System

Abstract

A system is provided.SOLUTION: A system comprising: means for registering a desired personality and skill; means for training an interactive generative artificial intelligence model based on the registered personality and skill; means for managing an interview schedule and sending a notification when an interview date approaches; means for conducting an interview based on the generated artificial intelligence model; means for inputting an applicant's answer and evaluating the answer in real time by the artificial intelligence model; means for storing all conversation records and evaluation results of the interview; and means for checking the stored records and making a final decision based on the evaluation results.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In traditional recruitment interviews, interviewer bias and lack of skills often led to insufficient assessment of applicants' aptitude, resulting in mismatches with positions after joining the company. Furthermore, there was a lack of efficient methods for recording and evaluating interviews, making reevaluation difficult. These issues made companies' recruitment processes inefficient, making it difficult to properly hire the talent they were looking for. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for registering a desired personality profile and skills, and a means for training an interactive generative AI model based on the registered personality profile and skills. It also includes a means for managing an interview schedule and sending notifications when the interview date and time approaches, a means for conducting the interview based on the generated AI model, a means for inputting applicant responses and having the AI ​​model evaluate them in real time, a means for saving all conversation records and evaluation results of the interview, and a means for reviewing the saved records and making a final decision based on the evaluation results. This makes it possible to compensate for interviewer biases and skill deficiencies, realize an efficient and fair hiring process, and secure suitable talent.

[0006] "Personality profile" refers to the characteristics, personality, and abilities of the ideal applicant that a company is looking for.

[0007] "Skills" refers to the specialized knowledge and techniques required to perform a specific job or task.

[0008] An "interactive generative artificial intelligence model" refers to an artificial intelligence system that interacts with humans on a conversational basis and generates and evaluates information in real time.

[0009] "Interview schedule" refers to the date and time of the interview between the applicant and interviewer, and related information.

[0010] "Notification" refers to a means of informing interested parties about a particular event or deadline.

[0011] "Questions" refer to specific questions asked of applicants during an interview.

[0012] "Evaluation criteria" refers to the standards or measures used to evaluate applicants' responses and behavior.

[0013] "Real-time assessment" refers to the process of assessing applicants at the same time they provide their answers.

[0014] "Interview transcript" refers to a record of all questions and answers asked during an interview.

[0015] "Final decision" refers to the final decision made after the interview to determine whether or not an applicant is accepted.

[0016] "Reevaluation" refers to the process of re-examining and re-evaluating content that has already been evaluated.

[0017] A "re-interview" refers to an interview that is conducted again after the initial interview. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[0040] Server-side processing

[0041] 1. Registering the desired profile and skills

[0042] The user, a company employee, enters the desired personality profile and skills required for the position through the system's management screen.

[0043] Specifically, information such as "communication skills," "problem-solving skills," and "programming skills (Python)" is registered.

[0044] 2. Training an interactive generative AI model

[0045] The server stores the entered personality and skill data in a database.

[0046] Based on this, the server also uses past interview data and existing employee profiles to train the AI ​​model.

[0047] After completing the training, the server builds an interactive generative AI model with an optimal set of questions and evaluation criteria.

[0048] 3. Managing interview schedules

[0049] When a user sets up an interview schedule in the system, the server stores and manages the schedule in a database.

[0050] As the interview date and time approaches, the server generates a notification and sends a reminder email to the applicant and interviewer.

[0051] Terminal side processing

[0052] 1. Download the AI ​​model

[0053] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server.

[0054] After downloading, the interviewer's device will conduct the interview based on the AI ​​model.

[0055] 2. Interview progress and real-time evaluation

[0056] During the interview, the device displays questions set by the AI ​​model to the applicant.

[0057] For example, questions such as "Please introduce yourself" and "Tell us about projects you have worked on in the past" will be displayed.

[0058] Interviewers enter applicants' answers into a device, and an AI model evaluates the answers in real time.

[0059] As a specific example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," the AI ​​model will evaluate them as having "high programming skills."

[0060] 3. Saving conversation records

[0061] After the entire interview process is completed, the terminal sends all questions, answers, and evaluation results to the server and stores them in a database.

[0062] User processing

[0063] 1. Review of evaluation results and interview records

[0064] The user, a company employee, logs into the system and checks the evaluation results and interview records stored on the server.

[0065] Specifically, users will view saved conversation records and the evaluation results from the AI ​​model to make a final decision regarding hiring or the next interview.

[0066] If necessary, a reassessment or re-interview can be scheduled.

[0067] Specific examples

[0068] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's aptitude in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[0072] Step 2:

[0073] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[0074] Step 3:

[0075] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training is complete, the AI ​​model will have the optimal set of questions and evaluation criteria.

[0076] Step 4:

[0077] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[0078] Step 5:

[0079] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[0080] Step 6:

[0081] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[0082] Step 7:

[0083] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[0084] Step 8:

[0085] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. For example, if an applicant answers, "I majored in computer science at university and have experience in many projects using Python," the AI ​​model will evaluate them as "having strong programming skills."

[0086] Step 9:

[0087] After the interview is over, all questions, answers, and evaluation results are sent from the terminal to the server and stored in a database.

[0088] Step 10:

[0089] The user, a company employee, logs in to the system and checks the saved evaluation results and interview records. Based on this, the user makes a final decision.

[0090] Step 11:

[0091] If necessary, the user can schedule a reassessment or re-interview and issue a new notification. Reassessments and re-interviews follow a similar process.

[0092] Example 1

[0093] 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."

[0094] In the traditional recruitment interview process, evaluations often vary and are biased because they depend on the interviewer's subjective judgment, creating the risk of unfair hiring decisions. Furthermore, preparing for interviews and managing schedules requires a great deal of effort, making efficient operation difficult. It is necessary to resolve these issues and improve the fairness and efficiency of the recruitment process.

[0095] 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.

[0096] In this invention, the server includes a means for registering desired personalities and skills, a means for training an interactive generative AI model based on the registered personalities and skills, and a means for managing interview schedules and sending notifications when interview dates and times approach, thereby enabling a fair and efficient hiring process.

[0097] The "desired profile" refers to the characteristics and qualities of the ideal person a company wants to hire.

[0098] "Skills" refer to the knowledge and techniques required to perform a specific task or job.

[0099] An "interactive generative AI model" refers to an artificial intelligence system that automatically generates questions based on dialogue and evaluates the answers.

[0100] "Training" refers to the process of providing learning data to a system to improve its performance.

[0101] An "interview schedule" refers to the planned date, time, and duration of the interview.

[0102] "Notification" refers to a message or alert that notifies you when the designated interview date and time is approaching.

[0103] "Terminal" refers to a computer or smart device used as part of a system.

[0104] "Download" refers to the transfer of data or programs from a server to a terminal.

[0105] "Interview proceedings" refers to the series of activities in which an interviewer asks questions of an applicant, receives answers, and evaluates them.

[0106] "Real-time evaluation" means analyzing applicants' responses immediately on the spot and providing evaluation results.

[0107] "Conversation record" refers to a record of all verbal exchanges and questions and answers that took place during an interview.

[0108] "Evaluation results" refers to judgments regarding the applicant's abilities and suitability obtained through interviews.

[0109] "Final decision" refers to the interviewer or company representative making the final decision regarding employment or the next interview based on the evaluation results.

[0110] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[0111] Server-side processing

[0112] First, the user (company representative) enters the desired personality profile and skills required for the position through the system's administration screen. This information is stored in a database. Examples of registered skills include "communication skills," "problem-solving skills," and "programming skills (Python)." The server then trains an AI model based on the stored personality profile and skill data, utilizing past interview data and existing employee profiles. Machine learning frameworks such as TensorFlow and PyTorch are used for training. Once training is complete, the server builds and saves an interactive generative AI model with the optimal question set and evaluation criteria. The server also receives the interview schedule set by the user and saves it in a database. As the interview date and time approaches, the server automatically sends reminder emails to applicants and interviewers.

[0113] Terminal side processing

[0114] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. After downloading, the device conducts the interview based on the AI ​​model. During the interview, the device displays questions set by the AI ​​model to the applicant, such as "Please tell us about yourself" or "Tell us about projects you have worked on in the past." When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. As a specific example of evaluation, if an applicant answers, "I majored in computer science at university and have worked on many projects using Python," the AI ​​model will evaluate the applicant as having "high programming skills." After the interview is over, the device sends all questions, answers, and evaluation results to the server and stores them in a database.

[0115] User processing

[0116] The user, a company representative, logs in to the system and checks the evaluation results and interview records stored on the server. The user then looks at the saved conversation records and the evaluation results from the AI ​​model and makes a final decision on hiring or the next interview. If necessary, they can also schedule a re-evaluation or re-interview.

[0117] Specific examples

[0118] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's suitability in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[0119] Prompt Sentence Examples

[0120] Here are some example prompts for a generative AI model:

[0121] "Please ask applicants the following questions and evaluate their answers: 1. Please introduce yourself. 2. Please tell us about a project you have worked on in the past. 3. Please tell us more about your experience working on a project using Python."

[0122] Based on this prompt, the AI ​​model generates appropriate questions and evaluates the applicant's answers.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] A user logs into the system and enters the desired personality profile and skills.

[0126] Specific operations: Company representatives access the system's administration screen, enter information such as "communication skills," "problem-solving skills," and "programming skills (Python)," and click the "Register" button.

[0127] Input: Information about the desired personality and skills

[0128] Output: Personality and skill information stored in a database

[0129] Step 2:

[0130] The server trains an interactive generative AI model based on the input personality and skill data.

[0131] How it works: The server retrieves personality and skill data from the database and combines it with past interview data and existing employee profiles. It trains the system using TensorFlow and PyTorch.

[0132] Input: Profiles in the database, skill data, past interview data

[0133] Output: A trained interactive generative AI model

[0134] Step 3:

[0135] The user schedules the interview.

[0136] Specific operation: The user logs in to the system, specifies the date and time of the interview, and clicks the "Save" button.

[0137] Input: Interview date and time

[0138] Output: Schedules saved in the database

[0139] Step 4:

[0140] The server prepares and sends the reminder notification.

[0141] Specific operation: When the interview date and time approaches, the server automatically sends a reminder email to the applicant and interviewer.

[0142] Input: Interview schedules in the database

[0143] Output: Reminder emails sent to applicants and interviewers

[0144] Step 5:

[0145] The interviewer's device downloads the latest interactive generative AI model from the server.

[0146] Specific operation: When the interviewer clicks the "Start interview" button, the device connects to the server and downloads the latest AI model.

[0147] Input: Interviewer request

[0148] Output: AI model downloaded to the device

[0149] Step 6:

[0150] During the interview, the device displays questions to the applicant based on the AI ​​model.

[0151] What it does: The device will ask questions such as "Tell us about yourself" and "Tell us about some of the projects you've worked on in the past."

[0152] Input: A trained AI model

[0153] Output: Questions shown to applicants

[0154] Step 7:

[0155] The interviewer enters the applicant's answers into the device, and the AI ​​model evaluates them in real time.

[0156] How it works: Interviewers input the applicant's answers, and the AI ​​model analyzes and evaluates the answers in real time. For example, an answer like "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[0157] Input: Applicant's response

[0158] Output: Real-time evaluation results

[0159] Step 8:

[0160] After the interview is over, all questions, answers, and evaluation results are sent to the server and saved.

[0161] Specific operation: When the interview is over, the interviewer clicks the "End interview" button, and the device sends the data to the server, which stores it in the database.

[0162] Input: All questions and answers, evaluation results

[0163] Output: Interview notes stored in a database

[0164] Step 9:

[0165] The user reviews the evaluation results and interview records and makes the final decision.

[0166] Specific operation: The user logs in to the system and selects the "Interview Record" menu to check the evaluation results and conversation records.

[0167] Input: Interview records and evaluation results in the database

[0168] Output: User's final decision

[0169] (Application example 1)

[0170] 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."

[0171] In the recruitment interview process, there is a problem of variability and bias in evaluations, making it difficult to make fair and efficient hiring decisions. Self-driving vehicles also require a method to respond quickly and accurately to user questions and emergency situations. The purpose of this invention is to provide a system using an interactive generative AI model to solve these problems.

[0172] 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.

[0173] In this invention, the server includes means for registering a desired personality profile and skills, means for training an interactive generative AI model based on the registered personality profile and skills, means for managing an interview schedule and sending a notification when the interview date and time approaches, means for conducting the interview based on the generated AI model, means for inputting the applicant's answers and having the AI ​​model evaluate them in real time, means for saving all conversation records and evaluation results of the interview, means for checking the saved records and making a final decision based on the evaluation results, means for providing operation assistance for the autonomous vehicle and responding to inquiries from users, means for setting a destination and providing route guidance, and means for generating responses to questions during operation. This makes it possible to reduce variability and bias in evaluations in the employment interview process and improve user support in autonomous vehicles.

[0174] "Desired profile" refers to the ideal person a company is looking for in a job interview, as well as the characteristics and skills required for a specific role.

[0175] "Skills" are the abilities and knowledge required to perform a specific job or role.

[0176] An "interactive generative artificial intelligence model" is an artificial intelligence model that assists with specific tasks by generating answers and responses through dialogue with the user.

[0177] "Interview schedule" refers to information for managing schedules such as interview dates, times, and locations.

[0178] A "notification" is a message or signal sent to inform a user of specific information or events.

[0179] An "interview" is a conversation with an applicant that takes place as part of the recruitment process.

[0180] An "applicant" is a person who applies for a particular job or position.

[0181] "Answer" means a response given by an applicant to a question.

[0182] "Real-time evaluation" means that the user's input and actions are evaluated immediately.

[0183] "Conversation recording" means recording the content of conversations that take place during interviews or dialogues.

[0184] "Evaluation results" refer to the results of the evaluation generated based on the applicant's responses and actions.

[0185] "Final judgment" refers to the final decision made based on the evaluation results.

[0186] An "autonomous vehicle" is a vehicle whose driving operations are automated.

[0187] "Operation assistance" refers to providing support to maintain the safety and comfort of users when operating an autonomous vehicle.

[0188] "Inquiry handling" means responding to questions or requests from users.

[0189] "Destination setting" refers to the act of inputting the location the user wants to reach into the system.

[0190] "Route guidance" refers to showing the optimal route to reach a destination.

[0191] A "question" is a question or request from a user.

[0192] A "response" is a response or response that a system gives to a question.

[0193] "Emergency response" means taking immediate and appropriate action in an emergency situation.

[0194] This invention is a system that uses an interactive generative AI model to streamline corporate recruitment interview processes and autonomous vehicle operation support, providing a fair and safe environment. The invention operates in cooperation between a server, terminals, and users, and realizes the system through each step.

[0195] Server-side processing

[0196] The server is responsible for the main data processing and training of the AI ​​model. The specific processing contents are as follows:

[0197] 1. Registering the desired profile and skills

[0198] The user, a company representative, enters the desired personality profile and necessary skills through the system's management screen.

[0199] For example, "communication skills" and "programming skills (Python)" are registered.

[0200] 2. Training an interactive generative AI model

[0201] The server trains the AI ​​model based on the registered data, including past interview data and existing employee profiles.

[0202] Once trained, the AI ​​model will have an optimal set of questions and evaluation criteria.

[0203] 3. Managing interview schedules

[0204] The system saves the interview schedule set in the database, generates notifications when the interview date and time approaches, and sends reminder emails to applicants and interviewers.

[0205] 4. Operational assistance for autonomous vehicles

[0206] The server uses an interactive generative AI model to calculate the optimal route based on the destination information set by the user.

[0207] It generates appropriate responses to real-time questions from the user and presents them through the touchscreen and speakers inside the car.

[0208] Terminal side processing

[0209] The terminal provides an execution environment for the interview process and autonomous driving support. The specific processing content is as follows:

[0210] 1. Download the AI ​​model

[0211] At the start of an interview or when the self-driving vehicle begins operation, the device downloads the latest interactive generative AI model from the server.

[0212] 2. Interview progress and real-time evaluation

[0213] During the interview, the AI ​​model generates questions and presents them to the applicant, who then enters their answers into a device, which then evaluates them in real time.

[0214] For example, if someone answers, "I majored in computer science at university and have worked on numerous projects using Python," they will be evaluated as having "high programming skills."

[0215] 3. Autonomous driving support

[0216] It provides users with destination setting and route guidance, and generates appropriate responses depending on the situation during driving.

[0217] For example, if the user asks "Where is the next rest stop?", the response will be "The next rest stop is 10km away."

[0218] 4. Emergency Response

[0219] In the event of an emergency, the system will present the user with appropriate countermeasures.

[0220] For example, in response to a query such as "I've been in an accident," the system responds with "Please call the police. Please check the condition of your vehicle."

[0221] User processing

[0222] Users operate and use the system as company personnel and autonomous vehicle users. The specific processing is as follows:

[0223] 1. Review of evaluation results and interview records

[0224] Company representatives log into the system, check the evaluation results and interview records, and make a final decision.

[0225] Reassessments and re-interviews can be scheduled as needed.

[0226] 2. Route guidance and real-time response

[0227] Users of self-driving vehicles can set their destination through the system and receive responses to questions during the journey.

[0228] Hardware and software used

[0229] Hardware: Touchscreen, microphone, speaker, database server, traffic control system

[0230] Software: Python, OpenAI GPT-3 API, Database Management System

[0231] Examples of explanatory text and prompts

[0232] Destination settings:

[0233] Input: User enters "I want to go to Ginza"

[0234] Processing result: Confirm the optimal route, "Proposed route: Go through XX to reach Ginza"

[0235] Inquiry response:

[0236] Input: User asks "Where is the next rest stop?"

[0237] Processing result: "The next rest stop is 10km away"

[0238] Prompt Sentence Examples

[0239] Destination setting: "The user has set Ginza as their destination. Please suggest the best route."

[0240] Question Response: "Generate an answer to the user's question: 'Where is the next rest stop?'"

[0241] Emergency Response: "Emergency: I've been in an accident. What is the appropriate response?"

[0242] In this way, we will realize a system that integrates the job interview process with autonomous vehicle operation support, improving evaluation fairness and user safety.

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] The server receives the desired personality profile and skills from the user, a company representative. Specifically, the company representative registers information such as "communication skills" and "programming skills (Python)" through the system's management screen. This input data is saved in a database on the server.

[0246] Step 2:

[0247] The server trains a generative conversational AI model based on stored data on desired personalities and skills, including past interview data and existing employee profiles. Input data includes past interview transcripts and employee profiles, and the AI ​​model generates an optimal set of questions and evaluation criteria based on this data.

[0248] Step 3:

[0249] The server manages interview schedules and generates notifications when the interview date and time approaches. The configured interview schedule is used as input, and reminder emails are sent to applicants and interviewers at the specified date and time. The output is the sending of reminder emails.

[0250] Step 4:

[0251] At the start of an interview, the device downloads the latest interactive generative AI model from the server. The input is the latest AI model stored on the server, and the download prepares the device for conducting the interview. The output is the model, which can be used.

[0252] Step 5:

[0253] During the interview, the device displays questions generated by the AI ​​model to the applicant and the applicant inputs their answers. Specifically, questions such as "Please introduce yourself" and "Tell us about your university project" are displayed. The applicant's answers are entered into the device as input, and a real-time evaluation is performed. The output is an evaluation result of the answers.

[0254] Step 6:

[0255] The device records the entire interview process, and sends all questions, answers, and evaluation results to the server, where they are stored in a database. The input includes the recorded conversation data, which is sent to the server and stored. The output is the saved conversation record and evaluation results.

[0256] Step 7:

[0257] The user, a company employee, logs into the system and checks the saved evaluation results and interview records. The saved data is used as input, and a final decision is made based on the evaluation results. The final decision is obtained as output.

[0258] Step 8:

[0259] The server calculates the optimal route based on the destination information set to assist in the operation of the autonomous vehicle and respond to inquiries from the user. The destination information set by the user is used as input, and the optimal route is generated as output.

[0260] Step 9:

[0261] The device uses a generative interactive AI model to generate responses to questions posed by the user while driving. Specifically, the question "Where is the next rest stop?" is used as input, and the device generates the response "The next rest stop is 10 km away." The response is then displayed as output.

[0262] Step 10:

[0263] When an emergency occurs, the device accepts inquiries from the user and uses a generative conversational AI model to suggest appropriate countermeasures. The details of the emergency are used as input, and in response to an inquiry such as "I've been in an accident," a response is generated such as "Please call the police. Please check the condition of your vehicle." The output is the emergency countermeasures.

[0264] 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.

[0265] This invention is an interview assistant system that combines an emotion engine with an interactive generative AI model to compensate for interviewer biases and skill deficiencies and make efficient and fair hiring decisions during corporate recruitment interviews. This system operates in cooperation with a server, terminal, user, and emotion engine, managing and executing the interview process through multiple steps.

[0266] Server-side processing

[0267] 1. Registering the desired profile and skills

[0268] Corporate users use the system's administration screen to input the desired profile and skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[0269] 2. Training an interactive generative AI model

[0270] The server stores the registered data in a database and uses it to train an AI model, combining it with past interview data and existing employee profiles. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[0271] 3. Managing interview schedules

[0272] When a user sets an interview schedule in the system, the server saves and manages the schedule in a database, and sends reminder notifications to applicants and interviewers as the interview date and time approaches.

[0273] Terminal side processing

[0274] 1. Download the AI ​​model

[0275] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[0276] 2. Interview process

[0277] The interview begins based on questions from the AI ​​model displayed on the interviewer's device, such as "Please introduce yourself."

[0278] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[0279] 3. Real-time evaluation

[0280] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[0281] 4. Conversation Recording and Emotional Data Storage

[0282] After the interview is over, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[0283] User processing

[0284] 1. Review of evaluation results and interview records

[0285] The user, a company employee, logs in to the system and checks the evaluation results, interview records, and emotional data stored on the server. Based on this, the final decision is made. For example, referring to the interview records and emotional data, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[0286] 2. Schedule a reassessment and re-interview

[0287] If necessary, the user can schedule a reassessment or re-interview and notifications will be sent out again accordingly.

[0288] Specific examples

[0289] For example, if a company is looking to hire a software engineer with leadership skills, the company representative would register the desired skills, such as "leadership," "programming skills (Python)," and "communication skills," in the system. During the interview, the AI ​​model would display questions such as "Please give us a specific example of a time when you demonstrated leadership," and the emotion engine would evaluate the applicant's confidence and sincerity in real time. After the interview, all data is saved, and the company representative would make the final hiring decision while referring to the evaluation results and emotion data. In this way, the present invention is a system that minimizes interviewer bias and enables more accurate talent evaluation.

[0290] The processing flow will be explained below.

[0291] Step 1:

[0292] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[0293] Step 2:

[0294] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[0295] Step 3:

[0296] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training, the AI ​​model will have the optimal set of questions and evaluation criteria.

[0297] Step 4:

[0298] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[0299] Step 5:

[0300] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[0301] Step 6:

[0302] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[0303] Step 7:

[0304] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[0305] Step 8:

[0306] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[0307] Step 9:

[0308] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[0309] Step 10:

[0310] After the interview, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[0311] Step 11:

[0312] The user, a company employee, logs into the system and checks the saved evaluation results, interview records, and emotional data. Based on this, the final decision is made. For example, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[0313] Step 12:

[0314] If necessary, the user can schedule a reassessment or re-interview, and the server will then issue a new notification to conduct the reassessment or re-interview.

[0315] Example 2

[0316] 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."

[0317] In corporate recruitment interviews, interviewer bias and lack of skills can affect hiring decisions, making it difficult to conduct efficient and fair talent evaluations. It is also difficult to properly evaluate applicants' emotions and non-verbal signals during the interview process. To solve these problems, an interview assistant system combining a dialogue-generating AI model and an emotion engine is needed.

[0318] 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.

[0319] In this invention, the server includes: means for registering desired personalities and skills; means for training an interactive generative AI model based on the registered personalities and skills; means for managing interview schedules and sending notifications when the interview date and time approaches; means for conducting interviews based on the generated AI model; means for inputting applicant responses and having the AI ​​model evaluate them in real time; means for analyzing the applicant's facial expressions, tone of voice, and content of speech in real time using an emotion engine during the interview to generate emotion data; means for saving all conversation records, evaluation results, and emotion data from the interview; and means for reviewing the saved records and making a final decision based on the evaluation results. This compensates for interviewer biases and skill deficiencies, enabling more efficient and fair hiring decisions. The emotion engine also takes applicants' non-verbal signals into account in the evaluation, achieving a more comprehensive talent evaluation.

[0320] 1. "Desired personality and skills" refers to the specific characteristics and abilities that companies seek in job applicants during job interviews.

[0321] 2. "Interactive generative AI model" refers to a model that uses AI technology to engage in two-way communication and automatically generate and evaluate applicants' responses.

[0322] 3. The "Emotion Engine" is a system that analyzes applicants' facial expressions, tone of voice, and speech content in real time to generate emotional data.

[0323] 4. "Interview schedule" refers to the interview date and time set by the company and participant information.

[0324] 5. "Notification" refers to reminders and confirmation messages sent to applicants and interviewers as the interview date and time approaches.

[0325] 6. "Interview Conduct" is the process of conducting an interview using an interactive generative artificial intelligence model.

[0326] 7. "Applicant Responses" refers to the information and opinions provided by the applicant during the interview.

[0327] 8. "Real-time evaluation" refers to the process in which a machine learning model instantly analyzes and evaluates applicants' responses.

[0328] 9. "Conversation records" refer to data that records questions and answers exchanged during an interview and the statements made by the applicant.

[0329] 10. "Evaluation Results" refers to the evaluation information of applicants generated by the interactive generative artificial intelligence model and emotion engine.

[0330] 11. "Arrangement of reassessment or reinterview" refers to the process of scheduling additional assessments or interviews based on the results of existing assessments.

[0331] 12. "Report" refers to a document prepared based on the applicant's evaluation results and emotional data.

[0332] The present invention provides an interview assistant system that combines an interactive generative AI model and an emotion engine to support efficient and fair hiring decisions in corporate job interviews. The following describes an embodiment of the system in detail.

[0333] System Configuration

[0334] server

[0335] 1. Registering the desired profile and skills

[0336] The user, a company representative, accesses the management screen through a browser and inputs the desired profile and skills. Examples of input include "communication skills," "problem-solving skills," and "Python programming skills."

[0337] The server stores this information in a database and performs verification processing to maintain data consistency as necessary.

[0338] 2. Training an interactive generative AI model

[0339] The server uses the registered data, past interview data, and existing employee profiles to train an AI model using machine learning libraries such as TensorFlow and PyTorch.

[0340] As a result of training, the AI ​​model will have an optimal set of questions and evaluation criteria.

[0341] 3. Managing interview schedules

[0342] The user sets the interview date and time and participant information through the calendar. The set information is saved on the server, and when the interview date and time approaches, a reminder notification is sent via email or SMS.

[0343] Terminal

[0344] 1. Download the AI ​​model

[0345] On the day of the interview, the interviewer's device downloads the latest AI model from the server, the file is sent via an HTTP request, and the model is installed on the device.

[0346] 2. Interview process

[0347] Questions generated by the AI ​​model are displayed on the device, and questions such as "Please introduce yourself" are displayed on the interviewer's screen.

[0348] During the interview, the device's camera and microphone are used to capture the applicant's facial expressions and tone of voice, which are then analyzed in real time by an emotion engine to generate emotional data.

[0349] 3. Real-time evaluation

[0350] When the interviewer types the applicant's answers into the device, the AI ​​model analyzes the answers and evaluates them based on keywords and sentiment data. For example, an answer such as "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[0351] 4. Conversation Recording and Emotional Data Storage

[0352] After the interview is over, all questions, answers, evaluation results, and emotional data are sent from the device to the server, and these are stored in a database.

[0353] User

[0354] 1. Review of evaluation results and interview records

[0355] Users can log in to the system and check the saved evaluation results and interview records. They make a final decision based on the detailed data.

[0356] 2. Schedule a reassessment and re-interview

[0357] Users can schedule reassessments and re-interviews, and once the schedule is set up, notifications are sent to applicants and interviewers.

[0358] Specific examples

[0359] This section describes a case where a company is looking to hire a software engineer with leadership skills.

[0360] Input content: Company representatives register skills such as "leadership," "Python programming skills," and "communication skills" in the system.

[0361] Interview Progress: On the day of the interview, the device displays questions such as, "Please give us a specific example of a time when you demonstrated leadership," while the emotion engine evaluates the candidate's confidence and sincerity in real time.

[0362] Reviewing the evaluation results: After the interview, company personnel can refer to the evaluation results and sentiment data and make an overall assessment, for example, "This applicant has strong leadership abilities and technical skills."

[0363] Prompt Sentence Examples

[0364] Below are some examples of prompts to input to the generative AI model.

[0365] Please tell us a specific example of how you demonstrated leadership.

[0366] "Please explain how you solved a difficult problem using past experience."

[0367] "Please tell us about your role and accomplishments in Python projects."

[0368] The present invention provides a system that supports efficient and fair hiring decisions through these settings.

[0369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0370] Step 1:

[0371] Registering the desired profile and skills

[0372] The user, a company representative, accesses the system's administration screen through a browser and enters the desired personality profile and skills. For example, the user enters information such as "communication skills," "problem-solving skills," and "Python programming skills" into the form and clicks the register button. The server validates this input data and saves it in the database. The input is the company representative's input, and the output is the registered data saved in the database.

[0373] Step 2:

[0374] Training interactive generative AI models

[0375] The server trains the AI ​​model based on the required skills and personality traits stored in the database, past interview data, and existing employee profiles. At this stage, machine learning libraries such as TensorFlow and PyTorch are used to analyze the data and optimize the model parameters. The input is the data in the database, and the output is a trained interactive generative AI model.

[0376] Step 3:

[0377] Managing interview schedules

[0378] Users log in to the system and set the interview date and time and participant information using a calendar interface. Once the settings are complete, the server saves the information in a database and sends reminder notifications to registered email addresses and phone numbers when the interview date and time approaches. The input is the user's schedule settings, and the output is the schedule information saved in the database and reminder notifications.

[0379] Step 4:

[0380] Downloading the AI ​​model

[0381] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. The device sends an HTTP request to the server, and the server responds by sending the AI ​​model file. Once the download is complete, the AI ​​model is installed on the device and it is ready to begin supporting the interview. The input is the download request to the server, and the output is the AI ​​model stored on the device.

[0382] Step 5:

[0383] Interview process

[0384] When the interview begins, questions generated by the AI ​​model are displayed on the interviewer's device. For example, a question such as "Please introduce yourself" may be selected. During the interview, the device uses its built-in camera and microphone to capture the applicant's facial expressions, tone of voice, and content of what is being said, which are then analyzed in real time by an emotion engine to generate emotional data. The input is the questions posed by the AI ​​model and the applicant's answers, and the output is the generated emotional data.

[0385] Step 6:

[0386] Real-time evaluation

[0387] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. It analyzes the applicant's answers and the emotion engine data to comprehensively evaluate an answer such as, "I majored in computer science at university and have experience in numerous projects using Python." The input is the applicant's answers and emotion data, and the output is the evaluation result.

[0388] Step 7:

[0389] Conversation recording and emotional data storage

[0390] After the interview is over, the device transmits all questions and answers, evaluation results, and emotional data to a server, which stores these data in a database for later analysis and re-evaluation. The input is all the data generated during the interview, and the output is the record stored in the database.

[0391] Step 8:

[0392] Checking evaluation results and interview records

[0393] The user, a company employee, logs in to the system and checks the saved evaluation results, interview records, and emotional data. They can also search and display the interview data of a specific applicant through the management screen, and refer to detailed information such as, "This applicant has very high confidence and problem-solving ability." The input is the saved data, and the output is the displayed evaluation results and interview records.

[0394] Step 9:

[0395] Schedule reassessments and re-interviews

[0396] If necessary, the user sets up a reassessment or re-interview. For example, if it is determined that an additional assessment is necessary based on the results of an existing assessment, the user selects the applicant for reassessment on the management screen and sets a new interview date and time. Once the setup is complete, the system sends a notification to the applicant and interviewer. The input is the reassessment setup information, and the output is the notification that was sent.

[0397] (Application example 2)

[0398] 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."

[0399] Traditional recruitment interview and sales staff training systems often suffer from issues such as bias and lack of skills on the part of interviewers and trainers, which can impair the fairness and efficiency of evaluations. Furthermore, the lack of a comprehensive evaluation system that includes the evaluation of emotions makes it difficult to accurately evaluate the aptitude and skills of applicants and staff.

[0400] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for registering required personality profiles and skills, means for training an interactive generative AI model based on the registered personality profiles and skills, means for managing schedules and sending notifications when schedules approach, means for supporting progress based on the generated AI model, means for inputting applicant responses and having the AI ​​model evaluate them in real time, means for saving the evaluated responses and results, means for checking the saved data and making a final decision based on the evaluation results, means for conducting training via a device such as a smartphone or a head-mounted display, and means for analyzing applicant emotions using an emotion engine and incorporating the emotions into the evaluation. This improves the fairness and efficiency of evaluations and enables comprehensive evaluation of the aptitude and skills of applicants and sales staff.

[0401] "Desired personality and skills" refers to the personality traits suitable for a particular job or role, as well as the specific abilities and knowledge that person should possess.

[0402] An "interactive generative artificial intelligence model" is an artificial intelligence model that generates dialogue in natural language based on input information and communicates interactively with the user.

[0403] The "means for managing schedules and sending notifications when the schedule approaches" is a system that manages a specific schedule and sends reminder notifications to the user when the date approaches.

[0404] A "processing aid" is a technique or tool provided to facilitate a particular process.

[0405] "A means for inputting applicants' responses and having an AI model evaluate them in real time" refers to a system in which applicants' responses are input into the system and the AI ​​immediately evaluates the responses.

[0406] The "means for storing evaluated answers and results" is a system for storing answers and results evaluated by artificial intelligence in a database.

[0407] "Means for reviewing stored data and making a final decision based on the evaluation results" refers to a mechanism for viewing stored data and making a final decision based on it.

[0408] "Means for conducting training via a device such as a smartphone or head-mounted display" refers to a system for conducting training using a smartphone or head-mounted display.

[0409] "Means of using an emotion engine to analyze applicants' emotions and incorporate them into the evaluation" is a system that uses technology to analyze applicants' emotions and reflects the results of that analysis in the evaluation process.

[0410] The "means for generating questions and evaluation criteria" is a mechanism for automatically generating questions for evaluating specific skills or characteristics and the criteria for how to evaluate them.

[0411] The "means for dynamically adjusting the next question" is a system that adjusts the next question in real time based on the applicant's answer.

[0412] The "means by which notifications are sent to users and raters" refers to the mechanism by which users and raters are notified of specific events or reminders.

[0413] "Means for arranging additional reassessments and rescheduling" refers to a mechanism for setting and managing reassessments and rescheduling as necessary.

[0414] This invention is a system for improving the fairness and efficiency of evaluations in corporate recruitment interviews and sales staff training in brick-and-mortar stores. This system manages and executes processes through multiple steps by interoperating with a server, terminals, users, and an emotion engine.

[0415] Server-side processing

[0416] 1. Registering target skills

[0417] The server allows users (company representatives and store managers) to enter, via the system's management screen, the profile of a suitable person for a particular job or role, as well as the specific abilities and knowledge that person should possess, such as customer service skills and product knowledge.

[0418] 2. Training an interactive generative AI model

[0419] The server stores the registered data in a database and uses it to train an AI model by combining it with past interview data, sales data, and customer feedback. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[0420] 3. Schedule management

[0421] The server stores the schedule set by the user in a database and sends reminder notifications to the evaluator and the user when the scheduled date approaches. These notifications are displayed on devices such as smartphones and head-mounted displays.

[0422] Terminal side processing

[0423] 1. Download the AI ​​model

[0424] On the day of training, the evaluator's device downloads the latest interactive generative AI model from the server, which supports the training process.

[0425] 2. Training Progression

[0426] The device will then begin training the AI ​​model based on scenarios and questions, such as, "A customer is having trouble choosing a product. As a salesperson, how would you respond?"

[0427] 3. Real-time evaluation

[0428] During training, the device uses an emotion engine to analyze the trainee's emotions in real time and generate results. When applicants or sales staff enter their answers, the AI ​​model evaluates them in real time. The emotion data generated by the emotion engine is also taken into account in the evaluation.

[0429] 4. Data storage

[0430] After the training is completed, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[0431] User processing

[0432] 1. Review of evaluation results and records

[0433] Users, such as company representatives and store managers, log in to the system, check the evaluation results and records stored on the server, and make a final decision based on this.

[0434] 2. Reevaluation and Rescheduling

[0435] If necessary, the user can reassess and reschedule and reissue the notification accordingly.

[0436] Hardware and software used

[0437] Hardware:

[0438] Smartphone

[0439] head-mounted display

[0440] software:

[0441] Interactive generative AI models: OpenAI API

[0442] Emotion Engine: Emotion Recognition Library

[0443] Specific examples

[0444] For example, when training sales staff at a store, a manager registers required skills such as "customer service skills" and "product knowledge" in the system. During training, the AI ​​model displays questions such as, "A customer is having trouble choosing a product. How would you respond as a salesperson?" and the emotion engine evaluates the staff member's response and emotions in real time. In this way, managers can evaluate staff skills with high accuracy and fairness.

[0445] Prompt Sentence Examples

[0446] "A customer is having trouble choosing a product. How would you, as a salesperson, respond?"

[0447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0448] Step 1:

[0449] The server receives input from users (company representatives or store managers) via the system's administration screen about the profile of a person suitable for a specific job or role, as well as the specific abilities and knowledge that person should possess. This obtains data on the required skills and profile, and stores this data in a database. The input in this step is the skill and profile information from the administration screen, and the output is this information stored in the database.

[0450] Step 2:

[0451] The server trains the interactive generative AI model based on the data registered in step 1. It also utilizes past interview data, sales data, and customer feedback to train the AI ​​model. This allows the AI ​​model to retain the optimal question set and evaluation criteria. The input here is skills, personality profile, and past data from the database, and the output is the fully trained AI model.

[0452] Step 3:

[0453] The server registers the schedule set by the user in the system and saves it in the database. When the set schedule approaches, a reminder notification is sent to the evaluator and user. The input is the schedule set by the user, and the output is the device information to which the notification will be sent.

[0454] Step 4:

[0455] On the day of training, the device downloads the latest interactive generative AI model from the server. The downloaded AI model assists the training process. The input here is the AI ​​model from the server, and the output is the AI ​​model downloaded to the device.

[0456] Step 5:

[0457] The device begins training based on the downloaded AI model scenario and questions. For example, a question such as, "A customer is having trouble choosing a product. How would you, as a salesperson, respond?" is displayed. The input is the question from the AI ​​model, and the output is the answer from the person being trained.

[0458] Step 6:

[0459] The device uses an emotion engine to analyze the emotions of the trainee in real time, generating emotion data such as the confidence and sincerity of the answer. The input here is the trainee's answer, and the output is the generated emotion data.

[0460] Step 7:

[0461] The device evaluates the trainee's responses and takes the generated emotional data into account in the evaluation. The AI ​​model performs the evaluation in real time and displays the results. The input is the trainee's responses and emotional data, and the output is the evaluation results.

[0462] Step 8:

[0463] After training is complete, the device sends all questions and answers, evaluation results, and emotion data to the server. The server stores this data in a database. The input is the data stored on the device, and the output is all data stored in the database.

[0464] Step 9:

[0465] The user logs into the system and checks the evaluation results and records stored on the server. Based on this, the final decision is made. The input of this step is the stored evaluation results and records, and the output is the user's final decision.

[0466] Step 10:

[0467] If necessary, the user can reevaluate or reschedule the notification and issue it again. The input here is the reevaluation or reschedule information, and the output is the schedule information to be re-notified.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] [Second embodiment]

[0472] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0473] 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.

[0474] 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).

[0475] 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.

[0476] 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.

[0477] 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).

[0478] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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.

[0483] 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."

[0484] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[0485] Server-side processing

[0486] 1. Registering the desired profile and skills

[0487] The user, a company employee, enters the desired personality profile and skills required for the position through the system's management screen.

[0488] Specifically, information such as "communication skills," "problem-solving skills," and "programming skills (Python)" is registered.

[0489] 2. Training an interactive generative AI model

[0490] The server stores the entered personality and skill data in a database.

[0491] Based on this, the server also uses past interview data and existing employee profiles to train the AI ​​model.

[0492] After completing the training, the server builds an interactive generative AI model with an optimal set of questions and evaluation criteria.

[0493] 3. Managing interview schedules

[0494] When a user sets up an interview schedule in the system, the server stores and manages the schedule in a database.

[0495] As the interview date and time approaches, the server generates a notification and sends a reminder email to the applicant and interviewer.

[0496] Terminal side processing

[0497] 1. Download the AI ​​model

[0498] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server.

[0499] After downloading, the interviewer's device will conduct the interview based on the AI ​​model.

[0500] 2. Interview progress and real-time evaluation

[0501] During the interview, the device displays questions set by the AI ​​model to the applicant.

[0502] For example, questions such as "Please introduce yourself" and "Tell us about projects you have worked on in the past" will be displayed.

[0503] Interviewers enter applicants' answers into a device, and an AI model evaluates the answers in real time.

[0504] As a specific example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," the AI ​​model will evaluate them as having "high programming skills."

[0505] 3. Saving conversation records

[0506] After the entire interview process is completed, the terminal sends all questions, answers, and evaluation results to the server and stores them in a database.

[0507] User processing

[0508] 1. Review of evaluation results and interview records

[0509] The user, a company employee, logs into the system and checks the evaluation results and interview records stored on the server.

[0510] Specifically, users will view saved conversation records and the evaluation results from the AI ​​model to make a final decision regarding hiring or the next interview.

[0511] If necessary, a reassessment or re-interview can be scheduled.

[0512] Specific examples

[0513] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's aptitude in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[0517] Step 2:

[0518] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[0519] Step 3:

[0520] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training is complete, the AI ​​model will have the optimal set of questions and evaluation criteria.

[0521] Step 4:

[0522] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[0523] Step 5:

[0524] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[0525] Step 6:

[0526] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[0527] Step 7:

[0528] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[0529] Step 8:

[0530] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. For example, if an applicant answers, "I majored in computer science at university and have experience in many projects using Python," the AI ​​model will evaluate them as "having strong programming skills."

[0531] Step 9:

[0532] After the interview is over, all questions, answers, and evaluation results are sent from the terminal to the server and stored in a database.

[0533] Step 10:

[0534] The user, a company employee, logs in to the system and checks the saved evaluation results and interview records. Based on this, the user makes a final decision.

[0535] Step 11:

[0536] If necessary, the user can schedule a reassessment or re-interview and issue a new notification. Reassessments and re-interviews follow a similar process.

[0537] Example 1

[0538] 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."

[0539] In the traditional recruitment interview process, evaluations often vary and are biased because they depend on the interviewer's subjective judgment, creating the risk of unfair hiring decisions. Furthermore, preparing for interviews and managing schedules requires a great deal of effort, making efficient operation difficult. It is necessary to resolve these issues and improve the fairness and efficiency of the recruitment process.

[0540] 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.

[0541] In this invention, the server includes a means for registering desired personalities and skills, a means for training an interactive generative AI model based on the registered personalities and skills, and a means for managing interview schedules and sending notifications when interview dates and times approach, thereby enabling a fair and efficient hiring process.

[0542] The "desired profile" refers to the characteristics and qualities of the ideal person a company wants to hire.

[0543] "Skills" refer to the knowledge and techniques required to perform a specific task or job.

[0544] An "interactive generative AI model" refers to an artificial intelligence system that automatically generates questions based on dialogue and evaluates the answers.

[0545] "Training" refers to the process of providing learning data to a system to improve its performance.

[0546] An "interview schedule" refers to the planned date, time, and duration of the interview.

[0547] "Notification" refers to a message or alert that notifies you when the designated interview date and time is approaching.

[0548] "Terminal" refers to a computer or smart device used as part of a system.

[0549] "Download" refers to the transfer of data or programs from a server to a terminal.

[0550] "Interview proceedings" refers to the series of activities in which an interviewer asks questions of an applicant, receives answers, and evaluates them.

[0551] "Real-time evaluation" means analyzing applicants' responses immediately on the spot and providing evaluation results.

[0552] "Conversation record" refers to a record of all verbal exchanges and questions and answers that took place during an interview.

[0553] "Evaluation results" refers to judgments regarding the applicant's abilities and suitability obtained through interviews.

[0554] "Final decision" refers to the interviewer or company representative making the final decision regarding employment or the next interview based on the evaluation results.

[0555] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[0556] Server-side processing

[0557] First, the user (company representative) enters the desired personality profile and skills required for the position through the system's administration screen. This information is stored in a database. Examples of registered skills include "communication skills," "problem-solving skills," and "programming skills (Python)." The server then trains an AI model based on the stored personality profile and skill data, utilizing past interview data and existing employee profiles. Machine learning frameworks such as TensorFlow and PyTorch are used for training. Once training is complete, the server builds and saves an interactive generative AI model with the optimal question set and evaluation criteria. The server also receives the interview schedule set by the user and saves it in a database. As the interview date and time approaches, the server automatically sends reminder emails to applicants and interviewers.

[0558] Terminal side processing

[0559] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. After downloading, the device conducts the interview based on the AI ​​model. During the interview, the device displays questions set by the AI ​​model to the applicant, such as "Please tell us about yourself" or "Tell us about projects you have worked on in the past." When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. As a specific example of evaluation, if an applicant answers, "I majored in computer science at university and have worked on many projects using Python," the AI ​​model will evaluate the applicant as having "high programming skills." After the interview is over, the device sends all questions, answers, and evaluation results to the server and stores them in a database.

[0560] User processing

[0561] The user, a company representative, logs in to the system and checks the evaluation results and interview records stored on the server. The user then looks at the saved conversation records and the evaluation results from the AI ​​model and makes a final decision on hiring or the next interview. If necessary, they can also schedule a re-evaluation or re-interview.

[0562] Specific examples

[0563] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's suitability in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[0564] Prompt Sentence Examples

[0565] Here are some example prompts for a generative AI model:

[0566] "Please ask applicants the following questions and evaluate their answers: 1. Please introduce yourself. 2. Please tell us about a project you have worked on in the past. 3. Please tell us more about your experience working on a project using Python."

[0567] Based on this prompt, the AI ​​model generates appropriate questions and evaluates the applicant's answers.

[0568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0569] Step 1:

[0570] A user logs into the system and enters the desired personality profile and skills.

[0571] Specific operations: Company representatives access the system's administration screen, enter information such as "communication skills," "problem-solving skills," and "programming skills (Python)," and click the "Register" button.

[0572] Input: Information about the desired personality and skills

[0573] Output: Personality and skill information stored in a database

[0574] Step 2:

[0575] The server trains an interactive generative AI model based on the input personality and skill data.

[0576] How it works: The server retrieves personality and skill data from the database and combines it with past interview data and existing employee profiles. It trains the system using TensorFlow and PyTorch.

[0577] Input: Profiles in the database, skill data, past interview data

[0578] Output: A trained interactive generative AI model

[0579] Step 3:

[0580] The user schedules the interview.

[0581] Specific operation: The user logs in to the system, specifies the date and time of the interview, and clicks the "Save" button.

[0582] Input: Interview date and time

[0583] Output: Schedules saved in the database

[0584] Step 4:

[0585] The server prepares and sends the reminder notification.

[0586] Specific operation: When the interview date and time approaches, the server automatically sends a reminder email to the applicant and interviewer.

[0587] Input: Interview schedules in the database

[0588] Output: Reminder emails sent to applicants and interviewers

[0589] Step 5:

[0590] The interviewer's device downloads the latest interactive generative AI model from the server.

[0591] Specific operation: When the interviewer clicks the "Start interview" button, the device connects to the server and downloads the latest AI model.

[0592] Input: Interviewer request

[0593] Output: AI model downloaded to the device

[0594] Step 6:

[0595] During the interview, the device displays questions to the applicant based on the AI ​​model.

[0596] What it does: The device will ask questions such as "Tell us about yourself" and "Tell us about some of the projects you've worked on in the past."

[0597] Input: A trained AI model

[0598] Output: Questions shown to applicants

[0599] Step 7:

[0600] The interviewer enters the applicant's answers into the device, and the AI ​​model evaluates them in real time.

[0601] How it works: Interviewers input the applicant's answers, and the AI ​​model analyzes and evaluates the answers in real time. For example, an answer like "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[0602] Input: Applicant's response

[0603] Output: Real-time evaluation results

[0604] Step 8:

[0605] After the interview is over, all questions, answers, and evaluation results are sent to the server and saved.

[0606] Specific operation: When the interview is over, the interviewer clicks the "End interview" button, and the device sends the data to the server, which stores it in the database.

[0607] Input: All questions and answers, evaluation results

[0608] Output: Interview notes stored in a database

[0609] Step 9:

[0610] The user reviews the evaluation results and interview records and makes the final decision.

[0611] Specific operation: The user logs in to the system and selects the "Interview Record" menu to check the evaluation results and conversation records.

[0612] Input: Interview records and evaluation results in the database

[0613] Output: User's final decision

[0614] (Application example 1)

[0615] 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."

[0616] In the recruitment interview process, there is a problem of variability and bias in evaluations, making it difficult to make fair and efficient hiring decisions. Self-driving vehicles also require a method to respond quickly and accurately to user questions and emergency situations. The purpose of this invention is to provide a system using an interactive generative AI model to solve these problems.

[0617] 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.

[0618] In this invention, the server includes means for registering a desired personality profile and skills, means for training an interactive generative AI model based on the registered personality profile and skills, means for managing an interview schedule and sending a notification when the interview date and time approaches, means for conducting the interview based on the generated AI model, means for inputting the applicant's answers and having the AI ​​model evaluate them in real time, means for saving all conversation records and evaluation results of the interview, means for checking the saved records and making a final decision based on the evaluation results, means for providing operation assistance for the autonomous vehicle and responding to inquiries from users, means for setting a destination and providing route guidance, and means for generating responses to questions during operation. This makes it possible to reduce variability and bias in evaluations in the employment interview process and improve user support in autonomous vehicles.

[0619] "Desired profile" refers to the ideal person a company is looking for in a job interview, as well as the characteristics and skills required for a specific role.

[0620] "Skills" are the abilities and knowledge required to perform a specific job or role.

[0621] An "interactive generative artificial intelligence model" is an artificial intelligence model that assists with specific tasks by generating answers and responses through dialogue with the user.

[0622] "Interview schedule" refers to information for managing schedules such as interview dates, times, and locations.

[0623] A "notification" is a message or signal sent to inform a user of specific information or events.

[0624] An "interview" is a conversation with an applicant that takes place as part of the recruitment process.

[0625] An "applicant" is a person who applies for a particular job or position.

[0626] "Answer" means a response given by an applicant to a question.

[0627] "Real-time evaluation" means that the user's input and actions are evaluated immediately.

[0628] "Conversation recording" means recording the content of conversations that take place during interviews or dialogues.

[0629] "Evaluation results" refer to the results of the evaluation generated based on the applicant's responses and actions.

[0630] "Final judgment" refers to the final decision made based on the evaluation results.

[0631] An "autonomous vehicle" is a vehicle whose driving operations are automated.

[0632] "Operation assistance" refers to providing support to maintain the safety and comfort of users when operating an autonomous vehicle.

[0633] "Inquiry handling" means responding to questions or requests from users.

[0634] "Destination setting" refers to the act of inputting the location the user wants to reach into the system.

[0635] "Route guidance" refers to showing the optimal route to reach a destination.

[0636] A "question" is a question or request from a user.

[0637] A "response" is a response or response that a system gives to a question.

[0638] "Emergency response" means taking immediate and appropriate action in an emergency situation.

[0639] This invention is a system that uses an interactive generative AI model to streamline corporate recruitment interview processes and autonomous vehicle operation support, providing a fair and safe environment. The invention operates in cooperation between a server, terminals, and users, and realizes the system through each step.

[0640] Server-side processing

[0641] The server is responsible for the main data processing and training of the AI ​​model. The specific processing contents are as follows:

[0642] 1. Registering the desired profile and skills

[0643] The user, a company representative, enters the desired personality profile and necessary skills through the system's management screen.

[0644] For example, "communication skills" and "programming skills (Python)" are registered.

[0645] 2. Training an interactive generative AI model

[0646] The server trains the AI ​​model based on the registered data, including past interview data and existing employee profiles.

[0647] Once trained, the AI ​​model will have an optimal set of questions and evaluation criteria.

[0648] 3. Managing interview schedules

[0649] The system saves the interview schedule set in the database, generates notifications when the interview date and time approaches, and sends reminder emails to applicants and interviewers.

[0650] 4. Operational assistance for autonomous vehicles

[0651] The server uses an interactive generative AI model to calculate the optimal route based on the destination information set by the user.

[0652] It generates appropriate responses to real-time questions from the user and presents them through the touchscreen and speakers inside the car.

[0653] Terminal side processing

[0654] The terminal provides an execution environment for the interview process and autonomous driving support. The specific processing content is as follows:

[0655] 1. Download the AI ​​model

[0656] At the start of an interview or when the self-driving vehicle begins operation, the device downloads the latest interactive generative AI model from the server.

[0657] 2. Interview progress and real-time evaluation

[0658] During the interview, the AI ​​model generates questions and presents them to the applicant, who then enters their answers into a device, which then evaluates them in real time.

[0659] For example, if someone answers, "I majored in computer science at university and have worked on numerous projects using Python," they will be evaluated as having "high programming skills."

[0660] 3. Autonomous driving support

[0661] It provides users with destination setting and route guidance, and generates appropriate responses depending on the situation during driving.

[0662] For example, if the user asks "Where is the next rest stop?", the response will be "The next rest stop is 10km away."

[0663] 4. Emergency Response

[0664] In the event of an emergency, the system will present the user with appropriate countermeasures.

[0665] For example, in response to a query such as "I've been in an accident," the system responds with "Please call the police. Please check the condition of your vehicle."

[0666] User processing

[0667] Users operate and use the system as company personnel and autonomous vehicle users. The specific processing is as follows:

[0668] 1. Review of evaluation results and interview records

[0669] Company representatives log into the system, check the evaluation results and interview records, and make a final decision.

[0670] Reassessments and re-interviews can be scheduled as needed.

[0671] 2. Route guidance and real-time response

[0672] Users of self-driving vehicles can set their destination through the system and receive responses to questions during the journey.

[0673] Hardware and software used

[0674] Hardware: Touchscreen, microphone, speaker, database server, traffic control system

[0675] Software: Python, OpenAI GPT-3 API, Database Management System

[0676] Examples of explanatory text and prompts

[0677] Destination settings:

[0678] Input: User enters "I want to go to Ginza"

[0679] Processing result: Confirm the optimal route, "Proposed route: Go through XX to reach Ginza"

[0680] Inquiry response:

[0681] Input: User asks "Where is the next rest stop?"

[0682] Processing result: "The next rest stop is 10km away"

[0683] Prompt Sentence Examples

[0684] Destination setting: "The user has set Ginza as their destination. Please suggest the best route."

[0685] Question Response: "Generate an answer to the user's question: 'Where is the next rest stop?'"

[0686] Emergency Response: "Emergency: I've been in an accident. What is the appropriate response?"

[0687] In this way, we will realize a system that integrates the job interview process with autonomous vehicle operation support, improving evaluation fairness and user safety.

[0688] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0689] Step 1:

[0690] The server receives the desired personality profile and skills from the user, a company representative. Specifically, the company representative registers information such as "communication skills" and "programming skills (Python)" through the system's management screen. This input data is saved in a database on the server.

[0691] Step 2:

[0692] The server trains a generative conversational AI model based on stored data on desired personalities and skills, including past interview data and existing employee profiles. Input data includes past interview transcripts and employee profiles, and the AI ​​model generates an optimal set of questions and evaluation criteria based on this data.

[0693] Step 3:

[0694] The server manages interview schedules and generates notifications when the interview date and time approaches. The configured interview schedule is used as input, and reminder emails are sent to applicants and interviewers at the specified date and time. The output is the sending of reminder emails.

[0695] Step 4:

[0696] At the start of an interview, the device downloads the latest interactive generative AI model from the server. The input is the latest AI model stored on the server, and the download prepares the device for conducting the interview. The output is the model, which can be used.

[0697] Step 5:

[0698] During the interview, the device displays questions generated by the AI ​​model to the applicant and the applicant inputs their answers. Specifically, questions such as "Please introduce yourself" and "Tell us about your university project" are displayed. The applicant's answers are entered into the device as input, and a real-time evaluation is performed. The output is an evaluation result of the answers.

[0699] Step 6:

[0700] The device records the entire interview process, and sends all questions, answers, and evaluation results to the server, where they are stored in a database. The input includes the recorded conversation data, which is sent to the server and stored. The output is the saved conversation record and evaluation results.

[0701] Step 7:

[0702] The user, a company employee, logs into the system and checks the saved evaluation results and interview records. The saved data is used as input, and a final decision is made based on the evaluation results. The final decision is obtained as output.

[0703] Step 8:

[0704] The server calculates the optimal route based on the destination information set to assist in the operation of the autonomous vehicle and respond to inquiries from the user. The destination information set by the user is used as input, and the optimal route is generated as output.

[0705] Step 9:

[0706] The device uses a generative interactive AI model to generate responses to questions posed by the user while driving. Specifically, the question "Where is the next rest stop?" is used as input, and the device generates the response "The next rest stop is 10 km away." The response is then displayed as output.

[0707] Step 10:

[0708] When an emergency occurs, the device accepts inquiries from the user and uses a generative conversational AI model to suggest appropriate countermeasures. The details of the emergency are used as input, and in response to an inquiry such as "I've been in an accident," a response is generated such as "Please call the police. Please check the condition of your vehicle." The output is the emergency countermeasures.

[0709] 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.

[0710] This invention is an interview assistant system that combines an emotion engine with an interactive generative AI model to compensate for interviewer biases and skill deficiencies and make efficient and fair hiring decisions during corporate recruitment interviews. This system operates in cooperation with a server, terminal, user, and emotion engine, managing and executing the interview process through multiple steps.

[0711] Server-side processing

[0712] 1. Registering the desired profile and skills

[0713] Corporate users use the system's administration screen to input the desired profile and skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[0714] 2. Training an interactive generative AI model

[0715] The server stores the registered data in a database and uses it to train an AI model, combining it with past interview data and existing employee profiles. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[0716] 3. Managing interview schedules

[0717] When a user sets an interview schedule in the system, the server saves and manages the schedule in a database, and sends reminder notifications to applicants and interviewers as the interview date and time approaches.

[0718] Terminal side processing

[0719] 1. Download the AI ​​model

[0720] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[0721] 2. Interview process

[0722] The interview begins based on questions from the AI ​​model displayed on the interviewer's device, such as "Please introduce yourself."

[0723] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[0724] 3. Real-time evaluation

[0725] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[0726] 4. Conversation Recording and Emotional Data Storage

[0727] After the interview is over, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[0728] User processing

[0729] 1. Review of evaluation results and interview records

[0730] The user, a company employee, logs in to the system and checks the evaluation results, interview records, and emotional data stored on the server. Based on this, the final decision is made. For example, referring to the interview records and emotional data, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[0731] 2. Schedule a reassessment and re-interview

[0732] If necessary, the user can schedule a reassessment or re-interview and notifications will be sent out again accordingly.

[0733] Specific examples

[0734] For example, if a company is looking to hire a software engineer with leadership skills, the company representative would register the desired skills, such as "leadership," "programming skills (Python)," and "communication skills," in the system. During the interview, the AI ​​model would display questions such as "Please give us a specific example of a time when you demonstrated leadership," and the emotion engine would evaluate the applicant's confidence and sincerity in real time. After the interview, all data is saved, and the company representative would make the final hiring decision while referring to the evaluation results and emotion data. In this way, the present invention is a system that minimizes interviewer bias and enables more accurate talent evaluation.

[0735] The processing flow will be explained below.

[0736] Step 1:

[0737] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[0738] Step 2:

[0739] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[0740] Step 3:

[0741] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training, the AI ​​model will have the optimal set of questions and evaluation criteria.

[0742] Step 4:

[0743] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[0744] Step 5:

[0745] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[0746] Step 6:

[0747] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[0748] Step 7:

[0749] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[0750] Step 8:

[0751] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[0752] Step 9:

[0753] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[0754] Step 10:

[0755] After the interview, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[0756] Step 11:

[0757] The user, a company employee, logs into the system and checks the saved evaluation results, interview records, and emotional data. Based on this, the final decision is made. For example, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[0758] Step 12:

[0759] If necessary, the user can schedule a reassessment or re-interview, and the server will then issue a new notification to conduct the reassessment or re-interview.

[0760] Example 2

[0761] 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."

[0762] In corporate recruitment interviews, interviewer bias and lack of skills can affect hiring decisions, making it difficult to conduct efficient and fair talent evaluations. It is also difficult to properly evaluate applicants' emotions and non-verbal signals during the interview process. To solve these problems, an interview assistant system combining a dialogue-generating AI model and an emotion engine is needed.

[0763] 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.

[0764] In this invention, the server includes: means for registering desired personalities and skills; means for training an interactive generative AI model based on the registered personalities and skills; means for managing interview schedules and sending notifications when the interview date and time approaches; means for conducting interviews based on the generated AI model; means for inputting applicant responses and having the AI ​​model evaluate them in real time; means for analyzing the applicant's facial expressions, tone of voice, and content of speech in real time using an emotion engine during the interview to generate emotion data; means for saving all conversation records, evaluation results, and emotion data from the interview; and means for reviewing the saved records and making a final decision based on the evaluation results. This compensates for interviewer biases and skill deficiencies, enabling more efficient and fair hiring decisions. The emotion engine also takes applicants' non-verbal signals into account in the evaluation, achieving a more comprehensive talent evaluation.

[0765] 1. "Desired personality and skills" refers to the specific characteristics and abilities that companies seek in job applicants during job interviews.

[0766] 2. "Interactive generative AI model" refers to a model that uses AI technology to engage in two-way communication and automatically generate and evaluate applicants' responses.

[0767] 3. The "Emotion Engine" is a system that analyzes applicants' facial expressions, tone of voice, and speech content in real time to generate emotional data.

[0768] 4. "Interview schedule" refers to the interview date and time set by the company and participant information.

[0769] 5. "Notification" refers to reminders and confirmation messages sent to applicants and interviewers as the interview date and time approaches.

[0770] 6. "Interview Conduct" is the process of conducting an interview using an interactive generative artificial intelligence model.

[0771] 7. "Applicant Responses" refers to the information and opinions provided by the applicant during the interview.

[0772] 8. "Real-time evaluation" refers to the process in which a machine learning model instantly analyzes and evaluates applicants' responses.

[0773] 9. "Conversation records" refer to data that records questions and answers exchanged during an interview and the statements made by the applicant.

[0774] 10. "Evaluation Results" refers to the evaluation information of applicants generated by the interactive generative artificial intelligence model and emotion engine.

[0775] 11. "Arrangement of reassessment or reinterview" refers to the process of scheduling additional assessments or interviews based on the results of existing assessments.

[0776] 12. "Report" refers to a document prepared based on the applicant's evaluation results and emotional data.

[0777] The present invention provides an interview assistant system that combines an interactive generative AI model and an emotion engine to support efficient and fair hiring decisions in corporate job interviews. The following describes an embodiment of the system in detail.

[0778] System Configuration

[0779] server

[0780] 1. Registering the desired profile and skills

[0781] The user, a company representative, accesses the management screen through a browser and inputs the desired profile and skills. Examples of input include "communication skills," "problem-solving skills," and "Python programming skills."

[0782] The server stores this information in a database and performs verification processing to maintain data consistency as necessary.

[0783] 2. Training an interactive generative AI model

[0784] The server uses the registered data, past interview data, and existing employee profiles to train an AI model using machine learning libraries such as TensorFlow and PyTorch.

[0785] As a result of training, the AI ​​model will have an optimal set of questions and evaluation criteria.

[0786] 3. Managing interview schedules

[0787] The user sets the interview date and time and participant information through the calendar. The set information is saved on the server, and when the interview date and time approaches, a reminder notification is sent via email or SMS.

[0788] Terminal

[0789] 1. Download the AI ​​model

[0790] On the day of the interview, the interviewer's device downloads the latest AI model from the server, the file is sent via an HTTP request, and the model is installed on the device.

[0791] 2. Interview process

[0792] Questions generated by the AI ​​model are displayed on the device, and questions such as "Please introduce yourself" are displayed on the interviewer's screen.

[0793] During the interview, the device's camera and microphone are used to capture the applicant's facial expressions and tone of voice, which are then analyzed in real time by an emotion engine to generate emotional data.

[0794] 3. Real-time evaluation

[0795] When the interviewer types the applicant's answers into the device, the AI ​​model analyzes the answers and evaluates them based on keywords and sentiment data. For example, an answer such as "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[0796] 4. Conversation Recording and Emotional Data Storage

[0797] After the interview is over, all questions, answers, evaluation results, and emotional data are sent from the device to the server, and these are stored in a database.

[0798] User

[0799] 1. Review of evaluation results and interview records

[0800] Users can log in to the system and check the saved evaluation results and interview records. They make a final decision based on the detailed data.

[0801] 2. Schedule a reassessment and re-interview

[0802] Users can schedule reassessments and re-interviews, and once the schedule is set up, notifications are sent to applicants and interviewers.

[0803] Specific examples

[0804] This section describes a case where a company is looking to hire a software engineer with leadership skills.

[0805] Input content: Company representatives register skills such as "leadership," "Python programming skills," and "communication skills" in the system.

[0806] Interview Progress: On the day of the interview, the device displays questions such as, "Please give us a specific example of a time when you demonstrated leadership," while the emotion engine evaluates the candidate's confidence and sincerity in real time.

[0807] Reviewing the evaluation results: After the interview, company personnel can refer to the evaluation results and sentiment data and make an overall assessment, for example, "This applicant has strong leadership abilities and technical skills."

[0808] Prompt Sentence Examples

[0809] Below are some examples of prompts to input to the generative AI model.

[0810] Please tell us a specific example of how you demonstrated leadership.

[0811] "Please explain how you solved a difficult problem using past experience."

[0812] "Please tell us about your role and accomplishments in Python projects."

[0813] The present invention provides a system that supports efficient and fair hiring decisions through these settings.

[0814] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0815] Step 1:

[0816] Registering the desired profile and skills

[0817] The user, a company representative, accesses the system's administration screen through a browser and enters the desired personality profile and skills. For example, the user enters information such as "communication skills," "problem-solving skills," and "Python programming skills" into the form and clicks the register button. The server validates this input data and saves it in the database. The input is the company representative's input, and the output is the registered data saved in the database.

[0818] Step 2:

[0819] Training interactive generative AI models

[0820] The server trains the AI ​​model based on the required skills and personality traits stored in the database, past interview data, and existing employee profiles. At this stage, machine learning libraries such as TensorFlow and PyTorch are used to analyze the data and optimize the model parameters. The input is the data in the database, and the output is a trained interactive generative AI model.

[0821] Step 3:

[0822] Managing interview schedules

[0823] Users log in to the system and set the interview date and time and participant information using a calendar interface. Once the settings are complete, the server saves the information in a database and sends reminder notifications to registered email addresses and phone numbers when the interview date and time approaches. The input is the user's schedule settings, and the output is the schedule information saved in the database and reminder notifications.

[0824] Step 4:

[0825] Downloading the AI ​​model

[0826] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. The device sends an HTTP request to the server, and the server responds by sending the AI ​​model file. Once the download is complete, the AI ​​model is installed on the device and it is ready to begin supporting the interview. The input is the download request to the server, and the output is the AI ​​model stored on the device.

[0827] Step 5:

[0828] Interview process

[0829] When the interview begins, questions generated by the AI ​​model are displayed on the interviewer's device. For example, a question such as "Please introduce yourself" may be selected. During the interview, the device uses its built-in camera and microphone to capture the applicant's facial expressions, tone of voice, and content of what is being said, which are then analyzed in real time by an emotion engine to generate emotional data. The input is the questions posed by the AI ​​model and the applicant's answers, and the output is the generated emotional data.

[0830] Step 6:

[0831] Real-time evaluation

[0832] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. It analyzes the applicant's answers and the emotion engine data to comprehensively evaluate an answer such as, "I majored in computer science at university and have experience in numerous projects using Python." The input is the applicant's answers and emotion data, and the output is the evaluation result.

[0833] Step 7:

[0834] Conversation recording and emotional data storage

[0835] After the interview is over, the device transmits all questions and answers, evaluation results, and emotional data to a server, which stores these data in a database for later analysis and re-evaluation. The input is all the data generated during the interview, and the output is the record stored in the database.

[0836] Step 8:

[0837] Checking evaluation results and interview records

[0838] The user, a company employee, logs in to the system and checks the saved evaluation results, interview records, and emotional data. They can also search and display the interview data of a specific applicant through the management screen, and refer to detailed information such as, "This applicant has very high confidence and problem-solving ability." The input is the saved data, and the output is the displayed evaluation results and interview records.

[0839] Step 9:

[0840] Schedule reassessments and re-interviews

[0841] If necessary, the user sets up a reassessment or re-interview. For example, if it is determined that an additional assessment is necessary based on the results of an existing assessment, the user selects the applicant for reassessment on the management screen and sets a new interview date and time. Once the setup is complete, the system sends a notification to the applicant and interviewer. The input is the reassessment setup information, and the output is the notification that was sent.

[0842] (Application example 2)

[0843] 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."

[0844] Traditional recruitment interview and sales staff training systems often suffer from issues such as bias and lack of skills on the part of interviewers and trainers, which can impair the fairness and efficiency of evaluations. Furthermore, the lack of a comprehensive evaluation system that includes the evaluation of emotions makes it difficult to accurately evaluate the aptitude and skills of applicants and staff.

[0845] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for registering required personality profiles and skills, means for training an interactive generative AI model based on the registered personality profiles and skills, means for managing schedules and sending notifications when schedules approach, means for supporting progress based on the generated AI model, means for inputting applicant responses and having the AI ​​model evaluate them in real time, means for saving the evaluated responses and results, means for checking the saved data and making a final decision based on the evaluation results, means for conducting training via a device such as a smartphone or a head-mounted display, and means for analyzing applicant emotions using an emotion engine and incorporating the emotions into the evaluation. This improves the fairness and efficiency of evaluations and enables comprehensive evaluation of the aptitude and skills of applicants and sales staff.

[0846] "Desired personality and skills" refers to the personality traits suitable for a particular job or role, as well as the specific abilities and knowledge that person should possess.

[0847] An "interactive generative artificial intelligence model" is an artificial intelligence model that generates dialogue in natural language based on input information and communicates interactively with the user.

[0848] The "means for managing schedules and sending notifications when the schedule approaches" is a system that manages a specific schedule and sends reminder notifications to the user when the date approaches.

[0849] A "processing aid" is a technique or tool provided to facilitate a particular process.

[0850] "A means for inputting applicants' responses and having an AI model evaluate them in real time" refers to a system in which applicants' responses are input into the system and the AI ​​immediately evaluates the responses.

[0851] The "means for storing evaluated answers and results" is a system for storing answers and results evaluated by artificial intelligence in a database.

[0852] "Means for reviewing stored data and making a final decision based on the evaluation results" refers to a mechanism for viewing stored data and making a final decision based on it.

[0853] "Means for conducting training via a device such as a smartphone or head-mounted display" refers to a system for conducting training using a smartphone or head-mounted display.

[0854] "Means of using an emotion engine to analyze applicants' emotions and incorporate them into the evaluation" is a system that uses technology to analyze applicants' emotions and reflects the results of that analysis in the evaluation process.

[0855] The "means for generating questions and evaluation criteria" is a mechanism for automatically generating questions for evaluating specific skills or characteristics and the criteria for how to evaluate them.

[0856] The "means for dynamically adjusting the next question" is a system that adjusts the next question in real time based on the applicant's answer.

[0857] The "means by which notifications are sent to users and raters" refers to the mechanism by which users and raters are notified of specific events or reminders.

[0858] "Means for arranging additional reassessments and rescheduling" refers to a mechanism for setting and managing reassessments and rescheduling as necessary.

[0859] This invention is a system for improving the fairness and efficiency of evaluations in corporate recruitment interviews and sales staff training in brick-and-mortar stores. This system manages and executes processes through multiple steps by interoperating with a server, terminals, users, and an emotion engine.

[0860] Server-side processing

[0861] 1. Registering target skills

[0862] The server allows users (company representatives and store managers) to enter, via the system's management screen, the profile of a suitable person for a particular job or role, as well as the specific abilities and knowledge that person should possess, such as customer service skills and product knowledge.

[0863] 2. Training an interactive generative AI model

[0864] The server stores the registered data in a database and uses it to train an AI model by combining it with past interview data, sales data, and customer feedback. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[0865] 3. Schedule management

[0866] The server stores the schedule set by the user in a database and sends reminder notifications to the evaluator and the user when the scheduled date approaches. These notifications are displayed on devices such as smartphones and head-mounted displays.

[0867] Terminal side processing

[0868] 1. Download the AI ​​model

[0869] On the day of training, the evaluator's device downloads the latest interactive generative AI model from the server, which supports the training process.

[0870] 2. Training Progression

[0871] The device will then begin training the AI ​​model based on scenarios and questions, such as, "A customer is having trouble choosing a product. As a salesperson, how would you respond?"

[0872] 3. Real-time evaluation

[0873] During training, the device uses an emotion engine to analyze the trainee's emotions in real time and generate results. When applicants or sales staff enter their answers, the AI ​​model evaluates them in real time. The emotion data generated by the emotion engine is also taken into account in the evaluation.

[0874] 4. Data storage

[0875] After the training is completed, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[0876] User processing

[0877] 1. Review of evaluation results and records

[0878] Users, such as company representatives and store managers, log in to the system, check the evaluation results and records stored on the server, and make a final decision based on this.

[0879] 2. Reevaluation and Rescheduling

[0880] If necessary, the user can reassess and reschedule and reissue the notification accordingly.

[0881] Hardware and software used

[0882] Hardware:

[0883] Smartphone

[0884] head-mounted display

[0885] software:

[0886] Interactive generative AI models: OpenAI API

[0887] Emotion Engine: Emotion Recognition Library

[0888] Specific examples

[0889] For example, when training sales staff at a store, a manager registers required skills such as "customer service skills" and "product knowledge" in the system. During training, the AI ​​model displays questions such as, "A customer is having trouble choosing a product. How would you respond as a salesperson?" and the emotion engine evaluates the staff member's response and emotions in real time. In this way, managers can evaluate staff skills with high accuracy and fairness.

[0890] Prompt Sentence Examples

[0891] "A customer is having trouble choosing a product. How would you, as a salesperson, respond?"

[0892] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0893] Step 1:

[0894] The server receives input from users (company representatives or store managers) via the system's administration screen about the profile of a person suitable for a specific job or role, as well as the specific abilities and knowledge that person should possess. This obtains data on the required skills and profile, and stores this data in a database. The input in this step is the skill and profile information from the administration screen, and the output is this information stored in the database.

[0895] Step 2:

[0896] The server trains the interactive generative AI model based on the data registered in step 1. It also utilizes past interview data, sales data, and customer feedback to train the AI ​​model. This allows the AI ​​model to retain the optimal question set and evaluation criteria. The input here is skills, personality profile, and past data from the database, and the output is the fully trained AI model.

[0897] Step 3:

[0898] The server registers the schedule set by the user in the system and saves it in the database. When the set schedule approaches, a reminder notification is sent to the evaluator and user. The input is the schedule set by the user, and the output is the device information to which the notification will be sent.

[0899] Step 4:

[0900] On the day of training, the device downloads the latest interactive generative AI model from the server. The downloaded AI model assists the training process. The input here is the AI ​​model from the server, and the output is the AI ​​model downloaded to the device.

[0901] Step 5:

[0902] The device begins training based on the downloaded AI model scenario and questions. For example, a question such as, "A customer is having trouble choosing a product. How would you, as a salesperson, respond?" is displayed. The input is the question from the AI ​​model, and the output is the answer from the person being trained.

[0903] Step 6:

[0904] The device uses an emotion engine to analyze the emotions of the trainee in real time, generating emotion data such as the confidence and sincerity of the answer. The input here is the trainee's answer, and the output is the generated emotion data.

[0905] Step 7:

[0906] The device evaluates the trainee's responses and takes the generated emotional data into account in the evaluation. The AI ​​model performs the evaluation in real time and displays the results. The input is the trainee's responses and emotional data, and the output is the evaluation results.

[0907] Step 8:

[0908] After training is complete, the device sends all questions and answers, evaluation results, and emotion data to the server. The server stores this data in a database. The input is the data stored on the device, and the output is all data stored in the database.

[0909] Step 9:

[0910] The user logs into the system and checks the evaluation results and records stored on the server. Based on this, the final decision is made. The input of this step is the stored evaluation results and records, and the output is the user's final decision.

[0911] Step 10:

[0912] If necessary, the user can reevaluate or reschedule the notification and issue it again. The input here is the reevaluation or reschedule information, and the output is the schedule information to be re-notified.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] [Third embodiment]

[0917] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0918] 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.

[0919] 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).

[0920] 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.

[0921] 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.

[0922] 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).

[0923] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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."

[0929] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[0930] Server-side processing

[0931] 1. Registering the desired profile and skills

[0932] The user, a company employee, enters the desired personality profile and skills required for the position through the system's management screen.

[0933] Specifically, information such as "communication skills," "problem-solving skills," and "programming skills (Python)" is registered.

[0934] 2. Training an interactive generative AI model

[0935] The server stores the entered personality and skill data in a database.

[0936] Based on this, the server also uses past interview data and existing employee profiles to train the AI ​​model.

[0937] After completing the training, the server builds an interactive generative AI model with an optimal set of questions and evaluation criteria.

[0938] 3. Managing interview schedules

[0939] When a user sets up an interview schedule in the system, the server stores and manages the schedule in a database.

[0940] As the interview date and time approaches, the server generates a notification and sends a reminder email to the applicant and interviewer.

[0941] Terminal side processing

[0942] 1. Download the AI ​​model

[0943] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server.

[0944] After downloading, the interviewer's device will conduct the interview based on the AI ​​model.

[0945] 2. Interview progress and real-time evaluation

[0946] During the interview, the device displays questions set by the AI ​​model to the applicant.

[0947] For example, questions such as "Please introduce yourself" and "Tell us about projects you have worked on in the past" will be displayed.

[0948] Interviewers enter applicants' answers into a device, and an AI model evaluates the answers in real time.

[0949] As a specific example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," the AI ​​model will evaluate them as having "high programming skills."

[0950] 3. Saving conversation records

[0951] After the entire interview process is completed, the terminal sends all questions, answers, and evaluation results to the server and stores them in a database.

[0952] User processing

[0953] 1. Review of evaluation results and interview records

[0954] The user, a company employee, logs into the system and checks the evaluation results and interview records stored on the server.

[0955] Specifically, users will view saved conversation records and the evaluation results from the AI ​​model to make a final decision regarding hiring or the next interview.

[0956] If necessary, a reassessment or re-interview can be scheduled.

[0957] Specific examples

[0958] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's aptitude in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[0959] The processing flow will be explained below.

[0960] Step 1:

[0961] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[0962] Step 2:

[0963] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[0964] Step 3:

[0965] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training is complete, the AI ​​model will have the optimal set of questions and evaluation criteria.

[0966] Step 4:

[0967] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[0968] Step 5:

[0969] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[0970] Step 6:

[0971] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[0972] Step 7:

[0973] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[0974] Step 8:

[0975] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. For example, if an applicant answers, "I majored in computer science at university and have experience in many projects using Python," the AI ​​model will evaluate them as "having strong programming skills."

[0976] Step 9:

[0977] After the interview is over, all questions, answers, and evaluation results are sent from the terminal to the server and stored in a database.

[0978] Step 10:

[0979] The user, a company employee, logs in to the system and checks the saved evaluation results and interview records. Based on this, the user makes a final decision.

[0980] Step 11:

[0981] If necessary, the user can schedule a reassessment or re-interview and issue a new notification. Reassessments and re-interviews follow a similar process.

[0982] Example 1

[0983] 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."

[0984] In the traditional recruitment interview process, evaluations often vary and are biased because they depend on the interviewer's subjective judgment, creating the risk of unfair hiring decisions. Furthermore, preparing for interviews and managing schedules requires a great deal of effort, making efficient operation difficult. It is necessary to resolve these issues and improve the fairness and efficiency of the recruitment process.

[0985] 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.

[0986] In this invention, the server includes a means for registering desired personalities and skills, a means for training an interactive generative AI model based on the registered personalities and skills, and a means for managing interview schedules and sending notifications when interview dates and times approach, thereby enabling a fair and efficient hiring process.

[0987] The "desired profile" refers to the characteristics and qualities of the ideal person a company wants to hire.

[0988] "Skills" refer to the knowledge and techniques required to perform a specific task or job.

[0989] An "interactive generative AI model" refers to an artificial intelligence system that automatically generates questions based on dialogue and evaluates the answers.

[0990] "Training" refers to the process of providing learning data to a system to improve its performance.

[0991] An "interview schedule" refers to the planned date, time, and duration of the interview.

[0992] "Notification" refers to a message or alert that notifies you when the designated interview date and time is approaching.

[0993] "Terminal" refers to a computer or smart device used as part of a system.

[0994] "Download" refers to the transfer of data or programs from a server to a terminal.

[0995] "Interview proceedings" refers to the series of activities in which an interviewer asks questions of an applicant, receives answers, and evaluates them.

[0996] "Real-time evaluation" means analyzing applicants' responses immediately on the spot and providing evaluation results.

[0997] "Conversation record" refers to a record of all verbal exchanges and questions and answers that took place during an interview.

[0998] "Evaluation results" refers to judgments regarding the applicant's abilities and suitability obtained through interviews.

[0999] "Final decision" refers to the interviewer or company representative making the final decision regarding employment or the next interview based on the evaluation results.

[1000] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[1001] Server-side processing

[1002] First, the user (company representative) enters the desired personality profile and skills required for the position through the system's administration screen. This information is stored in a database. Examples of registered skills include "communication skills," "problem-solving skills," and "programming skills (Python)." The server then trains an AI model based on the stored personality profile and skill data, utilizing past interview data and existing employee profiles. Machine learning frameworks such as TensorFlow and PyTorch are used for training. Once training is complete, the server builds and saves an interactive generative AI model with the optimal question set and evaluation criteria. The server also receives the interview schedule set by the user and saves it in a database. As the interview date and time approaches, the server automatically sends reminder emails to applicants and interviewers.

[1003] Terminal side processing

[1004] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. After downloading, the device conducts the interview based on the AI ​​model. During the interview, the device displays questions set by the AI ​​model to the applicant, such as "Please tell us about yourself" or "Tell us about projects you have worked on in the past." When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. As a specific example of evaluation, if an applicant answers, "I majored in computer science at university and have worked on many projects using Python," the AI ​​model will evaluate the applicant as having "high programming skills." After the interview is over, the device sends all questions, answers, and evaluation results to the server and stores them in a database.

[1005] User processing

[1006] The user, a company representative, logs in to the system and checks the evaluation results and interview records stored on the server. The user then looks at the saved conversation records and the evaluation results from the AI ​​model and makes a final decision on hiring or the next interview. If necessary, they can also schedule a re-evaluation or re-interview.

[1007] Specific examples

[1008] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's suitability in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[1009] Prompt Sentence Examples

[1010] Here are some example prompts for a generative AI model:

[1011] "Please ask applicants the following questions and evaluate their answers: 1. Please introduce yourself. 2. Please tell us about a project you have worked on in the past. 3. Please tell us more about your experience working on a project using Python."

[1012] Based on this prompt, the AI ​​model generates appropriate questions and evaluates the applicant's answers.

[1013] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1014] Step 1:

[1015] A user logs into the system and enters the desired personality profile and skills.

[1016] Specific operations: Company representatives access the system's administration screen, enter information such as "communication skills," "problem-solving skills," and "programming skills (Python)," and click the "Register" button.

[1017] Input: Information about the desired personality and skills

[1018] Output: Personality and skill information stored in a database

[1019] Step 2:

[1020] The server trains an interactive generative AI model based on the input personality and skill data.

[1021] How it works: The server retrieves personality and skill data from the database and combines it with past interview data and existing employee profiles. It trains the system using TensorFlow and PyTorch.

[1022] Input: Profiles in the database, skill data, past interview data

[1023] Output: A trained interactive generative AI model

[1024] Step 3:

[1025] The user schedules the interview.

[1026] Specific operation: The user logs in to the system, specifies the date and time of the interview, and clicks the "Save" button.

[1027] Input: Interview date and time

[1028] Output: Schedules saved in the database

[1029] Step 4:

[1030] The server prepares and sends the reminder notification.

[1031] Specific operation: When the interview date and time approaches, the server automatically sends a reminder email to the applicant and interviewer.

[1032] Input: Interview schedules in the database

[1033] Output: Reminder emails sent to applicants and interviewers

[1034] Step 5:

[1035] The interviewer's device downloads the latest interactive generative AI model from the server.

[1036] Specific operation: When the interviewer clicks the "Start interview" button, the device connects to the server and downloads the latest AI model.

[1037] Input: Interviewer request

[1038] Output: AI model downloaded to the device

[1039] Step 6:

[1040] During the interview, the device displays questions to the applicant based on the AI ​​model.

[1041] What it does: The device will ask questions such as "Tell us about yourself" and "Tell us about some of the projects you've worked on in the past."

[1042] Input: A trained AI model

[1043] Output: Questions shown to applicants

[1044] Step 7:

[1045] The interviewer enters the applicant's answers into the device, and the AI ​​model evaluates them in real time.

[1046] How it works: Interviewers input the applicant's answers, and the AI ​​model analyzes and evaluates the answers in real time. For example, an answer like "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[1047] Input: Applicant's response

[1048] Output: Real-time evaluation results

[1049] Step 8:

[1050] After the interview is over, all questions, answers, and evaluation results are sent to the server and saved.

[1051] Specific operation: When the interview is over, the interviewer clicks the "End interview" button, and the device sends the data to the server, which stores it in the database.

[1052] Input: All questions and answers, evaluation results

[1053] Output: Interview notes stored in a database

[1054] Step 9:

[1055] The user reviews the evaluation results and interview records and makes the final decision.

[1056] Specific operation: The user logs in to the system and selects the "Interview Record" menu to check the evaluation results and conversation records.

[1057] Input: Interview records and evaluation results in the database

[1058] Output: User's final decision

[1059] (Application example 1)

[1060] 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."

[1061] In the recruitment interview process, there is a problem of variability and bias in evaluations, making it difficult to make fair and efficient hiring decisions. Self-driving vehicles also require a method to respond quickly and accurately to user questions and emergency situations. The purpose of this invention is to provide a system using an interactive generative AI model to solve these problems.

[1062] 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.

[1063] In this invention, the server includes means for registering a desired personality profile and skills, means for training an interactive generative AI model based on the registered personality profile and skills, means for managing an interview schedule and sending a notification when the interview date and time approaches, means for conducting the interview based on the generated AI model, means for inputting the applicant's answers and having the AI ​​model evaluate them in real time, means for saving all conversation records and evaluation results of the interview, means for checking the saved records and making a final decision based on the evaluation results, means for providing operation assistance for the autonomous vehicle and responding to inquiries from users, means for setting a destination and providing route guidance, and means for generating responses to questions during operation. This makes it possible to reduce variability and bias in evaluations in the employment interview process and improve user support in autonomous vehicles.

[1064] "Desired profile" refers to the ideal person a company is looking for in a job interview, as well as the characteristics and skills required for a specific role.

[1065] "Skills" are the abilities and knowledge required to perform a specific job or role.

[1066] An "interactive generative artificial intelligence model" is an artificial intelligence model that assists with specific tasks by generating answers and responses through dialogue with the user.

[1067] "Interview schedule" refers to information for managing schedules such as interview dates, times, and locations.

[1068] A "notification" is a message or signal sent to inform a user of specific information or events.

[1069] An "interview" is a conversation with an applicant that takes place as part of the recruitment process.

[1070] An "applicant" is a person who applies for a particular job or position.

[1071] "Answer" means a response given by an applicant to a question.

[1072] "Real-time evaluation" means that the user's input and actions are evaluated immediately.

[1073] "Conversation recording" means recording the content of conversations that take place during interviews or dialogues.

[1074] "Evaluation results" refer to the results of the evaluation generated based on the applicant's responses and actions.

[1075] "Final judgment" refers to the final decision made based on the evaluation results.

[1076] An "autonomous vehicle" is a vehicle whose driving operations are automated.

[1077] "Operation assistance" refers to providing support to maintain the safety and comfort of users when operating an autonomous vehicle.

[1078] "Inquiry handling" means responding to questions or requests from users.

[1079] "Destination setting" refers to the act of inputting the location the user wants to reach into the system.

[1080] "Route guidance" refers to showing the optimal route to reach a destination.

[1081] A "question" is a question or request from a user.

[1082] A "response" is a response or response that a system gives to a question.

[1083] "Emergency response" means taking immediate and appropriate action in an emergency situation.

[1084] This invention is a system that uses an interactive generative AI model to streamline corporate recruitment interview processes and autonomous vehicle operation support, providing a fair and safe environment. The invention operates in cooperation between a server, terminals, and users, and realizes the system through each step.

[1085] Server-side processing

[1086] The server is responsible for the main data processing and training of the AI ​​model. The specific processing contents are as follows:

[1087] 1. Registering the desired profile and skills

[1088] The user, a company representative, enters the desired personality profile and necessary skills through the system's management screen.

[1089] For example, "communication skills" and "programming skills (Python)" are registered.

[1090] 2. Training an interactive generative AI model

[1091] The server trains the AI ​​model based on the registered data, including past interview data and existing employee profiles.

[1092] Once trained, the AI ​​model will have an optimal set of questions and evaluation criteria.

[1093] 3. Managing interview schedules

[1094] The system saves the interview schedule set in the database, generates notifications when the interview date and time approaches, and sends reminder emails to applicants and interviewers.

[1095] 4. Operational assistance for autonomous vehicles

[1096] The server uses an interactive generative AI model to calculate the optimal route based on the destination information set by the user.

[1097] It generates appropriate responses to real-time questions from the user and presents them through the touchscreen and speakers inside the car.

[1098] Terminal side processing

[1099] The terminal provides an execution environment for the interview process and autonomous driving support. The specific processing content is as follows:

[1100] 1. Download the AI ​​model

[1101] At the start of an interview or when the self-driving vehicle begins operation, the device downloads the latest interactive generative AI model from the server.

[1102] 2. Interview progress and real-time evaluation

[1103] During the interview, the AI ​​model generates questions and presents them to the applicant, who then enters their answers into a device, which then evaluates them in real time.

[1104] For example, if someone answers, "I majored in computer science at university and have worked on numerous projects using Python," they will be evaluated as having "high programming skills."

[1105] 3. Autonomous driving support

[1106] It provides users with destination setting and route guidance, and generates appropriate responses depending on the situation during driving.

[1107] For example, if the user asks "Where is the next rest stop?", the response will be "The next rest stop is 10km away."

[1108] 4. Emergency Response

[1109] In the event of an emergency, the system will present the user with appropriate countermeasures.

[1110] For example, in response to a query such as "I've been in an accident," the system responds with "Please call the police. Please check the condition of your vehicle."

[1111] User processing

[1112] Users operate and use the system as company personnel and autonomous vehicle users. The specific processing is as follows:

[1113] 1. Review of evaluation results and interview records

[1114] Company representatives log into the system, check the evaluation results and interview records, and make a final decision.

[1115] Reassessments and re-interviews can be scheduled as needed.

[1116] 2. Route guidance and real-time response

[1117] Users of self-driving vehicles can set their destination through the system and receive responses to questions during the journey.

[1118] Hardware and software used

[1119] Hardware: Touchscreen, microphone, speaker, database server, traffic control system

[1120] Software: Python, OpenAI GPT-3 API, Database Management System

[1121] Examples of explanatory text and prompts

[1122] Destination settings:

[1123] Input: User enters "I want to go to Ginza"

[1124] Processing result: Confirm the optimal route, "Proposed route: Go through XX to reach Ginza"

[1125] Inquiry response:

[1126] Input: User asks "Where is the next rest stop?"

[1127] Processing result: "The next rest stop is 10km away"

[1128] Prompt Sentence Examples

[1129] Destination setting: "The user has set Ginza as their destination. Please suggest the best route."

[1130] Question Response: "Generate an answer to the user's question: 'Where is the next rest stop?'"

[1131] Emergency Response: "Emergency: I've been in an accident. What is the appropriate response?"

[1132] In this way, we will realize a system that integrates the job interview process with autonomous vehicle operation support, improving evaluation fairness and user safety.

[1133] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1134] Step 1:

[1135] The server receives the desired personality profile and skills from the user, a company representative. Specifically, the company representative registers information such as "communication skills" and "programming skills (Python)" through the system's management screen. This input data is saved in a database on the server.

[1136] Step 2:

[1137] The server trains a generative conversational AI model based on stored data on desired personalities and skills, including past interview data and existing employee profiles. Input data includes past interview transcripts and employee profiles, and the AI ​​model generates an optimal set of questions and evaluation criteria based on this data.

[1138] Step 3:

[1139] The server manages interview schedules and generates notifications when the interview date and time approaches. The configured interview schedule is used as input, and reminder emails are sent to applicants and interviewers at the specified date and time. The output is the sending of reminder emails.

[1140] Step 4:

[1141] At the start of an interview, the device downloads the latest interactive generative AI model from the server. The input is the latest AI model stored on the server, and the download prepares the device for conducting the interview. The output is the model, which can be used.

[1142] Step 5:

[1143] During the interview, the device displays questions generated by the AI ​​model to the applicant and the applicant inputs their answers. Specifically, questions such as "Please introduce yourself" and "Tell us about your university project" are displayed. The applicant's answers are entered into the device as input, and a real-time evaluation is performed. The output is an evaluation result of the answers.

[1144] Step 6:

[1145] The device records the entire interview process, and sends all questions, answers, and evaluation results to the server, where they are stored in a database. The input includes the recorded conversation data, which is sent to the server and stored. The output is the saved conversation record and evaluation results.

[1146] Step 7:

[1147] The user, a company employee, logs into the system and checks the saved evaluation results and interview records. The saved data is used as input, and a final decision is made based on the evaluation results. The final decision is obtained as output.

[1148] Step 8:

[1149] The server calculates the optimal route based on the destination information set to assist in the operation of the autonomous vehicle and respond to inquiries from the user. The destination information set by the user is used as input, and the optimal route is generated as output.

[1150] Step 9:

[1151] The device uses a generative interactive AI model to generate responses to questions posed by the user while driving. Specifically, the question "Where is the next rest stop?" is used as input, and the device generates the response "The next rest stop is 10 km away." The response is then displayed as output.

[1152] Step 10:

[1153] When an emergency occurs, the device accepts inquiries from the user and uses a generative conversational AI model to suggest appropriate countermeasures. The details of the emergency are used as input, and in response to an inquiry such as "I've been in an accident," a response is generated such as "Please call the police. Please check the condition of your vehicle." The output is the emergency countermeasures.

[1154] 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.

[1155] This invention is an interview assistant system that combines an emotion engine with an interactive generative AI model to compensate for interviewer biases and skill deficiencies and make efficient and fair hiring decisions during corporate recruitment interviews. This system operates in cooperation with a server, terminal, user, and emotion engine, managing and executing the interview process through multiple steps.

[1156] Server-side processing

[1157] 1. Registering the desired profile and skills

[1158] Corporate users use the system's administration screen to input the desired profile and skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[1159] 2. Training an interactive generative AI model

[1160] The server stores the registered data in a database and uses it to train an AI model, combining it with past interview data and existing employee profiles. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[1161] 3. Managing interview schedules

[1162] When a user sets an interview schedule in the system, the server saves and manages the schedule in a database, and sends reminder notifications to applicants and interviewers as the interview date and time approaches.

[1163] Terminal side processing

[1164] 1. Download the AI ​​model

[1165] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[1166] 2. Interview process

[1167] The interview begins based on questions from the AI ​​model displayed on the interviewer's device, such as "Please introduce yourself."

[1168] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[1169] 3. Real-time evaluation

[1170] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[1171] 4. Conversation Recording and Emotional Data Storage

[1172] After the interview is over, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[1173] User processing

[1174] 1. Review of evaluation results and interview records

[1175] The user, a company employee, logs in to the system and checks the evaluation results, interview records, and emotional data stored on the server. Based on this, the final decision is made. For example, referring to the interview records and emotional data, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[1176] 2. Schedule a reassessment and re-interview

[1177] If necessary, the user can schedule a reassessment or re-interview and notifications will be sent out again accordingly.

[1178] Specific examples

[1179] For example, if a company is looking to hire a software engineer with leadership skills, the company representative would register the desired skills, such as "leadership," "programming skills (Python)," and "communication skills," in the system. During the interview, the AI ​​model would display questions such as "Please give us a specific example of a time when you demonstrated leadership," and the emotion engine would evaluate the applicant's confidence and sincerity in real time. After the interview, all data is saved, and the company representative would make the final hiring decision while referring to the evaluation results and emotion data. In this way, the present invention is a system that minimizes interviewer bias and enables more accurate talent evaluation.

[1180] The processing flow will be explained below.

[1181] Step 1:

[1182] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[1183] Step 2:

[1184] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[1185] Step 3:

[1186] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training, the AI ​​model will have the optimal set of questions and evaluation criteria.

[1187] Step 4:

[1188] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[1189] Step 5:

[1190] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[1191] Step 6:

[1192] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[1193] Step 7:

[1194] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[1195] Step 8:

[1196] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[1197] Step 9:

[1198] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[1199] Step 10:

[1200] After the interview, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[1201] Step 11:

[1202] The user, a company employee, logs into the system and checks the saved evaluation results, interview records, and emotional data. Based on this, the final decision is made. For example, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[1203] Step 12:

[1204] If necessary, the user can schedule a reassessment or re-interview, and the server will then issue a new notification to conduct the reassessment or re-interview.

[1205] Example 2

[1206] 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."

[1207] In corporate recruitment interviews, interviewer bias and lack of skills can affect hiring decisions, making it difficult to conduct efficient and fair talent evaluations. It is also difficult to properly evaluate applicants' emotions and non-verbal signals during the interview process. To solve these problems, an interview assistant system combining a dialogue-generating AI model and an emotion engine is needed.

[1208] 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.

[1209] In this invention, the server includes: means for registering desired personalities and skills; means for training an interactive generative AI model based on the registered personalities and skills; means for managing interview schedules and sending notifications when the interview date and time approaches; means for conducting interviews based on the generated AI model; means for inputting applicant responses and having the AI ​​model evaluate them in real time; means for analyzing the applicant's facial expressions, tone of voice, and content of speech in real time using an emotion engine during the interview to generate emotion data; means for saving all conversation records, evaluation results, and emotion data from the interview; and means for reviewing the saved records and making a final decision based on the evaluation results. This compensates for interviewer biases and skill deficiencies, enabling more efficient and fair hiring decisions. The emotion engine also takes applicants' non-verbal signals into account in the evaluation, achieving a more comprehensive talent evaluation.

[1210] 1. "Desired personality and skills" refers to the specific characteristics and abilities that companies seek in job applicants during job interviews.

[1211] 2. "Interactive generative AI model" refers to a model that uses AI technology to engage in two-way communication and automatically generate and evaluate applicants' responses.

[1212] 3. The "Emotion Engine" is a system that analyzes applicants' facial expressions, tone of voice, and speech content in real time to generate emotional data.

[1213] 4. "Interview schedule" refers to the interview date and time set by the company and participant information.

[1214] 5. "Notification" refers to reminders and confirmation messages sent to applicants and interviewers as the interview date and time approaches.

[1215] 6. "Interview Conduct" is the process of conducting an interview using an interactive generative artificial intelligence model.

[1216] 7. "Applicant Responses" refers to the information and opinions provided by the applicant during the interview.

[1217] 8. "Real-time evaluation" refers to the process in which a machine learning model instantly analyzes and evaluates applicants' responses.

[1218] 9. "Conversation records" refer to data that records questions and answers exchanged during an interview and the statements made by the applicant.

[1219] 10. "Evaluation Results" refers to the evaluation information of applicants generated by the interactive generative artificial intelligence model and emotion engine.

[1220] 11. "Arrangement of reassessment or reinterview" refers to the process of scheduling additional assessments or interviews based on the results of existing assessments.

[1221] 12. "Report" refers to a document prepared based on the applicant's evaluation results and emotional data.

[1222] The present invention provides an interview assistant system that combines an interactive generative AI model and an emotion engine to support efficient and fair hiring decisions in corporate job interviews. The following describes an embodiment of the system in detail.

[1223] System Configuration

[1224] server

[1225] 1. Registering the desired profile and skills

[1226] The user, a company representative, accesses the management screen through a browser and inputs the desired profile and skills. Examples of input include "communication skills," "problem-solving skills," and "Python programming skills."

[1227] The server stores this information in a database and performs verification processing to maintain data consistency as necessary.

[1228] 2. Training an interactive generative AI model

[1229] The server uses the registered data, past interview data, and existing employee profiles to train an AI model using machine learning libraries such as TensorFlow and PyTorch.

[1230] As a result of training, the AI ​​model will have an optimal set of questions and evaluation criteria.

[1231] 3. Managing interview schedules

[1232] The user sets the interview date and time and participant information through the calendar. The set information is saved on the server, and when the interview date and time approaches, a reminder notification is sent via email or SMS.

[1233] Terminal

[1234] 1. Download the AI ​​model

[1235] On the day of the interview, the interviewer's device downloads the latest AI model from the server, the file is sent via an HTTP request, and the model is installed on the device.

[1236] 2. Interview process

[1237] Questions generated by the AI ​​model are displayed on the device, and questions such as "Please introduce yourself" are displayed on the interviewer's screen.

[1238] During the interview, the device's camera and microphone are used to capture the applicant's facial expressions and tone of voice, which are then analyzed in real time by an emotion engine to generate emotional data.

[1239] 3. Real-time evaluation

[1240] When the interviewer types the applicant's answers into the device, the AI ​​model analyzes the answers and evaluates them based on keywords and sentiment data. For example, an answer such as "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[1241] 4. Conversation Recording and Emotional Data Storage

[1242] After the interview is over, all questions, answers, evaluation results, and emotional data are sent from the device to the server, and these are stored in a database.

[1243] User

[1244] 1. Review of evaluation results and interview records

[1245] Users can log in to the system and check the saved evaluation results and interview records. They make a final decision based on the detailed data.

[1246] 2. Schedule a reassessment and re-interview

[1247] Users can schedule reassessments and re-interviews, and once the schedule is set up, notifications are sent to applicants and interviewers.

[1248] Specific examples

[1249] This section describes a case where a company is looking to hire a software engineer with leadership skills.

[1250] Input content: Company representatives register skills such as "leadership," "Python programming skills," and "communication skills" in the system.

[1251] Interview Progress: On the day of the interview, the device displays questions such as, "Please give us a specific example of a time when you demonstrated leadership," while the emotion engine evaluates the candidate's confidence and sincerity in real time.

[1252] Reviewing the evaluation results: After the interview, company personnel can refer to the evaluation results and sentiment data and make an overall assessment, for example, "This applicant has strong leadership abilities and technical skills."

[1253] Prompt Sentence Examples

[1254] Below are some examples of prompts to input to the generative AI model.

[1255] Please tell us a specific example of how you demonstrated leadership.

[1256] "Please explain how you solved a difficult problem using past experience."

[1257] "Please tell us about your role and accomplishments in Python projects."

[1258] The present invention provides a system that supports efficient and fair hiring decisions through these settings.

[1259] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1260] Step 1:

[1261] Registering the desired profile and skills

[1262] The user, a company representative, accesses the system's administration screen through a browser and enters the desired personality profile and skills. For example, the user enters information such as "communication skills," "problem-solving skills," and "Python programming skills" into the form and clicks the register button. The server validates this input data and saves it in the database. The input is the company representative's input, and the output is the registered data saved in the database.

[1263] Step 2:

[1264] Training interactive generative AI models

[1265] The server trains the AI ​​model based on the required skills and personality traits stored in the database, past interview data, and existing employee profiles. At this stage, machine learning libraries such as TensorFlow and PyTorch are used to analyze the data and optimize the model parameters. The input is the data in the database, and the output is a trained interactive generative AI model.

[1266] Step 3:

[1267] Managing interview schedules

[1268] Users log in to the system and set the interview date and time and participant information using a calendar interface. Once the settings are complete, the server saves the information in a database and sends reminder notifications to registered email addresses and phone numbers when the interview date and time approaches. The input is the user's schedule settings, and the output is the schedule information saved in the database and reminder notifications.

[1269] Step 4:

[1270] Downloading the AI ​​model

[1271] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. The device sends an HTTP request to the server, and the server responds by sending the AI ​​model file. Once the download is complete, the AI ​​model is installed on the device and it is ready to begin supporting the interview. The input is the download request to the server, and the output is the AI ​​model stored on the device.

[1272] Step 5:

[1273] Interview process

[1274] When the interview begins, questions generated by the AI ​​model are displayed on the interviewer's device. For example, a question such as "Please introduce yourself" may be selected. During the interview, the device uses its built-in camera and microphone to capture the applicant's facial expressions, tone of voice, and content of what is being said, which are then analyzed in real time by an emotion engine to generate emotional data. The input is the questions posed by the AI ​​model and the applicant's answers, and the output is the generated emotional data.

[1275] Step 6:

[1276] Real-time evaluation

[1277] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. It analyzes the applicant's answers and the emotion engine data to comprehensively evaluate an answer such as, "I majored in computer science at university and have experience in numerous projects using Python." The input is the applicant's answers and emotion data, and the output is the evaluation result.

[1278] Step 7:

[1279] Conversation recording and emotional data storage

[1280] After the interview is over, the device transmits all questions and answers, evaluation results, and emotional data to a server, which stores these data in a database for later analysis and re-evaluation. The input is all the data generated during the interview, and the output is the record stored in the database.

[1281] Step 8:

[1282] Checking evaluation results and interview records

[1283] The user, a company employee, logs in to the system and checks the saved evaluation results, interview records, and emotional data. They can also search and display the interview data of a specific applicant through the management screen, and refer to detailed information such as, "This applicant has very high confidence and problem-solving ability." The input is the saved data, and the output is the displayed evaluation results and interview records.

[1284] Step 9:

[1285] Schedule reassessments and re-interviews

[1286] If necessary, the user sets up a reassessment or re-interview. For example, if it is determined that an additional assessment is necessary based on the results of an existing assessment, the user selects the applicant for reassessment on the management screen and sets a new interview date and time. Once the setup is complete, the system sends a notification to the applicant and interviewer. The input is the reassessment setup information, and the output is the notification that was sent.

[1287] (Application example 2)

[1288] 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."

[1289] Traditional recruitment interview and sales staff training systems often suffer from issues such as bias and lack of skills on the part of interviewers and trainers, which can impair the fairness and efficiency of evaluations. Furthermore, the lack of a comprehensive evaluation system that includes the evaluation of emotions makes it difficult to accurately evaluate the aptitude and skills of applicants and staff.

[1290] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for registering required personality profiles and skills, means for training an interactive generative AI model based on the registered personality profiles and skills, means for managing schedules and sending notifications when schedules approach, means for supporting progress based on the generated AI model, means for inputting applicant responses and having the AI ​​model evaluate them in real time, means for saving the evaluated responses and results, means for checking the saved data and making a final decision based on the evaluation results, means for conducting training via a device such as a smartphone or a head-mounted display, and means for analyzing applicant emotions using an emotion engine and incorporating the emotions into the evaluation. This improves the fairness and efficiency of evaluations and enables comprehensive evaluation of the aptitude and skills of applicants and sales staff.

[1291] "Desired personality and skills" refers to the personality traits suitable for a particular job or role, as well as the specific abilities and knowledge that person should possess.

[1292] An "interactive generative artificial intelligence model" is an artificial intelligence model that generates dialogue in natural language based on input information and communicates interactively with the user.

[1293] The "means for managing schedules and sending notifications when the schedule approaches" is a system that manages a specific schedule and sends reminder notifications to the user when the date approaches.

[1294] A "processing aid" is a technique or tool provided to facilitate a particular process.

[1295] "A means for inputting applicants' responses and having an AI model evaluate them in real time" refers to a system in which applicants' responses are input into the system and the AI ​​immediately evaluates the responses.

[1296] The "means for storing evaluated answers and results" is a system for storing answers and results evaluated by artificial intelligence in a database.

[1297] "Means for reviewing stored data and making a final decision based on the evaluation results" refers to a mechanism for viewing stored data and making a final decision based on it.

[1298] "Means for conducting training via a device such as a smartphone or head-mounted display" refers to a system for conducting training using a smartphone or head-mounted display.

[1299] "Means of using an emotion engine to analyze applicants' emotions and incorporate them into the evaluation" is a system that uses technology to analyze applicants' emotions and reflects the results of that analysis in the evaluation process.

[1300] The "means for generating questions and evaluation criteria" is a mechanism for automatically generating questions for evaluating specific skills or characteristics and the criteria for how to evaluate them.

[1301] The "means for dynamically adjusting the next question" is a system that adjusts the next question in real time based on the applicant's answer.

[1302] The "means by which notifications are sent to users and raters" refers to the mechanism by which users and raters are notified of specific events or reminders.

[1303] "Means for arranging additional reassessments and rescheduling" refers to a mechanism for setting and managing reassessments and rescheduling as necessary.

[1304] This invention is a system for improving the fairness and efficiency of evaluations in corporate recruitment interviews and sales staff training in brick-and-mortar stores. This system manages and executes processes through multiple steps by interoperating with a server, terminals, users, and an emotion engine.

[1305] Server-side processing

[1306] 1. Registering target skills

[1307] The server allows users (company representatives and store managers) to enter, via the system's management screen, the profile of a suitable person for a particular job or role, as well as the specific abilities and knowledge that person should possess, such as customer service skills and product knowledge.

[1308] 2. Training an interactive generative AI model

[1309] The server stores the registered data in a database and uses it to train an AI model by combining it with past interview data, sales data, and customer feedback. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[1310] 3. Schedule management

[1311] The server stores the schedule set by the user in a database and sends reminder notifications to the evaluator and the user when the scheduled date approaches. These notifications are displayed on devices such as smartphones and head-mounted displays.

[1312] Terminal side processing

[1313] 1. Download the AI ​​model

[1314] On the day of training, the evaluator's device downloads the latest interactive generative AI model from the server, which supports the training process.

[1315] 2. Training Progression

[1316] The device will then begin training the AI ​​model based on scenarios and questions, such as, "A customer is having trouble choosing a product. As a salesperson, how would you respond?"

[1317] 3. Real-time evaluation

[1318] During training, the device uses an emotion engine to analyze the trainee's emotions in real time and generate results. When applicants or sales staff enter their answers, the AI ​​model evaluates them in real time. The emotion data generated by the emotion engine is also taken into account in the evaluation.

[1319] 4. Data storage

[1320] After the training is completed, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[1321] User processing

[1322] 1. Review of evaluation results and records

[1323] Users, such as company representatives and store managers, log in to the system, check the evaluation results and records stored on the server, and make a final decision based on this.

[1324] 2. Reevaluation and Rescheduling

[1325] If necessary, the user can reassess and reschedule and reissue the notification accordingly.

[1326] Hardware and software used

[1327] Hardware:

[1328] Smartphone

[1329] head-mounted display

[1330] software:

[1331] Interactive generative AI models: OpenAI API

[1332] Emotion Engine: Emotion Recognition Library

[1333] Specific examples

[1334] For example, when training sales staff at a store, a manager registers required skills such as "customer service skills" and "product knowledge" in the system. During training, the AI ​​model displays questions such as, "A customer is having trouble choosing a product. How would you respond as a salesperson?" and the emotion engine evaluates the staff member's response and emotions in real time. In this way, managers can evaluate staff skills with high accuracy and fairness.

[1335] Prompt Sentence Examples

[1336] "A customer is having trouble choosing a product. How would you, as a salesperson, respond?"

[1337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1338] Step 1:

[1339] The server receives input from users (company representatives or store managers) via the system's administration screen about the profile of a person suitable for a specific job or role, as well as the specific abilities and knowledge that person should possess. This obtains data on the required skills and profile, and stores this data in a database. The input in this step is the skill and profile information from the administration screen, and the output is this information stored in the database.

[1340] Step 2:

[1341] The server trains the interactive generative AI model based on the data registered in step 1. It also utilizes past interview data, sales data, and customer feedback to train the AI ​​model. This allows the AI ​​model to retain the optimal question set and evaluation criteria. The input here is skills, personality profile, and past data from the database, and the output is the fully trained AI model.

[1342] Step 3:

[1343] The server registers the schedule set by the user in the system and saves it in the database. When the set schedule approaches, a reminder notification is sent to the evaluator and user. The input is the schedule set by the user, and the output is the device information to which the notification will be sent.

[1344] Step 4:

[1345] On the day of training, the device downloads the latest interactive generative AI model from the server. The downloaded AI model assists the training process. The input here is the AI ​​model from the server, and the output is the AI ​​model downloaded to the device.

[1346] Step 5:

[1347] The device begins training based on the downloaded AI model scenario and questions. For example, a question such as, "A customer is having trouble choosing a product. How would you, as a salesperson, respond?" is displayed. The input is the question from the AI ​​model, and the output is the answer from the person being trained.

[1348] Step 6:

[1349] The device uses an emotion engine to analyze the emotions of the trainee in real time, generating emotion data such as the confidence and sincerity of the answer. The input here is the trainee's answer, and the output is the generated emotion data.

[1350] Step 7:

[1351] The device evaluates the trainee's responses and takes the generated emotional data into account in the evaluation. The AI ​​model performs the evaluation in real time and displays the results. The input is the trainee's responses and emotional data, and the output is the evaluation results.

[1352] Step 8:

[1353] After training is complete, the device sends all questions and answers, evaluation results, and emotion data to the server. The server stores this data in a database. The input is the data stored on the device, and the output is all data stored in the database.

[1354] Step 9:

[1355] The user logs into the system and checks the evaluation results and records stored on the server. Based on this, the final decision is made. The input of this step is the stored evaluation results and records, and the output is the user's final decision.

[1356] Step 10:

[1357] If necessary, the user can reevaluate or reschedule the notification and issue it again. The input here is the reevaluation or reschedule information, and the output is the schedule information to be re-notified.

[1358] 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.

[1359] 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.

[1360] 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.

[1361] [Fourth embodiment]

[1362] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1363] 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.

[1364] 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).

[1365] 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.

[1366] 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.

[1367] 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).

[1368] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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."

[1375] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[1376] Server-side processing

[1377] 1. Registering the desired profile and skills

[1378] The user, a company employee, enters the desired personality profile and skills required for the position through the system's management screen.

[1379] Specifically, information such as "communication skills," "problem-solving skills," and "programming skills (Python)" is registered.

[1380] 2. Training an interactive generative AI model

[1381] The server stores the entered personality and skill data in a database.

[1382] Based on this, the server also uses past interview data and existing employee profiles to train the AI ​​model.

[1383] After completing the training, the server builds an interactive generative AI model with an optimal set of questions and evaluation criteria.

[1384] 3. Managing interview schedules

[1385] When a user sets up an interview schedule in the system, the server stores and manages the schedule in a database.

[1386] As the interview date and time approaches, the server generates a notification and sends a reminder email to the applicant and interviewer.

[1387] Terminal side processing

[1388] 1. Download the AI ​​model

[1389] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server.

[1390] After downloading, the interviewer's device will conduct the interview based on the AI ​​model.

[1391] 2. Interview progress and real-time evaluation

[1392] During the interview, the device displays questions set by the AI ​​model to the applicant.

[1393] For example, questions such as "Please introduce yourself" and "Tell us about projects you have worked on in the past" will be displayed.

[1394] Interviewers enter applicants' answers into a device, and an AI model evaluates the answers in real time.

[1395] As a specific example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," the AI ​​model will evaluate them as having "high programming skills."

[1396] 3. Saving conversation records

[1397] After the entire interview process is completed, the terminal sends all questions, answers, and evaluation results to the server and stores them in a database.

[1398] User processing

[1399] 1. Review of evaluation results and interview records

[1400] The user, a company employee, logs into the system and checks the evaluation results and interview records stored on the server.

[1401] Specifically, users will view saved conversation records and the evaluation results from the AI ​​model to make a final decision regarding hiring or the next interview.

[1402] If necessary, a reassessment or re-interview can be scheduled.

[1403] Specific examples

[1404] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's aptitude in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[1405] The processing flow will be explained below.

[1406] Step 1:

[1407] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[1408] Step 2:

[1409] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[1410] Step 3:

[1411] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training is complete, the AI ​​model will have the optimal set of questions and evaluation criteria.

[1412] Step 4:

[1413] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[1414] Step 5:

[1415] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[1416] Step 6:

[1417] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[1418] Step 7:

[1419] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[1420] Step 8:

[1421] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. For example, if an applicant answers, "I majored in computer science at university and have experience in many projects using Python," the AI ​​model will evaluate them as "having strong programming skills."

[1422] Step 9:

[1423] After the interview is over, all questions, answers, and evaluation results are sent from the terminal to the server and stored in a database.

[1424] Step 10:

[1425] The user, a company employee, logs in to the system and checks the saved evaluation results and interview records. Based on this, the user makes a final decision.

[1426] Step 11:

[1427] If necessary, the user can schedule a reassessment or re-interview and issue a new notification. Reassessments and re-interviews follow a similar process.

[1428] Example 1

[1429] 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."

[1430] In the traditional recruitment interview process, evaluations often vary and are biased because they depend on the interviewer's subjective judgment, creating the risk of unfair hiring decisions. Furthermore, preparing for interviews and managing schedules requires a great deal of effort, making efficient operation difficult. It is necessary to resolve these issues and improve the fairness and efficiency of the recruitment process.

[1431] 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.

[1432] In this invention, the server includes a means for registering desired personalities and skills, a means for training an interactive generative AI model based on the registered personalities and skills, and a means for managing interview schedules and sending notifications when interview dates and times approach, thereby enabling a fair and efficient hiring process.

[1433] The "desired profile" refers to the characteristics and qualities of the ideal person a company wants to hire.

[1434] "Skills" refer to the knowledge and techniques required to perform a specific task or job.

[1435] An "interactive generative AI model" refers to an artificial intelligence system that automatically generates questions based on dialogue and evaluates the answers.

[1436] "Training" refers to the process of providing learning data to a system to improve its performance.

[1437] An "interview schedule" refers to the planned date, time, and duration of the interview.

[1438] "Notification" refers to a message or alert that notifies you when the designated interview date and time is approaching.

[1439] "Terminal" refers to a computer or smart device used as part of a system.

[1440] "Download" refers to the transfer of data or programs from a server to a terminal.

[1441] "Interview proceedings" refers to the series of activities in which an interviewer asks questions of an applicant, receives answers, and evaluates them.

[1442] "Real-time evaluation" means analyzing applicants' responses immediately on the spot and providing evaluation results.

[1443] "Conversation record" refers to a record of all verbal exchanges and questions and answers that took place during an interview.

[1444] "Evaluation results" refers to judgments regarding the applicant's abilities and suitability obtained through interviews.

[1445] "Final decision" refers to the interviewer or company representative making the final decision regarding employment or the next interview based on the evaluation results.

[1446] This invention is an interview assistant system that uses an interactive generative AI model to reduce variability and bias in evaluations during a company's recruitment interview process and make efficient and fair hiring decisions. This system operates in cooperation between a server, terminals, and users, and manages and executes the interview process through multiple steps.

[1447] Server-side processing

[1448] First, the user (company representative) enters the desired personality profile and skills required for the position through the system's administration screen. This information is stored in a database. Examples of registered skills include "communication skills," "problem-solving skills," and "programming skills (Python)." The server then trains an AI model based on the stored personality profile and skill data, utilizing past interview data and existing employee profiles. Machine learning frameworks such as TensorFlow and PyTorch are used for training. Once training is complete, the server builds and saves an interactive generative AI model with the optimal question set and evaluation criteria. The server also receives the interview schedule set by the user and saves it in a database. As the interview date and time approaches, the server automatically sends reminder emails to applicants and interviewers.

[1449] Terminal side processing

[1450] At the start of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. After downloading, the device conducts the interview based on the AI ​​model. During the interview, the device displays questions set by the AI ​​model to the applicant, such as "Please tell us about yourself" or "Tell us about projects you have worked on in the past." When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. As a specific example of evaluation, if an applicant answers, "I majored in computer science at university and have worked on many projects using Python," the AI ​​model will evaluate the applicant as having "high programming skills." After the interview is over, the device sends all questions, answers, and evaluation results to the server and stores them in a database.

[1451] User processing

[1452] The user, a company representative, logs in to the system and checks the evaluation results and interview records stored on the server. The user then looks at the saved conversation records and the evaluation results from the AI ​​model and makes a final decision on hiring or the next interview. If necessary, they can also schedule a re-evaluation or re-interview.

[1453] Specific examples

[1454] For example, if a company is hiring a software engineer, the company representative registers the desired skills, such as "programming skills (Python)," "problem-solving ability," and "teamwork ability," in the system. The server uses this information to train an AI model, which then generates appropriate questions for the interview. With the support of the AI, the interviewer can evaluate the applicant's suitability in real time, and after the interview, they can smoothly check the evaluation results and make a final decision. In this way, the present invention is a useful system for streamlining a company's recruitment process and securing the right talent.

[1455] Prompt Sentence Examples

[1456] Here are some example prompts for a generative AI model:

[1457] "Please ask applicants the following questions and evaluate their answers: 1. Please introduce yourself. 2. Please tell us about a project you have worked on in the past. 3. Please tell us more about your experience working on a project using Python."

[1458] Based on this prompt, the AI ​​model generates appropriate questions and evaluates the applicant's answers.

[1459] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1460] Step 1:

[1461] A user logs into the system and enters the desired personality profile and skills.

[1462] Specific operations: Company representatives access the system's administration screen, enter information such as "communication skills," "problem-solving skills," and "programming skills (Python)," and click the "Register" button.

[1463] Input: Information about the desired personality and skills

[1464] Output: Personality and skill information stored in a database

[1465] Step 2:

[1466] The server trains an interactive generative AI model based on the input personality and skill data.

[1467] How it works: The server retrieves personality and skill data from the database and combines it with past interview data and existing employee profiles. It trains the system using TensorFlow and PyTorch.

[1468] Input: Profiles in the database, skill data, past interview data

[1469] Output: A trained interactive generative AI model

[1470] Step 3:

[1471] The user schedules the interview.

[1472] Specific operation: The user logs in to the system, specifies the date and time of the interview, and clicks the "Save" button.

[1473] Input: Interview date and time

[1474] Output: Schedules saved in the database

[1475] Step 4:

[1476] The server prepares and sends the reminder notification.

[1477] Specific operation: When the interview date and time approaches, the server automatically sends a reminder email to the applicant and interviewer.

[1478] Input: Interview schedules in the database

[1479] Output: Reminder emails sent to applicants and interviewers

[1480] Step 5:

[1481] The interviewer's device downloads the latest interactive generative AI model from the server.

[1482] Specific operation: When the interviewer clicks the "Start interview" button, the device connects to the server and downloads the latest AI model.

[1483] Input: Interviewer request

[1484] Output: AI model downloaded to the device

[1485] Step 6:

[1486] During the interview, the device displays questions to the applicant based on the AI ​​model.

[1487] What it does: The device will ask questions such as "Tell us about yourself" and "Tell us about some of the projects you've worked on in the past."

[1488] Input: A trained AI model

[1489] Output: Questions shown to applicants

[1490] Step 7:

[1491] The interviewer enters the applicant's answers into the device, and the AI ​​model evaluates them in real time.

[1492] How it works: Interviewers input the applicant's answers, and the AI ​​model analyzes and evaluates the answers in real time. For example, an answer like "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[1493] Input: Applicant's response

[1494] Output: Real-time evaluation results

[1495] Step 8:

[1496] After the interview is over, all questions, answers, and evaluation results are sent to the server and saved.

[1497] Specific operation: When the interview is over, the interviewer clicks the "End interview" button, and the device sends the data to the server, which stores it in the database.

[1498] Input: All questions and answers, evaluation results

[1499] Output: Interview notes stored in a database

[1500] Step 9:

[1501] The user reviews the evaluation results and interview records and makes the final decision.

[1502] Specific operation: The user logs in to the system and selects the "Interview Record" menu to check the evaluation results and conversation records.

[1503] Input: Interview records and evaluation results in the database

[1504] Output: User's final decision

[1505] (Application example 1)

[1506] 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."

[1507] In the recruitment interview process, there is a problem of variability and bias in evaluations, making it difficult to make fair and efficient hiring decisions. Self-driving vehicles also require a method to respond quickly and accurately to user questions and emergency situations. The purpose of this invention is to provide a system using an interactive generative AI model to solve these problems.

[1508] 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.

[1509] In this invention, the server includes means for registering a desired personality profile and skills, means for training an interactive generative AI model based on the registered personality profile and skills, means for managing an interview schedule and sending a notification when the interview date and time approaches, means for conducting the interview based on the generated AI model, means for inputting the applicant's answers and having the AI ​​model evaluate them in real time, means for saving all conversation records and evaluation results of the interview, means for checking the saved records and making a final decision based on the evaluation results, means for providing operation assistance for the autonomous vehicle and responding to inquiries from users, means for setting a destination and providing route guidance, and means for generating responses to questions during operation. This makes it possible to reduce variability and bias in evaluations in the employment interview process and improve user support in autonomous vehicles.

[1510] "Desired profile" refers to the ideal person a company is looking for in a job interview, as well as the characteristics and skills required for a specific role.

[1511] "Skills" are the abilities and knowledge required to perform a specific job or role.

[1512] An "interactive generative artificial intelligence model" is an artificial intelligence model that assists with specific tasks by generating answers and responses through dialogue with the user.

[1513] "Interview schedule" refers to information for managing schedules such as interview dates, times, and locations.

[1514] A "notification" is a message or signal sent to inform a user of specific information or events.

[1515] An "interview" is a conversation with an applicant that takes place as part of the recruitment process.

[1516] An "applicant" is a person who applies for a particular job or position.

[1517] "Answer" means a response given by an applicant to a question.

[1518] "Real-time evaluation" means that the user's input and actions are evaluated immediately.

[1519] "Conversation recording" means recording the content of conversations that take place during interviews or dialogues.

[1520] "Evaluation results" refer to the results of the evaluation generated based on the applicant's responses and actions.

[1521] "Final judgment" refers to the final decision made based on the evaluation results.

[1522] An "autonomous vehicle" is a vehicle whose driving operations are automated.

[1523] "Operation assistance" refers to providing support to maintain the safety and comfort of users when operating an autonomous vehicle.

[1524] "Inquiry handling" means responding to questions or requests from users.

[1525] "Destination setting" refers to the act of inputting the location the user wants to reach into the system.

[1526] "Route guidance" refers to showing the optimal route to reach a destination.

[1527] A "question" is a question or request from a user.

[1528] A "response" is a response or response that a system gives to a question.

[1529] "Emergency response" means taking immediate and appropriate action in an emergency situation.

[1530] This invention is a system that uses an interactive generative AI model to streamline corporate recruitment interview processes and autonomous vehicle operation support, providing a fair and safe environment. The invention operates in cooperation between a server, terminals, and users, and realizes the system through each step.

[1531] Server-side processing

[1532] The server is responsible for the main data processing and training of the AI ​​model. The specific processing contents are as follows:

[1533] 1. Registering the desired profile and skills

[1534] The user, a company representative, enters the desired personality profile and necessary skills through the system's management screen.

[1535] For example, "communication skills" and "programming skills (Python)" are registered.

[1536] 2. Training an interactive generative AI model

[1537] The server trains the AI ​​model based on the registered data, including past interview data and existing employee profiles.

[1538] Once trained, the AI ​​model will have an optimal set of questions and evaluation criteria.

[1539] 3. Managing interview schedules

[1540] The system saves the interview schedule set in the database, generates notifications when the interview date and time approaches, and sends reminder emails to applicants and interviewers.

[1541] 4. Operational assistance for autonomous vehicles

[1542] The server uses an interactive generative AI model to calculate the optimal route based on the destination information set by the user.

[1543] It generates appropriate responses to real-time questions from the user and presents them through the touchscreen and speakers inside the car.

[1544] Terminal side processing

[1545] The terminal provides an execution environment for the interview process and autonomous driving support. The specific processing content is as follows:

[1546] 1. Download the AI ​​model

[1547] At the start of an interview or when the self-driving vehicle begins operation, the device downloads the latest interactive generative AI model from the server.

[1548] 2. Interview progress and real-time evaluation

[1549] During the interview, the AI ​​model generates questions and presents them to the applicant, who then enters their answers into a device, which then evaluates them in real time.

[1550] For example, if someone answers, "I majored in computer science at university and have worked on numerous projects using Python," they will be evaluated as having "high programming skills."

[1551] 3. Autonomous driving support

[1552] It provides users with destination setting and route guidance, and generates appropriate responses depending on the situation during driving.

[1553] For example, if the user asks "Where is the next rest stop?", the response will be "The next rest stop is 10km away."

[1554] 4. Emergency Response

[1555] In the event of an emergency, the system will present the user with appropriate countermeasures.

[1556] For example, in response to a query such as "I've been in an accident," the system responds with "Please call the police. Please check the condition of your vehicle."

[1557] User processing

[1558] Users operate and use the system as company personnel and autonomous vehicle users. The specific processing is as follows:

[1559] 1. Review of evaluation results and interview records

[1560] Company representatives log into the system, check the evaluation results and interview records, and make a final decision.

[1561] Reassessments and re-interviews can be scheduled as needed.

[1562] 2. Route guidance and real-time response

[1563] Users of self-driving vehicles can set their destination through the system and receive responses to questions during the journey.

[1564] Hardware and software used

[1565] Hardware: Touchscreen, microphone, speaker, database server, traffic control system

[1566] Software: Python, OpenAI GPT-3 API, Database Management System

[1567] Examples of explanatory text and prompts

[1568] Destination settings:

[1569] Input: User enters "I want to go to Ginza"

[1570] Processing result: Confirm the optimal route, "Proposed route: Go through XX to reach Ginza"

[1571] Inquiry response:

[1572] Input: User asks "Where is the next rest stop?"

[1573] Processing result: "The next rest stop is 10km away"

[1574] Prompt Sentence Examples

[1575] Destination setting: "The user has set Ginza as their destination. Please suggest the best route."

[1576] Question Response: "Generate an answer to the user's question: 'Where is the next rest stop?'"

[1577] Emergency Response: "Emergency: I've been in an accident. What is the appropriate response?"

[1578] In this way, we will realize a system that integrates the job interview process with autonomous vehicle operation support, improving evaluation fairness and user safety.

[1579] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1580] Step 1:

[1581] The server receives the desired personality profile and skills from the user, a company representative. Specifically, the company representative registers information such as "communication skills" and "programming skills (Python)" through the system's management screen. This input data is saved in a database on the server.

[1582] Step 2:

[1583] The server trains a generative conversational AI model based on stored data on desired personalities and skills, including past interview data and existing employee profiles. Input data includes past interview transcripts and employee profiles, and the AI ​​model generates an optimal set of questions and evaluation criteria based on this data.

[1584] Step 3:

[1585] The server manages the interview schedule and generates notifications when the interview date and time approaches. The configured interview schedule is used as input, and reminder emails are sent to applicants and interviewers at the specified date and time. The output is the sending of reminder emails.

[1586] Step 4:

[1587] At the start of an interview, the device downloads the latest interactive generative AI model from the server. The input is the latest AI model stored on the server, and the download prepares the device for conducting the interview. The output is the model that can be used.

[1588] Step 5:

[1589] During the interview, the device displays questions generated by the AI ​​model to the applicant and the applicant inputs their answers. Specifically, questions such as "Please introduce yourself" and "Tell us about your university project" are displayed. The applicant's answers are entered into the device as input, and a real-time evaluation is performed. The output is an evaluation result of the answers.

[1590] Step 6:

[1591] The device records the entire interview process, and sends all questions, answers, and evaluation results to the server, where they are stored in a database. The input includes the recorded conversation data, which is sent to the server and stored. The output is the saved conversation record and evaluation results.

[1592] Step 7:

[1593] The user, a company employee, logs into the system and checks the saved evaluation results and interview records. The saved data is used as input, and a final decision is made based on the evaluation results. The final decision is obtained as output.

[1594] Step 8:

[1595] The server calculates the optimal route based on the destination information set to assist in the operation of the autonomous vehicle and respond to inquiries from the user. The destination information set by the user is used as input, and the optimal route is generated as output.

[1596] Step 9:

[1597] The device uses a generative interactive AI model to generate responses to questions posed by the user while driving. Specifically, the question "Where is the next rest stop?" is used as input, and the device generates the response "The next rest stop is 10 km away." The response is then displayed as output.

[1598] Step 10:

[1599] When an emergency occurs, the device accepts inquiries from the user and uses a generative conversational AI model to suggest appropriate countermeasures. The details of the emergency are used as input, and in response to an inquiry such as "I've been in an accident," a response is generated such as "Please call the police. Please check the condition of your vehicle." The output is the emergency countermeasures.

[1600] 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.

[1601] This invention is an interview assistant system that combines an emotion engine with an interactive generative AI model to compensate for interviewer biases and skill deficiencies and make efficient and fair hiring decisions during corporate recruitment interviews. This system operates in cooperation with a server, terminal, user, and emotion engine, managing and executing the interview process through multiple steps.

[1602] Server-side processing

[1603] 1. Registering the desired profile and skills

[1604] Corporate users use the system's administration screen to input the desired profile and skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[1605] 2. Training an interactive generative AI model

[1606] The server stores the registered data in a database and uses it to train an AI model, combining it with past interview data and existing employee profiles. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[1607] 3. Managing interview schedules

[1608] When a user sets an interview schedule in the system, the server saves and manages the schedule in a database, and sends reminder notifications to applicants and interviewers as the interview date and time approaches.

[1609] Terminal side processing

[1610] 1. Download the AI ​​model

[1611] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[1612] 2. Interview process

[1613] The interview begins based on questions from the AI ​​model displayed on the interviewer's device, such as "Please introduce yourself."

[1614] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[1615] 3. Real-time evaluation

[1616] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[1617] 4. Conversation Recording and Emotional Data Storage

[1618] After the interview is over, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[1619] User processing

[1620] 1. Review of evaluation results and interview records

[1621] The user, a company employee, logs in to the system and checks the evaluation results, interview records, and emotional data stored on the server. Based on this, the final decision is made. For example, referring to the interview records and emotional data, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[1622] 2. Schedule a reassessment and re-interview

[1623] If necessary, the user can schedule a reassessment or re-interview and notifications will be sent out again accordingly.

[1624] Specific examples

[1625] For example, if a company is looking to hire a software engineer with leadership skills, the company representative would register the desired skills, such as "leadership," "programming skills (Python)," and "communication skills," in the system. During the interview, the AI ​​model would display questions such as "Please give us a specific example of a time when you demonstrated leadership," and the emotion engine would evaluate the applicant's confidence and sincerity in real time. After the interview, all data is saved, and the company representative would make the final hiring decision while referring to the evaluation results and emotion data. In this way, the present invention is a system that minimizes interviewer bias and enables more accurate talent evaluation.

[1626] The processing flow will be explained below.

[1627] Step 1:

[1628] Users open the system's administration screen and input the characteristics of the person the company is looking for and the skills required for the position, including communication skills, problem-solving skills, and programming skills (Python).

[1629] Step 2:

[1630] The server stores the user-entered personality and skill data in a database, which is used to train the interactive generative AI model.

[1631] Step 3:

[1632] The server trains the AI ​​model based on the data stored in the database, combining it with past interview data and existing employee profiles. After training, the AI ​​model will have the optimal set of questions and evaluation criteria.

[1633] Step 4:

[1634] The user sets the interview schedule in the system, and the server stores and manages this schedule in a database.

[1635] Step 5:

[1636] As the interview date and time approaches, the server sends reminder notifications to applicants and interviewers, which include details about the interview.

[1637] Step 6:

[1638] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server, which supports the interview process.

[1639] Step 7:

[1640] The interview begins based on questions from the AI ​​model displayed on the interviewer's device. For example, a question such as "Please introduce yourself" is displayed on the device.

[1641] Step 8:

[1642] During the interview, the device uses an emotion engine to analyze the applicant's facial expressions, tone of voice, and content of speech in real time to generate emotional data.

[1643] Step 9:

[1644] When the interviewer enters the applicant's answers into the device, the AI ​​model evaluates them in real time. At the same time, the emotional data generated by the emotion engine is also taken into account in the evaluation. For example, if an applicant answers, "I majored in computer science at university and have experience in numerous projects using Python," and the emotion engine evaluates them as "confident," the AI ​​model will evaluate them as "having strong programming skills."

[1645] Step 10:

[1646] After the interview, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[1647] Step 11:

[1648] The user, a company employee, logs into the system and checks the saved evaluation results, interview records, and emotional data. Based on this, the final decision is made. For example, the employee may decide that "this applicant has very high confidence and problem-solving ability."

[1649] Step 12:

[1650] If necessary, the user can schedule a reassessment or re-interview, and the server will then issue a new notification to conduct the reassessment or re-interview.

[1651] Example 2

[1652] 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."

[1653] In corporate recruitment interviews, interviewer bias and lack of skills can affect hiring decisions, making it difficult to conduct efficient and fair talent evaluations. It is also difficult to properly evaluate applicants' emotions and non-verbal signals during the interview process. To solve these problems, an interview assistant system combining a dialogue-generating AI model and an emotion engine is needed.

[1654] 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.

[1655] In this invention, the server includes: means for registering desired personalities and skills; means for training an interactive generative AI model based on the registered personalities and skills; means for managing interview schedules and sending notifications when the interview date and time approaches; means for conducting interviews based on the generated AI model; means for inputting applicant responses and having the AI ​​model evaluate them in real time; means for analyzing the applicant's facial expressions, tone of voice, and content of speech in real time using an emotion engine during the interview to generate emotion data; means for saving all conversation records, evaluation results, and emotion data from the interview; and means for reviewing the saved records and making a final decision based on the evaluation results. This compensates for interviewer biases and skill deficiencies, enabling more efficient and fair hiring decisions. The emotion engine also takes applicants' non-verbal signals into account in the evaluation, achieving a more comprehensive talent evaluation.

[1656] 1. "Desired personality and skills" refers to the specific characteristics and abilities that companies seek in job applicants during job interviews.

[1657] 2. "Interactive generative AI model" refers to a model that uses AI technology to engage in two-way communication and automatically generate and evaluate applicants' responses.

[1658] 3. The "Emotion Engine" is a system that analyzes applicants' facial expressions, tone of voice, and speech content in real time to generate emotional data.

[1659] 4. "Interview schedule" refers to the interview date and time set by the company and participant information.

[1660] 5. "Notification" refers to reminders and confirmation messages sent to applicants and interviewers as the interview date and time approaches.

[1661] 6. "Interview Conduct" is the process of conducting an interview using an interactive generative artificial intelligence model.

[1662] 7. "Applicant Responses" refers to the information and opinions provided by the applicant during the interview.

[1663] 8. "Real-time evaluation" refers to the process in which a machine learning model instantly analyzes and evaluates applicants' responses.

[1664] 9. "Conversation records" refer to data that records questions and answers exchanged during an interview and the statements made by the applicant.

[1665] 10. "Evaluation Results" refers to the evaluation information of applicants generated by the interactive generative artificial intelligence model and emotion engine.

[1666] 11. "Arrangement of reassessment or reinterview" refers to the process of scheduling additional assessments or interviews based on the results of existing assessments.

[1667] 12. "Report" refers to a document prepared based on the applicant's evaluation results and emotional data.

[1668] The present invention provides an interview assistant system that combines an interactive generative AI model and an emotion engine to support efficient and fair hiring decisions in corporate job interviews. The following describes an embodiment of the system in detail.

[1669] System Configuration

[1670] server

[1671] 1. Registering the desired profile and skills

[1672] The user, a company representative, accesses the management screen through a browser and inputs the desired profile and skills. Examples of input include "communication skills," "problem-solving skills," and "Python programming skills."

[1673] The server stores this information in a database and performs verification processing to maintain data consistency as necessary.

[1674] 2. Training an interactive generative AI model

[1675] The server uses the registered data, past interview data, and existing employee profiles to train an AI model using machine learning libraries such as TensorFlow and PyTorch.

[1676] As a result of training, the AI ​​model will have an optimal set of questions and evaluation criteria.

[1677] 3. Managing interview schedules

[1678] The user sets the interview date and time and participant information through the calendar. The set information is saved on the server, and when the interview date and time approaches, a reminder notification is sent via email or SMS.

[1679] Terminal

[1680] 1. Download the AI ​​model

[1681] On the day of the interview, the interviewer's device downloads the latest AI model from the server, the file is sent via an HTTP request, and the model is installed on the device.

[1682] 2. Interview process

[1683] Questions generated by the AI ​​model are displayed on the device, and questions such as "Please introduce yourself" are displayed on the interviewer's screen.

[1684] During the interview, the device's camera and microphone are used to capture the applicant's facial expressions and tone of voice, which are then analyzed in real time by an emotion engine to generate emotional data.

[1685] 3. Real-time evaluation

[1686] When the interviewer types the applicant's answers into the device, the AI ​​model analyzes the answers and evaluates them based on keywords and sentiment data. For example, an answer such as "I majored in computer science at university and have experience with many projects using Python" would be evaluated highly.

[1687] 4. Conversation Recording and Emotional Data Storage

[1688] After the interview is over, all questions, answers, evaluation results, and emotional data are sent from the device to the server, and these are stored in a database.

[1689] User

[1690] 1. Review of evaluation results and interview records

[1691] Users can log in to the system and check the saved evaluation results and interview records. They make a final decision based on the detailed data.

[1692] 2. Schedule a reassessment and re-interview

[1693] Users can schedule reassessments and re-interviews, and once the schedule is set up, notifications are sent to applicants and interviewers.

[1694] Specific examples

[1695] This section describes a case where a company is looking to hire a software engineer with leadership skills.

[1696] Input content: Company representatives register skills such as "leadership," "Python programming skills," and "communication skills" in the system.

[1697] Interview Progress: On the day of the interview, the device displays questions such as, "Please give us a specific example of a time when you demonstrated leadership," while the emotion engine evaluates the candidate's confidence and sincerity in real time.

[1698] Reviewing the evaluation results: After the interview, company personnel can refer to the evaluation results and sentiment data and make an overall assessment, for example, "This applicant has strong leadership abilities and technical skills."

[1699] Prompt Sentence Examples

[1700] Below are some examples of prompts to input to the generative AI model.

[1701] Please tell us a specific example of how you demonstrated leadership.

[1702] "Please explain how you solved a difficult problem using past experience."

[1703] "Please tell us about your role and accomplishments in Python projects."

[1704] The present invention provides a system that supports efficient and fair hiring decisions through these settings.

[1705] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1706] Step 1:

[1707] Registering the desired profile and skills

[1708] The user, a company representative, accesses the system's administration screen through a browser and enters the desired personality profile and skills. For example, the user enters information such as "communication skills," "problem-solving skills," and "Python programming skills" into the form and clicks the register button. The server validates this input data and saves it in the database. The input is the company representative's input, and the output is the registered data saved in the database.

[1709] Step 2:

[1710] Training interactive generative AI models

[1711] The server trains the AI ​​model based on the required skills and personality traits stored in the database, past interview data, and existing employee profiles. At this stage, machine learning libraries such as TensorFlow and PyTorch are used to analyze the data and optimize the model parameters. The input is the data in the database, and the output is a trained interactive generative AI model.

[1712] Step 3:

[1713] Managing interview schedules

[1714] Users log in to the system and set the interview date and time and participant information using a calendar interface. Once the settings are complete, the server saves the information in a database and sends reminder notifications to registered email addresses and phone numbers when the interview date and time approaches. The input is the user's schedule settings, and the output is the schedule information saved in the database and reminder notifications.

[1715] Step 4:

[1716] Downloading the AI ​​model

[1717] On the day of the interview, the interviewer's device downloads the latest interactive generative AI model from the server. The device sends an HTTP request to the server, and the server responds by sending the AI ​​model file. Once the download is complete, the AI ​​model is installed on the device and it is ready to begin supporting the interview. The input is the download request to the server, and the output is the AI ​​model stored on the device.

[1718] Step 5:

[1719] Interview process

[1720] When the interview begins, questions generated by the AI ​​model are displayed on the interviewer's device. For example, a question such as "Please introduce yourself" may be selected. During the interview, the device uses its built-in camera and microphone to capture the applicant's facial expressions, tone of voice, and content of what is being said, which are then analyzed in real time by an emotion engine to generate emotional data. The input is the questions posed by the AI ​​model and the applicant's answers, and the output is the generated emotional data.

[1721] Step 6:

[1722] Real-time evaluation

[1723] When the interviewer inputs the applicant's answers into the device, the AI ​​model evaluates them in real time. It analyzes the applicant's answers and the emotion engine data to comprehensively evaluate an answer such as, "I majored in computer science at university and have experience in numerous projects using Python." The input is the applicant's answers and emotion data, and the output is the evaluation result.

[1724] Step 7:

[1725] Conversation recording and emotional data storage

[1726] After the interview is over, the device transmits all questions and answers, evaluation results, and emotional data to a server, which stores these data in a database for later analysis and re-evaluation. The input is all the data generated during the interview, and the output is the record stored in the database.

[1727] Step 8:

[1728] Checking evaluation results and interview records

[1729] The user, a company employee, logs in to the system and checks the saved evaluation results, interview records, and emotional data. They can also search and display the interview data of a specific applicant through the management screen, and refer to detailed information such as, "This applicant has very high confidence and problem-solving ability." The input is the saved data, and the output is the displayed evaluation results and interview records.

[1730] Step 9:

[1731] Schedule reassessments and re-interviews

[1732] If necessary, the user sets up a reassessment or re-interview. For example, if it is determined that an additional assessment is necessary based on the results of an existing assessment, the user selects the applicant for reassessment on the management screen and sets a new interview date and time. Once the setup is complete, the system sends a notification to the applicant and interviewer. The input is the reassessment setup information, and the output is the notification that was sent.

[1733] (Application example 2)

[1734] 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."

[1735] Traditional recruitment interview and sales staff training systems often suffer from issues such as bias and lack of skills on the part of interviewers and trainers, which can impair the fairness and efficiency of evaluations. Furthermore, the lack of a comprehensive evaluation system that includes the evaluation of emotions makes it difficult to accurately evaluate the aptitude and skills of applicants and staff.

[1736] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for registering required personality profiles and skills, means for training an interactive generative AI model based on the registered personality profiles and skills, means for managing schedules and sending notifications when schedules approach, means for supporting progress based on the generated AI model, means for inputting applicant responses and having the AI ​​model evaluate them in real time, means for saving the evaluated responses and results, means for checking the saved data and making a final decision based on the evaluation results, means for conducting training via a device such as a smartphone or a head-mounted display, and means for analyzing applicant emotions using an emotion engine and incorporating the emotions into the evaluation. This improves the fairness and efficiency of evaluations and enables comprehensive evaluation of the aptitude and skills of applicants and sales staff.

[1737] "Desired personality and skills" refers to the personality traits suitable for a particular job or role, as well as the specific abilities and knowledge that person should possess.

[1738] An "interactive generative artificial intelligence model" is an artificial intelligence model that generates dialogue in natural language based on input information and communicates interactively with the user.

[1739] The "means for managing schedules and sending notifications when the schedule approaches" is a system that manages a specific schedule and sends reminder notifications to the user when the date approaches.

[1740] A "processing aid" is a technique or tool provided to facilitate a particular process.

[1741] "A means for inputting applicants' responses and having an AI model evaluate them in real time" refers to a system in which applicants' responses are input into the system and the AI ​​immediately evaluates the responses.

[1742] The "means for storing evaluated answers and results" is a system for storing answers and results evaluated by artificial intelligence in a database.

[1743] "Means for reviewing stored data and making a final decision based on the evaluation results" refers to a mechanism for viewing stored data and making a final decision based on it.

[1744] "Means for conducting training via a device such as a smartphone or head-mounted display" refers to a system for conducting training using a smartphone or head-mounted display.

[1745] "Means of using an emotion engine to analyze applicants' emotions and incorporate them into the evaluation" is a system that uses technology to analyze applicants' emotions and reflects the results of that analysis in the evaluation process.

[1746] The "means for generating questions and evaluation criteria" is a mechanism for automatically generating questions for evaluating specific skills or characteristics and the criteria for how to evaluate them.

[1747] The "means for dynamically adjusting the next question" is a system that adjusts the next question in real time based on the applicant's answer.

[1748] The "means by which notifications are sent to users and raters" refers to the mechanism by which users and raters are notified of specific events or reminders.

[1749] "Means for arranging additional reassessments and rescheduling" refers to a mechanism for setting and managing reassessments and rescheduling as necessary.

[1750] This invention is a system for improving the fairness and efficiency of evaluations in corporate recruitment interviews and sales staff training in brick-and-mortar stores. This system manages and executes processes through multiple steps by interoperating with a server, terminals, users, and an emotion engine.

[1751] Server-side processing

[1752] 1. Registering target skills

[1753] The server allows users (company representatives and store managers) to enter, via the system's management screen, the profile of a suitable person for a particular job or role, as well as the specific abilities and knowledge that person should possess, such as customer service skills and product knowledge.

[1754] 2. Training an interactive generative AI model

[1755] The server stores the registered data in a database and uses it to train an AI model by combining it with past interview data, sales data, and customer feedback. Once trained, the AI ​​model retains the optimal question set and evaluation criteria.

[1756] 3. Schedule management

[1757] The server stores the schedule set by the user in a database and sends reminder notifications to the evaluator and the user when the scheduled date approaches. These notifications are displayed on devices such as smartphones and head-mounted displays.

[1758] Terminal side processing

[1759] 1. Download the AI ​​model

[1760] On the day of training, the evaluator's device downloads the latest interactive generative AI model from the server, which supports the training process.

[1761] 2. Training Progression

[1762] The device will then begin training the AI ​​model based on scenarios and questions, such as, "A customer is having trouble choosing a product. As a salesperson, how would you respond?"

[1763] 3. Real-time evaluation

[1764] During training, the device uses an emotion engine to analyze the trainee's emotions in real time and generate results. When applicants or sales staff enter their answers, the AI ​​model evaluates them in real time. The emotion data generated by the emotion engine is also taken into account in the evaluation.

[1765] 4. Data storage

[1766] After the training is completed, all questions and answers, evaluation results, and emotional data are sent from the device to the server and stored in a database.

[1767] User processing

[1768] 1. Review of evaluation results and records

[1769] Users, such as company representatives and store managers, log in to the system, check the evaluation results and records stored on the server, and make a final decision based on this.

[1770] 2. Reevaluation and Rescheduling

[1771] If necessary, the user can reassess and reschedule and reissue the notification accordingly.

[1772] Hardware and software used

[1773] Hardware:

[1774] Smartphone

[1775] head-mounted display

[1776] software:

[1777] Interactive generative AI models: OpenAI API

[1778] Emotion Engine: Emotion Recognition Library

[1779] Specific examples

[1780] For example, when training sales staff at a store, a manager registers required skills such as "customer service skills" and "product knowledge" in the system. During training, the AI ​​model displays questions such as, "A customer is having trouble choosing a product. How would you respond as a salesperson?" and the emotion engine evaluates the staff member's response and emotions in real time. In this way, managers can evaluate staff skills with high accuracy and fairness.

[1781] Prompt Sentence Examples

[1782] "A customer is having trouble choosing a product. How would you, as a salesperson, respond?"

[1783] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1784] Step 1:

[1785] The server receives input from users (company representatives or store managers) via the system's administration screen about the profile of a person suitable for a specific job or role, as well as the specific abilities and knowledge that person should possess. This obtains data on the required skills and profile, and stores this data in a database. The input in this step is the skill and profile information from the administration screen, and the output is this information stored in the database.

[1786] Step 2:

[1787] The server trains the interactive generative AI model based on the data registered in step 1. It also utilizes past interview data, sales data, and customer feedback to train the AI ​​model. This allows the AI ​​model to retain the optimal question set and evaluation criteria. The input here is skills, personality profile, and past data from the database, and the output is the fully trained AI model.

[1788] Step 3:

[1789] The server registers the schedule set by the user in the system and saves it in the database. When the set schedule approaches, a reminder notification is sent to the evaluator and user. The input is the schedule set by the user, and the output is the device information to which the notification will be sent.

[1790] Step 4:

[1791] On the day of training, the device downloads the latest interactive generative AI model from the server. The downloaded AI model assists the training process. The input here is the AI ​​model from the server, and the output is the AI ​​model downloaded to the device.

[1792] Step 5:

[1793] The device begins training based on the downloaded AI model scenario and questions. For example, a question such as, "A customer is having trouble choosing a product. How would you, as a salesperson, respond?" is displayed. The input is the question from the AI ​​model, and the output is the answer from the person being trained.

[1794] Step 6:

[1795] The device uses an emotion engine to analyze the emotions of the trainee in real time, generating emotion data such as the confidence and sincerity of the answer. The input here is the trainee's answer, and the output is the generated emotion data.

[1796] Step 7:

[1797] The device evaluates the trainee's responses and takes the generated emotional data into account in the evaluation. The AI ​​model performs the evaluation in real time and displays the results. The input is the trainee's responses and emotional data, and the output is the evaluation results.

[1798] Step 8:

[1799] After training is complete, the device sends all questions and answers, evaluation results, and emotion data to the server. The server stores this data in a database. The input is the data stored on the device, and the output is all data stored in the database.

[1800] Step 9:

[1801] The user logs into the system and checks the evaluation results and records stored on the server. Based on this, the final decision is made. The input of this step is the stored evaluation results and records, and the output is the user's final decision.

[1802] Step 10:

[1803] If necessary, the user can reevaluate or reschedule the notification and issue it again. The input here is the reevaluation or reschedule information, and the output is the schedule information to be re-notified.

[1804] 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.

[1805] 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.

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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.

[1810] 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).

[1811] 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.

[1812] 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."

[1813] 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.

[1814] 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).

[1815] 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.

[1816] 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.

[1817] 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.

[1818] 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.

[1819] 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.

[1820] 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.

[1821] 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.

[1822] 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.

[1823] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1824] 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.

[1825] The following is further disclosed regarding the above embodiment.

[1826] (Claim 1)

[1827] A means to register the desired profile and skills;

[1828] A means for training an interactive generative artificial intelligence model based on the registered persona and skills;

[1829] A way to manage interview schedules and send notifications when the interview date and time approaches,

[1830] A means for conducting an interview based on the generated artificial intelligence model;

[1831] A means for inputting applicants' responses and having the AI ​​model evaluate them in real time;

[1832] a means for storing all conversation records and evaluation results of said interviews;

[1833] means for reviewing the stored records and making a final decision based on the evaluation results;

[1834] A system including:

[1835] (Claim 2)

[1836] a means for generating interview questions and assessment criteria;

[1837] a means of dynamically adjusting the next question based on the applicant's answers;

[1838] The system of claim 1 further comprising:

[1839] (Claim 3)

[1840] means for transmitting said notice to applicants and interviewers;

[1841] a means for arranging for further reassessments or re-interviews for said final determination; and

[1842] The system of claim 1 further comprising:

[1843] "Example 1"

[1844] (Claim 1)

[1845] A means to register the desired profile and skills;

[1846] A means for training an interactive generative AI model based on the registered persona and skills;

[1847] A way to manage interview schedules and send notifications when the interview date and time approaches,

[1848] A means for conducting an interview based on the generated generative AI model;

[1849] A means for inputting applicants' responses and having the generative AI model evaluate them in real time;

[1850] a means for storing all conversation records and evaluation results of said interviews;

[1851] means for reviewing the stored records and making a final decision based on the evaluation results;

[1852] A means for the interviewer's device to download the latest generative AI model from the server,

[1853] A system including:

[1854] (Claim 2)

[1855] The system of claim 1, which generates interview questions and evaluation criteria.

[1856] (Claim 3)

[1857] 10. The system of claim 1, wherein the next question is dynamically adjusted based on the response.

[1858] "Application Example 1"

[1859] (Claim 1)

[1860] A means to register the desired profile and skills;

[1861] A means for training an interactive generative artificial intelligence model based on the registered persona and skills;

[1862] A way to manage interview schedules and send notifications when the interview date and time approaches,

[1863] A means for conducting an interview based on the generated artificial intelligence model;

[1864] A means for inputting applicants' responses and having the AI ​​model evaluate them in real time;

[1865] a means for storing all conversation records and evaluation results of said interviews;

[1866] means for reviewing the stored records and making a final decision based on the evaluation results;

[1867] A means of providing operational support for autonomous vehicles and responding to inquiries from users;

[1868] A means for setting a destination and providing route guidance;

[1869] means for generating responses to queries during operation;

[1870] A system including:

[1871] (Claim 2)

[1872] a means for generating interview questions and assessment criteria; ...

Claims

1. A means to register the desired profile and skills; A means for training an interactive generative artificial intelligence model based on the registered persona and skills; A way to manage interview schedules and send notifications when the interview date and time approaches, A means for conducting an interview based on the generated artificial intelligence model; A means for inputting applicants' responses and having the AI ​​model evaluate them in real time; a means for storing all conversation records and evaluation results of said interviews; means for reviewing the stored records and making a final decision based on the evaluation results; A system including:

2. a means for generating interview questions and assessment criteria; a means of dynamically adjusting the next question based on the applicant's answers; The system of claim 1 further comprising:

3. means for transmitting said notice to applicants and interviewers; a means for arranging for further reassessments or re-interviews for said final determination; and The system of claim 1 further comprising:

Images