System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting business information; means for inputting job candidate information; means for building a learning model from the business information; means for building a learning model from the job candidate information; means for generating an interview session using the learning model; means for recording and analyzing interaction data throughout the interview session; means for evaluating a degree of match between a business and a job candidate from the interaction data; and means for providing a match evaluation result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The current recruitment process makes it difficult to match companies and job seekers, sometimes resulting in the hiring of unsuitable candidates. To prevent such mismatches, it is necessary to accurately understand the company's philosophy and culture, the desired skill set, and the job seeker's skills, mindset, and desired conditions, and then make an appropriate match based on that. However, this process is time-consuming and costly. Furthermore, the traditional interview format makes it difficult to completely bridge the gap between the company and the job seeker, often resulting in dissatisfaction for both parties. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting company information and job seeker information, a means for building a learning model from company information, a means for building a learning model from job seeker information, a means for generating interview sessions using the learning model, a means for recording and analyzing dialogue data from the interview sessions, a means for evaluating the compatibility between companies and job seekers from the dialogue data, and a means for providing the compatibility evaluation results. This enables efficient and effective matching between companies and job seekers, reducing time and costs. In addition, AI-assisted interviews promote open communication and provide a forum for honest exchange of opinions, enabling a deeper understanding of the compatibility between the company culture and the job seeker.

[0006] "Corporate information" refers to information about the specific requirements and characteristics that a company seeks, such as the company's philosophy, culture, the type of person it is looking for, and the necessary skill sets.

[0007] "Job Seeker Information" means information about a job seeker's skill set, work history, desired qualifications, specialized knowledge and experience.

[0008] A "learning model" is a data structure based on AI algorithms generated from company and job seeker information to understand and evaluate company requirements and job seeker profiles.

[0009] An "interview session" is a process in which an AI interviewer and an AI job seeker virtually meet face-to-face and engage in dialogue using a learning model.

[0010] "Fitness" is an evaluation indicator that shows how closely a company's requirements match a job seeker's profile.

[0011] "Dialogue data" is a record of questions and answers asked during an interview session, and is data for analysis by AI.

[0012] The "suitability evaluation result" is a result obtained after analyzing the dialogue data, which indicates the suitability of the match between the company and the job seeker.

[0013] A "matching list" is a list of job seekers who are optimally matched with companies, generated based on the results of the compatibility evaluation.

[0014] "Terminal" means the computing device used by a company's HR personnel and job seekers to enter information and receive notifications and results from the system.

[0015] A "server" is a central computer system that controls the entire system and processes, stores, and communicates data. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is a system that inputs company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Specifically, the AI ​​learns the company's philosophy and culture, as well as the job seeker's skill set and desired conditions, and then generates and evaluates appropriate interview sessions. The specific operation of the system is described in detail below.

[0038] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0039] Next, job seekers use the device to enter their skill set, work history, and desired qualifications. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the device to the server and stored in a database as job seeker information.

[0040] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0041] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[0042] The server analyzes the conversation data from the interview session and evaluates the job seeker's compatibility. The compatibility assessment evaluates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. For example, the conversation data can determine whether the job seeker is good at teamwork and has the necessary skills.

[0043] Finally, the server provides the evaluation results to both the company and the job seeker. HR personnel at the company can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0044] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[0045] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user (a company's HR staff) uses a terminal to enter company information, specifically the company's philosophy, culture, desired skill set, and desired employee profile. The entered data is sent from the terminal to the server.

[0049] Step 2:

[0050] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[0051] Step 3:

[0052] The user (job seeker) uses a terminal to enter job seeker information, specifically, skill set, work history, and desired conditions. The entered data is sent from the terminal to the server.

[0053] Step 4:

[0054] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[0055] Step 5:

[0056] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and required skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions.

[0057] Step 6:

[0058] The server evaluates the learning model, adjusts the optimal parameters, and then stores them in a database, forming learning models for the AI ​​interviewer and AI job seeker.

[0059] Step 7:

[0060] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[0061] Step 8:

[0062] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[0063] Step 9:

[0064] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[0065] Step 10:

[0066] The server generates answers based on an AI job seeker model and displays answers such as "I led projects at my previous workplace and led them to success" on the device.

[0067] Step 11:

[0068] The server records all data from the interview dialogue and uses NLP algorithms to analyze the dialogue, particularly to evaluate how well it matches the company's philosophy and skill requirements.

[0069] Step 12:

[0070] The server evaluates the degree of compatibility based on the conversation data and generates an evaluation result that indicates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set.

[0071] Step 13:

[0072] The server generates an API request that notifies both the company and the job seeker of the evaluation results.

[0073] Step 14:

[0074] The terminal displays the feedback results to the user (the company's HR staff) and provides a list of candidates. It also displays the suitability evaluation results to the user (the job seeker) and provides information about the next steps.

[0075] Step 15:

[0076] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[0077] Step 16:

[0078] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[0079] Through the above process, the system efficiently achieves optimal matching between companies and job seekers.

[0080] Example 1

[0081] 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."

[0082] There is a need to efficiently and effectively match companies and job seekers, and improve the compatibility between them. Conventional methods require a lot of time and effort to determine whether the skills and desired conditions of job seekers match the talent a company is looking for. In addition, creating appropriate interview questions and evaluating answers is done manually, which can lead to subjectivity and reduced accuracy. A system is needed to solve these problems.

[0083] 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.

[0084] In this invention, the server includes means for inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating an interview session using the learning model, means for recording dialogue data, means for analyzing the recorded dialogue data, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing the company's philosophy and culture and the job seeker's skill set, and means for generating a trained AI model to be used. This makes it possible to objectively and efficiently evaluate the compatibility between the company and the job seeker and to match optimal personnel.

[0085] A "means for entering company information" is a device or software that allows a company to provide its philosophy, culture, desired skill sets, etc.

[0086] "Means for entering job seeker information" refers to devices or software that allow job seekers to provide their skill sets, work history, desired conditions, etc.

[0087] "Means for building a learning model from corporate information" refers to software or algorithms that allow an AI model to learn data such as a company's philosophy, culture, and desired skill sets based on input corporate information.

[0088] "Means for constructing a learning model from job seeker information" refers to software or algorithms that allow an AI model to learn data such as the job seeker's skill set, work history, and desired conditions based on the job seeker information entered.

[0089] A "means for generating an interview session using a trained model" is software or an algorithm that uses a trained AI model to generate question and answer dialogue in an interview.

[0090] A "means for recording dialogue data" is a device or software for storing data on the exchange of questions and answers that takes place during an interview session.

[0091] The "means for analyzing recorded dialogue data" is software or algorithms for analyzing the stored dialogue data and evaluating the content of questions and answers.

[0092] "Means for evaluating the compatibility between companies and job seekers based on dialogue data" refers to software or algorithms that objectively determine the compatibility between companies and job seekers based on analyzed dialogue data.

[0093] "Means for providing suitability assessment results" refers to a device or software for notifying both companies and job seekers of the assessment results.

[0094] "Means for analyzing a company's philosophy and culture, and a job seeker's skill set" refers to software or algorithms that extract and analyze the characteristics of each input information from the company and the job seeker.

[0095] The "means for generating the trained AI model to be used" refers to software or algorithms for training and running the AI ​​model using data on company information and job seeker information.

[0096] This invention is a system for inputting company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Below, we will explain in detail the procedures for specifically implementing this invention, as well as the hardware and software used.

[0097] First, a company's HR personnel uses a terminal to input company information, including the company's philosophy, culture, and desired skill set. For example, a specific requirement might be entered as "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0098] Next, the job seeker uses the terminal to enter their skill set, work history, desired conditions, etc. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[0099] The server builds an AI learning model based on this company information and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. This creates learning models for the AI ​​interviewer and AI job seeker. The specific software used includes AI algorithms that use natural language processing (NLP) technology.

[0100] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker generates answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would generate an answer like, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[0101] The server analyzes conversation data from the interview session to evaluate compatibility. This evaluation includes how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. The compatibility evaluation results are notified to both the company and the job seeker. The company's HR staff can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results to understand their compatibility with the company.

[0102] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[0103] Prompt Sentence Examples

[0104] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[0105] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Specific explanation of program processing

[0108] Step 1: Enter your company information

[0109] User (Corporate HR Person):

[0110] Input: Information such as company philosophy, culture, and desired skill sets.

[0111] Action: Enter the required company information into the device's input form.

[0112] Processing: Data entered into the form is checked for accuracy through validation.

[0113] Output: Validated company information data.

[0114] Action: Data is sent to the server.

[0115] Step 2: Enter job seeker information

[0116] User (job seeker):

[0117] Input: Information about the job seeker, such as their skill set, work history, and desired qualifications.

[0118] Action: Enter your information into the device's input form.

[0119] Processing: Data entered into the form is checked for accuracy through validation.

[0120] Output: Validated job candidate information data.

[0121] Action: Data is sent to the server.

[0122] Step 3: Save your company and job candidate information

[0123] server:

[0124] Input: Validated company and job applicant information data.

[0125] What it does: Stores company and job seeker information in a database.

[0126] Process: Data is inserted into the database table.

[0127] Output: The record ID stored in the database.

[0128] Step 4: Training the AI ​​model

[0129] server:

[0130] Input: Company and candidate information stored in a database.

[0131] What it does: Retrieves company and job candidate information from a database.

[0132] Processing: Using the acquired data, analyze the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions.

[0133] Output: Feature data as the analysis result.

[0134] How it works: Train an AI model using feature data.

[0135] Step 5: Save the trained AI model

[0136] server:

[0137] Input: A trained AI model.

[0138] What it does: Saves the trained AI model on the server.

[0139] Processing: Serialize the model and save it to storage.

[0140] Output: The path of the AI ​​model saved in storage.

[0141] Step 6: Generate interview sessions

[0142] server:

[0143] Input: A trained AI model, company information, and job candidate information.

[0144] What it does: Loads an AI model and generates an interview session.

[0145] Processing: Generate appropriate questions from the company's perspective and generate answers from the job seeker's perspective.

[0146] Output: Interaction data from the interview session.

[0147] How it works: The interview session is recorded in real time.

[0148] Step 7: Record and analyze interaction data

[0149] server:

[0150] Input: Interaction data from the interview session.

[0151] What it does: Records interaction data and stores it in a database.

[0152] Processing: Analyze the recorded dialogue data using natural language processing techniques.

[0153] Output: Parsed interaction data.

[0154] How it works: The analysis results are used to input data into a model that evaluates the compatibility between companies and job seekers.

[0155] Step 8: Goodness of fit assessment

[0156] server:

[0157] Input: Parsed interaction data.

[0158] What it does: Runs the model to evaluate goodness of fit.

[0159] Processing: Calculate the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile.

[0160] Output: Goodness of fit evaluation results.

[0161] Behavior: Saves the results of the relevance evaluation to a database.

[0162] Step 9: Notification of evaluation results

[0163] Terminals (for corporate HR personnel and job seekers):

[0164] Input: Relevance assessment results stored in the database.

[0165] Behavior: Obtains evaluation results to display on the device.

[0166] Processing: Converts the data into a different format and displays it on a dashboard.

[0167] Output: The displayable evaluation results.

[0168] How it works: The company's HR staff reviews the assessment results and shortlists the most suitable candidates, and job seekers also review their own assessment results to understand their compatibility with the company.

[0169] Specific prompt examples

[0170] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[0171] (Application example 1)

[0172] 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."

[0173] It is extremely important for companies to find the right talent quickly and effectively, but traditional methods are often cumbersome and time-consuming. It also makes it difficult for job seekers to find the best company for them. In particular, when searching for personnel specializing in factory robot maintenance, specialized skill sets are required, and compatibility with teamwork and corporate culture must also be considered. To solve these challenges, advanced matching technology is required.

[0174] 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.

[0175] In this invention, the server includes a means for registering company information and job seeker information in a database, a means for recommending optimal personnel using artificial intelligence technology, and a means for evaluating suitability based on dialogue data and generating a matching list based on the evaluation results. This enables companies to quickly and effectively match job seekers with optimal personnel, even for factory robot maintenance personnel.

[0176] "Company information" refers to detailed information about the company, such as its mission, culture, and the skill sets it seeks.

[0177] "Job Seeker Information" refers to detailed information about a job seeker, such as their skill set, work history, and desired qualifications.

[0178] A "learning model" is an algorithm constructed by artificial intelligence based on company information and job seeker information.

[0179] An "interview session" is a virtual interview generated by an AI interviewer with a company's perspective and an AI job seeker with a job seeker's perspective.

[0180] "Dialogue data" refers to records of questions and answers asked during an interview session.

[0181] "Fitness" is an indicator that shows how closely the company's requirements match the job seeker's profile.

[0182] "Means of registering in a database" is part of a system for storing and managing company information and job seeker information.

[0183] "Recommendation method" refers to the process of using artificial intelligence technology to suggest the best candidates for a company.

[0184] A "matching list" is a list of candidates who are best suited to a company, generated based on the results of a suitability assessment.

[0185] This invention is a system that inputs company information and job seeker information and uses AI technology to achieve optimal matching. It is particularly designed to provide effective matching for factory robot maintenance personnel.

[0186] First, a company's HR staff or user enters company information using a terminal. This company information includes the company's mission, culture, and desired skill set. For example, specific requirements may include, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." The entered company information is sent to a server and registered in a database.

[0187] Next, job seekers use the same terminal to enter their skillset, work history, and desired qualifications, including specific information such as "five years of software engineering experience, fluent in Java and Python." The job seeker information is also sent to the server and registered in the database.

[0188] The server uses AI technology to build a learning model based on registered company and job seeker information. The learning model understands the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions. AI frameworks such as TensorFlow are used in this step.

[0189] Once learning is complete, the server generates an interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation data is recorded in real time.

[0190] The server analyzes the recorded conversation data and evaluates the compatibility between the company and the job seeker. This evaluation includes the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile. The results of the compatibility evaluation are provided to both the company and the job seeker.

[0191] For example, a company's input data might include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python." Meanwhile, job seeker data might include, "Five years of software engineering experience and a strong proficiency in Java and Python." Based on this data, the generative AI model suggests optimal matches. Examples of prompts used in interview sessions include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python" and "Job seeker has five years of software engineering experience and is strong in Java and Python."

[0192] This system will enable quick and effective matching of companies and job seekers for factory robot maintenance personnel.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] First, the user inputs company information. The input company information includes the company's mission, culture, and desired skill set. For example, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, and the server registers the received company information in a database. Input: Company information, Output: Company information saved in the database

[0196] Step 2:

[0197] Next, the job seeker enters their skill set, work history, and desired conditions. This includes specific information such as "I have five years of software engineering experience and am proficient in Java and Python." This input is also sent from the terminal to the server and registered in the database as job seeker information. Input: Job seeker information, Output: Job seeker information saved in the database

[0198] Step 3:

[0199] The server uses artificial intelligence technology to build a learning model based on registered company information and job seeker information. This learning model is generated using AI frameworks such as TensorFlow. From company information, the company's philosophy, culture, and required skill set are understood, and from job seeker information, the job seeker's skill set, work history, and desired conditions are understood. Input: Company information and job seeker information from the database, Output: Built learning model

[0200] Step 4:

[0201] Once the learning is complete, the server generates an interview session. In the interview session, a virtual interview is conducted by an AI interviewer with the perspective of the company and an AI job seeker with the perspective of the job seeker. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "I led a project at my previous workplace and led it to success." Input: Learning model, Output: Generated interview session

[0202] Step 5:

[0203] The server records interview sessions in real time and analyzes the dialogue data. The analyzed dialogue data is used to evaluate the compatibility between companies and job seekers. Input: Interview session dialogue data, Output: Analyzed dialogue data

[0204] Step 6:

[0205] The server evaluates the compatibility between the company and the job seeker based on the analyzed dialogue data. This evaluation measures how well the company's philosophy, culture, and desired skill set match the job seeker's profile. Input: Analyzed dialogue data, Output: Compatibility evaluation results

[0206] Step 7:

[0207] Finally, based on the results of the compatibility evaluation, the server generates an optimal matching list. This list is provided to both companies and job seekers, allowing companies to quickly find suitable personnel and job seekers to understand which companies are best suited to them. Input: Compatibility evaluation results, Output: Generated matching list

[0208] The above is the specific processing flow of the system that realizes optimal matching of factory robots with maintenance personnel.

[0209] 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.

[0210] This invention is a system that inputs company information and job seeker information and builds a learning model based on each piece of information. Furthermore, by combining it with an emotion engine, the emotions of users (HR personnel and job seekers) are analyzed in real time during the interview session, and the results are reflected in the evaluation of suitability. The specific operation of the system is described in detail below.

[0211] First, the user (a company's HR staff) uses a terminal to input company information. For example, they might input specific requirements such as, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, which then stores it in a database as company information.

[0212] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they can input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[0213] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0214] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0215] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, it can determine whether a user (job seeker) is nervous during an interview and provide a positive or negative evaluation.

[0216] The server integrates and analyzes the dialogue data and emotional data from the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy and culture, the desired skill set, and the job seeker's profile and emotional data match. For example, the dialogue data and emotional data can be used to determine whether the job seeker is good at teamwork, has the necessary skills, and shows appropriate emotional responses.

[0217] Finally, the server notifies both the company and the job seeker of the evaluation results. HR personnel at the company can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0218] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, the job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." Based on this information, the server builds a learning model and conducts an interview session. During the interview session, an emotion engine analyzes the job seeker's facial expressions and tone of voice to detect emotions such as "confident." The dialogue data and emotion data are then used to evaluate suitability, allowing the company to quickly and efficiently find the best candidate.

[0219] In this way, the present invention is a system that efficiently and effectively matches companies and job seekers, and by taking emotional data into consideration, provides a more accurate evaluation of suitability.

[0220] The processing flow will be explained below.

[0221] Step 1:

[0222] The user (a company's HR staff member) uses a terminal to enter company information. Specifically, the user enters the company's philosophy, culture, and the desired skill set and profile of the employee. For example, the user might enter requirements such as "Our company values ​​teamwork and is seeking employees who are proficient in Java and Python." This information is then sent from the terminal to the server.

[0223] Step 2:

[0224] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[0225] Step 3:

[0226] The user (job seeker) uses a terminal to enter job seeker information. Specifically, they enter their skill set, work history, and desired conditions. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server.

[0227] Step 4:

[0228] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[0229] Step 5:

[0230] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0231] Step 6:

[0232] The server evaluates the learning model, adjusts the optimal parameters, and then saves them in a database, thereby finalizing the learning models for the AI ​​interviewer and AI job seeker.

[0233] Step 7:

[0234] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[0235] Step 8:

[0236] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[0237] Step 9:

[0238] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[0239] Step 10:

[0240] The server generates an answer based on the AI ​​job seeker model and displays it on the user's (job seeker's) device. For example, the answer generated might be, "I led a project at my previous workplace and led it to success."

[0241] Step 11:

[0242] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, if a user (job seeker) is judged to be "confident," the engine collects emotional data.

[0243] Step 12:

[0244] The server records interview dialogue data and emotional data, and then uses NLP algorithms to analyze the dialogue content and emotional data, particularly to evaluate how well the candidate fits the company's philosophy and skill requirements.

[0245] Step 13:

[0246] The server combines the dialogue data and emotional data to assess suitability and generate an evaluation result based on the company's philosophy and culture, the desired skill set, the candidate's profile, and the emotional data detected during the interview.

[0247] Step 14:

[0248] The server notifies both the company and the job seeker of the evaluation results. The user (the company's HR staff) can check the evaluation results using a terminal and create a list of the most suitable candidates. The user (job seeker) can also check their own evaluation results and understand their compatibility with the company.

[0249] Step 15:

[0250] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[0251] Step 16:

[0252] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[0253] In this way, by combining emotional data, it is possible to further improve the accuracy of matching between companies and job seekers.

[0254] Example 2

[0255] 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."

[0256] Conventional systems for matching companies and job seekers often rely on a simple match between the company's requirements and the job seeker's skill set, and it is difficult to evaluate compatibility by taking into account conversational data and emotional data during the interview session. This makes it difficult to identify job seekers who are a good fit with the company's philosophy and culture, resulting in a problem of reduced matching accuracy.

[0257] 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.

[0258] In this invention, the server includes means for inputting company information and job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data and emotion data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data and emotion data, and means for providing the compatibility evaluation results. This enables compatibility evaluation based on a comprehensive analysis of the dialogue data and emotion data, thereby achieving more accurate matching between companies and job seekers.

[0259] "Company information" refers to information about the company's philosophy, culture, desired skill sets, and other requirements.

[0260] "Job Seeker Information" refers to information about a job seeker's skill set, work history, and desired conditions.

[0261] The "learning model" is an artificial intelligence model that understands the characteristics of companies and job seekers based on input company and job seeker information, and conducts interview sessions.

[0262] An "interview session" is a process in which an AI interviewer and an AI job seeker conduct a virtual interview, recording and analyzing the interactions between users (HR personnel and job seekers) in real time.

[0263] "Dialogue data" refers to data regarding the content of questions and answers recorded during an interview session.

[0264] "Emotional data" refers to data that includes emotional characteristics such as facial expressions, tone of voice, and word choice of the user that are analyzed during the interview session.

[0265] "Fit" is an evaluation value that indicates how well a company's philosophy, culture, and desired skill set match the job seeker's skill set, work history, desired conditions, and emotional data.

[0266] The "results of compatibility evaluation" are results regarding the compatibility between a company and a job seeker, evaluated based on dialogue data and emotion data.

[0267] This invention is a system that inputs company information and job seeker information and builds a learning model based on that information. Furthermore, by using an emotion engine, the system analyzes the emotions of users (HR personnel and job seekers) in real time during the interview session and reflects the results in the evaluation of suitability. The detailed configuration and operation of the system are described below.

[0268] Hardware and software used

[0269] The server receives and stores company and job seeker information, and has multiple functions for building learning models and generating interview sessions. The software running on the server includes databases (e.g., MySQL), AI model building tools (e.g., TensorFlow), and emotion analysis software (e.g., Microsoft Azure Emotion API).

[0270] The terminal is a device that users use to input company and job seeker information, and is usually a PC or tablet.

[0271] Program processing explanation

[0272] The user (a company's HR staff) first uses a terminal to input company information, such as specific requirements like "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to the server, which then stores it in a database as company information.

[0273] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server, which then stores it in a database as job seeker information.

[0274] The server builds an AI learning model based on company and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. Based on this information, learning models for the AI ​​interviewer and AI job seeker are created.

[0275] Once the learning model is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0276] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during the interview session to determine their emotions in real time. For example, it can analyze whether a job seeker is nervous during the interview. This information is sent to the server along with the dialogue data.

[0277] The server integrates and analyzes the dialogue and emotional data obtained during the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the job seeker's profile and emotional data. For example, it determines whether the job seeker excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[0278] Finally, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0279] Examples of concrete examples and prompts

[0280] As a concrete example, consider the case of a software development company recruiting engineers for a new project. The user (the company's HR person) enters company information into the terminal, such as "We value teamwork and require Java and Python skills." Meanwhile, the user (job seeker) enters job seeker information, such as "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python."

[0281] This information is sent to a server and stored in a database. The server uses this information to build a learning model and conduct the interview session. The emotion engine analyzes the job seeker's facial expressions and tone of voice during the interview session to detect emotions such as "confidence." The server then evaluates the candidate's suitability based on the dialogue data and emotion data, and notifies the company and job seeker of the evaluation results. This allows companies to find the best job seekers quickly and efficiently.

[0282] Example prompt sentence:

[0283] "Our system builds an AI learning model based on company and job seeker information, and analyzes user sentiment in real time during interview sessions. Specifically, by inputting the company name, job description, and desired skill set, along with the job seeker's skill set and work history, we can match the two appropriately. For example, we can match companies that value Java and Python skills with job seekers who possess those skills."

[0284] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0285] Step 1:

[0286] The user (a company's HR staff) uses a terminal to enter company information. The input data includes the company's philosophy, culture, and desired skill set. The entered information is sent from the terminal to the server. The server receives this data and stores it in a database. Specifically, the user enters information into a form and clicks the "Submit" button, which sends the data to the server.

[0287] Step 2:

[0288] The user (job seeker) uses a terminal to input their skill set, work history, and desired conditions. The input data includes the job seeker's technical skills, past work experience, and desired work environment. The input information is also sent from the terminal to the server. After receiving this data, the server stores it in a database. Specifically, the data is sent when the job seeker enters their information into the form and clicks the "Submit" button.

[0289] Step 3:

[0290] The server builds an AI learning model based on company and job seeker information stored in the database. This learning model is generated by understanding the company's values, culture, and requirements, and incorporating the job seeker's skill set, work history, and desired conditions. Data processing involves converting the company and job seeker information into feature vectors, and training the model using a machine learning algorithm (e.g., TensorFlow). Specifically, the company and job seeker information is preprocessed and converted into an input format for the AI ​​model, after which the model is trained.

[0291] Step 4:

[0292] Once the learning model is generated, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks pre-set questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. The generated interview session is presented to the user. The input is the constructed learning model, and the output is a simulated interview session with questions and answers. Specifically, the scenario for the interview session is automatically generated, and its contents are displayed to the user.

[0293] Step 5:

[0294] The emotion engine analyzes the emotions of users (HR personnel and job seekers) in real time during an interview session. Inputs include the user's facial expressions, tone of voice, and choice of words, and the emotion engine analyzes this data to determine the user's emotional state in real time. This is done using emotion analysis software such as the Microsoft Azure Emotion API. Specifically, while the user is participating in a video interview, the video and audio data is analyzed in real time.

[0295] Step 6:

[0296] The server integrates and analyzes the dialogue data and emotional data from the interview session to evaluate the compatibility between the company and the job seeker. The input data is dialogue data and emotional data, and a compatibility score is generated as the output. Data processing involves converting each dataset into a feature vector and calculating compatibility using statistical and machine learning algorithms (e.g., decision trees, SVM). Specifically, the compatibility of the job seeker with the company is quantified based on the dialogue content and emotional responses.

[0297] Step 7:

[0298] Finally, the server notifies both the company and the job seeker of the evaluation results. The input is the compatibility evaluation results, and the output is displayed on the company's and job seeker's devices. Specifically, the notified data is displayed to each user via email or dashboard, allowing the company's HR staff to create a list of the most suitable candidates. Job seekers can check their own evaluation results and understand their compatibility with the company.

[0299] (Application example 2)

[0300] 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."

[0301] Current interview systems have difficulty acquiring and analyzing valid data in real time when assessing the compatibility between job seekers and companies. In particular, analysis of job seekers' emotional states and voice data is insufficient, often resulting in a lack of information needed for appropriate matching. Furthermore, due to limitations on physical interview locations, job seekers must physically travel to the interview venue, which is time-consuming and costly. This creates a significant burden on both companies and job seekers.

[0302] 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 inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining the emotional state, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space. This makes it possible to evaluate the compatibility between companies and job seekers with high accuracy and analyze the emotional state and dialogue content during the interview in real time. Furthermore, using a virtual space allows interviews to be conducted without being restricted by physical location, thereby reducing time and cost.

[0303] "Company information" refers to information such as the company's philosophy, culture, required skill sets, and working conditions.

[0304] "Job seeker information" refers to information such as the job seeker's skill set, work history, desired conditions, and self-promotion.

[0305] A "learning model" is an AI model that is built based on company information and job seeker information to evaluate suitability.

[0306] An "interview session" refers to a simulated dialogue between a company and a job seeker using a learning model.

[0307] "Dialogue data" is question and answer data recorded during an interview session.

[0308] "Fitness" is an index that evaluates how well a company's requirements match the abilities and characteristics of a job seeker.

[0309] "Means for analyzing video data in real time and determining emotional state" refers to a system that uses video data acquired from a camera to analyze facial expressions and determine emotions.

[0310] The "means for analyzing voice data and converting it into text data" is a voice recognition system that converts voice obtained from a microphone into text.

[0311] "Virtual space" means a digital space recreated using virtual reality technology.

[0312] This invention is a system that inputs company information and job seeker information and builds a learning model based on the respective information. The system configuration includes means for inputting company information, means for inputting job seeker information, means for building a learning model from the company information and job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining emotional states, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space.

[0313] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0314] Next, job seekers use the terminal to enter their skill set, work history, desired conditions, etc. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in a database as job seeker information.

[0315] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0316] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0317] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. Specifically, it analyzes facial expressions using video data acquired from a camera to determine their emotional state. It also converts audio acquired from a microphone into text and records the conversation.

[0318] For example, a company's HR representative enters a virtual conference room, and a job seeker also joins the virtual conference room. The system captures the job seeker's face with a camera, performs real-time emotion analysis, and records their emotional state during the interview. At the same time, the system converts the job seeker's voice responses into text using speech recognition and saves the interview session details.

[0319] Finally, the server integrates and analyzes the dialogue and emotional data from the interview session to assess the job candidate's suitability. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the candidate's profile and emotional data. For example, the dialogue and emotional data can be used to determine whether the candidate excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[0320] Based on this, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0321] A specific example of a prompt is as follows:

[0322] "Five years of experience as a software engineer and team leader. Proficient in Java and Python."

[0323] In this way, the present invention evaluates the compatibility between a company and a job seeker with high accuracy, analyzes the emotional state and dialogue content during the interview in real time, and realizes effective and efficient interviews using virtual space.

[0324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0325] Step 1:

[0326] The user (a company's HR representative) uses a terminal to input company information. The input company information includes the company's philosophy, culture, required skill set, working conditions, etc. The company information sent from the terminal is stored in a database by the server. This information is later used to build a learning model.

[0327] Step 2:

[0328] The user (job seeker) uses a terminal to input their own job seeker information. The input job seeker information includes skill set, work history, desired conditions, self-promotion, etc. The job seeker information sent from the terminal is stored in a database by the server. This data, like company information, is also used to build the learning model.

[0329] Step 3:

[0330] The server builds a learning model based on the saved company and job seeker information. Specifically, it incorporates elements such as the company's philosophy, desired skills, and work history to create models of the AI ​​interviewer and AI job seeker. This prepares the server to evaluate the compatibility between the company and the job seeker.

[0331] Step 4:

[0332] The server uses the constructed learning model to generate an interview session. During the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. Based on the generated prompt, the AI ​​interviewer might ask, for example, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success."

[0333] Step 5:

[0334] Users (corporate HR personnel and job seekers) participate in interviews in a virtual space. Specifically, the HR personnel and job seekers each log in to a virtual conference room and the interview session begins. Dialogue takes place in real time using device devices such as cameras and microphones.

[0335] Step 6:

[0336] The server analyzes the video data in real time during the interview session to determine the emotional state. The video data acquired from the camera is analyzed using a facial recognition algorithm and recorded as emotional data. For example, emotional states such as nervousness or confidence can be identified.

[0337] Step 7:

[0338] The server analyzes the audio data captured during the interview session and converts it into text data. The audio data collected from the microphone is converted into text data through a voice recognition system and recorded as the conversation. Specific questions and answers are then stored in a database.

[0339] Step 8:

[0340] The server integrates and analyzes the conversation data and emotional data acquired in real time to evaluate the compatibility between the company and the job seeker. Specifically, it compares the emotional state and content of the conversation to evaluate how well the candidate matches the skills and culture the company is looking for. For example, it determines whether the job seeker answers questions with confidence.

[0341] Step 9:

[0342] The server provides the results of the suitability assessment to the company's HR personnel and job seekers. The company's HR personnel can check the assessment results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own assessment results and understand their suitability for the company.

[0343] Examples:

[0344] A typical example of a prompt would be "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python," and the AI ​​interviewer would ask questions based on this. As a result, the accuracy of matching between companies and job seekers is improved, and interviews can be conducted efficiently using the virtual space.

[0345] 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.

[0346] 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.

[0347] 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.

[0348] [Second embodiment]

[0349] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0350] 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.

[0351] 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).

[0352] 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.

[0353] 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.

[0354] 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).

[0355] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0360] 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."

[0361] This invention is a system that inputs company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Specifically, the AI ​​learns the company's philosophy and culture, as well as the job seeker's skill set and desired conditions, and then generates and evaluates appropriate interview sessions. The specific operation of the system is described in detail below.

[0362] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0363] Next, job seekers use the device to enter their skill set, work history, and desired qualifications. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the device to the server and stored in a database as job seeker information.

[0364] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0365] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[0366] The server analyzes the conversation data from the interview session and evaluates the job seeker's compatibility. The compatibility assessment evaluates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. For example, the conversation data can determine whether the job seeker is good at teamwork and has the necessary skills.

[0367] Finally, the server provides the evaluation results to both the company and the job seeker. HR personnel at the company can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0368] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[0369] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[0370] The processing flow will be explained below.

[0371] Step 1:

[0372] The user (a company's HR staff) uses a terminal to enter company information, specifically the company's philosophy, culture, desired skill set, and desired employee profile. The entered data is sent from the terminal to the server.

[0373] Step 2:

[0374] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[0375] Step 3:

[0376] The user (job seeker) uses a terminal to enter job seeker information, specifically, skill set, work history, and desired conditions. The entered data is sent from the terminal to the server.

[0377] Step 4:

[0378] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[0379] Step 5:

[0380] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and required skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions.

[0381] Step 6:

[0382] The server evaluates the learning model, adjusts the optimal parameters, and then stores them in a database, forming learning models for the AI ​​interviewer and AI job seeker.

[0383] Step 7:

[0384] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[0385] Step 8:

[0386] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[0387] Step 9:

[0388] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[0389] Step 10:

[0390] The server generates answers based on an AI job seeker model and displays answers such as "I led projects at my previous workplace and led them to success" on the device.

[0391] Step 11:

[0392] The server records all data from the interview dialogue and uses NLP algorithms to analyze the dialogue, particularly to evaluate how well it matches the company's philosophy and skill requirements.

[0393] Step 12:

[0394] The server evaluates the degree of compatibility based on the conversation data and generates an evaluation result that indicates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set.

[0395] Step 13:

[0396] The server generates an API request that notifies both the company and the job seeker of the evaluation results.

[0397] Step 14:

[0398] The terminal displays the feedback results to the user (the company's HR staff) and provides a list of candidates. It also displays the suitability evaluation results to the user (the job seeker) and provides information about the next steps.

[0399] Step 15:

[0400] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[0401] Step 16:

[0402] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[0403] Through the above process, the system efficiently achieves optimal matching between companies and job seekers.

[0404] Example 1

[0405] 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."

[0406] There is a need to efficiently and effectively match companies and job seekers, and improve the compatibility between them. Conventional methods require a lot of time and effort to determine whether the skills and desired conditions of job seekers match the talent a company is looking for. In addition, creating appropriate interview questions and evaluating answers is done manually, which can lead to subjectivity and reduced accuracy. A system is needed to solve these problems.

[0407] 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.

[0408] In this invention, the server includes means for inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating an interview session using the learning model, means for recording dialogue data, means for analyzing the recorded dialogue data, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing the company's philosophy and culture and the job seeker's skill set, and means for generating a trained AI model to be used. This makes it possible to objectively and efficiently evaluate the compatibility between the company and the job seeker and to match optimal personnel.

[0409] A "means for entering company information" is a device or software that allows a company to provide its philosophy, culture, desired skill sets, etc.

[0410] "Means for entering job seeker information" refers to devices or software that allow job seekers to provide their skill sets, work history, desired conditions, etc.

[0411] "Means for building a learning model from corporate information" refers to software or algorithms that allow an AI model to learn data such as a company's philosophy, culture, and desired skill sets based on input corporate information.

[0412] "Means for constructing a learning model from job seeker information" refers to software or algorithms that allow an AI model to learn data such as the job seeker's skill set, work history, and desired conditions based on the job seeker information entered.

[0413] A "means for generating an interview session using a trained model" is software or an algorithm that uses a trained AI model to generate question and answer dialogue in an interview.

[0414] A "means for recording dialogue data" is a device or software for storing data on the exchange of questions and answers that takes place during an interview session.

[0415] The "means for analyzing recorded dialogue data" is software or algorithms for analyzing the stored dialogue data and evaluating the content of questions and answers.

[0416] "Means for evaluating the compatibility between companies and job seekers based on dialogue data" refers to software or algorithms that objectively determine the compatibility between companies and job seekers based on analyzed dialogue data.

[0417] "Means for providing suitability assessment results" refers to a device or software for notifying both companies and job seekers of the assessment results.

[0418] "Means for analyzing a company's philosophy and culture, and a job seeker's skill set" refers to software or algorithms that extract and analyze the characteristics of each input information from the company and the job seeker.

[0419] The "means for generating the trained AI model to be used" refers to software or algorithms for training and running the AI ​​model using data on company information and job seeker information.

[0420] This invention is a system for inputting company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Below, we will explain in detail the procedures for specifically implementing this invention, as well as the hardware and software used.

[0421] First, a company's HR personnel uses a terminal to input company information, including the company's philosophy, culture, and desired skill set. For example, a specific requirement might be entered as "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0422] Next, the job seeker uses the terminal to enter their skill set, work history, desired conditions, etc. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[0423] The server builds an AI learning model based on this company information and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. This creates learning models for the AI ​​interviewer and AI job seeker. The specific software used includes AI algorithms that use natural language processing (NLP) technology.

[0424] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker generates answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would generate an answer like, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[0425] The server analyzes conversation data from the interview session to evaluate compatibility. This evaluation includes how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. The compatibility evaluation results are notified to both the company and the job seeker. The company's HR staff can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results to understand their compatibility with the company.

[0426] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[0427] Prompt Sentence Examples

[0428] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[0429] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[0430] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0431] Specific explanation of program processing

[0432] Step 1: Enter your company information

[0433] User (Corporate HR Person):

[0434] Input: Information such as company philosophy, culture, and desired skill sets.

[0435] Action: Enter the required company information into the device's input form.

[0436] Processing: Data entered into the form is checked for accuracy through validation.

[0437] Output: Validated company information data.

[0438] Action: Data is sent to the server.

[0439] Step 2: Enter job seeker information

[0440] User (job seeker):

[0441] Input: Information about the job seeker, such as their skill set, work history, and desired qualifications.

[0442] Action: Enter your information into the device's input form.

[0443] Processing: Data entered into the form is checked for accuracy through validation.

[0444] Output: Validated job candidate information data.

[0445] Action: Data is sent to the server.

[0446] Step 3: Save your company and job candidate information

[0447] server:

[0448] Input: Validated company and job applicant information data.

[0449] What it does: Stores company and job seeker information in a database.

[0450] Process: Data is inserted into the database table.

[0451] Output: The record ID stored in the database.

[0452] Step 4: Training the AI ​​model

[0453] server:

[0454] Input: Company and candidate information stored in a database.

[0455] What it does: Retrieves company and job candidate information from a database.

[0456] Processing: Using the acquired data, analyze the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions.

[0457] Output: Feature data as the analysis result.

[0458] How it works: Train an AI model using feature data.

[0459] Step 5: Save the trained AI model

[0460] server:

[0461] Input: A trained AI model.

[0462] What it does: Saves the trained AI model on the server.

[0463] Processing: Serialize the model and save it to storage.

[0464] Output: The path of the AI ​​model saved in storage.

[0465] Step 6: Generate interview sessions

[0466] server:

[0467] Input: A trained AI model, company information, and job candidate information.

[0468] What it does: Loads an AI model and generates an interview session.

[0469] Processing: Generate appropriate questions from the company's perspective and generate answers from the job seeker's perspective.

[0470] Output: Interaction data from the interview session.

[0471] How it works: The interview session is recorded in real time.

[0472] Step 7: Record and analyze interaction data

[0473] server:

[0474] Input: Interaction data from the interview session.

[0475] What it does: Records interaction data and stores it in a database.

[0476] Processing: Analyze the recorded dialogue data using natural language processing techniques.

[0477] Output: Parsed interaction data.

[0478] How it works: The analysis results are used to input data into a model that evaluates the compatibility between companies and job seekers.

[0479] Step 8: Goodness of fit assessment

[0480] server:

[0481] Input: Parsed interaction data.

[0482] What it does: Runs the model to evaluate goodness of fit.

[0483] Processing: Calculate the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile.

[0484] Output: Goodness of fit evaluation results.

[0485] Behavior: Saves the results of the relevance evaluation to a database.

[0486] Step 9: Notification of evaluation results

[0487] Terminals (for corporate HR personnel and job seekers):

[0488] Input: Relevance assessment results stored in the database.

[0489] Behavior: Obtains evaluation results to display on the device.

[0490] Processing: Converts the data into a different format and displays it on a dashboard.

[0491] Output: The displayable evaluation results.

[0492] How it works: The company's HR staff reviews the assessment results and shortlists the most suitable candidates, and job seekers also review their own assessment results to understand their compatibility with the company.

[0493] Specific prompt examples

[0494] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[0495] (Application example 1)

[0496] 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."

[0497] It is extremely important for companies to find the right talent quickly and effectively, but traditional methods are often cumbersome and time-consuming. It also makes it difficult for job seekers to find the best company for them. In particular, when searching for personnel specializing in factory robot maintenance, specialized skill sets are required, and compatibility with teamwork and corporate culture must also be considered. To solve these challenges, advanced matching technology is required.

[0498] 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.

[0499] In this invention, the server includes a means for registering company information and job seeker information in a database, a means for recommending optimal personnel using artificial intelligence technology, and a means for evaluating suitability based on dialogue data and generating a matching list based on the evaluation results. This enables companies to quickly and effectively match job seekers with optimal personnel, even for factory robot maintenance personnel.

[0500] "Company information" refers to detailed information about the company, such as its mission, culture, and the skill sets it seeks.

[0501] "Job Seeker Information" refers to detailed information about a job seeker, such as their skill set, work history, and desired qualifications.

[0502] A "learning model" is an algorithm constructed by artificial intelligence based on company information and job seeker information.

[0503] An "interview session" is a virtual interview generated by an AI interviewer with a company's perspective and an AI job seeker with a job seeker's perspective.

[0504] "Dialogue data" refers to records of questions and answers asked during an interview session.

[0505] "Fitness" is an indicator that shows how closely the company's requirements match the job seeker's profile.

[0506] "Means of registering in a database" is part of a system for storing and managing company information and job seeker information.

[0507] "Recommendation method" refers to the process of using artificial intelligence technology to suggest the best candidates for a company.

[0508] A "matching list" is a list of candidates who are best suited to a company, generated based on the results of a suitability assessment.

[0509] This invention is a system that inputs company information and job seeker information and uses AI technology to achieve optimal matching. It is particularly designed to provide effective matching for factory robot maintenance personnel.

[0510] First, a company's HR staff or user enters company information using a terminal. This company information includes the company's mission, culture, and desired skill set. For example, specific requirements may include, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." The entered company information is sent to a server and registered in a database.

[0511] Next, job seekers use the same terminal to enter their skillset, work history, and desired qualifications, including specific information such as "five years of software engineering experience, fluent in Java and Python." The job seeker information is also sent to the server and registered in the database.

[0512] The server uses AI technology to build a learning model based on registered company and job seeker information. The learning model understands the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions. AI frameworks such as TensorFlow are used in this step.

[0513] Once learning is complete, the server generates an interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation data is recorded in real time.

[0514] The server analyzes the recorded conversation data and evaluates the compatibility between the company and the job seeker. This evaluation includes the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile. The results of the compatibility evaluation are provided to both the company and the job seeker.

[0515] For example, a company's input data might include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python." Meanwhile, job seeker data might include, "Five years of software engineering experience and a strong proficiency in Java and Python." Based on this data, the generative AI model suggests optimal matches. Examples of prompts used in interview sessions include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python" and "Job seeker has five years of software engineering experience and is strong in Java and Python."

[0516] This system will enable quick and effective matching of companies and job seekers for factory robot maintenance personnel.

[0517] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0518] Step 1:

[0519] First, the user inputs company information. The input company information includes the company's mission, culture, and desired skill set. For example, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, and the server registers the received company information in a database. Input: Company information, Output: Company information saved in the database

[0520] Step 2:

[0521] Next, the job seeker enters their skill set, work history, and desired conditions. This includes specific information such as "I have five years of software engineering experience and am proficient in Java and Python." This input is also sent from the terminal to the server and registered in the database as job seeker information. Input: Job seeker information, Output: Job seeker information saved in the database

[0522] Step 3:

[0523] The server uses artificial intelligence technology to build a learning model based on registered company information and job seeker information. This learning model is generated using AI frameworks such as TensorFlow. From company information, the company's philosophy, culture, and required skill set are understood, and from job seeker information, the job seeker's skill set, work history, and desired conditions are understood. Input: Company information and job seeker information from the database, Output: Built learning model

[0524] Step 4:

[0525] Once the learning is complete, the server generates an interview session. In the interview session, a virtual interview is conducted by an AI interviewer with the perspective of the company and an AI job seeker with the perspective of the job seeker. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "I led a project at my previous workplace and led it to success." Input: Learning model, Output: Generated interview session

[0526] Step 5:

[0527] The server records interview sessions in real time and analyzes the dialogue data. The analyzed dialogue data is used to evaluate the compatibility between companies and job seekers. Input: Interview session dialogue data, Output: Analyzed dialogue data

[0528] Step 6:

[0529] The server evaluates the compatibility between the company and the job seeker based on the analyzed dialogue data. This evaluation measures how well the company's philosophy, culture, and desired skill set match the job seeker's profile. Input: Analyzed dialogue data, Output: Compatibility evaluation results

[0530] Step 7:

[0531] Finally, based on the results of the compatibility evaluation, the server generates an optimal matching list. This list is provided to both companies and job seekers, allowing companies to quickly find suitable personnel and job seekers to understand which companies are best suited to them. Input: Compatibility evaluation results, Output: Generated matching list

[0532] The above is the specific processing flow of the system that realizes optimal matching of factory robots with maintenance personnel.

[0533] 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.

[0534] This invention is a system that inputs company information and job seeker information and builds a learning model based on each piece of information. Furthermore, by combining it with an emotion engine, the emotions of users (HR personnel and job seekers) are analyzed in real time during the interview session, and the results are reflected in the evaluation of suitability. The specific operation of the system is described in detail below.

[0535] First, the user (a company's HR staff) uses a terminal to input company information. For example, they might input specific requirements such as, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, which then stores it in a database as company information.

[0536] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they can input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[0537] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0538] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0539] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, it can determine whether a user (job seeker) is nervous during an interview and provide a positive or negative evaluation.

[0540] The server integrates and analyzes the dialogue data and emotional data from the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy and culture, the desired skill set, and the job seeker's profile and emotional data match. For example, the dialogue data and emotional data can be used to determine whether the job seeker is good at teamwork, has the necessary skills, and shows appropriate emotional responses.

[0541] Finally, the server notifies both the company and the job seeker of the evaluation results. HR personnel at the company can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0542] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, the job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." Based on this information, the server builds a learning model and conducts an interview session. During the interview session, an emotion engine analyzes the job seeker's facial expressions and tone of voice to detect emotions such as "confident." The dialogue data and emotion data are then used to evaluate suitability, allowing the company to quickly and efficiently find the best candidate.

[0543] In this way, the present invention is a system that efficiently and effectively matches companies and job seekers, and by taking emotional data into consideration, provides a more accurate evaluation of suitability.

[0544] The processing flow will be explained below.

[0545] Step 1:

[0546] The user (a company's HR staff member) uses a terminal to enter company information. Specifically, the user enters the company's philosophy, culture, and the desired skill set and profile of the employee. For example, the user might enter requirements such as "Our company values ​​teamwork and is seeking employees who are proficient in Java and Python." This information is then sent from the terminal to the server.

[0547] Step 2:

[0548] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[0549] Step 3:

[0550] The user (job seeker) uses a terminal to enter job seeker information. Specifically, they enter their skill set, work history, and desired conditions. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server.

[0551] Step 4:

[0552] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[0553] Step 5:

[0554] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0555] Step 6:

[0556] The server evaluates the learning model, adjusts the optimal parameters, and then saves them in a database, thereby finalizing the learning models for the AI ​​interviewer and AI job seeker.

[0557] Step 7:

[0558] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[0559] Step 8:

[0560] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[0561] Step 9:

[0562] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[0563] Step 10:

[0564] The server generates an answer based on the AI ​​job seeker model and displays it on the user's (job seeker's) device. For example, the answer generated might be, "I led a project at my previous workplace and led it to success."

[0565] Step 11:

[0566] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, if a user (job seeker) is judged to be "confident," the engine collects emotional data.

[0567] Step 12:

[0568] The server records interview dialogue data and emotional data, and then uses NLP algorithms to analyze the dialogue content and emotional data, particularly to evaluate how well the candidate fits the company's philosophy and skill requirements.

[0569] Step 13:

[0570] The server combines the dialogue data and emotional data to assess suitability and generate an evaluation result based on the company's philosophy and culture, the desired skill set, the candidate's profile, and the emotional data detected during the interview.

[0571] Step 14:

[0572] The server notifies both the company and the job seeker of the evaluation results. The user (the company's HR staff) can check the evaluation results using a terminal and create a list of the most suitable candidates. The user (job seeker) can also check their own evaluation results and understand their compatibility with the company.

[0573] Step 15:

[0574] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[0575] Step 16:

[0576] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[0577] In this way, by combining emotional data, it is possible to further improve the accuracy of matching between companies and job seekers.

[0578] Example 2

[0579] 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."

[0580] Conventional systems for matching companies and job seekers often rely on a simple match between the company's requirements and the job seeker's skill set, and it is difficult to evaluate compatibility by taking into account conversational data and emotional data during the interview session. This makes it difficult to identify job seekers who are a good fit with the company's philosophy and culture, resulting in a problem of reduced matching accuracy.

[0581] 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.

[0582] In this invention, the server includes means for inputting company information and job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data and emotion data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data and emotion data, and means for providing the compatibility evaluation results. This enables compatibility evaluation based on a comprehensive analysis of the dialogue data and emotion data, thereby achieving more accurate matching between companies and job seekers.

[0583] "Company information" refers to information about the company's philosophy, culture, desired skill sets, and other requirements.

[0584] "Job Seeker Information" refers to information about a job seeker's skill set, work history, and desired conditions.

[0585] The "learning model" is an artificial intelligence model that understands the characteristics of companies and job seekers based on input company and job seeker information, and conducts interview sessions.

[0586] An "interview session" is a process in which an AI interviewer and an AI job seeker conduct a virtual interview, recording and analyzing the interactions between users (HR personnel and job seekers) in real time.

[0587] "Dialogue data" refers to data regarding the content of questions and answers recorded during an interview session.

[0588] "Emotional data" refers to data that includes emotional characteristics such as facial expressions, tone of voice, and word choice of the user that are analyzed during the interview session.

[0589] "Fit" is an evaluation value that indicates how well a company's philosophy, culture, and desired skill set match the job seeker's skill set, work history, desired conditions, and emotional data.

[0590] The "results of compatibility evaluation" are results regarding the compatibility between a company and a job seeker, evaluated based on dialogue data and emotion data.

[0591] This invention is a system that inputs company information and job seeker information and builds a learning model based on that information. Furthermore, by using an emotion engine, the system analyzes the emotions of users (HR personnel and job seekers) in real time during the interview session and reflects the results in the evaluation of suitability. The detailed configuration and operation of the system are described below.

[0592] Hardware and software used

[0593] The server receives and stores company and job seeker information, and has multiple functions for building learning models and generating interview sessions. The software running on the server includes databases (e.g., MySQL), AI model building tools (e.g., TensorFlow), and emotion analysis software (e.g., Microsoft Azure Emotion API).

[0594] The terminal is a device that users use to input company and job seeker information, and is usually a PC or tablet.

[0595] Program processing explanation

[0596] The user (a company's HR staff) first uses a terminal to input company information, such as specific requirements like "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to the server, which then stores it in a database as company information.

[0597] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server, which then stores it in a database as job seeker information.

[0598] The server builds an AI learning model based on company and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. Based on this information, learning models for the AI ​​interviewer and AI job seeker are created.

[0599] Once the learning model is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0600] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during the interview session to determine their emotions in real time. For example, it can analyze whether a job seeker is nervous during the interview. This information is sent to the server along with the dialogue data.

[0601] The server integrates and analyzes the dialogue and emotional data obtained during the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the job seeker's profile and emotional data. For example, it determines whether the job seeker excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[0602] Finally, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0603] Examples of concrete examples and prompts

[0604] As a concrete example, consider the case of a software development company recruiting engineers for a new project. The user (the company's HR person) enters company information into the terminal, such as "We value teamwork and require Java and Python skills." Meanwhile, the user (job seeker) enters job seeker information, such as "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python."

[0605] This information is sent to a server and stored in a database. The server uses this information to build a learning model and conduct the interview session. The emotion engine analyzes the job seeker's facial expressions and tone of voice during the interview session to detect emotions such as "confidence." The server then evaluates the candidate's suitability based on the dialogue data and emotion data, and notifies the company and job seeker of the evaluation results. This allows companies to find the best job seekers quickly and efficiently.

[0606] Example prompt sentence:

[0607] "Our system builds an AI learning model based on company and job seeker information, and analyzes user sentiment in real time during interview sessions. Specifically, by inputting the company name, job description, and desired skill set, along with the job seeker's skill set and work history, we can match the two appropriately. For example, we can match companies that value Java and Python skills with job seekers who possess those skills."

[0608] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0609] Step 1:

[0610] The user (a company's HR staff) uses a terminal to enter company information. The input data includes the company's philosophy, culture, and desired skill set. The entered information is sent from the terminal to the server. The server receives this data and stores it in a database. Specifically, the user enters information into a form and clicks the "Submit" button, which sends the data to the server.

[0611] Step 2:

[0612] The user (job seeker) uses a terminal to input their skill set, work history, and desired conditions. The input data includes the job seeker's technical skills, past work experience, and desired work environment. The input information is also sent from the terminal to the server. After receiving this data, the server stores it in a database. Specifically, the data is sent when the job seeker enters their information into the form and clicks the "Submit" button.

[0613] Step 3:

[0614] The server builds an AI learning model based on company and job seeker information stored in the database. This learning model is generated by understanding the company's values, culture, and requirements, and incorporating the job seeker's skill set, work history, and desired conditions. Data processing involves converting the company and job seeker information into feature vectors, and training the model using a machine learning algorithm (e.g., TensorFlow). Specifically, the company and job seeker information is preprocessed and converted into an input format for the AI ​​model, after which the model is trained.

[0615] Step 4:

[0616] Once the learning model is generated, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks pre-set questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. The generated interview session is presented to the user. The input is the constructed learning model, and the output is a simulated interview session with questions and answers. Specifically, the scenario for the interview session is automatically generated, and its contents are displayed to the user.

[0617] Step 5:

[0618] The emotion engine analyzes the emotions of users (HR personnel and job seekers) in real time during an interview session. Inputs include the user's facial expressions, tone of voice, and choice of words, and the emotion engine analyzes this data to determine the user's emotional state in real time. This is done using emotion analysis software such as the Microsoft Azure Emotion API. Specifically, while the user is participating in a video interview, the video and audio data is analyzed in real time.

[0619] Step 6:

[0620] The server integrates and analyzes the dialogue data and emotional data from the interview session to evaluate the compatibility between the company and the job seeker. The input data is dialogue data and emotional data, and a compatibility score is generated as the output. Data processing involves converting each dataset into a feature vector and calculating compatibility using statistical and machine learning algorithms (e.g., decision trees, SVM). Specifically, the compatibility of the job seeker with the company is quantified based on the dialogue content and emotional responses.

[0621] Step 7:

[0622] Finally, the server notifies both the company and the job seeker of the evaluation results. The input is the compatibility evaluation results, and the output is displayed on the company's and job seeker's devices. Specifically, the notified data is displayed to each user via email or dashboard, allowing the company's HR staff to create a list of the most suitable candidates. Job seekers can check their own evaluation results and understand their compatibility with the company.

[0623] (Application example 2)

[0624] 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."

[0625] Current interview systems have difficulty acquiring and analyzing valid data in real time when assessing the compatibility between job seekers and companies. In particular, analysis of job seekers' emotional states and voice data is insufficient, often resulting in a lack of information needed for appropriate matching. Furthermore, due to limitations on physical interview locations, job seekers must physically travel to the interview venue, which is time-consuming and costly. This creates a significant burden on both companies and job seekers.

[0626] 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 inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining the emotional state, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space. This makes it possible to evaluate the compatibility between companies and job seekers with high accuracy and analyze the emotional state and dialogue content during the interview in real time. Furthermore, using a virtual space allows interviews to be conducted without being restricted by physical location, thereby reducing time and cost.

[0627] "Company information" refers to information such as the company's philosophy, culture, required skill sets, and working conditions.

[0628] "Job seeker information" refers to information such as the job seeker's skill set, work history, desired conditions, and self-promotion.

[0629] A "learning model" is an AI model that is built based on company information and job seeker information to evaluate suitability.

[0630] An "interview session" refers to a simulated dialogue between a company and a job seeker using a learning model.

[0631] "Dialogue data" is question and answer data recorded during an interview session.

[0632] "Fitness" is an index that evaluates how well a company's requirements match the abilities and characteristics of a job seeker.

[0633] "Means for analyzing video data in real time and determining emotional state" refers to a system that uses video data acquired from a camera to analyze facial expressions and determine emotions.

[0634] The "means for analyzing voice data and converting it into text data" is a voice recognition system that converts voice obtained from a microphone into text.

[0635] "Virtual space" means a digital space recreated using virtual reality technology.

[0636] This invention is a system that inputs company information and job seeker information and builds a learning model based on the respective information. The system configuration includes means for inputting company information, means for inputting job seeker information, means for building a learning model from the company information and job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining emotional states, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space.

[0637] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0638] Next, job seekers use the terminal to enter their skill set, work history, desired conditions, etc. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in a database as job seeker information.

[0639] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0640] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0641] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. Specifically, it analyzes facial expressions using video data acquired from a camera to determine their emotional state. It also converts audio acquired from a microphone into text and records the conversation.

[0642] For example, a company's HR representative enters a virtual conference room, and a job seeker also joins the virtual conference room. The system captures the job seeker's face with a camera, performs real-time emotion analysis, and records their emotional state during the interview. At the same time, the system converts the job seeker's voice responses into text using speech recognition and saves the interview session details.

[0643] Finally, the server integrates and analyzes the dialogue and emotional data from the interview session to assess the job candidate's suitability. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the candidate's profile and emotional data. For example, the dialogue and emotional data can be used to determine whether the candidate excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[0644] Based on this, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0645] A specific example of a prompt is as follows:

[0646] "Five years of experience as a software engineer and team leader. Proficient in Java and Python."

[0647] In this way, the present invention evaluates the compatibility between a company and a job seeker with high accuracy, analyzes the emotional state and dialogue content during the interview in real time, and realizes effective and efficient interviews using virtual space.

[0648] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0649] Step 1:

[0650] The user (a company's HR representative) uses a terminal to input company information. The input company information includes the company's philosophy, culture, required skill set, working conditions, etc. The company information sent from the terminal is stored in a database by the server. This information is later used to build a learning model.

[0651] Step 2:

[0652] The user (job seeker) uses a terminal to input their own job seeker information. The input job seeker information includes skill set, work history, desired conditions, self-promotion, etc. The job seeker information sent from the terminal is stored in a database by the server. This data, like company information, is also used to build the learning model.

[0653] Step 3:

[0654] The server builds a learning model based on the saved company and job seeker information. Specifically, it incorporates elements such as the company's philosophy, desired skills, and work history to create models of the AI ​​interviewer and AI job seeker. This prepares the server to evaluate the compatibility between the company and the job seeker.

[0655] Step 4:

[0656] The server uses the constructed learning model to generate an interview session. During the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. Based on the generated prompt, the AI ​​interviewer might ask, for example, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success."

[0657] Step 5:

[0658] Users (corporate HR personnel and job seekers) participate in interviews in a virtual space. Specifically, the HR personnel and job seekers each log in to a virtual conference room and the interview session begins. Dialogue takes place in real time using device devices such as cameras and microphones.

[0659] Step 6:

[0660] The server analyzes the video data in real time during the interview session to determine the emotional state. The video data acquired from the camera is analyzed using a facial recognition algorithm and recorded as emotional data. For example, emotional states such as nervousness or confidence can be identified.

[0661] Step 7:

[0662] The server analyzes the audio data captured during the interview session and converts it into text data. The audio data collected from the microphone is converted into text data through a voice recognition system and recorded as the conversation. Specific questions and answers are then stored in a database.

[0663] Step 8:

[0664] The server integrates and analyzes the conversation data and emotional data acquired in real time to evaluate the compatibility between the company and the job seeker. Specifically, it compares the emotional state and content of the conversation to evaluate how well the candidate matches the skills and culture the company is looking for. For example, it determines whether the job seeker answers questions with confidence.

[0665] Step 9:

[0666] The server provides the results of the suitability assessment to the company's HR personnel and job seekers. The company's HR personnel can check the assessment results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own assessment results and understand their suitability for the company.

[0667] Examples:

[0668] A typical example of a prompt would be "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python," and the AI ​​interviewer would ask questions based on this. As a result, the accuracy of matching between companies and job seekers is improved, and interviews can be conducted efficiently using the virtual space.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] [Third embodiment]

[0673] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0674] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0675] 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).

[0676] 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.

[0677] 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.

[0678] 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).

[0679] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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."

[0685] This invention is a system that inputs company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Specifically, the AI ​​learns the company's philosophy and culture, as well as the job seeker's skill set and desired conditions, and then generates and evaluates appropriate interview sessions. The specific operation of the system is described in detail below.

[0686] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0687] Next, job seekers use the device to enter their skill set, work history, and desired qualifications. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the device to the server and stored in a database as job seeker information.

[0688] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0689] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[0690] The server analyzes the conversation data from the interview session and evaluates the job seeker's compatibility. The compatibility assessment evaluates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. For example, the conversation data can determine whether the job seeker is good at teamwork and has the necessary skills.

[0691] Finally, the server provides the evaluation results to both the company and the job seeker. HR personnel at the company can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0692] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[0693] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[0694] The processing flow will be explained below.

[0695] Step 1:

[0696] The user (a company's HR staff) uses a terminal to enter company information, specifically the company's philosophy, culture, desired skill set, and desired employee profile. The entered data is sent from the terminal to the server.

[0697] Step 2:

[0698] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[0699] Step 3:

[0700] The user (job seeker) uses a terminal to enter job seeker information, specifically, skill set, work history, and desired conditions. The entered data is sent from the terminal to the server.

[0701] Step 4:

[0702] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[0703] Step 5:

[0704] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and required skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions.

[0705] Step 6:

[0706] The server evaluates the learning model, adjusts the optimal parameters, and then stores them in a database, forming learning models for the AI ​​interviewer and AI job seeker.

[0707] Step 7:

[0708] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[0709] Step 8:

[0710] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[0711] Step 9:

[0712] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[0713] Step 10:

[0714] The server generates answers based on an AI job seeker model and displays answers such as "I led projects at my previous workplace and led them to success" on the device.

[0715] Step 11:

[0716] The server records all data from the interview dialogue and uses NLP algorithms to analyze the dialogue, particularly to evaluate how well it matches the company's philosophy and skill requirements.

[0717] Step 12:

[0718] The server evaluates the degree of compatibility based on the conversation data and generates an evaluation result that indicates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set.

[0719] Step 13:

[0720] The server generates an API request that notifies both the company and the job seeker of the evaluation results.

[0721] Step 14:

[0722] The terminal displays the feedback results to the user (the company's HR staff) and provides a list of candidates. It also displays the suitability evaluation results to the user (the job seeker) and provides information about the next steps.

[0723] Step 15:

[0724] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[0725] Step 16:

[0726] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[0727] Through the above process, the system efficiently achieves optimal matching between companies and job seekers.

[0728] Example 1

[0729] 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."

[0730] There is a need to efficiently and effectively match companies and job seekers, and improve the compatibility between them. Conventional methods require a lot of time and effort to determine whether the skills and desired conditions of job seekers match the talent a company is looking for. In addition, creating appropriate interview questions and evaluating answers is done manually, which can lead to subjectivity and reduced accuracy. A system is needed to solve these problems.

[0731] 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.

[0732] In this invention, the server includes means for inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating an interview session using the learning model, means for recording dialogue data, means for analyzing the recorded dialogue data, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing the company's philosophy and culture and the job seeker's skill set, and means for generating a trained AI model to be used. This makes it possible to objectively and efficiently evaluate the compatibility between the company and the job seeker and to match optimal personnel.

[0733] A "means for entering company information" is a device or software that allows a company to provide its philosophy, culture, desired skill sets, etc.

[0734] "Means for entering job seeker information" refers to devices or software that allow job seekers to provide their skill sets, work history, desired conditions, etc.

[0735] "Means for building a learning model from corporate information" refers to software or algorithms that allow an AI model to learn data such as a company's philosophy, culture, and desired skill sets based on input corporate information.

[0736] "Means for constructing a learning model from job seeker information" refers to software or algorithms that allow an AI model to learn data such as the job seeker's skill set, work history, and desired conditions based on the job seeker information entered.

[0737] A "means for generating an interview session using a trained model" is software or an algorithm that uses a trained AI model to generate question and answer dialogue in an interview.

[0738] A "means for recording dialogue data" is a device or software for storing data on the exchange of questions and answers that takes place during an interview session.

[0739] The "means for analyzing recorded dialogue data" is software or algorithms for analyzing the stored dialogue data and evaluating the content of questions and answers.

[0740] "Means for evaluating the compatibility between companies and job seekers based on dialogue data" refers to software or algorithms that objectively determine the compatibility between companies and job seekers based on analyzed dialogue data.

[0741] "Means for providing suitability assessment results" refers to a device or software for notifying both companies and job seekers of the assessment results.

[0742] "Means for analyzing a company's philosophy and culture, and a job seeker's skill set" refers to software or algorithms that extract and analyze the characteristics of each input information from the company and the job seeker.

[0743] The "means for generating the trained AI model to be used" refers to software or algorithms for training and running the AI ​​model using data on company information and job seeker information.

[0744] This invention is a system for inputting company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Below, we will explain in detail the procedures for specifically implementing this invention, as well as the hardware and software used.

[0745] First, a company's HR personnel uses a terminal to input company information, including the company's philosophy, culture, and desired skill set. For example, a specific requirement might be entered as "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0746] Next, the job seeker uses the terminal to enter their skill set, work history, desired conditions, etc. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[0747] The server builds an AI learning model based on this company information and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. This creates learning models for the AI ​​interviewer and AI job seeker. The specific software used includes AI algorithms that use natural language processing (NLP) technology.

[0748] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker generates answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would generate an answer like, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[0749] The server analyzes conversation data from the interview session to evaluate compatibility. This evaluation includes how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. The compatibility evaluation results are notified to both the company and the job seeker. The company's HR staff can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results to understand their compatibility with the company.

[0750] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[0751] Prompt Sentence Examples

[0752] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[0753] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[0754] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0755] Specific explanation of program processing

[0756] Step 1: Enter your company information

[0757] User (Corporate HR Person):

[0758] Input: Information such as company philosophy, culture, and desired skill sets.

[0759] Action: Enter the required company information into the device's input form.

[0760] Processing: Data entered into the form is checked for accuracy through validation.

[0761] Output: Validated company information data.

[0762] Action: Data is sent to the server.

[0763] Step 2: Enter job seeker information

[0764] User (job seeker):

[0765] Input: Information about the job seeker, such as their skill set, work history, and desired qualifications.

[0766] Action: Enter your information into the device's input form.

[0767] Processing: Data entered into the form is checked for accuracy through validation.

[0768] Output: Validated job candidate information data.

[0769] Action: Data is sent to the server.

[0770] Step 3: Save your company and job candidate information

[0771] server:

[0772] Input: Validated company and job applicant information data.

[0773] What it does: Stores company and job seeker information in a database.

[0774] Process: Data is inserted into the database table.

[0775] Output: The record ID stored in the database.

[0776] Step 4: Training the AI ​​model

[0777] server:

[0778] Input: Company and candidate information stored in a database.

[0779] What it does: Retrieves company and job candidate information from a database.

[0780] Processing: Using the acquired data, analyze the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions.

[0781] Output: Feature data as the analysis result.

[0782] How it works: Train an AI model using feature data.

[0783] Step 5: Save the trained AI model

[0784] server:

[0785] Input: A trained AI model.

[0786] What it does: Saves the trained AI model on the server.

[0787] Processing: Serialize the model and save it to storage.

[0788] Output: The path of the AI ​​model saved in storage.

[0789] Step 6: Generate interview sessions

[0790] server:

[0791] Input: A trained AI model, company information, and job candidate information.

[0792] What it does: Loads an AI model and generates an interview session.

[0793] Processing: Generate appropriate questions from the company's perspective and generate answers from the job seeker's perspective.

[0794] Output: Interaction data from the interview session.

[0795] How it works: The interview session is recorded in real time.

[0796] Step 7: Record and analyze interaction data

[0797] server:

[0798] Input: Interaction data from the interview session.

[0799] What it does: Records interaction data and stores it in a database.

[0800] Processing: Analyze the recorded dialogue data using natural language processing techniques.

[0801] Output: Parsed interaction data.

[0802] How it works: The analysis results are used to input data into a model that evaluates the compatibility between companies and job seekers.

[0803] Step 8: Goodness of fit assessment

[0804] server:

[0805] Input: Parsed interaction data.

[0806] What it does: Runs the model to evaluate goodness of fit.

[0807] Processing: Calculate the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile.

[0808] Output: Goodness of fit evaluation results.

[0809] Behavior: Saves the results of the relevance evaluation to a database.

[0810] Step 9: Notification of evaluation results

[0811] Terminals (for corporate HR personnel and job seekers):

[0812] Input: Relevance assessment results stored in the database.

[0813] Behavior: Obtains evaluation results to display on the device.

[0814] Processing: Converts the data into a different format and displays it on a dashboard.

[0815] Output: The displayable evaluation results.

[0816] How it works: The company's HR staff reviews the assessment results and shortlists the most suitable candidates, and job seekers also review their own assessment results to understand their compatibility with the company.

[0817] Specific prompt examples

[0818] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[0819] (Application example 1)

[0820] 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."

[0821] It is extremely important for companies to find the right talent quickly and effectively, but traditional methods are often cumbersome and time-consuming. It also makes it difficult for job seekers to find the best company for them. In particular, when searching for personnel specializing in factory robot maintenance, specialized skill sets are required, and compatibility with teamwork and corporate culture must also be considered. To solve these challenges, advanced matching technology is required.

[0822] 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.

[0823] In this invention, the server includes a means for registering company information and job seeker information in a database, a means for recommending optimal personnel using artificial intelligence technology, and a means for evaluating suitability based on dialogue data and generating a matching list based on the evaluation results. This enables companies to quickly and effectively match job seekers with optimal personnel, even for factory robot maintenance personnel.

[0824] "Company information" refers to detailed information about the company, such as its mission, culture, and the skill sets it seeks.

[0825] "Job Seeker Information" refers to detailed information about a job seeker, such as their skill set, work history, and desired qualifications.

[0826] A "learning model" is an algorithm constructed by artificial intelligence based on company information and job seeker information.

[0827] An "interview session" is a virtual interview generated by an AI interviewer with a company's perspective and an AI job seeker with a job seeker's perspective.

[0828] "Dialogue data" refers to records of questions and answers asked during an interview session.

[0829] "Fitness" is an indicator that shows how closely the company's requirements match the job seeker's profile.

[0830] "Means of registering in a database" is part of a system for storing and managing company information and job seeker information.

[0831] "Recommendation method" refers to the process of using artificial intelligence technology to suggest the best candidates for a company.

[0832] A "matching list" is a list of candidates who are best suited to a company, generated based on the results of a suitability assessment.

[0833] This invention is a system that inputs company information and job seeker information and uses AI technology to achieve optimal matching. It is particularly designed to provide effective matching for factory robot maintenance personnel.

[0834] First, a company's HR staff or user enters company information using a terminal. This company information includes the company's mission, culture, and desired skill set. For example, specific requirements may include, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." The entered company information is sent to a server and registered in a database.

[0835] Next, job seekers use the same terminal to enter their skillset, work history, and desired qualifications, including specific information such as "five years of software engineering experience, fluent in Java and Python." The job seeker information is also sent to the server and registered in the database.

[0836] The server uses AI technology to build a learning model based on registered company and job seeker information. The learning model understands the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions. AI frameworks such as TensorFlow are used in this step.

[0837] Once learning is complete, the server generates an interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation data is recorded in real time.

[0838] The server analyzes the recorded conversation data and evaluates the compatibility between the company and the job seeker. This evaluation includes the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile. The results of the compatibility evaluation are provided to both the company and the job seeker.

[0839] For example, a company's input data might include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python." Meanwhile, job seeker data might include, "Five years of software engineering experience and a strong proficiency in Java and Python." Based on this data, the generative AI model suggests optimal matches. Examples of prompts used in interview sessions include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python" and "Job seeker has five years of software engineering experience and is strong in Java and Python."

[0840] This system will enable quick and effective matching of companies and job seekers for factory robot maintenance personnel.

[0841] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0842] Step 1:

[0843] First, the user inputs company information. The input company information includes the company's mission, culture, and desired skill set. For example, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, and the server registers the received company information in a database. Input: Company information, Output: Company information saved in the database

[0844] Step 2:

[0845] Next, the job seeker enters their skill set, work history, and desired conditions. This includes specific information such as "I have five years of software engineering experience and am proficient in Java and Python." This input is also sent from the terminal to the server and registered in the database as job seeker information. Input: Job seeker information, Output: Job seeker information saved in the database

[0846] Step 3:

[0847] The server uses artificial intelligence technology to build a learning model based on registered company information and job seeker information. This learning model is generated using AI frameworks such as TensorFlow. From company information, the company's philosophy, culture, and required skill set are understood, and from job seeker information, the job seeker's skill set, work history, and desired conditions are understood. Input: Company information and job seeker information from the database, Output: Built learning model

[0848] Step 4:

[0849] Once the learning is complete, the server generates an interview session. In the interview session, a virtual interview is conducted by an AI interviewer with the perspective of the company and an AI job seeker with the perspective of the job seeker. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "I led a project at my previous workplace and led it to success." Input: Learning model, Output: Generated interview session

[0850] Step 5:

[0851] The server records interview sessions in real time and analyzes the dialogue data. The analyzed dialogue data is used to evaluate the compatibility between companies and job seekers. Input: Interview session dialogue data, Output: Analyzed dialogue data

[0852] Step 6:

[0853] The server evaluates the compatibility between the company and the job seeker based on the analyzed dialogue data. This evaluation measures how well the company's philosophy, culture, and desired skill set match the job seeker's profile. Input: Analyzed dialogue data, Output: Compatibility evaluation results

[0854] Step 7:

[0855] Finally, based on the results of the compatibility evaluation, the server generates an optimal matching list. This list is provided to both companies and job seekers, allowing companies to quickly find suitable personnel and job seekers to understand which companies are best suited to them. Input: Compatibility evaluation results, Output: Generated matching list

[0856] The above is the specific processing flow of the system that realizes optimal matching of factory robots with maintenance personnel.

[0857] 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.

[0858] This invention is a system that inputs company information and job seeker information and builds a learning model based on each piece of information. Furthermore, by combining it with an emotion engine, the emotions of users (HR personnel and job seekers) are analyzed in real time during the interview session, and the results are reflected in the evaluation of suitability. The specific operation of the system is described in detail below.

[0859] First, the user (a company's HR staff) uses a terminal to input company information. For example, they might input specific requirements such as, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, which then stores it in a database as company information.

[0860] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they can input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[0861] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0862] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0863] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, it can determine whether a user (job seeker) is nervous during an interview and provide a positive or negative evaluation.

[0864] The server integrates and analyzes the dialogue data and emotional data from the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy and culture, the desired skill set, and the job seeker's profile and emotional data match. For example, the dialogue data and emotional data can be used to determine whether the job seeker is good at teamwork, has the necessary skills, and shows appropriate emotional responses.

[0865] Finally, the server notifies both the company and the job seeker of the evaluation results. HR personnel at the company can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0866] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, the job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." Based on this information, the server builds a learning model and conducts an interview session. During the interview session, an emotion engine analyzes the job seeker's facial expressions and tone of voice to detect emotions such as "confident." The dialogue data and emotion data are then used to evaluate suitability, allowing the company to quickly and efficiently find the best candidate.

[0867] In this way, the present invention is a system that efficiently and effectively matches companies and job seekers, and by taking emotional data into consideration, provides a more accurate evaluation of suitability.

[0868] The processing flow will be explained below.

[0869] Step 1:

[0870] The user (a company's HR staff member) uses a terminal to enter company information. Specifically, the user enters the company's philosophy, culture, and the desired skill set and profile of the employee. For example, the user might enter requirements such as "Our company values ​​teamwork and is seeking employees who are proficient in Java and Python." This information is then sent from the terminal to the server.

[0871] Step 2:

[0872] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[0873] Step 3:

[0874] The user (job seeker) uses a terminal to enter job seeker information. Specifically, they enter their skill set, work history, and desired conditions. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server.

[0875] Step 4:

[0876] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[0877] Step 5:

[0878] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0879] Step 6:

[0880] The server evaluates the learning model, adjusts the optimal parameters, and then saves them in a database, thereby finalizing the learning models for the AI ​​interviewer and AI job seeker.

[0881] Step 7:

[0882] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[0883] Step 8:

[0884] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[0885] Step 9:

[0886] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[0887] Step 10:

[0888] The server generates an answer based on the AI ​​job seeker model and displays it on the user's (job seeker's) device. For example, the answer generated might be, "I led a project at my previous workplace and led it to success."

[0889] Step 11:

[0890] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, if a user (job seeker) is judged to be "confident," the engine collects emotional data.

[0891] Step 12:

[0892] The server records interview dialogue data and emotional data, and then uses NLP algorithms to analyze the dialogue content and emotional data, particularly to evaluate how well the candidate fits the company's philosophy and skill requirements.

[0893] Step 13:

[0894] The server combines the dialogue data and emotional data to assess suitability and generate an evaluation result based on the company's philosophy and culture, the desired skill set, the candidate's profile, and the emotional data detected during the interview.

[0895] Step 14:

[0896] The server notifies both the company and the job seeker of the evaluation results. The user (the company's HR staff) can check the evaluation results using a terminal and create a list of the most suitable candidates. The user (job seeker) can also check their own evaluation results and understand their compatibility with the company.

[0897] Step 15:

[0898] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[0899] Step 16:

[0900] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[0901] In this way, by combining emotional data, it is possible to further improve the accuracy of matching between companies and job seekers.

[0902] Example 2

[0903] 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."

[0904] Conventional systems for matching companies and job seekers often rely on a simple match between the company's requirements and the job seeker's skill set, and it is difficult to evaluate compatibility by taking into account conversational data and emotional data during the interview session. This makes it difficult to identify job seekers who are a good fit with the company's philosophy and culture, resulting in a problem of reduced matching accuracy.

[0905] 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.

[0906] In this invention, the server includes means for inputting company information and job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data and emotion data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data and emotion data, and means for providing the compatibility evaluation results. This enables compatibility evaluation based on a comprehensive analysis of the dialogue data and emotion data, thereby achieving more accurate matching between companies and job seekers.

[0907] "Company information" refers to information about the company's philosophy, culture, desired skill sets, and other requirements.

[0908] "Job Seeker Information" refers to information about a job seeker's skill set, work history, and desired conditions.

[0909] The "learning model" is an artificial intelligence model that understands the characteristics of companies and job seekers based on input company and job seeker information, and conducts interview sessions.

[0910] An "interview session" is a process in which an AI interviewer and an AI job seeker conduct a virtual interview, recording and analyzing the interactions between users (HR personnel and job seekers) in real time.

[0911] "Dialogue data" refers to data regarding the content of questions and answers recorded during an interview session.

[0912] "Emotional data" refers to data that includes emotional characteristics such as facial expressions, tone of voice, and word choice of the user that are analyzed during the interview session.

[0913] "Fit" is an evaluation value that indicates how well a company's philosophy, culture, and desired skill set match the job seeker's skill set, work history, desired conditions, and emotional data.

[0914] The "results of compatibility evaluation" are results regarding the compatibility between a company and a job seeker, evaluated based on dialogue data and emotion data.

[0915] This invention is a system that inputs company information and job seeker information and builds a learning model based on that information. Furthermore, by using an emotion engine, the system analyzes the emotions of users (HR personnel and job seekers) in real time during the interview session and reflects the results in the evaluation of suitability. The detailed configuration and operation of the system are described below.

[0916] Hardware and software used

[0917] The server receives and stores company and job seeker information, and has multiple functions for building learning models and generating interview sessions. The software running on the server includes databases (e.g., MySQL), AI model building tools (e.g., TensorFlow), and emotion analysis software (e.g., Microsoft Azure Emotion API).

[0918] The terminal is a device that users use to input company and job seeker information, and is usually a PC or tablet.

[0919] Program processing explanation

[0920] The user (a company's HR staff) first uses a terminal to input company information, such as specific requirements like "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to the server, which then stores it in a database as company information.

[0921] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server, which then stores it in a database as job seeker information.

[0922] The server builds an AI learning model based on company and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. Based on this information, learning models for the AI ​​interviewer and AI job seeker are created.

[0923] Once the learning model is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0924] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during the interview session to determine their emotions in real time. For example, it can analyze whether a job seeker is nervous during the interview. This information is sent to the server along with the dialogue data.

[0925] The server integrates and analyzes the dialogue and emotional data obtained during the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the job seeker's profile and emotional data. For example, it determines whether the job seeker excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[0926] Finally, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0927] Examples of concrete examples and prompts

[0928] As a concrete example, consider the case of a software development company recruiting engineers for a new project. The user (the company's HR person) enters company information into the terminal, such as "We value teamwork and require Java and Python skills." Meanwhile, the user (job seeker) enters job seeker information, such as "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python."

[0929] This information is sent to a server and stored in a database. The server uses this information to build a learning model and conduct the interview session. The emotion engine analyzes the job seeker's facial expressions and tone of voice during the interview session to detect emotions such as "confidence." The server then evaluates the candidate's suitability based on the dialogue data and emotion data, and notifies the company and job seeker of the evaluation results. This allows companies to find the best job seekers quickly and efficiently.

[0930] Example prompt sentence:

[0931] "Our system builds an AI learning model based on company and job seeker information, and analyzes user sentiment in real time during interview sessions. Specifically, by inputting the company name, job description, and desired skill set, along with the job seeker's skill set and work history, we can match the two appropriately. For example, we can match companies that value Java and Python skills with job seekers who possess those skills."

[0932] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0933] Step 1:

[0934] The user (a company's HR staff) uses a terminal to enter company information. The input data includes the company's philosophy, culture, and desired skill set. The entered information is sent from the terminal to the server. The server receives this data and stores it in a database. Specifically, the user enters information into a form and clicks the "Submit" button, which sends the data to the server.

[0935] Step 2:

[0936] The user (job seeker) uses a terminal to input their skill set, work history, and desired conditions. The input data includes the job seeker's technical skills, past work experience, and desired work environment. The input information is also sent from the terminal to the server. After receiving this data, the server stores it in a database. Specifically, the data is sent when the job seeker enters their information into the form and clicks the "Submit" button.

[0937] Step 3:

[0938] The server builds an AI learning model based on company and job seeker information stored in the database. This learning model is generated by understanding the company's values, culture, and requirements, and incorporating the job seeker's skill set, work history, and desired conditions. Data processing involves converting the company and job seeker information into feature vectors, and training the model using a machine learning algorithm (e.g., TensorFlow). Specifically, the company and job seeker information is preprocessed and converted into an input format for the AI ​​model, after which the model is trained.

[0939] Step 4:

[0940] Once the learning model is generated, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks pre-set questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. The generated interview session is presented to the user. The input is the constructed learning model, and the output is a simulated interview session with questions and answers. Specifically, the scenario for the interview session is automatically generated, and its contents are displayed to the user.

[0941] Step 5:

[0942] The emotion engine analyzes the emotions of users (HR personnel and job seekers) in real time during an interview session. Inputs include the user's facial expressions, tone of voice, and choice of words, and the emotion engine analyzes this data to determine the user's emotional state in real time. This is done using emotion analysis software such as the Microsoft Azure Emotion API. Specifically, while the user is participating in a video interview, the video and audio data is analyzed in real time.

[0943] Step 6:

[0944] The server integrates and analyzes the dialogue data and emotional data from the interview session to evaluate the compatibility between the company and the job seeker. The input data is dialogue data and emotional data, and a compatibility score is generated as the output. Data processing involves converting each dataset into a feature vector and calculating compatibility using statistical and machine learning algorithms (e.g., decision trees, SVM). Specifically, the compatibility of the job seeker with the company is quantified based on the dialogue content and emotional responses.

[0945] Step 7:

[0946] Finally, the server notifies both the company and the job seeker of the evaluation results. The input is the compatibility evaluation results, and the output is displayed on the company's and job seeker's devices. Specifically, the notified data is displayed to each user via email or dashboard, allowing the company's HR staff to create a list of the most suitable candidates. Job seekers can check their own evaluation results and understand their compatibility with the company.

[0947] (Application example 2)

[0948] 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."

[0949] Current interview systems have difficulty acquiring and analyzing valid data in real time when assessing the compatibility between job seekers and companies. In particular, analysis of job seekers' emotional states and voice data is insufficient, often resulting in a lack of information needed for appropriate matching. Furthermore, due to limitations on physical interview locations, job seekers must physically travel to the interview venue, which is time-consuming and costly. This creates a significant burden on both companies and job seekers.

[0950] 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 inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining the emotional state, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space. This makes it possible to evaluate the compatibility between companies and job seekers with high accuracy and analyze the emotional state and dialogue content during the interview in real time. Furthermore, using a virtual space allows interviews to be conducted without being restricted by physical location, thereby reducing time and cost.

[0951] "Company information" refers to information such as the company's philosophy, culture, required skill sets, and working conditions.

[0952] "Job seeker information" refers to information such as the job seeker's skill set, work history, desired conditions, and self-promotion.

[0953] A "learning model" is an AI model that is built based on company information and job seeker information to evaluate suitability.

[0954] An "interview session" refers to a simulated dialogue between a company and a job seeker using a learning model.

[0955] "Dialogue data" is question and answer data recorded during an interview session.

[0956] "Fitness" is an index that evaluates how well a company's requirements match the abilities and characteristics of a job seeker.

[0957] "Means for analyzing video data in real time and determining emotional state" refers to a system that uses video data acquired from a camera to analyze facial expressions and determine emotions.

[0958] The "means for analyzing voice data and converting it into text data" is a voice recognition system that converts voice obtained from a microphone into text.

[0959] "Virtual space" means a digital space recreated using virtual reality technology.

[0960] This invention is a system that inputs company information and job seeker information and builds a learning model based on the respective information. The system configuration includes means for inputting company information, means for inputting job seeker information, means for building a learning model from the company information and job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining emotional states, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space.

[0961] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[0962] Next, job seekers use the terminal to enter their skill set, work history, desired conditions, etc. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in a database as job seeker information.

[0963] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[0964] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[0965] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. Specifically, it analyzes facial expressions using video data acquired from a camera to determine their emotional state. It also converts audio acquired from a microphone into text and records the conversation.

[0966] For example, a company's HR representative enters a virtual conference room, and a job seeker also joins the virtual conference room. The system captures the job seeker's face with a camera, performs real-time emotion analysis, and records their emotional state during the interview. At the same time, the system converts the job seeker's voice responses into text using speech recognition and saves the interview session details.

[0967] Finally, the server integrates and analyzes the dialogue and emotional data from the interview session to assess the job candidate's suitability. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the candidate's profile and emotional data. For example, the dialogue and emotional data can be used to determine whether the candidate excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[0968] Based on this, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[0969] A specific example of a prompt is as follows:

[0970] "Five years of experience as a software engineer and team leader. Proficient in Java and Python."

[0971] In this way, the present invention evaluates the compatibility between a company and a job seeker with high accuracy, analyzes the emotional state and dialogue content during the interview in real time, and realizes effective and efficient interviews using virtual space.

[0972] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0973] Step 1:

[0974] The user (a company's HR representative) uses a terminal to input company information. The input company information includes the company's philosophy, culture, required skill set, working conditions, etc. The company information sent from the terminal is stored in a database by the server. This information is later used to build a learning model.

[0975] Step 2:

[0976] The user (job seeker) uses a terminal to input their own job seeker information. The input job seeker information includes skill set, work history, desired conditions, self-promotion, etc. The job seeker information sent from the terminal is stored in a database by the server. This data, like company information, is also used to build the learning model.

[0977] Step 3:

[0978] The server builds a learning model based on the saved company and job seeker information. Specifically, it incorporates elements such as the company's philosophy, desired skills, and work history to create models of the AI ​​interviewer and AI job seeker. This prepares the server to evaluate the compatibility between the company and the job seeker.

[0979] Step 4:

[0980] The server uses the constructed learning model to generate an interview session. During the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. Based on the generated prompt, the AI ​​interviewer might ask, for example, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success."

[0981] Step 5:

[0982] Users (corporate HR personnel and job seekers) participate in interviews in a virtual space. Specifically, the HR personnel and job seekers each log in to a virtual conference room and the interview session begins. Dialogue takes place in real time using device devices such as cameras and microphones.

[0983] Step 6:

[0984] The server analyzes the video data in real time during the interview session to determine the emotional state. The video data acquired from the camera is analyzed using a facial recognition algorithm and recorded as emotional data. For example, emotional states such as nervousness or confidence can be identified.

[0985] Step 7:

[0986] The server analyzes the audio data captured during the interview session and converts it into text data. The audio data collected from the microphone is converted into text data through a voice recognition system and recorded as the conversation. Specific questions and answers are then stored in a database.

[0987] Step 8:

[0988] The server integrates and analyzes the conversation data and emotional data acquired in real time to evaluate the compatibility between the company and the job seeker. Specifically, it compares the emotional state and content of the conversation to evaluate how well the candidate matches the skills and culture the company is looking for. For example, it determines whether the job seeker answers questions with confidence.

[0989] Step 9:

[0990] The server provides the results of the suitability assessment to the company's HR personnel and job seekers. The company's HR personnel can check the assessment results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own assessment results and understand their suitability for the company.

[0991] Examples:

[0992] A typical example of a prompt would be "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python," and the AI ​​interviewer would ask questions based on this. As a result, the accuracy of matching between companies and job seekers is improved, and interviews can be conducted efficiently using the virtual space.

[0993] 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.

[0994] 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.

[0995] 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.

[0996] [Fourth embodiment]

[0997] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0998] 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.

[0999] 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).

[1000] 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.

[1001] 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.

[1002] 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).

[1003] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] 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.

[1009] 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."

[1010] This invention is a system that inputs company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Specifically, the AI ​​learns the company's philosophy and culture, as well as the job seeker's skill set and desired conditions, and then generates and evaluates appropriate interview sessions. The specific operation of the system is described in detail below.

[1011] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[1012] Next, job seekers use the device to enter their skill set, work history, and desired qualifications. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the device to the server and stored in a database as job seeker information.

[1013] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[1014] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[1015] The server analyzes the conversation data from the interview session and evaluates the job seeker's compatibility. The compatibility assessment evaluates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. For example, the conversation data can determine whether the job seeker is good at teamwork and has the necessary skills.

[1016] Finally, the server provides the evaluation results to both the company and the job seeker. HR personnel at the company can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[1017] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[1018] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[1019] The processing flow will be explained below.

[1020] Step 1:

[1021] The user (a company's HR staff) uses a terminal to enter company information, specifically the company's philosophy, culture, desired skill set, and desired employee profile. The entered data is sent from the terminal to the server.

[1022] Step 2:

[1023] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[1024] Step 3:

[1025] The user (job seeker) uses a terminal to enter job seeker information, specifically, skill set, work history, and desired conditions. The entered data is sent from the terminal to the server.

[1026] Step 4:

[1027] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[1028] Step 5:

[1029] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and required skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions.

[1030] Step 6:

[1031] The server evaluates the learning model, adjusts the optimal parameters, and then stores them in a database, forming learning models for the AI ​​interviewer and AI job seeker.

[1032] Step 7:

[1033] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[1034] Step 8:

[1035] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[1036] Step 9:

[1037] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[1038] Step 10:

[1039] The server generates answers based on an AI job seeker model and displays answers such as "I led projects at my previous workplace and led them to success" on the device.

[1040] Step 11:

[1041] The server records all data from the interview dialogue and uses NLP algorithms to analyze the dialogue, particularly to evaluate how well it matches the company's philosophy and skill requirements.

[1042] Step 12:

[1043] The server evaluates the degree of compatibility based on the conversation data and generates an evaluation result that indicates how well the job seeker's profile matches the company's philosophy, culture, and desired skill set.

[1044] Step 13:

[1045] The server generates an API request that notifies both the company and the job seeker of the evaluation results.

[1046] Step 14:

[1047] The terminal displays the feedback results to the user (the company's HR staff) and provides a list of candidates. It also displays the suitability evaluation results to the user (the job seeker) and provides information about the next steps.

[1048] Step 15:

[1049] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[1050] Step 16:

[1051] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[1052] Through the above process, the system efficiently achieves optimal matching between companies and job seekers.

[1053] Example 1

[1054] 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."

[1055] There is a need to efficiently and effectively match companies and job seekers, and improve the compatibility between them. Conventional methods require a lot of time and effort to determine whether the skills and desired conditions of job seekers match the talent a company is looking for. In addition, creating appropriate interview questions and evaluating answers is done manually, which can lead to subjectivity and reduced accuracy. A system is needed to solve these problems.

[1056] 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.

[1057] In this invention, the server includes means for inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating an interview session using the learning model, means for recording dialogue data, means for analyzing the recorded dialogue data, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing the company's philosophy and culture and the job seeker's skill set, and means for generating a trained AI model to be used. This makes it possible to objectively and efficiently evaluate the compatibility between the company and the job seeker and to match optimal personnel.

[1058] A "means for entering company information" is a device or software that allows a company to provide its philosophy, culture, desired skill sets, etc.

[1059] "Means for entering job seeker information" refers to devices or software that allow job seekers to provide their skill sets, work history, desired conditions, etc.

[1060] "Means for building a learning model from corporate information" refers to software or algorithms that allow an AI model to learn data such as a company's philosophy, culture, and desired skill sets based on input corporate information.

[1061] "Means for constructing a learning model from job seeker information" refers to software or algorithms that allow an AI model to learn data such as the job seeker's skill set, work history, and desired conditions based on the job seeker information entered.

[1062] A "means for generating an interview session using a trained model" is software or an algorithm that uses a trained AI model to generate question and answer dialogue in an interview.

[1063] A "means for recording dialogue data" is a device or software for storing data on the exchange of questions and answers that takes place during an interview session.

[1064] The "means for analyzing recorded dialogue data" is software or algorithms for analyzing the stored dialogue data and evaluating the content of questions and answers.

[1065] "Means for evaluating the compatibility between companies and job seekers based on dialogue data" refers to software or algorithms that objectively determine the compatibility between companies and job seekers based on analyzed dialogue data.

[1066] "Means for providing suitability assessment results" refers to a device or software for notifying both companies and job seekers of the assessment results.

[1067] "Means for analyzing a company's philosophy and culture, and a job seeker's skill set" refers to software or algorithms that extract and analyze the characteristics of each input information from the company and the job seeker.

[1068] The "means for generating the trained AI model to be used" refers to software or algorithms for training and running the AI ​​model using data on company information and job seeker information.

[1069] This invention is a system for inputting company information and job seeker information, and uses AI technology to achieve optimal matching between companies and job seekers. Below, we will explain in detail the procedures for specifically implementing this invention, as well as the hardware and software used.

[1070] First, a company's HR personnel uses a terminal to input company information, including the company's philosophy, culture, and desired skill set. For example, a specific requirement might be entered as "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to a server, which then stores it in a database as company information.

[1071] Next, the job seeker uses the terminal to enter their skill set, work history, desired conditions, etc. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[1072] The server builds an AI learning model based on this company information and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. This creates learning models for the AI ​​interviewer and AI job seeker. The specific software used includes AI algorithms that use natural language processing (NLP) technology.

[1073] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker generates answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would generate an answer like, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time and evaluated later.

[1074] The server analyzes conversation data from the interview session to evaluate compatibility. This evaluation includes how well the job seeker's profile matches the company's philosophy, culture, and desired skill set. The compatibility evaluation results are notified to both the company and the job seeker. The company's HR staff can check the evaluation results using a terminal and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results to understand their compatibility with the company.

[1075] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, a job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." The server learns this information and generates an interview session between an AI interviewer and an AI job seeker. By analyzing the dialogue data obtained from this interview session and evaluating the suitability, the company can quickly and efficiently find the best job seeker.

[1076] Prompt Sentence Examples

[1077] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[1078] In this way, the present invention is a system that can efficiently and effectively match companies and job seekers, achieving results that are satisfactory for both parties.

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Specific explanation of program processing

[1081] Step 1: Enter your company information

[1082] User (Corporate HR Person):

[1083] Input: Information such as company philosophy, culture, and desired skill sets.

[1084] Action: Enter the required company information into the device's input form.

[1085] Processing: Data entered into the form is checked for accuracy through validation.

[1086] Output: Validated company information data.

[1087] Action: Data is sent to the server.

[1088] Step 2: Enter job seeker information

[1089] User (job seeker):

[1090] Input: Information about the job seeker, such as their skill set, work history, and desired qualifications.

[1091] Action: Enter your information into the device's input form.

[1092] Processing: Data entered into the form is checked for accuracy through validation.

[1093] Output: Validated job candidate information data.

[1094] Action: Data is sent to the server.

[1095] Step 3: Save your company and job candidate information

[1096] server:

[1097] Input: Validated company and job applicant information data.

[1098] What it does: Stores company and job seeker information in a database.

[1099] Process: Data is inserted into the database table.

[1100] Output: The record ID stored in the database.

[1101] Step 4: Training the AI ​​model

[1102] server:

[1103] Input: Company and candidate information stored in a database.

[1104] What it does: Retrieves company and job candidate information from a database.

[1105] Processing: Using the acquired data, analyze the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions.

[1106] Output: Feature data as the analysis result.

[1107] How it works: Train an AI model using feature data.

[1108] Step 5: Save the trained AI model

[1109] server:

[1110] Input: A trained AI model.

[1111] What it does: Saves the trained AI model on the server.

[1112] Processing: Serialize the model and save it to storage.

[1113] Output: The path of the AI ​​model saved in storage.

[1114] Step 6: Generate interview sessions

[1115] server:

[1116] Input: A trained AI model, company information, and job candidate information.

[1117] What it does: Loads an AI model and generates an interview session.

[1118] Processing: Generate appropriate questions from the company's perspective and generate answers from the job seeker's perspective.

[1119] Output: Interaction data from the interview session.

[1120] How it works: The interview session is recorded in real time.

[1121] Step 7: Record and analyze interaction data

[1122] server:

[1123] Input: Interaction data from the interview session.

[1124] What it does: Records interaction data and stores it in a database.

[1125] Processing: Analyze the recorded dialogue data using natural language processing techniques.

[1126] Output: Parsed interaction data.

[1127] How it works: The analysis results are used to input data into a model that evaluates the compatibility between companies and job seekers.

[1128] Step 8: Goodness of fit assessment

[1129] server:

[1130] Input: Parsed interaction data.

[1131] What it does: Runs the model to evaluate goodness of fit.

[1132] Processing: Calculate the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile.

[1133] Output: Goodness of fit evaluation results.

[1134] Behavior: Saves the results of the relevance evaluation to a database.

[1135] Step 9: Notification of evaluation results

[1136] Terminals (for corporate HR personnel and job seekers):

[1137] Input: Relevance assessment results stored in the database.

[1138] Behavior: Obtains evaluation results to display on the device.

[1139] Processing: Converts the data into a different format and displays it on a dashboard.

[1140] Output: The displayable evaluation results.

[1141] How it works: The company's HR staff reviews the assessment results and shortlists the most suitable candidates, and job seekers also review their own assessment results to understand their compatibility with the company.

[1142] Specific prompt examples

[1143] "We're looking for an engineer for a new project. Our company philosophy is teamwork-oriented, and we're looking for Java and Python skills. Generate the best interview questions and answers based on the candidate's experience and skill set."

[1144] (Application example 1)

[1145] 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."

[1146] It is extremely important for companies to find the right talent quickly and effectively, but traditional methods are often cumbersome and time-consuming. It also makes it difficult for job seekers to find the best company for them. In particular, when searching for personnel specializing in factory robot maintenance, specialized skill sets are required, and compatibility with teamwork and corporate culture must also be considered. To solve these challenges, advanced matching technology is required.

[1147] 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.

[1148] In this invention, the server includes a means for registering company information and job seeker information in a database, a means for recommending optimal personnel using artificial intelligence technology, and a means for evaluating suitability based on dialogue data and generating a matching list based on the evaluation results. This enables companies to quickly and effectively match job seekers with optimal personnel, even for factory robot maintenance personnel.

[1149] "Company information" refers to detailed information about the company, such as its mission, culture, and the skill sets it seeks.

[1150] "Job Seeker Information" refers to detailed information about a job seeker, such as their skill set, work history, and desired qualifications.

[1151] A "learning model" is an algorithm constructed by artificial intelligence based on company information and job seeker information.

[1152] An "interview session" is a virtual interview generated by an AI interviewer with a company's perspective and an AI job seeker with a job seeker's perspective.

[1153] "Dialogue data" refers to records of questions and answers asked during an interview session.

[1154] "Fitness" is an indicator that shows how closely the company's requirements match the job seeker's profile.

[1155] "Means of registering in a database" is part of a system for storing and managing company information and job seeker information.

[1156] "Recommendation method" refers to the process of using artificial intelligence technology to suggest the best candidates for a company.

[1157] A "matching list" is a list of candidates who are best suited to a company, generated based on the results of a suitability assessment.

[1158] This invention is a system that inputs company information and job seeker information and uses AI technology to achieve optimal matching. It is particularly designed to provide effective matching for factory robot maintenance personnel.

[1159] First, a company's HR staff or user enters company information using a terminal. This company information includes the company's mission, culture, and desired skill set. For example, specific requirements may include, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." The entered company information is sent to a server and registered in a database.

[1160] Next, job seekers use the same terminal to enter their skillset, work history, and desired qualifications, including specific information such as "five years of software engineering experience, fluent in Java and Python." The job seeker information is also sent to the server and registered in the database.

[1161] The server uses AI technology to build a learning model based on registered company and job seeker information. The learning model understands the company's philosophy and culture, the desired skill set, and the job seeker's skill set, work history, and desired conditions. AI frameworks such as TensorFlow are used in this step.

[1162] Once learning is complete, the server generates an interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker would respond, "At my previous workplace, I led a project and led it to success." This conversation data is recorded in real time.

[1163] The server analyzes the recorded conversation data and evaluates the compatibility between the company and the job seeker. This evaluation includes the degree to which the company's philosophy, culture, and desired skill set match the job seeker's profile. The results of the compatibility evaluation are provided to both the company and the job seeker.

[1164] For example, a company's input data might include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python." Meanwhile, job seeker data might include, "Five years of software engineering experience and a strong proficiency in Java and Python." Based on this data, the generative AI model suggests optimal matches. Examples of prompts used in interview sessions include, "Our company values ​​teamwork and is seeking candidates with proficiency in Java and Python" and "Job seeker has five years of software engineering experience and is strong in Java and Python."

[1165] This system will enable quick and effective matching of companies and job seekers for factory robot maintenance personnel.

[1166] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1167] Step 1:

[1168] First, the user inputs company information. The input company information includes the company's mission, culture, and desired skill set. For example, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, and the server registers the received company information in a database. Input: Company information, Output: Company information saved in the database

[1169] Step 2:

[1170] Next, the job seeker enters their skill set, work history, and desired conditions. This includes specific information such as "I have five years of software engineering experience and am proficient in Java and Python." This input is also sent from the terminal to the server and registered in the database as job seeker information. Input: Job seeker information, Output: Job seeker information saved in the database

[1171] Step 3:

[1172] The server uses artificial intelligence technology to build a learning model based on registered company information and job seeker information. This learning model is generated using AI frameworks such as TensorFlow. From company information, the company's philosophy, culture, and required skill set are understood, and from job seeker information, the job seeker's skill set, work history, and desired conditions are understood. Input: Company information and job seeker information from the database, Output: Built learning model

[1173] Step 4:

[1174] Once the learning is complete, the server generates an interview session. In the interview session, a virtual interview is conducted by an AI interviewer with the perspective of the company and an AI job seeker with the perspective of the job seeker. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "I led a project at my previous workplace and led it to success." Input: Learning model, Output: Generated interview session

[1175] Step 5:

[1176] The server records interview sessions in real time and analyzes the dialogue data. The analyzed dialogue data is used to evaluate the compatibility between companies and job seekers. Input: Interview session dialogue data, Output: Analyzed dialogue data

[1177] Step 6:

[1178] The server evaluates the compatibility between the company and the job seeker based on the analyzed dialogue data. This evaluation measures how well the company's philosophy, culture, and desired skill set match the job seeker's profile. Input: Analyzed dialogue data, Output: Compatibility evaluation results

[1179] Step 7:

[1180] Finally, based on the results of the compatibility evaluation, the server generates an optimal matching list. This list is provided to both companies and job seekers, allowing companies to quickly find suitable personnel and job seekers to understand which companies are best suited to them. Input: Compatibility evaluation results, Output: Generated matching list

[1181] The above is the specific processing flow of the system that realizes optimal matching of factory robots with maintenance personnel.

[1182] 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.

[1183] This invention is a system that inputs company information and job seeker information and builds a learning model based on each piece of information. Furthermore, by combining it with an emotion engine, the emotions of users (HR personnel and job seekers) are analyzed in real time during the interview session, and the results are reflected in the evaluation of suitability. The specific operation of the system is described in detail below.

[1184] First, the user (a company's HR staff) uses a terminal to input company information. For example, they might input specific requirements such as, "Our company values ​​teamwork and is seeking personnel who are proficient in Java and Python." This information is sent from the terminal to the server, which then stores it in a database as company information.

[1185] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they can input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in the database as job seeker information.

[1186] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[1187] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[1188] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, it can determine whether a user (job seeker) is nervous during an interview and provide a positive or negative evaluation.

[1189] The server integrates and analyzes the dialogue data and emotional data from the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy and culture, the desired skill set, and the job seeker's profile and emotional data match. For example, the dialogue data and emotional data can be used to determine whether the job seeker is good at teamwork, has the necessary skills, and shows appropriate emotional responses.

[1190] Finally, the server notifies both the company and the job seeker of the evaluation results. HR personnel at the company can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[1191] As a concrete example, consider a software development company looking to recruit engineers for a new project. The company enters company information such as "We value teamwork and require Java and Python skills." Meanwhile, the job seeker enters job seeker information such as "I have five years of experience as a software engineer, have served as a team leader, and am proficient in Java and Python." Based on this information, the server builds a learning model and conducts an interview session. During the interview session, an emotion engine analyzes the job seeker's facial expressions and tone of voice to detect emotions such as "confident." The dialogue data and emotion data are then used to evaluate suitability, allowing the company to quickly and efficiently find the best candidate.

[1192] In this way, the present invention is a system that efficiently and effectively matches companies and job seekers, and by taking emotional data into consideration, provides a more accurate evaluation of suitability.

[1193] The processing flow will be explained below.

[1194] Step 1:

[1195] The user (a company's HR staff member) uses a terminal to enter company information. Specifically, the user enters the company's philosophy, culture, and the desired skill set and profile of the employee. For example, the user might enter requirements such as "Our company values ​​teamwork and is seeking employees who are proficient in Java and Python." This information is then sent from the terminal to the server.

[1196] Step 2:

[1197] The server receives the company information and stores it in a database, then performs data quality checks and pre-processes the data (normalization, tokenization, etc.) as needed.

[1198] Step 3:

[1199] The user (job seeker) uses a terminal to enter job seeker information. Specifically, they enter their skill set, work history, and desired conditions. For example, they enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server.

[1200] Step 4:

[1201] The server receives the job applicant information and stores it in a database. It then performs data quality checks, just like with company information, and performs data preprocessing if necessary.

[1202] Step 5:

[1203] The server builds an AI learning model based on preprocessed company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[1204] Step 6:

[1205] The server evaluates the learning model, adjusts the optimal parameters, and then saves them in a database, thereby finalizing the learning models for the AI ​​interviewer and AI job seeker.

[1206] Step 7:

[1207] The server references the trained model and the newly applied job applicant data to generate an appropriate interview session, generates an API request to start the interview session, and sends a notification to the device.

[1208] Step 8:

[1209] The terminal displays a notification to the user (the company's HR staff) that the interview has started and provides an interface. Similarly, the terminal also notifies the user (the job seeker) that the interview has started.

[1210] Step 9:

[1211] The server manages the interview session in real time, and the AI ​​interviewer generates questions from the company's perspective, such as "Tell me about your teamwork experience."

[1212] Step 10:

[1213] The server generates an answer based on the AI ​​job seeker model and displays it on the user's (job seeker's) device. For example, the answer generated might be, "I led a project at my previous workplace and led it to success."

[1214] Step 11:

[1215] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. For example, if a user (job seeker) is judged to be "confident," the engine collects emotional data.

[1216] Step 12:

[1217] The server records interview dialogue data and emotional data, and then uses NLP algorithms to analyze the dialogue content and emotional data, particularly to evaluate how well the candidate fits the company's philosophy and skill requirements.

[1218] Step 13:

[1219] The server combines the dialogue data and emotional data to assess suitability and generate an evaluation result based on the company's philosophy and culture, the desired skill set, the candidate's profile, and the emotional data detected during the interview.

[1220] Step 14:

[1221] The server notifies both the company and the job seeker of the evaluation results. The user (the company's HR staff) can check the evaluation results using a terminal and create a list of the most suitable candidates. The user (job seeker) can also check their own evaluation results and understand their compatibility with the company.

[1222] Step 15:

[1223] The server generates the optimal matching list based on all interview data and evaluation results and sends it to the company's terminal.

[1224] Step 16:

[1225] The terminal displays a matching list to the user (a company's HR staff) and provides an interface for selecting the most suitable candidate.

[1226] In this way, by combining emotional data, it is possible to further improve the accuracy of matching between companies and job seekers.

[1227] Example 2

[1228] 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."

[1229] Conventional systems for matching companies and job seekers often rely on a simple match between the company's requirements and the job seeker's skill set, and it is difficult to evaluate compatibility by taking into account conversational data and emotional data during the interview session. This makes it difficult to identify job seekers who are a good fit with the company's philosophy and culture, resulting in a problem of reduced matching accuracy.

[1230] 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.

[1231] In this invention, the server includes means for inputting company information and job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data and emotion data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data and emotion data, and means for providing the compatibility evaluation results. This enables compatibility evaluation based on a comprehensive analysis of the dialogue data and emotion data, thereby achieving more accurate matching between companies and job seekers.

[1232] "Company information" refers to information about the company's philosophy, culture, desired skill sets, and other requirements.

[1233] "Job Seeker Information" refers to information about a job seeker's skill set, work history, and desired conditions.

[1234] The "learning model" is an artificial intelligence model that understands the characteristics of companies and job seekers based on input company and job seeker information, and conducts interview sessions.

[1235] An "interview session" is a process in which an AI interviewer and an AI job seeker conduct a virtual interview, recording and analyzing the interactions between users (HR personnel and job seekers) in real time.

[1236] "Dialogue data" refers to data regarding the content of questions and answers recorded during an interview session.

[1237] "Emotional data" refers to data that includes emotional characteristics such as facial expressions, tone of voice, and word choice of the user that are analyzed during the interview session.

[1238] "Fit" is an evaluation value that indicates how well a company's philosophy, culture, and desired skill set match the job seeker's skill set, work history, desired conditions, and emotional data.

[1239] The "results of compatibility evaluation" are results regarding the compatibility between a company and a job seeker, evaluated based on dialogue data and emotion data.

[1240] This invention is a system that inputs company information and job seeker information and builds a learning model based on that information. Furthermore, by using an emotion engine, the system analyzes the emotions of users (HR personnel and job seekers) in real time during the interview session and reflects the results in the evaluation of suitability. The detailed configuration and operation of the system are described below.

[1241] Hardware and software used

[1242] The server receives and stores company and job seeker information, and has multiple functions for building learning models and generating interview sessions. The software running on the server includes databases (e.g., MySQL), AI model building tools (e.g., TensorFlow), and emotion analysis software (e.g., Microsoft Azure Emotion API).

[1243] The terminal is a device that users use to input company and job seeker information, and is usually a PC or tablet.

[1244] Program processing explanation

[1245] The user (a company's HR staff) first uses a terminal to input company information, such as specific requirements like "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to the server, which then stores it in a database as company information.

[1246] Next, the user (job seeker) uses the terminal to input their skill set, work history, and desired conditions. For example, they input information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server, which then stores it in a database as job seeker information.

[1247] The server builds an AI learning model based on company and job seeker information. Specifically, it extracts the company's philosophy, culture, and desired skill set from the company information, and the job seeker's skill set, work history, and desired conditions from the job seeker information. Based on this information, learning models for the AI ​​interviewer and AI job seeker are created.

[1248] Once the learning model is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[1249] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during the interview session to determine their emotions in real time. For example, it can analyze whether a job seeker is nervous during the interview. This information is sent to the server along with the dialogue data.

[1250] The server integrates and analyzes the dialogue and emotional data obtained during the interview session to assess the degree of fit. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the job seeker's profile and emotional data. For example, it determines whether the job seeker excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[1251] Finally, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[1252] Examples of concrete examples and prompts

[1253] As a concrete example, consider the case of a software development company recruiting engineers for a new project. The user (the company's HR person) enters company information into the terminal, such as "We value teamwork and require Java and Python skills." Meanwhile, the user (job seeker) enters job seeker information, such as "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python."

[1254] This information is sent to a server and stored in a database. The server uses this information to build a learning model and conduct the interview session. The emotion engine analyzes the job seeker's facial expressions and tone of voice during the interview session to detect emotions such as "confidence." The server then evaluates the candidate's suitability based on the dialogue data and emotion data, and notifies the company and job seeker of the evaluation results. This allows companies to find the best job seekers quickly and efficiently.

[1255] Example prompt sentence:

[1256] "Our system builds an AI learning model based on company and job seeker information, and analyzes user sentiment in real time during interview sessions. Specifically, by inputting the company name, job description, and desired skill set, along with the job seeker's skill set and work history, we can match the two appropriately. For example, we can match companies that value Java and Python skills with job seekers who possess those skills."

[1257] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1258] Step 1:

[1259] The user (a company's HR staff) uses a terminal to enter company information. The input data includes the company's philosophy, culture, and desired skill set. The entered information is sent from the terminal to the server. The server receives this data and stores it in a database. Specifically, the user enters information into a form and clicks the "Submit" button, which sends the data to the server.

[1260] Step 2:

[1261] The user (job seeker) uses a terminal to input their skill set, work history, and desired conditions. The input data includes the job seeker's technical skills, past work experience, and desired work environment. The input information is also sent from the terminal to the server. After receiving this data, the server stores it in a database. Specifically, the data is sent when the job seeker enters their information into the form and clicks the "Submit" button.

[1262] Step 3:

[1263] The server builds an AI learning model based on company and job seeker information stored in the database. This learning model is generated by understanding the company's values, culture, and requirements, and incorporating the job seeker's skill set, work history, and desired conditions. Data processing involves converting the company and job seeker information into feature vectors, and training the model using a machine learning algorithm (e.g., TensorFlow). Specifically, the company and job seeker information is preprocessed and converted into an input format for the AI ​​model, after which the model is trained.

[1264] Step 4:

[1265] Once the learning model is generated, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks pre-set questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. The generated interview session is presented to the user. The input is the constructed learning model, and the output is a simulated interview session with questions and answers. Specifically, the scenario for the interview session is automatically generated, and its contents are displayed to the user.

[1266] Step 5:

[1267] The emotion engine analyzes the emotions of users (HR personnel and job seekers) in real time during an interview session. Inputs include the user's facial expressions, tone of voice, and choice of words, and the emotion engine analyzes this data to determine the user's emotional state in real time. This is done using emotion analysis software such as the Microsoft Azure Emotion API. Specifically, while the user is participating in a video interview, the video and audio data is analyzed in real time.

[1268] Step 6:

[1269] The server integrates and analyzes the dialogue data and emotional data from the interview session to evaluate the compatibility between the company and the job seeker. The input data is dialogue data and emotional data, and a compatibility score is generated as the output. Data processing involves converting each dataset into a feature vector and calculating compatibility using statistical and machine learning algorithms (e.g., decision trees, SVM). Specifically, the compatibility of the job seeker with the company is quantified based on the dialogue content and emotional responses.

[1270] Step 7:

[1271] Finally, the server notifies both the company and the job seeker of the evaluation results. The input is the compatibility evaluation results, and the output is displayed on the company's and job seeker's devices. Specifically, the notified data is displayed to each user via email or dashboard, allowing the company's HR staff to create a list of the most suitable candidates. Job seekers can check their own evaluation results and understand their compatibility with the company.

[1272] (Application example 2)

[1273] 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."

[1274] Current interview systems have difficulty acquiring and analyzing valid data in real time when assessing the compatibility between job seekers and companies. In particular, analysis of job seekers' emotional states and voice data is insufficient, often resulting in a lack of information needed for appropriate matching. Furthermore, due to limitations on physical interview locations, job seekers must physically travel to the interview venue, which is time-consuming and costly. This creates a significant burden on both companies and job seekers.

[1275] 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 inputting company information, means for inputting job seeker information, means for constructing a learning model from the company information, means for constructing a learning model from the job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between the company and the job seeker from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining the emotional state, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space. This makes it possible to evaluate the compatibility between companies and job seekers with high accuracy and analyze the emotional state and dialogue content during the interview in real time. Furthermore, using a virtual space allows interviews to be conducted without being restricted by physical location, thereby reducing time and cost.

[1276] "Company information" refers to information such as the company's philosophy, culture, required skill sets, and working conditions.

[1277] "Job seeker information" refers to information such as the job seeker's skill set, work history, desired conditions, and self-promotion.

[1278] A "learning model" is an AI model that is built based on company information and job seeker information to evaluate suitability.

[1279] An "interview session" refers to a simulated dialogue between a company and a job seeker using a learning model.

[1280] "Dialogue data" is question and answer data recorded during an interview session.

[1281] "Fitness" is an index that evaluates how well a company's requirements match the abilities and characteristics of a job seeker.

[1282] "Means for analyzing video data in real time and determining emotional state" refers to a system that uses video data acquired from a camera to analyze facial expressions and determine emotions.

[1283] The "means for analyzing voice data and converting it into text data" is a voice recognition system that converts voice obtained from a microphone into text.

[1284] "Virtual space" means a digital space recreated using virtual reality technology.

[1285] This invention is a system that inputs company information and job seeker information and builds a learning model based on the respective information. The system configuration includes means for inputting company information, means for inputting job seeker information, means for building a learning model from the company information and job seeker information, means for generating interview sessions using the learning model, means for recording and analyzing dialogue data through the interview sessions, means for evaluating the compatibility between companies and job seekers from the dialogue data, means for providing the compatibility evaluation results, means for analyzing video data in real time and determining emotional states, means for analyzing audio data and converting it into text data, and means for conducting interviews between companies and job seekers in a virtual space.

[1286] First, a company's HR staff uses a terminal to input company information, such as specific requirements like, "Our company values ​​teamwork and is seeking personnel with Java and Python skills." This information is sent from the terminal to a server, which then stores it in a database as company information.

[1287] Next, job seekers use the terminal to enter their skill set, work history, desired conditions, etc. For example, they may enter information such as "I have five years of software engineering experience and am proficient in Java and Python." This information is also sent from the terminal to the server and stored in a database as job seeker information.

[1288] The server builds an AI learning model based on company and job seeker information. From the company information, it understands the company's philosophy, culture, and desired skill set, and from the job seeker information, it understands the job seeker's skill set, work history, and desired conditions. This forms a learning model for the AI ​​interviewer and AI job seeker.

[1289] Once the learning is complete, the server generates an appropriate interview session. In the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. For example, the AI ​​interviewer might ask, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success." This conversation is recorded in real time.

[1290] The emotion engine analyzes the facial expressions, tone of voice, and word choice of users (HR personnel and job seekers) during interview sessions to determine their emotions in real time. Specifically, it analyzes facial expressions using video data acquired from a camera to determine their emotional state. It also converts audio acquired from a microphone into text and records the conversation.

[1291] For example, a company's HR representative enters a virtual conference room, and a job seeker also joins the virtual conference room. The system captures the job seeker's face with a camera, performs real-time emotion analysis, and records their emotional state during the interview. At the same time, the system converts the job seeker's voice responses into text using speech recognition and saves the interview session details.

[1292] Finally, the server integrates and analyzes the dialogue and emotional data from the interview session to assess the job candidate's suitability. The fit assessment evaluates how well the company's philosophy, culture, and desired skill set match the candidate's profile and emotional data. For example, the dialogue and emotional data can be used to determine whether the candidate excels in teamwork, possesses the necessary skills, and displays appropriate emotional responses.

[1293] Based on this, the server notifies both the company and the job seeker of the evaluation results. The company's HR staff can check the evaluation results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own evaluation results and understand their compatibility with the company.

[1294] A specific example of a prompt is as follows:

[1295] "Five years of experience as a software engineer and team leader. Proficient in Java and Python."

[1296] In this way, the present invention evaluates the compatibility between a company and a job seeker with high accuracy, analyzes the emotional state and dialogue content during the interview in real time, and realizes effective and efficient interviews using virtual space.

[1297] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1298] Step 1:

[1299] The user (a company's HR representative) uses a terminal to input company information. The input company information includes the company's philosophy, culture, required skill set, working conditions, etc. The company information sent from the terminal is stored in a database by the server. This information is later used to build a learning model.

[1300] Step 2:

[1301] The user (job seeker) uses a terminal to input their own job seeker information. The input job seeker information includes skill set, work history, desired conditions, self-promotion, etc. The job seeker information sent from the terminal is stored in a database by the server. This data, like company information, is also used to build the learning model.

[1302] Step 3:

[1303] The server builds a learning model based on the saved company and job seeker information. Specifically, it incorporates elements such as the company's philosophy, desired skills, and work history to create models of the AI ​​interviewer and AI job seeker. This prepares the server to evaluate the compatibility between the company and the job seeker.

[1304] Step 4:

[1305] The server uses the constructed learning model to generate an interview session. During the interview session, the AI ​​interviewer asks questions from the company's perspective, and the AI ​​job seeker answers from the job seeker's perspective. Based on the generated prompt, the AI ​​interviewer might ask, for example, "Tell me about your teamwork experience," and the AI ​​job seeker might respond, "At my previous workplace, I led a project and led it to success."

[1306] Step 5:

[1307] Users (corporate HR personnel and job seekers) participate in interviews in a virtual space. Specifically, the HR personnel and job seekers each log in to a virtual conference room and the interview session begins. Dialogue takes place in real time using device devices such as cameras and microphones.

[1308] Step 6:

[1309] The server analyzes the video data in real time during the interview session to determine the emotional state. The video data acquired from the camera is analyzed using a facial recognition algorithm and recorded as emotional data. For example, emotional states such as nervousness or confidence can be identified.

[1310] Step 7:

[1311] The server analyzes the audio data captured during the interview session and converts it into text data. The audio data collected from the microphone is converted into text data through a voice recognition system and recorded as the conversation. Specific questions and answers are then stored in a database.

[1312] Step 8:

[1313] The server integrates and analyzes the conversation data and emotional data acquired in real time to evaluate the compatibility between the company and the job seeker. Specifically, it compares the emotional state and content of the conversation to evaluate how well the candidate matches the skills and culture the company is looking for. For example, it determines whether the job seeker answers questions with confidence.

[1314] Step 9:

[1315] The server provides the results of the suitability assessment to the company's HR personnel and job seekers. The company's HR personnel can check the assessment results using their terminals and shortlist the most suitable candidates. Similarly, job seekers can check their own assessment results and understand their suitability for the company.

[1316] Examples:

[1317] A typical example of a prompt would be "I have five years of experience as a software engineer and have served as a team leader. I am proficient in Java and Python," and the AI ​​interviewer would ask questions based on this. As a result, the accuracy of matching between companies and job seekers is improved, and interviews can be conducted efficiently using the virtual space.

[1318] 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.

[1319] 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.

[1320] 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.

[1321] 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.

[1322] FIG. 9 illustrates 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 behaviors 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.

[1323] 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.

[1324] 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).

[1325] 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.

[1326] 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."

[1327] 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.

[1328] 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).

[1329] 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.

[1330] 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.

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1338] 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.

[1339] The following is further disclosed regarding the above embodiment.

[1340] (Claim 1)

[1341] A means for inputting company information;

[1342] a means for inputting job seeker information;

[1343] A means of building learning models from company information;

[1344] A means for constructing a learning model from job seeker information;

[1345] a means for generating an interview session using the learned model;

[1346] a means of recording and analyzing interaction data throughout the interview session;

[1347] A means of evaluating the compatibility between companies and job seekers from dialogue data, and

[1348] means for providing a goodness of fit assessment result;

[1349] A system including:

[1350] (Claim 2)

[1351] 2. The system according to claim 1, wherein the company information input means and the job seeker information input means are each performed via a terminal.

[1352] (Claim 3)

[1353] 2. The system according to claim 1, further comprising means for generating an optimal matching list based on the compatibility evaluation result.

[1354] "Example 1"

[1355] (Claim 1)

[1356] A means for inputting company information;

[1357] a means for inputting job seeker information;

[1358] ...

Claims

1. A means for inputting company information; a means for inputting job seeker information; A means of building learning models from company information; A means for constructing a learning model from job seeker information; means for generating an interview session using the learned model; a means of recording and analyzing interaction data through interview sessions; A means of evaluating the compatibility between companies and job seekers from dialogue data, and means for providing a goodness of fit assessment result; A system including:

2. 2. The system according to claim 1, wherein the company information input means and the job seeker information input means are each performed via a terminal.

3. 2. The system according to claim 1, further comprising means for generating an optimal matching list based on the results of the compatibility evaluation.

Images