For example, the user inputs a specific answer such as "I have been involved in developing web applications in the past."

[2207] The emotion engine analyzes emotions from the user's voice and text in real time and generates emotion data.

[2208] The device sends the user's answer and the generated emotion data in JSON format to the server. The input data includes the user's answer text and emotion analysis data.

[2209] The server parses the received JSON data and prepares it for use in the next step.

[2210] Step 4:

[2211] Evaluation by generative AI and emotion engine

[2212] The server inputs the received answers and sentiment data into a generative AI, for example, using a natural language processing model such as GPT-4.

[2213] The generative AI analyzes the answers and generates a score, such as "Project management skills: 80 / 100." The input to the generative AI model is the user's answers and emotional data.

[2214] The emotion engine passes the analyzed emotion data to the generation AI, which takes this into consideration when making an evaluation.

[2215] The server stores the generated scores and emotion data in a database. The output data includes the evaluation scores and emotion data.

[2216] Step 5:

[2217] Notification of evaluation results

[2218] The server converts the evaluation results into a format that can be notified to the user. The server generates evaluation results and formats them in a format that is easy for the user to understand.

[2219] The server transmits the evaluation results to the terminal.

[2220] The device will display to the user, "Your evaluation score is 85 / 100. Reliable emotional expression observed."

[2221] Step 6:

[2222] Integration of final interview data

[2223] The server aggregates all interview process data, including each user's answers, emotional data, and the evaluation results of the generative AI.

[2224] The server generates a comprehensive report for the final interviewer, which includes detailed evaluation results and analyzed emotional data.

[2225] The server sends the report to the terminal of the final interviewer.

[2226] (Application example 2)

[2227] 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."

[2228] The traditional recruitment process involves a lot of manual work and relies heavily on the interviewer's subjectivity, making it difficult to achieve fair and efficient evaluations. It is also difficult to properly analyze the applicant's emotions during the interview and reflect them in the evaluation. In particular, when interviewers are not always present at the factory, the interview itself becomes difficult and inefficient. There is a need for a system that can solve these issues.

[2229] 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.

[2230] In this invention, the server includes: a means for a user to input login information; a means for the server to authenticate the user's login information; a means for the server to generate a list of questions based on the position the user has applied for; a means for the user to input answers to the list of questions; a means for the server to pass the user's answers to a generation AI for evaluation; a means for the emotion engine to analyze emotion data based on the user's answers; a means for the server to store the evaluation results by the generation AI and the emotion engine in a database; a means for the server to notify the user of the evaluation results; a means for the server to integrate all interview data and generate a report to be provided to the final interviewer; and a means for the robot assistant to present questions for the job interview and collect voice responses from the applicant. This enables fair and efficient personnel evaluation, and makes it possible to achieve an efficient interview process even when an interviewer is not present, particularly in job interviews at factories, etc.

[2231] A "user" is a person who uses this system to log in and input answers to the position they are applying for.

[2232] A "server" is a computer device that processes and manages information, stores data entered by users and evaluation results in a database, and notifies users of such data.

[2233] "Login Information" means authentication information such as ID and password required for a User to access the System.

[2234] "Applied position" is information about the type of job or position for which the user is applying.

[2235] A "question list" is a set of questions generated based on the position being applied for, which are presented to the applicant during the interview.

[2236] "Generative AI" is an artificial intelligence technology that analyzes user responses and generates evaluations.

[2237] "Evaluation results" are data on user responses analyzed by the generative AI and emotion engine, including evaluation scores and comments.

[2238] An "emotion engine" is a technology that analyzes emotions based on user responses and extracts emotional data from voice and text.

[2239] The "database" is an information management system for storing evaluation results and interview data.

[2240] A "robot assistant" is an artificial intelligence-equipped device that has the ability to pose questions during job interviews and collect applicants' voice responses.

[2241] The "final interviewer" is the person whose role it is to make the final hiring decision based on all interview data.

[2242] "Interview data" refers to all information related to the interview, such as the user's answers, emotional data, and evaluation results.

[2243] This invention is a system that uses generative AI and an emotion engine to automate the recruitment process and achieve fair and efficient personnel evaluation. This system can support efficient interview processes, especially in recruitment interviews at factories, even when interviewers are not present.

[2244] System Program

[2245] User Login

[2246] The user enters their ID and password on the login screen, and the server authenticates this login information. After successful authentication, the server generates a session ID and sends it to the user's device.

[2247] Question list generation and presentation

[2248] The server generates a list of questions based on the user's applied position information, and the list of questions is presented to the user via the user terminal or robot assistant.

[2249] Collecting response and sentiment data

[2250] When a user answers a question by typing or speaking, the robot assistant collects the voice data and the emotion engine analyzes the emotion from the voice data.

[2251] Evaluation by generative AI and emotion engine

[2252] The server passes the user's response data and emotion data to the AI ​​generator to generate an evaluation. The generated evaluation score and emotion data are stored in a database.

[2253] Notification of evaluation results

[2254] The server converts the evaluation results into a format suitable for the user and sends them to the user's terminal, where they are displayed.

[2255] Integration of final interview data

[2256] The server aggregates all the interview data and generates a report to be provided to the final interviewer, who then sends the report to his / her terminal.

[2257] Hardware and Software

[2258] EmotionEngine: Software for analyzing emotions in voice and text data

[2259] EvaluationModel: Evaluation model using generative AI

[2260] Robot assistants: AI-powered devices that pose questions and collect spoken responses

[2261] Server: A computer device that processes and manages information, stores evaluation results in a database, and sends notifications.

[2262] Specific examples

[2263] When a user applies for a software engineer position, the server follows this sequence:

[2264] 1. The server generates questions for software engineers, such as "Tell me about your past project experience."

[2265] 2. The user types or speaks the answer, "I have worked on developing web applications in the past..."

[2266] 3. The emotion engine analyzes the voice data and generates emotion data.

[2267] 4. The server and the generation AI work together to evaluate the user's technical skills and emotions and generate a score such as "Project management skills: 80 / 100."

[2268] 5. The server converts the evaluation results into a different format and notifies the user device, "Your evaluation score is 85 / 100. Reliable emotional expression was observed."

[2269] Prompt Sentence Examples

[2270] "I'm applying for a factory machine operator position. Please generate a list of questions for this position."

[2271] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2272] Step 1:

[2273] The user enters their login information.

[2274] Input: The user enters the ID and password.

[2275] Operation: The user's device displays the login screen, and the user enters their ID and password.

[2276] Output: Login information is sent from the user terminal to the server.

[2277] Step 2:

[2278] The server authenticates the user's login information.

[2279] Input: The server receives the user's ID and password.

[2280] How it works: The server checks the database and verifies the login information.

[2281] Output: When authentication is successful, the server generates a session ID and sends it to the user's device.

[2282] Step 3:

[2283] The server generates a list of questions based on the position the user is applying for.

[2284] Input: User's application information for the position.

[2285] Operation: The server references the database and creates a list of questions corresponding to the position being applied for.

[2286] Output: The generated question list is sent to the user terminal or robot assistant.

[2287] Step 4:

[2288] The user enters answers into the questionnaire.

[2289] Input: Question list sent from the server.

[2290] Action: The user types in or speaks a response.

[2291] Output: The user device or robot assistant collects the answers and sends them to the server.

[2292] Step 5:

[2293] The server passes the user's answers to the generation AI for evaluation.

[2294] Input: User response data.

[2295] How it works: The server passes the user's text response to the generative AI model for analysis.

[2296] Output: The ratings generated by the generation AI are sent back to the server.

[2297] Step 6:

[2298] The emotion engine analyzes the emotion data based on the user's responses.

[2299] Input: User's voice response data.

[2300] How it works: The emotion engine analyzes the voice data and generates emotion data.

[2301] Output: The analyzed emotion data is sent to the server.

[2302] Step 7:

[2303] The server stores the evaluation results from the generation AI and emotion engine in a database.

[2304] Input: Evaluation data from generative AI and emotion data from emotion engine.

[2305] Operation: The server integrates and stores the rating data and emotion data in a database.

[2306] Output: A database entry containing the evaluation results and emotion data.

[2307] Step 8:

[2308] The server notifies the user of the evaluation results.

[2309] Input: Evaluation results stored in a database.

[2310] Operation: The server converts the evaluation results into a notification format and sends them to the user terminal.

[2311] Output: The user is notified of the evaluation results.

[2312] Step 9:

[2313] The server consolidates all the interview data and generates a report that is provided to the final interviewer.

[2314] Input: All interview data.

[2315] How it works: The server analyzes the data and creates a report for the final interviewer.

[2316] Output: The generated report is sent to the terminal of the final interviewer.

[2317] 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.

[2318] 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.

[2319] 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.

[2320] 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.

[2321] 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.

[2322] 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.

[2323] 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).

[2324] 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.

[2325] 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."

[2326] 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.

[2327] 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).

[2328] 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.

[2329] 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.

[2330] 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.

[2331] 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.

[2332] 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.

[2333] 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.

[2334] 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.

[2335] 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.

[2336] 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.

[2337] 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.

[2338] The following is further disclosed regarding the above embodiment.

[2339] (Claim 1)

[2340] a means for a user to enter login information;

[2341] a means by which the server authenticates the user's login information;

[2342] A means for the server to generate a list of questions based on the position applied for by the user;

[2343] a means for a user to input answers to a list of questions;

[2344] The server passes the user's answers to the AI ​​generator for evaluation.

[2345] A means for the server to store the evaluation results by the generated AI in a database;

[2346] A means for the server to notify the user of the evaluation result;

[2347] a means for the server to consolidate all interview data and generate a report to be provided to the final interviewer;

[2348] A system including:

[2349] (Claim 2)

[2350] 2. The system of claim 1, wherein the answers entered by the user are sent to the server in JSON format.

[2351] (Claim 3)

[2352] The system of claim 1, wherein the server generates a report to be provided to the final interviewer.

[2353] "Example 1"

[2354] (Claim 1)

[2355] a means for a user to enter login information;

[2356] a means by which the server authenticates the user's login information;

[2357] A means for the server to generate a list of questions based on the position applied for by the user;

[2358] a means for a user to input answers to a list of questions;

[2359] The server passes the user's answers to the AI ​​generator for evaluation.

[2360] A means for the server to store the evaluation results by the generated AI in a database;

[2361] A means for the server to notify the user of the evaluation result;

[2362] a means for the server to consolidate all interview data and generate a report to be provided to the final interviewer;

[2363] A means for the terminal to display a login screen to the user and prompt the user to enter an ID and password;

[2364] A means for the server to generate a session ID and send it back to the terminal if authentication is successful;

[2365] A means for the server to send the user's inputted answers in JSON format to the server;

[2366] A system including:

[2367] (Claim 2)

[2368] 2. The system of claim 1, wherein the answers entered by the user are sent to the server in JSON format.

[2369] (Claim 3)

[2370] The system of claim 1, wherein the server generates a report to be provided to the final interviewer.

[2371] "Application Example 1"

[2372] (Claim 1)

[2373] a means for a user to enter login information;

[2374] a means by which the server authenticates the user's login information;

[2375] means for the server to generate a list of questions based on the user's role;

[2376] a means for a user to input answers to a list of questions;

[2377] A means for the server to pass the user's answers to the generative AI model for evaluation;

[2378] A means for the server to store the evaluation results by the generated AI model in a database;

[2379] A means for the server to notify the user of the evaluation result;

[2380] a means for the server to consolidate all the assessment data and generate a report to be provided to an administrator;

[2381] A system including:

[2382] (Claim 2)

[2383] 2. The system of claim 1, wherein the answers entered by the user are sent to the server in JSON format.

[2384] (Claim 3)

[2385] 10. The system of claim 1, wherein the server generates a report to provide to an administrator.

[2386] "Example 2: Combining Emotion Engines"

[2387] (Claim 1)

[2388] a means for a user to enter login information;

[2389] a means by which the server authenticates the user's login information;

[2390] A means for the server to generate a list of questions based on the position applied for by the user;

[2391] a means for a user to input answers to a list of questions;

[2392] A means for the terminal to acquire the user's answer and emotion data and transmit them to the server;

[2393] The server passes the user's answers to the AI ​​generator for evaluation.

[2394] A means for the server to pass the user's emotion data acquired from the emotion engine to the generation AI;

[2395] A means for the server to store the evaluation results by the generated AI in a database;

[2396] A means for the server to notify the user of the evaluation result;

[2397] a means for the server to consolidate all interview data and generate a report to be provided to the final interviewer;

[2398] A system including:

[2399] (Claim 2)

[2400] 2. The system of claim 1, wherein the answers and emotion data entered by the user are transmitted to the server in JSON format.

[2401] (Claim 3)

[2402] The system of claim 1, wherein the server generates a report to be provided to the final interviewer.

[2403] "Application example 2 when combining emotion engines"

[2404] (Claim 1)

[2405] a means for a user to enter login information;

[2406] a means by which the server authenticates the user's login information;

[2407] A means for the server to generate a list of questions based on the position applied for by the user;

[2408] a means for a user to input answers to a list of questions;

[2409] The server passes the user's answers to the AI ​​generator for evaluation.

[2410] a means for the emotion engine to analyze emotion data based on the user's response;

[2411] The server stores the evaluation results from the generation AI and emotion engine in a database;

[2412] A means for the server to notify the user of the evaluation result;

[2413] a means for the server to consolidate all interview data and generate a report to be provided to the final interviewer;

[2414] A means for a robotic assistant to pose questions for job interviews and collect voice responses from applicants;

[2415] A system including:

[2416] (Claim 2)

[2417] 2. The system of claim 1, wherein the answers entered by the user are sent to the server in JSON format.

[2418] (Claim 3)

[2419] The system of claim 1, wherein the server generates a report to be provided to the final interviewer. [Explanation of symbols]

[2420] 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 means for a user to enter login information; a means by which the server authenticates the user's login information; A means for the server to generate a list of questions based on the position applied for by the user; a means for a user to input answers to a list of questions; The server passes the user's answers to the AI ​​generator for evaluation. A means for the server to store the evaluation results by the generated AI in a database; A means for the server to notify the user of the evaluation result; a means for the server to consolidate all interview data and generate a report to be provided to the final interviewer; A system including:

2. The system according to claim 1, wherein the answers entered by the user are sent to the server in JSON format.

3. The system of claim 1, wherein the server generates a report to be provided to the final interviewer.

Images