System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving and storing information of a candidate in a database; means for transmitting a link to start an interview to the candidate; means for receiving and storing response data from the candidate; means for analyzing the response data of the candidate; means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate; and means for providing a management screen and allowing a personnel manager to confirm an evaluation 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] Traditional hiring processes rely on the subjective judgment of interviewers, which often results in a lack of fairness in candidate evaluation. Furthermore, dealing with a large number of applicants requires a lot of time and resources, resulting in a lack of efficiency. Furthermore, it is difficult to accurately grasp a candidate's thinking style and personality during the interview process, making it difficult to determine appropriate placements and roles. There is a need for a method to solve these issues and achieve a fairer and more efficient hiring process. [Means for solving the problem]

[0005] The present invention is a system that includes a means for receiving and storing candidate information in a database, a means for sending candidates a link to start an interview, a means for receiving and storing response data from candidates, a means for analyzing the candidate response data, a means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, and a means for providing a management screen that allows human resources personnel to check the evaluation results.Furthermore, by using a generative model as a means for analyzing candidate response data, and by providing a means for determining who will advance to the next interview from the management screen and considering appropriate assignments, a fair and efficient hiring process is realized.

[0006] "Candidate Information" refers to personal and job-related information provided by a candidate when registering, such as name, contact details, and desired job type.

[0007] A "database" is a data storage area installed within a system for efficiently storing and managing candidate information and response data.

[0008] An "interview start link" is a specific URL that allows a candidate to start the interview, and is sent to the candidate via email or other means.

[0009] "Response data" refers to data including responses entered by candidates during an interview.

[0010] A "generative model" is an artificial intelligence model used to analyze candidate response data and generate evaluation results.

[0011] An "evaluation report" is a document that provides a detailed summary of the candidate's thinking style and personality based on the results of analysis by the generative model.

[0012] The "administration screen" is the interface that allows human resources personnel to access the system, check the candidate evaluation results, and decide on the next steps.

[0013] The "evaluation results" are data that indicate the candidate's thinking style and personality, as a result of the generative model analyzing the response data.

[0014] "Candidates who advance to the next interview" are those who are deemed appropriate to proceed to the next interview based on the evaluation results.

[0015] An "appropriate assignment" is a job or department that best matches the candidate's skills and characteristics, based on the candidate's evaluation results. [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] The present invention provides a system for fairly and objectively evaluating a candidate's thinking style and personality to streamline the recruitment process. The system of the present invention includes multiple modules, and specific embodiments thereof will be described below.

[0038] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and saves the response data entered by candidates during the interview and uses a generative model to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen and includes a mechanism that allows human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[0039] The specific flow of the system operation will be explained below.

[0040] User Registration

[0041] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0042] Interview begins

[0043] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[0044] Interview Dialogue

[0045] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[0046] Data analysis and evaluation

[0047] The server calls a generative model (such as ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the user's answer content and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0048] Notification and confirmation of evaluation results

[0049] The server generates a detailed evaluation report for each user based on the analysis results.The server then sends an email to the user notifying them that the evaluation report is complete and provides them with an access link to the evaluation report.The user can view the evaluation report by clicking the link in the email.

[0050] Admin screen and decision making

[0051] The company's human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. Based on the evaluation results, the company's human resources personnel selects who will advance to the next interview and considers appropriate assignments. Finally, the server sends emails to the target users informing them of the next interview based on the selection results.

[0052] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process. For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates the candidate as "strong leadership orientation." This evaluation is then used to determine appropriate assignments and roles.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[0056] Step 2:

[0057] The terminal receives the information entered by the user and clicks the "Submit" button.

[0058] Step 3:

[0059] The server stores the received user information in a database.

[0060] Step 4:

[0061] The server generates a registration completion notification and sends it to the terminal.

[0062] Step 5:

[0063] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[0064] Step 6:

[0065] The user clicks on the start interview link in the confirmation email.

[0066] Step 7:

[0067] The server creates a new interview session and records the session ID in the database.

[0068] Step 8:

[0069] The server displays the interview flow page on the terminal.

[0070] Step 9:

[0071] The device displays an initial question (e.g., "What are your career goals?") to the user.

[0072] Step 10:

[0073] The user enters an answer to the question and clicks the "Submit" button.

[0074] Step 11:

[0075] The terminal transmits the user's answer to the server.

[0076] Step 12:

[0077] The server stores the received response data in a database.

[0078] Step 13:

[0079] The server invokes the generative model to analyze the response data stored in the database.

[0080] Step 14:

[0081] The generative model analyzes the content of the user's answers and generates evaluation results.

[0082] Step 15:

[0083] The server stores the evaluation results received from the generative model in a database.

[0084] Step 16:

[0085] The server generates an evaluation report for each user based on the analysis results.

[0086] Step 17:

[0087] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[0088] Step 18:

[0089] Users can click on the link in the email to view the evaluation report.

[0090] Step 19:

[0091] The company's human resources personnel log in to the management screen and check the evaluation results of all users.

[0092] Step 20:

[0093] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[0094] Step 21:

[0095] The company's human resources staff will consider appropriate placement.

[0096] Step 22:

[0097] The server will then send an email to the target user informing them of the next interview.

[0098] Example 1

[0099] 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."

[0100] In the traditional recruitment process, it was difficult to fairly and objectively evaluate candidates' thinking styles and personalities, posing challenges to the fairness and efficiency of the evaluation. It was also difficult to effectively utilize the evaluation data and quickly determine the appropriate placement. This made the entire recruitment process time-consuming and costly.

[0101] 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.

[0102] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for using a generative AI model as a means for analyzing candidate response data, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for providing a management screen so that a person in charge can check the evaluation results, and means for selecting candidates to advance to the next interview and considering appropriate departments. This makes it possible to fairly and objectively evaluate candidates' thinking styles and personalities, effectively utilize the evaluation data to quickly determine appropriate assignments, and improve the efficiency of the entire recruitment process.

[0103] "Candidate Information" means basic data about individuals being evaluated during the recruitment process, such as name, contact details, and desired job type.

[0104] A "database" is a system that stores information in an organized manner and makes it quickly and efficiently accessible when needed.

[0105] "Interview Start Link" means the URL or hyperlink that allows a Candidate to begin an online interview.

[0106] "Response Data" means the text responses entered by the Candidate during the interview.

[0107] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze input data and generate evaluations and outputs based on that content.

[0108] An "evaluation report" is a report summarizing the results of an analysis conducted by a generative AI model based on candidate response data.

[0109] The "administration screen" is an interface that allows system administrators and corporate human resources personnel to operate the system and check and manipulate evaluation results and candidate information.

[0110] "Person in Charge" refers to the HR department staff member who manages the recruitment process within a company and is responsible for evaluating candidates and conducting interviews.

[0111] A "suitable department" is a department or position that is deemed the best fit based on the candidate's skills and assessment results.

[0112] The present invention is a system for fairly and objectively evaluating candidates' thinking styles and personalities to streamline the hiring process. The system of the present invention includes multiple modules, and specific embodiments are described below. The system has a series of processes for collecting information from candidates and evaluating them through interviews. The system has the function of storing candidate information in a database and sending a link to start the interview. Furthermore, the system collects and stores response data entered by candidates during interviews and uses a generative model to analyze that data. An evaluation report is generated based on the analysis results and notified to the candidate. The system also provides a management screen and includes a mechanism for personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate department.

[0113] The specific operation flow of this system is as follows: The system sends the user's registration information from the terminal to the server, and the server saves the received registration information in a database. After saving, the server generates a link to start the interview and sends it to the user via the terminal.

[0114] When a user clicks the start interview link, the server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and starts the interview. The terminal displays the interview questions to the user, and the user enters their answers. The answer data is sent from the terminal to the server, which stores it in the database. This process is repeated until answers to all questions are collected.

[0115] After all the answer data has been collected, the server calls a generative model (e.g., ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0116] The server then generates a detailed evaluation report for each user based on the analysis results. An email is sent to the user informing them that the evaluation report is complete, along with a link to access the report. The user can view the evaluation report by clicking the link in the email.

[0117] Through the management screen, company personnel can log in to the system and check the evaluation results of all users. Based on the evaluation results, personnel will consider and decide who will advance to the next interview and the appropriate department. Finally, the server will send emails to the selected users informing them of the next interview based on the selection results.

[0118] For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates it as "strong leadership orientation." This evaluation is used to determine the appropriate department and role.

[0119] Examples of prompt statements

[0120] Analyze the candidate's answers as follows:

[0121] Answer: "As a technical leader, I want to bring the team together."

[0122] Analysis example: "Strong leadership orientation"

[0123] The system of the present invention analyzes candidate responses in conjunction with a generative AI model to provide a fair and objective evaluation, resulting in an efficient and reliable hiring process.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1: User Registration

[0126] 1. The user accesses the system's website and enters information into the new registration form.

[0127] Input: Basic information such as name, contact information, desired job type, etc.

[0128] Output: Data set of input information

[0129] 2. The terminal sends the information entered by the user to the server.

[0130] Input: User registration information dataset

[0131] Output: Information data sent to the server

[0132] 3. The server stores the received information in a database.

[0133] Input: Information data sent from the terminal

[0134] Output: Candidate information stored in the database

[0135] 4. The server generates a registration completion notification and sends it to the terminal.

[0136] Input: Information stored in a database

[0137] Output: Registration completion notification data

[0138] 5. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0139] Input: Registration completion notification data, interview link

[0140] Output: Registration success message displayed, confirmation email sent

[0141] Step 2: Start the interview

[0142] 1. The user clicks on the start interview link in the confirmation email.

[0143] Input: Confirmation email, interview link

[0144] Output: Request for interview page

[0145] 2. The server creates a new interview session and records the session ID in the database.

[0146] Input: User's interview page request

[0147] Output: Generated session ID, session information recorded in database

[0148] 3. The server displays the interview flow page on the terminal and starts the interview.

[0149] Input: Session information

[0150] Output: Interview flow page displayed on terminal

[0151] Step 3: Interview

[0152] 1. The terminal displays the first question of the interview to the user.

[0153] Input: Interview question data

[0154] Output: Question printed to terminal

[0155] 2. The user enters the answer to the question and clicks the "Submit" button.

[0156] Input: Answer to question

[0157] Output: Sending response data from the device to the server

[0158] 3. The server stores the received response in a database.

[0159] Input: User response data

[0160] Output: Response data stored in a database

[0161] 4. This process is repeated until all questions have been answered.

[0162] Input: Next question data

[0163] Output: Repeated question and answer data collection

[0164] Step 4: Data analysis and evaluation

[0165] 1. The server invokes a generative model (e.g., ChatGPT) to analyze the response data stored in the database.

[0166] Input: Saved response data

[0167] Output: Data input to the generative model

[0168] 2. The generative AI model analyzes the user's answers and generates an evaluation result.

[0169] Input: Answer data

[0170] Output: Parsed evaluation results

[0171] 3. The evaluation results are returned to the server, which stores them in a database.

[0172] Input: Evaluation result data

[0173] Output: Evaluation results stored in a database

[0174] Step 5: Notification and confirmation of evaluation results

[0175] 1. The server generates a detailed evaluation report for each user based on the analysis results.

[0176] Input: Analysis result data

[0177] Output: Generated assessment report

[0178] 2. The server then sends the user an email informing them that the evaluation report is complete and providing a link to access the report.

[0179] Input: Evaluation report, notification email data

[0180] Output: Notification email sent

[0181] 3. Users can click on the link in the email to view the evaluation report.

[0182] Input: Link in notification email

[0183] Output: Access to the assessment report

[0184] Step 6: Dashboard and decision making

[0185] 1. The company's human resources personnel logs in to the administration screen and checks the evaluation results of all users through the interface provided by the system.

[0186] Input: Login information, system interface

[0187] Output: Displayed evaluation results

[0188] 2. Based on the evaluation results, the company's human resources staff will consider and decide who will advance to the next interview and the appropriate department.

[0189] Input: Evaluation result data

[0190] Output: Determined interview candidates, appropriate department

[0191] 3. Finally, the server will send an email to the selected user informing them of the next interview based on the selection results.

[0192] Input: Selection result data

[0193] Output: Interview notification email sent

[0194] (Application example 1)

[0195] 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."

[0196] Conventional candidate evaluation systems only evaluate candidates' thinking styles and personalities, making it difficult to evaluate employee performance in brick-and-mortar stores and provide feedback in real time. There is also a need for a system that can analyze employees' customer service attitudes and behaviors in detail and provide appropriate feedback in real time. The purpose of this project is to solve this issue and improve employee performance and customer satisfaction.

[0197] 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.

[0198] In this invention, the server includes a means for receiving candidate information and storing it in a database, a means for sending the candidate a link to start an interview, a means for receiving and storing response data from the candidate, and a means for evaluating the performance of store employees and providing feedback in real time, thereby enabling not only candidate evaluation but also performance evaluation and real-time feedback of employees in a physical store.

[0199] "Means of receiving candidate information and storing it in a database" refers to the process of collecting data such as personal information and resumes provided by job seekers and storing it in a database.

[0200] "Method of sending candidate an interview start link" is the process of sending job seekers an email or message containing a URL to start an interview.

[0201] "Means for receiving and storing candidate response data" refers to the process of collecting responses and information entered by job seekers during interviews and storing them in a database.

[0202] "Means for analyzing candidate response data" refers to the process of analyzing collected job seeker response data using algorithms or generative models.

[0203] "Means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate" refers to the process of creating an evaluation report summarizing the analysis results and notifying the job seeker of the results.

[0204] "Providing an administration screen and a means for human resources personnel to check the evaluation results" refers to a process that allows human resources personnel to check the evaluation results of job applicants using an administration screen within the system.

[0205] "Means for evaluating store associate performance and providing real-time feedback" refers to a process that monitors the work performance of employees working in physical stores, evaluates their performance using a generative model, and immediately provides areas for improvement and advice.

[0206] The present invention is a system for evaluating the performance of store clerks in a physical store and providing feedback in real time. This system is configured using hardware and software such as smart glasses, a camera, a microphone, and a generative model (e.g., GPT-3.5-turbo). Specific embodiments for implementing the present invention are described below.

[0207] System Overview

[0208] 1. Collection and storage of candidate information

[0209] The server first receives the individual information of the store clerk and stores it in a database. This information includes the individual's name, contact information, work history, etc. The user (in this case, the store clerk) accesses the system's website and enters the necessary data into the "New Registration" form. The entered data is sent from the terminal to the server, which then stores it in the database.

[0210] 2. Send the interview start link

[0211] After the salesperson completes the registration, the server sends the user a confirmation email containing a link to start the interview. The user clicks on the link in the email to start the interview (or start the job).

[0212] 3. Store Employee Performance Evaluation

[0213] When a user wears the smart glasses and performs actual work, the smart glasses' camera and microphone record the actions and voices of the store clerk in real time, and the device sends this collected data to a server for analysis.

[0214] 4. Data Analysis

[0215] The server analyzes the collected data using a generative model. For example, the data includes information on how the salesperson responded to the customer and how they explained the product. The analysis results are returned to the server, and an evaluation report is generated as needed.

[0216] 5. Providing real-time feedback

[0217] Based on the analysis, the server evaluates the employee's performance and provides real-time feedback, including specific advice and areas for improvement, which is displayed on the smart glasses' display.

[0218] 6. Providing an administration screen

[0219] The server provides a management screen that allows human resources personnel to check the evaluation results of store employees. This management screen allows for the centralized management of each store employee's performance evaluation, feedback, work history, etc.

[0220] Hardware and Software Used

[0221] Smart glasses: Collect video and audio from the store clerk's perspective.

[0222] Camera: The camera built into the smart glasses records the footage.

[0223] Microphone: A microphone built into the smart glasses records audio.

[0224] Generative models: Analyze data using generative AI models such as GPT-3.5-turbo.

[0225] Database: Stores employee information, collected data, and evaluation results.

[0226] Specific examples

[0227] Specifically, we consider a scenario in which a salesperson explains the features of a new product to a customer. The following is an example of a prompt sentence to use when analyzing data collected in this scenario.

[0228] Example prompt: "Based on the following observation, please evaluate the salesperson's customer service attitude: 'The salesperson explained the features of the new product in detail to the customer.'"

[0229] A generative model analyzes the prompt and provides real-time evaluation feedback, helping to improve the store clerk's performance.

[0230] In this way, the present invention can provide efficient performance evaluation and immediate feedback to employees in brick-and-mortar stores.

[0231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0232] Step 1:

[0233] The server receives data such as personal information and work history provided by the user and stores it in a database. When the user uses a terminal to enter the required data into the "New Registration" form and clicks the submit button, the input data is sent from the terminal to the server. The server receives this and stores it in a database. The input data includes the individual's name, contact information, work history, etc.

[0234] Step 2:

[0235] After the user's registration is complete, the server will send the user a confirmation email containing a link to begin the interview (job). Once the registration process is complete, the server will automatically send a confirmation email with a link to the user's email address. This link is a means of guiding the user to begin the interview or job.

[0236] Step 3:

[0237] The user clicks on the link in the confirmation email to begin the interview (task). When the link is clicked, the server creates a new session and records the session ID in the database. The server then displays the interview page on the terminal, ready for the user to begin the interview.

[0238] Step 4:

[0239] The user wears smart glasses and records their actions and voices in real time while working. The smart glasses' camera and microphone collect video and audio data, which are then transmitted to a server by the device.

[0240] Step 5:

[0241] The server sends the collected video and audio data to the generative model for analysis. The generative model analyzes the input data and evaluates the salesperson's performance. Specifically, the server sends a prompt to the generative model, such as "Please rate the salesperson's behavior while explaining the features of a new product," and receives the evaluation data in return.

[0242] Step 6:

[0243] The server creates a detailed evaluation report based on the evaluation data returned from the generative model and provides the results to the user as feedback in real time.The evaluation and areas for improvement are displayed on the smart glasses display, and appropriate advice is provided to the user in real time.

[0244] Step 7:

[0245] The server stores the analysis results and feedback in a database. This allows human resources personnel to check the evaluation results of each user at any time from the management screen. The management screen allows for centralized management of each employee's performance evaluation, feedback, work history, etc.

[0246] The above steps make it possible to evaluate a user's performance in real time and provide appropriate feedback.

[0247] 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.

[0248] The present invention is a system that combines a system that fairly and objectively evaluates a candidate's thinking style and personality to streamline the hiring process with an emotion engine that recognizes the candidate's emotions. This system includes multiple modules, and specific embodiments thereof will be described below.

[0249] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and stores the response data entered by candidates during the interview, and uses a generative model and emotion engine to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen, allowing human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[0250] The specific flow of the system operation will be explained below.

[0251] User Registration

[0252] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0253] Interview begins

[0254] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[0255] Interview Dialogue

[0256] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[0257] Data analysis and evaluation

[0258] The server calls the generative model and emotion engine to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The emotion engine recognizes the user's emotion based on the answer data and adds the emotion data to the evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0259] Notification and confirmation of evaluation results

[0260] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the evaluation report. The user can view the evaluation report by clicking the link in the email.

[0261] Admin screen and decision making

[0262] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[0263] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process and providing a detailed evaluation that takes the candidate's emotions into account. For example, if a candidate answers, "I want to lead a team as a technical leader," and the emotion expressed at that time is recognized as "confidence," the analysis results of the generative model and emotion engine will evaluate the candidate as "strongly leadership-oriented and confident." This evaluation is then used to determine appropriate assignments and roles.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[0267] Step 2:

[0268] The terminal receives the information entered by the user and clicks the "Submit" button.

[0269] Step 3:

[0270] The server stores the received user information in a database.

[0271] Step 4:

[0272] The server generates a registration completion notification and sends it to the terminal.

[0273] Step 5:

[0274] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[0275] Step 6:

[0276] The user clicks on the start interview link in the confirmation email.

[0277] Step 7:

[0278] The server creates a new interview session and records the session ID in the database.

[0279] Step 8:

[0280] The server displays the interview flow page on the terminal.

[0281] Step 9:

[0282] The device displays an initial question (e.g., "What are your career goals?") to the user.

[0283] Step 10:

[0284] The user enters an answer to the question and clicks the "Submit" button.

[0285] Step 11:

[0286] The terminal transmits the user's answer to the server.

[0287] Step 12:

[0288] The server stores the received response data in a database.

[0289] Step 13:

[0290] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[0291] Step 14:

[0292] The generative model analyzes the content of the user's answers and generates an evaluation result. At the same time, the emotion engine recognizes the user's emotions based on the answer data and generates emotion data.

[0293] Step 15:

[0294] The server stores the evaluation results received from the generative model and the emotion data received from the emotion engine in a database.

[0295] Step 16:

[0296] The server generates an evaluation report for each user based on the analysis results, which includes not only evaluation data on thinking style and personality, but also emotional data.

[0297] Step 17:

[0298] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[0299] Step 18:

[0300] Users can click on the link in the email to view the evaluation report.

[0301] Step 19:

[0302] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system, which also includes emotional data.

[0303] Step 20:

[0304] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[0305] Step 21:

[0306] The company's human resources staff will consider appropriate placement.

[0307] Step 22:

[0308] The server will then send an email to the target user informing them of the next interview.

[0309] Example 2

[0310] 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."

[0311] In the traditional hiring process, it is difficult to fairly and objectively evaluate candidates' thinking styles and personalities, resulting in low hiring efficiency. Furthermore, because the evaluation does not take emotions into account, it is difficult to determine appropriate assignments and roles. Furthermore, tasks such as analyzing data and notifying evaluation results are complex, placing a heavy burden on human resources personnel.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0313] In this invention, the server includes: means for receiving candidate information and storing it in a database; means for sending a link to start an interview to the candidate; means for receiving and storing response data from the candidate; means for calling a generative AI model and an emotion recognition engine to analyze the candidate's response data; means for generating an evaluation report based on the generated evaluation data and recognized emotion data and notifying the candidate; and means for providing a management screen and viewing a detailed report including the evaluation results and emotion data. This enables fair and objective evaluation of candidates and realizes an efficient hiring process. Furthermore, detailed evaluations that take emotion data into account make it easier to determine appropriate assignments and roles.

[0314] "Candidate Information" refers to personal information such as the name, contact details, and desired job title of individuals involved in the recruitment process.

[0315] "Database" refers to an information management system in which candidate information, response data, evaluation data, etc. are systematically stored.

[0316] "Interview Start Link" means the web link that enables a Candidate to begin an interview.

[0317] "Response Data" refers to the information provided by a Candidate in response to each question during an interview.

[0318] "Generative AI model" refers to the artificial intelligence model used to analyze and evaluate candidate response data.

[0319] An "emotion recognition engine" refers to software that analyzes and recognizes emotions from candidate response data.

[0320] "Assessment Report" means a detailed report containing assessment data and perceived emotional data regarding a Candidate's thinking style and personality.

[0321] "Management screen" refers to the interface that human resources personnel use to view and manage evaluation results and detailed reports.

[0322] A "human resources professional" is someone whose role is to evaluate candidates and determine appropriate placements during a company's recruitment process.

[0323] A "detailed report" refers to a report that includes specific information about each candidate based on the assessment results and perceived emotional data.

[0324] User Registration

[0325] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. The server stores the received data in a database. Once the data is saved, the server generates a registration completion notice and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0326] Interview begins

[0327] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[0328] Interview Dialogue

[0329] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user, for example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected.

[0330] Example: A user answers, "As a technical lead, I want to manage a team."

[0331] Data analysis and evaluation

[0332] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database.

[0333] Example: The user's answers are evaluated as "Strong in leadership orientation and confident."

[0334] Notification and confirmation of evaluation results

[0335] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. The user can view the evaluation report by clicking the link in the email.

[0336] Admin screen and decision making

[0337] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[0338] Hardware and software used

[0339] The system utilizes the following hardware and software:

[0340] Server: Manages the database, generates interview sessions, analyzes data, and generates evaluation reports.

[0341] Database: Stores candidate information, response data, and evaluation data.

[0342] Terminal: Enters data from the user, displays questions, and transmits the response data.

[0343] Generative AI model: Analyzes response data and generates evaluation results.

[0344] Emotion recognition engine: Recognizes emotions based on response data.

[0345] Prompt Sentence Examples

[0346] Prompt: "If users say they want to lead a team as a technical leader, rate them as leadership-oriented and confident."

[0347] As a result, this system can evaluate candidates fairly and objectively, enabling an efficient recruitment process. It also makes it possible to determine appropriate assignments and roles based on detailed evaluations that take emotional data into account.

[0348] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0349] Step 1: User Registration

[0350] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. Specifically, the device sends the form data in JSON format. The server receives it and saves it in a database. Once saved, the server generates a registration completion notification and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0351] Input: Data entered by the user into the "Sign Up" form

[0352] Output: Registration completion notification, confirmation email

[0353] Step 2: Start the interview

[0354] The user clicks the start interview link in the confirmation email. The server detects this access and creates a new interview session. It records the session ID in the database and displays the interview flow page on the terminal. Specifically, the server returns the URL of the flow page along with the session ID.

[0355] Input: User clicks a link

[0356] Output: View Interview Flow Page

[0357] Step 3: Interview

[0358] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user. For example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected. Specifically, the terminal displays an answer input field and a submit button after each question.

[0359] Input: User's answer

[0360] Output: Response data stored in a database

[0361] Step 4: Data analysis and evaluation

[0362] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database. Specifically, the server converts the response data into prompt sentences and inputs them into each engine.

[0363] Input: Response data stored in the database

[0364] Output: Parsed rating and sentiment data

[0365] Step 5: Notification and confirmation of evaluation results

[0366] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. Specifically, the server generates and sends an email containing the report URL.

[0367] Input: Parsed rating data and emotion data

[0368] Output: Evaluation report, notification email

[0369] Step 6: Dashboard and decision making

[0370] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Based on the selection results, the server sends emails to the relevant users informing them of the next interview. Specifically, the server generates and sends emails containing interview details to the selected candidates.

[0371] Input: Evaluation result

[0372] Output: Notification email with interview details

[0373] (Application example 2)

[0374] 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."

[0375] In the conventional recruitment process, it is difficult to fairly and objectively evaluate a candidate's thinking style and personality, and there is no way to properly grasp their emotional state.In addition, there is no system that automatically proposes optimal operation schedules and work allocations based on recruitment evaluation data, making it difficult to achieve efficient personnel allocation and operation management.

[0376] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0377] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for analyzing candidate response data by utilizing a generative model capable of identifying emotional states, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for optimizing operation schedules and work allocation based on the evaluation report, and means for providing a management screen so that human resources personnel can check the evaluation results. This enables fair and objective evaluation that takes into account not only the candidate's thinking style and personality but also their emotional state, and further makes it possible to automatically optimize operation schedules and work allocation based on that data.

[0378] "Candidate" means an individual who applies for a particular job or role in the recruitment process.

[0379] "Start Interview Link" means the link that the Candidate clicks to begin the interview.

[0380] "Response Data" refers to the response information entered by a candidate during an interview.

[0381] "Generative modeling" refers to an AI model used to analyze a candidate's thinking style, personality, and emotional state.

[0382] "Ability to identify emotional states" refers to the skill of recognizing and assessing the emotions displayed by candidates during interviews.

[0383] An "evaluation report" is a report summarizing the results of an analysis based on the candidate's thinking style, personality, and emotional state.

[0384] "Operation schedule" refers to a plan for operations by autonomous vehicles and drivers.

[0385] "Work allocation" refers to the process of determining how specific duties or tasks will be divided.

[0386] The "management screen" is an interface that allows human resources personnel to check the candidate evaluation results and make decisions.

[0387] This invention provides a system that evaluates candidates' thinking styles, personalities, and emotional states, and optimizes operation schedules and work allocation based on the results. This system is mainly composed of three main components: a server, a terminal, and a user.

[0388] server

[0389] The server receives candidate information and stores it in a database. Specifically, the server sends the candidate a link to start the interview and receives response data from the candidate during the interview. The response data is stored in a database, and then a generative model capable of identifying emotional states is used to analyze the candidate's thinking style, personality, and emotional state. An evaluation report is generated based on the analysis results and notified to the candidate. This evaluation report includes not only the candidate's analysis data but also a summary including their emotional state.

[0390] Terminal

[0391] The terminal is a device used by candidates to participate in interviews. The user first clicks on the link to start the interview through the terminal and accesses the interview form. The answer data entered by the candidate is sent to the server via the terminal. The terminal also has a means to receive notification of the evaluation results and display them to the candidate.

[0392] User

[0393] Users refer to candidates who participate in the interview process and human resources personnel who review the candidate evaluation results. Candidates click the interview start link, answer questions, and submit their responses. Human resources personnel review the evaluation results through the administration screen, and based on the results, determine who will advance to the next interview and consider appropriate assignments.

[0394] Hardware and software used

[0395] Hardware: devices such as smartphones

[0396] Software: Backend API built with Python, Flask (API server), MongoDB (database), generative AI models such as GPT-3

[0397] Specific examples

[0398] For example, if a professional driver responds, "I will strive to drive safely and aim to be the best driver," and the emotion he or she feels at the time is recognized as "concentration and a sense of security," the system will suggest the "optimal driving schedule and vehicle allocation" based on the analysis results. In this way, a system that takes into account the driver's thinking style and emotional state will enable safe and efficient driving management.

[0399] Prompt Sentence Examples

[0400] Please answer the following questions:

[0401] 1. What are your career goals?

[0402] 2. What do you feel while driving?

[0403] Sample Answer 1: I will drive safely and aim to be the best driver.

[0404] Sample answer 2: Concentration, sense of security

[0405] In this way, the present invention realizes a multifaceted evaluation of candidates and optimization of operation management based on the evaluation.

[0406] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0407] Step 1:

[0408] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form.

[0409] Input: Candidate information such as name, contact details, and desired job position.

[0410] Operation: The information is sent from the device to the server, which receives it and stores it in a database. After storing it, the server generates a registration completion notice and sends it to the device.

[0411] Output: Registration successful message.

[0412] Step 2:

[0413] The server will send the user a confirmation email notifying them of successful registration and including a link to start the interview.

[0414] Input: Candidate information stored in the database.

[0415] What it does: The server generates a link to the interview flow and sends it embedded in a confirmation email.

[0416] Output: A confirmation email with a link to start the interview.

[0417] Step 3:

[0418] The user clicks the start interview link, creating a new interview session.

[0419] Input: User clicks a link.

[0420] Action: The server records the session ID in the database and displays the interview flow page on the terminal.

[0421] Output: Interview flow page.

[0422] Step 4:

[0423] The user enters answers to the questions displayed on the interview screen.

[0424] Input: Each question and its answer.

[0425] How it works: The user enters an answer and clicks the "Submit" button. The device sends the answer data to the server, which receives it and stores it in a database. This process is repeated for all questions.

[0426] Output: All response data stored in a database.

[0427] Step 5:

[0428] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[0429] Input: Response data.

[0430] How it works: The server uses a generative model and an emotion engine to analyze the response data and generate evaluation results. Data processing involves evaluation and emotion recognition based on the response content.

[0431] Output: Analysis results (evaluation data).

[0432] Step 6:

[0433] The server generates an evaluation report based on the analysis results and notifies the user.

[0434] Input: Analysis results.

[0435] Actions: The server generates an assessment report and sends the user an email informing them that it is complete and providing a link to access the report.

[0436] Output: Assessment report and notification email.

[0437] Step 7:

[0438] The user checks the evaluation report.

[0439] Input: Click on the link in the notification email.

[0440] How it works: The user clicks on the link to view the assessment report, and the server serves a page displaying the assessment results.

[0441] Output: View the assessment report.

[0442] Step 8:

[0443] The HR staff logs in to the administration screen and checks the evaluation results of all users.

[0444] Input: Access to the admin panel.

[0445] How it works: The server provides an administration interface and displays candidate evaluation data.

[0446] Output: Evaluation results for each candidate.

[0447] Step 9:

[0448] Based on the evaluation results, human resources personnel will decide who will advance to the next interview and consider appropriate assignments.

[0449] Input: Evaluation result.

[0450] How it works: HR personnel make decisions based on evaluation data.

[0451] Output: List of candidates who will advance to the next interview, and determination of appropriate placement.

[0452] Step 10:

[0453] Based on the selection results, the server will send an email to the target user informing them of the next interview.

[0454] Input: List of candidates selected for next interview, assignment information.

[0455] Action: The server generates a notification email and sends it to the affected user.

[0456] Output: Interview notification email.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] [Second embodiment]

[0461] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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).

[0467] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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."

[0473] The present invention provides a system for fairly and objectively evaluating a candidate's thinking style and personality to streamline the recruitment process. The system of the present invention includes multiple modules, and specific embodiments thereof will be described below.

[0474] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and saves the response data entered by candidates during the interview and uses a generative model to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen and includes a mechanism that allows human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[0475] The specific flow of the system operation will be explained below.

[0476] User Registration

[0477] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0478] Interview begins

[0479] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[0480] Interview Dialogue

[0481] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[0482] Data analysis and evaluation

[0483] The server calls a generative model (such as ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the user's answer content and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0484] Notification and confirmation of evaluation results

[0485] The server generates a detailed evaluation report for each user based on the analysis results.The server then sends an email to the user notifying them that the evaluation report is complete and provides them with an access link to the evaluation report.The user can view the evaluation report by clicking the link in the email.

[0486] Admin screen and decision making

[0487] The company's human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. Based on the evaluation results, the company's human resources personnel selects who will advance to the next interview and considers appropriate assignments. Finally, the server sends emails to the target users informing them of the next interview based on the selection results.

[0488] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process. For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates the candidate as "strong leadership orientation." This evaluation is then used to determine appropriate assignments and roles.

[0489] The processing flow will be explained below.

[0490] Step 1:

[0491] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[0492] Step 2:

[0493] The terminal receives the information entered by the user and clicks the "Submit" button.

[0494] Step 3:

[0495] The server stores the received user information in a database.

[0496] Step 4:

[0497] The server generates a registration completion notification and sends it to the terminal.

[0498] Step 5:

[0499] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[0500] Step 6:

[0501] The user clicks on the start interview link in the confirmation email.

[0502] Step 7:

[0503] The server creates a new interview session and records the session ID in the database.

[0504] Step 8:

[0505] The server displays the interview flow page on the terminal.

[0506] Step 9:

[0507] The device displays an initial question (e.g., "What are your career goals?") to the user.

[0508] Step 10:

[0509] The user enters an answer to the question and clicks the "Submit" button.

[0510] Step 11:

[0511] The terminal transmits the user's answer to the server.

[0512] Step 12:

[0513] The server stores the received response data in a database.

[0514] Step 13:

[0515] The server invokes the generative model to analyze the response data stored in the database.

[0516] Step 14:

[0517] The generative model analyzes the content of the user's answers and generates evaluation results.

[0518] Step 15:

[0519] The server stores the evaluation results received from the generative model in a database.

[0520] Step 16:

[0521] The server generates an evaluation report for each user based on the analysis results.

[0522] Step 17:

[0523] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[0524] Step 18:

[0525] Users can click on the link in the email to view the evaluation report.

[0526] Step 19:

[0527] The company's human resources personnel log in to the management screen and check the evaluation results of all users.

[0528] Step 20:

[0529] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[0530] Step 21:

[0531] The company's human resources staff will consider appropriate placement.

[0532] Step 22:

[0533] The server will then send an email to the target user informing them of the next interview.

[0534] Example 1

[0535] 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."

[0536] In the traditional recruitment process, it was difficult to fairly and objectively evaluate candidates' thinking styles and personalities, posing challenges to the fairness and efficiency of the evaluation. It was also difficult to effectively utilize the evaluation data and quickly determine the appropriate placement. This made the entire recruitment process time-consuming and costly.

[0537] 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.

[0538] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for using a generative AI model as a means for analyzing candidate response data, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for providing a management screen so that a person in charge can check the evaluation results, and means for selecting candidates to advance to the next interview and considering appropriate departments. This makes it possible to fairly and objectively evaluate candidates' thinking styles and personalities, effectively utilize the evaluation data to quickly determine appropriate assignments, and improve the efficiency of the entire recruitment process.

[0539] "Candidate Information" means basic data about individuals being evaluated during the recruitment process, such as name, contact details, and desired job type.

[0540] A "database" is a system that stores information in an organized manner and makes it quickly and efficiently accessible when needed.

[0541] "Interview Start Link" means the URL or hyperlink that allows a Candidate to begin an online interview.

[0542] "Response Data" means the text responses entered by the Candidate during the interview.

[0543] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze input data and generate evaluations and outputs based on that content.

[0544] An "evaluation report" is a report summarizing the results of an analysis conducted by a generative AI model based on candidate response data.

[0545] The "administration screen" is an interface that allows system administrators and corporate human resources personnel to operate the system and check and manipulate evaluation results and candidate information.

[0546] "Person in Charge" refers to the HR department staff member who manages the recruitment process within a company and is responsible for evaluating candidates and conducting interviews.

[0547] A "suitable department" is a department or position that is deemed the best fit based on the candidate's skills and assessment results.

[0548] The present invention is a system for fairly and objectively evaluating candidates' thinking styles and personalities to streamline the hiring process. The system of the present invention includes multiple modules, and specific embodiments are described below. The system has a series of processes for collecting information from candidates and evaluating them through interviews. The system has the function of storing candidate information in a database and sending a link to start the interview. Furthermore, the system collects and stores response data entered by candidates during interviews and uses a generative model to analyze that data. An evaluation report is generated based on the analysis results and notified to the candidate. The system also provides a management screen and includes a mechanism for personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate department.

[0549] The specific operation flow of this system is as follows: The system sends the user's registration information from the terminal to the server, and the server saves the received registration information in a database. After saving, the server generates a link to start the interview and sends it to the user via the terminal.

[0550] When a user clicks the start interview link, the server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and starts the interview. The terminal displays the interview questions to the user, and the user enters their answers. The answer data is sent from the terminal to the server, which stores it in the database. This process is repeated until answers to all questions are collected.

[0551] After all the answer data has been collected, the server calls a generative model (e.g., ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0552] The server then generates a detailed evaluation report for each user based on the analysis results. An email is sent to the user informing them that the evaluation report is complete, along with a link to access the report. The user can view the evaluation report by clicking the link in the email.

[0553] Through the management screen, company personnel can log in to the system and check the evaluation results of all users. Based on the evaluation results, personnel will consider and decide who will advance to the next interview and the appropriate department. Finally, the server will send emails to the selected users informing them of the next interview based on the selection results.

[0554] For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates it as "strong leadership orientation." This evaluation is used to determine the appropriate department and role.

[0555] Examples of prompt statements

[0556] Analyze the candidate's answers as follows:

[0557] Answer: "As a technical leader, I want to bring the team together."

[0558] Analysis example: "Strong leadership orientation"

[0559] The system of the present invention analyzes candidate responses in conjunction with a generative AI model to provide a fair and objective evaluation, resulting in an efficient and reliable hiring process.

[0560] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0561] Step 1: User Registration

[0562] 1. The user accesses the system's website and enters information into the new registration form.

[0563] Input: Basic information such as name, contact information, desired job type, etc.

[0564] Output: Data set of input information

[0565] 2. The terminal sends the information entered by the user to the server.

[0566] Input: User registration information dataset

[0567] Output: Information data sent to the server

[0568] 3. The server stores the received information in a database.

[0569] Input: Information data sent from the terminal

[0570] Output: Candidate information stored in the database

[0571] 4. The server generates a registration completion notification and sends it to the terminal.

[0572] Input: Information stored in a database

[0573] Output: Registration completion notification data

[0574] 5. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0575] Input: Registration completion notification data, interview link

[0576] Output: Registration success message displayed, confirmation email sent

[0577] Step 2: Start the interview

[0578] 1. The user clicks on the start interview link in the confirmation email.

[0579] Input: Confirmation email, interview link

[0580] Output: Request for interview page

[0581] 2. The server creates a new interview session and records the session ID in the database.

[0582] Input: User's interview page request

[0583] Output: Generated session ID, session information recorded in database

[0584] 3. The server displays the interview flow page on the terminal and starts the interview.

[0585] Input: Session information

[0586] Output: Interview flow page displayed on terminal

[0587] Step 3: Interview

[0588] 1. The terminal displays the first question of the interview to the user.

[0589] Input: Interview question data

[0590] Output: Question printed to terminal

[0591] 2. The user enters the answer to the question and clicks the "Submit" button.

[0592] Input: Answer to question

[0593] Output: Sending response data from the device to the server

[0594] 3. The server stores the received response in a database.

[0595] Input: User response data

[0596] Output: Response data stored in a database

[0597] 4. This process is repeated until all questions have been answered.

[0598] Input: Next question data

[0599] Output: Repeated question and answer data collection

[0600] Step 4: Data analysis and evaluation

[0601] 1. The server invokes a generative model (e.g., ChatGPT) to analyze the response data stored in the database.

[0602] Input: Saved response data

[0603] Output: Data input to the generative model

[0604] 2. The generative AI model analyzes the user's answers and generates an evaluation result.

[0605] Input: Answer data

[0606] Output: Parsed evaluation results

[0607] 3. The evaluation results are returned to the server, which stores them in a database.

[0608] Input: Evaluation result data

[0609] Output: Evaluation results stored in a database

[0610] Step 5: Notification and confirmation of evaluation results

[0611] 1. The server generates a detailed evaluation report for each user based on the analysis results.

[0612] Input: Analysis result data

[0613] Output: Generated assessment report

[0614] 2. The server then sends the user an email informing them that the evaluation report is complete and providing a link to access the report.

[0615] Input: Evaluation report, notification email data

[0616] Output: Notification email sent

[0617] 3. Users can click on the link in the email to view the evaluation report.

[0618] Input: Link in notification email

[0619] Output: Access to the assessment report

[0620] Step 6: Dashboard and decision making

[0621] 1. The company's human resources personnel logs in to the administration screen and checks the evaluation results of all users through the interface provided by the system.

[0622] Input: Login information, system interface

[0623] Output: Displayed evaluation results

[0624] 2. Based on the evaluation results, the company's human resources staff will consider and decide who will advance to the next interview and the appropriate department.

[0625] Input: Evaluation result data

[0626] Output: Determined interview candidates, appropriate department

[0627] 3. Finally, the server will send an email to the selected user informing them of the next interview based on the selection results.

[0628] Input: Selection result data

[0629] Output: Interview notification email sent

[0630] (Application example 1)

[0631] 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."

[0632] Conventional candidate evaluation systems only evaluate candidates' thinking styles and personalities, making it difficult to evaluate employee performance in brick-and-mortar stores and provide feedback in real time. There is also a need for a system that can analyze employees' customer service attitudes and behaviors in detail and provide appropriate feedback in real time. The purpose of this project is to solve this issue and improve employee performance and customer satisfaction.

[0633] 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.

[0634] In this invention, the server includes a means for receiving candidate information and storing it in a database, a means for sending the candidate a link to start an interview, a means for receiving and storing response data from the candidate, and a means for evaluating the performance of store employees and providing feedback in real time, thereby enabling not only candidate evaluation but also performance evaluation and real-time feedback of employees in a physical store.

[0635] "Means of receiving candidate information and storing it in a database" refers to the process of collecting data such as personal information and resumes provided by job seekers and storing it in a database.

[0636] "Method of sending candidate an interview start link" is the process of sending job seekers an email or message containing a URL to start an interview.

[0637] "Means for receiving and storing candidate response data" refers to the process of collecting responses and information entered by job seekers during interviews and storing them in a database.

[0638] "Means for analyzing candidate response data" refers to the process of analyzing collected job seeker response data using algorithms or generative models.

[0639] "Means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate" refers to the process of creating an evaluation report summarizing the analysis results and notifying the job seeker of the results.

[0640] "Providing an administration screen and a means for human resources personnel to check the evaluation results" refers to a process that allows human resources personnel to check the evaluation results of job applicants using an administration screen within the system.

[0641] "Means for evaluating store associate performance and providing real-time feedback" refers to a process that monitors the work performance of employees working in physical stores, evaluates their performance using a generative model, and immediately provides areas for improvement and advice.

[0642] The present invention is a system for evaluating the performance of store clerks in a physical store and providing feedback in real time. This system is configured using hardware and software such as smart glasses, a camera, a microphone, and a generative model (e.g., GPT-3.5-turbo). Specific embodiments for implementing the present invention are described below.

[0643] System Overview

[0644] 1. Collection and storage of candidate information

[0645] The server first receives the individual information of the store clerk and stores it in a database. This information includes the individual's name, contact information, work history, etc. The user (in this case, the store clerk) accesses the system's website and enters the necessary data into the "New Registration" form. The entered data is sent from the terminal to the server, which then stores it in the database.

[0646] 2. Send the interview start link

[0647] After the salesperson completes the registration, the server sends the user a confirmation email containing a link to start the interview. The user clicks on the link in the email to start the interview (or start the job).

[0648] 3. Store Employee Performance Evaluation

[0649] When a user wears the smart glasses and performs actual work, the smart glasses' camera and microphone record the actions and voices of the store clerk in real time, and the device sends this collected data to a server for analysis.

[0650] 4. Data Analysis

[0651] The server analyzes the collected data using a generative model. For example, the data includes information on how the salesperson responded to the customer and how they explained the product. The analysis results are returned to the server, and an evaluation report is generated as needed.

[0652] 5. Providing real-time feedback

[0653] Based on the analysis, the server evaluates the employee's performance and provides real-time feedback, including specific advice and areas for improvement, which is displayed on the smart glasses' display.

[0654] 6. Providing an administration screen

[0655] The server provides a management screen that allows human resources personnel to check the evaluation results of store employees. This management screen allows for the centralized management of each store employee's performance evaluation, feedback, work history, etc.

[0656] Hardware and Software Used

[0657] Smart glasses: Collect video and audio from the store clerk's perspective.

[0658] Camera: The camera built into the smart glasses records the footage.

[0659] Microphone: A microphone built into the smart glasses records audio.

[0660] Generative models: Analyze data using generative AI models such as GPT-3.5-turbo.

[0661] Database: Stores employee information, collected data, and evaluation results.

[0662] Specific examples

[0663] Specifically, we consider a scenario in which a salesperson explains the features of a new product to a customer. The following is an example of a prompt sentence to use when analyzing data collected in this scenario.

[0664] Example prompt: "Based on the following observation, please evaluate the salesperson's customer service attitude: 'The salesperson explained the features of the new product in detail to the customer.'"

[0665] A generative model analyzes the prompt and provides real-time evaluation feedback, helping to improve the store clerk's performance.

[0666] In this way, the present invention can provide efficient performance evaluation and immediate feedback to employees in brick-and-mortar stores.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] The server receives data such as personal information and work history provided by the user and stores it in a database. When the user uses a terminal to enter the required data into the "New Registration" form and clicks the submit button, the input data is sent from the terminal to the server. The server receives this and stores it in a database. The input data includes the individual's name, contact information, work history, etc.

[0670] Step 2:

[0671] After the user's registration is complete, the server will send the user a confirmation email containing a link to begin the interview (job). Once the registration process is complete, the server will automatically send a confirmation email with a link to the user's email address. This link is a means of guiding the user to begin the interview or job.

[0672] Step 3:

[0673] The user clicks on the link in the confirmation email to begin the interview (task). When the link is clicked, the server creates a new session and records the session ID in the database. The server then displays the interview page on the terminal, ready for the user to begin the interview.

[0674] Step 4:

[0675] The user wears smart glasses and records their actions and voices in real time while working. The smart glasses' camera and microphone collect video and audio data, which are then transmitted to a server by the device.

[0676] Step 5:

[0677] The server sends the collected video and audio data to the generative model for analysis. The generative model analyzes the input data and evaluates the salesperson's performance. Specifically, the server sends a prompt to the generative model, such as "Please rate the salesperson's behavior while explaining the features of a new product," and receives the evaluation data in return.

[0678] Step 6:

[0679] The server creates a detailed evaluation report based on the evaluation data returned from the generative model and provides the results to the user as feedback in real time.The evaluation and areas for improvement are displayed on the smart glasses display, and appropriate advice is provided to the user in real time.

[0680] Step 7:

[0681] The server stores the analysis results and feedback in a database. This allows human resources personnel to check the evaluation results of each user at any time from the management screen. The management screen allows for centralized management of each employee's performance evaluation, feedback, work history, etc.

[0682] The above steps make it possible to evaluate a user's performance in real time and provide appropriate feedback.

[0683] 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.

[0684] The present invention is a system that combines a system that fairly and objectively evaluates a candidate's thinking style and personality to streamline the hiring process with an emotion engine that recognizes the candidate's emotions. This system includes multiple modules, and specific embodiments thereof will be described below.

[0685] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and stores the response data entered by candidates during the interview, and uses a generative model and emotion engine to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen, allowing human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[0686] The specific flow of the system operation will be explained below.

[0687] User Registration

[0688] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0689] Interview begins

[0690] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[0691] Interview Dialogue

[0692] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[0693] Data analysis and evaluation

[0694] The server calls the generative model and emotion engine to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The emotion engine recognizes the user's emotion based on the answer data and adds the emotion data to the evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0695] Notification and confirmation of evaluation results

[0696] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the evaluation report. The user can view the evaluation report by clicking the link in the email.

[0697] Admin screen and decision making

[0698] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[0699] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process and providing a detailed evaluation that takes the candidate's emotions into account. For example, if a candidate answers, "I want to lead a team as a technical leader," and the emotion expressed at that time is recognized as "confidence," the analysis results of the generative model and emotion engine will evaluate the candidate as "strongly leadership-oriented and confident." This evaluation is then used to determine appropriate assignments and roles.

[0700] The processing flow will be explained below.

[0701] Step 1:

[0702] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[0703] Step 2:

[0704] The terminal receives the information entered by the user and clicks the "Submit" button.

[0705] Step 3:

[0706] The server stores the received user information in a database.

[0707] Step 4:

[0708] The server generates a registration completion notification and sends it to the terminal.

[0709] Step 5:

[0710] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[0711] Step 6:

[0712] The user clicks on the start interview link in the confirmation email.

[0713] Step 7:

[0714] The server creates a new interview session and records the session ID in the database.

[0715] Step 8:

[0716] The server displays the interview flow page on the terminal.

[0717] Step 9:

[0718] The device displays an initial question (e.g., "What are your career goals?") to the user.

[0719] Step 10:

[0720] The user enters an answer to the question and clicks the "Submit" button.

[0721] Step 11:

[0722] The terminal transmits the user's answer to the server.

[0723] Step 12:

[0724] The server stores the received response data in a database.

[0725] Step 13:

[0726] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[0727] Step 14:

[0728] The generative model analyzes the content of the user's answers and generates an evaluation result. At the same time, the emotion engine recognizes the user's emotions based on the answer data and generates emotion data.

[0729] Step 15:

[0730] The server stores the evaluation results received from the generative model and the emotion data received from the emotion engine in a database.

[0731] Step 16:

[0732] The server generates an evaluation report for each user based on the analysis results, which includes not only evaluation data on thinking style and personality, but also emotional data.

[0733] Step 17:

[0734] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[0735] Step 18:

[0736] Users can click on the link in the email to view the evaluation report.

[0737] Step 19:

[0738] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system, which also includes emotional data.

[0739] Step 20:

[0740] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[0741] Step 21:

[0742] The company's human resources staff will consider appropriate placement.

[0743] Step 22:

[0744] The server will then send an email to the target user informing them of the next interview.

[0745] Example 2

[0746] 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."

[0747] In the traditional hiring process, it is difficult to fairly and objectively evaluate candidates' thinking styles and personalities, resulting in low hiring efficiency. Furthermore, because the evaluation does not take emotions into account, it is difficult to determine appropriate assignments and roles. Furthermore, tasks such as analyzing data and notifying evaluation results are complex, placing a heavy burden on human resources personnel.

[0748] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0749] In this invention, the server includes: means for receiving candidate information and storing it in a database; means for sending a link to start an interview to the candidate; means for receiving and storing response data from the candidate; means for calling a generative AI model and an emotion recognition engine to analyze the candidate's response data; means for generating an evaluation report based on the generated evaluation data and recognized emotion data and notifying the candidate; and means for providing a management screen and viewing a detailed report including the evaluation results and emotion data. This enables fair and objective evaluation of candidates and realizes an efficient hiring process. Furthermore, detailed evaluations that take emotion data into account make it easier to determine appropriate assignments and roles.

[0750] "Candidate Information" refers to personal information such as the name, contact details, and desired job title of individuals involved in the recruitment process.

[0751] "Database" refers to an information management system in which candidate information, response data, evaluation data, etc. are systematically stored.

[0752] "Interview Start Link" means the web link that enables a Candidate to begin an interview.

[0753] "Response Data" refers to the information provided by a Candidate in response to each question during an interview.

[0754] "Generative AI model" refers to the artificial intelligence model used to analyze and evaluate candidate response data.

[0755] An "emotion recognition engine" refers to software that analyzes and recognizes emotions from candidate response data.

[0756] "Assessment Report" means a detailed report containing assessment data and perceived emotional data regarding a Candidate's thinking style and personality.

[0757] "Management screen" refers to the interface that human resources personnel use to view and manage evaluation results and detailed reports.

[0758] A "human resources professional" is someone whose role is to evaluate candidates and determine appropriate placements during a company's recruitment process.

[0759] A "detailed report" refers to a report that includes specific information about each candidate based on the assessment results and perceived emotional data.

[0760] User Registration

[0761] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. The server stores the received data in a database. Once the data is saved, the server generates a registration completion notice and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0762] Interview begins

[0763] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[0764] Interview Dialogue

[0765] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user, for example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected.

[0766] Example: A user answers, "As a technical lead, I want to manage a team."

[0767] Data analysis and evaluation

[0768] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database.

[0769] Example: The user's answers are evaluated as "Strong in leadership orientation and confident."

[0770] Notification and confirmation of evaluation results

[0771] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. The user can view the evaluation report by clicking the link in the email.

[0772] Admin screen and decision making

[0773] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[0774] Hardware and software used

[0775] The system utilizes the following hardware and software:

[0776] Server: Manages the database, generates interview sessions, analyzes data, and generates evaluation reports.

[0777] Database: Stores candidate information, response data, and evaluation data.

[0778] Terminal: Enters data from the user, displays questions, and transmits the response data.

[0779] Generative AI model: Analyzes response data and generates evaluation results.

[0780] Emotion recognition engine: Recognizes emotions based on response data.

[0781] Prompt Sentence Examples

[0782] Prompt: "If users say they want to lead a team as a technical leader, rate them as leadership-oriented and confident."

[0783] As a result, this system can evaluate candidates fairly and objectively, enabling an efficient recruitment process. It also makes it possible to determine appropriate assignments and roles based on detailed evaluations that take emotional data into account.

[0784] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0785] Step 1: User Registration

[0786] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. Specifically, the device sends the form data in JSON format. The server receives it and saves it in a database. Once saved, the server generates a registration completion notification and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0787] Input: Data entered by the user into the "Sign Up" form

[0788] Output: Registration completion notification, confirmation email

[0789] Step 2: Start the interview

[0790] The user clicks the start interview link in the confirmation email. The server detects this access and creates a new interview session. It records the session ID in the database and displays the interview flow page on the terminal. Specifically, the server returns the URL of the flow page along with the session ID.

[0791] Input: User clicks a link

[0792] Output: View Interview Flow Page

[0793] Step 3: Interview

[0794] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user. For example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected. Specifically, the terminal displays an answer input field and a submit button after each question.

[0795] Input: User's answer

[0796] Output: Response data stored in a database

[0797] Step 4: Data analysis and evaluation

[0798] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database. Specifically, the server converts the response data into prompt sentences and inputs them into each engine.

[0799] Input: Response data stored in the database

[0800] Output: Parsed rating and sentiment data

[0801] Step 5: Notification and confirmation of evaluation results

[0802] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. Specifically, the server generates and sends an email containing the report URL.

[0803] Input: Parsed rating data and emotion data

[0804] Output: Evaluation report, notification email

[0805] Step 6: Dashboard and decision making

[0806] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Based on the selection results, the server sends emails to the relevant users informing them of the next interview. Specifically, the server generates and sends emails containing interview details to the selected candidates.

[0807] Input: Evaluation result

[0808] Output: Notification email with interview details

[0809] (Application example 2)

[0810] 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."

[0811] In the conventional recruitment process, it is difficult to fairly and objectively evaluate a candidate's thinking style and personality, and there is no way to properly grasp their emotional state.In addition, there is no system that automatically proposes optimal operation schedules and work allocations based on recruitment evaluation data, making it difficult to achieve efficient personnel allocation and operation management.

[0812] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0813] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for analyzing candidate response data by utilizing a generative model capable of identifying emotional states, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for optimizing operation schedules and work allocation based on the evaluation report, and means for providing a management screen so that human resources personnel can check the evaluation results. This enables fair and objective evaluation that takes into account not only the candidate's thinking style and personality but also their emotional state, and further makes it possible to automatically optimize operation schedules and work allocation based on that data.

[0814] "Candidate" means an individual who applies for a particular job or role in the recruitment process.

[0815] "Start Interview Link" means the link that the Candidate clicks to begin the interview.

[0816] "Response Data" refers to the response information entered by a candidate during an interview.

[0817] "Generative modeling" refers to an AI model used to analyze a candidate's thinking style, personality, and emotional state.

[0818] "Ability to identify emotional states" refers to the skill of recognizing and assessing the emotions displayed by candidates during interviews.

[0819] An "evaluation report" is a report summarizing the results of an analysis based on the candidate's thinking style, personality, and emotional state.

[0820] "Operation schedule" refers to a plan for operations by autonomous vehicles and drivers.

[0821] "Work allocation" refers to the process of determining how specific duties or tasks will be divided.

[0822] The "management screen" is an interface that allows human resources personnel to check the candidate evaluation results and make decisions.

[0823] This invention provides a system that evaluates candidates' thinking styles, personalities, and emotional states, and optimizes operation schedules and work allocation based on the results. This system is mainly composed of three main components: a server, a terminal, and a user.

[0824] server

[0825] The server receives candidate information and stores it in a database. Specifically, the server sends the candidate a link to start the interview and receives response data from the candidate during the interview. The response data is stored in a database, and then a generative model capable of identifying emotional states is used to analyze the candidate's thinking style, personality, and emotional state. An evaluation report is generated based on the analysis results and notified to the candidate. This evaluation report includes not only the candidate's analysis data but also a summary including their emotional state.

[0826] Terminal

[0827] The terminal is a device used by candidates to participate in interviews. The user first clicks on the link to start the interview through the terminal and accesses the interview form. The answer data entered by the candidate is sent to the server via the terminal. The terminal also has a means to receive notification of the evaluation results and display them to the candidate.

[0828] User

[0829] Users refer to candidates who participate in the interview process and human resources personnel who review the candidate evaluation results. Candidates click the interview start link, answer questions, and submit their responses. Human resources personnel review the evaluation results through the administration screen, and based on the results, determine who will advance to the next interview and consider appropriate assignments.

[0830] Hardware and software used

[0831] Hardware: devices such as smartphones

[0832] Software: Backend API built with Python, Flask (API server), MongoDB (database), generative AI models such as GPT-3

[0833] Specific examples

[0834] For example, if a professional driver responds, "I will strive to drive safely and aim to be the best driver," and the emotion he or she feels at the time is recognized as "concentration and a sense of security," the system will suggest the "optimal driving schedule and vehicle allocation" based on the analysis results. In this way, a system that takes into account the driver's thinking style and emotional state will enable safe and efficient driving management.

[0835] Prompt Sentence Examples

[0836] Please answer the following questions:

[0837] 1. What are your career goals?

[0838] 2. What do you feel while driving?

[0839] Sample Answer 1: I will drive safely and aim to be the best driver.

[0840] Sample answer 2: Concentration, sense of security

[0841] In this way, the present invention realizes a multifaceted evaluation of candidates and optimization of operation management based on the evaluation.

[0842] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0843] Step 1:

[0844] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form.

[0845] Input: Candidate information such as name, contact details, and desired job position.

[0846] Operation: The information is sent from the device to the server, which receives it and stores it in a database. After storing it, the server generates a registration completion notice and sends it to the device.

[0847] Output: Registration successful message.

[0848] Step 2:

[0849] The server will send the user a confirmation email notifying them of successful registration and including a link to start the interview.

[0850] Input: Candidate information stored in the database.

[0851] What it does: The server generates a link to the interview flow and sends it embedded in a confirmation email.

[0852] Output: A confirmation email with a link to start the interview.

[0853] Step 3:

[0854] The user clicks the start interview link, creating a new interview session.

[0855] Input: User clicks a link.

[0856] Action: The server records the session ID in the database and displays the interview flow page on the terminal.

[0857] Output: Interview flow page.

[0858] Step 4:

[0859] The user enters answers to the questions displayed on the interview screen.

[0860] Input: Each question and its answer.

[0861] How it works: The user enters an answer and clicks the "Submit" button. The device sends the answer data to the server, which receives it and stores it in a database. This process is repeated for all questions.

[0862] Output: All response data stored in a database.

[0863] Step 5:

[0864] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[0865] Input: Response data.

[0866] How it works: The server uses a generative model and an emotion engine to analyze the response data and generate evaluation results. Data processing involves evaluation and emotion recognition based on the response content.

[0867] Output: Analysis results (evaluation data).

[0868] Step 6:

[0869] The server generates an evaluation report based on the analysis results and notifies the user.

[0870] Input: Analysis results.

[0871] Actions: The server generates an assessment report and sends the user an email informing them that it is complete and providing a link to access the report.

[0872] Output: Assessment report and notification email.

[0873] Step 7:

[0874] The user checks the evaluation report.

[0875] Input: Click on the link in the notification email.

[0876] How it works: The user clicks on the link to view the assessment report, and the server serves a page displaying the assessment results.

[0877] Output: View the assessment report.

[0878] Step 8:

[0879] The HR staff logs in to the administration screen and checks the evaluation results of all users.

[0880] Input: Access to the admin panel.

[0881] How it works: The server provides an administration interface and displays candidate evaluation data.

[0882] Output: Evaluation results for each candidate.

[0883] Step 9:

[0884] Based on the evaluation results, human resources personnel will decide who will advance to the next interview and consider appropriate assignments.

[0885] Input: Evaluation result.

[0886] How it works: HR personnel make decisions based on evaluation data.

[0887] Output: List of candidates who will advance to the next interview, and determination of appropriate placement.

[0888] Step 10:

[0889] Based on the selection results, the server will send an email to the target user informing them of the next interview.

[0890] Input: List of candidates selected for next interview, assignment information.

[0891] Action: The server generates a notification email and sends it to the affected user.

[0892] Output: Interview notification email.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] [Third embodiment]

[0897] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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).

[0903] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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."

[0909] The present invention provides a system for fairly and objectively evaluating a candidate's thinking style and personality to streamline the recruitment process. The system of the present invention includes multiple modules, and specific embodiments thereof will be described below.

[0910] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and saves the response data entered by candidates during the interview and uses a generative model to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen and includes a mechanism that allows human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[0911] The specific flow of the system operation will be explained below.

[0912] User Registration

[0913] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[0914] Interview begins

[0915] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[0916] Interview Dialogue

[0917] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[0918] Data analysis and evaluation

[0919] The server calls a generative model (such as ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the user's answer content and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0920] Notification and confirmation of evaluation results

[0921] The server generates a detailed evaluation report for each user based on the analysis results.The server then sends an email to the user notifying them that the evaluation report is complete and provides them with an access link to the evaluation report.The user can view the evaluation report by clicking the link in the email.

[0922] Admin screen and decision making

[0923] The company's human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. Based on the evaluation results, the company's human resources personnel selects who will advance to the next interview and considers appropriate assignments. Finally, the server sends emails to the target users informing them of the next interview based on the selection results.

[0924] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process. For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates the candidate as "strong leadership orientation." This evaluation is then used to determine appropriate assignments and roles.

[0925] The processing flow will be explained below.

[0926] Step 1:

[0927] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[0928] Step 2:

[0929] The terminal receives the information entered by the user and clicks the "Submit" button.

[0930] Step 3:

[0931] The server stores the received user information in a database.

[0932] Step 4:

[0933] The server generates a registration completion notification and sends it to the terminal.

[0934] Step 5:

[0935] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[0936] Step 6:

[0937] The user clicks on the start interview link in the confirmation email.

[0938] Step 7:

[0939] The server creates a new interview session and records the session ID in the database.

[0940] Step 8:

[0941] The server displays the interview flow page on the terminal.

[0942] Step 9:

[0943] The device displays an initial question (e.g., "What are your career goals?") to the user.

[0944] Step 10:

[0945] The user enters an answer to the question and clicks the "Submit" button.

[0946] Step 11:

[0947] The terminal transmits the user's answer to the server.

[0948] Step 12:

[0949] The server stores the received response data in a database.

[0950] Step 13:

[0951] The server invokes the generative model to analyze the response data stored in the database.

[0952] Step 14:

[0953] The generative model analyzes the content of the user's answers and generates evaluation results.

[0954] Step 15:

[0955] The server stores the evaluation results received from the generative model in a database.

[0956] Step 16:

[0957] The server generates an evaluation report for each user based on the analysis results.

[0958] Step 17:

[0959] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[0960] Step 18:

[0961] Users can click on the link in the email to view the evaluation report.

[0962] Step 19:

[0963] The company's human resources personnel log in to the management screen and check the evaluation results of all users.

[0964] Step 20:

[0965] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[0966] Step 21:

[0967] The company's human resources staff will consider appropriate placement.

[0968] Step 22:

[0969] The server will then send an email to the target user informing them of the next interview.

[0970] Example 1

[0971] 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."

[0972] In the traditional recruitment process, it was difficult to fairly and objectively evaluate candidates' thinking styles and personalities, posing challenges to the fairness and efficiency of the evaluation. It was also difficult to effectively utilize the evaluation data and quickly determine the appropriate placement. This made the entire recruitment process time-consuming and costly.

[0973] 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.

[0974] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for using a generative AI model as a means for analyzing candidate response data, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for providing a management screen so that a person in charge can check the evaluation results, and means for selecting candidates to advance to the next interview and considering appropriate departments. This makes it possible to fairly and objectively evaluate candidates' thinking styles and personalities, effectively utilize the evaluation data to quickly determine appropriate assignments, and improve the efficiency of the entire recruitment process.

[0975] "Candidate Information" means basic data about individuals being evaluated during the recruitment process, such as name, contact details, and desired job type.

[0976] A "database" is a system that stores information in an organized manner and makes it quickly and efficiently accessible when needed.

[0977] "Interview Start Link" means the URL or hyperlink that allows a Candidate to begin an online interview.

[0978] "Response Data" means the text responses entered by the Candidate during the interview.

[0979] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze input data and generate evaluations and outputs based on that content.

[0980] An "evaluation report" is a report summarizing the results of an analysis conducted by a generative AI model based on candidate response data.

[0981] The "administration screen" is an interface that allows system administrators and corporate human resources personnel to operate the system and check and manipulate evaluation results and candidate information.

[0982] "Person in Charge" refers to the HR department staff member who manages the recruitment process within a company and is responsible for evaluating candidates and conducting interviews.

[0983] A "suitable department" is a department or position that is deemed the best fit based on the candidate's skills and assessment results.

[0984] The present invention is a system for fairly and objectively evaluating candidates' thinking styles and personalities to streamline the hiring process. The system of the present invention includes multiple modules, and specific embodiments are described below. The system has a series of processes for collecting information from candidates and evaluating them through interviews. The system has the function of storing candidate information in a database and sending a link to start the interview. Furthermore, the system collects and stores response data entered by candidates during interviews and uses a generative model to analyze that data. An evaluation report is generated based on the analysis results and notified to the candidate. The system also provides a management screen and includes a mechanism for personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate department.

[0985] The specific operation flow of this system is as follows: The system sends the user's registration information from the terminal to the server, and the server saves the received registration information in a database. After saving, the server generates a link to start the interview and sends it to the user via the terminal.

[0986] When a user clicks the start interview link, the server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and starts the interview. The terminal displays the interview questions to the user, and the user enters their answers. The answer data is sent from the terminal to the server, which stores it in the database. This process is repeated until answers to all questions are collected.

[0987] After all the answer data has been collected, the server calls a generative model (e.g., ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[0988] The server then generates a detailed evaluation report for each user based on the analysis results. An email is sent to the user informing them that the evaluation report is complete, along with a link to access the report. The user can view the evaluation report by clicking the link in the email.

[0989] Through the management screen, company personnel can log in to the system and check the evaluation results of all users. Based on the evaluation results, personnel will consider and decide who will advance to the next interview and the appropriate department. Finally, the server will send emails to the selected users informing them of the next interview based on the selection results.

[0990] For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates it as "strong leadership orientation." This evaluation is used to determine the appropriate department and role.

[0991] Examples of prompt statements

[0992] Analyze the candidate's answers as follows:

[0993] Answer: "As a technical leader, I want to bring the team together."

[0994] Analysis example: "Strong leadership orientation"

[0995] The system of the present invention analyzes candidate responses in conjunction with a generative AI model to provide a fair and objective evaluation, resulting in an efficient and reliable hiring process.

[0996] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0997] Step 1: User Registration

[0998] 1. The user accesses the system's website and enters information into the new registration form.

[0999] Input: Basic information such as name, contact information, desired job type, etc.

[1000] Output: Data set of input information

[1001] 2. The terminal sends the information entered by the user to the server.

[1002] Input: User registration information dataset

[1003] Output: Information data sent to the server

[1004] 3. The server stores the received information in a database.

[1005] Input: Information data sent from the terminal

[1006] Output: Candidate information stored in the database

[1007] 4. The server generates a registration completion notification and sends it to the terminal.

[1008] Input: Information stored in a database

[1009] Output: Registration completion notification data

[1010] 5. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1011] Input: Registration completion notification data, interview link

[1012] Output: Registration success message displayed, confirmation email sent

[1013] Step 2: Start the interview

[1014] 1. The user clicks on the start interview link in the confirmation email.

[1015] Input: Confirmation email, interview link

[1016] Output: Request for interview page

[1017] 2. The server creates a new interview session and records the session ID in the database.

[1018] Input: User's interview page request

[1019] Output: Generated session ID, session information recorded in database

[1020] 3. The server displays the interview flow page on the terminal and starts the interview.

[1021] Input: Session information

[1022] Output: Interview flow page displayed on terminal

[1023] Step 3: Interview

[1024] 1. The terminal displays the first question of the interview to the user.

[1025] Input: Interview question data

[1026] Output: Question printed to terminal

[1027] 2. The user enters the answer to the question and clicks the "Submit" button.

[1028] Input: Answer to question

[1029] Output: Sending response data from the device to the server

[1030] 3. The server stores the received response in a database.

[1031] Input: User response data

[1032] Output: Response data stored in a database

[1033] 4. This process is repeated until all questions have been answered.

[1034] Input: Next question data

[1035] Output: Repeated question and answer data collection

[1036] Step 4: Data analysis and evaluation

[1037] 1. The server invokes a generative model (e.g., ChatGPT) to analyze the response data stored in the database.

[1038] Input: Saved response data

[1039] Output: Data input to the generative model

[1040] 2. The generative AI model analyzes the user's answers and generates an evaluation result.

[1041] Input: Answer data

[1042] Output: Parsed evaluation results

[1043] 3. The evaluation results are returned to the server, which stores them in a database.

[1044] Input: Evaluation result data

[1045] Output: Evaluation results stored in a database

[1046] Step 5: Notification and confirmation of evaluation results

[1047] 1. The server generates a detailed evaluation report for each user based on the analysis results.

[1048] Input: Analysis result data

[1049] Output: Generated assessment report

[1050] 2. The server then sends the user an email informing them that the evaluation report is complete and providing a link to access the report.

[1051] Input: Evaluation report, notification email data

[1052] Output: Notification email sent

[1053] 3. Users can click on the link in the email to view the evaluation report.

[1054] Input: Link in notification email

[1055] Output: Access to the assessment report

[1056] Step 6: Dashboard and decision making

[1057] 1. The company's human resources personnel logs in to the administration screen and checks the evaluation results of all users through the interface provided by the system.

[1058] Input: Login information, system interface

[1059] Output: Displayed evaluation results

[1060] 2. Based on the evaluation results, the company's human resources staff will consider and decide who will advance to the next interview and the appropriate department.

[1061] Input: Evaluation result data

[1062] Output: Determined interview candidates, appropriate department

[1063] 3. Finally, the server will send an email to the selected user informing them of the next interview based on the selection results.

[1064] Input: Selection result data

[1065] Output: Interview notification email sent

[1066] (Application example 1)

[1067] 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."

[1068] Conventional candidate evaluation systems only evaluate candidates' thinking styles and personalities, making it difficult to evaluate employee performance in brick-and-mortar stores and provide feedback in real time. There is also a need for a system that can analyze employees' customer service attitudes and behaviors in detail and provide appropriate feedback in real time. The purpose of this project is to solve this issue and improve employee performance and customer satisfaction.

[1069] 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.

[1070] In this invention, the server includes a means for receiving candidate information and storing it in a database, a means for sending the candidate a link to start an interview, a means for receiving and storing response data from the candidate, and a means for evaluating the performance of store employees and providing feedback in real time, thereby enabling not only candidate evaluation but also performance evaluation and real-time feedback of employees in a physical store.

[1071] "Means of receiving candidate information and storing it in a database" refers to the process of collecting data such as personal information and resumes provided by job seekers and storing it in a database.

[1072] "Method of sending candidate an interview start link" is the process of sending job seekers an email or message containing a URL to start an interview.

[1073] "Means for receiving and storing candidate response data" refers to the process of collecting responses and information entered by job seekers during interviews and storing them in a database.

[1074] "Means for analyzing candidate response data" refers to the process of analyzing collected job seeker response data using algorithms or generative models.

[1075] "Means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate" refers to the process of creating an evaluation report summarizing the analysis results and notifying the job seeker of the results.

[1076] "Providing an administration screen and a means for human resources personnel to check the evaluation results" refers to a process that allows human resources personnel to check the evaluation results of job applicants using an administration screen within the system.

[1077] "Means for evaluating store associate performance and providing real-time feedback" refers to a process that monitors the work performance of employees working in physical stores, evaluates their performance using a generative model, and immediately provides areas for improvement and advice.

[1078] The present invention is a system for evaluating the performance of store clerks in a physical store and providing feedback in real time. This system is configured using hardware and software such as smart glasses, a camera, a microphone, and a generative model (e.g., GPT-3.5-turbo). Specific embodiments for implementing the present invention are described below.

[1079] System Overview

[1080] 1. Collection and storage of candidate information

[1081] The server first receives the individual information of the store clerk and stores it in a database. This information includes the individual's name, contact information, work history, etc. The user (in this case, the store clerk) accesses the system's website and enters the necessary data into the "New Registration" form. The entered data is sent from the terminal to the server, which then stores it in the database.

[1082] 2. Send the interview start link

[1083] After the salesperson completes the registration, the server sends the user a confirmation email containing a link to start the interview. The user clicks on the link in the email to start the interview (or start the job).

[1084] 3. Store Employee Performance Evaluation

[1085] When a user wears the smart glasses and performs actual work, the smart glasses' camera and microphone record the actions and voices of the store clerk in real time, and the device sends this collected data to a server for analysis.

[1086] 4. Data Analysis

[1087] The server analyzes the collected data using a generative model. For example, the data includes information on how the salesperson responded to the customer and how they explained the product. The analysis results are returned to the server, and an evaluation report is generated as needed.

[1088] 5. Providing real-time feedback

[1089] Based on the analysis, the server evaluates the employee's performance and provides real-time feedback, including specific advice and areas for improvement, which is displayed on the smart glasses' display.

[1090] 6. Providing an administration screen

[1091] The server provides a management screen that allows human resources personnel to check the evaluation results of store employees. This management screen allows for the centralized management of each store employee's performance evaluation, feedback, work history, etc.

[1092] Hardware and Software Used

[1093] Smart glasses: Collect video and audio from the store clerk's perspective.

[1094] Camera: The camera built into the smart glasses records the footage.

[1095] Microphone: A microphone built into the smart glasses records audio.

[1096] Generative models: Analyze data using generative AI models such as GPT-3.5-turbo.

[1097] Database: Stores employee information, collected data, and evaluation results.

[1098] Specific examples

[1099] Specifically, we consider a scenario in which a salesperson explains the features of a new product to a customer. The following is an example of a prompt sentence to use when analyzing data collected in this scenario.

[1100] Example prompt: "Based on the following observation, please evaluate the salesperson's customer service attitude: 'The salesperson explained the features of the new product in detail to the customer.'"

[1101] A generative model analyzes the prompt and provides real-time evaluation feedback, helping to improve the store clerk's performance.

[1102] In this way, the present invention can provide efficient performance evaluation and immediate feedback to employees in brick-and-mortar stores.

[1103] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1104] Step 1:

[1105] The server receives data such as personal information and work history provided by the user and stores it in a database. When the user uses a terminal to enter the required data into the "New Registration" form and clicks the submit button, the input data is sent from the terminal to the server. The server receives this and stores it in a database. The input data includes the individual's name, contact information, work history, etc.

[1106] Step 2:

[1107] After the user's registration is complete, the server will send the user a confirmation email containing a link to begin the interview (job). Once the registration process is complete, the server will automatically send a confirmation email with a link to the user's email address. This link is a means of guiding the user to begin the interview or job.

[1108] Step 3:

[1109] The user clicks on the link in the confirmation email to begin the interview (task). When the link is clicked, the server creates a new session and records the session ID in the database. The server then displays the interview page on the terminal, ready for the user to begin the interview.

[1110] Step 4:

[1111] The user wears smart glasses and records their actions and voices in real time while working. The smart glasses' camera and microphone collect video and audio data, which are then transmitted to a server by the device.

[1112] Step 5:

[1113] The server sends the collected video and audio data to the generative model for analysis. The generative model analyzes the input data and evaluates the salesperson's performance. Specifically, the server sends a prompt to the generative model, such as "Please rate the salesperson's behavior while explaining the features of a new product," and receives the evaluation data in return.

[1114] Step 6:

[1115] The server creates a detailed evaluation report based on the evaluation data returned from the generative model and provides the results to the user as feedback in real time.The evaluation and areas for improvement are displayed on the smart glasses display, and appropriate advice is provided to the user in real time.

[1116] Step 7:

[1117] The server stores the analysis results and feedback in a database. This allows human resources personnel to check the evaluation results of each user at any time from the management screen. The management screen allows for centralized management of each employee's performance evaluation, feedback, work history, etc.

[1118] The above steps make it possible to evaluate a user's performance in real time and provide appropriate feedback.

[1119] 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.

[1120] The present invention is a system that combines a system that fairly and objectively evaluates a candidate's thinking style and personality to streamline the hiring process with an emotion engine that recognizes the candidate's emotions. This system includes multiple modules, and specific embodiments thereof will be described below.

[1121] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and stores the response data entered by candidates during the interview, and uses a generative model and emotion engine to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen, allowing human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[1122] The specific flow of the system operation will be explained below.

[1123] User Registration

[1124] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1125] Interview begins

[1126] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[1127] Interview Dialogue

[1128] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[1129] Data analysis and evaluation

[1130] The server calls the generative model and emotion engine to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The emotion engine recognizes the user's emotion based on the answer data and adds the emotion data to the evaluation result. The evaluation result is returned to the server, which stores it in the database.

[1131] Notification and confirmation of evaluation results

[1132] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the evaluation report. The user can view the evaluation report by clicking the link in the email.

[1133] Admin screen and decision making

[1134] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[1135] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process and providing a detailed evaluation that takes the candidate's emotions into account. For example, if a candidate answers, "I want to lead a team as a technical leader," and the emotion expressed at that time is recognized as "confidence," the analysis results of the generative model and emotion engine will evaluate the candidate as "strongly leadership-oriented and confident." This evaluation is then used to determine appropriate assignments and roles.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[1139] Step 2:

[1140] The terminal receives the information entered by the user and clicks the "Submit" button.

[1141] Step 3:

[1142] The server stores the received user information in a database.

[1143] Step 4:

[1144] The server generates a registration completion notification and sends it to the terminal.

[1145] Step 5:

[1146] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[1147] Step 6:

[1148] The user clicks on the start interview link in the confirmation email.

[1149] Step 7:

[1150] The server creates a new interview session and records the session ID in the database.

[1151] Step 8:

[1152] The server displays the interview flow page on the terminal.

[1153] Step 9:

[1154] The device displays an initial question (e.g., "What are your career goals?") to the user.

[1155] Step 10:

[1156] The user enters an answer to the question and clicks the "Submit" button.

[1157] Step 11:

[1158] The terminal transmits the user's answer to the server.

[1159] Step 12:

[1160] The server stores the received response data in a database.

[1161] Step 13:

[1162] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[1163] Step 14:

[1164] The generative model analyzes the content of the user's answers and generates an evaluation result. At the same time, the emotion engine recognizes the user's emotions based on the answer data and generates emotion data.

[1165] Step 15:

[1166] The server stores the evaluation results received from the generative model and the emotion data received from the emotion engine in a database.

[1167] Step 16:

[1168] The server generates an evaluation report for each user based on the analysis results, which includes not only evaluation data on thinking style and personality, but also emotional data.

[1169] Step 17:

[1170] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[1171] Step 18:

[1172] Users can click on the link in the email to view the evaluation report.

[1173] Step 19:

[1174] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system, which also includes emotional data.

[1175] Step 20:

[1176] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[1177] Step 21:

[1178] The company's human resources staff will consider appropriate placement.

[1179] Step 22:

[1180] The server will then send an email to the target user informing them of the next interview.

[1181] Example 2

[1182] 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."

[1183] In the traditional hiring process, it is difficult to fairly and objectively evaluate candidates' thinking styles and personalities, resulting in low hiring efficiency. Furthermore, because the evaluation does not take emotions into account, it is difficult to determine appropriate assignments and roles. Furthermore, tasks such as analyzing data and notifying evaluation results are complex, placing a heavy burden on human resources personnel.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1185] In this invention, the server includes: means for receiving candidate information and storing it in a database; means for sending a link to start an interview to the candidate; means for receiving and storing response data from the candidate; means for calling a generative AI model and an emotion recognition engine to analyze the candidate's response data; means for generating an evaluation report based on the generated evaluation data and recognized emotion data and notifying the candidate; and means for providing a management screen and viewing a detailed report including the evaluation results and emotion data. This enables fair and objective evaluation of candidates and realizes an efficient hiring process. Furthermore, detailed evaluations that take emotion data into account make it easier to determine appropriate assignments and roles.

[1186] "Candidate Information" refers to personal information such as the name, contact details, and desired job title of individuals involved in the recruitment process.

[1187] "Database" refers to an information management system in which candidate information, response data, evaluation data, etc. are systematically stored.

[1188] "Interview Start Link" means the web link that enables a Candidate to begin an interview.

[1189] "Response Data" refers to the information provided by a Candidate in response to each question during an interview.

[1190] "Generative AI model" refers to the artificial intelligence model used to analyze and evaluate candidate response data.

[1191] An "emotion recognition engine" refers to software that analyzes and recognizes emotions from candidate response data.

[1192] "Assessment Report" means a detailed report containing assessment data and perceived emotional data regarding a Candidate's thinking style and personality.

[1193] "Management screen" refers to the interface that human resources personnel use to view and manage evaluation results and detailed reports.

[1194] A "human resources professional" is someone whose role is to evaluate candidates and determine appropriate placements during a company's recruitment process.

[1195] A "detailed report" refers to a report that includes specific information about each candidate based on the assessment results and perceived emotional data.

[1196] User Registration

[1197] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. The server stores the received data in a database. Once the data is saved, the server generates a registration completion notice and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1198] Interview begins

[1199] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[1200] Interview Dialogue

[1201] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user, for example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected.

[1202] Example: A user answers, "As a technical lead, I want to manage a team."

[1203] Data analysis and evaluation

[1204] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database.

[1205] Example: The user's answers are evaluated as "Strong in leadership orientation and confident."

[1206] Notification and confirmation of evaluation results

[1207] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. The user can view the evaluation report by clicking the link in the email.

[1208] Admin screen and decision making

[1209] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[1210] Hardware and software used

[1211] The system utilizes the following hardware and software:

[1212] Server: Manages the database, generates interview sessions, analyzes data, and generates evaluation reports.

[1213] Database: Stores candidate information, response data, and evaluation data.

[1214] Terminal: Enters data from the user, displays questions, and transmits the response data.

[1215] Generative AI model: Analyzes response data and generates evaluation results.

[1216] Emotion recognition engine: Recognizes emotions based on response data.

[1217] Prompt Sentence Examples

[1218] Prompt: "If users say they want to lead a team as a technical leader, rate them as leadership-oriented and confident."

[1219] As a result, this system can evaluate candidates fairly and objectively, enabling an efficient recruitment process. It also makes it possible to determine appropriate assignments and roles based on detailed evaluations that take emotional data into account.

[1220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1221] Step 1: User Registration

[1222] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. Specifically, the device sends the form data in JSON format. The server receives it and saves it in a database. Once saved, the server generates a registration completion notification and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1223] Input: Data entered by the user into the "Sign Up" form

[1224] Output: Registration completion notification, confirmation email

[1225] Step 2: Start the interview

[1226] The user clicks the start interview link in the confirmation email. The server detects this access and creates a new interview session. It records the session ID in the database and displays the interview flow page on the terminal. Specifically, the server returns the URL of the flow page along with the session ID.

[1227] Input: User clicks a link

[1228] Output: View Interview Flow Page

[1229] Step 3: Interview

[1230] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user. For example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected. Specifically, the terminal displays an answer input field and a submit button after each question.

[1231] Input: User's answer

[1232] Output: Response data stored in a database

[1233] Step 4: Data analysis and evaluation

[1234] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database. Specifically, the server converts the response data into prompt sentences and inputs them into each engine.

[1235] Input: Response data stored in the database

[1236] Output: Parsed rating and sentiment data

[1237] Step 5: Notification and confirmation of evaluation results

[1238] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. Specifically, the server generates and sends an email containing the report URL.

[1239] Input: Parsed rating data and emotion data

[1240] Output: Evaluation report, notification email

[1241] Step 6: Dashboard and decision making

[1242] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Based on the selection results, the server sends emails to the relevant users informing them of the next interview. Specifically, the server generates and sends emails containing interview details to the selected candidates.

[1243] Input: Evaluation result

[1244] Output: Notification email with interview details

[1245] (Application example 2)

[1246] 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."

[1247] In the conventional recruitment process, it is difficult to fairly and objectively evaluate a candidate's thinking style and personality, and there is no way to properly grasp their emotional state.In addition, there is no system that automatically proposes optimal operation schedules and work allocations based on recruitment evaluation data, making it difficult to achieve efficient personnel allocation and operation management.

[1248] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1249] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for analyzing candidate response data by utilizing a generative model capable of identifying emotional states, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for optimizing operation schedules and work allocation based on the evaluation report, and means for providing a management screen so that human resources personnel can check the evaluation results. This enables fair and objective evaluation that takes into account not only the candidate's thinking style and personality but also their emotional state, and further makes it possible to automatically optimize operation schedules and work allocation based on that data.

[1250] "Candidate" means an individual who applies for a particular job or role in the recruitment process.

[1251] "Start Interview Link" means the link that the Candidate clicks to begin the interview.

[1252] "Response Data" refers to the response information entered by a candidate during an interview.

[1253] "Generative modeling" refers to an AI model used to analyze a candidate's thinking style, personality, and emotional state.

[1254] "Ability to identify emotional states" refers to the skill of recognizing and assessing the emotions displayed by candidates during interviews.

[1255] An "evaluation report" is a report summarizing the results of an analysis based on the candidate's thinking style, personality, and emotional state.

[1256] "Operation schedule" refers to a plan for operations by autonomous vehicles and drivers.

[1257] "Work allocation" refers to the process of determining how specific duties or tasks will be divided.

[1258] The "management screen" is an interface that allows human resources personnel to check the candidate evaluation results and make decisions.

[1259] This invention provides a system that evaluates candidates' thinking styles, personalities, and emotional states, and optimizes operation schedules and work allocation based on the results. This system is mainly composed of three main components: a server, a terminal, and a user.

[1260] server

[1261] The server receives candidate information and stores it in a database. Specifically, the server sends the candidate a link to start the interview and receives response data from the candidate during the interview. The response data is stored in a database, and then a generative model capable of identifying emotional states is used to analyze the candidate's thinking style, personality, and emotional state. An evaluation report is generated based on the analysis results and notified to the candidate. This evaluation report includes not only the candidate's analysis data but also a summary including their emotional state.

[1262] Terminal

[1263] The terminal is a device used by candidates to participate in interviews. The user first clicks on the link to start the interview through the terminal and accesses the interview form. The answer data entered by the candidate is sent to the server via the terminal. The terminal also has a means to receive notification of the evaluation results and display them to the candidate.

[1264] User

[1265] Users refer to candidates who participate in the interview process and human resources personnel who review the candidate evaluation results. Candidates click the interview start link, answer questions, and submit their responses. Human resources personnel review the evaluation results through the administration screen, and based on the results, determine who will advance to the next interview and consider appropriate assignments.

[1266] Hardware and software used

[1267] Hardware: devices such as smartphones

[1268] Software: Backend API built with Python, Flask (API server), MongoDB (database), generative AI models such as GPT-3

[1269] Specific examples

[1270] For example, if a professional driver responds, "I will strive to drive safely and aim to be the best driver," and the emotion he or she feels at the time is recognized as "concentration and a sense of security," the system will suggest the "optimal driving schedule and vehicle allocation" based on the analysis results. In this way, a system that takes into account the driver's thinking style and emotional state will enable safe and efficient driving management.

[1271] Prompt Sentence Examples

[1272] Please answer the following questions:

[1273] 1. What are your career goals?

[1274] 2. What do you feel while driving?

[1275] Sample Answer 1: I will drive safely and aim to be the best driver.

[1276] Sample answer 2: Concentration, sense of security

[1277] In this way, the present invention realizes a multifaceted evaluation of candidates and optimization of operation management based on the evaluation.

[1278] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1279] Step 1:

[1280] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form.

[1281] Input: Candidate information such as name, contact details, and desired job position.

[1282] Operation: The information is sent from the device to the server, which receives it and stores it in a database. After storing it, the server generates a registration completion notice and sends it to the device.

[1283] Output: Registration successful message.

[1284] Step 2:

[1285] The server will send the user a confirmation email notifying them of successful registration and including a link to start the interview.

[1286] Input: Candidate information stored in the database.

[1287] What it does: The server generates a link to the interview flow and sends it embedded in a confirmation email.

[1288] Output: A confirmation email with a link to start the interview.

[1289] Step 3:

[1290] The user clicks the start interview link, creating a new interview session.

[1291] Input: User clicks a link.

[1292] Action: The server records the session ID in the database and displays the interview flow page on the terminal.

[1293] Output: Interview flow page.

[1294] Step 4:

[1295] The user enters answers to the questions displayed on the interview screen.

[1296] Input: Each question and its answer.

[1297] How it works: The user enters an answer and clicks the "Submit" button. The device sends the answer data to the server, which receives it and stores it in a database. This process is repeated for all questions.

[1298] Output: All response data stored in a database.

[1299] Step 5:

[1300] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[1301] Input: Response data.

[1302] How it works: The server uses a generative model and an emotion engine to analyze the response data and generate evaluation results. Data processing involves evaluation and emotion recognition based on the response content.

[1303] Output: Analysis results (evaluation data).

[1304] Step 6:

[1305] The server generates an evaluation report based on the analysis results and notifies the user.

[1306] Input: Analysis results.

[1307] Actions: The server generates an assessment report and sends the user an email informing them that it is complete and providing a link to access the report.

[1308] Output: Assessment report and notification email.

[1309] Step 7:

[1310] The user checks the evaluation report.

[1311] Input: Click on the link in the notification email.

[1312] How it works: The user clicks on the link to view the assessment report, and the server serves a page displaying the assessment results.

[1313] Output: View the assessment report.

[1314] Step 8:

[1315] The HR staff logs in to the administration screen and checks the evaluation results of all users.

[1316] Input: Access to the admin panel.

[1317] How it works: The server provides an administration interface and displays candidate evaluation data.

[1318] Output: Evaluation results for each candidate.

[1319] Step 9:

[1320] Based on the evaluation results, human resources personnel will decide who will advance to the next interview and consider appropriate assignments.

[1321] Input: Evaluation result.

[1322] How it works: HR personnel make decisions based on evaluation data.

[1323] Output: List of candidates who will advance to the next interview, and determination of appropriate placement.

[1324] Step 10:

[1325] Based on the selection results, the server will send an email to the target user informing them of the next interview.

[1326] Input: List of candidates selected for next interview, assignment information.

[1327] Action: The server generates a notification email and sends it to the affected user.

[1328] Output: Interview notification email.

[1329] 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.

[1330] 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.

[1331] 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.

[1332] [Fourth embodiment]

[1333] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1334] 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.

[1335] 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).

[1336] 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.

[1337] 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.

[1338] 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).

[1339] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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."

[1346] The present invention provides a system for fairly and objectively evaluating a candidate's thinking style and personality to streamline the recruitment process. The system of the present invention includes multiple modules, and specific embodiments thereof will be described below.

[1347] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and saves the response data entered by candidates during the interview and uses a generative model to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen and includes a mechanism that allows human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[1348] The specific flow of the system operation will be explained below.

[1349] User Registration

[1350] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1351] Interview begins

[1352] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[1353] Interview Dialogue

[1354] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[1355] Data analysis and evaluation

[1356] The server calls a generative model (such as ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the user's answer content and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[1357] Notification and confirmation of evaluation results

[1358] The server generates a detailed evaluation report for each user based on the analysis results. The server then sends an email to the user informing them that the evaluation report is complete and provides a link to access the report. The user can view the evaluation report by clicking the link in the email.

[1359] Admin screen and decision making

[1360] The company's human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. Based on the evaluation results, the company's human resources personnel selects who will advance to the next interview and considers appropriate assignments. Finally, the server sends emails to the target users informing them of the next interview based on the selection results.

[1361] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process. For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates the candidate as "strong leadership orientation." This evaluation is then used to determine appropriate assignments and roles.

[1362] The processing flow will be explained below.

[1363] Step 1:

[1364] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[1365] Step 2:

[1366] The terminal receives the information entered by the user and clicks the "Submit" button.

[1367] Step 3:

[1368] The server stores the received user information in a database.

[1369] Step 4:

[1370] The server generates a registration completion notification and sends it to the terminal.

[1371] Step 5:

[1372] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[1373] Step 6:

[1374] The user clicks on the start interview link in the confirmation email.

[1375] Step 7:

[1376] The server creates a new interview session and records the session ID in the database.

[1377] Step 8:

[1378] The server displays the interview flow page on the terminal.

[1379] Step 9:

[1380] The device displays an initial question (e.g., "What are your career goals?") to the user.

[1381] Step 10:

[1382] The user enters an answer to the question and clicks the "Submit" button.

[1383] Step 11:

[1384] The terminal transmits the user's answer to the server.

[1385] Step 12:

[1386] The server stores the received response data in a database.

[1387] Step 13:

[1388] The server invokes the generative model to analyze the response data stored in the database.

[1389] Step 14:

[1390] The generative model analyzes the content of the user's answers and generates evaluation results.

[1391] Step 15:

[1392] The server stores the evaluation results received from the generative model in a database.

[1393] Step 16:

[1394] The server generates an evaluation report for each user based on the analysis results.

[1395] Step 17:

[1396] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[1397] Step 18:

[1398] Users can click on the link in the email to view the evaluation report.

[1399] Step 19:

[1400] The company's human resources personnel log in to the management screen and check the evaluation results of all users.

[1401] Step 20:

[1402] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[1403] Step 21:

[1404] The company's human resources staff will consider appropriate placement.

[1405] Step 22:

[1406] The server will then send an email to the target user informing them of the next interview.

[1407] Example 1

[1408] 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."

[1409] In the traditional recruitment process, it was difficult to fairly and objectively evaluate candidates' thinking styles and personalities, posing challenges to the fairness and efficiency of the evaluation. It was also difficult to effectively utilize the evaluation data and quickly determine the appropriate placement. This made the entire recruitment process time-consuming and costly.

[1410] 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.

[1411] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for using a generative AI model as a means for analyzing candidate response data, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for providing a management screen so that a person in charge can check the evaluation results, and means for selecting candidates to advance to the next interview and considering appropriate departments. This makes it possible to fairly and objectively evaluate candidates' thinking styles and personalities, effectively utilize the evaluation data to quickly determine appropriate assignments, and improve the efficiency of the entire recruitment process.

[1412] "Candidate Information" means basic data about individuals being evaluated during the recruitment process, such as name, contact details, and desired job type.

[1413] A "database" is a system that stores information in an organized manner and makes it quickly and efficiently accessible when needed.

[1414] "Interview Start Link" means the URL or hyperlink that allows a Candidate to begin an online interview.

[1415] "Response Data" means the text responses entered by the Candidate during the interview.

[1416] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze input data and generate evaluations and outputs based on that content.

[1417] An "evaluation report" is a report summarizing the results of an analysis conducted by a generative AI model based on candidate response data.

[1418] The "administration screen" is an interface that allows system administrators and corporate human resources personnel to operate the system and check and manipulate evaluation results and candidate information.

[1419] "Person in Charge" refers to the HR department staff member who manages the recruitment process within a company and is responsible for evaluating candidates and conducting interviews.

[1420] A "suitable department" is a department or position that is deemed the best fit based on the candidate's skills and assessment results.

[1421] The present invention is a system for fairly and objectively evaluating candidates' thinking styles and personalities to streamline the hiring process. The system of the present invention includes multiple modules, and specific embodiments are described below. The system has a series of processes for collecting information from candidates and evaluating them through interviews. The system has the function of storing candidate information in a database and sending a link to start the interview. Furthermore, the system collects and stores response data entered by candidates during interviews and uses a generative model to analyze that data. An evaluation report is generated based on the analysis results and notified to the candidate. The system also provides a management screen and includes a mechanism for personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate department.

[1422] The specific operation flow of this system is as follows: The system sends the user's registration information from the terminal to the server, and the server saves the received registration information in a database. After saving, the server generates a link to start the interview and sends it to the user via the terminal.

[1423] When a user clicks the start interview link, the server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and starts the interview. The terminal displays the interview questions to the user, and the user enters their answers. The answer data is sent from the terminal to the server, which stores it in the database. This process is repeated until answers to all questions are collected.

[1424] After all the answer data has been collected, the server calls a generative model (e.g., ChatGPT) to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The evaluation result is returned to the server, which stores it in the database.

[1425] The server then generates a detailed evaluation report for each user based on the analysis results. An email is sent to the user informing them that the evaluation report is complete, along with a link to access the report. The user can view the evaluation report by clicking the link in the email.

[1426] Through the management screen, company personnel can log in to the system and check the evaluation results of all users. Based on the evaluation results, personnel will consider and decide who will advance to the next interview and the appropriate department. Finally, the server will send emails to the selected users informing them of the next interview based on the selection results.

[1427] For example, if a candidate answers, "I want to lead a team as a technical leader," the generative model analyzes the answer and evaluates it as "strong leadership orientation." This evaluation is used to determine the appropriate department and role.

[1428] Examples of prompt statements

[1429] Analyze the candidate's answers as follows:

[1430] Answer: "As a technical leader, I want to bring the team together."

[1431] Analysis example: "Strong leadership orientation"

[1432] The system of the present invention analyzes candidate responses in conjunction with a generative AI model to provide a fair and objective evaluation, resulting in an efficient and reliable hiring process.

[1433] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1434] Step 1: User Registration

[1435] 1. The user accesses the system's website and enters information into the new registration form.

[1436] Input: Basic information such as name, contact information, desired job type, etc.

[1437] Output: Data set of input information

[1438] 2. The terminal sends the information entered by the user to the server.

[1439] Input: User registration information dataset

[1440] Output: Information data sent to the server

[1441] 3. The server stores the received information in a database.

[1442] Input: Information data sent from the terminal

[1443] Output: Candidate information stored in the database

[1444] 4. The server generates a registration completion notification and sends it to the terminal.

[1445] Input: Information stored in a database

[1446] Output: Registration completion notification data

[1447] 5. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1448] Input: Registration completion notification data, interview link

[1449] Output: Registration success message displayed, confirmation email sent

[1450] Step 2: Start the interview

[1451] 1. The user clicks on the start interview link in the confirmation email.

[1452] Input: Confirmation email, interview link

[1453] Output: Request for interview page

[1454] 2. The server creates a new interview session and records the session ID in the database.

[1455] Input: User's interview page request

[1456] Output: Generated session ID, session information recorded in database

[1457] 3. The server displays the interview flow page on the terminal and starts the interview.

[1458] Input: Session information

[1459] Output: Interview flow page displayed on terminal

[1460] Step 3: Interview

[1461] 1. The terminal displays the first question of the interview to the user.

[1462] Input: Interview question data

[1463] Output: Question printed to terminal

[1464] 2. The user enters the answer to the question and clicks the "Submit" button.

[1465] Input: Answer to question

[1466] Output: Sending response data from the device to the server

[1467] 3. The server stores the received response in a database.

[1468] Input: User response data

[1469] Output: Response data stored in a database

[1470] 4. This process is repeated until all questions have been answered.

[1471] Input: Next question data

[1472] Output: Repeated question and answer data collection

[1473] Step 4: Data analysis and evaluation

[1474] 1. The server invokes a generative model (e.g., ChatGPT) to analyze the response data stored in the database.

[1475] Input: Saved response data

[1476] Output: Data input to the generative model

[1477] 2. The generative AI model analyzes the user's answers and generates an evaluation result.

[1478] Input: Answer data

[1479] Output: Parsed evaluation results

[1480] 3. The evaluation results are returned to the server, which stores them in a database.

[1481] Input: Evaluation result data

[1482] Output: Evaluation results stored in a database

[1483] Step 5: Notification and confirmation of evaluation results

[1484] 1. The server generates a detailed evaluation report for each user based on the analysis results.

[1485] Input: Analysis result data

[1486] Output: Generated assessment report

[1487] 2. The server then sends the user an email informing them that the evaluation report is complete and providing a link to access the report.

[1488] Input: Evaluation report, notification email data

[1489] Output: Notification email sent

[1490] 3. Users can click on the link in the email to view the evaluation report.

[1491] Input: Link in notification email

[1492] Output: Access to the assessment report

[1493] Step 6: Dashboard and decision making

[1494] 1. The company's human resources personnel logs in to the administration screen and checks the evaluation results of all users through the interface provided by the system.

[1495] Input: Login information, system interface

[1496] Output: Displayed evaluation results

[1497] 2. Based on the evaluation results, the company's human resources staff will consider and decide who will advance to the next interview and the appropriate department.

[1498] Input: Evaluation result data

[1499] Output: Determined interview candidates, appropriate department

[1500] 3. Finally, the server will send an email to the selected user informing them of the next interview based on the selection results.

[1501] Input: Selection result data

[1502] Output: Interview notification email sent

[1503] (Application example 1)

[1504] 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."

[1505] Conventional candidate evaluation systems only evaluate candidates' thinking styles and personalities, making it difficult to evaluate employee performance in brick-and-mortar stores and provide feedback in real time. There is also a need for a system that can analyze employees' customer service attitudes and behaviors in detail and provide appropriate feedback in real time. The purpose of this project is to solve this issue and improve employee performance and customer satisfaction.

[1506] 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.

[1507] In this invention, the server includes a means for receiving candidate information and storing it in a database, a means for sending the candidate a link to start an interview, a means for receiving and storing response data from the candidate, and a means for evaluating the performance of store employees and providing feedback in real time, thereby enabling not only candidate evaluation but also performance evaluation and real-time feedback of employees in a physical store.

[1508] "Means of receiving candidate information and storing it in a database" refers to the process of collecting data such as personal information and resumes provided by job seekers and storing it in a database.

[1509] "Method of sending candidate an interview start link" is the process of sending job seekers an email or message containing a URL to start an interview.

[1510] "Means for receiving and storing candidate response data" refers to the process of collecting responses and information entered by job seekers during interviews and storing them in a database.

[1511] "Means for analyzing candidate response data" refers to the process of analyzing collected job seeker response data using algorithms or generative models.

[1512] "Means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate" refers to the process of creating an evaluation report summarizing the analysis results and notifying the job seeker of the results.

[1513] "Providing an administration screen and a means for human resources personnel to check the evaluation results" refers to a process that allows human resources personnel to check the evaluation results of job applicants using an administration screen within the system.

[1514] "Means for evaluating store associate performance and providing real-time feedback" refers to a process that monitors the work performance of employees working in physical stores, evaluates their performance using a generative model, and immediately provides areas for improvement and advice.

[1515] The present invention is a system for evaluating the performance of store clerks in a physical store and providing feedback in real time. This system is configured using hardware and software such as smart glasses, a camera, a microphone, and a generative model (e.g., GPT-3.5-turbo). Specific embodiments for implementing the present invention are described below.

[1516] System Overview

[1517] 1. Collection and storage of candidate information

[1518] The server first receives the individual information of the store clerk and stores it in a database. This information includes the individual's name, contact information, work history, etc. The user (in this case, the store clerk) accesses the system's website and enters the necessary data into the "New Registration" form. The entered data is sent from the terminal to the server, which then stores it in the database.

[1519] 2. Send the interview start link

[1520] After the salesperson completes the registration, the server sends the user a confirmation email containing a link to start the interview. The user clicks on the link in the email to start the interview (or start the job).

[1521] 3. Store Employee Performance Evaluation

[1522] When a user wears the smart glasses and performs actual work, the smart glasses' camera and microphone record the actions and voices of the store clerk in real time, and the device sends this collected data to a server for analysis.

[1523] 4. Data Analysis

[1524] The server analyzes the collected data using a generative model. For example, the data includes information on how the salesperson responded to the customer and how they explained the product. The analysis results are returned to the server, and an evaluation report is generated as needed.

[1525] 5. Providing real-time feedback

[1526] Based on the analysis, the server evaluates the employee's performance and provides real-time feedback, including specific advice and areas for improvement, which is displayed on the smart glasses' display.

[1527] 6. Providing an administration screen

[1528] The server provides a management screen that allows human resources personnel to check the evaluation results of store employees. This management screen allows for the centralized management of each store employee's performance evaluation, feedback, work history, etc.

[1529] Hardware and Software Used

[1530] Smart glasses: Collect video and audio from the store clerk's perspective.

[1531] Camera: The camera built into the smart glasses records the footage.

[1532] Microphone: A microphone built into the smart glasses records audio.

[1533] Generative models: Analyze data using generative AI models such as GPT-3.5-turbo.

[1534] Database: Stores employee information, collected data, and evaluation results.

[1535] Specific examples

[1536] Specifically, we consider a scenario in which a salesperson explains the features of a new product to a customer. The following is an example of a prompt sentence to use when analyzing data collected in this scenario.

[1537] Example prompt: "Based on the following observation, please evaluate the salesperson's customer service attitude: 'The salesperson explained the features of the new product in detail to the customer.'"

[1538] A generative model analyzes the prompt and provides real-time evaluation feedback, helping to improve the store clerk's performance.

[1539] In this way, the present invention can provide efficient performance evaluation and immediate feedback to employees in brick-and-mortar stores.

[1540] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1541] Step 1:

[1542] The server receives data such as personal information and work history provided by the user and stores it in a database. When the user uses a terminal to enter the required data into the "New Registration" form and clicks the submit button, the input data is sent from the terminal to the server. The server receives this and stores it in a database. The input data includes the individual's name, contact information, work history, etc.

[1543] Step 2:

[1544] After the user's registration is complete, the server will send the user a confirmation email containing a link to begin the interview (job). Once the registration process is complete, the server will automatically send a confirmation email with a link to the user's email address. This link is a means of guiding the user to begin the interview or job.

[1545] Step 3:

[1546] The user clicks on the link in the confirmation email to begin the interview (task). When the link is clicked, the server creates a new session and records the session ID in the database. The server then displays the interview page on the terminal, ready for the user to begin the interview.

[1547] Step 4:

[1548] The user wears smart glasses and records their actions and voices in real time while working. The smart glasses' camera and microphone collect video and audio data, which are then transmitted to a server by the device.

[1549] Step 5:

[1550] The server sends the collected video and audio data to the generative model for analysis. The generative model analyzes the input data and evaluates the salesperson's performance. Specifically, the server sends a prompt to the generative model, such as "Please rate the salesperson's behavior while explaining the features of a new product," and receives the evaluation data in return.

[1551] Step 6:

[1552] The server creates a detailed evaluation report based on the evaluation data returned from the generative model and provides the results to the user as feedback in real time.The evaluation and areas for improvement are displayed on the smart glasses display, and appropriate advice is provided to the user in real time.

[1553] Step 7:

[1554] The server stores the analysis results and feedback in a database. This allows human resources personnel to check the evaluation results of each user at any time from the management screen. The management screen allows for centralized management of each employee's performance evaluation, feedback, work history, etc.

[1555] The above steps make it possible to evaluate a user's performance in real time and provide appropriate feedback.

[1556] 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.

[1557] The present invention is a system that combines a system that fairly and objectively evaluates a candidate's thinking style and personality to streamline the hiring process with an emotion engine that recognizes the candidate's emotions. This system includes multiple modules, and specific embodiments thereof will be described below.

[1558] This system has a series of processes for collecting information from candidates and evaluating them through interviews. The system stores candidate information in a database and has the function of sending a link to start the interview. It also collects and stores the response data entered by candidates during the interview, and uses a generative model and emotion engine to analyze this data. An evaluation report is generated based on the analysis results and notified to the candidate. It also provides a management screen, allowing human resources personnel to check the evaluation results and decide who should proceed to the next interview and the appropriate assignment.

[1559] The specific flow of the system operation will be explained below.

[1560] User Registration

[1561] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. This information is sent from the terminal to the server, which receives it and stores it in a database. After saving it, the server generates a registration completion notice and sends it to the terminal. The terminal displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1562] Interview begins

[1563] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[1564] Interview Dialogue

[1565] When the interview screen appears, the device displays the first question (e.g., "What are your career goals?") to the user. The user enters the answer to the question and clicks the "Submit" button. The answer is sent from the device to the server, which receives it and stores it in a database. This process is repeated until answers to all questions have been collected.

[1566] Data analysis and evaluation

[1567] The server calls the generative model and emotion engine to analyze the answer data stored in the database. The generative model analyzes the content of the user's answer and generates an evaluation result. The emotion engine recognizes the user's emotion based on the answer data and adds the emotion data to the evaluation result. The evaluation result is returned to the server, which stores it in the database.

[1568] Notification and confirmation of evaluation results

[1569] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the evaluation report. The user can view the evaluation report by clicking the link in the email.

[1570] Admin screen and decision making

[1571] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[1572] Through the above process, the system of the present invention can evaluate candidates fairly and objectively, realizing an efficient hiring process and providing a detailed evaluation that takes the candidate's emotions into account. For example, if a candidate answers, "I want to lead a team as a technical leader," and the emotion expressed at that time is recognized as "confidence," the analysis results of the generative model and emotion engine will evaluate the candidate as "strongly leadership-oriented and confident." This evaluation is then used to determine appropriate assignments and roles.

[1573] The processing flow will be explained below.

[1574] Step 1:

[1575] Users access the system's website and enter information such as their name, contact details, and desired job type into the "New Registration" form.

[1576] Step 2:

[1577] The terminal receives the information entered by the user and clicks the "Submit" button.

[1578] Step 3:

[1579] The server stores the received user information in a database.

[1580] Step 4:

[1581] The server generates a registration completion notification and sends it to the terminal.

[1582] Step 5:

[1583] The device will display a message to the user confirming registration and will send a confirmation email containing a link to start the interview.

[1584] Step 6:

[1585] The user clicks on the start interview link in the confirmation email.

[1586] Step 7:

[1587] The server creates a new interview session and records the session ID in the database.

[1588] Step 8:

[1589] The server displays the interview flow page on the terminal.

[1590] Step 9:

[1591] The device displays an initial question (e.g., "What are your career goals?") to the user.

[1592] Step 10:

[1593] The user enters an answer to the question and clicks the "Submit" button.

[1594] Step 11:

[1595] The terminal transmits the user's answer to the server.

[1596] Step 12:

[1597] The server stores the received response data in a database.

[1598] Step 13:

[1599] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[1600] Step 14:

[1601] The generative model analyzes the content of the user's answers and generates an evaluation result. At the same time, the emotion engine recognizes the user's emotions based on the answer data and generates emotion data.

[1602] Step 15:

[1603] The server stores the evaluation results received from the generative model and the emotion data received from the emotion engine in a database.

[1604] Step 16:

[1605] The server generates an evaluation report for each user based on the analysis results, which includes not only evaluation data on thinking style and personality, but also emotional data.

[1606] Step 17:

[1607] The server will send an email to the user informing them that the evaluation report is complete and providing a link to access the evaluation report.

[1608] Step 18:

[1609] Users can click on the link in the email to view the evaluation report.

[1610] Step 19:

[1611] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system, which also includes emotional data.

[1612] Step 20:

[1613] Based on the evaluation results, the company's human resources staff will select candidates to advance to the next interview.

[1614] Step 21:

[1615] The company's human resources staff will consider appropriate placement.

[1616] Step 22:

[1617] The server will then send an email to the target user informing them of the next interview.

[1618] Example 2

[1619] 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."

[1620] In the traditional hiring process, it is difficult to fairly and objectively evaluate candidates' thinking styles and personalities, resulting in low hiring efficiency. Furthermore, because the evaluation does not take emotions into account, it is difficult to determine appropriate assignments and roles. Furthermore, tasks such as analyzing data and notifying evaluation results are complex, placing a heavy burden on human resources personnel.

[1621] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1622] In this invention, the server includes: means for receiving candidate information and storing it in a database; means for sending a link to start an interview to the candidate; means for receiving and storing response data from the candidate; means for calling a generative AI model and an emotion recognition engine to analyze the candidate's response data; means for generating an evaluation report based on the generated evaluation data and recognized emotion data and notifying the candidate; and means for providing a management screen and viewing a detailed report including the evaluation results and emotion data. This enables fair and objective evaluation of candidates and realizes an efficient hiring process. Furthermore, detailed evaluations that take emotion data into account make it easier to determine appropriate assignments and roles.

[1623] "Candidate Information" refers to personal information such as the name, contact details, and desired job title of individuals involved in the recruitment process.

[1624] "Database" refers to an information management system in which candidate information, response data, evaluation data, etc. are systematically stored.

[1625] "Interview Start Link" means the web link that enables a Candidate to begin an interview.

[1626] "Response Data" refers to the information provided by a Candidate in response to each question during an interview.

[1627] "Generative AI model" refers to the artificial intelligence model used to analyze and evaluate candidate response data.

[1628] An "emotion recognition engine" refers to software that analyzes and recognizes emotions from candidate response data.

[1629] "Assessment Report" means a detailed report containing assessment data and perceived emotional data regarding a Candidate's thinking style and personality.

[1630] "Management screen" refers to the interface that human resources personnel use to view and manage evaluation results and detailed reports.

[1631] A "human resources professional" is someone whose role is to evaluate candidates and determine appropriate placements during a company's recruitment process.

[1632] A "detailed report" refers to a report that includes specific information about each candidate based on the assessment results and perceived emotional data.

[1633] User Registration

[1634] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. The server stores the received data in a database. Once the data is saved, the server generates a registration completion notice and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1635] Interview begins

[1636] The user clicks the start interview link in the confirmation email. The server creates a new interview session and records the session ID in the database. The server then displays the interview flow page on the terminal and the interview begins.

[1637] Interview Dialogue

[1638] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user, for example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected.

[1639] Example: A user answers, "As a technical lead, I want to manage a team."

[1640] Data analysis and evaluation

[1641] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database.

[1642] Example: The user's answers are evaluated as "Strong in leadership orientation and confident."

[1643] Notification and confirmation of evaluation results

[1644] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. The user can view the evaluation report by clicking the link in the email.

[1645] Admin screen and decision making

[1646] Corporate human resources personnel can log in to the management screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Finally, the server sends emails to the selected users informing them of the next interview based on the selection results.

[1647] Hardware and software used

[1648] The system utilizes the following hardware and software:

[1649] Server: Manages the database, generates interview sessions, analyzes data, and generates evaluation reports.

[1650] Database: Stores candidate information, response data, and evaluation data.

[1651] Terminal: Enters data from the user, displays questions, and transmits the response data.

[1652] Generative AI model: Analyzes response data and generates evaluation results.

[1653] Emotion recognition engine: Recognizes emotions based on response data.

[1654] Prompt Sentence Examples

[1655] Prompt: "If users say they want to lead a team as a technical leader, rate them as leadership-oriented and confident."

[1656] As a result, this system can evaluate candidates fairly and objectively, enabling an efficient recruitment process. It also makes it possible to determine appropriate assignments and roles based on detailed evaluations that take emotional data into account.

[1657] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1658] Step 1: User Registration

[1659] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form. The device collects this information and sends it to the server. Specifically, the device sends the form data in JSON format. The server receives it and saves it in a database. Once saved, the server generates a registration completion notification and sends it to the device. The device displays a registration completion message to the user and sends the user a confirmation email containing a link to start the interview.

[1660] Input: Data entered by the user into the "Sign Up" form

[1661] Output: Registration completion notification, confirmation email

[1662] Step 2: Start the interview

[1663] The user clicks the start interview link in the confirmation email. The server detects this access and creates a new interview session. It records the session ID in the database and displays the interview flow page on the terminal. Specifically, the server returns the URL of the flow page along with the session ID.

[1664] Input: User clicks a link

[1665] Output: View Interview Flow Page

[1666] Step 3: Interview

[1667] When the interview flow page is displayed on the terminal, the terminal displays the first question to the user. For example, "What are your career goals?" The user enters an answer and clicks the "Submit" button. The terminal sends the answer data to the server, which stores it in a database. This process is repeated until answers to all questions have been collected. Specifically, the terminal displays an answer input field and a submit button after each question.

[1668] Input: User's answer

[1669] Output: Response data stored in a database

[1670] Step 4: Data analysis and evaluation

[1671] The server calls the generative AI model and emotion recognition engine to analyze the response data stored in the database. The generative AI model analyzes the content of the user's response and generates an evaluation result. The emotion recognition engine recognizes the user's emotion based on the response data and adds the emotion data to the evaluation result. The analysis result is returned to the server and stored in the database. Specifically, the server converts the response data into prompt sentences and inputs them into each engine.

[1672] Input: Response data stored in the database

[1673] Output: Parsed rating and sentiment data

[1674] Step 5: Notification and confirmation of evaluation results

[1675] The server generates a detailed evaluation report for each user based on the analysis results. This report includes not only evaluation data on the user's thinking style and personality, but also emotional data. The server then sends the user an email notifying them that the evaluation report is complete and provides them with an access link to the report. Specifically, the server generates and sends an email containing the report URL.

[1676] Input: Parsed rating data and emotion data

[1677] Output: Evaluation report, notification email

[1678] Step 6: Dashboard and decision making

[1679] Corporate human resources personnel can log in to the administration screen and check the evaluation results of all users through the interface provided by the system. The evaluation results also include emotional data, allowing for more detailed judgments. Based on the evaluation results, corporate human resources personnel select candidates to advance to the next interview and consider appropriate assignments. Based on the selection results, the server sends emails to the relevant users informing them of the next interview. Specifically, the server generates and sends emails containing interview details to the selected candidates.

[1680] Input: Evaluation result

[1681] Output: Notification email with interview details

[1682] (Application example 2)

[1683] 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."

[1684] In the conventional recruitment process, it is difficult to fairly and objectively evaluate a candidate's thinking style and personality, and there is no way to properly grasp their emotional state.In addition, there is no system that automatically proposes optimal operation schedules and work allocations based on recruitment evaluation data, making it difficult to achieve efficient personnel allocation and operation management.

[1685] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1686] In this invention, the server includes means for receiving candidate information and saving it in a database, means for sending candidates a link to start an interview, means for receiving and saving response data from candidates, means for analyzing candidate response data by utilizing a generative model capable of identifying emotional states, means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate, means for optimizing operation schedules and work allocation based on the evaluation report, and means for providing a management screen so that human resources personnel can check the evaluation results. This enables fair and objective evaluation that takes into account not only the candidate's thinking style and personality but also their emotional state, and further makes it possible to automatically optimize operation schedules and work allocation based on that data.

[1687] "Candidate" means an individual who applies for a particular job or role in the recruitment process.

[1688] "Start Interview Link" means the link that the Candidate clicks to begin the interview.

[1689] "Response Data" refers to the response information entered by a candidate during an interview.

[1690] "Generative modeling" refers to an AI model used to analyze a candidate's thinking style, personality, and emotional state.

[1691] "Ability to identify emotional states" refers to the skill of recognizing and assessing the emotions displayed by candidates during interviews.

[1692] An "evaluation report" is a report summarizing the results of an analysis based on the candidate's thinking style, personality, and emotional state.

[1693] "Operation schedule" refers to a plan for operations by autonomous vehicles and drivers.

[1694] "Work allocation" refers to the process of determining how specific duties or tasks will be divided.

[1695] The "management screen" is an interface that allows human resources personnel to check the candidate evaluation results and make decisions.

[1696] This invention provides a system that evaluates candidates' thinking styles, personalities, and emotional states, and optimizes operation schedules and work allocation based on the results. This system is mainly composed of three main components: a server, a terminal, and a user.

[1697] server

[1698] The server receives candidate information and stores it in a database. Specifically, the server sends the candidate a link to start the interview and receives response data from the candidate during the interview. The response data is stored in a database, and then a generative model capable of identifying emotional states is used to analyze the candidate's thinking style, personality, and emotional state. An evaluation report is generated based on the analysis results and notified to the candidate. This evaluation report includes not only the candidate's analysis data but also a summary including their emotional state.

[1699] Terminal

[1700] The terminal is a device used by candidates to participate in interviews. The user first clicks on the link to start the interview through the terminal and accesses the interview form. The answer data entered by the candidate is sent to the server via the terminal. The terminal also has a means to receive notification of the evaluation results and display them to the candidate.

[1701] User

[1702] Users refer to candidates who participate in the interview process and human resources personnel who review the candidate evaluation results. Candidates click the interview start link, answer questions, and submit their responses. Human resources personnel review the evaluation results through the administration screen, and based on the results, determine who will advance to the next interview and consider appropriate assignments.

[1703] Hardware and software used

[1704] Hardware: devices such as smartphones

[1705] Software: Backend API built with Python, Flask (API server), MongoDB (database), generative AI models such as GPT-3

[1706] Specific examples

[1707] For example, if a professional driver responds, "I will strive to drive safely and aim to be the best driver," and the emotion he or she feels at the time is recognized as "concentration and a sense of security," the system will suggest the "optimal driving schedule and vehicle allocation" based on the analysis results. In this way, a system that takes into account the driver's thinking style and emotional state will enable safe and efficient driving management.

[1708] Prompt Sentence Examples

[1709] Please answer the following questions:

[1710] 1. What are your career goals?

[1711] 2. What do you feel while driving?

[1712] Sample Answer 1: I will drive safely and aim to be the best driver.

[1713] Sample answer 2: Concentration, sense of security

[1714] In this way, the present invention realizes a multifaceted evaluation of candidates and optimization of operation management based on the evaluation.

[1715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1716] Step 1:

[1717] The user accesses the system's website and enters information such as name, contact details, and desired job type into the "New Registration" form.

[1718] Input: Candidate information such as name, contact details, and desired job position.

[1719] Operation: The information is sent from the device to the server, which receives it and stores it in a database. After storing it, the server generates a registration completion notice and sends it to the device.

[1720] Output: Registration successful message.

[1721] Step 2:

[1722] The server will send the user a confirmation email notifying them of successful registration and including a link to start the interview.

[1723] Input: Candidate information stored in the database.

[1724] What it does: The server generates a link to the interview flow and sends it embedded in a confirmation email.

[1725] Output: A confirmation email with a link to start the interview.

[1726] Step 3:

[1727] The user clicks the start interview link, creating a new interview session.

[1728] Input: User clicks a link.

[1729] Action: The server records the session ID in the database and displays the interview flow page on the terminal.

[1730] Output: Interview flow page.

[1731] Step 4:

[1732] The user enters answers to the questions displayed on the interview screen.

[1733] Input: Each question and its answer.

[1734] How it works: The user enters an answer and clicks the "Submit" button. The device sends the answer data to the server, which receives it and stores it in a database. This process is repeated for all questions.

[1735] Output: All response data stored in a database.

[1736] Step 5:

[1737] The server invokes the generative model and emotion engine to analyze the response data stored in the database.

[1738] Input: Response data.

[1739] How it works: The server uses a generative model and an emotion engine to analyze the response data and generate evaluation results. Data processing involves evaluation and emotion recognition based on the response content.

[1740] Output: Analysis results (evaluation data).

[1741] Step 6:

[1742] The server generates an evaluation report based on the analysis results and notifies the user.

[1743] Input: Analysis results.

[1744] Actions: The server generates an assessment report and sends the user an email informing them that it is complete and providing a link to access the report.

[1745] Output: Assessment report and notification email.

[1746] Step 7:

[1747] The user checks the evaluation report.

[1748] Input: Click on the link in the notification email.

[1749] How it works: The user clicks on the link to view the assessment report, and the server serves a page displaying the assessment results.

[1750] Output: View the assessment report.

[1751] Step 8:

[1752] The HR staff logs in to the administration screen and checks the evaluation results of all users.

[1753] Input: Access to the admin panel.

[1754] How it works: The server provides an administration interface and displays candidate evaluation data.

[1755] Output: Evaluation results for each candidate.

[1756] Step 9:

[1757] Based on the evaluation results, human resources personnel will decide who will advance to the next interview and consider appropriate assignments.

[1758] Input: Evaluation result.

[1759] How it works: HR personnel make decisions based on evaluation data.

[1760] Output: List of candidates who will advance to the next interview, and determination of appropriate placement.

[1761] Step 10:

[1762] Based on the selection results, the server will send an email to the target user informing them of the next interview.

[1763] Input: List of candidates selected for next interview, assignment information.

[1764] Action: The server generates a notification email and sends it to the affected user.

[1765] Output: Interview notification email.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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).

[1773] 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.

[1774] 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."

[1775] 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.

[1776] 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).

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1786] 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.

[1787] The following is further disclosed regarding the above embodiment.

[1788] (Claim 1)

[1789] a means of receiving and storing candidate information in a database;

[1790] A means to send candidates a link to start the interview;

[1791] a means for receiving and storing response data from candidates;

[1792] a means for analyzing candidate response data;

[1793] A means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate;

[1794] We provide a management screen so that HR personnel can check the evaluation results.

[1795] A system including:

[1796] (Claim 2)

[1797] 2. The system of claim 1, wherein a generative model is used as a means for analyzing candidate response data.

[1798] (Claim 3)

[1799] The system according to claim 1, further comprising a means for determining who will advance to the next interview from the management screen and considering appropriate assignments.

[1800] "Example 1"

[1801] (Claim 1)

[1802] a means of receiving and storing candidate information in a database;

[1803] A means to send candidates a link to start the interview;

[1804] a means for receiving and storing response data from candidates;

[1805] Using generative AI models to analyze candidate response data;

[1806] A means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate;

[1807] We provide a management screen so that the person in charge can check the evaluation results.

[1808] A means to select candidates for the next interview and to consider suitable departments;

[1809] A system including:

[1810] (Claim 2)

[1811] 10. The system of claim 1, further comprising means for analyzing candidate response data using a generative AI model.

[1812] (Claim 3)

[1813] 2. The system according to claim 1, wherein an analysis result is generated based on the response data, and an evaluation report is generated based on the generated evaluation data.

[1814] "Application Example 1"

[1815] (Claim 1)

[1816] a means of receiving and storing candidate information in a database;

[1817] A means to send candidates a link to start the interview;

[1818] a means for receiving and storing response data from candidates;

[1819] a means for analyzing candidate response data;

[1820] A means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate;

[1821] We provide a management screen so that HR personnel can check the evaluation results.

[1822] a means of evaluating associate performance and providing real-time feedback;

[1823] A system including:

[1824] (Claim 2)

[1825] 2. The system of claim 1, wherein a generative model is used as a means for analyzing candidate response data.

[1826] (Claim 3)

[1827] The system according to claim 1, further comprising a means for determining who will advance to the next interview from the management screen and considering appropriate assignments.

[1828] "Example 2: Combining Emotion Engines"

[1829] (Claim 1)

[1830] a means of receiving and storing candidate information in a database;

[1831] A means to send candidates a link to start the interview;

[1832] a means for receiving and storing response data from candidates;

[1833] means for invoking a generative AI model and an emotion recognition engine to analyze the candidate response data;

[1834] a means for generating an evaluation report based on the generated evaluation data and the recognized emotion data and notifying the candidate of the report;

[1835] It provides a management screen and a means to check detailed reports including evaluation results and emotional data,

[1836] A system including:

[1837] (Claim 2)

[1838] The system of claim 1, which utilizes a generative AI model as a means for analyzing candidate response data.

[1839] (Claim 3)

[1840] The system according to claim 1, further comprising a means for determining who will advance to the next interview from the management screen and considering appropriate assignments.

[1841] "Application example 2 when combining emotion engines"

[1842] (Claim 1)

[1843] a means of receiving and storing candidate information in a database;

[1844] A means to send candidates a link to start the interview;

[1845] a means for receiving and storing response data from candidates;

[1846] A means of analyzing candidate response data by utilizing a generative model capable of identifying emotional states;

[1847] A means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate;

[1848] A means for optimizing operation schedules and work allocation based on the evaluation report;

[1849] We provide a management screen so that HR personnel can check the evaluation results.

[1850] A system including:

[1851] (Claim 2)

[1852] 2. The system of claim 1, wherein a generative model is used as a means for analyzing candidate response data.

[1853] (Claim 3)

[1854] The system according to claim 1, further comprising a means for determining who will advance to the next interview from the management screen and considering appropriate assignments. [Explanation of symbols]

[1855] 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 of receiving and storing candidate information in a database; A means to send candidates a link to start the interview; a means for receiving and storing response data from candidates; a means for analyzing candidate response data; A means for generating an evaluation report based on the analyzed evaluation data and notifying the candidate; We provide a management screen so that HR personnel can check the evaluation results. A system including:

2. The system according to claim 1, wherein a generative model is used as a means for analyzing candidate response data.

3. 2. The system according to claim 1, further comprising a means for determining who will advance to the next interview from the management screen and for considering appropriate assignments.

Images