System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting basic information of a candidate; means including a generation AI for generating a test based on the basic information; means for providing the generated test to the candidate and allowing the candidate to conduct the test; means including a generation AI for receiving, evaluating and scoring a result of conducting the test; and means for reporting the scored result.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] When hiring mid-career employees, companies seek personnel who can contribute immediately, but there are few ways to quantitatively assess applicants' skills in advance, and actual performance is only assessed after they are assigned, which carries significant risk. Furthermore, there is no established method for assessing the qualities of job seekers seeking reskilling and a new career path, hindering the mobility of talent. This situation tends to result in low match rates and high turnover rates, which is detrimental to both companies and job seekers. The present invention aims to solve these issues by matching appropriate talent, reducing turnover, and revitalizing reskilling. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting basic information about an applicant, a means including a generation AI that generates a test based on that basic information, a means for providing the generated test to the applicant and for the applicant to take the test, a means including a generation AI that receives, evaluates, and scores the test results, and a means for reporting the scored results. This system quantifies applicants' skills in advance, allowing companies to efficiently evaluate applicants' immediate work potential. Furthermore, job seekers who choose to change industries after reskilling will have their skills evaluated fairly and objectively, increasing their opportunities to find suitable workplaces. This allows companies to efficiently hire the right talent, reducing turnover and stimulating reskilling.

[0006] "Applicant" refers to an individual who applies for a position when a company is recruiting mid-career employees.

[0007] "Basic information" refers to personal data such as the applicant's name, email address, desired job type, years of experience, and skill set.

[0008] "Generative AI" refers to a system that uses artificial intelligence to automatically generate tests suitable for applicants.

[0009] "Tests" refer to coding tasks, design tasks, writing tasks, etc. that are automatically generated by generative AI to assess applicants' skills.

[0010] "Scoring" refers to the process by which the generative AI analyzes the test results and generates a quantitative evaluation value.

[0011] "Server" means an electronic device containing a central processing unit for receiving, storing, and processing applicant information.

[0012] "Terminal" refers to a device such as a computer or smartphone that an applicant uses to connect to the server and enter information.

[0013] "Reporting" refers to notifying companies and applicants of the scoring results.

[0014] "Human resource mobility" refers to the trend of workers changing jobs or finding employment in different workplaces or different occupations.

[0015] "Reskilling" refers to the activity of job seekers who learn new skills in order to move to a different industry. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] System Program and Description

[0038] To implement this invention, a system is constructed and operated according to the following procedure.

[0039] 1. Applicant information input interface

[0040] A user accesses the system and enters basic information and desired job type.

[0041] The terminal collects the information entered by the applicant and transmits it to the server.

[0042] 2. Test Generation

[0043] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[0044] 3. Conducting the test

[0045] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[0046] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[0047] 4. Evaluation of deliverables

[0048] The server receives the test answers and begins evaluation by the generative AI.

[0049] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[0050] 5. Score generation and notification

[0051] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[0052] The server notifies the company and applicant of the score report.

[0053] Specific examples

[0054] 1. Enter user information

[0055] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[0056] Terminal: Collects "A's" information through a web form and sends it to the server.

[0057] 2. Test Generation

[0058] Server: Based on the information of applicant "A," the generation AI automatically generates tests such as "algorithm problems" and "database operation."

[0059] 3. Conducting the test

[0060] Terminal: Display the generated coding test to applicant "A".

[0061] User: Applicant "A" writes a binary search algorithm in Python and completes the test.

[0062] 4. Evaluation of deliverables

[0063] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring.

[0064] 5. Score generation and notification

[0065] Server: Create a score report (e.g., algorithm 80 points, database 90 points) based on the evaluation of applicant "A."

[0066] The server will send the score report to the company and applicant "A" via email.

[0067] System benefits

[0068] This system allows companies to obtain quantitative information on skills in advance, enabling them to efficiently hire the right people. It also allows applicants to objectively evaluate their own skills, enabling them to apply to suitable workplaces.

[0069] In this way, the present invention provides a system that can improve the efficiency of a company's recruitment process and properly evaluate the skills of applicants.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] A user accesses the system and logs in.

[0073] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[0074] Step 2:

[0075] The device sends the login information to the server.

[0076] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[0077] Step 3:

[0078] The server verifies the login information and performs authentication.

[0079] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[0080] Step 4:

[0081] The user enters basic information and desired job type.

[0082] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[0083] Step 5:

[0084] The terminal sends the entered basic information to the server.

[0085] What it does: Converts the information entered by the user into JSON format and sends it to the server.

[0086] Step 6:

[0087] The server stores the received basic information in a database.

[0088] How it works: The server stores the received basic information in a database and begins selecting an appropriate AI model.

[0089] Step 7:

[0090] The server generates appropriate tests based on the generated AI.

[0091] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates program coding tests, design assignments, and more.

[0092] Step 8:

[0093] The server sends the generated test to the user's device.

[0094] Operation: The generated test content is converted into JSON format and sent to the user's device.

[0095] Step 9:

[0096] The terminal displays the received test to the user.

[0097] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[0098] Step 10:

[0099] The user takes the generated test and enters the answers.

[0100] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[0101] Step 11:

[0102] The terminal sends the user's test results to the server.

[0103] Behavior: The answers to the test completed by the user are converted into JSON format and sent to the server.

[0104] Step 12:

[0105] The server inputs the received test results into the generation AI and begins evaluation.

[0106] How it works: The server passes the received answer to the generation AI, which starts the process of evaluating and scoring the answer.

[0107] Step 13:

[0108] The server receives the evaluation results from the generation AI and generates a score.

[0109] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for the algorithm, 90 points for the database) is calculated.

[0110] Step 14:

[0111] The server creates a score report and notifies the company and the user.

[0112] Operation: A score report is generated based on the scoring results and sent to the company and user as an attachment to a notification email.

[0113] Step 15:

[0114] Users and businesses review the score report.

[0115] What it does: Users and businesses receive a notification email and click the link to view or download their score report.

[0116] This series of processes allows companies to quantitatively evaluate applicants' skills in advance, allowing them to efficiently hire the right people. Applicants also receive an objective evaluation of their skills, providing them with information that will be useful in their job search.

[0117] Example 1

[0118] 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."

[0119] In today's hiring process, there is a lack of efficient and objective methods for evaluating applicants' skills. Companies also face the problem of finding the right talent, which increases the time and cost required to hire them. Furthermore, applicants themselves have few opportunities to objectively evaluate their own skills, making it difficult to find the right job. To address these issues, a system is needed that can generate appropriate tests based on applicants' basic information and objectively evaluate the test results.

[0120] 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.

[0121] In this invention, the server includes: means for inputting basic information about the applicant; means including a generation AI for generating a test based on the basic information; means for providing the generated test to the applicant and for the applicant to take the test; means including a generation AI for receiving, evaluating, and scoring the results of the test; and means for generating and notifying a score report based on the evaluation results. This allows companies to efficiently and objectively evaluate applicants' skills and quickly hire the right talent. Applicants can also objectively understand their own skills and apply to suitable jobs.

[0122] "Applicant" refers to an individual participating in the recruitment process.

[0123] "Basic information" refers to personal information entered by applicants, such as name, contact information, and desired job type.

[0124] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate and evaluate tests.

[0125] "Tests" refer to tasks automatically created by generative AI to assess applicants' skills.

[0126] "Scoring" refers to the process in which generative AI evaluates the test results and assigns a numerical score.

[0127] "Score report" refers to a report summarizing the scoring results generated by the generating AI.

[0128] "Means of notification" refers to the means of communication used to inform applicants and companies of their score reports.

[0129] In order to implement the present invention, the following hardware and software are used.

[0130] Hardware and software used

[0131] Hardware:

[0132] Server: High performance computing server (e.g. AWS EC2)

[0133] Device: PC or tablet (browser compatible) used by the user

[0134] software:

[0135] Web front-end: HTML, CSS, JavaScript

[0136] Backend: Django framework in Python

[0137] Generative AI models: OpenAI's GPT-4 and Google's BERT

[0138] Specific operation of the system

[0139] 1. User information input interface

[0140] A user opens a web browser and logs in.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Specific processing flow of the program

[0143] Step 1:

[0144] A user opens a web browser and accesses a login page. The user enters login information and logs into the system. The terminal sends the entered login information to the server. The server authenticates the login information and displays the user's homepage. This completes the user's authentication to access the system. Input: Login information. Output: User's homepage.

[0145] Step 2:

[0146] The user enters the necessary information, such as desired job type and personal information, into a form. The terminal sends the entered information to the server. The server stores this information in a database. This information is also used for later processing. Input: desired job type, personal information. Output: information stored in the database.

[0147] Step 3:

[0148] The server creates a prompt to generate an appropriate test based on the information received from the user. For example, it generates a prompt that reads, "Applicant A is looking for a software engineer position. Please generate a test that is suitable for him." Based on the generated prompt, it asks the generative AI model to generate a test. The generative AI model generates test content in response to the prompt and sends it back to the server. Input: User information. Output: Generated test content.

[0149] Step 4:

[0150] The server sends the generated test content to the terminal and displays it. The user checks and takes the test through the terminal. The terminal sends the answers entered by the user to the server. Input: Generated test content, user answers. Output: Answers sent to the server.

[0151] Step 5:

[0152] The server creates an evaluation prompt based on the received test answer. For example, it generates a prompt such as "Please evaluate the following Python code. Score it in terms of efficiency, accuracy, and refactoring," and attaches the answer code. It then sends the prompt to the generative AI model, requesting it to evaluate the answer. The server generates a score based on the evaluation returned by the generative AI model. Input: Test answer. Output: Generated score.

[0153] Step 6:

[0154] The server generates a score report based on the evaluation score and notifies the appropriate companies and applicants. The score report is sent via email, etc. Input: Evaluation score. Output: Score report and notification.

[0155] (Application example 1)

[0156] 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."

[0157] In the cybersecurity field, it is important to accurately evaluate the skills of experts and hire the right people. However, traditional hiring processes lack a means to quantitatively and objectively evaluate applicants' skills, requiring companies to spend a great deal of time and effort to find the right talent. Applicants also have limited opportunities to have their skills properly evaluated, making it difficult for them to effectively conduct their job search. There is a need for a method to solve these problems and improve the efficiency and accuracy of skill evaluation.

[0158] 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.

[0159] In this invention, the server includes: a means for inputting basic information about an applicant; a means including a generation AI for generating a test based on the basic information; a means for providing the generated test to the applicant and having the applicant take the test; a means including a generation AI for receiving, evaluating, and scoring the test results; a means for evaluating the skills of cybersecurity professionals; and a means for reporting the scored results. This allows companies to accurately evaluate applicants' cybersecurity skills and efficiently hire the right talent. Furthermore, applicants can apply for more suitable jobs by having their skills objectively evaluated.

[0160] "Applicant" refers to an individual participating in the recruitment process and applying for a particular position.

[0161] "Basic information" refers to data entered by the applicant, such as personal information, desired job type, and skill set.

[0162] "Generative AI" refers to a program that uses machine learning and artificial intelligence techniques to automatically generate and evaluate tests appropriate for applicants.

[0163] "Test" refers to tasks or questions automatically generated by generative AI to assess applicants' skills and abilities.

[0164] A "cybersecurity professional" is an individual with expertise in areas such as network security, application security, and threat analysis.

[0165] "Skill assessment" refers to the process in which generative AI evaluates and scores the abilities of applicants based on the results of tests they take.

[0166] A "score report" refers to a report in which the generative AI evaluates the test results and summarizes the quantitative scores and analysis results.

[0167] In order to implement the present invention, the following system is constructed and operated: The system mainly includes processes related to a server, a terminal, and a user.

[0168] 1. Enter basic information about the applicant

[0169] The server first provides an interface for collecting basic information about applicants. The user enters their information (name, email address, desired job type, skill set, etc.) through this interface and sends it to the server. The terminal then uses a web form or application to collect this information.

[0170] 2. Automatic test generation

[0171] The server automatically generates appropriate tests using a generative AI based on the collected basic information of applicants. This generative AI uses machine learning models (e.g., OpenAI's GPT-based models) to create questions (e.g., network security assessment, application security analysis, threat analysis, etc.) that are optimal for each applicant.

[0172] 3. Conducting the test

[0173] The server provides the generated test to the applicant. The user takes the test using a device at hand (smartphone, tablet, laptop, etc.). The test content consists of tasks and questions corresponding to each specialized field.

[0174] 4. Evaluation of deliverables

[0175] The server receives the test results sent by the user and evaluates them using a generative AI, which scores the applicant's work and creates a detailed score report based on evaluation criteria (e.g., accuracy, efficiency, problem-solving ability).

[0176] 5. Score report delivery

[0177] The server notifies companies and applicants of the generated score report via email, dashboard, etc.

[0178] Hardware and software used

[0179] The hardware used is cloud servers such as AWS EC2 and Google Cloud. Generative AI models include OpenAI's GPT model and Hugging Face's Transformer. Databases such as MongoDB and PostgreSQL are used to manage applicant information. The entire system is built using Flask (Python) as a web framework.

[0180] Specific examples

[0181] For example, applicant "Yamada Taro" applies for a position as a network security engineer. The applicant enters basic information through a web form and selects "Network Security Engineer" as the desired job type. Based on this information, the server's generation AI automatically generates network penetration testing and threat analysis tasks and provides them to the applicant. When the applicant performs these tasks and submits them to the server, the generation AI evaluates the deliverables and creates a score report. The score report is then notified to the applicant and the hiring manager.

[0182] Prompt Sentence Examples

[0183] Applicant information: The applicant's name is "Yamada Taro", the desired job is "Network Security Engineer", and the skills are "Network Penetration Testing", "Firewall Configuration", and "Incident Response".

[0184] Test Generation Requirements: Please generate specialized tests suitable for the network security field. For example, "Security vulnerability detection" and "Network traffic analysis."

[0185] Evaluation criteria: accuracy, efficiency, and resolving ability.

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] The server provides an interface for entering basic information about applicants. Users enter their information (name, email address, desired job type, skill set, etc.) and send this information to the server via their terminal. The server receives the input data and stores it in a database. Input: Basic information about applicants. Output: Saved basic information about applicants.

[0189] Step 2:

[0190] The server calls a generative AI module based on the stored basic information and automatically generates an appropriate test. This generative AI uses, for example, OpenAI's GPT model. The generative AI generates specific test questions (e.g., network penetration tests, threat analysis tasks, etc.) based on the input skill set and desired job type. Input: Basic information about the applicant. Output: Generated test.

[0191] Step 3:

[0192] The terminal provides the generated test to the applicant. The user accesses the test using a terminal (smartphone, tablet, laptop, etc.) and answers the questions. After completing the answers, the user sends the results (code, answer document, etc.) to the server via the terminal. Input: Generated test. Output: Applicant's answers.

[0193] Step 4:

[0194] The server receives the test results sent by the user and calls the generation AI module again for evaluation. The generation AI evaluates the applicant's submission and generates a score. It also takes into account accuracy, efficiency, problem-solving ability, etc. as evaluation criteria. Input: Applicant's answers. Output: Generated score.

[0195] Step 5:

[0196] The server creates a score report based on the completed score. This score report also includes detailed evaluation results by the generation AI. The server notifies the company and applicant of this report by email. Input: Generated score. Output: Generated score report.

[0197] 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.

[0198] System Program and Description

[0199] To implement this invention, a system is constructed and operated according to the following procedure.

[0200] 1. Applicant information input interface

[0201] A user accesses the system and enters basic information and desired job type.

[0202] The terminal collects the information entered by the applicant and transmits it to the server.

[0203] The device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions at that time (e.g., tension, relief, etc.).

[0204] The server stores the emotion data along with basic information.

[0205] 2. Test Generation

[0206] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[0207] The emotion engine references the user's past emotional data and adjusts the test content to make the user feel more relaxed.

[0208] 3. Conducting the test

[0209] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[0210] During the test, the device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions in real time, and this data is sent to the server.

[0211] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[0212] 4. Evaluation of deliverables

[0213] The server receives the test answers and begins evaluation by the generative AI.

[0214] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[0215] The server uses an emotion engine to evaluate the emotional data collected during the test. For example, if a tester has a high rate of correct answers when under high stress, their adaptability will be evaluated.

[0216] 5. Score generation and notification

[0217] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[0218] The server includes the results of the analysis of emotional data (e.g., performance under stress, performance under normal circumstances) in the score report.

[0219] The server notifies the company and applicant of the score report.

[0220] Specific examples

[0221] 1. Enter user information

[0222] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[0223] Device: Collects information about "A" through a web form and sends it to the server. The device also uses a camera and microphone to analyze "A"'s facial expressions and voice to obtain emotional data.

[0224] 2. Test Generation

[0225] Server: Based on information about applicant "A," the generation AI automatically generates "algorithm problems" and "database operation" tests, and the emotion engine adjusts the content.

[0226] 3. Conducting the test

[0227] Device: The generated coding test is displayed to applicant "A" and emotional data is collected in real time while the test is being conducted.

[0228] User: Applicant "A" created a binary search algorithm in Python and completed the test. The device also sent emotion data to the server.

[0229] 4. Evaluation of deliverables

[0230] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring. In addition, it reflects emotional data in the evaluation.

[0231] 5. Score generation and notification

[0232] Server: Create a score report based on the evaluation of applicant "A" and include emotional data (e.g., performance under stress).

[0233] The server sends the score report to the company and applicant "A" via email.

[0234] System benefits

[0235] This system allows companies to evaluate applicants' emotional adaptability as well as their technical skills, making it possible to make a comprehensive judgment that takes into account not only technical ability but also mental aptitude. Applicants also receive feedback based on their emotional state, which helps them to better understand themselves.

[0236] The processing flow will be explained below.

[0237] Step 1:

[0238] A user accesses the system and logs in.

[0239] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[0240] Step 2:

[0241] The device sends the login information to the server.

[0242] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[0243] Step 3:

[0244] The server verifies the login information and performs authentication.

[0245] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[0246] Step 4:

[0247] The user enters basic information and desired job type.

[0248] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[0249] Step 5:

[0250] The terminal sends the entered basic information to the server.

[0251] How it works: The information entered by the user is converted into JSON format and sent to the server. It also uses the camera and microphone to analyze the user's facial expressions and voice in real time to obtain emotional data.

[0252] Step 6:

[0253] The server stores the received basic information and emotion data in a database.

[0254] Operation: The server stores the received basic information and emotion data in a database and begins selecting an appropriate AI model.

[0255] Step 7:

[0256] The server generates appropriate tests based on the generated AI.

[0257] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates coding tests, design assignments, etc. The emotion engine references past emotional data and adjusts the content to make it more relaxing for the user.

[0258] Step 8:

[0259] The server sends the generated test to the user's device.

[0260] Operation: The generated test content is converted into JSON format and sent to the user's device.

[0261] Step 9:

[0262] The terminal displays the received test to the user.

[0263] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[0264] Step 10:

[0265] The user takes the generated test and enters the answers.

[0266] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[0267] Step 11:

[0268] The device sends the user's test results and emotional data to the server.

[0269] How it works: The answers to the tests completed by the user are converted into JSON format and sent to the server along with real-time emotional data.

[0270] Step 12:

[0271] The server inputs the received test results into the generation AI and begins evaluation.

[0272] How it works: The server passes the received answers and emotion data to the generation AI, which then begins the process of evaluating and scoring the answers.

[0273] Step 13:

[0274] The server receives the evaluation results from the generation AI and generates a score.

[0275] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for algorithm, 90 points for design) is calculated. The impact on performance is also evaluated, taking into account emotional data.

[0276] Step 14:

[0277] The server creates a score report and notifies the company and the user.

[0278] Operation: A score report is generated based on the scoring results, and includes the results of emotional data analysis (e.g., performance under stress, performance under normal circumstances). A notification email is sent to the company and user with a link to download the score report.

[0279] Step 15:

[0280] Users and businesses review the score report.

[0281] What it does: Users and businesses click on the link in the notification email they receive to view or download their score report.

[0282] This process allows companies to assess applicants' technical skills and emotional readiness in advance, enabling them to efficiently hire the right talent. Applicants also receive feedback based on their skills and emotional state, allowing them to better target workplaces.

[0283] Example 2

[0284] 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."

[0285] In the modern recruitment process, it is necessary to evaluate not only the technical skills of applicants but also their mental and emotional adaptability. However, conventional systems focus on technical evaluation and lack the ability to properly evaluate and reflect the emotional state of applicants, making it difficult to provide a comprehensive evaluation.

[0286] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting basic information of the applicant, a means for analyzing the applicant's emotions and saving the data, a means including a generation AI for generating a test based on the basic information, and a means for adjusting the test content based on the emotion data. This makes it possible to comprehensively evaluate the applicant's technical skills and emotional adaptability.

[0287] "Applicant" refers to a person participating in the recruitment examination or selection process.

[0288] "Basic information" refers to basic attribute information about the applicant, such as name, contact information, work history, and desired job type.

[0289] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to automatically perform specific tasks.

[0290] "Test" refers to tasks or questions designed to assess an applicant's technical skills and aptitude.

[0291] "Emotional data" refers to information about the emotional state of applicants analyzed from their facial expressions, voice, etc.

[0292] "Adjustment measures" refer to mechanisms for changing and optimizing the content and format of tests based on emotional data and other information.

[0293] "Evaluation means" refers to the system for analyzing the test results and performing scoring and evaluation.

[0294] "Real time" refers to near-instant processing and response.

[0295] A "server" refers to a computer system that provides data processing and storage functions over a network.

[0296] "Scoring" refers to the process of quantifying an applicant's performance based on test results.

[0297] The system is designed to assess applicants' technical skills and emotional readiness and is implemented using the following hardware and software components:

[0298] Hardware Components

[0299] 1. Server - A computer system that provides data processing and storage capabilities (e.g., AWS EC2, Google Cloud Compute Engine).

[0300] 2. Terminal - The device (e.g., PC, tablet, smartphone) on which the applicant enters information and takes the test.

[0301] 3. Camera and Microphone - Input devices to capture the applicant's facial expressions and voice (e.g. webcam, built-in microphone).

[0302] Software Components

[0303] 1. Web Browser - The interface through which applicants enter their information (e.g., Google Chrome, Mozilla Firefox).

[0304] 2. Emotion analysis software - Software to analyze applicants' facial expressions and voice (e.g., OpenCV, Google Cloud Speech).

[0305] 3. Database - A storage system (e.g., MySQL, PostgreSQL) for storing basic information and sentiment data about applicants.

[0306] 4. Generative AI models - Artificial intelligence models for automatically generating and evaluating tests (e.g., OpenAI GPT-3).

[0307] 5. Machine learning models - Models for analyzing and classifying applicant sentiment data (e.g., scikit-learn, TensorFlow).

[0308] 6. Code analysis engine - Software used to evaluate the code submitted for testing (e.g., Pylint, SonarQube).

[0309] How it works

[0310] Enter applicant information

[0311] A user accesses an application form using a web browser and enters basic information (such as name, contact details, work history, desired job type, etc.). The device collects the applicant information and sends it to the server. At the same time, it uses a camera and microphone to analyze the applicant's facial expressions and voice and generate emotional data. This emotional data is also sent to the server.

[0312] Information storage and analysis

[0313] The server stores the received applicant's basic information and emotional data in a database. The server then refers to past emotional data, analyzes the newly acquired emotional data, and classifies it into an appropriate category (e.g., nervous, relieved).

[0314] Test Generation and Tuning

[0315] The server inputs prompts into the generative AI model based on the applicant's basic information to generate an appropriate test. The server then adjusts the test content based on the applicant's emotional data, aiming to create a relaxed environment for the applicant. For example, it may simplify the question format or set a flexible time limit to reduce tension.

[0316] Example prompt for a generative AI model:

[0317] "Generate coding tests for software engineers."

[0318] Testing and Sentiment Analysis

[0319] The device displays the generated test to the applicant, and the user follows the instructions to take the test. While the test is being taken, the device analyzes facial expressions and voice using a camera and microphone, capturing emotional data in real time and sending it to the server. This allows the collection of the applicant's performance data to be as accurate as possible.

[0320] Test Evaluation and Scoring

[0321] The server receives the test answers sent from the device and begins evaluating them using a generative AI model, which evaluates technical aspects such as code accuracy and efficiency, as well as its adaptability based on emotional data.

[0322] Score report generation and notification

[0323] The server creates a score report based on the test results and the analysis of the emotional data, and notifies the company and applicant. The report includes not only the technical score but also the applicant's emotional state (e.g., performance under stress, performance under normal circumstances).

[0324] This allows companies to comprehensively assess candidates' technical skills and emotional readiness, leading to better hiring decisions, while providing candidates with opportunities to deepen their self-understanding and grow through feedback.

[0325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0326] Step 1: Enter and submit your application information

[0327] A user accesses the application form using a web browser and enters basic information (name, contact details, work history, desired job type, etc.). The entered information is recorded on the device.

[0328] The device sends the applicant's basic information to the server via API. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice. This generates emotional data, which is also sent to the server.

[0329] Input: Name, contact information, work history, desired job type, facial expression data, voice data

[0330] Output: Basic information of applicants, emotional data

[0331] Step 2: Store and analyze applicant information

[0332] The server stores the applicant's basic information and emotional data received from the terminal in a database.

[0333] The server analyzes the emotion data using a machine learning model (e.g., scikit-learn, TensorFlow) and classifies it into categories such as "tension" or "relief." This classification result is also stored in the database.

[0334] Input: Basic information of applicant, emotional data

[0335] Output: Stored applicant basic information, categorized emotion data

[0336] Step 3: Generate and refine tests

[0337] The server inputs a prompt into the generative AI model based on the applicant's basic information to generate an appropriate test. For example, the prompt might be, "Please generate a coding test for software engineers."

[0338] The server adjusts the generated test, referencing the emotional data and adjusting the content and difficulty of the test to make the applicant feel more relaxed.

[0339] Input: basic information of applicant, emotion data, prompt sentence

[0340] Output: Generated tests, adjusted test content

[0341] Step 4: View and perform tests

[0342] The terminal displays the generated test to the applicant.

[0343] The user follows the test questions and enters their answers, for example, creating a binary search algorithm in Python.

[0344] Input: Adjusted test content

[0345] Output: Applicant's test answers

[0346] Step 5: Sentiment analysis and sending during the test

[0347] During the test, the device uses a camera and microphone to analyze the applicant's facial expressions and voice in real time, capturing emotional data, which is then sent to a server.

[0348] Input: Real-time facial expression data, voice data

[0349] Output: Real-time emotion data

[0350] Step 6: Submit and evaluate your test answers

[0351] The terminal transmits the applicant's response to the server.

[0352] The server evaluates applicants' test answers using a generative AI model and uses a code analysis engine (e.g., Pylint, SonarQube) to check the code for accuracy, efficiency, and readability.

[0353] Input: Applicant's test answers, emotion data

[0354] Output: Evaluation results, technical score, emotional adaptability score

[0355] Step 7: Generate and notify your score report

[0356] The server generates a comprehensive score report based on the test evaluation results and emotional data, which includes a technical score and an emotional adaptability score.

[0357] The server generates a report and notifies the company and applicants by email.

[0358] Input: Assessment results, technical score, emotional adaptability score

[0359] Output: Generated score report, notification email

[0360] (Application example 2)

[0361] 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."

[0362] Conventional applicant evaluation systems only evaluate applicants' technical skills and knowledge, and do not consider psychological factors such as their emotional state or stress level. As a result, they are unable to properly evaluate the applicant's overall suitability, which can lead to flaws in personnel selection. Furthermore, while there is a need to understand the emotional state and stress levels of workers in factories and other places in real time to improve work efficiency and safety, current systems are unable to meet this need.

[0363] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting basic information about the applicant, a means including a generation AI for generating a test based on the basic information, and a means for providing the generated test to the applicant, who then takes the test. This enables a comprehensive aptitude evaluation that takes into account not only the applicant's technical skills but also their emotional state. The server also includes a means including an emotion engine for acquiring and analyzing the worker's emotional data, a means for integrating and analyzing the emotion data and test result data, and a means for adjusting tasks based on emotions and performance. This makes it possible to grasp the worker's emotional state in real time and appropriately adjust tasks accordingly, which is expected to improve work efficiency and safety.

[0364] "Applicant" refers to an individual who uses the System to be evaluated.

[0365] "Basic Information" refers to the personal data and biographical information that applicants enter into the system.

[0366] "Generative AI" refers to artificial intelligence that automatically generates appropriate tests based on basic information about applicants and evaluates them.

[0367] "Tests" refer to tasks or questions created by generative AI to assess applicants' skills and knowledge.

[0368] An "emotion engine" is a system that analyzes the facial expressions and voices of applicants and workers and recognizes their emotional state in real time.

[0369] "Test Result Data" refers to performance data from tests taken by applicants.

[0370] "Emotional data" refers to analytical results data that show the emotional state of applicants and workers.

[0371] A "task" refers to a specific task or assignment assigned to an applicant or worker.

[0372] "Task adjustment" refers to changing the content and difficulty of tasks assigned to workers based on emotional data and test result data.

[0373] To implement this invention, it is necessary to build and operate a system using the following procedure: First, a user (applicant or worker) inputs basic information through a terminal. The terminal then sends this basic information to a server, which then uses a generation AI to automatically generate a test appropriate for the applicant.

[0374] Next, the terminal displays the generated test to the applicant, who then takes the test. During the test, the terminal uses an emotion engine to analyze the facial expressions and voice of the applicant or worker, obtaining emotional data in real time. This data is then sent to the server.

[0375] The server receives the test results and emotion data, and uses generative AI to comprehensively evaluate these data. Based on the evaluation results, the server assigns a score and adjusts tasks based on emotion and performance.

[0376] The hardware used includes smart helmets and badges with built-in cameras and microphones, and a server for data management and analysis. The software used includes EmotionRecognizer (emotion engine), TaskScheduler (task coordination engine), and factory_database (database management system).

[0377] As a concrete example, let's say worker "A" is working in a foundry at a factory. The smart helmet captures "A's" facial expressions and voice in real time, and the emotion engine analyzes them. If the analysis identifies that "A" is in a high-stress state, the task adjustment engine automatically shifts "A" to an easier task. Furthermore, relaxing music begins to play from the smart helmet.

[0378] Examples of prompts to input to a generative AI model include:

[0379] "Adjust the tasks of the factory workers based on the following data: Worker ID: 3, Emotional Data: High Stress Level, Performance Data: Casting Efficiency 75%. If the worker is feeling stressed, assign them tasks that will help them relax."

[0380] As described above, this system makes it possible to comprehensively evaluate an applicant's technical skills and emotional state, and by assigning appropriate tasks based on the worker's emotional state, it is expected to improve work efficiency and safety.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1:

[0383] The user inputs basic information and desired job type through the terminal. The terminal acquires the applicant's basic information (name, career history, desired job type, etc.) and sends it to the server.

[0384] Input: User (applicant) basic information

[0385] Output: Send basic information data to the server

[0386] Specific operation: Information entered on the terminal is sent to the server in real time and stored in a database on the server.

[0387] Step 2:

[0388] The device uses a camera and microphone to capture the applicant's facial expressions and voice, which are then analyzed by an emotion engine. The resulting emotion data is then sent to a server.

[0389] Input: Applicant's video and audio data

[0390] Output: Sending emotion data to the server

[0391] Specific operation: Data taken from the device's camera and microphone is analyzed by EmotionRecognizer and sent to the server as emotion data.

[0392] Step 3:

[0393] The server uses generative AI based on basic information and emotional data to generate a test that is appropriate for the applicant.

[0394] Input: Basic information data, emotion data

[0395] Output: Generated test data

[0396] Specific operation: The generation AI on the server generates appropriate tests based on basic information and emotional data, and saves the test content in a database.

[0397] Step 4:

[0398] The device presents the generated test to the applicant, who then takes the test. Test performance data and real-time emotional data are sent to the server.

[0399] Input: Generated test data

[0400] Output: Test performance data, real-time sentiment data

[0401] How it works: Applicants take the test and the results are sent from their devices to a server. Facial expressions and voices are also analyzed during the test, and emotional data is sent to the server in real time.

[0402] Step 5:

[0403] The server receives test performance and sentiment data and uses generative AI to evaluate and score it.

[0404] Input: Test performance data, emotion data

[0405] Output: Evaluation results, scoring data

[0406] Specific operation: The generation AI on the server analyzes the test results and emotional data, and performs an overall evaluation and scoring. These evaluation results are stored in a database.

[0407] Step 6:

[0408] The server executes a means for adjusting tasks suitable for the worker based on the scoring results and emotion data.

[0409] Input: Evaluation results, scoring data

[0410] Output: Reconciled task data

[0411] Specific operation: The TaskScheduler on the server calculates the optimal task based on the evaluation results and emotion data, and saves the adjusted task in a database.

[0412] Step 7:

[0413] The adjusted tasks are notified to the workers, who receive instructions for the new tasks via their terminals and start the appropriate tasks.

[0414] Input: Adjusted task data

[0415] Output: Task notification to workers

[0416] Specific operation: The terminal notifies the worker of the content of the new task, and the worker receives instructions for carrying out the task.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Second embodiment]

[0421] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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. 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] In the smart glasses 214, 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.

[0432] 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."

[0433] System Program and Description

[0434] To implement this invention, a system is constructed and operated according to the following procedure.

[0435] 1. Applicant information input interface

[0436] A user accesses the system and enters basic information and desired job type.

[0437] The terminal collects the information entered by the applicant and transmits it to the server.

[0438] 2. Test Generation

[0439] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[0440] 3. Conducting the test

[0441] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[0442] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[0443] 4. Evaluation of deliverables

[0444] The server receives the test answers and begins evaluation by the generative AI.

[0445] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[0446] 5. Score generation and notification

[0447] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[0448] The server notifies the company and applicant of the score report.

[0449] Specific examples

[0450] 1. Enter user information

[0451] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[0452] Terminal: Collects "A's" information through a web form and sends it to the server.

[0453] 2. Test Generation

[0454] Server: Based on the information of applicant "A," the generation AI automatically generates tests such as "algorithm problems" and "database operation."

[0455] 3. Conducting the test

[0456] Terminal: Display the generated coding test to applicant "A".

[0457] User: Applicant "A" writes a binary search algorithm in Python and completes the test.

[0458] 4. Evaluation of deliverables

[0459] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring.

[0460] 5. Score generation and notification

[0461] Server: Create a score report (e.g., algorithm 80 points, database 90 points) based on the evaluation of applicant "A."

[0462] The server will send the score report to the company and applicant "A" via email.

[0463] System benefits

[0464] This system allows companies to obtain quantitative information on skills in advance, enabling them to efficiently hire the right people. It also allows applicants to objectively evaluate their own skills, enabling them to apply to suitable workplaces.

[0465] In this way, the present invention provides a system that can improve the efficiency of a company's recruitment process and properly evaluate the skills of applicants.

[0466] The processing flow will be explained below.

[0467] Step 1:

[0468] A user accesses the system and logs in.

[0469] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[0470] Step 2:

[0471] The device sends the login information to the server.

[0472] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[0473] Step 3:

[0474] The server verifies the login information and performs authentication.

[0475] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[0476] Step 4:

[0477] The user enters basic information and desired job type.

[0478] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[0479] Step 5:

[0480] The terminal sends the entered basic information to the server.

[0481] What it does: Converts the information entered by the user into JSON format and sends it to the server.

[0482] Step 6:

[0483] The server stores the received basic information in a database.

[0484] How it works: The server stores the received basic information in a database and begins selecting an appropriate AI model.

[0485] Step 7:

[0486] The server generates appropriate tests based on the generated AI.

[0487] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates program coding tests, design assignments, and more.

[0488] Step 8:

[0489] The server sends the generated test to the user's device.

[0490] Operation: The generated test content is converted into JSON format and sent to the user's device.

[0491] Step 9:

[0492] The terminal displays the received test to the user.

[0493] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[0494] Step 10:

[0495] The user takes the generated test and enters the answers.

[0496] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[0497] Step 11:

[0498] The terminal sends the user's test results to the server.

[0499] Behavior: The answers to the test completed by the user are converted into JSON format and sent to the server.

[0500] Step 12:

[0501] The server inputs the received test results into the generation AI and begins evaluation.

[0502] How it works: The server passes the received answer to the generation AI, which starts the process of evaluating and scoring the answer.

[0503] Step 13:

[0504] The server receives the evaluation results from the generation AI and generates a score.

[0505] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for the algorithm, 90 points for the database) is calculated.

[0506] Step 14:

[0507] The server creates a score report and notifies the company and the user.

[0508] Operation: A score report is generated based on the scoring results and sent to the company and user as an attachment to a notification email.

[0509] Step 15:

[0510] Users and businesses review the score report.

[0511] What it does: Users and businesses receive a notification email and click the link to view or download their score report.

[0512] This series of processes allows companies to quantitatively evaluate applicants' skills in advance, allowing them to efficiently hire the right people. Applicants also receive an objective evaluation of their skills, providing them with information that will be useful in their job search.

[0513] Example 1

[0514] 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."

[0515] In today's hiring process, there is a lack of efficient and objective methods for evaluating applicants' skills. Companies also face the problem of finding the right talent, which increases the time and cost required to hire them. Furthermore, applicants themselves have few opportunities to objectively evaluate their own skills, making it difficult to find the right job. To address these issues, a system is needed that can generate appropriate tests based on applicants' basic information and objectively evaluate the test results.

[0516] 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.

[0517] In this invention, the server includes: means for inputting basic information about the applicant; means including a generation AI for generating a test based on the basic information; means for providing the generated test to the applicant and for the applicant to take the test; means including a generation AI for receiving, evaluating, and scoring the results of the test; and means for generating and notifying a score report based on the evaluation results. This allows companies to efficiently and objectively evaluate applicants' skills and quickly hire the right talent. Applicants can also objectively understand their own skills and apply to suitable jobs.

[0518] "Applicant" refers to an individual participating in the recruitment process.

[0519] "Basic information" refers to personal information entered by applicants, such as name, contact information, and desired job type.

[0520] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate and evaluate tests.

[0521] "Tests" refer to tasks automatically created by generative AI to assess applicants' skills.

[0522] "Scoring" refers to the process in which generative AI evaluates the test results and assigns a numerical score.

[0523] "Score report" refers to a report summarizing the scoring results generated by the generating AI.

[0524] "Means of notification" refers to the means of communication used to inform applicants and companies of their score reports.

[0525] In order to implement the present invention, the following hardware and software are used.

[0526] Hardware and software used

[0527] Hardware:

[0528] Server: High performance computing server (e.g. AWS EC2)

[0529] Device: PC or tablet (browser compatible) used by the user

[0530] software:

[0531] Web front-end: HTML, CSS, JavaScript

[0532] Backend: Django framework in Python

[0533] Generative AI models: OpenAI's GPT-4 and Google's BERT

[0534] Specific operation of the system

[0535] 1. User information input interface

[0536] A user opens a web browser and logs in.

[0537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0538] Specific processing flow of the program

[0539] Step 1:

[0540] A user opens a web browser and accesses a login page. The user enters login information and logs into the system. The terminal sends the entered login information to the server. The server authenticates the login information and displays the user's homepage. This completes the user's authentication to access the system. Input: Login information. Output: User's homepage.

[0541] Step 2:

[0542] The user enters the necessary information, such as desired job type and personal information, into a form. The terminal sends the entered information to the server. The server stores this information in a database. This information is also used for later processing. Input: desired job type, personal information. Output: information stored in the database.

[0543] Step 3:

[0544] The server creates a prompt to generate an appropriate test based on the information received from the user. For example, it generates a prompt that reads, "Applicant A is looking for a software engineer position. Please generate a test that is suitable for him." Based on the generated prompt, it asks the generative AI model to generate a test. The generative AI model generates test content in response to the prompt and sends it back to the server. Input: User information. Output: Generated test content.

[0545] Step 4:

[0546] The server sends the generated test content to the terminal and displays it. The user checks and takes the test through the terminal. The terminal sends the answers entered by the user to the server. Input: Generated test content, user answers. Output: Answers sent to the server.

[0547] Step 5:

[0548] The server creates an evaluation prompt based on the received test answer. For example, it generates a prompt such as "Please evaluate the following Python code. Score it in terms of efficiency, accuracy, and refactoring," and attaches the answer code. It then sends the prompt to the generative AI model, requesting it to evaluate the answer. The server generates a score based on the evaluation returned by the generative AI model. Input: Test answer. Output: Generated score.

[0549] Step 6:

[0550] The server generates a score report based on the evaluation score and notifies the appropriate companies and applicants. The score report is sent via email, etc. Input: Evaluation score. Output: Score report and notification.

[0551] (Application example 1)

[0552] 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."

[0553] In the cybersecurity field, it is important to accurately evaluate the skills of experts and hire the right people. However, traditional hiring processes lack a means to quantitatively and objectively evaluate applicants' skills, requiring companies to spend a great deal of time and effort to find the right talent. Applicants also have limited opportunities to have their skills properly evaluated, making it difficult for them to effectively conduct their job search. There is a need for a method to solve these problems and improve the efficiency and accuracy of skill evaluation.

[0554] 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.

[0555] In this invention, the server includes: a means for inputting basic information about an applicant; a means including a generation AI for generating a test based on the basic information; a means for providing the generated test to the applicant and having the applicant take the test; a means including a generation AI for receiving, evaluating, and scoring the test results; a means for evaluating the skills of cybersecurity professionals; and a means for reporting the scored results. This allows companies to accurately evaluate applicants' cybersecurity skills and efficiently hire the right talent. Furthermore, applicants can apply for more suitable jobs by having their skills objectively evaluated.

[0556] "Applicant" refers to an individual participating in the recruitment process and applying for a particular position.

[0557] "Basic information" refers to data entered by the applicant, such as personal information, desired job type, and skill set.

[0558] "Generative AI" refers to a program that uses machine learning and artificial intelligence techniques to automatically generate and evaluate tests appropriate for applicants.

[0559] "Test" refers to tasks or questions automatically generated by generative AI to assess applicants' skills and abilities.

[0560] A "cybersecurity professional" is an individual with expertise in areas such as network security, application security, and threat analysis.

[0561] "Skill assessment" refers to the process in which generative AI evaluates and scores the abilities of applicants based on the results of tests they take.

[0562] A "score report" refers to a report in which the generative AI evaluates the test results and summarizes the quantitative scores and analysis results.

[0563] In order to implement the present invention, the following system is constructed and operated: The system mainly includes processes related to a server, a terminal, and a user.

[0564] 1. Enter basic information about the applicant

[0565] The server first provides an interface for collecting basic information about applicants. The user enters their information (name, email address, desired job type, skill set, etc.) through this interface and sends it to the server. The terminal then uses a web form or application to collect this information.

[0566] 2. Automatic test generation

[0567] The server automatically generates appropriate tests using a generative AI based on the collected basic information of applicants. This generative AI uses machine learning models (e.g., OpenAI's GPT-based models) to create questions (e.g., network security assessment, application security analysis, threat analysis, etc.) that are optimal for each applicant.

[0568] 3. Conducting the test

[0569] The server provides the generated test to the applicant. The user takes the test using a device at hand (smartphone, tablet, laptop, etc.). The test content consists of tasks and questions corresponding to each specialized field.

[0570] 4. Evaluation of deliverables

[0571] The server receives the test results sent by the user and evaluates them using a generative AI, which scores the applicant's work and creates a detailed score report based on evaluation criteria (e.g., accuracy, efficiency, problem-solving ability).

[0572] 5. Score report delivery

[0573] The server notifies companies and applicants of the generated score report via email, dashboard, etc.

[0574] Hardware and software used

[0575] The hardware used is cloud servers such as AWS EC2 and Google Cloud. Generative AI models include OpenAI's GPT model and Hugging Face's Transformer. Databases such as MongoDB and PostgreSQL are used to manage applicant information. The entire system is built using Flask (Python) as a web framework.

[0576] Specific examples

[0577] For example, applicant "Yamada Taro" applies for a position as a network security engineer. The applicant enters basic information through a web form and selects "Network Security Engineer" as the desired job type. Based on this information, the server's generation AI automatically generates network penetration testing and threat analysis tasks and provides them to the applicant. When the applicant performs these tasks and submits them to the server, the generation AI evaluates the deliverables and creates a score report. The score report is then notified to the applicant and the hiring manager.

[0578] Prompt Sentence Examples

[0579] Applicant information: The applicant's name is "Yamada Taro", the desired job is "Network Security Engineer", and the skills are "Network Penetration Testing", "Firewall Configuration", and "Incident Response".

[0580] Test Generation Requirements: Please generate specialized tests suitable for the network security field. For example, "Security vulnerability detection" and "Network traffic analysis."

[0581] Evaluation criteria: accuracy, efficiency, and resolving ability.

[0582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0583] Step 1:

[0584] The server provides an interface for entering basic information about applicants. Users enter their information (name, email address, desired job type, skill set, etc.) and send this information to the server via their terminal. The server receives the input data and stores it in a database. Input: Basic information about applicants. Output: Saved basic information about applicants.

[0585] Step 2:

[0586] The server calls a generative AI module based on the stored basic information and automatically generates an appropriate test. This generative AI uses, for example, OpenAI's GPT model. The generative AI generates specific test questions (e.g., network penetration tests, threat analysis tasks, etc.) based on the input skill set and desired job type. Input: Basic information about the applicant. Output: Generated test.

[0587] Step 3:

[0588] The terminal provides the generated test to the applicant. The user accesses the test using a terminal (smartphone, tablet, laptop, etc.) and answers the questions. After completing the answers, the user sends the results (code, answer document, etc.) to the server via the terminal. Input: Generated test. Output: Applicant's answers.

[0589] Step 4:

[0590] The server receives the test results sent by the user and calls the generation AI module again for evaluation. The generation AI evaluates the applicant's submission and generates a score. It also takes into account accuracy, efficiency, problem-solving ability, etc. as evaluation criteria. Input: Applicant's answers. Output: Generated score.

[0591] Step 5:

[0592] The server creates a score report based on the completed score. This score report also includes detailed evaluation results by the generation AI. The server notifies the company and applicant of this report by email. Input: Generated score. Output: Generated score report.

[0593] 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.

[0594] System Program and Description

[0595] To implement this invention, a system is constructed and operated according to the following procedure.

[0596] 1. Applicant information input interface

[0597] A user accesses the system and enters basic information and desired job type.

[0598] The terminal collects the information entered by the applicant and transmits it to the server.

[0599] The device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions at that time (e.g., tension, relief, etc.).

[0600] The server stores the emotion data along with basic information.

[0601] 2. Test Generation

[0602] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[0603] The emotion engine references the user's past emotional data and adjusts the test content to make the user feel more relaxed.

[0604] 3. Conducting the test

[0605] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[0606] During the test, the device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions in real time, and this data is sent to the server.

[0607] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[0608] 4. Evaluation of deliverables

[0609] The server receives the test answers and begins evaluation by the generative AI.

[0610] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[0611] The server uses an emotion engine to evaluate the emotional data collected during the test. For example, if a tester has a high rate of correct answers when under high stress, their adaptability will be evaluated.

[0612] 5. Score generation and notification

[0613] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[0614] The server includes the results of the analysis of emotional data (e.g., performance under stress, performance under normal circumstances) in the score report.

[0615] The server notifies the company and applicant of the score report.

[0616] Specific examples

[0617] 1. Enter user information

[0618] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[0619] Device: Collects information about "A" through a web form and sends it to the server. The device also uses a camera and microphone to analyze "A"'s facial expressions and voice to obtain emotional data.

[0620] 2. Test Generation

[0621] Server: Based on information about applicant "A," the generation AI automatically generates "algorithm problems" and "database operation" tests, and the emotion engine adjusts the content.

[0622] 3. Conducting the test

[0623] Device: The generated coding test is displayed to applicant "A" and emotional data is collected in real time while the test is being conducted.

[0624] User: Applicant "A" created a binary search algorithm in Python and completed the test. The device also sent emotion data to the server.

[0625] 4. Evaluation of deliverables

[0626] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring. In addition, it reflects emotional data in the evaluation.

[0627] 5. Score generation and notification

[0628] Server: Create a score report based on the evaluation of applicant "A" and include emotional data (e.g., performance under stress).

[0629] The server sends the score report to the company and applicant "A" via email.

[0630] System benefits

[0631] This system allows companies to evaluate applicants' emotional adaptability as well as their technical skills, making it possible to make a comprehensive judgment that takes into account not only technical ability but also mental aptitude. Applicants also receive feedback based on their emotional state, which helps them to better understand themselves.

[0632] The processing flow will be explained below.

[0633] Step 1:

[0634] A user accesses the system and logs in.

[0635] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[0636] Step 2:

[0637] The device sends the login information to the server.

[0638] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[0639] Step 3:

[0640] The server verifies the login information and performs authentication.

[0641] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[0642] Step 4:

[0643] The user enters basic information and desired job type.

[0644] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[0645] Step 5:

[0646] The terminal sends the entered basic information to the server.

[0647] How it works: The information entered by the user is converted into JSON format and sent to the server. It also uses the camera and microphone to analyze the user's facial expressions and voice in real time to obtain emotional data.

[0648] Step 6:

[0649] The server stores the received basic information and emotion data in a database.

[0650] Operation: The server stores the received basic information and emotion data in a database and begins selecting an appropriate AI model.

[0651] Step 7:

[0652] The server generates appropriate tests based on the generated AI.

[0653] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates coding tests, design assignments, etc. The emotion engine references past emotional data and adjusts the content to make it more relaxing for the user.

[0654] Step 8:

[0655] The server sends the generated test to the user's device.

[0656] Operation: The generated test content is converted into JSON format and sent to the user's device.

[0657] Step 9:

[0658] The terminal displays the received test to the user.

[0659] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[0660] Step 10:

[0661] The user takes the generated test and enters the answers.

[0662] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[0663] Step 11:

[0664] The device sends the user's test results and emotional data to the server.

[0665] How it works: The answers to the tests completed by the user are converted into JSON format and sent to the server along with real-time emotional data.

[0666] Step 12:

[0667] The server inputs the received test results into the generation AI and begins evaluation.

[0668] How it works: The server passes the received answers and emotion data to the generation AI, which then begins the process of evaluating and scoring the answers.

[0669] Step 13:

[0670] The server receives the evaluation results from the generation AI and generates a score.

[0671] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for algorithm, 90 points for design) is calculated. The impact on performance is also evaluated, taking into account emotional data.

[0672] Step 14:

[0673] The server creates a score report and notifies the company and the user.

[0674] Operation: A score report is generated based on the scoring results, and includes the results of emotional data analysis (e.g., performance under stress, performance under normal circumstances). A notification email is sent to the company and user with a link to download the score report.

[0675] Step 15:

[0676] Users and businesses review the score report.

[0677] What it does: Users and businesses click on the link in the notification email they receive to view or download their score report.

[0678] This process allows companies to assess applicants' technical skills and emotional readiness in advance, enabling them to efficiently hire the right talent. Applicants also receive feedback based on their skills and emotional state, allowing them to better target workplaces.

[0679] Example 2

[0680] 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."

[0681] In the modern recruitment process, it is necessary to evaluate not only the technical skills of applicants but also their mental and emotional adaptability. However, conventional systems focus on technical evaluation and lack the ability to properly evaluate and reflect the emotional state of applicants, making it difficult to provide a comprehensive evaluation.

[0682] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting basic information of the applicant, a means for analyzing the applicant's emotions and saving the data, a means including a generation AI for generating a test based on the basic information, and a means for adjusting the test content based on the emotion data. This makes it possible to comprehensively evaluate the applicant's technical skills and emotional adaptability.

[0683] "Applicant" refers to a person participating in the recruitment examination or selection process.

[0684] "Basic information" refers to basic attribute information about the applicant, such as name, contact information, work history, and desired job type.

[0685] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to automatically perform specific tasks.

[0686] "Test" refers to tasks or questions designed to assess an applicant's technical skills and aptitude.

[0687] "Emotional data" refers to information about the emotional state of applicants analyzed from their facial expressions, voice, etc.

[0688] "Adjustment measures" refer to mechanisms for changing and optimizing the content and format of tests based on emotional data and other information.

[0689] "Evaluation means" refers to the system for analyzing the test results and performing scoring and evaluation.

[0690] "Real time" refers to near-instant processing and response.

[0691] A "server" refers to a computer system that provides data processing and storage functions over a network.

[0692] "Scoring" refers to the process of quantifying an applicant's performance based on test results.

[0693] The system is designed to assess applicants' technical skills and emotional readiness and is implemented using the following hardware and software components:

[0694] Hardware Components

[0695] 1. Server - A computer system that provides data processing and storage capabilities (e.g., AWS EC2, Google Cloud Compute Engine).

[0696] 2. Terminal - The device (e.g., PC, tablet, smartphone) on which the applicant enters information and takes the test.

[0697] 3. Camera and Microphone - Input devices to capture the applicant's facial expressions and voice (e.g. webcam, built-in microphone).

[0698] Software Components

[0699] 1. Web Browser - The interface through which applicants enter their information (e.g., Google Chrome, Mozilla Firefox).

[0700] 2. Emotion analysis software - Software to analyze applicants' facial expressions and voice (e.g., OpenCV, Google Cloud Speech).

[0701] 3. Database - A storage system (e.g., MySQL, PostgreSQL) for storing basic information and sentiment data about applicants.

[0702] 4. Generative AI models - Artificial intelligence models for automatically generating and evaluating tests (e.g., OpenAI GPT-3).

[0703] 5. Machine learning models - Models for analyzing and classifying applicant sentiment data (e.g., scikit-learn, TensorFlow).

[0704] 6. Code analysis engine - Software used to evaluate the code submitted for testing (e.g., Pylint, SonarQube).

[0705] How it works

[0706] Enter applicant information

[0707] A user accesses an application form using a web browser and enters basic information (such as name, contact details, work history, desired job type, etc.). The device collects the applicant information and sends it to the server. At the same time, it uses a camera and microphone to analyze the applicant's facial expressions and voice and generate emotional data. This emotional data is also sent to the server.

[0708] Information storage and analysis

[0709] The server stores the received applicant's basic information and emotional data in a database. The server then refers to past emotional data, analyzes the newly acquired emotional data, and classifies it into an appropriate category (e.g., nervous, relieved).

[0710] Test Generation and Tuning

[0711] The server inputs prompts into the generative AI model based on the applicant's basic information to generate an appropriate test. The server then adjusts the test content based on the applicant's emotional data, aiming to create a relaxed environment for the applicant. For example, it may simplify the question format or set a flexible time limit to reduce tension.

[0712] Example prompt for a generative AI model:

[0713] "Generate coding tests for software engineers."

[0714] Testing and Sentiment Analysis

[0715] The device displays the generated test to the applicant, and the user follows the instructions to take the test. While the test is being taken, the device analyzes facial expressions and voice using a camera and microphone, capturing emotional data in real time and sending it to the server. This allows the collection of the applicant's performance data to be as accurate as possible.

[0716] Test Evaluation and Scoring

[0717] The server receives the test answers sent from the device and begins evaluating them using a generative AI model, which evaluates technical aspects such as code accuracy and efficiency, as well as its adaptability based on emotional data.

[0718] Score report generation and notification

[0719] The server creates a score report based on the test results and the analysis of the emotional data, and notifies the company and applicant. The report includes not only the technical score but also the applicant's emotional state (e.g., performance under stress, performance under normal circumstances).

[0720] This allows companies to comprehensively assess candidates' technical skills and emotional readiness, leading to better hiring decisions, while providing candidates with opportunities to deepen their self-understanding and grow through feedback.

[0721] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0722] Step 1: Enter and submit your application information

[0723] A user accesses the application form using a web browser and enters basic information (name, contact details, work history, desired job type, etc.). The entered information is recorded on the device.

[0724] The device sends the applicant's basic information to the server via API. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice. This generates emotional data, which is also sent to the server.

[0725] Input: Name, contact information, work history, desired job type, facial expression data, voice data

[0726] Output: Basic information of applicants, emotional data

[0727] Step 2: Store and analyze applicant information

[0728] The server stores the applicant's basic information and emotional data received from the terminal in a database.

[0729] The server analyzes the emotion data using a machine learning model (e.g., scikit-learn, TensorFlow) and classifies it into categories such as "tension" or "relief." This classification result is also stored in the database.

[0730] Input: Basic information of applicant, emotional data

[0731] Output: Stored applicant basic information, categorized emotion data

[0732] Step 3: Generate and refine tests

[0733] The server inputs a prompt into the generative AI model based on the applicant's basic information to generate an appropriate test. For example, the prompt might be, "Please generate a coding test for software engineers."

[0734] The server adjusts the generated test, referencing the emotional data and adjusting the content and difficulty of the test to make the applicant feel more relaxed.

[0735] Input: basic information of applicant, emotion data, prompt sentence

[0736] Output: Generated tests, adjusted test content

[0737] Step 4: View and perform tests

[0738] The terminal displays the generated test to the applicant.

[0739] The user follows the test questions and enters their answers, for example, creating a binary search algorithm in Python.

[0740] Input: Adjusted test content

[0741] Output: Applicant's test answers

[0742] Step 5: Sentiment analysis and sending during the test

[0743] During the test, the device uses a camera and microphone to analyze the applicant's facial expressions and voice in real time, capturing emotional data, which is then sent to a server.

[0744] Input: Real-time facial expression data, voice data

[0745] Output: Real-time emotion data

[0746] Step 6: Submit and evaluate your test answers

[0747] The terminal transmits the applicant's response to the server.

[0748] The server evaluates applicants' test answers using a generative AI model and uses a code analysis engine (e.g., Pylint, SonarQube) to check the code for accuracy, efficiency, and readability.

[0749] Input: Applicant's test answers, emotion data

[0750] Output: Evaluation results, technical score, emotional adaptability score

[0751] Step 7: Generate and notify your score report

[0752] The server generates a comprehensive score report based on the test evaluation results and emotional data, which includes a technical score and an emotional adaptability score.

[0753] The server generates a report and notifies the company and applicants by email.

[0754] Input: Assessment results, technical score, emotional adaptability score

[0755] Output: Generated score report, notification email

[0756] (Application example 2)

[0757] 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."

[0758] Conventional applicant evaluation systems only evaluate applicants' technical skills and knowledge, and do not consider psychological factors such as their emotional state or stress level. As a result, they are unable to properly evaluate the applicant's overall suitability, which can lead to flaws in personnel selection. Furthermore, while there is a need to understand the emotional state and stress levels of workers in factories and other places in real time to improve work efficiency and safety, current systems are unable to meet this need.

[0759] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting basic information about the applicant, a means including a generation AI for generating a test based on the basic information, and a means for providing the generated test to the applicant, who then takes the test. This enables a comprehensive aptitude evaluation that takes into account not only the applicant's technical skills but also their emotional state. The server also includes a means including an emotion engine for acquiring and analyzing the worker's emotional data, a means for integrating and analyzing the emotion data and test result data, and a means for adjusting tasks based on emotions and performance. This makes it possible to grasp the worker's emotional state in real time and appropriately adjust tasks accordingly, which is expected to improve work efficiency and safety.

[0760] "Applicant" refers to an individual who uses the System to be evaluated.

[0761] "Basic Information" refers to the personal data and biographical information that applicants enter into the system.

[0762] "Generative AI" refers to artificial intelligence that automatically generates appropriate tests based on basic information about applicants and evaluates them.

[0763] "Tests" refer to tasks or questions created by generative AI to assess applicants' skills and knowledge.

[0764] An "emotion engine" is a system that analyzes the facial expressions and voices of applicants and workers and recognizes their emotional state in real time.

[0765] "Test Result Data" refers to performance data from tests taken by applicants.

[0766] "Emotional data" refers to analytical results data that show the emotional state of applicants and workers.

[0767] A "task" refers to a specific task or assignment assigned to an applicant or worker.

[0768] "Task adjustment" refers to changing the content and difficulty of tasks assigned to workers based on emotional data and test result data.

[0769] To implement this invention, it is necessary to build and operate a system using the following procedure: First, a user (applicant or worker) inputs basic information through a terminal. The terminal then sends this basic information to a server, which then uses a generation AI to automatically generate a test appropriate for the applicant.

[0770] Next, the terminal displays the generated test to the applicant, who then takes the test. During the test, the terminal uses an emotion engine to analyze the facial expressions and voice of the applicant or worker, obtaining emotional data in real time. This data is then sent to the server.

[0771] The server receives the test results and emotion data, and uses generative AI to comprehensively evaluate these data. Based on the evaluation results, the server assigns a score and adjusts tasks based on emotion and performance.

[0772] The hardware used includes smart helmets and badges with built-in cameras and microphones, and a server for data management and analysis. The software used includes EmotionRecognizer (emotion engine), TaskScheduler (task coordination engine), and factory_database (database management system).

[0773] As a concrete example, let's say worker "A" is working in a foundry at a factory. The smart helmet captures "A's" facial expressions and voice in real time, and the emotion engine analyzes them. If the analysis identifies that "A" is in a high-stress state, the task adjustment engine automatically shifts "A" to an easier task. Furthermore, relaxing music begins to play from the smart helmet.

[0774] Examples of prompts to input to a generative AI model include:

[0775] "Adjust the tasks of the factory workers based on the following data: Worker ID: 3, Emotional Data: High Stress Level, Performance Data: Casting Efficiency 75%. If the worker is feeling stressed, assign them tasks that will help them relax."

[0776] As described above, this system makes it possible to comprehensively evaluate an applicant's technical skills and emotional state, and by assigning appropriate tasks based on the worker's emotional state, it is expected to improve work efficiency and safety.

[0777] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0778] Step 1:

[0779] The user inputs basic information and desired job type through the terminal. The terminal acquires the applicant's basic information (name, career history, desired job type, etc.) and sends it to the server.

[0780] Input: User (applicant) basic information

[0781] Output: Send basic information data to the server

[0782] Specific operation: Information entered on the terminal is sent to the server in real time and stored in a database on the server.

[0783] Step 2:

[0784] The device uses a camera and microphone to capture the applicant's facial expressions and voice, which are then analyzed by an emotion engine. The resulting emotion data is then sent to a server.

[0785] Input: Applicant's video and audio data

[0786] Output: Sending emotion data to the server

[0787] Specific operation: Data taken from the device's camera and microphone is analyzed by EmotionRecognizer and sent to the server as emotion data.

[0788] Step 3:

[0789] The server uses generative AI based on basic information and emotional data to generate a test that is appropriate for the applicant.

[0790] Input: Basic information data, emotion data

[0791] Output: Generated test data

[0792] Specific operation: The generation AI on the server generates appropriate tests based on basic information and emotional data, and saves the test content in a database.

[0793] Step 4:

[0794] The device presents the generated test to the applicant, who then takes the test. Test performance data and real-time emotional data are sent to the server.

[0795] Input: Generated test data

[0796] Output: Test performance data, real-time sentiment data

[0797] How it works: Applicants take the test and the results are sent from their devices to a server. Facial expressions and voices are also analyzed during the test, and emotional data is sent to the server in real time.

[0798] Step 5:

[0799] The server receives test performance and sentiment data and uses generative AI to evaluate and score it.

[0800] Input: Test performance data, emotion data

[0801] Output: Evaluation results, scoring data

[0802] Specific operation: The generation AI on the server analyzes the test results and emotional data, and performs an overall evaluation and scoring. These evaluation results are stored in a database.

[0803] Step 6:

[0804] The server executes a means for adjusting tasks suitable for the worker based on the scoring results and emotion data.

[0805] Input: Evaluation results, scoring data

[0806] Output: Reconciled task data

[0807] Specific operation: The TaskScheduler on the server calculates the optimal task based on the evaluation results and emotion data, and saves the adjusted task in a database.

[0808] Step 7:

[0809] The adjusted tasks are notified to the workers, who receive instructions for the new tasks via their terminals and start the appropriate tasks.

[0810] Input: Adjusted task data

[0811] Output: Task notification to workers

[0812] Specific operation: The terminal notifies the worker of the content of the new task, and the worker receives instructions for carrying out the task.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] [Third embodiment]

[0817] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0818] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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).

[0823] 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. 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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."

[0829] System Program and Description

[0830] To implement this invention, a system is constructed and operated according to the following procedure.

[0831] 1. Applicant information input interface

[0832] A user accesses the system and enters basic information and desired job type.

[0833] The terminal collects the information entered by the applicant and transmits it to the server.

[0834] 2. Test Generation

[0835] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[0836] 3. Conducting the test

[0837] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[0838] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[0839] 4. Evaluation of deliverables

[0840] The server receives the test answers and begins evaluation by the generative AI.

[0841] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[0842] 5. Score generation and notification

[0843] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[0844] The server notifies the company and applicant of the score report.

[0845] Specific examples

[0846] 1. Enter user information

[0847] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[0848] Terminal: Collects "A's" information through a web form and sends it to the server.

[0849] 2. Test Generation

[0850] Server: Based on the information of applicant "A," the generation AI automatically generates tests such as "algorithm problems" and "database operation."

[0851] 3. Conducting the test

[0852] Terminal: Display the generated coding test to applicant "A".

[0853] User: Applicant "A" writes a binary search algorithm in Python and completes the test.

[0854] 4. Evaluation of deliverables

[0855] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring.

[0856] 5. Score generation and notification

[0857] Server: Create a score report (e.g., algorithm 80 points, database 90 points) based on the evaluation of applicant "A."

[0858] The server will send the score report to the company and applicant "A" via email.

[0859] System benefits

[0860] This system allows companies to obtain quantitative information on skills in advance, enabling them to efficiently hire the right people. It also allows applicants to objectively evaluate their own skills, enabling them to apply to suitable workplaces.

[0861] In this way, the present invention provides a system that can improve the efficiency of a company's recruitment process and properly evaluate the skills of applicants.

[0862] The processing flow will be explained below.

[0863] Step 1:

[0864] A user accesses the system and logs in.

[0865] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[0866] Step 2:

[0867] The device sends the login information to the server.

[0868] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[0869] Step 3:

[0870] The server verifies the login information and performs authentication.

[0871] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[0872] Step 4:

[0873] The user enters basic information and desired job type.

[0874] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[0875] Step 5:

[0876] The terminal sends the entered basic information to the server.

[0877] What it does: Converts the information entered by the user into JSON format and sends it to the server.

[0878] Step 6:

[0879] The server stores the received basic information in a database.

[0880] How it works: The server stores the received basic information in a database and begins selecting an appropriate AI model.

[0881] Step 7:

[0882] The server generates appropriate tests based on the generated AI.

[0883] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates program coding tests, design assignments, and more.

[0884] Step 8:

[0885] The server sends the generated test to the user's device.

[0886] Operation: The generated test content is converted into JSON format and sent to the user's device.

[0887] Step 9:

[0888] The terminal displays the received test to the user.

[0889] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[0890] Step 10:

[0891] The user takes the generated test and enters the answers.

[0892] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[0893] Step 11:

[0894] The terminal sends the user's test results to the server.

[0895] Behavior: The answers to the test completed by the user are converted into JSON format and sent to the server.

[0896] Step 12:

[0897] The server inputs the received test results into the generation AI and begins evaluation.

[0898] How it works: The server passes the received answer to the generation AI, which starts the process of evaluating and scoring the answer.

[0899] Step 13:

[0900] The server receives the evaluation results from the generation AI and generates a score.

[0901] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for the algorithm, 90 points for the database) is calculated.

[0902] Step 14:

[0903] The server creates a score report and notifies the company and the user.

[0904] Operation: A score report is generated based on the scoring results and sent to the company and user as an attachment to a notification email.

[0905] Step 15:

[0906] Users and businesses review the score report.

[0907] What it does: Users and businesses receive a notification email and click the link to view or download their score report.

[0908] This series of processes allows companies to quantitatively evaluate applicants' skills in advance, allowing them to efficiently hire the right people. Applicants also receive an objective evaluation of their skills, providing them with information that will be useful in their job search.

[0909] Example 1

[0910] 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."

[0911] In today's hiring process, there is a lack of efficient and objective methods for evaluating applicants' skills. Companies also face the problem of finding the right talent, which increases the time and cost required to hire them. Furthermore, applicants themselves have few opportunities to objectively evaluate their own skills, making it difficult to find the right job. To address these issues, a system is needed that can generate appropriate tests based on applicants' basic information and objectively evaluate the test results.

[0912] 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.

[0913] In this invention, the server includes: means for inputting basic information about the applicant; means including a generation AI for generating a test based on the basic information; means for providing the generated test to the applicant and for the applicant to take the test; means including a generation AI for receiving, evaluating, and scoring the results of the test; and means for generating and notifying a score report based on the evaluation results. This allows companies to efficiently and objectively evaluate applicants' skills and quickly hire the right talent. Applicants can also objectively understand their own skills and apply to suitable jobs.

[0914] "Applicant" refers to an individual participating in the recruitment process.

[0915] "Basic information" refers to personal information entered by applicants, such as name, contact information, and desired job type.

[0916] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate and evaluate tests.

[0917] "Tests" refer to tasks automatically created by generative AI to assess applicants' skills.

[0918] "Scoring" refers to the process in which generative AI evaluates the test results and assigns a numerical score.

[0919] "Score report" refers to a report summarizing the scoring results generated by the generating AI.

[0920] "Means of notification" refers to the means of communication used to inform applicants and companies of their score reports.

[0921] In order to implement the present invention, the following hardware and software are used.

[0922] Hardware and software used

[0923] Hardware:

[0924] Server: High performance computing server (e.g. AWS EC2)

[0925] Device: PC or tablet (browser compatible) used by the user

[0926] software:

[0927] Web front-end: HTML, CSS, JavaScript

[0928] Backend: Django framework in Python

[0929] Generative AI models: OpenAI's GPT-4 and Google's BERT

[0930] Specific operation of the system

[0931] 1. User information input interface

[0932] A user opens a web browser and logs in.

[0933] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0934] Specific processing flow of the program

[0935] Step 1:

[0936] A user opens a web browser and accesses a login page. The user enters login information and logs into the system. The terminal sends the entered login information to the server. The server authenticates the login information and displays the user's homepage. This completes the user's authentication to access the system. Input: Login information. Output: User's homepage.

[0937] Step 2:

[0938] The user enters the necessary information, such as desired job type and personal information, into a form. The terminal sends the entered information to the server. The server stores this information in a database. This information is also used for later processing. Input: desired job type, personal information. Output: information stored in the database.

[0939] Step 3:

[0940] The server creates a prompt to generate an appropriate test based on the information received from the user. For example, it generates a prompt that reads, "Applicant A is looking for a software engineer position. Please generate a test that is suitable for him." Based on the generated prompt, it asks the generative AI model to generate a test. The generative AI model generates test content in response to the prompt and sends it back to the server. Input: User information. Output: Generated test content.

[0941] Step 4:

[0942] The server sends the generated test content to the terminal and displays it. The user checks and takes the test through the terminal. The terminal sends the answers entered by the user to the server. Input: Generated test content, user answers. Output: Answers sent to the server.

[0943] Step 5:

[0944] The server creates an evaluation prompt based on the received test answer. For example, it generates a prompt such as "Please evaluate the following Python code. Score it in terms of efficiency, accuracy, and refactoring," and attaches the answer code. It then sends the prompt to the generative AI model, requesting it to evaluate the answer. The server generates a score based on the evaluation returned by the generative AI model. Input: Test answer. Output: Generated score.

[0945] Step 6:

[0946] The server generates a score report based on the evaluation score and notifies the appropriate companies and applicants. The score report is sent via email, etc. Input: Evaluation score. Output: Score report and notification.

[0947] (Application example 1)

[0948] 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."

[0949] In the cybersecurity field, it is important to accurately evaluate the skills of experts and hire the right people. However, traditional hiring processes lack a means to quantitatively and objectively evaluate applicants' skills, requiring companies to spend a great deal of time and effort to find the right talent. Applicants also have limited opportunities to have their skills properly evaluated, making it difficult for them to effectively conduct their job search. There is a need for a method to solve these problems and improve the efficiency and accuracy of skill evaluation.

[0950] 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.

[0951] In this invention, the server includes: a means for inputting basic information about an applicant; a means including a generation AI for generating a test based on the basic information; a means for providing the generated test to the applicant and having the applicant take the test; a means including a generation AI for receiving, evaluating, and scoring the test results; a means for evaluating the skills of cybersecurity professionals; and a means for reporting the scored results. This allows companies to accurately evaluate applicants' cybersecurity skills and efficiently hire the right talent. Furthermore, applicants can apply for more suitable jobs by having their skills objectively evaluated.

[0952] "Applicant" refers to an individual participating in the recruitment process and applying for a particular position.

[0953] "Basic information" refers to data entered by the applicant, such as personal information, desired job type, and skill set.

[0954] "Generative AI" refers to a program that uses machine learning and artificial intelligence techniques to automatically generate and evaluate tests appropriate for applicants.

[0955] "Test" refers to tasks or questions automatically generated by generative AI to assess applicants' skills and abilities.

[0956] A "cybersecurity professional" is an individual with expertise in areas such as network security, application security, and threat analysis.

[0957] "Skill assessment" refers to the process in which generative AI evaluates and scores the abilities of applicants based on the results of tests they take.

[0958] A "score report" refers to a report in which the generative AI evaluates the test results and summarizes the quantitative scores and analysis results.

[0959] In order to implement the present invention, the following system is constructed and operated: The system mainly includes processes related to a server, a terminal, and a user.

[0960] 1. Enter basic information about the applicant

[0961] The server first provides an interface for collecting basic information about applicants. The user enters their information (name, email address, desired job type, skill set, etc.) through this interface and sends it to the server. The terminal then uses a web form or application to collect this information.

[0962] 2. Automatic test generation

[0963] The server automatically generates appropriate tests using a generative AI based on the collected basic information of applicants. This generative AI uses machine learning models (e.g., OpenAI's GPT-based models) to create questions (e.g., network security assessment, application security analysis, threat analysis, etc.) that are optimal for each applicant.

[0964] 3. Conducting the test

[0965] The server provides the generated test to the applicant. The user takes the test using a device at hand (smartphone, tablet, laptop, etc.). The test content consists of tasks and questions corresponding to each specialized field.

[0966] 4. Evaluation of deliverables

[0967] The server receives the test results sent by the user and evaluates them using a generative AI, which scores the applicant's work and creates a detailed score report based on evaluation criteria (e.g., accuracy, efficiency, problem-solving ability).

[0968] 5. Score report delivery

[0969] The server notifies companies and applicants of the generated score report via email, dashboard, etc.

[0970] Hardware and software used

[0971] The hardware used is cloud servers such as AWS EC2 and Google Cloud. Generative AI models include OpenAI's GPT model and Hugging Face's Transformer. Databases such as MongoDB and PostgreSQL are used to manage applicant information. The entire system is built using Flask (Python) as a web framework.

[0972] Specific examples

[0973] For example, applicant "Yamada Taro" applies for a position as a network security engineer. The applicant enters basic information through a web form and selects "Network Security Engineer" as the desired job type. Based on this information, the server's generation AI automatically generates network penetration testing and threat analysis tasks and provides them to the applicant. When the applicant performs these tasks and submits them to the server, the generation AI evaluates the deliverables and creates a score report. The score report is then notified to the applicant and the hiring manager.

[0974] Prompt Sentence Examples

[0975] Applicant information: The applicant's name is "Yamada Taro", the desired job is "Network Security Engineer", and the skills are "Network Penetration Testing", "Firewall Configuration", and "Incident Response".

[0976] Test Generation Requirements: Please generate specialized tests suitable for the network security field. For example, "Security vulnerability detection" and "Network traffic analysis."

[0977] Evaluation criteria: accuracy, efficiency, and resolving ability.

[0978] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0979] Step 1:

[0980] The server provides an interface for entering basic information about applicants. Users enter their information (name, email address, desired job type, skill set, etc.) and send this information to the server via their terminal. The server receives the input data and stores it in a database. Input: Basic information about applicants. Output: Saved basic information about applicants.

[0981] Step 2:

[0982] The server calls a generative AI module based on the stored basic information and automatically generates an appropriate test. This generative AI uses, for example, OpenAI's GPT model. The generative AI generates specific test questions (e.g., network penetration tests, threat analysis tasks, etc.) based on the input skill set and desired job type. Input: Basic information about the applicant. Output: Generated test.

[0983] Step 3:

[0984] The terminal provides the generated test to the applicant. The user accesses the test using a terminal (smartphone, tablet, laptop, etc.) and answers the questions. After completing the answers, the user sends the results (code, answer document, etc.) to the server via the terminal. Input: Generated test. Output: Applicant's answers.

[0985] Step 4:

[0986] The server receives the test results sent by the user and calls the generation AI module again for evaluation. The generation AI evaluates the applicant's submission and generates a score. It also takes into account accuracy, efficiency, problem-solving ability, etc. as evaluation criteria. Input: Applicant's answers. Output: Generated score.

[0987] Step 5:

[0988] The server creates a score report based on the completed score. This score report also includes detailed evaluation results by the generation AI. The server notifies the company and applicant of this report by email. Input: Generated score. Output: Generated score report.

[0989] 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.

[0990] System Program and Description

[0991] To implement this invention, a system is constructed and operated according to the following procedure.

[0992] 1. Applicant information input interface

[0993] A user accesses the system and enters basic information and desired job type.

[0994] The terminal collects the information entered by the applicant and transmits it to the server.

[0995] The device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions at that time (e.g., tension, relief, etc.).

[0996] The server stores the emotion data along with basic information.

[0997] 2. Test Generation

[0998] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[0999] The emotion engine references the user's past emotional data and adjusts the test content to make the user feel more relaxed.

[1000] 3. Conducting the test

[1001] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[1002] During the test, the device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions in real time, and this data is sent to the server.

[1003] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[1004] 4. Evaluation of deliverables

[1005] The server receives the test answers and begins evaluation by the generative AI.

[1006] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[1007] The server uses an emotion engine to evaluate the emotional data collected during the test. For example, if a tester has a high rate of correct answers when under high stress, their adaptability will be evaluated.

[1008] 5. Score generation and notification

[1009] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[1010] The server includes the results of the analysis of emotional data (e.g., performance under stress, performance under normal circumstances) in the score report.

[1011] The server notifies the company and applicant of the score report.

[1012] Specific examples

[1013] 1. Enter user information

[1014] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[1015] Device: Collects information about "A" through a web form and sends it to the server. The device also uses a camera and microphone to analyze "A"'s facial expressions and voice to obtain emotional data.

[1016] 2. Test Generation

[1017] Server: Based on information about applicant "A," the generation AI automatically generates "algorithm problems" and "database operation" tests, and the emotion engine adjusts the content.

[1018] 3. Conducting the test

[1019] Device: The generated coding test is displayed to applicant "A" and emotional data is collected in real time while the test is being conducted.

[1020] User: Applicant "A" created a binary search algorithm in Python and completed the test. The device also sent emotion data to the server.

[1021] 4. Evaluation of deliverables

[1022] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring. In addition, it reflects emotional data in the evaluation.

[1023] 5. Score generation and notification

[1024] Server: Create a score report based on the evaluation of applicant "A" and include emotional data (e.g., performance under stress).

[1025] The server sends the score report to the company and applicant "A" via email.

[1026] System benefits

[1027] This system allows companies to evaluate applicants' emotional adaptability as well as their technical skills, making it possible to make a comprehensive judgment that takes into account not only technical ability but also mental aptitude. Applicants also receive feedback based on their emotional state, which helps them to better understand themselves.

[1028] The processing flow will be explained below.

[1029] Step 1:

[1030] A user accesses the system and logs in.

[1031] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[1032] Step 2:

[1033] The device sends the login information to the server.

[1034] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[1035] Step 3:

[1036] The server verifies the login information and performs authentication.

[1037] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[1038] Step 4:

[1039] The user enters basic information and desired job type.

[1040] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[1041] Step 5:

[1042] The terminal sends the entered basic information to the server.

[1043] How it works: The information entered by the user is converted into JSON format and sent to the server. It also uses the camera and microphone to analyze the user's facial expressions and voice in real time to obtain emotional data.

[1044] Step 6:

[1045] The server stores the received basic information and emotion data in a database.

[1046] Operation: The server stores the received basic information and emotion data in a database and begins selecting an appropriate AI model.

[1047] Step 7:

[1048] The server generates appropriate tests based on the generated AI.

[1049] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates coding tests, design assignments, etc. The emotion engine references past emotional data and adjusts the content to make it more relaxing for the user.

[1050] Step 8:

[1051] The server sends the generated test to the user's device.

[1052] Operation: The generated test content is converted into JSON format and sent to the user's device.

[1053] Step 9:

[1054] The terminal displays the received test to the user.

[1055] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[1056] Step 10:

[1057] The user takes the generated test and enters the answers.

[1058] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[1059] Step 11:

[1060] The device sends the user's test results and emotional data to the server.

[1061] How it works: The answers to the tests completed by the user are converted into JSON format and sent to the server along with real-time emotional data.

[1062] Step 12:

[1063] The server inputs the received test results into the generation AI and begins evaluation.

[1064] How it works: The server passes the received answers and emotion data to the generation AI, which then begins the process of evaluating and scoring the answers.

[1065] Step 13:

[1066] The server receives the evaluation results from the generation AI and generates a score.

[1067] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for algorithm, 90 points for design) is calculated. The impact on performance is also evaluated, taking into account emotional data.

[1068] Step 14:

[1069] The server creates a score report and notifies the company and the user.

[1070] Operation: A score report is generated based on the scoring results, and includes the results of emotional data analysis (e.g., performance under stress, performance under normal circumstances). A notification email is sent to the company and user with a link to download the score report.

[1071] Step 15:

[1072] Users and businesses review the score report.

[1073] What it does: Users and businesses click on the link in the notification email they receive to view or download their score report.

[1074] This process allows companies to assess applicants' technical skills and emotional readiness in advance, enabling them to efficiently hire the right talent. Applicants also receive feedback based on their skills and emotional state, allowing them to better target workplaces.

[1075] Example 2

[1076] 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."

[1077] In the modern recruitment process, it is necessary to evaluate not only the technical skills of applicants but also their mental and emotional adaptability. However, conventional systems focus on technical evaluation and lack the ability to properly evaluate and reflect the emotional state of applicants, making it difficult to provide a comprehensive evaluation.

[1078] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting basic information of the applicant, a means for analyzing the applicant's emotions and saving the data, a means including a generation AI for generating a test based on the basic information, and a means for adjusting the test content based on the emotion data. This makes it possible to comprehensively evaluate the applicant's technical skills and emotional adaptability.

[1079] "Applicant" refers to a person participating in the recruitment examination or selection process.

[1080] "Basic information" refers to basic attribute information about the applicant, such as name, contact information, work history, and desired job type.

[1081] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to automatically perform specific tasks.

[1082] "Test" refers to tasks or questions designed to assess an applicant's technical skills and aptitude.

[1083] "Emotional data" refers to information about the emotional state of applicants analyzed from their facial expressions, voice, etc.

[1084] "Adjustment measures" refer to mechanisms for changing and optimizing the content and format of tests based on emotional data and other information.

[1085] "Evaluation means" refers to the system for analyzing the test results and performing scoring and evaluation.

[1086] "Real time" refers to near-instant processing and response.

[1087] A "server" refers to a computer system that provides data processing and storage functions over a network.

[1088] "Scoring" refers to the process of quantifying an applicant's performance based on test results.

[1089] The system is designed to assess applicants' technical skills and emotional readiness and is implemented using the following hardware and software components:

[1090] Hardware Components

[1091] 1. Server - A computer system that provides data processing and storage capabilities (e.g., AWS EC2, Google Cloud Compute Engine).

[1092] 2. Terminal - The device (e.g., PC, tablet, smartphone) on which the applicant enters information and takes the test.

[1093] 3. Camera and Microphone - Input devices to capture the applicant's facial expressions and voice (e.g. webcam, built-in microphone).

[1094] Software Components

[1095] 1. Web Browser - The interface through which applicants enter their information (e.g., Google Chrome, Mozilla Firefox).

[1096] 2. Emotion analysis software - Software to analyze applicants' facial expressions and voice (e.g., OpenCV, Google Cloud Speech).

[1097] 3. Database - A storage system (e.g., MySQL, PostgreSQL) for storing basic information and sentiment data about applicants.

[1098] 4. Generative AI models - Artificial intelligence models for automatically generating and evaluating tests (e.g., OpenAI GPT-3).

[1099] 5. Machine learning models - Models for analyzing and classifying applicant sentiment data (e.g., scikit-learn, TensorFlow).

[1100] 6. Code analysis engine - Software used to evaluate the code submitted for testing (e.g., Pylint, SonarQube).

[1101] How it works

[1102] Enter applicant information

[1103] A user accesses an application form using a web browser and enters basic information (such as name, contact details, work history, desired job type, etc.). The device collects the applicant information and sends it to the server. At the same time, it uses a camera and microphone to analyze the applicant's facial expressions and voice and generate emotional data. This emotional data is also sent to the server.

[1104] Information storage and analysis

[1105] The server stores the received applicant's basic information and emotional data in a database. The server then refers to past emotional data, analyzes the newly acquired emotional data, and classifies it into an appropriate category (e.g., nervous, relieved).

[1106] Test Generation and Tuning

[1107] The server inputs prompts into the generative AI model based on the applicant's basic information to generate an appropriate test. The server then adjusts the test content based on the applicant's emotional data, aiming to create a relaxed environment for the applicant. For example, it may simplify the question format or set a flexible time limit to reduce tension.

[1108] Example prompt for a generative AI model:

[1109] "Generate coding tests for software engineers."

[1110] Testing and Sentiment Analysis

[1111] The device displays the generated test to the applicant, and the user follows the instructions to take the test. While the test is being taken, the device analyzes facial expressions and voice using a camera and microphone, capturing emotional data in real time and sending it to the server. This allows the collection of the applicant's performance data to be as accurate as possible.

[1112] Test Evaluation and Scoring

[1113] The server receives the test answers sent from the device and begins evaluating them using a generative AI model, which evaluates technical aspects such as code accuracy and efficiency, as well as its adaptability based on emotional data.

[1114] Score report generation and notification

[1115] The server creates a score report based on the test results and the analysis of the emotional data, and notifies the company and applicant. The report includes not only the technical score but also the applicant's emotional state (e.g., performance under stress, performance under normal circumstances).

[1116] This allows companies to comprehensively assess candidates' technical skills and emotional readiness, leading to better hiring decisions, while providing candidates with opportunities to deepen their self-understanding and grow through feedback.

[1117] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1118] Step 1: Enter and submit your application information

[1119] A user accesses the application form using a web browser and enters basic information (name, contact details, work history, desired job type, etc.). The entered information is recorded on the device.

[1120] The device sends the applicant's basic information to the server via API. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice. This generates emotional data, which is also sent to the server.

[1121] Input: Name, contact information, work history, desired job type, facial expression data, voice data

[1122] Output: Basic information of applicants, emotional data

[1123] Step 2: Store and analyze applicant information

[1124] The server stores the applicant's basic information and emotional data received from the terminal in a database.

[1125] The server analyzes the emotion data using a machine learning model (e.g., scikit-learn, TensorFlow) and classifies it into categories such as "tension" or "relief." This classification result is also stored in the database.

[1126] Input: Basic information of applicant, emotional data

[1127] Output: Stored applicant basic information, categorized emotion data

[1128] Step 3: Generate and refine tests

[1129] The server inputs a prompt into the generative AI model based on the applicant's basic information to generate an appropriate test. For example, the prompt might be, "Please generate a coding test for software engineers."

[1130] The server adjusts the generated test, referencing the emotional data and adjusting the content and difficulty of the test to make the applicant feel more relaxed.

[1131] Input: basic information of applicant, emotion data, prompt sentence

[1132] Output: Generated tests, adjusted test content

[1133] Step 4: View and perform tests

[1134] The terminal displays the generated test to the applicant.

[1135] The user follows the test questions and enters their answers, for example, creating a binary search algorithm in Python.

[1136] Input: Adjusted test content

[1137] Output: Applicant's test answers

[1138] Step 5: Sentiment analysis and sending during the test

[1139] During the test, the device uses a camera and microphone to analyze the applicant's facial expressions and voice in real time, capturing emotional data, which is then sent to a server.

[1140] Input: Real-time facial expression data, voice data

[1141] Output: Real-time emotion data

[1142] Step 6: Submit and evaluate your test answers

[1143] The terminal transmits the applicant's response to the server.

[1144] The server evaluates applicants' test answers using a generative AI model and uses a code analysis engine (e.g., Pylint, SonarQube) to check the code for accuracy, efficiency, and readability.

[1145] Input: Applicant's test answers, emotion data

[1146] Output: Evaluation results, technical score, emotional adaptability score

[1147] Step 7: Generate and notify your score report

[1148] The server generates a comprehensive score report based on the test evaluation results and emotional data, which includes a technical score and an emotional adaptability score.

[1149] The server generates a report and notifies the company and applicants by email.

[1150] Input: Assessment results, technical score, emotional adaptability score

[1151] Output: Generated score report, notification email

[1152] (Application example 2)

[1153] 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."

[1154] Conventional applicant evaluation systems only evaluate applicants' technical skills and knowledge, and do not consider psychological factors such as their emotional state or stress level. As a result, they are unable to properly evaluate the applicant's overall suitability, which can lead to flaws in personnel selection. Furthermore, while there is a need to understand the emotional state and stress levels of workers in factories and other places in real time to improve work efficiency and safety, current systems are unable to meet this need.

[1155] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting basic information about the applicant, a means including a generation AI for generating a test based on the basic information, and a means for providing the generated test to the applicant, who then takes the test. This enables a comprehensive aptitude evaluation that takes into account not only the applicant's technical skills but also their emotional state. The server also includes a means including an emotion engine for acquiring and analyzing the worker's emotional data, a means for integrating and analyzing the emotion data and test result data, and a means for adjusting tasks based on emotions and performance. This makes it possible to grasp the worker's emotional state in real time and appropriately adjust tasks accordingly, which is expected to improve work efficiency and safety.

[1156] "Applicant" refers to an individual who uses the System to be evaluated.

[1157] "Basic Information" refers to the personal data and biographical information that applicants enter into the system.

[1158] "Generative AI" refers to artificial intelligence that automatically generates appropriate tests based on basic information about applicants and evaluates them.

[1159] "Tests" refer to tasks or questions created by generative AI to assess applicants' skills and knowledge.

[1160] An "emotion engine" is a system that analyzes the facial expressions and voices of applicants and workers and recognizes their emotional state in real time.

[1161] "Test Result Data" refers to performance data from tests taken by applicants.

[1162] "Emotional data" refers to analytical results data that show the emotional state of applicants and workers.

[1163] A "task" refers to a specific task or assignment assigned to an applicant or worker.

[1164] "Task adjustment" refers to changing the content and difficulty of tasks assigned to workers based on emotional data and test result data.

[1165] To implement this invention, it is necessary to build and operate a system using the following procedure: First, a user (applicant or worker) inputs basic information through a terminal. The terminal then sends this basic information to a server, which then uses a generation AI to automatically generate a test appropriate for the applicant.

[1166] Next, the terminal displays the generated test to the applicant, who then takes the test. During the test, the terminal uses an emotion engine to analyze the facial expressions and voice of the applicant or worker, obtaining emotional data in real time. This data is then sent to the server.

[1167] The server receives the test results and emotion data, and uses generative AI to comprehensively evaluate these data. Based on the evaluation results, the server assigns a score and adjusts tasks based on emotion and performance.

[1168] The hardware used includes smart helmets and badges with built-in cameras and microphones, and a server for data management and analysis. The software used includes EmotionRecognizer (emotion engine), TaskScheduler (task coordination engine), and factory_database (database management system).

[1169] As a concrete example, let's say worker "A" is working in a foundry at a factory. The smart helmet captures "A's" facial expressions and voice in real time, and the emotion engine analyzes them. If the analysis identifies that "A" is in a high-stress state, the task adjustment engine automatically shifts "A" to an easier task. Furthermore, relaxing music begins to play from the smart helmet.

[1170] Examples of prompts to input to a generative AI model include:

[1171] "Adjust the tasks of the factory workers based on the following data: Worker ID: 3, Emotional Data: High Stress Level, Performance Data: Casting Efficiency 75%. If the worker is feeling stressed, assign them tasks that will help them relax."

[1172] As described above, this system makes it possible to comprehensively evaluate an applicant's technical skills and emotional state, and by assigning appropriate tasks based on the worker's emotional state, it is expected to improve work efficiency and safety.

[1173] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1174] Step 1:

[1175] The user inputs basic information and desired job type through the terminal. The terminal acquires the applicant's basic information (name, career history, desired job type, etc.) and sends it to the server.

[1176] Input: User (applicant) basic information

[1177] Output: Send basic information data to the server

[1178] Specific operation: Information entered on the terminal is sent to the server in real time and stored in a database on the server.

[1179] Step 2:

[1180] The device uses a camera and microphone to capture the applicant's facial expressions and voice, which are then analyzed by an emotion engine. The resulting emotion data is then sent to a server.

[1181] Input: Applicant's video and audio data

[1182] Output: Sending emotion data to the server

[1183] Specific operation: Data taken from the device's camera and microphone is analyzed by EmotionRecognizer and sent to the server as emotion data.

[1184] Step 3:

[1185] The server uses generative AI based on basic information and emotional data to generate a test that is appropriate for the applicant.

[1186] Input: Basic information data, emotion data

[1187] Output: Generated test data

[1188] Specific operation: The generation AI on the server generates appropriate tests based on basic information and emotional data, and saves the test content in a database.

[1189] Step 4:

[1190] The device presents the generated test to the applicant, who then takes the test. Test performance data and real-time emotional data are sent to the server.

[1191] Input: Generated test data

[1192] Output: Test performance data, real-time sentiment data

[1193] How it works: Applicants take the test and the results are sent from their devices to a server. Facial expressions and voices are also analyzed during the test, and emotional data is sent to the server in real time.

[1194] Step 5:

[1195] The server receives test performance and sentiment data and uses generative AI to evaluate and score it.

[1196] Input: Test performance data, emotion data

[1197] Output: Evaluation results, scoring data

[1198] Specific operation: The generation AI on the server analyzes the test results and emotional data, and performs an overall evaluation and scoring. These evaluation results are stored in a database.

[1199] Step 6:

[1200] The server executes a means for adjusting tasks suitable for the worker based on the scoring results and emotion data.

[1201] Input: Evaluation results, scoring data

[1202] Output: Reconciled task data

[1203] Specific operation: The TaskScheduler on the server calculates the optimal task based on the evaluation results and emotion data, and saves the adjusted task in a database.

[1204] Step 7:

[1205] The adjusted tasks are notified to the workers, who receive instructions for the new tasks via their terminals and start the appropriate tasks.

[1206] Input: Adjusted task data

[1207] Output: Task notification to workers

[1208] Specific operation: The terminal notifies the worker of the content of the new task, and the worker receives instructions for carrying out the task.

[1209] 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.

[1210] 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.

[1211] 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.

[1212] [Fourth embodiment]

[1213] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1214] 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.

[1215] 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).

[1216] 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.

[1217] 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.

[1218] 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).

[1219] 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. 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.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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."

[1226] System Program and Description

[1227] To implement this invention, a system is constructed and operated according to the following procedure.

[1228] 1. Applicant information input interface

[1229] A user accesses the system and enters basic information and desired job type.

[1230] The terminal collects the information entered by the applicant and transmits it to the server.

[1231] 2. Test Generation

[1232] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[1233] 3. Conducting the test

[1234] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[1235] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[1236] 4. Evaluation of deliverables

[1237] The server receives the test answers and begins evaluation by the generative AI.

[1238] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[1239] 5. Score generation and notification

[1240] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[1241] The server notifies the company and applicant of the score report.

[1242] Specific examples

[1243] 1. Enter user information

[1244] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[1245] Terminal: Collects "A's" information through a web form and sends it to the server.

[1246] 2. Test Generation

[1247] Server: Based on the information of applicant "A," the generation AI automatically generates tests such as "algorithm problems" and "database operation."

[1248] 3. Conducting the test

[1249] Terminal: Display the generated coding test to applicant "A".

[1250] User: Applicant "A" writes a binary search algorithm in Python and completes the test.

[1251] 4. Evaluation of deliverables

[1252] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring.

[1253] 5. Score generation and notification

[1254] Server: Create a score report (e.g., algorithm 80 points, database 90 points) based on the evaluation of applicant "A."

[1255] The server will send the score report to the company and applicant "A" via email.

[1256] System benefits

[1257] This system allows companies to obtain quantitative information on skills in advance, enabling them to efficiently hire the right people. It also allows applicants to objectively evaluate their own skills, enabling them to apply to suitable workplaces.

[1258] In this way, the present invention provides a system that can improve the efficiency of a company's recruitment process and properly evaluate the skills of applicants.

[1259] The processing flow will be explained below.

[1260] Step 1:

[1261] A user accesses the system and logs in.

[1262] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[1263] Step 2:

[1264] The device sends the login information to the server.

[1265] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[1266] Step 3:

[1267] The server verifies the login information and performs authentication.

[1268] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[1269] Step 4:

[1270] The user enters basic information and desired job type.

[1271] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[1272] Step 5:

[1273] The terminal sends the entered basic information to the server.

[1274] What it does: Converts the information entered by the user into JSON format and sends it to the server.

[1275] Step 6:

[1276] The server stores the received basic information in a database.

[1277] How it works: The server stores the received basic information in a database and begins selecting an appropriate AI model.

[1278] Step 7:

[1279] The server generates appropriate tests based on the generated AI.

[1280] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates program coding tests, design assignments, and more.

[1281] Step 8:

[1282] The server sends the generated test to the user's device.

[1283] Operation: The generated test content is converted into JSON format and sent to the user's device.

[1284] Step 9:

[1285] The terminal displays the received test to the user.

[1286] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[1287] Step 10:

[1288] The user takes the generated test and enters the answers.

[1289] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[1290] Step 11:

[1291] The terminal sends the user's test results to the server.

[1292] Behavior: The answers to the test completed by the user are converted into JSON format and sent to the server.

[1293] Step 12:

[1294] The server inputs the received test results into the generation AI and begins evaluation.

[1295] How it works: The server passes the received answer to the generation AI, which starts the process of evaluating and scoring the answer.

[1296] Step 13:

[1297] The server receives the evaluation results from the generation AI and generates a score.

[1298] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for the algorithm, 90 points for the database) is calculated.

[1299] Step 14:

[1300] The server creates a score report and notifies the company and the user.

[1301] Operation: A score report is generated based on the scoring results and sent to the company and user as an attachment to a notification email.

[1302] Step 15:

[1303] Users and businesses review the score report.

[1304] What it does: Users and businesses receive a notification email and click the link to view or download their score report.

[1305] This series of processes allows companies to quantitatively evaluate applicants' skills in advance, allowing them to efficiently hire the right people. Applicants also receive an objective evaluation of their skills, providing them with information that will be useful in their job search.

[1306] Example 1

[1307] 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."

[1308] In today's hiring process, there is a lack of efficient and objective methods for evaluating applicants' skills. Companies also face the problem of finding the right talent, which increases the time and cost required to hire them. Furthermore, applicants themselves have few opportunities to objectively evaluate their own skills, making it difficult to find the right job. To address these issues, a system is needed that can generate appropriate tests based on applicants' basic information and objectively evaluate the test results.

[1309] 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.

[1310] In this invention, the server includes: means for inputting basic information about the applicant; means including a generation AI for generating a test based on the basic information; means for providing the generated test to the applicant and for the applicant to take the test; means including a generation AI for receiving, evaluating, and scoring the results of the test; and means for generating and notifying a score report based on the evaluation results. This allows companies to efficiently and objectively evaluate applicants' skills and quickly hire the right talent. Applicants can also objectively understand their own skills and apply to suitable jobs.

[1311] "Applicant" refers to an individual participating in the recruitment process.

[1312] "Basic information" refers to personal information entered by applicants, such as name, contact information, and desired job type.

[1313] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate and evaluate tests.

[1314] "Tests" refer to tasks automatically created by generative AI to assess applicants' skills.

[1315] "Scoring" refers to the process in which generative AI evaluates the test results and assigns a numerical score.

[1316] "Score report" refers to a report summarizing the scoring results generated by the generating AI.

[1317] "Means of notification" refers to the means of communication used to inform applicants and companies of their score reports.

[1318] In order to implement the present invention, the following hardware and software are used.

[1319] Hardware and software used

[1320] Hardware:

[1321] Server: High performance computing server (e.g. AWS EC2)

[1322] Device: PC or tablet (browser compatible) used by the user

[1323] software:

[1324] Web front-end: HTML, CSS, JavaScript

[1325] Backend: Django framework in Python

[1326] Generative AI models: OpenAI's GPT-4 and Google's BERT

[1327] Specific operation of the system

[1328] 1. User information input interface

[1329] A user opens a web browser and logs in.

[1330] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1331] Specific processing flow of the program

[1332] Step 1:

[1333] A user opens a web browser and accesses a login page. The user enters login information and logs into the system. The terminal sends the entered login information to the server. The server authenticates the login information and displays the user's homepage. This completes the user's authentication to access the system. Input: Login information. Output: User's homepage.

[1334] Step 2:

[1335] The user enters the necessary information, such as desired job type and personal information, into a form. The terminal sends the entered information to the server. The server stores this information in a database. This information is also used for later processing. Input: desired job type, personal information. Output: information stored in the database.

[1336] Step 3:

[1337] The server creates a prompt to generate an appropriate test based on the information received from the user. For example, it generates a prompt that reads, "Applicant A is looking for a software engineer position. Please generate a test that is suitable for him." Based on the generated prompt, it asks the generative AI model to generate a test. The generative AI model generates test content in response to the prompt and sends it back to the server. Input: User information. Output: Generated test content.

[1338] Step 4:

[1339] The server sends the generated test content to the terminal and displays it. The user checks and takes the test through the terminal. The terminal sends the answers entered by the user to the server. Input: Generated test content, user answers. Output: Answers sent to the server.

[1340] Step 5:

[1341] The server creates an evaluation prompt based on the received test answer. For example, it generates a prompt such as "Please evaluate the following Python code. Score it in terms of efficiency, accuracy, and refactoring," and attaches the answer code. It then sends the prompt to the generative AI model, requesting it to evaluate the answer. The server generates a score based on the evaluation returned by the generative AI model. Input: Test answer. Output: Generated score.

[1342] Step 6:

[1343] The server generates a score report based on the evaluation score and notifies the appropriate companies and applicants. The score report is sent via email, etc. Input: Evaluation score. Output: Score report and notification.

[1344] (Application example 1)

[1345] 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."

[1346] In the cybersecurity field, it is important to accurately evaluate the skills of experts and hire the right people. However, traditional hiring processes lack a means to quantitatively and objectively evaluate applicants' skills, requiring companies to spend a great deal of time and effort to find the right talent. Applicants also have limited opportunities to have their skills properly evaluated, making it difficult for them to effectively conduct their job search. There is a need for a method to solve these problems and improve the efficiency and accuracy of skill evaluation.

[1347] 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.

[1348] In this invention, the server includes: a means for inputting basic information about an applicant; a means including a generation AI for generating a test based on the basic information; a means for providing the generated test to the applicant and having the applicant take the test; a means including a generation AI for receiving, evaluating, and scoring the test results; a means for evaluating the skills of cybersecurity professionals; and a means for reporting the scored results. This allows companies to accurately evaluate applicants' cybersecurity skills and efficiently hire the right talent. Furthermore, applicants can apply for more suitable jobs by having their skills objectively evaluated.

[1349] "Applicant" refers to an individual participating in the recruitment process and applying for a particular position.

[1350] "Basic information" refers to data entered by the applicant, such as personal information, desired job type, and skill set.

[1351] "Generative AI" refers to a program that uses machine learning and artificial intelligence techniques to automatically generate and evaluate tests appropriate for applicants.

[1352] "Test" refers to tasks or questions automatically generated by generative AI to assess applicants' skills and abilities.

[1353] A "cybersecurity professional" is an individual with expertise in areas such as network security, application security, and threat analysis.

[1354] "Skill assessment" refers to the process in which generative AI evaluates and scores the abilities of applicants based on the results of tests they take.

[1355] A "score report" refers to a report in which the generative AI evaluates the test results and summarizes the quantitative scores and analysis results.

[1356] In order to implement the present invention, the following system is constructed and operated: The system mainly includes processes related to a server, a terminal, and a user.

[1357] 1. Enter basic information about the applicant

[1358] The server first provides an interface for collecting basic information about applicants. The user enters their information (name, email address, desired job type, skill set, etc.) through this interface and sends it to the server. The terminal then uses a web form or application to collect this information.

[1359] 2. Automatic test generation

[1360] The server automatically generates appropriate tests using a generative AI based on the collected basic information of applicants. This generative AI uses machine learning models (e.g., OpenAI's GPT-based models) to create questions (e.g., network security assessment, application security analysis, threat analysis, etc.) that are optimal for each applicant.

[1361] 3. Conducting the test

[1362] The server provides the generated test to the applicant. The user takes the test using a device at hand (smartphone, tablet, laptop, etc.). The test content consists of tasks and questions corresponding to each specialized field.

[1363] 4. Evaluation of deliverables

[1364] The server receives the test results sent by the user and evaluates them using a generative AI, which scores the applicant's work and creates a detailed score report based on evaluation criteria (e.g., accuracy, efficiency, problem-solving ability).

[1365] 5. Score report delivery

[1366] The server notifies companies and applicants of the generated score report via email, dashboard, etc.

[1367] Hardware and software used

[1368] The hardware used is cloud servers such as AWS EC2 and Google Cloud. Generative AI models include OpenAI's GPT model and Hugging Face's Transformer. Databases such as MongoDB and PostgreSQL are used to manage applicant information. The entire system is built using Flask (Python) as a web framework.

[1369] Specific examples

[1370] For example, applicant "Yamada Taro" applies for a position as a network security engineer. The applicant enters basic information through a web form and selects "Network Security Engineer" as the desired job type. Based on this information, the server's generation AI automatically generates network penetration testing and threat analysis tasks and provides them to the applicant. When the applicant performs these tasks and submits them to the server, the generation AI evaluates the deliverables and creates a score report. The score report is then notified to the applicant and the hiring manager.

[1371] Prompt Sentence Examples

[1372] Applicant information: The applicant's name is "Yamada Taro", the desired job is "Network Security Engineer", and the skills are "Network Penetration Testing", "Firewall Configuration", and "Incident Response".

[1373] Test Generation Requirements: Please generate specialized tests suitable for the network security field. For example, "Security vulnerability detection" and "Network traffic analysis."

[1374] Evaluation criteria: accuracy, efficiency, and resolving ability.

[1375] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1376] Step 1:

[1377] The server provides an interface for entering basic information about applicants. Users enter their information (name, email address, desired job type, skill set, etc.) and send this information to the server via their terminal. The server receives the input data and stores it in a database. Input: Basic information about applicants. Output: Saved basic information about applicants.

[1378] Step 2:

[1379] The server calls a generative AI module based on the stored basic information and automatically generates an appropriate test. This generative AI uses, for example, OpenAI's GPT model. The generative AI generates specific test questions (e.g., network penetration tests, threat analysis tasks, etc.) based on the input skill set and desired job type. Input: Basic information about the applicant. Output: Generated test.

[1380] Step 3:

[1381] The terminal provides the generated test to the applicant. The user accesses the test using a terminal (smartphone, tablet, laptop, etc.) and answers the questions. After completing the answers, the user sends the results (code, answer document, etc.) to the server via the terminal. Input: Generated test. Output: Applicant's answers.

[1382] Step 4:

[1383] The server receives the test results sent by the user and calls the generation AI module again for evaluation. The generation AI evaluates the applicant's submission and generates a score. It also takes into account accuracy, efficiency, problem-solving ability, etc. as evaluation criteria. Input: Applicant's answers. Output: Generated score.

[1384] Step 5:

[1385] The server creates a score report based on the completed score. This score report also includes detailed evaluation results by the generation AI. The server notifies the company and applicant of this report by email. Input: Generated score. Output: Generated score report.

[1386] 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.

[1387] System Program and Description

[1388] To implement this invention, a system is constructed and operated according to the following procedure.

[1389] 1. Applicant information input interface

[1390] A user accesses the system and enters basic information and desired job type.

[1391] The terminal collects the information entered by the applicant and transmits it to the server.

[1392] The device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions at that time (e.g., tension, relief, etc.).

[1393] The server stores the emotion data along with basic information.

[1394] 2. Test Generation

[1395] Based on the applicant's information sent to the server, the generative AI generates tests that are appropriate for the applicant. For example, it automatically generates coding tests for engineers and design tasks for designers.

[1396] The emotion engine references the user's past emotional data and adjusts the test content to make the user feel more relaxed.

[1397] 3. Conducting the test

[1398] The terminal displays the generated test to the applicant, who then follows the instructions to take the test.

[1399] During the test, the device uses an emotion engine to analyze the user's facial expressions and voice and recognize their emotions in real time, and this data is sent to the server.

[1400] Users take the test and enter their answers. For example, engineers write Python code, and designers submit UI / UX designs.

[1401] 4. Evaluation of deliverables

[1402] The server receives the test answers and begins evaluation by the generative AI.

[1403] Generative AI scores engineers on the accuracy and efficiency of their code, and designers on the aesthetics and usability of their design.

[1404] The server uses an emotion engine to evaluate the emotional data collected during the test. For example, if a tester has a high rate of correct answers when under high stress, their adaptability will be evaluated.

[1405] 5. Score generation and notification

[1406] Based on the generated scores, the server creates a score report that quantifies the applicant's skill assessment.

[1407] The server includes the results of the analysis of emotional data (e.g., performance under stress, performance under normal circumstances) in the score report.

[1408] The server notifies the company and applicant of the score report.

[1409] Specific examples

[1410] 1. Enter user information

[1411] User: Applicant "A" selects "Software Engineer" as the job he or she would like to change jobs to.

[1412] Device: Collects information about "A" through a web form and sends it to the server. The device also uses a camera and microphone to analyze "A"'s facial expressions and voice to obtain emotional data.

[1413] 2. Test Generation

[1414] Server: Based on information about applicant "A," the generation AI automatically generates "algorithm problems" and "database operation" tests, and the emotion engine adjusts the content.

[1415] 3. Conducting the test

[1416] Device: The generated coding test is displayed to applicant "A" and emotional data is collected in real time while the test is being conducted.

[1417] User: Applicant "A" created a binary search algorithm in Python and completed the test. The device also sent emotion data to the server.

[1418] 4. Evaluation of deliverables

[1419] Server: The generative AI evaluates the code of applicant "A" and generates scores for efficiency, accuracy, and refactoring. In addition, it reflects emotional data in the evaluation.

[1420] 5. Score generation and notification

[1421] Server: Create a score report based on the evaluation of applicant "A" and include emotional data (e.g., performance under stress).

[1422] The server sends the score report to the company and applicant "A" via email.

[1423] System benefits

[1424] This system allows companies to evaluate applicants' emotional adaptability as well as their technical skills, making it possible to make a comprehensive judgment that takes into account not only technical ability but also mental aptitude. Applicants also receive feedback based on their emotional state, which helps them to better understand themselves.

[1425] The processing flow will be explained below.

[1426] Step 1:

[1427] A user accesses the system and logs in.

[1428] Action: A user accesses the system's login screen using a web browser or smartphone app and enters their user ID and password.

[1429] Step 2:

[1430] The device sends the login information to the server.

[1431] How it works: The device encrypts the login information entered by the user and sends it to the server over a secure connection.

[1432] Step 3:

[1433] The server verifies the login information and performs authentication.

[1434] Operation: The server checks the received login information against the database and returns a successful authentication result to the terminal.

[1435] Step 4:

[1436] The user enters basic information and desired job type.

[1437] How it works: After successfully logging in, a form appears in which the user enters their name, email address, desired job title, years of experience, skill set, etc.

[1438] Step 5:

[1439] The terminal sends the entered basic information to the server.

[1440] How it works: The information entered by the user is converted into JSON format and sent to the server. It also uses the camera and microphone to analyze the user's facial expressions and voice in real time to obtain emotional data.

[1441] Step 6:

[1442] The server stores the received basic information and emotion data in a database.

[1443] Operation: The server stores the received basic information and emotion data in a database and begins selecting an appropriate AI model.

[1444] Step 7:

[1445] The server generates appropriate tests based on the generated AI.

[1446] How it works: Based on the user's desired job type and skill set, the generative AI automatically generates coding tests, design assignments, etc. The emotion engine references past emotional data and adjusts the content to make it more relaxing for the user.

[1447] Step 8:

[1448] The server sends the generated test to the user's device.

[1449] Operation: The generated test content is converted into JSON format and sent to the user's device.

[1450] Step 9:

[1451] The terminal displays the received test to the user.

[1452] Operation: The received test content is displayed in the user interface, allowing the user to perform the test.

[1453] Step 10:

[1454] The user takes the generated test and enters the answers.

[1455] How it works: The user performs coding or design tasks in response to the presented problem and enters their answers in the corresponding form.

[1456] Step 11:

[1457] The device sends the user's test results and emotional data to the server.

[1458] How it works: The answers to the tests completed by the user are converted into JSON format and sent to the server along with real-time emotional data.

[1459] Step 12:

[1460] The server inputs the received test results into the generation AI and begins evaluation.

[1461] How it works: The server passes the received answers and emotion data to the generation AI, which then begins the process of evaluating and scoring the answers.

[1462] Step 13:

[1463] The server receives the evaluation results from the generation AI and generates a score.

[1464] How it works: The evaluation data returned by the generative AI is aggregated and an overall score (e.g., 80 points for algorithm, 90 points for design) is calculated. The impact on performance is also evaluated, taking into account emotional data.

[1465] Step 14:

[1466] The server creates a score report and notifies the company and the user.

[1467] Operation: A score report is generated based on the scoring results, and includes the results of emotional data analysis (e.g., performance under stress, performance under normal circumstances). A notification email is sent to the company and user with a link to download the score report.

[1468] Step 15:

[1469] Users and businesses review the score report.

[1470] What it does: Users and businesses click on the link in the notification email they receive to view or download their score report.

[1471] This process allows companies to assess applicants' technical skills and emotional readiness in advance, enabling them to efficiently hire the right talent. Applicants also receive feedback based on their skills and emotional state, allowing them to better target workplaces.

[1472] Example 2

[1473] 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."

[1474] In the modern recruitment process, it is necessary to evaluate not only the technical skills of applicants but also their mental and emotional adaptability. However, conventional systems focus on technical evaluation and lack the ability to properly evaluate and reflect the emotional state of applicants, making it difficult to provide a comprehensive evaluation.

[1475] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting basic information of the applicant, a means for analyzing the applicant's emotions and saving the data, a means including a generation AI for generating a test based on the basic information, and a means for adjusting the test content based on the emotion data. This makes it possible to comprehensively evaluate the applicant's technical skills and emotional adaptability.

[1476] "Applicant" refers to a person participating in the recruitment examination or selection process.

[1477] "Basic information" refers to basic attribute information about the applicant, such as name, contact information, work history, and desired job type.

[1478] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to automatically perform specific tasks.

[1479] "Test" refers to tasks or questions designed to assess an applicant's technical skills and aptitude.

[1480] "Emotional data" refers to information about the emotional state of applicants analyzed from their facial expressions, voice, etc.

[1481] "Adjustment measures" refer to mechanisms for changing and optimizing the content and format of tests based on emotional data and other information.

[1482] "Evaluation means" refers to the system for analyzing the test results and performing scoring and evaluation.

[1483] "Real time" refers to near-instant processing and response.

[1484] A "server" refers to a computer system that provides data processing and storage functions over a network.

[1485] "Scoring" refers to the process of quantifying an applicant's performance based on test results.

[1486] The system is designed to assess applicants' technical skills and emotional readiness and is implemented using the following hardware and software components:

[1487] Hardware Components

[1488] 1. Server - A computer system that provides data processing and storage capabilities (e.g., AWS EC2, Google Cloud Compute Engine).

[1489] 2. Terminal - The device (e.g., PC, tablet, smartphone) on which the applicant enters information and takes the test.

[1490] 3. Camera and Microphone - Input devices to capture the applicant's facial expressions and voice (e.g. webcam, built-in microphone).

[1491] Software Components

[1492] 1. Web Browser - The interface through which applicants enter their information (e.g., Google Chrome, Mozilla Firefox).

[1493] 2. Emotion analysis software - Software to analyze applicants' facial expressions and voice (e.g., OpenCV, Google Cloud Speech).

[1494] 3. Database - A storage system (e.g., MySQL, PostgreSQL) for storing basic information and sentiment data about applicants.

[1495] 4. Generative AI models - Artificial intelligence models for automatically generating and evaluating tests (e.g., OpenAI GPT-3).

[1496] 5. Machine learning models - Models for analyzing and classifying applicant sentiment data (e.g., scikit-learn, TensorFlow).

[1497] 6. Code analysis engine - Software used to evaluate the code submitted for testing (e.g., Pylint, SonarQube).

[1498] How it works

[1499] Enter applicant information

[1500] A user accesses an application form using a web browser and enters basic information (such as name, contact details, work history, desired job type, etc.). The device collects the applicant information and sends it to the server. At the same time, it uses a camera and microphone to analyze the applicant's facial expressions and voice and generate emotional data. This emotional data is also sent to the server.

[1501] Information storage and analysis

[1502] The server stores the received applicant's basic information and emotional data in a database. The server then refers to past emotional data, analyzes the newly acquired emotional data, and classifies it into an appropriate category (e.g., nervous, relieved).

[1503] Test Generation and Tuning

[1504] The server inputs prompts into the generative AI model based on the applicant's basic information to generate an appropriate test. The server then adjusts the test content based on the applicant's emotional data, aiming to create a relaxed environment for the applicant. For example, it may simplify the question format or set a flexible time limit to reduce tension.

[1505] Example prompt for a generative AI model:

[1506] "Generate coding tests for software engineers."

[1507] Testing and Sentiment Analysis

[1508] The device displays the generated test to the applicant, and the user follows the instructions to take the test. While the test is being taken, the device analyzes facial expressions and voice using a camera and microphone, capturing emotional data in real time and sending it to the server. This allows the collection of the applicant's performance data to be as accurate as possible.

[1509] Test Evaluation and Scoring

[1510] The server receives the test answers sent from the device and begins evaluating them using a generative AI model, which evaluates technical aspects such as code accuracy and efficiency, as well as its adaptability based on emotional data.

[1511] Score report generation and notification

[1512] The server creates a score report based on the test results and the analysis of the emotional data, and notifies the company and applicant. The report includes not only the technical score but also the applicant's emotional state (e.g., performance under stress, performance under normal circumstances).

[1513] This allows companies to comprehensively assess candidates' technical skills and emotional readiness, leading to better hiring decisions, while providing candidates with opportunities to deepen their self-understanding and grow through feedback.

[1514] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1515] Step 1: Enter and submit your application information

[1516] A user accesses the application form using a web browser and enters basic information (name, contact details, work history, desired job type, etc.). The entered information is recorded on the device.

[1517] The device sends the applicant's basic information to the server via API. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice. This generates emotional data, which is also sent to the server.

[1518] Input: Name, contact information, work history, desired job type, facial expression data, voice data

[1519] Output: Basic information of applicants, emotional data

[1520] Step 2: Store and analyze applicant information

[1521] The server stores the applicant's basic information and emotional data received from the terminal in a database.

[1522] The server analyzes the emotion data using a machine learning model (e.g., scikit-learn, TensorFlow) and classifies it into categories such as "tension" or "relief." This classification result is also stored in the database.

[1523] Input: Basic information of applicant, emotional data

[1524] Output: Stored applicant basic information, categorized emotion data

[1525] Step 3: Generate and refine tests

[1526] The server inputs a prompt into the generative AI model based on the applicant's basic information to generate an appropriate test. For example, the prompt might be, "Please generate a coding test for software engineers."

[1527] The server adjusts the generated test, referencing the emotional data and adjusting the content and difficulty of the test to make the applicant feel more relaxed.

[1528] Input: basic information of applicant, emotion data, prompt sentence

[1529] Output: Generated tests, adjusted test content

[1530] Step 4: View and perform tests

[1531] The terminal displays the generated test to the applicant.

[1532] The user follows the test questions and enters their answers, for example, creating a binary search algorithm in Python.

[1533] Input: Adjusted test content

[1534] Output: Applicant's test answers

[1535] Step 5: Sentiment analysis and sending during the test

[1536] During the test, the device uses a camera and microphone to analyze the applicant's facial expressions and voice in real time, capturing emotional data, which is then sent to a server.

[1537] Input: Real-time facial expression data, voice data

[1538] Output: Real-time emotion data

[1539] Step 6: Submit and evaluate your test answers

[1540] The terminal transmits the applicant's response to the server.

[1541] The server evaluates applicants' test answers using a generative AI model and uses a code analysis engine (e.g., Pylint, SonarQube) to check the code for accuracy, efficiency, and readability.

[1542] Input: Applicant's test answers, emotion data

[1543] Output: Evaluation results, technical score, emotional adaptability score

[1544] Step 7: Generate and notify your score report

[1545] The server generates a comprehensive score report based on the test evaluation results and emotional data, which includes a technical score and an emotional adaptability score.

[1546] The server generates a report and notifies the company and applicants by email.

[1547] Input: Assessment results, technical score, emotional adaptability score

[1548] Output: Generated score report, notification email

[1549] (Application example 2)

[1550] 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."

[1551] Conventional applicant evaluation systems only evaluate applicants' technical skills and knowledge, and do not consider psychological factors such as their emotional state or stress level. As a result, they are unable to properly evaluate the applicant's overall suitability, which can lead to flaws in personnel selection. Furthermore, while there is a need to understand the emotional state and stress levels of workers in factories and other places in real time to improve work efficiency and safety, current systems are unable to meet this need.

[1552] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting basic information about the applicant, a means including a generation AI for generating a test based on the basic information, and a means for providing the generated test to the applicant, who then takes the test. This enables a comprehensive aptitude evaluation that takes into account not only the applicant's technical skills but also their emotional state. The server also includes a means including an emotion engine for acquiring and analyzing the worker's emotional data, a means for integrating and analyzing the emotion data and test result data, and a means for adjusting tasks based on emotions and performance. This makes it possible to grasp the worker's emotional state in real time and appropriately adjust tasks accordingly, which is expected to improve work efficiency and safety.

[1553] "Applicant" refers to an individual who uses the System to be evaluated.

[1554] "Basic Information" refers to the personal data and biographical information that applicants enter into the system.

[1555] "Generative AI" refers to artificial intelligence that automatically generates appropriate tests based on basic information about applicants and evaluates them.

[1556] "Tests" refer to tasks or questions created by generative AI to assess applicants' skills and knowledge.

[1557] An "emotion engine" is a system that analyzes the facial expressions and voices of applicants and workers and recognizes their emotional state in real time.

[1558] "Test Result Data" refers to performance data from tests taken by applicants.

[1559] "Emotional data" refers to analytical results data that show the emotional state of applicants and workers.

[1560] A "task" refers to a specific task or assignment assigned to an applicant or worker.

[1561] "Task adjustment" refers to changing the content and difficulty of tasks assigned to workers based on emotional data and test result data.

[1562] To implement this invention, it is necessary to build and operate a system using the following procedure: First, a user (applicant or worker) inputs basic information through a terminal. The terminal then sends this basic information to a server, which then uses a generation AI to automatically generate a test appropriate for the applicant.

[1563] Next, the terminal displays the generated test to the applicant, who then takes the test. During the test, the terminal uses an emotion engine to analyze the facial expressions and voice of the applicant or worker, obtaining emotional data in real time. This data is then sent to the server.

[1564] The server receives the test results and emotion data, and uses generative AI to comprehensively evaluate these data. Based on the evaluation results, the server assigns a score and adjusts tasks based on emotion and performance.

[1565] The hardware used includes smart helmets and badges with built-in cameras and microphones, and a server for data management and analysis. The software used includes EmotionRecognizer (emotion engine), TaskScheduler (task coordination engine), and factory_database (database management system).

[1566] As a concrete example, let's say worker "A" is working in a foundry at a factory. The smart helmet captures "A's" facial expressions and voice in real time, and the emotion engine analyzes them. If the analysis identifies that "A" is in a high-stress state, the task adjustment engine automatically shifts "A" to an easier task. Furthermore, relaxing music begins to play from the smart helmet.

[1567] Examples of prompts to input to a generative AI model include:

[1568] "Adjust the tasks of the factory workers based on the following data: Worker ID: 3, Emotional Data: High Stress Level, Performance Data: Casting Efficiency 75%. If the worker is feeling stressed, assign them tasks that will help them relax."

[1569] As described above, this system makes it possible to comprehensively evaluate an applicant's technical skills and emotional state, and by assigning appropriate tasks based on the worker's emotional state, it is expected to improve work efficiency and safety.

[1570] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1571] Step 1:

[1572] The user inputs basic information and desired job type through the terminal. The terminal acquires the applicant's basic information (name, career history, desired job type, etc.) and sends it to the server.

[1573] Input: User (applicant) basic information

[1574] Output: Send basic information data to the server

[1575] Specific operation: Information entered on the terminal is sent to the server in real time and stored in a database on the server.

[1576] Step 2:

[1577] The device uses a camera and microphone to capture the applicant's facial expressions and voice, which are then analyzed by an emotion engine. The resulting emotion data is then sent to a server.

[1578] Input: Applicant's video and audio data

[1579] Output: Sending emotion data to the server

[1580] Specific operation: Data taken from the device's camera and microphone is analyzed by EmotionRecognizer and sent to the server as emotion data.

[1581] Step 3:

[1582] The server uses generative AI based on basic information and emotional data to generate a test that is appropriate for the applicant.

[1583] Input: Basic information data, emotion data

[1584] Output: Generated test data

[1585] Specific operation: The generation AI on the server generates appropriate tests based on basic information and emotional data, and saves the test content in a database.

[1586] Step 4:

[1587] The device presents the generated test to the applicant, who then takes the test. Test performance data and real-time emotional data are sent to the server.

[1588] Input: Generated test data

[1589] Output: Test performance data, real-time sentiment data

[1590] How it works: Applicants take the test and the results are sent from their devices to a server. Facial expressions and voices are also analyzed during the test, and emotional data is sent to the server in real time.

[1591] Step 5:

[1592] The server receives test performance and sentiment data and uses generative AI to evaluate and score it.

[1593] Input: Test performance data, emotion data

[1594] Output: Evaluation results, scoring data

[1595] Specific operation: The generation AI on the server analyzes the test results and emotional data, and performs an overall evaluation and scoring. These evaluation results are stored in a database.

[1596] Step 6:

[1597] The server executes a means for adjusting tasks suitable for the worker based on the scoring results and emotion data.

[1598] Input: Evaluation results, scoring data

[1599] Output: Reconciled task data

[1600] Specific operation: The TaskScheduler on the server calculates the optimal task based on the evaluation results and emotion data, and saves the adjusted task in a database.

[1601] Step 7:

[1602] The adjusted tasks are notified to the workers, who receive instructions for the new tasks via their terminals and start the appropriate tasks.

[1603] Input: Adjusted task data

[1604] Output: Task notification to workers

[1605] Specific operation: The terminal notifies the worker of the content of the new task, and the worker receives instructions for carrying out the task.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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).

[1613] 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.

[1614] 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."

[1615] 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.

[1616] 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).

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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, in order to avoid confusion and to 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.

[1626] 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.

[1627] The following is further disclosed regarding the above embodiment.

[1628] (Claim 1)

[1629] A means for entering basic information about applicants;

[1630] a generating AI that generates a test based on the basic information;

[1631] means for providing the generated test to an applicant and for the applicant to administer the test;

[1632] A generating AI means for receiving, evaluating, and scoring the results of the test;

[1633] means for reporting the scored results;

[1634] A system including:

[1635] (Claim 2)

[1636] 2. The system according to claim 1, wherein the test is a program coding task, a design creation task, or a writing task.

[1637] (Claim 3)

[1638] The system of claim 1, wherein the generation AI automatically generates and evaluates tests.

[1639] "Example 1"

[1640] (Claim 1)

[1641] A means for entering basic information about applicants;

[1642] a generating AI that generates a test based on the basic information;

[1643] means for providing the generated test to an applicant and for the applicant to administer the test;

[1644] A generating AI means for receiving, evaluating, and scoring the results of the test;

[1645] A means for generating and notifying a score report based on the evaluation results;

[1646] A system including:

[1647] (Claim 2)

[1648] 2. The system of claim 1, wherein the test is a program coding task, a design creation task, or a writing task.

[1649] (Claim 3)

[1650] The system of claim 1, wherein the generation AI automatically generates and evaluates tests and utilizes asynchronous API calls.

[1651] "Application Example 1"

[1652] (Claim 1)

[1653] A means for entering basic information about applicants;

[1654] a generating AI that generates a test based on the basic information;

[1655] means for providing the generated test to an applicant and for the applicant to administer the test;

[1656] A generating AI means for receiving, evaluating, and scoring the results of the test;

[1657] A means of assessing the skills of cybersecurity professionals;

[1658] means for reporting the scored results;

[1659] A system including:

[1660] (Claim 2)

[1661] 10. The system of claim 1, wherein the test is a network security assessment, an application security analysis, or a threat analysis exercise.

[1662] (Claim 3)

[1663] The system of claim 1, wherein the generation AI automatically generates and evaluates tests.

[1664] "Example 2: Combining Emotion Engines"

[1665] (Claim 1)

[1666] A means for entering basic information about applicants;

[1667] a generating AI that generates a test based on the basic information;

[1668] means for providing the generated test to an applicant and for the applicant to administer the test;

[1669] A generating AI means for receiving, evaluating, and scoring the results of the test;

[1670] means for reporting the scored results;

[1671] A means of analyzing applicants' emotions and storing that data;

[1672] means for adjusting test content based on the emotion data;

[1673] A means for acquiring emotion data in real time during the test and transmitting it to a server;

[1674] a means for providing feedback to a scoring result based on the emotion data;

[1675] A system including:

[1676] (Claim 2)

[1677] 2. The system of claim 1, wherein the test is a program coding task, a design creation task, or a writing task, and adjustments are made based on emotional data.

[1678] (Claim 3)

[1679] The system of claim 1, wherein the generative AI automatically generates and evaluates tests and includes feedback based on emotional data.

[1680] "Application example 2 when combining emotion engines"

[1681] (Claim 1)

[1682] A means for entering basic information about applicants;

[1683] a generating AI that generates a test based on the basic information;

[1684] means for providing the generated test to an applicant and for the applicant to administer the test;

[1685] A generating AI means for receiving, evaluating, and scoring the results of the test;

[1686] means for reporting the scored results;

[1687] means including an emotion engine for acquiring and analyzing emotion data of a worker;

[1688] means for integrating and analyzing the emotion data and test result data;

[1689] a means of adjusting tasks based on emotion and performance;

[1690] A system including:

[1691] (Claim 2)

[1692] 2. The system according to claim 1, wherein the test is a program coding task, a design creation task, a writing task, or a simulation of factory work.

[1693] (Claim 3)

[1694] The system of claim 1, wherein the generative AI automatically generates and evaluates tests and adjusts tasks based on emotional data. [Explanation of symbols]

[1695] 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 entering basic information about applicants; a generating AI that generates a test based on the basic information; means for providing the generated test to an applicant and for the applicant to administer the test; A means including a generating AI that receives, evaluates, and scores the results of the test; means for reporting the scored results; A system including:

2. 2. The system according to claim 1, wherein the test is a program coding task, a design creation task, or a writing task.

3. The system of claim 1, wherein the generation AI automatically generates and evaluates tests.

Images