system

Abstract

We provide the system. [Solution] A means of receiving student information and generating student avatars based on that information, A means of receiving information on the personnel needs of a company and generating interviewer avatars based on that information, A method for generating student avatars and interviewer avatars to conduct interviews with each other and evaluate the degree of matching based on the results, A means of notifying each user of the evaluation results, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern job-hunting activities, there is a problem that mismatches between students and companies frequently occur, causing early departures and increased recruitment costs. The main cause of such problems is that the recruitment process proceeds without students and companies fully understanding each other's characteristics and cultures. Therefore, there is a need to provide an effective matching system for both students and companies to find suitable partners.

Means for Solving the Problems

[0005] This invention provides a system that generates student avatars based on student information and interviewer avatars based on the personnel information sought by companies. In this system, the generated avatars conduct mock interviews using voice or text, and the degree of matching is evaluated based on the results. The evaluation results are notified to the user, making it easier for both students and companies to choose the appropriate partner. This reduces mismatches and improves the efficiency of the recruitment process.

[0006] A "student avatar" is a virtual character that reflects the individuality and characteristics of a student. It is generated based on the student's information and represents the student in mock interviews.

[0007] An "interviewer avatar" is a virtual character generated based on the ideal candidate profile sought by a company. It mimics the company's values ​​and required skills, and represents the interviewer in a mock interview.

[0008] A "mock interview" is a simulated interview conducted using natural language between generated avatars, and is a process used to verify the suitability of students and companies.

[0009] "Matching score" is a numerical indicator that quantifies the degree of compatibility between a student's and a company's aptitudes, calculated based on the results of mock interviews. It is used to evaluate the appropriate match between a company and a suitable candidate.

[0010] The "evaluation results" are presented to the user as an analysis of performance, including the degree of matching, based on data obtained from the dialogue between avatars during the mock interview. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the 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.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0025] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention provides a system for achieving appropriate matching between students and companies. In this system, an avatar corresponding to each user is generated when the user inputs their information into a terminal.

[0033] The user (student) enters personal information such as their educational background, skills, and interests into the terminal. The terminal sends this data to the server. Based on the received information, the server uses generative AI technology to generate a student avatar that reflects the student's characteristics. This avatar virtually reproduces the student's personality and background.

[0034] On the other hand, users (companies) input their desired candidate profile and corporate culture characteristics into a terminal. This information is also sent to the server, which generates interviewer avatars that match the company's values ​​and desired skills. These avatars mimic the ideal candidate profile that the company seeks.

[0035] The server automatically matches the generated student avatar with the interviewer avatar and begins a mock interview. The mock interview is conducted via voice or text, with the avatars exploring each other's suitability through predetermined questions and answers. Natural language processing and machine learning technologies are used in this process.

[0036] After the interview, the server analyzes the conversation between the avatars and calculates the degree of matching. This calculated degree of matching is provided as feedback to both the student and the company, clearly indicating how well they are a good match. This feedback helps improve future job hunting activities and allows companies to develop optimal recruitment methods.

[0037] For example, if a student provides information indicating they have a strong interest in programming, the server generates a student avatar that reflects that information. If a company provides information indicating they are looking for creative engineers, the server generates an interviewer avatar that asks creative questions. In a mock interview, the student avatar talks about their project experience, and the interviewer avatar asks for details about that project, thereby evaluating their specific suitability.

[0038] This invention is expected to enable effective matching between students and companies, significantly improving the efficiency of the recruitment process.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user (student) enters personal information such as their educational background, skills, and hobbies into the terminal. The terminal then sends this information to the server.

[0042] Step 2:

[0043] The user (company) inputs information about the desired employee profile and corporate culture into a terminal. The terminal then sends this information to the server.

[0044] Step 3:

[0045] The server uses AI generation technology based on information received from students to generate student avatars that reflect the students' characteristics.

[0046] Step 4:

[0047] The server uses AI technology to generate interviewer avatars that mimic the company's values ​​and desired skills, based on information received from the company.

[0048] Step 5:

[0049] The server matches student avatars with interviewer avatars and sets up a mock interview scenario.

[0050] Step 6:

[0051] The server uses voice or text based on a pre-configured scenario to have avatars conduct mock interviews with each other.

[0052] Step 7:

[0053] The server analyzes the content of the mock interview dialogue and calculates the degree of matching.

[0054] Step 8:

[0055] The server notifies each user via their device of the calculated matching score and feedback on the conversation content.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Traditionally, achieving a proper match between students and companies has required specialized knowledge in interviews and human resources, resulting in significant time and expense. Furthermore, inefficient management and utilization of personal and company information have led to challenges such as students being unable to find suitable companies and companies struggling to find ideal talent. This invention aims to solve these problems.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for receiving personal information and generating a personal avatar based on that information, means for receiving characteristic information requested by an organization and generating an organization avatar based on that information, and means for conducting interview simulations between the personal avatar and the organization avatar using a generation AI model and evaluating the degree of fit based on the results. This enables effective matching between students and companies while significantly reducing time and costs.

[0061] "Personal information" refers to data that indicates personal attributes such as educational background, skills, and interests, which are necessary for avatar generation.

[0062] A "personal avatar" is a video or text character created by an AI model based on personal information, which virtually represents the characteristics of that individual.

[0063] "Organizational characteristic information" refers to data that indicates the characteristics such as skills, values, and culture that a company or organization seeks.

[0064] An "organizational avatar" is a video or text character that virtually represents the ideal employee profile, created by an AI model based on the characteristics information sought by the organization.

[0065] A "generative AI model" is a technology that uses algorithms learned from large amounts of data to generate avatars based on input information from individuals or organizations.

[0066] "Interview simulation" is a virtual dialogue process in which generated individual avatars and organizational avatars conduct mock interviews through voice or text.

[0067] "Fit" is a score that indicates the degree of potential matching between an individual and an organization, calculated based on the results of an interview simulation.

[0068] This invention is a system that generates avatars based on the characteristics of individuals and organizations, and enables effective matching through virtual interviews. A specific example of this system is described below.

[0069] Each user (individual) enters personal information such as their educational background, skills, and interests into a terminal. This terminal can be, for example, a PC or smartphone. The entered information is sent to a server in real time. The server processes this information and uses a generative AI model to generate a personalized avatar that reflects the individual's characteristics. This generative AI model is pre-trained on a large dataset.

[0070] On the other hand, the user (organization) inputs the desired characteristics and cultural features into the terminal. This information is similarly sent to the server, which then generates an organizational avatar representing the ideal employee profile. This, too, is realized by a generative AI model.

[0071] The generated individual and organizational avatars are automatically matched by the server, and the interview simulation begins. This simulation is conducted using voice or text and is implemented using WebRTC or chatbot frameworks. Natural language processing technology is used throughout the interview process to analyze the interactions between the avatars.

[0072] As a practical example, if a user (individual) provides information such as "I have a strong interest in programming," the server will generate a personal avatar that reflects their programming skills based on this information. If an organization provides information such as "We are looking for creative engineers," the server will generate an organizational avatar that asks creative questions in line with that request. In a mock interview, the personal avatar talks about their project experience, and the organizational avatar asks detailed questions about the project, and the degree of suitability is evaluated.

[0073] Example of a prompt:

[0074] "Based on the information entered by the students, generate avatars that highlight their programming skills. Conduct mock interviews to verify that the avatars match the skill sets required by the companies."

[0075] This system enables efficient matching between individuals and organizations, significantly reducing time and costs.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The user (individual) enters personal information such as educational background, skills, and interests into the terminal. The terminal structures the entered data and converts it into a format for transmission to the server. The input is output as JSON data and sent to the server. The server receives this data and prepares for the next processing step.

[0079] Step 2:

[0080] The server inputs data received from the user into a generative AI model. This data is used as a prompt for generating an avatar that reflects the individual's characteristics. Based on this prompt, the generative AI model runs its algorithm and outputs data for the individual avatar. This output is avatar data that visualizes and textualizes the individual's characteristics.

[0081] Step 3:

[0082] The user (organization) inputs information about the desired characteristics and culture into the terminal. The terminal converts the data into a format that the server can easily process and sends it to the server. This data is also output in JSON format and sent to the server.

[0083] Step 4:

[0084] The server inputs data received from the organization into a generating AI model. The model uses this data as a prompt to generate an organizational avatar that reflects the characteristics the organization desires, and outputs data for the organizational avatar. This data is avatar data that visualizes and textualizes the skills and values ​​the organization desires.

[0085] Step 5:

[0086] The server matches the generated individual avatar with the organization avatar. Using both avatar data sets, it then initiates an interview simulation. The simulation manages the interaction between the avatars using natural language processing techniques. This interaction takes place via voice calls or a chat interface, and interaction data is generated as output.

[0087] Step 6:

[0088] The server analyzes interaction data from the interview simulation. It uses machine learning algorithms to calculate the degree of fit from the input dialogue data. This degree of fit is output as a score indicating the compatibility between the individual and the organization.

[0089] Step 7:

[0090] The server provides feedback to each user (individual and organization) regarding the calculated fitness score. This feedback is generated as text and sent to the user's device. Users can then use this feedback to identify future strategies and areas for improvement.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Traditional recruitment processes often lacked opportunities for direct communication between students and companies, resulting in lower matching accuracy. Furthermore, understanding appropriate corporate cultures and required skills was difficult, causing students to miss out on opportunities to connect with companies that truly matched their abilities and interests. These challenges need to be addressed.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for receiving user information and generating a first virtual representation based on that information, means for receiving requirements requested by a company and generating a second virtual representation based on that information, and means for the generated first and second virtual representations to engage in a virtual dialogue with each other and evaluate the degree of suitability based on the results. This makes it possible to enable effective matching between students and companies and improve the efficiency of the recruitment process.

[0096] "Users" refer to students and companies that use the system to provide information and generate their own virtual representations.

[0097] A "virtual representation" is a digital avatar created using a generative AI model based on user information, and it virtually reproduces the user's characteristics.

[0098] "Interaction" refers to the mutual exchange and dialogue that takes place between virtual representations within a virtual space, and is used to evaluate the suitability and level of understanding between the two parties.

[0099] "Fit" is an index that indicates the degree of agreement in suitability and interests between users, calculated based on the results of interactions between virtual representations.

[0100] To implement this invention, a server connected to an information and communication network and terminals accessible by multiple users are required. Users (students) use the terminals to input information such as their academic background, skills, and interests. This information is transmitted to the server via the network. Based on the received information, the server uses a generative AI model to generate a virtual representation that reflects the characteristics of the student.

[0101] Meanwhile, corporate users also input information such as the requirements for the personnel they are looking for and their corporate culture through their terminals, and similarly send this information to the server. Based on this, the server generates virtual interviewers that match the skill sets required by the company.

[0102] The generated virtual representations interact with each other in a virtual space. This process involves constructing a virtual environment using software such as Unity, and utilizing natural language processing technology to analyze the dialogue and evaluate its relevance. The resulting evaluation is then scored as a relevance by the server and provided as feedback to both users.

[0103] For example, if a user enters "I am interested in AI technology," the server generates a virtual representation that reflects this. If a company user writes "We are looking for innovative engineers," a virtual interviewer is generated based on that information. In the simulated conversation, the virtual representation discusses specific projects and ideas, and its suitability is evaluated.

[0104] Examples of prompt messages include: "The student avatar has a deep interest in AI technology. The company avatar is seeking engineers who pursue innovation and will evaluate their suitability through concrete project experience."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The terminal prompts the user (student) to input information such as their educational background, skills, and interests. This input information is formatted as a user profile and sent to the server.

[0108] Step 2:

[0109] The server generates a virtual representation of the student using a generative AI model based on the received user profile. This process analyzes the input characteristic information and performs data processing to construct an appropriate avatar based on the results. The generated virtual representation is then used in the next interaction step.

[0110] Step 3:

[0111] On the other hand, the terminal allows users (companies) to input information such as the requirements for the personnel they are looking for and their corporate culture. This information is compiled into a company profile and sent to the server.

[0112] Step 4:

[0113] The server generates virtual interviewers suitable for each company based on their company profile. This generation process involves scrutinizing the company's values ​​and skill requirements, and performing data calculations to design corresponding virtual representations.

[0114] Step 5:

[0115] The server facilitates virtual interactions between generated student virtual representations and virtual company interviewers in a virtual space. Here, software such as Unity is used to provide a visual interface, and natural language processing techniques are employed to enable text and voice interactions. The content of the dialogue between the two is recorded and used to evaluate the degree of relevance.

[0116] Step 6:

[0117] The server analyzes data obtained from the interaction and parses the dialogue content through natural language processing. The analyzed data becomes input information for calculating the degree of fit, and the degree of matching is quantified through a scoring algorithm.

[0118] Step 7:

[0119] The server notifies both the student and the company of the calculated matching score as feedback. This feedback serves as a guide for self-improvement and strategy formulation in future recruitment activities.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention provides a matching system that takes into account the emotions of both students and companies. This system generates avatars based on user information, and when these avatars conduct mock interviews, it uses an emotion engine to recognize emotions during the conversation, thereby achieving more accurate matching.

[0122] The user (student) enters their information into a terminal. The terminal sends this data to a server. Based on this, the server uses a generation AI to create a student avatar that reflects the student's personality. Similarly, companies also enter their desired candidate profile into the server, and an interviewer avatar reflecting the company's characteristics is generated.

[0123] The generated avatars are matched by the server, and a mock interview begins. At this point, an emotion engine operates, analyzing the emotional state of the users (students and companies) in real time during the conversation between the avatars. Based on the recognized emotions, the server can adjust the interview's progress. This adjustment includes changing the content of questions and the pace of the conversation according to the emotions.

[0124] After the mock interview, the server analyzes emotional data and incorporates this emotional information into the matching score. As a result, in addition to matching based solely on skills and experience, emotional compatibility is also considered, leading to a more precise matching process. The evaluation results are notified to both the student and the company via their respective devices.

[0125] For example, if a student avatar feels slightly anxious during a mock interview, the emotion engine can detect this, and the server can instruct the interviewer avatar to soften their demeanor. Furthermore, if the company avatar is detected as being satisfied with the responses, it can emphasize additional positive feedback.

[0126] This invention, by taking into account the emotional states of students and companies, enables more suitable and sustainable matching in partnerships than conventional systems.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The user (student) enters personal information such as educational background, work experience, skills, and hobbies into the terminal. The terminal then sends the entered information to the server.

[0130] Step 2:

[0131] The user (company) inputs the desired skills, experience, and personality traits of the personnel into a terminal. This information, including the company culture and values, is then sent to the server.

[0132] Step 3:

[0133] The server uses a generation AI based on student information to create student avatars. These avatars are virtual characters that reflect the individuality of the students.

[0134] Step 4:

[0135] The server uses AI to generate interviewer avatars based on company information. These avatars are virtual characters that reflect the characteristics of the personnel the company is looking for.

[0136] Step 5:

[0137] The server combines the generated student avatar with the interviewer avatar and starts the mock interview session.

[0138] Step 6:

[0139] The server utilizes an emotion engine to analyze the emotional state of the student avatar and interviewer avatar's dialogue in real time during the mock interview. This analysis may include changes in voice tone and facial expressions.

[0140] Step 7:

[0141] The server dynamically adjusts the interview process using analysis results from the emotion engine. Specifically, it takes actions such as changing the content and order of questions based on the interviewee's emotions.

[0142] Step 8:

[0143] The server comprehensively analyzes the conversation content and emotional data after the interview to calculate the degree of matching. Emotional compatibility is also included in the evaluation criteria.

[0144] Step 9:

[0145] The server sends an evaluation summarizing the analysis results to the terminal, notifying users (students and companies) of the degree of matching and emotional feedback.

[0146] Step 10:

[0147] Based on the feedback received, users consider their next steps and repeat the process as needed.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] Traditional matching systems focus on skills and experience, failing to consider emotional compatibility, resulting in insufficient compatibility in actual partnerships. Furthermore, the inability to analyze emotional shifts during interviews and communication in real time and adjust conversations accordingly meant that truly valuable feedback was not being provided to both students and companies.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes means for receiving user information and generating individual virtual characters, means for receiving requirements for the work system and generating virtual characters for evaluators, and means for virtual characters to conduct simulated conversations and analyze their emotional states. This enables more precise and sustainable matching that takes emotional compatibility into account.

[0153] A "user" refers to an individual or group that uses the system to input their own information and confirms their suitability through matching and evaluation.

[0154] "Information" refers to data about the user's personality and preferences, specifically including data such as educational background, interests, and work experience.

[0155] A "virtual person" refers to an avatar digitally constructed using a generative AI model based on user or company information.

[0156] A "simulated dialogue" refers to a simulation in which generated virtual characters engage in a conversation, and is conducted based on an interview scenario.

[0157] "Emotional state" refers to an individual's psychological reactions and changes detected during simulated dialogue, and is analyzed from factors such as voice and facial expressions.

[0158] A "evaluator" is a virtual character created based on the company's requirements, and refers to an avatar that is responsible for asking questions and providing feedback in simulated conversations.

[0159] "Requirements for operational structure" refer to the type of personnel a company seeks and the skill sets expected for their roles.

[0160] "Matching score" refers to an indicator that shows the compatibility between a user and a company, and is quantified by taking into account skills and emotional factors.

[0161] "System" refers to the hardware and software configuration for integrating and executing the generation of virtual characters, the progression of simulated dialogues, sentiment analysis, and notification of evaluation results.

[0162] The following describes the "modes for carrying out the invention."

[0163] ---

[0164] The embodiment of this invention consists of a method in which a user, a terminal, and a server cooperate to build a virtual interview matching system. The user first inputs personal information and occupational preferences via the terminal. This terminal is equipped with an input support interface and has communication capabilities that enable secure data transmission.

[0165] The terminal sends the information entered by the user to the server. The communication protocol used here should preferably be one with enhanced security, such as HTTPS. Based on the received information, the server uses a generative AI model to generate a virtual person (avatar) that reflects the user's characteristics. This generation process can combine widely used image generation technologies such as DALL-E and natural language processing technologies. Similarly, the company's requirements are also sent to the server, and an evaluator avatar matching the company's desired candidate profile is generated.

[0166] The generated virtual characters and evaluator avatars begin a simulated dialogue on the server. This simulated dialogue utilizes speech recognition and natural language processing technologies for sentiment analysis. Specifically, sentiment analysis tools such as IBM Watson® are used to analyze subtle emotional changes during the conversation in real time. Based on these results, the server adjusts the content and pace of the dialogue.

[0167] Emotional state-based matching evaluation is performed after the simulated dialogue is completed. The server analyzes the accumulated emotional data to evaluate the compatibility between the user and the company with greater accuracy. This enables a more precise matching evaluation that incorporates emotional elements.

[0168] For example, a prompt message such as, "Generate an avatar based on the student's profile information and begin an emotion-based mock interview with the company. Next, analyze the emotional changes during the interview and reflect the results in the matching evaluation," is used, and the process proceeds accordingly.

[0169] This embodiment enables users and companies to build longer-term and more sustainable relationships through communication that takes emotional states into account.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] Users use the device to input their personal information and career preferences. Specifically, they enter their name, age, educational background, field of expertise, and desired job duties. The device temporarily stores this data in a database such as SQLite. This prepares the user's basic information data.

[0173] Step 2:

[0174] The terminal sends the information entered by the user to the server. Here, the HTTPS protocol is used to securely transfer the data. The server parses the received information in JSON format and converts it into a format usable by the generated AI model. The output of this step is user profile data that the AI ​​model can process.

[0175] Step 3:

[0176] The server uses a generative AI model to generate a virtual character based on user profile data. For example, it outputs an avatar that reflects the user's characteristics as an image using the DALL-E model. At this stage, an avatar with visual and auditory features based on user information is obtained.

[0177] Step 4:

[0178] The personnel information requested by companies is also entered into the server, and evaluator avatars are generated in the same way. This information is processed based on data provided in advance by companies, and avatars that reflect the characteristics of each company are output. In this way, the server maintains virtual representations of both students and companies.

[0179] Step 5:

[0180] The server initiates a simulated dialogue using the generated virtual character and evaluator avatar. It activates an emotion analysis engine and uses natural language processing technology to analyze the conversation between the avatars. At each step, avatar voice and text data are input, and an audio analysis tool outputs emotion changes in real time.

[0181] Step 6:

[0182] The server adjusts the content and flow of the simulated conversation based on the detected emotions. Specifically, it softens questions to alleviate the user's tension or asks more detailed questions to elicit the answers the company is looking for. This results in a smoother and more meaningful conversation.

[0183] Step 7:

[0184] After the simulated dialogue concludes, the server analyzes the accumulated emotional state data to precisely evaluate the compatibility between the user and the company. This evaluation integrates the results of the emotional analysis with the initial data and outputs it as a numerical matching score. Based on these results, both the user and the company are notified.

[0185] (Application Example 2)

[0186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0187] In recent years, the importance of using digital technology to provide experiences optimized for individual users has increased. Traditional matching systems only consider partial suitability based on skills and experience, and fail to fully consider the emotional responses of viewers in content delivery. Therefore, a deeper level of user experience optimization is desired. This would enable the building of long-term partnerships for both users and businesses and improve viewer satisfaction, but there is a lack of a holistic approach to address these issues.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0189] In this invention, the server includes means for receiving user attribute data and generating a digital representation of the user that reflects their personality based on that attribute data; means for receiving requirements data of a business entity and generating a digital representation that reflects the characteristics of the business entity based on that requirements data; means for the generated digital representation of the user and the digital representation of the business entity to interact with each other and evaluate affinity based on the content of the interaction; and means for acquiring the user's reactions while they are viewing and adjusting the content provided based on the acquired reactions. This not only enables sophisticated matching that takes into account emotional compatibility between the user and the business entity, but also makes it possible to provide viewers with a personalized viewing experience in real time.

[0190] "User attribute data" refers to information that represents the characteristics and traits of individual users, and is used to generate digital representations that reflect their individuality.

[0191] "A digital representation of a user that reflects their individuality" refers to a virtual representation that is generated based on the user's attribute data and embodies the user's characteristics.

[0192] "Business entity requirements data" refers to information that represents the characteristics and conditions required by a specific business entity, and is used to generate a digital representation of that business entity.

[0193] A "digital representation that reflects the characteristics of the business entity" is a virtual representation that concretizes the characteristics and requirements of the business entity based on the business entity's requirements data.

[0194] "Engaging in mutual dialogue" refers to the act of generated digital representations interacting with each other, engaging in discussions and simulated dialogues.

[0195] "Assessing affinity" is the act of measuring the emotional and practical fit between users and businesses based on interactions between digital representations.

[0196] "Viewing reactions" refer to the psychological or emotional responses that users exhibit while viewing content.

[0197] "Adjusting the content provided" refers to the process of appropriately changing and adjusting the content of the media being viewed based on user feedback obtained.

[0198] To implement this invention, first, the server receives user attribute data and, based on that data, uses a generated AI model to create a digital representation that reflects the user's personality. In response, the requirements data of the business entity is also input to the server, and based on that, a digital representation that reflects the characteristics of the business entity is generated. With this, both digital representations are ready to begin a simulated dialogue.

[0199] The server manages the interaction between digital representations and uses a generative AI model to evaluate the emotional affinity between the user and the business entity in real time during the interaction. This uses a pre-configured algorithm to quantify emotion and compatibility.

[0200] Furthermore, the device acquires the user's reactions in real time while they are watching using smart glasses or similar devices, and sends this data to the server. Based on this, the server uses a generative AI model to adjust the content provided, using the prompt message, "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion."

[0201] As a concrete example, while a user is watching entertainment, smart glasses capture their facial expressions, and the server analyzes this information to determine how the viewer is feeling. Based on the analysis, if the viewer is enjoying themselves, the system provides more similar scenes; if they show signs of anxiety, it presents calming content, thereby providing an experience optimized for each individual user.

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The user inputs their attribute data using a terminal. The terminal sends the input attribute data to the server. The server receives this data and uses a generative AI model to generate a digital representation that reflects the user's personality. The input is the user's attribute data, and the output is the user's digital representation.

[0205] Step 2:

[0206] The business entity inputs its requirements data using a terminal. The terminal sends this requirements data to a server. The server receives the data and generates a digital representation that reflects the characteristics of the business entity using a generative AI model. The input is the business entity's requirements data, and the output is the digital representation of the business entity.

[0207] Step 3:

[0208] The server initiates a simulated dialogue using the generated digital representations of the user and the business entity. It generates dialogue prompts and advances the dialogue using a generative AI model. The input is the digital representations of the user and the business entity, and the output is the content and progress of the dialogue.

[0209] Step 4:

[0210] The server uses a generated AI model to evaluate emotional affinity between the user and the business entity in real time during simulated dialogue. This uses an emotion analysis algorithm. The input is the dialogue content and generated prompt sentences, and the output is the affinity evaluation value.

[0211] Step 5:

[0212] The device captures the user's reactions while they are viewing content through smart glasses and sends that data to a server. The input is the user's reaction data while they are viewing, and the output is the reaction data sent to the server.

[0213] Step 6:

[0214] The server analyzes user reaction data and uses a generative AI model to generate a prompt message: "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion." It then adjusts the content provided in real time. The input is viewer reaction data, and the output is the adjusted content.

[0215] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0216] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0217] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0221] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0222] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0223] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0224] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0225] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0226] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0227] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0228] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0229] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0230] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0231] This invention provides a system for achieving appropriate matching between students and companies. In this system, an avatar corresponding to each user is generated when the user inputs their information into a terminal.

[0232] The user (student) enters personal information such as their educational background, skills, and interests into the terminal. The terminal sends this data to the server. Based on the received information, the server uses generative AI technology to generate a student avatar that reflects the student's characteristics. This avatar virtually reproduces the student's personality and background.

[0233] On the other hand, users (companies) input the desired candidate profile and characteristics of their corporate culture into a terminal. This information is also sent to the server, which generates interviewer avatars that match the company's values ​​and desired skills. These avatars are modeled after the ideal candidate profile that the company seeks.

[0234] The server automatically matches the generated student avatar with the interviewer avatar and begins a mock interview. The mock interview is conducted via voice or text, with the avatars exploring each other's suitability through predetermined questions and answers. Natural language processing and machine learning technologies are used in this process.

[0235] After the interview, the server analyzes the conversation between the avatars and calculates the degree of matching. This calculated degree of matching is provided as feedback to both the student and the company, clearly indicating how well they are a good match. This feedback helps improve future job hunting activities and allows companies to develop optimal recruitment methods.

[0236] For example, if a student provides information indicating they have a strong interest in programming, the server generates a student avatar that reflects that information. If a company provides information indicating they are looking for creative engineers, the server generates an interviewer avatar that asks creative questions. In a mock interview, the student avatar talks about their project experience, and the interviewer avatar asks for details about that project, thereby evaluating their specific suitability.

[0237] This invention is expected to enable effective matching between students and companies, significantly improving the efficiency of the recruitment process.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The user (student) enters personal information such as their educational background, skills, and hobbies into the terminal. The terminal then sends this information to the server.

[0241] Step 2:

[0242] The user (company) inputs information about the desired employee profile and corporate culture into a terminal. The terminal then sends this information to the server.

[0243] Step 3:

[0244] The server uses AI generation technology based on information received from students to generate student avatars that reflect the students' characteristics.

[0245] Step 4:

[0246] The server uses AI technology to generate interviewer avatars that mimic the company's values ​​and desired skills, based on information received from the company.

[0247] Step 5:

[0248] The server matches student avatars with interviewer avatars and sets up a mock interview scenario.

[0249] Step 6:

[0250] The server uses voice or text based on a pre-configured scenario to have avatars conduct mock interviews with each other.

[0251] Step 7:

[0252] The server analyzes the content of the mock interview dialogue and calculates the degree of matching.

[0253] Step 8:

[0254] The server notifies each user via their device of the calculated matching score and feedback on the conversation content.

[0255] (Example 1)

[0256] Next, we will describe Example 1. 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."

[0257] Traditionally, achieving a proper match between students and companies has required specialized knowledge in interviews and human resources, resulting in significant time and expense. Furthermore, inefficient management and utilization of personal and company information have led to challenges such as students being unable to find suitable companies and companies struggling to find ideal talent. This invention aims to solve these problems.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes means for receiving personal information and generating a personal avatar based on that information, means for receiving characteristic information requested by an organization and generating an organization avatar based on that information, and means for conducting interview simulations between the personal avatar and the organization avatar using a generation AI model and evaluating the degree of fit based on the results. This enables effective matching between students and companies while significantly reducing time and costs.

[0260] "Personal information" refers to data that indicates personal attributes such as educational background, skills, and interests, which are necessary for avatar generation.

[0261] A "personal avatar" is a video or text character created by an AI model based on personal information, which virtually represents the characteristics of that individual.

[0262] "Organizational characteristic information" refers to data that indicates the characteristics such as skills, values, and culture that a company or organization seeks.

[0263] An "organizational avatar" is a video or text character that virtually represents the ideal employee profile, created by an AI model based on the characteristics information sought by the organization.

[0264] A "generative AI model" is a technology that uses algorithms learned from large amounts of data to generate avatars based on input information from individuals or organizations.

[0265] "Interview simulation" is a virtual dialogue process in which generated individual avatars and organizational avatars conduct mock interviews through voice or text.

[0266] "Fit" is a score that indicates the degree of potential matching between an individual and an organization, calculated based on the results of an interview simulation.

[0267] This invention is a system that generates avatars based on the characteristics of individuals and organizations, and enables effective matching through virtual interviews. A specific example of this system is described below.

[0268] Each user (individual) enters personal information such as their educational background, skills, and interests into a terminal. This terminal can be, for example, a PC or smartphone. The entered information is sent to a server in real time. The server processes this information and uses a generative AI model to generate a personalized avatar that reflects the individual's characteristics. This generative AI model is pre-trained on a large dataset.

[0269] On the other hand, the user (organization) inputs the desired characteristics and cultural features into the terminal. This information is similarly sent to the server, which then generates an organizational avatar representing the ideal employee profile. This, too, is realized by a generative AI model.

[0270] The generated individual and organizational avatars are automatically matched by the server, and the interview simulation begins. This simulation is conducted using voice or text and is implemented using WebRTC or chatbot frameworks. Natural language processing technology is used throughout the interview process to analyze the interactions between the avatars.

[0271] As a practical example, if a user (individual) provides information such as "I have a strong interest in programming," the server will generate a personal avatar that reflects their programming skills based on this information. If an organization provides information such as "We are looking for creative engineers," the server will generate an organizational avatar that asks creative questions in line with that request. In a mock interview, the personal avatar talks about their project experience, and the organizational avatar asks detailed questions about the project, and the degree of suitability is evaluated.

[0272] Example of a prompt:

[0273] "Based on the information entered by the students, generate avatars that highlight their programming skills. Conduct mock interviews to verify that the avatars match the skill sets required by the companies."

[0274] This system enables efficient matching between individuals and organizations, significantly reducing time and costs.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The user (individual) enters personal information such as educational background, skills, and interests into the terminal. The terminal structures the entered data and converts it into a format for transmission to the server. The input is output as JSON data and sent to the server. The server receives this data and prepares for the next processing step.

[0278] Step 2:

[0279] The server inputs the data received from the user into the generative AI model. This data is used as a prompt for avatar generation that reflects the characteristics of an individual. The generative AI model operates an algorithm based on this prompt and outputs data for the individual avatar. This output is avatar data that visualizes and textually represents the characteristics of an individual.

[0280] Step 3:

[0281] The user (organization) inputs information regarding required characteristics and culture into the terminal. The terminal converts the data into a format that is easy for the server to process and transmits it to the server. This is also output in JSON format and transmitted to the server.

[0282] Step 4:

[0283] The server inputs the data received from the organization into the generative AI model. The model uses it as a prompt for generating an organization avatar that reflects the required characteristics of the organization and outputs data for the organization avatar. This data is avatar data that visualizes and textually represents the skills and values required by the organization.

[0284] Step 5:

[0285] The server matches the generated individual avatar and organization avatar. Here, using both avatar data, it starts a interview simulation. The simulation manages the interaction between avatars using natural language processing technology. This interaction is conducted via a voice call or chat interface, and interaction data is generated as output.

[0286] Step 6:

[0287] The server analyzes interaction data from the interview simulation. It uses machine learning algorithms to calculate the degree of fit from the input dialogue data. This degree of fit is output as a score indicating the compatibility between the individual and the organization.

[0288] Step 7:

[0289] The server provides feedback to each user (individual and organization) regarding the calculated fitness score. This feedback is generated as text and sent to the user's device. Users can then use this feedback to identify future strategies and areas for improvement.

[0290] (Application Example 1)

[0291] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0292] Traditional recruitment processes often lacked opportunities for direct communication between students and companies, resulting in lower matching accuracy. Furthermore, understanding appropriate corporate cultures and required skills was difficult, causing students to miss out on opportunities to connect with companies that truly matched their abilities and interests. These challenges need to be addressed.

[0293] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0294] In this invention, the server includes means for receiving user information and generating a first virtual representation based on that information, means for receiving requirements requested by a company and generating a second virtual representation based on that information, and means for the generated first and second virtual representations to engage in a virtual dialogue with each other and evaluate the degree of suitability based on the results. This makes it possible to enable effective matching between students and companies and improve the efficiency of the recruitment process.

[0295] "Users" refer to students and companies that use the system to provide information and generate their own virtual representations.

[0296] A "virtual representation" is a digital avatar created using a generative AI model based on user information, and it virtually reproduces the user's characteristics.

[0297] "Interaction" refers to the mutual exchange and dialogue that takes place between virtual representations within a virtual space, and is used to evaluate the suitability and level of understanding between the two parties.

[0298] "Fit" is an index that indicates the degree of agreement in suitability and interests between users, calculated based on the results of interactions between virtual representations.

[0299] To implement this invention, a server connected to an information and communication network and terminals accessible by multiple users are required. Users (students) use the terminals to input information such as their academic background, skills, and interests. This information is transmitted to the server via the network. Based on the received information, the server uses a generative AI model to generate a virtual representation that reflects the characteristics of the student.

[0300] Meanwhile, corporate users also input information such as the requirements for the personnel they are looking for and their corporate culture through their terminals, and similarly send this information to the server. Based on this, the server generates virtual interviewers that match the skill sets required by the company.

[0301] The generated virtual representations interact with each other in a virtual space. This process involves constructing a virtual environment using software such as Unity, and utilizing natural language processing technology to analyze the dialogue and evaluate its relevance. The resulting evaluation is then scored as a relevance by the server and provided as feedback to both users.

[0302] As a specific example, when a user inputs "interested in AI technology", the server generates a virtual representation reflecting this. When a corporate user describes "seeking innovative engineers", a virtual interviewer based on this information is generated. In the simulated conversation, the fitness level is evaluated by having the virtual representation discuss specific projects or ideas.

[0303] Examples of prompt sentences include "The student avatar has a deep interest in AI technology. The corporate avatar is seeking engineers who pursue innovation and will evaluate their suitability through specific project experiences."

[0304] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0305] Step 1:

[0306] The terminal prompts the user (student) to input information such as educational background, skills, and interests. The input information is formatted as a user profile and sent to the server.

[0307] Step 2:

[0308] Based on the received user profile, the server uses the generated AI model to generate a virtual representation of the student. In this process, the input characteristic information is analyzed, and data processing is performed to configure an appropriate avatar based on the results. The generated virtual representation is used in the next interaction step.

[0309] Step 3:

[0310] On the other hand, the terminal prompts the user (corporation) to input information such as the requirements for the desired personnel and corporate culture. This information is summarized as a corporate profile and sent to the server.

[0311] Step 4:

[0312] The server generates virtual interviewers suitable for each company based on their company profile. This generation process involves scrutinizing the company's values ​​and skill requirements, and performing data calculations to design corresponding virtual representations.

[0313] Step 5:

[0314] The server facilitates virtual interactions between generated student virtual representations and virtual company interviewers in a virtual space. Here, software such as Unity is used to provide a visual interface, and natural language processing techniques are employed to enable text and voice interactions. The content of the dialogue between the two is recorded and used to evaluate the degree of relevance.

[0315] Step 6:

[0316] The server analyzes data obtained from the interaction and parses the dialogue content through natural language processing. The analyzed data becomes input information for calculating the degree of fit, and the degree of matching is quantified through a scoring algorithm.

[0317] Step 7:

[0318] The server notifies both the student and the company of the calculated matching score as feedback. This feedback serves as a guide for self-improvement and strategy formulation in future recruitment activities.

[0319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0320] This invention provides a matching system that takes into account the emotions of both students and companies. This system generates avatars based on user information, and when these avatars conduct mock interviews, it uses an emotion engine to recognize emotions during the conversation, thereby achieving more accurate matching.

[0321] The user (student) enters their information into a terminal. The terminal sends this data to a server. Based on this, the server uses a generation AI to create a student avatar that reflects the student's personality. Similarly, companies also enter their desired candidate profile into the server, and an interviewer avatar reflecting the company's characteristics is generated.

[0322] The generated avatars are matched by the server, and a mock interview begins. At this point, an emotion engine operates, analyzing the emotional state of the users (students and companies) in real time during the conversation between the avatars. Based on the recognized emotions, the server can adjust the interview's progress. This adjustment includes changing the content of questions and the pace of the conversation according to the emotions.

[0323] After the mock interview, the server analyzes emotional data and incorporates this emotional information into the matching score. As a result, in addition to matching based solely on skills and experience, emotional compatibility is also considered, leading to a more precise matching process. The evaluation results are notified to both the student and the company via their respective devices.

[0324] For example, if a student avatar feels slightly anxious during a mock interview, the emotion engine can detect this, and the server can instruct the interviewer avatar to soften their demeanor. Furthermore, if the company avatar is detected as being satisfied with the responses, it can emphasize additional positive feedback.

[0325] This invention, by taking into account the emotional states of students and companies, enables more suitable and sustainable matching in partnerships than conventional systems.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] The user (student) enters personal information such as educational background, work experience, skills, and hobbies into the terminal. The terminal then sends the entered information to the server.

[0329] Step 2:

[0330] The user (company) inputs the desired skills, experience, and personality traits of the personnel into a terminal. This information, including the company culture and values, is then sent to the server.

[0331] Step 3:

[0332] The server uses a generation AI based on student information to create student avatars. These avatars are virtual characters that reflect the individuality of the students.

[0333] Step 4:

[0334] The server uses AI to generate interviewer avatars based on company information. These avatars are virtual characters that reflect the characteristics of the personnel the company is looking for.

[0335] Step 5:

[0336] The server combines the generated student avatar with the interviewer avatar and starts the mock interview session.

[0337] Step 6:

[0338] The server utilizes an emotion engine to analyze the emotional state of the student avatar and interviewer avatar's dialogue in real time during the mock interview. This analysis may include changes in voice tone and facial expressions.

[0339] Step 7:

[0340] The server dynamically adjusts the interview process using analysis results from the emotion engine. Specifically, it takes actions such as changing the content and order of questions based on the interviewee's emotions.

[0341] Step 8:

[0342] The server comprehensively analyzes the conversation content and emotional data after the interview to calculate the degree of matching. Emotional compatibility is also included in the evaluation criteria.

[0343] Step 9:

[0344] The server sends an evaluation summarizing the analysis results to the terminal, notifying users (students and companies) of the degree of matching and emotional feedback.

[0345] Step 10:

[0346] Based on the feedback received, users consider their next steps and repeat the process as needed.

[0347] (Example 2)

[0348] Next, we will describe Example 2. 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".

[0349] Traditional matching systems focus on skills and experience, failing to consider emotional compatibility, resulting in insufficient compatibility in actual partnerships. Furthermore, the inability to analyze emotional shifts during interviews and communication in real time and adjust conversations accordingly meant that truly valuable feedback was not being provided to both students and companies.

[0350] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0351] In this invention, the server includes means for receiving user information and generating individual virtual characters, means for receiving requirements for the work system and generating virtual characters for evaluators, and means for virtual characters to conduct simulated conversations and analyze their emotional states. This enables more precise and sustainable matching that takes emotional compatibility into account.

[0352] A "user" refers to an individual or group that uses the system to input their own information and confirms their suitability through matching and evaluation.

[0353] "Information" refers to data about the user's personality and preferences, specifically including data such as educational background, interests, and work experience.

[0354] A "virtual person" refers to an avatar digitally constructed using a generative AI model based on user or company information.

[0355] A "simulated dialogue" refers to a simulation in which generated virtual characters engage in a conversation, and is conducted based on an interview scenario.

[0356] "Emotional state" refers to an individual's psychological reactions and changes detected during simulated dialogue, and is analyzed from factors such as voice and facial expressions.

[0357] A "evaluator" is a virtual character created based on the company's requirements, and refers to an avatar that is responsible for asking questions and providing feedback in simulated conversations.

[0358] "Requirements for operational structure" refer to the type of personnel a company seeks and the skill sets expected for their roles.

[0359] "Matching score" refers to an indicator that shows the compatibility between a user and a company, and is quantified by taking into account skills and emotional factors.

[0360] "System" refers to the hardware and software configuration for integrating and executing the generation of virtual characters, the progression of simulated dialogues, sentiment analysis, and notification of evaluation results.

[0361] The following describes the "modes for carrying out the invention."

[0362] ---

[0363] The embodiment of this invention consists of a method in which a user, a terminal, and a server cooperate to build a virtual interview matching system. The user first inputs personal information and occupational preferences via the terminal. This terminal is equipped with an input support interface and has communication capabilities that enable secure data transmission.

[0364] The terminal sends the information entered by the user to the server. The communication protocol used here should preferably be one with enhanced security, such as HTTPS. Based on the received information, the server uses a generative AI model to generate a virtual person (avatar) that reflects the user's characteristics. This generation process can combine widely used image generation technologies such as DALL-E and natural language processing technologies. Similarly, the company's requirements are also sent to the server, and an evaluator avatar matching the company's desired candidate profile is generated.

[0365] The generated virtual characters and evaluator avatars begin a simulated dialogue on the server. This simulated dialogue utilizes speech recognition and natural language processing technologies for sentiment analysis. For example, sentiment analysis tools like IBM Watson are used to analyze subtle emotional changes during the conversation in real time. Based on these results, the server adjusts the content and pace of the dialogue.

[0366] Emotional state-based matching evaluation is performed after the simulated dialogue is completed. The server analyzes the accumulated emotional data to evaluate the compatibility between the user and the company with greater accuracy. This enables a more precise matching evaluation that incorporates emotional elements.

[0367] For example, a prompt message such as, "Generate an avatar based on the student's profile information and begin an emotion-based mock interview with the company. Next, analyze the emotional changes during the interview and reflect the results in the matching evaluation," is used, and the process proceeds accordingly.

[0368] This embodiment enables users and companies to build longer-term and more sustainable relationships through communication that takes emotional states into account.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] Users use the device to input their personal information and career preferences. Specifically, they enter their name, age, educational background, field of expertise, and desired job duties. The device temporarily stores this data in a database such as SQLite. This prepares the user's basic information data.

[0372] Step 2:

[0373] The terminal sends the information entered by the user to the server. Here, the HTTPS protocol is used to securely transfer the data. The server parses the received information in JSON format and converts it into a format usable by the generated AI model. The output of this step is user profile data that the AI ​​model can process.

[0374] Step 3:

[0375] The server uses a generative AI model to generate a virtual character based on user profile data. For example, it outputs an avatar that reflects the user's characteristics as an image using the DALL-E model. At this stage, an avatar with visual and auditory features based on user information is obtained.

[0376] Step 4:

[0377] The personnel information requested by companies is also entered into the server, and evaluator avatars are generated in the same way. This information is processed based on data provided in advance by companies, and avatars that reflect the characteristics of each company are output. In this way, the server maintains virtual representations of both students and companies.

[0378] Step 5:

[0379] The server initiates a simulated dialogue using the generated virtual character and evaluator avatar. It activates an emotion analysis engine and uses natural language processing technology to analyze the conversation between the avatars. At each step, avatar voice and text data are input, and an audio analysis tool outputs emotion changes in real time.

[0380] Step 6:

[0381] The server adjusts the content and flow of the simulated conversation based on the detected emotions. Specifically, it softens questions to alleviate the user's tension or asks more detailed questions to elicit the answers the company is looking for. This results in a smoother and more meaningful conversation.

[0382] Step 7:

[0383] After the simulated dialogue concludes, the server analyzes the accumulated emotional state data to precisely evaluate the compatibility between the user and the company. This evaluation integrates the results of the emotional analysis with the initial data and outputs it as a numerical matching score. Based on these results, both the user and the company are notified.

[0384] (Application Example 2)

[0385] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0386] In recent years, the importance of using digital technology to provide experiences optimized for individual users has increased. Traditional matching systems only consider partial suitability based on skills and experience, and fail to fully consider the emotional responses of viewers in content delivery. Therefore, a deeper level of user experience optimization is desired. This would enable the building of long-term partnerships for both users and businesses and improve viewer satisfaction, but there is a lack of a holistic approach to address these issues.

[0387] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0388] In this invention, the server includes means for receiving user attribute data and generating a digital representation of the user that reflects their personality based on that attribute data; means for receiving requirements data of a business entity and generating a digital representation that reflects the characteristics of the business entity based on that requirements data; means for the generated digital representation of the user and the digital representation of the business entity to interact with each other and evaluate affinity based on the content of the interaction; and means for acquiring the user's reactions while they are viewing and adjusting the content provided based on the acquired reactions. This not only enables sophisticated matching that takes into account emotional compatibility between the user and the business entity, but also makes it possible to provide viewers with a personalized viewing experience in real time.

[0389] "User attribute data" refers to information that represents the characteristics and traits of individual users, and is used to generate digital representations that reflect their individuality.

[0390] "A digital representation of a user that reflects their individuality" refers to a virtual representation that is generated based on the user's attribute data and embodies the user's characteristics.

[0391] "Business entity requirements data" refers to information that represents the characteristics and conditions required by a specific business entity, and is used to generate a digital representation of that business entity.

[0392] A "digital representation that reflects the characteristics of the business entity" is a virtual representation that concretizes the characteristics and requirements of the business entity based on the business entity's requirements data.

[0393] "Engaging in mutual dialogue" refers to the act of generated digital representations interacting with each other, engaging in discussions and simulated dialogues.

[0394] "Assessing affinity" is the act of measuring the emotional and practical fit between users and businesses based on interactions between digital representations.

[0395] "Viewing reactions" refer to the psychological or emotional responses that users exhibit while viewing content.

[0396] "Adjusting the content provided" refers to the process of appropriately changing and adjusting the content of the media being viewed based on user feedback obtained.

[0397] To implement this invention, first, the server receives user attribute data and, based on that data, uses a generated AI model to create a digital representation that reflects the user's personality. In response, the requirements data of the business entity is also input to the server, and based on that, a digital representation that reflects the characteristics of the business entity is generated. With this, both digital representations are ready to begin a simulated dialogue.

[0398] The server manages the interaction between digital representations and uses a generative AI model to evaluate the emotional affinity between the user and the business entity in real time during the interaction. This uses a pre-configured algorithm to quantify emotion and compatibility.

[0399] Furthermore, the device acquires the user's reactions in real time while they are watching using smart glasses or similar devices, and sends this data to the server. Based on this, the server uses a generative AI model to adjust the content provided, using the prompt message, "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion."

[0400] As a concrete example, while a user is watching entertainment, smart glasses capture their facial expressions, and the server analyzes this information to determine how the viewer is feeling. Based on the analysis, if the viewer is enjoying themselves, the system provides more similar scenes; if they show signs of anxiety, it presents calming content, thereby providing an experience optimized for each individual user.

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The user inputs their attribute data using a terminal. The terminal sends the input attribute data to the server. The server receives this data and uses a generative AI model to generate a digital representation that reflects the user's personality. The input is the user's attribute data, and the output is the user's digital representation.

[0404] Step 2:

[0405] The business entity inputs its requirements data using a terminal. The terminal sends this requirements data to a server. The server receives the data and generates a digital representation that reflects the characteristics of the business entity using a generative AI model. The input is the business entity's requirements data, and the output is the digital representation of the business entity.

[0406] Step 3:

[0407] The server initiates a simulated dialogue using the generated digital representations of the user and the business entity. It generates dialogue prompts and advances the dialogue using a generative AI model. The input is the digital representations of the user and the business entity, and the output is the content and progress of the dialogue.

[0408] Step 4:

[0409] The server uses a generated AI model to evaluate emotional affinity between the user and the business entity in real time during simulated dialogue. This uses an emotion analysis algorithm. The input is the dialogue content and generated prompt sentences, and the output is the affinity evaluation value.

[0410] Step 5:

[0411] The device captures the user's reactions while they are viewing content through smart glasses and sends that data to a server. The input is the user's reaction data while they are viewing, and the output is the reaction data sent to the server.

[0412] Step 6:

[0413] The server analyzes user reaction data and uses a generative AI model to generate a prompt message: "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion." It then adjusts the content provided in real time. The input is viewer reaction data, and the output is the adjusted content.

[0414] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0415] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0416] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0417] [Third Embodiment]

[0418] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0419] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0420] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0421] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0422] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0423] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0424] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0425] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0426] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0427] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0428] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0429] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0430] This invention provides a system for achieving appropriate matching between students and companies. In this system, an avatar corresponding to each user is generated when the user inputs their information into a terminal.

[0431] The user (student) enters personal information such as their educational background, skills, and interests into the terminal. The terminal sends this data to the server. Based on the received information, the server uses generative AI technology to generate a student avatar that reflects the student's characteristics. This avatar virtually reproduces the student's personality and background.

[0432] On the other hand, users (companies) input the desired candidate profile and characteristics of their corporate culture into a terminal. This information is also sent to the server, which generates interviewer avatars that match the company's values ​​and desired skills. These avatars are modeled after the ideal candidate profile that the company seeks.

[0433] The server automatically matches the generated student avatar with the interviewer avatar and begins a mock interview. The mock interview is conducted via voice or text, with the avatars exploring each other's suitability through predetermined questions and answers. Natural language processing and machine learning technologies are used in this process.

[0434] After the interview, the server analyzes the conversation between the avatars and calculates the degree of matching. This calculated degree of matching is provided as feedback to both the student and the company, clearly indicating how well they are a good match. This feedback helps improve future job hunting activities and allows companies to develop optimal recruitment methods.

[0435] For example, if a student provides information indicating they have a strong interest in programming, the server generates a student avatar that reflects that information. If a company provides information indicating they are looking for creative engineers, the server generates an interviewer avatar that asks creative questions. In a mock interview, the student avatar talks about their project experience, and the interviewer avatar asks for details about that project, thereby evaluating their specific suitability.

[0436] This invention is expected to enable effective matching between students and companies, significantly improving the efficiency of the recruitment process.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] The user (student) enters personal information such as their educational background, skills, and hobbies into the terminal. The terminal then sends this information to the server.

[0440] Step 2:

[0441] The user (company) inputs information about the desired employee profile and corporate culture into a terminal. The terminal then sends this information to the server.

[0442] Step 3:

[0443] The server uses AI generation technology based on information received from students to generate student avatars that reflect the students' characteristics.

[0444] Step 4:

[0445] The server uses AI technology to generate interviewer avatars that mimic the company's values ​​and desired skills, based on information received from the company.

[0446] Step 5:

[0447] The server matches student avatars with interviewer avatars and sets up a mock interview scenario.

[0448] Step 6:

[0449] The server uses voice or text based on a pre-configured scenario to have avatars conduct mock interviews with each other.

[0450] Step 7:

[0451] The server analyzes the content of the mock interview dialogue and calculates the degree of matching.

[0452] Step 8:

[0453] The server notifies each user via their device of the calculated matching score and feedback on the conversation content.

[0454] (Example 1)

[0455] Next, we will describe Example 1. 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."

[0456] Traditionally, achieving a proper match between students and companies has required specialized knowledge in interviews and human resources, resulting in significant time and expense. Furthermore, inefficient management and utilization of personal and company information have led to challenges such as students being unable to find suitable companies and companies struggling to find ideal talent. This invention aims to solve these problems.

[0457] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0458] In this invention, the server includes means for receiving personal information and generating a personal avatar based on that information, means for receiving characteristic information requested by an organization and generating an organization avatar based on that information, and means for conducting interview simulations between the personal avatar and the organization avatar using a generation AI model and evaluating the degree of fit based on the results. This enables effective matching between students and companies while significantly reducing time and costs.

[0459] "Personal information" refers to data that indicates personal attributes such as educational background, skills, and interests, which are necessary for avatar generation.

[0460] A "personal avatar" is a video or text character created by an AI model based on personal information, which virtually represents the characteristics of that individual.

[0461] "Organizational characteristic information" refers to data that indicates the characteristics such as skills, values, and culture that a company or organization seeks.

[0462] An "organizational avatar" is a video or text character that virtually represents the ideal employee profile, created by an AI model based on the characteristics information sought by the organization.

[0463] A "generative AI model" is a technology that uses algorithms learned from large amounts of data to generate avatars based on input information from individuals or organizations.

[0464] "Interview simulation" is a virtual dialogue process in which generated individual avatars and organizational avatars conduct mock interviews through voice or text.

[0465] "Fit" is a score that indicates the degree of potential matching between an individual and an organization, calculated based on the results of an interview simulation.

[0466] This invention is a system that generates avatars based on the characteristics of individuals and organizations, and enables effective matching through virtual interviews. A specific example of this system is described below.

[0467] Each user (individual) enters personal information such as their educational background, skills, and interests into a terminal. This terminal can be, for example, a PC or smartphone. The entered information is sent to a server in real time. The server processes this information and uses a generative AI model to generate a personalized avatar that reflects the individual's characteristics. This generative AI model is pre-trained on a large dataset.

[0468] On the other hand, the user (organization) inputs the desired characteristics and cultural features into the terminal. This information is similarly sent to the server, which then generates an organizational avatar representing the ideal employee profile. This, too, is realized by a generative AI model.

[0469] The generated individual and organizational avatars are automatically matched by the server, and the interview simulation begins. This simulation is conducted using voice or text and is implemented using WebRTC or chatbot frameworks. Natural language processing technology is used throughout the interview process to analyze the interactions between the avatars.

[0470] As a practical example, if a user (individual) provides information such as "I have a strong interest in programming," the server will generate a personal avatar that reflects their programming skills based on this information. If an organization provides information such as "We are looking for creative engineers," the server will generate an organizational avatar that asks creative questions in line with that request. In a mock interview, the personal avatar talks about their project experience, and the organizational avatar asks detailed questions about the project, and the degree of suitability is evaluated.

[0471] Example of a prompt:

[0472] "Based on the information entered by the students, generate avatars that highlight their programming skills. Conduct mock interviews to verify that the avatars match the skill sets required by the companies."

[0473] This system enables efficient matching between individuals and organizations, significantly reducing time and costs.

[0474] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0475] Step 1:

[0476] The user (individual) enters personal information such as educational background, skills, and interests into the terminal. The terminal structures the entered data and converts it into a format for transmission to the server. The input is output as JSON data and sent to the server. The server receives this data and prepares for the next processing step.

[0477] Step 2:

[0478] The server inputs data received from the user into a generative AI model. This data is used as a prompt for generating an avatar that reflects the individual's characteristics. Based on this prompt, the generative AI model runs its algorithm and outputs data for the individual avatar. This output is avatar data that visualizes and textualizes the individual's characteristics.

[0479] Step 3:

[0480] The user (organization) inputs information about the desired characteristics and culture into the terminal. The terminal converts the data into a format that the server can easily process and sends it to the server. This data is also output in JSON format and sent to the server.

[0481] Step 4:

[0482] The server inputs data received from the organization into a generating AI model. The model uses this data as a prompt to generate an organizational avatar that reflects the characteristics the organization desires, and outputs data for the organizational avatar. This data is avatar data that visualizes and textualizes the skills and values ​​the organization desires.

[0483] Step 5:

[0484] The server matches the generated individual avatar with the organization avatar. Using both avatar data sets, it then initiates an interview simulation. The simulation manages the interaction between the avatars using natural language processing techniques. This interaction takes place via voice calls or a chat interface, and interaction data is generated as output.

[0485] Step 6:

[0486] The server analyzes interaction data from the interview simulation. It uses machine learning algorithms to calculate the degree of fit from the input dialogue data. This degree of fit is output as a score indicating the compatibility between the individual and the organization.

[0487] Step 7:

[0488] The server provides feedback to each user (individual and organization) regarding the calculated fitness score. This feedback is generated as text and sent to the user's device. Users can then use this feedback to identify future strategies and areas for improvement.

[0489] (Application Example 1)

[0490] Next, we will explain Application Example 1. In the following explanation, 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."

[0491] Traditional recruitment processes often lacked opportunities for direct communication between students and companies, resulting in lower matching accuracy. Furthermore, understanding appropriate corporate cultures and required skills was difficult, causing students to miss out on opportunities to connect with companies that truly matched their abilities and interests. These challenges need to be addressed.

[0492] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0493] In this invention, the server includes means for receiving user information and generating a first virtual representation based on that information, means for receiving requirements requested by a company and generating a second virtual representation based on that information, and means for the generated first and second virtual representations to engage in a virtual dialogue with each other and evaluate the degree of suitability based on the results. This makes it possible to enable effective matching between students and companies and improve the efficiency of the recruitment process.

[0494] "Users" refer to students and companies that use the system to provide information and generate their own virtual representations.

[0495] A "virtual representation" is a digital avatar created using a generative AI model based on user information, and it virtually reproduces the user's characteristics.

[0496] "Interaction" refers to the mutual exchange and dialogue that takes place between virtual representations within a virtual space, and is used to evaluate the suitability and level of understanding between the two parties.

[0497] "Fit" is an index that indicates the degree of agreement in suitability and interests between users, calculated based on the results of interactions between virtual representations.

[0498] To implement this invention, a server connected to an information and communication network and terminals accessible by multiple users are required. Users (students) use the terminals to input information such as their academic background, skills, and interests. This information is transmitted to the server via the network. Based on the received information, the server uses a generative AI model to generate a virtual representation that reflects the characteristics of the student.

[0499] Meanwhile, corporate users also input information such as the requirements for the personnel they are looking for and their corporate culture through their terminals, and similarly send this information to the server. Based on this, the server generates virtual interviewers that match the skill sets required by the company.

[0500] The generated virtual representations interact with each other in a virtual space. This process involves constructing a virtual environment using software such as Unity, and utilizing natural language processing technology to analyze the dialogue and evaluate its relevance. The resulting evaluation is then scored as a relevance by the server and provided as feedback to both users.

[0501] For example, if a user enters "I am interested in AI technology," the server generates a virtual representation that reflects this. If a company user writes "We are looking for innovative engineers," a virtual interviewer is generated based on that information. In the simulated conversation, the virtual representation discusses specific projects and ideas, and its suitability is evaluated.

[0502] Examples of prompt messages include: "The student avatar has a deep interest in AI technology. The company avatar is seeking engineers who pursue innovation and will evaluate their suitability through concrete project experience."

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] The terminal prompts the user (student) to input information such as their educational background, skills, and interests. This input information is formatted as a user profile and sent to the server.

[0506] Step 2:

[0507] The server generates a virtual representation of the student using a generative AI model based on the received user profile. This process analyzes the input characteristic information and performs data processing to construct an appropriate avatar based on the results. The generated virtual representation is then used in the next interaction step.

[0508] Step 3:

[0509] On the other hand, the terminal allows users (companies) to input information such as the requirements for the personnel they are looking for and their corporate culture. This information is compiled into a company profile and sent to the server.

[0510] Step 4:

[0511] The server generates virtual interviewers suitable for a company based on its corporate profile. This generation process involves scrutinizing the company's values ​​and skill requirements, and performing data calculations to design corresponding virtual representations.

[0512] Step 5:

[0513] The server facilitates virtual interactions between generated student virtual representations and virtual company interviewers in a virtual space. Here, software such as Unity is used to provide a visual interface, and natural language processing techniques are employed to enable text and voice interactions. The content of the dialogue between the two is recorded and used to evaluate the degree of relevance.

[0514] Step 6:

[0515] The server analyzes data obtained from the interaction and parses the dialogue content through natural language processing. The analyzed data becomes input information for calculating the degree of fit, and the degree of matching is quantified through a scoring algorithm.

[0516] Step 7:

[0517] The server notifies both the user (student) and the user (company) of the calculated matching score as feedback. This feedback serves as a guide for self-improvement and strategy formulation in future recruitment activities.

[0518] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0519] This invention provides a matching system that takes into account the emotions of both students and companies. This system generates avatars based on user information, and when these avatars conduct mock interviews, it uses an emotion engine to recognize emotions during the conversation, thereby achieving more accurate matching.

[0520] The user (student) enters their information into a terminal. The terminal sends this data to a server. Based on this, the server uses a generation AI to create a student avatar that reflects the student's personality. Similarly, companies also enter their desired candidate profile into the server, and an interviewer avatar reflecting the company's characteristics is generated.

[0521] The generated avatars are matched by the server, and a mock interview begins. At this point, an emotion engine operates, analyzing the emotional state of the users (students and companies) in real time during the conversation between the avatars. Based on the recognized emotions, the server can adjust the interview's progress. This adjustment includes changing the content of questions and the pace of the conversation according to the emotions.

[0522] After the mock interview, the server analyzes emotional data and incorporates this emotional information into the matching score. As a result, in addition to matching based solely on skills and experience, emotional compatibility is also considered, leading to a more precise matching process. The evaluation results are notified to both the student and the company via their respective devices.

[0523] For example, if a student avatar feels slightly anxious during a mock interview, the emotion engine can detect this, and the server can instruct the interviewer avatar to soften their demeanor. Furthermore, if the company avatar is detected as being satisfied with the responses, it can emphasize additional positive feedback.

[0524] This invention, by taking into account the emotional states of students and companies, enables more suitable and sustainable matching in partnerships than conventional systems.

[0525] The following describes the processing flow.

[0526] Step 1:

[0527] The user (student) enters personal information such as educational background, work experience, skills, and hobbies into the terminal. The terminal then sends the entered information to the server.

[0528] Step 2:

[0529] The user (company) inputs the desired skills, experience, and personality traits of the personnel into a terminal. This information, including the company culture and values, is then sent to the server.

[0530] Step 3:

[0531] The server uses a generation AI based on student information to create student avatars. These avatars are virtual characters that reflect the individuality of the students.

[0532] Step 4:

[0533] The server uses AI generation based on company information to create interviewer avatars. These avatars are virtual characters that reflect the characteristics of the personnel the company is looking for.

[0534] Step 5:

[0535] The server combines the generated student avatar with the interviewer avatar and starts the mock interview session.

[0536] Step 6:

[0537] The server utilizes an emotion engine to analyze the emotional state of the student avatar and interviewer avatar's dialogue in real time during the mock interview. This analysis may include changes in voice tone and facial expressions.

[0538] Step 7:

[0539] The server uses the analysis results from the emotion engine to dynamically adjust the interview process. Specifically, it takes actions such as changing the content and order of questions based on the interviewee's emotions.

[0540] Step 8:

[0541] The server comprehensively analyzes the conversation content and emotional data after the interview to calculate the degree of matching. Emotional compatibility is also included in the evaluation criteria.

[0542] Step 9:

[0543] The server sends an evaluation summarizing the analysis results to the terminal, notifying users (students and companies) of the degree of matching and emotional feedback.

[0544] Step 10:

[0545] Based on the feedback received, users consider their next steps and repeat the process as needed.

[0546] (Example 2)

[0547] Next, we will describe Example 2. 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."

[0548] Traditional matching systems focus on skills and experience, failing to consider emotional compatibility, resulting in insufficient compatibility in actual partnerships. Furthermore, the inability to analyze emotional shifts during interviews and communication in real time and adjust conversations accordingly meant that truly valuable feedback was not being provided to both students and companies.

[0549] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0550] In this invention, the server includes means for receiving user information and generating individual virtual characters, means for receiving requirements for the work system and generating virtual characters for evaluators, and means for virtual characters to conduct simulated conversations and analyze their emotional states. This enables more precise and sustainable matching that takes emotional compatibility into account.

[0551] A "user" refers to an individual or group that uses the system to input their own information and confirms their suitability through matching and evaluation.

[0552] "Information" refers to data about the user's personality and preferences, specifically including data such as educational background, interests, and work experience.

[0553] A "virtual person" refers to an avatar digitally constructed using a generative AI model based on user or company information.

[0554] A "simulated dialogue" refers to a simulation in which generated virtual characters engage in a conversation, and is conducted based on an interview scenario.

[0555] "Emotional state" refers to an individual's psychological reactions and changes detected during simulated dialogue, and is analyzed from factors such as voice and facial expressions.

[0556] A "evaluator" is a virtual character created based on the company's requirements, and refers to an avatar that is responsible for asking questions and providing feedback in simulated conversations.

[0557] "Requirements for operational structure" refer to the type of personnel a company seeks and the skill sets expected for their roles.

[0558] "Matching score" refers to an indicator that shows the compatibility between a user and a company, and is quantified by taking into account skills and emotional factors.

[0559] "System" refers to the hardware and software configuration for integrating and executing the generation of virtual characters, the progression of simulated dialogues, sentiment analysis, and notification of evaluation results.

[0560] The following describes the "modes for carrying out the invention."

[0561] ---

[0562] The embodiment of this invention consists of a method in which a user, a terminal, and a server cooperate to build a virtual interview matching system. The user first inputs personal information and occupational preferences via the terminal. This terminal is equipped with an input support interface and has communication capabilities that enable secure data transmission.

[0563] The terminal sends the information entered by the user to the server. The communication protocol used here should preferably be one with enhanced security, such as HTTPS. Based on the received information, the server uses a generative AI model to generate a virtual person (avatar) that reflects the user's characteristics. This generation process can combine widely used image generation technologies such as DALL-E and natural language processing technologies. Similarly, the company's requirements are also sent to the server, and an evaluator avatar matching the company's desired candidate profile is generated.

[0564] The generated virtual characters and evaluator avatars begin a simulated dialogue on the server. This simulated dialogue utilizes speech recognition and natural language processing technologies for sentiment analysis. For example, sentiment analysis tools like IBM Watson are used to analyze subtle emotional changes during the conversation in real time. Based on these results, the server adjusts the content and pace of the dialogue.

[0565] Emotional state-based matching evaluation is performed after the simulated dialogue is completed. The server analyzes the accumulated emotional data to evaluate the compatibility between the user and the company with greater accuracy. This enables a more precise matching evaluation that incorporates emotional elements.

[0566] For example, a prompt message such as, "Generate an avatar based on the student's profile information and begin an emotion-based mock interview with the company. Next, analyze the emotional changes during the interview and reflect the results in the matching evaluation," is used, and the process proceeds accordingly.

[0567] This embodiment enables users and companies to build longer-term and more sustainable relationships through communication that takes emotional states into account.

[0568] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0569] Step 1:

[0570] Users use the device to input their personal information and career preferences. Specifically, they enter their name, age, educational background, field of expertise, and desired job duties. The device temporarily stores this data in a database such as SQLite. This prepares the user's basic information data.

[0571] Step 2:

[0572] The terminal sends the information entered by the user to the server. Here, the HTTPS protocol is used to securely transfer the data. The server parses the received information in JSON format and converts it into a format usable by the generated AI model. The output of this step is user profile data that the AI ​​model can process.

[0573] Step 3:

[0574] The server uses a generative AI model to generate a virtual character based on user profile data. For example, it outputs an avatar that reflects the user's characteristics as an image using the DALL-E model. At this stage, an avatar with visual and auditory features based on user information is obtained.

[0575] Step 4:

[0576] The personnel information requested by companies is also entered into the server, and evaluator avatars are generated in the same way. This information is processed based on data provided in advance by companies, and avatars that reflect the characteristics of each company are output. In this way, the server maintains virtual representations of both students and companies.

[0577] Step 5:

[0578] The server initiates a simulated dialogue using the generated virtual character and evaluator avatar. It activates an emotion analysis engine and uses natural language processing technology to analyze the conversation between the avatars. At each step, avatar voice and text data are input, and an audio analysis tool outputs emotion changes in real time.

[0579] Step 6:

[0580] The server adjusts the content and flow of the simulated conversation based on the detected emotions. Specifically, it softens questions to alleviate the user's tension or asks more detailed questions to elicit the answers the company is looking for. This results in a smoother and more meaningful conversation.

[0581] Step 7:

[0582] After the simulated dialogue concludes, the server analyzes the accumulated emotional state data to precisely evaluate the compatibility between the user and the company. This evaluation integrates the results of the emotional analysis with the initial data and outputs it as a numerical matching score. Based on these results, both the user and the company are notified.

[0583] (Application Example 2)

[0584] Next, we will explain application example 2. In the following explanation, 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."

[0585] In recent years, the importance of using digital technology to provide experiences optimized for individual users has increased. Traditional matching systems only consider partial suitability based on skills and experience, and fail to fully consider the emotional responses of viewers in content delivery. Therefore, a deeper level of user experience optimization is desired. This would enable the building of long-term partnerships for both users and businesses and improve viewer satisfaction, but there is a lack of a holistic approach to address these issues.

[0586] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0587] In this invention, the server includes means for receiving user attribute data and generating a digital representation of the user that reflects their personality based on that attribute data; means for receiving requirements data of a business entity and generating a digital representation that reflects the characteristics of the business entity based on that requirements data; means for the generated digital representation of the user and the digital representation of the business entity to interact with each other and evaluate affinity based on the content of the interaction; and means for acquiring the user's reactions while they are viewing and adjusting the content provided based on the acquired reactions. This not only enables sophisticated matching that takes into account emotional compatibility between the user and the business entity, but also makes it possible to provide viewers with a personalized viewing experience in real time.

[0588] "User attribute data" refers to information that represents the characteristics and traits of individual users, and is used to generate digital representations that reflect their individuality.

[0589] "A digital representation of a user that reflects their individuality" refers to a virtual representation that is generated based on the user's attribute data and embodies the user's characteristics.

[0590] "Business entity requirements data" refers to information that represents the characteristics and conditions required by a specific business entity, and is used to generate a digital representation of that business entity.

[0591] A "digital representation that reflects the characteristics of the business entity" is a virtual representation that concretizes the characteristics and requirements of the business entity based on the business entity's requirements data.

[0592] "Engaging in mutual dialogue" refers to the act of generated digital representations interacting with each other, engaging in discussions and simulated dialogues.

[0593] "Assessing affinity" is the act of measuring the emotional and practical fit between users and businesses based on interactions between digital representations.

[0594] "Viewing reactions" refer to the psychological or emotional responses that users exhibit while viewing content.

[0595] "Adjusting the content provided" refers to the process of appropriately changing and adjusting the content of the media being viewed based on user feedback obtained.

[0596] To implement this invention, first, the server receives user attribute data and, based on that data, uses a generated AI model to create a digital representation that reflects the user's personality. In response, the requirements data of the business entity is also input to the server, and based on that, a digital representation that reflects the characteristics of the business entity is generated. With this, both digital representations are ready to begin a simulated dialogue.

[0597] The server manages the interaction between digital representations and uses a generative AI model to evaluate the emotional affinity between the user and the business entity in real time during the interaction. This uses a pre-configured algorithm to quantify emotion and compatibility.

[0598] Furthermore, the device acquires the user's reactions in real time while they are watching using smart glasses or similar devices, and sends this data to the server. Based on this, the server uses a generative AI model to adjust the content provided, using the prompt message, "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion."

[0599] As a concrete example, while a user is watching entertainment, smart glasses capture their facial expressions, and the server analyzes this information to determine how the viewer is feeling. Based on the analysis, if the viewer is enjoying themselves, the system provides more similar scenes; if they show signs of anxiety, it presents calming content, thereby providing an experience optimized for each individual user.

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The user inputs their attribute data using a terminal. The terminal sends the input attribute data to the server. The server receives this data and uses a generative AI model to generate a digital representation that reflects the user's personality. The input is the user's attribute data, and the output is the user's digital representation.

[0603] Step 2:

[0604] Businesses input their requirements data using a terminal. The terminal sends this requirements data to a server. The server receives the data and generates a digital representation that reflects the characteristics of the business using a generative AI model. The input is the business's requirements data, and the output is the digital representation of the business.

[0605] Step 3:

[0606] The server initiates a simulated dialogue using the generated digital representations of the user and the business entity. It generates dialogue prompts and advances the dialogue using a generative AI model. The input is the digital representations of the user and the business entity, and the output is the content and progress of the dialogue.

[0607] Step 4:

[0608] The server uses a generated AI model to evaluate emotional affinity between the user and the business entity in real time during simulated dialogue. This uses an emotion analysis algorithm. The input is the dialogue content and generated prompt sentences, and the output is the affinity evaluation value.

[0609] Step 5:

[0610] The device captures the user's reactions while they are viewing content through smart glasses and sends that data to a server. The input is the user's reaction data while they are viewing, and the output is the reaction data sent to the server.

[0611] Step 6:

[0612] The server analyzes user reaction data and uses a generative AI model to generate a prompt message: "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion." It then adjusts the content provided in real time. The input is viewer reaction data, and the output is the adjusted content.

[0613] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0614] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0615] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] As shown in Figure 7, the 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.

[0619] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0620] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0621] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0622] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0623] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0624] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0625] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0626] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0627] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0628] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0629] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] This invention provides a system for achieving appropriate matching between students and companies. In this system, an avatar corresponding to each user is generated when the user inputs their information into a terminal.

[0631] The user (student) enters personal information such as their educational background, skills, and interests into the terminal. The terminal sends this data to the server. Based on the received information, the server uses generative AI technology to generate a student avatar that reflects the student's characteristics. This avatar virtually reproduces the student's personality and background.

[0632] On the other hand, users (companies) input the desired candidate profile and characteristics of their corporate culture into a terminal. This information is also sent to the server, which generates interviewer avatars that match the company's values ​​and desired skills. These avatars are modeled after the ideal candidate profile that the company seeks.

[0633] The server automatically matches the generated student avatar with the interviewer avatar and begins a mock interview. The mock interview is conducted via voice or text, with the avatars exploring each other's suitability through predetermined questions and answers. Natural language processing and machine learning technologies are used in this process.

[0634] After the interview, the server analyzes the conversation between the avatars and calculates the degree of matching. This calculated degree of matching is provided as feedback to both the student and the company, clearly indicating how well they are a good match. This feedback helps improve future job hunting activities and allows companies to develop optimal recruitment methods.

[0635] For example, if a student provides information indicating they have a strong interest in programming, the server generates a student avatar that reflects that information. If a company provides information indicating they are looking for creative engineers, the server generates an interviewer avatar that asks creative questions. In a mock interview, the student avatar talks about their project experience, and the interviewer avatar asks for details about that project, thereby evaluating their specific suitability.

[0636] This invention is expected to enable effective matching between students and companies, significantly improving the efficiency of the recruitment process.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] The user (student) enters personal information such as their educational background, skills, and hobbies into the terminal. The terminal then sends this information to the server.

[0640] Step 2:

[0641] The user (company) inputs information about the desired employee profile and corporate culture into a terminal. The terminal then sends this information to the server.

[0642] Step 3:

[0643] The server uses AI generation technology based on information received from students to generate student avatars that reflect the students' characteristics.

[0644] Step 4:

[0645] The server uses AI technology to generate interviewer avatars that mimic the company's values ​​and desired skills, based on information received from the company.

[0646] Step 5:

[0647] The server matches student avatars with interviewer avatars and sets up a mock interview scenario.

[0648] Step 6:

[0649] The server uses voice or text based on a pre-configured scenario to have avatars conduct mock interviews with each other.

[0650] Step 7:

[0651] The server analyzes the content of the mock interview dialogue and calculates the degree of matching.

[0652] Step 8:

[0653] The server notifies each user via their device of the calculated matching score and feedback on the conversation content.

[0654] (Example 1)

[0655] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0656] Traditionally, achieving a proper match between students and companies has required specialized knowledge in interviews and human resources, resulting in significant time and expense. Furthermore, inefficient management and utilization of personal and company information have led to challenges such as students being unable to find suitable companies and companies struggling to find ideal talent. This invention aims to solve these problems.

[0657] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0658] In this invention, the server includes means for receiving personal information and generating a personal avatar based on that information, means for receiving characteristic information requested by an organization and generating an organization avatar based on that information, and means for conducting interview simulations between the personal avatar and the organization avatar using a generation AI model and evaluating the degree of fit based on the results. This enables effective matching between students and companies while significantly reducing time and costs.

[0659] "Personal information" refers to data that indicates personal attributes such as educational background, skills, and interests, which are necessary for avatar generation.

[0660] A "personal avatar" is a video or text character created by an AI model based on personal information, which virtually represents the characteristics of that individual.

[0661] "Organizational characteristic information" refers to data that indicates the characteristics such as skills, values, and culture that a company or organization seeks.

[0662] An "organizational avatar" is a video or text character that virtually represents the ideal employee profile, created by an AI model based on the characteristics information sought by the organization.

[0663] A "generative AI model" is a technology that uses algorithms learned from large amounts of data to generate avatars based on input information from individuals or organizations.

[0664] "Interview simulation" is a virtual dialogue process in which generated individual avatars and organizational avatars conduct mock interviews through voice or text.

[0665] "Fit" is a score that indicates the degree of potential matching between an individual and an organization, calculated based on the results of an interview simulation.

[0666] This invention is a system that generates avatars based on the characteristics of individuals and organizations, and enables effective matching through virtual interviews. A specific example of this system is described below.

[0667] Each user (individual) enters personal information such as their educational background, skills, and interests into a terminal. This terminal can be, for example, a PC or smartphone. The entered information is sent to a server in real time. The server processes this information and uses a generative AI model to generate a personalized avatar that reflects the individual's characteristics. This generative AI model is pre-trained on a large dataset.

[0668] On the other hand, the user (organization) inputs the desired characteristics and cultural features into the terminal. This information is similarly sent to the server, which then generates an organizational avatar representing the ideal employee profile. This, too, is realized by a generative AI model.

[0669] The generated individual and organizational avatars are automatically matched by the server, and the interview simulation begins. This simulation is conducted using voice or text and is implemented using WebRTC or chatbot frameworks. Natural language processing technology is used throughout the interview process to analyze the interactions between the avatars.

[0670] As a practical example, if a user (individual) provides information such as "I have a strong interest in programming," the server will generate a personal avatar that reflects their programming skills based on this information. If an organization provides information such as "We are looking for creative engineers," the server will generate an organizational avatar that asks creative questions in line with that request. In a mock interview, the personal avatar talks about their project experience, and the organizational avatar asks detailed questions about the project, and the degree of suitability is evaluated.

[0671] Example of a prompt:

[0672] "Based on the information entered by the students, generate avatars that highlight their programming skills. Conduct mock interviews to verify that the avatars match the skill sets required by the companies."

[0673] This system enables efficient matching between individuals and organizations, significantly reducing time and costs.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The user (individual) enters personal information such as educational background, skills, and interests into the terminal. The terminal structures the entered data and converts it into a format for transmission to the server. The input is output as JSON data and sent to the server. The server receives this data and prepares for the next processing step.

[0677] Step 2:

[0678] The server inputs data received from the user into a generative AI model. This data is used as a prompt for generating an avatar that reflects the individual's characteristics. Based on this prompt, the generative AI model runs its algorithm and outputs data for the individual avatar. This output is avatar data that visualizes and textualizes the individual's characteristics.

[0679] Step 3:

[0680] The user (organization) inputs information about the desired characteristics and culture into the terminal. The terminal converts the data into a format that the server can easily process and sends it to the server. This data is also output in JSON format and sent to the server.

[0681] Step 4:

[0682] The server inputs data received from the organization into a generating AI model. The model uses this data as a prompt to generate an organizational avatar that reflects the characteristics the organization desires, and outputs data for the organizational avatar. This data is avatar data that visualizes and textualizes the skills and values ​​the organization desires.

[0683] Step 5:

[0684] The server matches the generated individual avatar with the organization avatar. Using both avatar data sets, it then initiates an interview simulation. The simulation manages the interaction between the avatars using natural language processing techniques. This interaction takes place via voice calls or a chat interface, and interaction data is generated as output.

[0685] Step 6:

[0686] The server analyzes interaction data from the interview simulation. It uses machine learning algorithms to calculate the degree of fit from the input dialogue data. This degree of fit is output as a score indicating the compatibility between the individual and the organization.

[0687] Step 7:

[0688] The server provides feedback to each user (individual and organization) regarding the calculated fitness score. This feedback is generated as text and sent to the user's device. Users can then use this feedback to identify future strategies and areas for improvement.

[0689] (Application Example 1)

[0690] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] Traditional recruitment processes often lacked opportunities for direct communication between students and companies, resulting in lower matching accuracy. Furthermore, understanding appropriate corporate cultures and required skills was difficult, causing students to miss out on opportunities to connect with companies that truly matched their abilities and interests. These challenges need to be addressed.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0693] In this invention, the server includes means for receiving user information and generating a first virtual representation based on that information, means for receiving requirements requested by a company and generating a second virtual representation based on that information, and means for the generated first and second virtual representations to engage in a virtual dialogue with each other and evaluate the degree of suitability based on the results. This makes it possible to enable effective matching between students and companies and improve the efficiency of the recruitment process.

[0694] "Users" refer to students and companies that use the system to provide information and generate their own virtual representations.

[0695] A "virtual representation" is a digital avatar created using a generative AI model based on user information, and it virtually reproduces the user's characteristics.

[0696] "Interaction" refers to the mutual exchange and dialogue that takes place between virtual representations within a virtual space, and is used to evaluate the suitability and level of understanding between the two parties.

[0697] "Fit" is an index that indicates the degree of agreement in suitability and interests between users, calculated based on the results of interactions between virtual representations.

[0698] To implement this invention, a server connected to an information and communication network and terminals accessible by multiple users are required. Users (students) use the terminals to input information such as their academic background, skills, and interests. This information is transmitted to the server via the network. Based on the received information, the server uses a generative AI model to generate a virtual representation that reflects the characteristics of the student.

[0699] Meanwhile, corporate users also input information such as the requirements for the personnel they are looking for and their corporate culture through their terminals, and similarly send this information to the server. Based on this, the server generates virtual interviewers that match the skill sets required by the company.

[0700] The generated virtual representations interact with each other in a virtual space. This process involves constructing a virtual environment using software such as Unity, and utilizing natural language processing technology to analyze the dialogue and evaluate its relevance. The resulting evaluation is then scored as a relevance by the server and provided as feedback to both users.

[0701] For example, if a user enters "I am interested in AI technology," the server generates a virtual representation that reflects this. If a company user writes "We are looking for innovative engineers," a virtual interviewer is generated based on that information. In the simulated conversation, the virtual representation discusses specific projects and ideas, and its suitability is evaluated.

[0702] Examples of prompt messages include: "The student avatar has a deep interest in AI technology. The company avatar is seeking engineers who pursue innovation and will evaluate their suitability through concrete project experience."

[0703] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0704] Step 1:

[0705] The terminal prompts the user (student) to input information such as their educational background, skills, and interests. This input information is formatted as a user profile and sent to the server.

[0706] Step 2:

[0707] The server generates a virtual representation of the student using a generative AI model based on the received user profile. This process analyzes the input characteristic information and performs data processing to construct an appropriate avatar based on the results. The generated virtual representation is then used in the next interaction step.

[0708] Step 3:

[0709] On the other hand, the terminal allows users (companies) to input information such as the requirements for the personnel they are looking for and their corporate culture. This information is compiled into a company profile and sent to the server.

[0710] Step 4:

[0711] The server generates virtual interviewers suitable for a company based on its corporate profile. This generation process involves scrutinizing the company's values ​​and skill requirements, and performing data calculations to design corresponding virtual representations.

[0712] Step 5:

[0713] The server facilitates virtual interactions between generated student virtual representations and virtual company interviewers in a virtual space. Here, software such as Unity is used to provide a visual interface, and natural language processing techniques are employed to enable text and voice interactions. The content of the dialogue between the two is recorded and used to evaluate the degree of relevance.

[0714] Step 6:

[0715] The server analyzes data obtained from the interaction and parses the dialogue content through natural language processing. The analyzed data becomes input information for calculating the degree of fit, and the degree of matching is quantified through a scoring algorithm.

[0716] Step 7:

[0717] The server notifies both the user (student) and the user (company) of the calculated matching score as feedback. This feedback serves as a guide for self-improvement and strategy formulation in future recruitment activities.

[0718] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0719] This invention provides a matching system that takes into account the emotions of both students and companies. This system generates avatars based on user information, and when these avatars conduct mock interviews, it uses an emotion engine to recognize emotions during the conversation, thereby achieving more accurate matching.

[0720] The user (student) enters their information into a terminal. The terminal sends this data to a server. Based on this, the server uses a generation AI to create a student avatar that reflects the student's personality. Similarly, companies also enter their desired candidate profile into the server, and an interviewer avatar reflecting the company's characteristics is generated.

[0721] The generated avatars are matched by the server, and a mock interview begins. At this point, an emotion engine operates, analyzing the emotional state of the users (students and companies) in real time during the conversation between the avatars. Based on the recognized emotions, the server can adjust the interview's progress. This adjustment includes changing the content of questions and the pace of the conversation according to the emotions.

[0722] After the mock interview, the server analyzes emotional data and incorporates this emotional information into the matching score. As a result, in addition to matching based solely on skills and experience, emotional compatibility is also considered, leading to a more precise matching process. The evaluation results are notified to both the student and the company via their respective devices.

[0723] For example, if a student avatar feels slightly anxious during a mock interview, the emotion engine can detect this, and the server can instruct the interviewer avatar to soften their demeanor. Furthermore, if the company avatar is detected as being satisfied with the responses, it can emphasize additional positive feedback.

[0724] This invention, by taking into account the emotional states of students and companies, enables more suitable and sustainable matching in partnerships than conventional systems.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] The user (student) enters personal information such as educational background, work experience, skills, and hobbies into the terminal. The terminal then sends the entered information to the server.

[0728] Step 2:

[0729] The user (company) inputs the desired skills, experience, and personality traits of the personnel into a terminal. This information, including the company culture and values, is then sent to the server.

[0730] Step 3:

[0731] The server uses a generation AI based on student information to create student avatars. These avatars are virtual characters that reflect the individuality of the students.

[0732] Step 4:

[0733] The server uses AI generation based on company information to create interviewer avatars. These avatars are virtual characters that reflect the characteristics of the personnel the company is looking for.

[0734] Step 5:

[0735] The server combines the generated student avatar with the interviewer avatar and starts the mock interview session.

[0736] Step 6:

[0737] The server utilizes an emotion engine to analyze the emotional state of the student avatar and interviewer avatar's dialogue in real time during the mock interview. This analysis may include changes in voice tone and facial expressions.

[0738] Step 7:

[0739] The server uses the analysis results from the emotion engine to dynamically adjust the interview process. Specifically, it takes actions such as changing the content and order of questions based on the interviewee's emotions.

[0740] Step 8:

[0741] The server comprehensively analyzes the conversation content and emotional data after the interview to calculate the degree of matching. Emotional compatibility is also included in the evaluation criteria.

[0742] Step 9:

[0743] The server sends an evaluation summarizing the analysis results to the terminal, notifying users (students and companies) of the degree of matching and emotional feedback.

[0744] Step 10:

[0745] Based on the feedback received, users consider their next steps and repeat the process as needed.

[0746] (Example 2)

[0747] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0748] Traditional matching systems focus on skills and experience, failing to consider emotional compatibility, resulting in insufficient compatibility in actual partnerships. Furthermore, the inability to analyze emotional shifts during interviews and communication in real time and adjust conversations accordingly meant that truly valuable feedback was not being provided to both students and companies.

[0749] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0750] In this invention, the server includes means for receiving user information and generating individual virtual characters, means for receiving requirements for the work system and generating virtual characters for evaluators, and means for virtual characters to conduct simulated conversations and analyze their emotional states. This enables more precise and sustainable matching that takes emotional compatibility into account.

[0751] A "user" refers to an individual or group that uses the system to input their own information and confirms their suitability through matching and evaluation.

[0752] "Information" refers to data about the user's personality and preferences, specifically including data such as educational background, interests, and work experience.

[0753] A "virtual person" refers to an avatar digitally constructed using a generative AI model based on user or company information.

[0754] A "simulated dialogue" refers to a simulation in which generated virtual characters engage in a conversation, and is conducted based on an interview scenario.

[0755] "Emotional state" refers to an individual's psychological reactions and changes detected during simulated dialogue, and is analyzed from factors such as voice and facial expressions.

[0756] A "evaluator" is a virtual character created based on the company's requirements, and refers to an avatar that is responsible for asking questions and providing feedback in simulated conversations.

[0757] "Requirements for operational structure" refer to the type of personnel a company seeks and the skill sets expected for their roles.

[0758] "Matching score" refers to an indicator that shows the compatibility between a user and a company, and is quantified by taking into account skills and emotional factors.

[0759] "System" refers to the hardware and software configuration for integrating and executing the generation of virtual characters, the progression of simulated dialogues, sentiment analysis, and notification of evaluation results.

[0760] The following describes the "modes for carrying out the invention."

[0761] ---

[0762] The embodiment of this invention consists of a method in which a user, a terminal, and a server cooperate to build a virtual interview matching system. The user first inputs personal information and occupational preferences via the terminal. This terminal is equipped with an input support interface and has communication capabilities that enable secure data transmission.

[0763] The terminal sends the information entered by the user to the server. The communication protocol used here should preferably be one with enhanced security, such as HTTPS. Based on the received information, the server uses a generative AI model to generate a virtual person (avatar) that reflects the user's characteristics. This generation process can combine widely used image generation technologies such as DALL-E and natural language processing technologies. Similarly, the company's requirements are also sent to the server, and an evaluator avatar matching the company's desired candidate profile is generated.

[0764] The generated virtual characters and evaluator avatars begin a simulated dialogue on the server. This simulated dialogue utilizes speech recognition and natural language processing technologies for sentiment analysis. For example, sentiment analysis tools like IBM Watson are used to analyze subtle emotional changes during the conversation in real time. Based on these results, the server adjusts the content and pace of the dialogue.

[0765] Emotional state-based matching evaluation is performed after the simulated dialogue is completed. The server analyzes the accumulated emotional data to evaluate the compatibility between the user and the company with greater accuracy. This enables a more precise matching evaluation that incorporates emotional elements.

[0766] For example, a prompt message such as, "Generate an avatar based on the student's profile information and begin an emotion-based mock interview with the company. Next, analyze the emotional changes during the interview and reflect the results in the matching evaluation," is used, and the process proceeds accordingly.

[0767] This embodiment enables users and companies to build longer-term and more sustainable relationships through communication that takes emotional states into account.

[0768] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0769] Step 1:

[0770] Users use the device to input their personal information and career preferences. Specifically, they enter their name, age, educational background, field of expertise, and desired job duties. The device temporarily stores this data in a database such as SQLite. This prepares the user's basic information data.

[0771] Step 2:

[0772] The terminal sends the information entered by the user to the server. Here, the HTTPS protocol is used to securely transfer the data. The server parses the received information in JSON format and converts it into a format usable by the generated AI model. The output of this step is user profile data that the AI ​​model can process.

[0773] Step 3:

[0774] The server uses a generative AI model to generate a virtual character based on user profile data. For example, it outputs an avatar that reflects the user's characteristics as an image using the DALL-E model. At this stage, an avatar with visual and auditory features based on user information is obtained.

[0775] Step 4:

[0776] The personnel information requested by companies is also entered into the server, and evaluator avatars are generated in the same way. This information is processed based on data provided in advance by companies, and avatars that reflect the characteristics of each company are output. In this way, the server maintains virtual representations of both students and companies.

[0777] Step 5:

[0778] The server initiates a simulated dialogue using the generated virtual character and evaluator avatar. It activates an emotion analysis engine and uses natural language processing technology to analyze the conversation between the avatars. At each step, avatar voice and text data are input, and an audio analysis tool outputs emotion changes in real time.

[0779] Step 6:

[0780] The server adjusts the content and flow of the simulated conversation based on the detected emotions. Specifically, it softens questions to alleviate the user's tension or asks more detailed questions to elicit the answers the company is looking for. This results in a smoother and more meaningful conversation.

[0781] Step 7:

[0782] After the simulated dialogue concludes, the server analyzes the accumulated emotional state data to precisely evaluate the compatibility between the user and the company. This evaluation integrates the results of the emotional analysis with the initial data and outputs it as a numerical matching score. Based on these results, both the user and the company are notified.

[0783] (Application Example 2)

[0784] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0785] In recent years, the importance of using digital technology to provide experiences optimized for individual users has increased. Traditional matching systems only consider partial suitability based on skills and experience, and fail to fully consider the emotional responses of viewers in content delivery. Therefore, a deeper level of user experience optimization is desired. This would enable the building of long-term partnerships for both users and businesses and improve viewer satisfaction, but there is a lack of a holistic approach to address these issues.

[0786] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0787] In this invention, the server includes means for receiving user attribute data and generating a digital representation of the user that reflects their personality based on that attribute data; means for receiving requirements data of a business entity and generating a digital representation that reflects the characteristics of the business entity based on that requirements data; means for the generated digital representation of the user and the digital representation of the business entity to interact with each other and evaluate affinity based on the content of the interaction; and means for acquiring the user's reactions while they are viewing and adjusting the content provided based on the acquired reactions. This not only enables sophisticated matching that takes into account emotional compatibility between the user and the business entity, but also makes it possible to provide viewers with a personalized viewing experience in real time.

[0788] "User attribute data" refers to information that represents the characteristics and traits of individual users, and is used to generate digital representations that reflect their individuality.

[0789] "A digital representation of a user that reflects their individuality" refers to a virtual representation that is generated based on the user's attribute data and embodies the user's characteristics.

[0790] "Business entity requirements data" refers to information that represents the characteristics and conditions required by a specific business entity, and is used to generate a digital representation of that business entity.

[0791] A "digital representation that reflects the characteristics of the business entity" is a virtual representation that concretizes the characteristics and requirements of the business entity based on the business entity's requirements data.

[0792] "Engaging in mutual dialogue" refers to the act of generated digital representations interacting with each other, engaging in discussions and simulated dialogues.

[0793] "Assessing affinity" is the act of measuring the emotional and practical fit between users and businesses based on interactions between digital representations.

[0794] "Viewing reactions" refer to the psychological or emotional responses that users exhibit while viewing content.

[0795] "Adjusting the content provided" refers to the process of appropriately changing and adjusting the content of the media being viewed based on user feedback obtained.

[0796] To implement this invention, first, the server receives user attribute data and, based on that data, uses a generated AI model to create a digital representation that reflects the user's personality. In response, the requirements data of the business entity is also input to the server, and based on that, a digital representation that reflects the characteristics of the business entity is generated. With this, both digital representations are ready to begin a simulated dialogue.

[0797] The server manages the interaction between digital representations and uses a generative AI model to evaluate the emotional affinity between the user and the business entity in real time during the interaction. This uses a pre-configured algorithm to quantify emotion and compatibility.

[0798] Furthermore, the device acquires the user's reactions in real time while they are watching using smart glasses or similar devices, and sends this data to the server. Based on this, the server uses a generative AI model to adjust the content provided, using the prompt message, "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion."

[0799] As a concrete example, while a user is watching entertainment, smart glasses capture their facial expressions, and the server analyzes this information to determine how the viewer is feeling. Based on the analysis, if the viewer is enjoying themselves, the system provides more similar scenes; if they show signs of anxiety, it presents calming content, thereby providing an experience optimized for each individual user.

[0800] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0801] Step 1:

[0802] The user inputs their attribute data using a terminal. The terminal sends the input attribute data to the server. The server receives this data and uses a generative AI model to generate a digital representation that reflects the user's personality. The input is the user's attribute data, and the output is the user's digital representation.

[0803] Step 2:

[0804] Businesses input their requirements data using a terminal. The terminal sends this requirements data to a server. The server receives the data and generates a digital representation that reflects the characteristics of the business using a generative AI model. The input is the business's requirements data, and the output is the digital representation of the business.

[0805] Step 3:

[0806] The server initiates a simulated dialogue using the generated digital representations of the user and the business entity. It generates dialogue prompts and advances the dialogue using a generative AI model. The input is the digital representations of the user and the business entity, and the output is the content and progress of the dialogue.

[0807] Step 4:

[0808] The server uses a generated AI model to evaluate emotional affinity between the user and the business entity in real time during simulated dialogue. This uses an emotion analysis algorithm. The input is the dialogue content and generated prompt sentences, and the output is the affinity evaluation value.

[0809] Step 5:

[0810] The device captures the user's reactions while they are viewing content through smart glasses and sends that data to a server. The input is the user's reaction data while they are viewing, and the output is the reaction data sent to the server.

[0811] Step 6:

[0812] The server analyzes user reaction data and uses a generative AI model to generate a prompt message: "Analyze the current emotional state of this viewer and suggest the next scene that matches that emotion." It then adjusts the content provided in real time. The input is viewer reaction data, and the output is the adjusted content.

[0813] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0814] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0816] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0817] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0818] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0819] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0820] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0821] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0822] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0823] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0824] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0825] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0826] 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.

[0827] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0828] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0829] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0830] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0831] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0832] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0833] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0834] The following is further disclosed regarding the embodiments described above.

[0835] (Claim 1)

[0836] A means of receiving student information and generating student avatars based on that information,

[0837] A means of receiving information on the personnel needs of a company and generating interviewer avatars based on that information,

[0838] A method for generating student avatars and interviewer avatars to conduct interviews with each other and evaluate the degree of matching based on the results,

[0839] A means of notifying each user of the evaluation results,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, comprising means for student avatars and interviewer avatars to conduct interview simulations using voice or text.

[0843] (Claim 3)

[0844] The system according to claim 1, comprising means for analyzing interview results and outputting the degree of matching as a score.

[0845] "Example 1"

[0846] (Claim 1)

[0847] A means of receiving personal information and generating a personal avatar based on that information,

[0848] A means of receiving characteristic information requested by an organization and generating an organizational avatar based on that information,

[0849] A method for conducting interview simulations between individual avatars and organizational avatars using a generative AI model, and evaluating the degree of fit based on the results,

[0850] A means of notifying each user of the evaluation results,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, comprising means for individual avatars and organizational avatars to conduct interview simulations using voice or text.

[0854] (Claim 3)

[0855] The system according to claim 1, comprising means for analyzing the results of an interview simulation and outputting the degree of suitability as a numerical value.

[0856] "Application Example 1"

[0857] (Claim 1)

[0858] A means for receiving user information and generating a first virtual representation based on that information,

[0859] A means of receiving the requirements requested by a company and generating a second virtual representation based on that information,

[0860] A means by which the generated first virtual representation and the second virtual representation engage in a virtual dialogue with each other and evaluate the degree of fit based on the result,

[0861] A means of notifying each user of the evaluation results,

[0862] A means to enable interaction between the virtual representation of a company and the virtual representation of a user within a virtual space,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, comprising means for performing a dialogue simulation using voice or text for a first virtual representation and a second virtual representation.

[0866] (Claim 3)

[0867] The system according to claim 1, comprising means for analyzing the results of a virtual dialogue and outputting a degree of fit as an index.

[0868] "Example 2 of combining an emotion engine"

[0869] (Claim 1)

[0870] A means of receiving user information and generating individual virtual characters based on that information,

[0871] A means of receiving requests for a work system and generating virtual evaluators based on those requests,

[0872] A method for analyzing the emotional state during a simulated dialogue between a generated individual virtual character and a virtual evaluator,

[0873] A means of adjusting the progress of the dialogue based on emotional state and evaluating the degree of matching,

[0874] A means of notifying each user of the evaluation results via a data communication terminal,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, comprising means for conducting a simulated interview using voice or text information between individual virtual individuals and a virtual evaluator, and for performing emotion analysis.

[0878] (Claim 3)

[0879] The system according to claim 1, comprising means for analyzing the results of a simulated dialogue and outputting a numerical value representing the degree of matching, taking into account the emotional state.

[0880] "Application example 2 when combining with an emotional engine"

[0881] (Claim 1)

[0882] A means of receiving user attribute data and generating a digital representation of the user that reflects their individuality based on that attribute data,

[0883] A means for receiving requirements data of a business entity and generating a digital representation that reflects the characteristics of the business entity based on that requirements data,

[0884] A means by which the generated digital representation of the user and the digital representation of the business entity interact with each other, and evaluate the affinity based on the content of the interaction,

[0885] A means of notifying each user of the evaluation results,

[0886] A means of obtaining user reactions while they are viewing content and adjusting the content provided based on those reactions,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, comprising means for the digital representation of a user and the digital representation of a business entity to conduct a simulated dialogue using voice or text, and means for analyzing the emotional state of the viewer.

[0890] (Claim 3)

[0891] The system according to claim 1, comprising means for analyzing the results of a simulated dialogue and outputting affinity as a numerical value, and means for personalizing the viewing experience. [Explanation of symbols]

[0892] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving student information and generating student avatars based on that information, A means of receiving information on the personnel needs of a company and generating interviewer avatars based on that information, A method for generating student avatars and interviewer avatars to conduct interviews with each other and evaluate the degree of matching based on the results, A means of notifying each user of the evaluation results, A system that includes this.

2. The system according to claim 1, comprising means for student avatars and interviewer avatars to conduct interview simulations using voice or text.

3. The system according to claim 1, comprising means for analyzing interview results and outputting the degree of matching as a score.

Images