system

Abstract

We provide the system. [Solution] A method for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology, A method for matching company job posting data with job seeker analysis data in real time to achieve optimal matching, A means of supporting communication between companies and job seekers for scheduling interviews and sharing feedback, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , , ,

[0001] The technology of the present disclosure relates to a system. <0​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​This invention provides a talent matching system utilizing generative AI. The system includes means for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology. Furthermore, it includes means for real-time comparison of company job postings and the analyzed data of job seekers to achieve optimal matching, thereby improving the accuracy of matching between job seekers and companies. It also supports communication between companies and job seekers for scheduling interviews and sharing feedback, streamlining the recruitment process. Additionally, it includes means for evaluating long-term suitability by considering the degree of alignment with company values ​​and culture, thereby reducing employee turnover.

[0006] A "job seeker" refers to an individual who is seeking employment and possesses the necessary skills, experience, and values.

[0007] "Work history data" refers to data that includes information about the jobs a job seeker has held in the past, as well as the skills and experience they have acquired.

[0008] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[0009] A "generative AI model" is a type of algorithm in which artificial intelligence learns from large amounts of data and generates and analyzes information to perform a specific task.

[0010] "Company recruitment data" refers to data that includes information about the job responsibilities, required skill sets, and recruitment conditions that companies are seeking.

[0011] "Real-time matching" refers to a process that instantly compares and analyzes data and quickly outputs the results.

[0012] "Supporting communication" refers to providing means and functions that facilitate the smooth transmission of information and exchange of opinions.

[0013] "Value and cultural alignment" is an indicator that measures the degree to which the beliefs and behavioral norms of a company and a job seeker align.

[0014] "Long-term fit" is a criterion used to assess the likelihood of a company and a job seeker maintaining a good relationship over a long period and the possibility of continued employment. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered 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.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system that efficiently matches job seekers with job postings from companies using generation AI. To implement this system, the following configuration is adopted.

[0037] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0038] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. For example, keywords such as "Python programming experience" and "data analysis skills" are identified from the job seeker's resume.

[0039] The server then matches the analyzed job seeker data with the company's job postings. Based on the requirements entered by the company, such as "3+ years of data analysis experience" or "team leadership skills," the server selects candidates and evaluates their suitability. This process is performed in real time, and a list of suitable candidates is generated immediately.

[0040] Company representatives, as users, can view the candidate list through their terminals. If a suitable candidate is found, they can immediately request to schedule an interview. This request is transmitted to the job seeker via the server, and the job seeker can indicate a convenient date and time.

[0041] The server also provides a feedback function, allowing companies to input evaluations of job applicants after interviews. This feedback is shared with the job applicants, facilitating information exchange to help them move on to the next step.

[0042] As a concrete example, consider a case where a company is recruiting data scientists. The company enters job information from a terminal, and the server automatically lists job seekers with data science skills based on those requirements. This list is sent to the company's representative, and once suitable candidates are selected, interview dates are immediately scheduled. This entire process is efficiently realized through interaction between the server, terminal, and user.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The terminal provides a data entry interface for both companies and job seekers. Companies enter job requirements, and job seekers upload their resumes and work histories.

[0046] Step 2:

[0047] The server stores the data received from the terminals in a database. Here, company job postings and detailed work histories of job seekers are reliably recorded.

[0048] Step 3:

[0049] The server uses a generative AI model to analyze job seekers' work history data. This analysis utilizes natural language processing techniques to extract elements such as skills, experience, and values.

[0050] Step 4:

[0051] The server matches the analyzed job seeker data with the company's job postings and executes the matching process. It lists and prioritizes candidates who match the company's requirements in real time.

[0052] Step 5:

[0053] The server generates a list of candidates and sends it to the user, who is the company representative. The list includes information on each candidate's suitability and skills.

[0054] Step 6:

[0055] The user reviews the list of candidates sent via their device and schedules interviews with suitable candidates. Scheduling is done by entering preferred interview dates and times.

[0056] Step 7:

[0057] The server receives the interview scheduling request and notifies the job seeker. Once the job seeker selects a convenient date and time, that information is fed back to the company.

[0058] Step 8:

[0059] Users (companies) enter feedback from their terminals after interviews. This feedback is shared with job seekers via the server and used in further selection processes.

[0060] (Example 1)

[0061] 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."

[0062] The current job-seeking and company matching process often suffers from a mismatch between job seekers' skills and values ​​and companies' recruitment requirements, making efficient matching difficult. Furthermore, scheduling interviews and sharing feedback is time-consuming, leading to inefficient communication. As a result, companies struggle to find suitable talent, and job seekers have difficulty finding a company that fits their needs.

[0063] 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.

[0064] This invention includes a server that acquires job seekers' work history information and analyzes their abilities, experience, and value using natural language processing technology; a server that matches company job postings with the analyzed job seekers' information in real time to achieve the best possible match; and a server that supports communication between companies and job seekers to coordinate interview schedules and share evaluation opinions. This enables efficient and accurate matching between job seekers and companies, and allows for rapid scheduling of interviews and sharing of feedback.

[0065] "Work history information" refers to information that includes the work a job seeker has performed in the past, the content of that work, and the skills and experience gained through that work.

[0066] "Natural language processing technology" is a technology that uses computers to analyze and understand human language and extract its meaning.

[0067] "Job postings" refer to information that companies are recruiting for, including the types of jobs they are looking for, the skills and experience they require, and the working conditions.

[0068] "Analytical information" refers to evaluation results based on skills, experience, and values ​​extracted from the job seeker's work history information.

[0069] "Real-time matching" is a process that instantly compares job seekers' information with the requirements of companies and evaluates the degree of match.

[0070] "Adjusting the interview schedule" is the process of determining a mutually convenient date for both the company and the job seeker.

[0071] "Evaluation feedback" refers to the evaluation and feedback that a company provides to a job applicant after an interview.

[0072] "Supporting communication" means providing the necessary functions to facilitate smooth information exchange between companies and job seekers.

[0073] This invention is a system that efficiently matches job seekers with job postings from companies using a generative AI model. This system mainly consists of a server, terminals, and users (company representatives and job seekers).

[0074] The terminal provides an interface for receiving data input from both companies and job seekers. Company representatives use the terminal to input job information specifying the required duties and skills for job seekers. Job seekers also upload their work history information, including past work experience and acquired skills. This information is transmitted to the server via a secure protocol.

[0075] The server plays a primary role in processing the received data. First, it uses generative AI models and natural language processing techniques to analyze the job seeker's work history information. This analysis utilizes natural language processing libraries (e.g., spaCy and NLTK) to extract specific skills and experience from job seekers, thereby identifying actual job duties and possible roles. Based on these analysis results, the server matches the requirements sought by companies and uses advanced algorithms to select the most suitable candidates.

[0076] The company representative, as the user, is instantly shown a list of optimal candidates generated by the server on their device. Based on this list, the company representative can quickly make decisions and create interview offers for suitable candidates. Furthermore, interview schedules are coordinated with job seekers via the server, and a calendar API is used to harmonize the schedules of both parties.

[0077] For example, when a company is recruiting data scientists, the server analyzes the company's requirements, such as "data analysis" and "Python skills," and lists job seekers who possess those skills. This list is sent to the company representative in real time.

[0078] Example of a prompt:

[0079] "Please list suitable candidates for the data scientist position."

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The terminal accepts data input from both companies and job seekers. Company representatives use the terminal's input form to enter job information such as the job title, required skills, and years of experience. Job seekers upload their resumes and work histories through the terminal. This input data is standardized based on a sample format and sent to the server.

[0083] Step 2:

[0084] The server uses generative AI models and natural language processing techniques to analyze the received work history information. Specifically, it uses natural language processing libraries (e.g., spaCy and NLTK) to analyze text data and extract keywords related to important skills and experience. For example, it extracts skills such as "Python" and "data analysis" from resumes and saves them as analyzed data.

[0085] Step 3:

[0086] The server matches the analyzed job seeker data with the company's job postings. This process compares the requirements entered by the company (e.g., skills, years of experience) with the analyzed job seeker data, applying a matching algorithm to identify the most suitable candidates. As a result of the matching, a list of highly suitable candidates is generated, and evaluation scores are calculated.

[0087] Step 4:

[0088] The company representative, acting as the user, views a list of candidates provided by the server on their terminal. Based on this list, the company representative selects interview candidates and enters a request to schedule interviews. The interview request is immediately sent to the server, and the job seeker is notified.

[0089] Step 5:

[0090] When the server receives an interview request from a company representative, it notifies the job seeker and retrieves their response. At this point, the server uses a calendar API to automate the process of coordinating convenient interview dates and synchronizes the schedules of both parties.

[0091] Step 6:

[0092] The server receives post-interview feedback from companies and shares it with job seekers via the system. Company representatives input feedback via their terminals, and the server transmits this information to job seekers. This allows job seekers to learn about their interview evaluation and areas for improvement.

[0093] (Application Example 1)

[0094] 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."

[0095] In the job search process, there is a need for a system that enables efficient and appropriate matching between job seekers and companies, and facilitates smooth progress through the initial hiring procedures. However, current systems often struggle to accurately match job seekers' skills with company requirements, and post-hiring procedures are frequently cumbersome. Therefore, a method is needed to quickly select the most suitable candidates and streamline the entire recruitment process.

[0096] 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.

[0097] In this invention, the server includes means for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology; means for comparing company job data with the analyzed job seeker data in real time to perform optimal matching; means for supporting information exchange between companies and job seekers to coordinate interview schedules and share evaluation results; and means for supporting job seekers with the initial procedures required after being hired using e-commerce technology. This improves the efficiency of matching job seekers and companies and streamlines the entire recruitment process.

[0098] "Job seeker's work history data" refers to information that shows what kind of work a job seeker has done in the past and what skills and knowledge they possess.

[0099] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for document analysis and the extraction of specific information.

[0100] "Company recruitment data" refers to information about job titles, required skills, working conditions, and other requirements that companies present when recruiting new employees.

[0101] "Real-time matching" refers to a process that processes data immediately upon receipt and performs matching based on current conditions.

[0102] "Optimal matching" means evaluating how well a job seeker's skills and experience align with a company's requirements and selecting the most suitable candidate.

[0103] "Scheduling an interview" refers to the process where the company and the job seeker confirm each other's availability and set an interview date and time that is appropriate.

[0104] "Evaluation results" refer to the company's assessment and opinions of job applicants obtained through interviews and document screening.

[0105] "Supporting information exchange" means enabling both parties to exchange necessary information quickly and accurately.

[0106] "Initial procedures" refer to the necessary procedures related to contracts and joining the company when a job seeker is hired.

[0107] "Electronic commerce technology" refers to technologies that enable various commercial transactions online and are used for payment and contract procedures.

[0108] The server receives work history data from job seekers and analyzes it using natural language processing technology with a generative AI model. From the data obtained through the analysis, information such as the job seeker's skills, experience, and values ​​is extracted and compared in real time with the company's job postings. Based on this, the company can obtain the most suitable candidates.

[0109] The server also includes a function to assist in scheduling interviews between the company and job seekers, providing an interface to streamline communication and ensure smooth exchange of necessary information. This allows both parties to easily determine interview dates and times.

[0110] Furthermore, if a candidate is selected, the server uses e-commerce technology to assist with the initial hiring procedures for the job seeker. This allows the job seeker to expedite the hiring process.

[0111] As a concrete example, an AI model generated on a server extracts keywords such as data analysis skills and leadership experience from job seekers' resume data, calculates the degree of matching with the company's job requirements, and lists highly matching candidates. This entire process allows companies to quickly find the most suitable talent.

[0112] An example of a prompt message would be: "Consider the applicant's past experience and skill set, evaluate whether they are the best fit for the company's job posting, and show how training costs will be paid if hired."

[0113] This system utilizes Python libraries and APIs on cloud services to enable real-time data processing.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The terminal receives work history data (resumes and work history documents) from job seekers. This data includes basic information, experience, and skill sets entered by the job seekers. The terminal sends this data to the server. It receives work history data as input and generates data in a format that is sent to the server as output.

[0117] Step 2:

[0118] The server inputs the received work history data into a generating AI model, which then analyzes it using natural language processing technology. This process extracts information such as the job seeker's skills, experience, and values. The input is the received work history data, which is then analyzed by the generating AI model and output as structured data. In this extraction process, the focus is on specific skills, such as "experience programming in Python."

[0119] Step 3:

[0120] The server matches structured analytical data with company job posting data to achieve the best possible match. Input requires analyzed job seeker data and company request data. In this step, the server compares the received analytical data with the job posting data in real time, calculates a matching score based on the items with the highest degree of match, and outputs it. Specifically, filtering is performed using database queries.

[0121] Step 4:

[0122] The user (company representative) uses a terminal to view a list of matching candidates sent from the server. The list of matching candidates is prioritized based on scores. The input is a list of candidates sent from the server, and the output is the selection of interviewees based on this list. Specific actions include using a GUI to view information about the candidates on the list.

[0123] Step 5:

[0124] The server assists in scheduling interviews between companies and job seekers, facilitating smooth information exchange by prompting users as needed. It takes the schedule information of both companies and job seekers as input and generates a pre-arranged interview schedule as output. This operation uses prompts such as "Considering the job seeker's past experience and skill set..." to suggest a date and time that works for both parties.

[0125] Step 6:

[0126] If a candidate is selected, the server uses e-commerce technology to provide the job seeker with the necessary initial procedural information. Inputs include the selected candidate information and a list of required procedures, while outputs include payment options and procedural steps presented to the candidate. Specific actions include online payment procedures for accepting the job offer and subsequent training costs.

[0127] 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.

[0128] This invention incorporates an emotion engine that recognizes user emotions into a system that efficiently matches job seekers with company job postings using generative AI. The system has the following configuration.

[0129] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0130] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. Simultaneously, the server uses an emotion engine to analyze the job seeker's emotional characteristics from the data and incorporates this into the matching evaluation.

[0131] The server then compares the analyzed job seeker data with the company's job postings and executes the matching process. Here, it lists candidates who match the company's requirements in real time and adjusts the fit based on the sentiment analysis results, so that not only documented skills but also emotional fit is included in the evaluation.

[0132] The company representative, acting as the user, can review the candidate list via their terminal and select candidates, including evaluating emotional compatibility. Once a suitable candidate is found, they can request to schedule an interview. This request is transmitted to the job seeker via the server, who can then indicate a convenient date and time.

[0133] During the interview process, the server uses an emotion engine to analyze the emotions of both the company and the job seeker in real time. This information is fed back to the interviewer to help them appropriately adjust their responses and questions during the interview.

[0134] As a concrete example, consider a case where a company is recruiting sales staff with strong customer service skills. In this scenario, the server analyzes not only the job applicant's work experience but also their emotional characteristics related to customer service (e.g., empathy, stress tolerance), and lists candidates who match the company's desired profile. Through this series of interactions, the company can effectively find candidates who are emotionally and skillfully suitable.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The terminal provides an interface for easy input from both companies and job seekers. Companies enter job requirements and desired conditions, while job seekers upload their resumes and work histories. This data is then transferred to the server.

[0138] Step 2:

[0139] The server stores the received data in a database. This ensures that company job postings and job seeker work history data are accurately recorded and available for subsequent processing.

[0140] Step 3:

[0141] The server uses a generative AI model to analyze job seekers' work history data. This analysis uses natural language processing techniques to extract the job seeker's skills, experience, values, and emotional characteristics. For example, attributes such as "leadership," "stress tolerance," and "cooperativeness" are identified.

[0142] Step 4:

[0143] The server integrates company job posting data and job seeker analysis data to perform real-time matching. Here, user emotional characteristics are also taken into consideration, and the degree of suitability is adjusted by an emotion engine.

[0144] Step 5:

[0145] The server generates a list of matching candidates, which is then provided to the user, who is the company representative. This is a detailed list that includes not only the candidate's skill set but also an assessment of emotional compatibility.

[0146] Step 6:

[0147] The user reviews the candidate list provided through their device, selects the candidate they deem most suitable, and schedules an interview. The user confirms the candidate's emotional characteristics on their device while finalizing the interview schedule.

[0148] Step 7:

[0149] The server uses an emotion engine to perform emotional analysis during interviews, evaluating the real-time emotional state of both the company and the job seeker. This evaluation is fed back to the interviewer, who can use it to adjust the questions and their demeanor during the interview.

[0150] Step 8:

[0151] After an interview, the user (company) enters feedback, registering their evaluation and emotional observations about the job seeker on the server. The server then uses this feedback for further analysis and prepares to proceed to the next selection step.

[0152] (Example 2)

[0153] 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".

[0154] In the labor market, a challenge lies in the difficulty of quickly and optimally matching job seekers with companies, taking into account skills, values, and emotional compatibility. Traditional systems are limited to matching skills and experience, and are unable to assess overall compatibility, including emotional aspects, thus hindering the establishment of long-term employment relationships and the streamlining of short-term recruitment processes.

[0155] 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.

[0156] In this invention, the server includes means for analyzing the skills, experience, and values ​​of job seekers using natural language processing; means for using sentiment analysis technology to analyze the emotional characteristics of job seekers; and means for matching the job requirements of employers with the analyzed information of job seekers in real time to perform optimal matching. This makes it possible to make a comprehensive suitability judgment that takes both skills and emotions into consideration, and promotes the efficient matching of the most suitable personnel.

[0157] "Job seeker's work history information" refers to records of the jobs and duties an individual has performed to date, and serves as basic data for evaluating their skill set and achievements.

[0158] "Natural language processing" is a general term for technologies that enable computers to understand and analyze human language and extract useful information.

[0159] "Emotional analysis technology" refers to technology that analyzes and identifies an individual's emotional state from text, voice, and facial expressions.

[0160] "Job requirements" are a compilation of information outlining the skills, experience, personality traits, and other requirements that a company seeks from its employees.

[0161] "Real-time matching" refers to the process of instantly comparing and evaluating information on job seekers and companies, and analyzing the degree of compatibility.

[0162] "Fit" is an indicator that shows the degree to which a job seeker's skills and emotional characteristics match the requirements and culture of a company.

[0163] "Communication support means" refers to methods that provide tools and protocols for efficiently sending and receiving information.

[0164] "Real-time analysis during interviews" refers to a technology that analyzes participants' emotions and reactions in real time during an interview and provides necessary information immediately.

[0165] This invention is a system that supports the optimal matching of job seekers and companies. The system mainly consists of terminals, servers, and users.

[0166] The terminal provides an interface for companies and job seekers to input data. Company users can enter recruitment information for required personnel into the terminal's form, while job seekers can upload career information such as resumes and work histories. This data is transmitted to the server via the SSL / TLS protocol.

[0167] The server is responsible for the core processing of this system. It uses a generative AI model and performs natural language processing to analyze the received job seeker's work history information. This analysis extracts the job seeker's skills, experience, and values ​​and converts them into structured data. Furthermore, the server employs sentiment analysis technology to analyze emotional characteristics from the job seeker's writing. This allows for the measurement of not only skills but also emotional compatibility.

[0168] After the analysis is complete, the server matches the data against the company's job requirements and compares and evaluates both sets of data in real time. The resulting candidate list is then prioritized based on factors such as emotional compatibility and skill match.

[0169] Each company representative, acting as a user, can view a list of candidates sent from the server via their terminal. This list includes skill and emotional compatibility scores for each candidate, allowing company representatives to select candidates and schedule interviews. The determined interview schedule is then notified to the job seeker via the server. During the interview, the server analyzes the emotions of the interviewees in real time and provides this information as feedback to the interviewer.

[0170] As a concrete example, consider a company looking for highly skilled customer support personnel. In this case, the server analyzes not only the job applicant's work experience but also their emotional characteristics (e.g., empathy, stress tolerance) and lists the applicants who best match the company's desired profile. This interaction allows the company to quickly and effectively find the right talent.

[0171] An example of a prompt for a generative AI model is: "Analyze the following work history data and extract the job seeker's skills and emotional characteristics."

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The terminal receives input data from both the company user and the job seeker. Company users enter job requirements, and job seeker users upload their resumes and work histories. The input data at this time consists of the company's job requirements and the job seeker's work history information. As output, the input data is securely transmitted to the server using the SSL / TLS protocol.

[0175] Step 2:

[0176] The server analyzes the job seeker's work history information that it receives. Using a generative AI model, it performs natural language processing to extract the job seeker's skills, experience, and values ​​from the input work history. The input here is the job seeker's work history information, and the output is structured data such as the job seeker's skill set obtained through analysis.

[0177] Step 3:

[0178] The server uses emotion analysis technology to evaluate the emotional characteristics of job applicants. It takes written information submitted by the applicant as input, analyzes their emotional state from that text, and quantifies characteristics such as empathy and stress tolerance. The output is data representing these emotional characteristics.

[0179] Step 4:

[0180] The server matches job requirements with analyzed information on job seekers in real time. It uses the job requirements provided by companies and analyzed data on job seekers as input, and calculates a confidence score based on a matching algorithm. The output is a list of job seekers with a high degree of matching.

[0181] Step 5:

[0182] The user, a company representative, reviews the candidate list sent from the server via their terminal. The input is a list of job seekers and their suitability ratings, and the company representative selects candidates to interview based on this. The output is a list of job seekers whose selection process is progressing.

[0183] Step 6:

[0184] The server collects and analyzes emotional data between the company and the job seeker using emotion analysis technology during the interview process. It uses audio and video data from the interview as input to accurately measure emotional states in real time. The output provides this emotional information as feedback to the interviewer, supporting them in adjusting questions and responses.

[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 modern recruitment processes, emotional compatibility is just as important as a candidate's technical skills and experience. However, traditional systems struggle to effectively assess the emotional fit between candidates and companies, making it difficult to find the best talent. Similarly, electronic payment systems may fail to provide an appropriate interface that responds to user emotions, potentially compromising user satisfaction.

[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 job seekers' work history information and analyzing their abilities, experience, and value using natural language processing technology; means for matching company job postings with the analyzed job seeker information in real time to achieve the best possible match; means for supporting communication between companies and job seekers to coordinate interview schedules and share opinions; and means for analyzing the emotions of decision-makers and dynamically adjusting the user interface based on the results. This enables technically and emotionally optimal matching for both job seekers and companies, and allows for flexible responses to user emotions in electronic payments.

[0190] "Work history information" refers to detailed data about a job seeker's past work experience, demonstrating their skills and abilities.

[0191] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0192] "Company job postings" refer to information about the personnel requirements and job descriptions that companies are looking for.

[0193] "Real-time matching" is a process that instantly compares received data and determines whether it matches.

[0194] "Communication for sharing and exchanging opinions" refers to a means of communication that allows for the two-way exchange of news and ideas.

[0195] "Emotional analysis" refers to the analytical process used to determine and evaluate an individual's emotional state.

[0196] A "user interface" is the screen configuration that allows the user and the system to interact with each other.

[0197] "Dynamic adjustment" means that settings and displays are changed as needed depending on the situation.

[0198] This invention is a system for achieving optimal matching between job seekers and companies, and is capable of comprehensively evaluating the emotional and technical characteristics of job seekers. The system mainly consists of three elements: a server, a terminal, and a user.

[0199] First, the terminal provides an interface for collecting input information from companies and job seekers. Companies enter job postings through the terminal, and job seekers upload their work history information. This information is then sent to the server.

[0200] Next, the server analyzes the received information. Here, a generative AI model is used, and natural language processing techniques are employed to extract the job seeker's abilities, experience, and value. Simultaneously, an emotion engine is used to evaluate the job seeker's emotional characteristics, and emotional compatibility is incorporated into the matching process.

[0201] Furthermore, in electronic payments, the server analyzes the user's emotions in real time. Based on the analysis results, the user interface design is dynamically adapted. This allows for the provision of an optimal interface tailored to the user's emotions. Specifically, if the user is feeling anxious, the screen's colors are changed to calmer tones to promote a sense of security.

[0202] In implementing this system, we will use emotion recognition APIs (e.g., Microsoft® Azure® Emotion API) and React Native as a framework, enabling the development of highly versatile applications.

[0203] For example, if a company is looking for someone with excellent communication skills, the system will analyze the applicant's past work experience and emotional characteristics to list the most suitable candidates. An example of a prompt to the generative AI model is, "Suggest the best UI theme and navigation message for when the user is feeling anxious."

[0204] In this way, a system is built in which servers, terminals, and users work together to achieve both technical and emotional matching.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The terminal receives job postings entered by companies and work history information uploaded by job seekers. The input information is collected via user forms and sent to the server. This is the process of delivering relevant information to the server through the act of data transmission.

[0208] Step 2:

[0209] The server analyzes the received information. First, it uses a generative AI model to extract the job seeker's skills, experience, and value from their work history information using natural language processing techniques. The input is work history information, and the output is the analyzed skill set. This analysis involves the process of textual analysis of the data.

[0210] Step 3:

[0211] The server then uses an emotion engine to evaluate the job seeker's emotional characteristics. Input is work history information, and voice and facial expression data may also be required. The output is an emotional characteristic score. This process involves data calculations called emotion analysis.

[0212] Step 4:

[0213] The server matches company job postings with analyzed job seeker data in real time, calculates technical and emotional fit scores, and lists the best candidates. The input is the analyzed data (output from the previous step) and the company job postings. The output is a list of job seekers with a high degree of matching. This operation involves information matching and fit calculation.

[0214] Step 5:

[0215] The device supports communication between companies and job seekers for scheduling interviews. Users propose interview dates, and both parties are notified. This is done through the sharing of the proposed date and time.

[0216] Step 6:

[0217] In the electronic payment process, the server analyzes the user's emotions in real time from their facial image and voice data, and dynamically adjusts the user interface displayed on the terminal based on the results. The input is real-time data including emotions, and the output is the modified interface state. This step involves emotion analysis and interface updating.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] This invention is a system that efficiently matches job seekers with job postings from companies using generation AI. To implement this system, the following configuration is adopted.

[0235] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0236] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. For example, keywords such as "Python programming experience" and "data analysis skills" are identified from the job seeker's resume.

[0237] The server then matches the analyzed job seeker data with the company's job postings. Based on the requirements entered by the company, such as "3+ years of data analysis experience" or "team leadership skills," the server selects candidates and evaluates their suitability. This process is performed in real time, and a list of suitable candidates is generated immediately.

[0238] Company representatives, as users, can view the candidate list through their terminals. If a suitable candidate is found, they can immediately request to schedule an interview. This request is transmitted to the job seeker via the server, and the job seeker can indicate a convenient date and time.

[0239] The server also provides a feedback function, allowing companies to input evaluations of job applicants after interviews. This feedback is shared with the job applicants, facilitating information exchange to help them move on to the next step.

[0240] As a concrete example, consider a case where a company is recruiting data scientists. The company enters job information from a terminal, and the server automatically lists job seekers with data science skills based on those requirements. This list is sent to the company's representative, and once suitable candidates are selected, interview dates are immediately scheduled. This entire process is efficiently realized through interaction between the server, terminal, and user.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The terminal provides a data entry interface for both companies and job seekers. Companies enter job requirements, and job seekers upload their resumes and work histories.

[0244] Step 2:

[0245] The server stores the data received from the terminals in a database. Here, company job postings and detailed work histories of job seekers are reliably recorded.

[0246] Step 3:

[0247] The server uses a generative AI model to analyze job seekers' work history data. This analysis utilizes natural language processing techniques to extract elements such as skills, experience, and values.

[0248] Step 4:

[0249] The server matches the analyzed job seeker data with the company's job postings and executes the matching process. It lists and prioritizes candidates who match the company's requirements in real time.

[0250] Step 5:

[0251] The server generates a list of candidates and sends it to the user, who is the company representative. The list includes information on each candidate's suitability and skills.

[0252] Step 6:

[0253] The user reviews the list of candidates sent via their device and schedules interviews with suitable candidates. Scheduling is done by entering preferred interview dates and times.

[0254] Step 7:

[0255] The server receives the interview scheduling request and notifies the job seeker. Once the job seeker selects a convenient date and time, that information is fed back to the company.

[0256] Step 8:

[0257] Users (companies) enter feedback from their terminals after interviews. This feedback is shared with job seekers via the server and used in further selection processes.

[0258] (Example 1)

[0259] 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."

[0260] The current job-seeking and company matching process often suffers from a mismatch between job seekers' skills and values ​​and companies' recruitment requirements, making efficient matching difficult. Furthermore, scheduling interviews and sharing feedback is time-consuming, leading to inefficient communication. As a result, companies struggle to find suitable talent, and job seekers have difficulty finding a company that fits their needs.

[0261] 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.

[0262] This invention includes a server that acquires job seekers' work history information and analyzes their abilities, experience, and value using natural language processing technology; a server that matches company job postings with the analyzed job seekers' information in real time to achieve the best possible match; and a server that supports communication between companies and job seekers to coordinate interview schedules and share evaluation opinions. This enables efficient and accurate matching between job seekers and companies, and allows for rapid scheduling of interviews and sharing of feedback.

[0263] "Work history information" refers to information that includes the work a job seeker has performed in the past, the content of that work, and the skills and experience gained through that work.

[0264] "Natural language processing technology" is a technology that uses computers to analyze and understand human language and extract its meaning.

[0265] "Job postings" refer to information that companies are recruiting for, including the types of jobs they are looking for, the skills and experience they require, and the working conditions.

[0266] "Analytical information" refers to evaluation results based on skills, experience, and values ​​extracted from the job seeker's work history information.

[0267] "Real-time matching" is a process that instantly compares job seekers' information with the requirements of companies and evaluates the degree of match.

[0268] "Adjusting the interview schedule" is the process of determining a mutually convenient date for both the company and the job seeker.

[0269] "Evaluation feedback" refers to the evaluation and feedback that a company provides to a job applicant after an interview.

[0270] "Supporting communication" means providing the necessary functions to facilitate smooth information exchange between companies and job seekers.

[0271] This invention is a system that efficiently matches job seekers with job postings from companies using a generative AI model. This system mainly consists of a server, terminals, and users (company representatives and job seekers).

[0272] The terminal provides an interface for receiving data input from both companies and job seekers. Company representatives use the terminal to input job information specifying the required duties and skills for job seekers. Job seekers also upload their work history information, including past work experience and acquired skills. This information is transmitted to the server via a secure protocol.

[0273] The server plays a primary role in processing the received data. First, it uses generative AI models and natural language processing techniques to analyze the job seeker's work history information. This analysis utilizes natural language processing libraries (e.g., spaCy and NLTK) to extract specific skills and experience from job seekers, thereby identifying actual job duties and possible roles. Based on these analysis results, the server matches the requirements sought by companies and uses advanced algorithms to select the most suitable candidates.

[0274] The company representative, as the user, is instantly shown a list of optimal candidates generated by the server on their device. Based on this list, the company representative can quickly make decisions and create interview offers for suitable candidates. Furthermore, interview schedules are coordinated with job seekers via the server, and a calendar API is used to harmonize the schedules of both parties.

[0275] For example, when a company is recruiting data scientists, the server analyzes the company's requirements, such as "data analysis" and "Python skills," and lists job seekers who possess those skills. This list is sent to the company representative in real time.

[0276] Example of a prompt:

[0277] "Please list suitable candidates for the data scientist position."

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The terminal accepts data input from both companies and job seekers. Company representatives use the terminal's input form to enter job information such as the job title, required skills, and years of experience. Job seekers upload their resumes and work histories through the terminal. This input data is standardized based on a sample format and sent to the server.

[0281] Step 2:

[0282] The server uses an AI model and natural language processing technology generated to analyze the received work history information. Specifically, it analyzes the text data using natural language processing libraries (e.g., spaCy or NLTK) to extract keywords for important skills and experiences. For example, skills such as "Python" and "data analysis" are extracted from the resume and saved as analyzed data.

[0283] Step 3:

[0284] The server compares the analyzed job seeker data with the company's job offers. In this process, a matching algorithm is applied to compare the requirements (e.g., skills, years of experience) entered by the company with the analyzed data of the job seeker to identify the most suitable candidates. As a result of the matching, a list of highly compatible candidates is generated and an evaluation score is calculated.

[0285] Step 4:

[0286] The corporate staff member, who is the user, checks the candidate list provided by the server on the terminal. Based on this list, the corporate staff member selects interview candidates and enters a request to adjust the interview schedule. The interview request is immediately sent to the server and notified to the job seeker.

[0287] Step 5:

[0288] When the server receives an interview request from the corporate staff member, it notifies the job seeker and obtains the job seeker's response. At this time, the server utilizes the Calendar API to automate the process of adjusting a convenient interview schedule and synchronize the schedules of both parties.

[0289] Step 6:

[0290] The server receives post-interview feedback from companies and shares it with job seekers via the system. Company representatives input feedback via their terminals, and the server transmits this information to job seekers. This allows job seekers to learn about their interview evaluation and areas for improvement.

[0291] (Application Example 1)

[0292] 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."

[0293] In the job search process, there is a need for a system that enables efficient and appropriate matching between job seekers and companies, and facilitates smooth progress through the initial hiring procedures. However, current systems often struggle to accurately match job seekers' skills with company requirements, and post-hiring procedures are frequently cumbersome. Therefore, a method is needed to quickly select the most suitable candidates and streamline the entire recruitment process.

[0294] 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.

[0295] In this invention, the server includes means for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology; means for comparing company job data with the analyzed job seeker data in real time to perform optimal matching; means for supporting information exchange between companies and job seekers to coordinate interview schedules and share evaluation results; and means for supporting job seekers with the initial procedures required after being hired using e-commerce technology. This improves the efficiency of matching job seekers and companies and streamlines the entire recruitment process.

[0296] "Job seeker's work history data" refers to information that shows what kind of work a job seeker has done in the past and what skills and knowledge they possess.

[0297] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for document analysis and the extraction of specific information.

[0298] "Company recruitment data" refers to information about job titles, required skills, working conditions, and other requirements that companies present when recruiting new employees.

[0299] "Real-time matching" refers to a process that processes data immediately upon receipt and performs matching based on current conditions.

[0300] "Optimal matching" means evaluating how well a job seeker's skills and experience align with a company's requirements and selecting the most suitable candidate.

[0301] "Scheduling an interview" refers to the process where the company and the job seeker confirm each other's availability and set an interview date and time that is appropriate.

[0302] "Evaluation results" refer to the company's assessment and opinions of job applicants obtained through interviews and document screening.

[0303] "Supporting information exchange" means enabling both parties to exchange necessary information quickly and accurately.

[0304] "Initial procedures" refer to the necessary procedures related to contracts and joining the company when a job seeker is hired.

[0305] "Electronic commerce technology" refers to technologies that enable various commercial transactions online and are used for payment and contract procedures.

[0306] The server receives work history data from job seekers and analyzes it using natural language processing technology with a generative AI model. From the data obtained through the analysis, information such as the job seeker's skills, experience, and values ​​is extracted and compared in real time with the company's job postings. Based on this, the company can obtain the most suitable candidates.

[0307] The server also has a function to assist in scheduling interviews between the company and job seekers, and provides an interface for efficient communication so that necessary information exchange can be smoothly carried out. As a result, both parties can smoothly determine the interview date and time.

[0308] Furthermore, when the employment is determined, the server uses e-commerce transaction technology to assist in the initial procedures regarding the employment of job seekers. As a result, job seekers can quickly progress through the employment process.

[0309] As a specific example, an AI model generated on the server extracts keywords such as data analysis skills and leadership experience from the resume data of job seekers, calculates the degree of match with the recruitment requirements posted by the company, and lists candidates with a high degree of match. Through this series of processes, the company can quickly find the most suitable talents.

[0310] As an example of a prompt sentence, a sentence such as "Considering the past experience and skill set of the job seeker, evaluate whether it is most suitable for the company's job information, and display the payment method for training expenses in the case of employment." is used.

[0311] This system uses Python libraries and APIs on cloud services to enable real-time data processing.

[0312] The flow of specific processing in Application Example 1 will be described using FIG. 12. <8500098>5> Step 1:

[0314] The terminal receives job history data (resume and job history) from the job seeker. This data includes basic information, experience, skill set, etc. input by the job seeker. The terminal sends this data to the server. It receives job history data as input and generates data in a format that is sent to the server as output.

[0315] Step 2:

[0316] The server inputs the received work history data into a generating AI model, which then analyzes it using natural language processing technology. This process extracts information such as the job seeker's skills, experience, and values. The input is the received work history data, which is then analyzed by the generating AI model and output as structured data. In this extraction process, the focus is on specific skills, such as "experience programming in Python."

[0317] Step 3:

[0318] The server matches structured analytical data with company job posting data to achieve the best possible match. Input requires analyzed job seeker data and company request data. In this step, the server compares the received analytical data with the job posting data in real time, calculates a matching score based on the items with the highest degree of match, and outputs it. Specifically, filtering is performed using database queries.

[0319] Step 4:

[0320] The user (company representative) uses a terminal to view a list of matching candidates sent from the server. The list of matching candidates is prioritized based on scores. The input is a list of candidates sent from the server, and the output is the selection of interviewees based on this list. Specific actions include using a GUI to view information about the candidates on the list.

[0321] Step 5:

[0322] The server assists in scheduling interviews between companies and job seekers, facilitating smooth information exchange by prompting users as needed. It takes the schedule information of both companies and job seekers as input and generates a pre-arranged interview schedule as output. This operation uses prompts such as "Considering the job seeker's past experience and skill set..." to suggest a date and time that works for both parties.

[0323] Step 6:

[0324] If a candidate is selected, the server uses e-commerce technology to provide the job seeker with the necessary initial procedural information. Inputs include the selected candidate information and a list of required procedures, while outputs include payment options and procedural steps presented to the candidate. Specific actions include online payment procedures for accepting the job offer and subsequent training costs.

[0325] 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.

[0326] This invention incorporates an emotion engine that recognizes user emotions into a system that efficiently matches job seekers with company job postings using generative AI. The system has the following configuration.

[0327] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0328] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. Simultaneously, the server uses an emotion engine to analyze the job seeker's emotional characteristics from the data and incorporates this into the matching evaluation.

[0329] The server then compares the analyzed job seeker data with the company's job postings and executes the matching process. Here, it lists candidates who match the company's requirements in real time and adjusts the fit based on the sentiment analysis results, so that not only documented skills but also emotional fit is included in the evaluation.

[0330] The company representative, acting as the user, can review the candidate list via their terminal and select candidates, including evaluating emotional compatibility. Once a suitable candidate is found, they can request to schedule an interview. This request is transmitted to the job seeker via the server, who can then indicate a convenient date and time.

[0331] During the interview process, the server uses an emotion engine to analyze the emotions of both the company and the job seeker in real time. This information is fed back to the interviewer to help them appropriately adjust their responses and questions during the interview.

[0332] As a concrete example, consider a case where a company is recruiting sales staff with strong customer service skills. In this scenario, the server analyzes not only the job applicant's work experience but also their emotional characteristics related to customer service (e.g., empathy, stress tolerance), and lists candidates who match the company's desired profile. Through this series of interactions, the company can effectively find candidates who are emotionally and skillfully suitable.

[0333] The following describes the processing flow.

[0334] Step 1:

[0335] The terminal provides an interface for easy input from both companies and job seekers. Companies enter job requirements and desired conditions, while job seekers upload their resumes and work histories. This data is then transferred to the server.

[0336] Step 2:

[0337] The server stores the received data in a database. This ensures that company job postings and job seeker work history data are accurately recorded and available for subsequent processing.

[0338] Step 3:

[0339] The server uses a generative AI model to analyze job seekers' work history data. This analysis uses natural language processing techniques to extract the job seeker's skills, experience, values, and emotional characteristics. For example, attributes such as "leadership," "stress tolerance," and "cooperativeness" are identified.

[0340] Step 4:

[0341] The server integrates company job posting data and job seeker analysis data to perform real-time matching. Here, user emotional characteristics are also taken into consideration, and the degree of suitability is adjusted by an emotion engine.

[0342] Step 5:

[0343] The server generates a list of matching candidates, which is then provided to the user, who is the company representative. This is a detailed list that includes not only the candidate's skill set but also an assessment of emotional compatibility.

[0344] Step 6:

[0345] The user reviews the candidate list provided through their device, selects the candidate they deem most suitable, and schedules an interview. The user confirms the candidate's emotional characteristics on their device while finalizing the interview schedule.

[0346] Step 7:

[0347] The server uses an emotion engine to perform emotional analysis during interviews, evaluating the real-time emotional state of both the company and the job seeker. This evaluation is fed back to the interviewer, who can use it to adjust the questions and their demeanor during the interview.

[0348] Step 8:

[0349] After an interview, the user (company) enters feedback, registering their evaluation and emotional observations about the job seeker on the server. The server then uses this feedback for further analysis and prepares to proceed to the next selection step.

[0350] (Example 2)

[0351] 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".

[0352] In the labor market, a challenge lies in the difficulty of quickly and optimally matching job seekers with companies, taking into account skills, values, and emotional compatibility. Traditional systems are limited to matching skills and experience, and are unable to assess overall compatibility, including emotional aspects, thus hindering the establishment of long-term employment relationships and the streamlining of short-term recruitment processes.

[0353] 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.

[0354] In this invention, the server includes means for analyzing the skills, experience, and values ​​of job seekers using natural language processing; means for using sentiment analysis technology to analyze the emotional characteristics of job seekers; and means for matching the job requirements of employers with the analyzed information of job seekers in real time to perform optimal matching. This makes it possible to make a comprehensive suitability judgment that takes both skills and emotions into consideration, and promotes the efficient matching of the most suitable personnel.

[0355] "Job seeker's work history information" refers to records of the jobs and duties an individual has performed to date, and serves as basic data for evaluating their skill set and achievements.

[0356] "Natural language processing" is a general term for technologies that enable computers to understand and analyze human language and extract useful information.

[0357] "Emotional analysis technology" refers to technology that analyzes and identifies an individual's emotional state from text, voice, and facial expressions.

[0358] "Job requirements" are a compilation of information outlining the skills, experience, personality traits, and other requirements that a company seeks from its employees.

[0359] "Real-time matching" refers to the process of instantly comparing and evaluating information on job seekers and companies, and analyzing the degree of compatibility.

[0360] "Fit" is an indicator that shows the degree to which a job seeker's skills and emotional characteristics match the requirements and culture of a company.

[0361] "Communication support means" refers to methods that provide tools and protocols for efficiently sending and receiving information.

[0362] "Real-time analysis during interviews" refers to a technology that analyzes participants' emotions and reactions in real time during an interview and provides necessary information immediately.

[0363] This invention is a system that supports the optimal matching of job seekers and companies. The system mainly consists of terminals, servers, and users.

[0364] The terminal provides an interface for companies and job seekers to input data. Company users can enter recruitment information for required personnel into the terminal's form, while job seekers can upload career information such as resumes and work histories. This data is transmitted to the server via the SSL / TLS protocol.

[0365] The server is responsible for the core processing of this system. It uses a generative AI model and performs natural language processing to analyze the received job seeker's work history information. This analysis extracts the job seeker's skills, experience, and values ​​and converts them into structured data. Furthermore, the server employs sentiment analysis technology to analyze emotional characteristics from the job seeker's writing. This allows for the measurement of not only skills but also emotional compatibility.

[0366] After the analysis is complete, the server matches the data against the company's job requirements and compares and evaluates both sets of data in real time. The resulting candidate list is then prioritized based on factors such as emotional compatibility and skill match.

[0367] Each company representative, acting as a user, can view a list of candidates sent from the server via their terminal. This list includes skill and emotional compatibility scores for each candidate, allowing company representatives to select candidates and schedule interviews. The determined interview schedule is then notified to the job seeker via the server. During the interview, the server analyzes the emotions of the interviewees in real time and provides this information as feedback to the interviewer.

[0368] As a concrete example, consider a company looking for highly skilled customer support personnel. In this case, the server analyzes not only the job applicant's work experience but also their emotional characteristics (e.g., empathy, stress tolerance) and lists the applicants who best match the company's desired profile. This interaction allows the company to quickly and effectively find the right talent.

[0369] An example of a prompt for a generative AI model is: "Analyze the following work history data and extract the job seeker's skills and emotional characteristics."

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The terminal receives input data from both the company user and the job seeker. Company users enter job requirements, and job seeker users upload their resumes and work histories. The input data at this time consists of the company's job requirements and the job seeker's work history information. As output, the input data is securely transmitted to the server using the SSL / TLS protocol.

[0373] Step 2:

[0374] The server analyzes the job seeker's work history information that it receives. Using a generative AI model, it performs natural language processing to extract the job seeker's skills, experience, and values ​​from the input work history. The input here is the job seeker's work history information, and the output is structured data such as the job seeker's skill set obtained through analysis.

[0375] Step 3:

[0376] The server uses emotion analysis technology to evaluate the emotional characteristics of job applicants. It takes written information submitted by the applicant as input, analyzes their emotional state from that text, and quantifies characteristics such as empathy and stress tolerance. The output is data representing these emotional characteristics.

[0377] Step 4:

[0378] The server matches job requirements with analyzed information on job seekers in real time. It uses the job requirements provided by companies and analyzed data on job seekers as input, and calculates a confidence score based on a matching algorithm. The output is a list of job seekers with a high degree of matching.

[0379] Step 5:

[0380] The user, a company representative, reviews the candidate list sent from the server via their terminal. The input is a list of job seekers and their suitability ratings, and the company representative selects candidates to interview based on this. The output is a list of job seekers whose selection process is progressing.

[0381] Step 6:

[0382] The server collects and analyzes emotional data between the company and the job seeker using emotion analysis technology during the interview process. It uses audio and video data from the interview as input to accurately measure emotional states in real time. The output provides this emotional information as feedback to the interviewer, supporting them in adjusting questions and responses.

[0383] (Application Example 2)

[0384] 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."

[0385] In modern recruitment processes, emotional compatibility is just as important as a candidate's technical skills and experience. However, traditional systems struggle to effectively assess the emotional fit between candidates and companies, making it difficult to find the best talent. Similarly, electronic payment systems may fail to provide an appropriate interface that responds to user emotions, potentially compromising user satisfaction.

[0386] 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.

[0387] In this invention, the server includes means for receiving job seekers' work history information and analyzing their abilities, experience, and value using natural language processing technology; means for matching company job postings with the analyzed job seeker information in real time to achieve the best possible match; means for supporting communication between companies and job seekers to coordinate interview schedules and share opinions; and means for analyzing the emotions of decision-makers and dynamically adjusting the user interface based on the results. This enables technically and emotionally optimal matching for both job seekers and companies, and allows for flexible responses to user emotions in electronic payments.

[0388] "Work history information" refers to detailed data about a job seeker's past work experience, demonstrating their skills and abilities.

[0389] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0390] "Company job postings" refer to information about the personnel requirements and job descriptions that companies are looking for.

[0391] "Real-time matching" is a process that instantly compares received data and determines whether it matches.

[0392] "Communication for sharing and exchanging opinions" refers to a means of communication that allows for the two-way exchange of news and ideas.

[0393] "Emotional analysis" refers to the analytical process used to determine and evaluate an individual's emotional state.

[0394] A "user interface" is the screen configuration that allows the user and the system to interact with each other.

[0395] "Dynamic adjustment" means that settings and displays are changed as needed depending on the situation.

[0396] This invention is a system for achieving optimal matching between job seekers and companies, and is capable of comprehensively evaluating the emotional and technical characteristics of job seekers. The system mainly consists of three elements: a server, a terminal, and a user.

[0397] First, the terminal provides an interface for collecting input information from companies and job seekers. Companies enter job postings through the terminal, and job seekers upload their work history information. This information is then sent to the server.

[0398] Next, the server analyzes the received information. Here, a generative AI model is used, and natural language processing techniques are employed to extract the job seeker's abilities, experience, and value. Simultaneously, an emotion engine is used to evaluate the job seeker's emotional characteristics, and emotional compatibility is incorporated into the matching process.

[0399] Furthermore, in electronic payments, the server analyzes the user's emotions in real time. Based on the analysis results, the user interface design is dynamically adapted. This allows for the provision of an optimal interface tailored to the user's emotions. Specifically, if the user is feeling anxious, the screen's colors are changed to calmer tones to promote a sense of security.

[0400] In implementing this system, we will use emotion recognition APIs (e.g., Microsoft Azure Emotion API) and the React Native framework to enable the development of highly versatile applications.

[0401] For example, if a company is looking for someone with excellent communication skills, the system will analyze the applicant's past work experience and emotional characteristics to list the most suitable candidates. An example of a prompt to the generative AI model is, "Suggest the best UI theme and navigation message for when the user is feeling anxious."

[0402] In this way, a system is built in which servers, terminals, and users work together to achieve both technical and emotional matching.

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] The terminal receives job postings entered by companies and work history information uploaded by job seekers. The input information is collected via user forms and sent to the server. This is the process of delivering relevant information to the server through the act of data transmission.

[0406] Step 2:

[0407] The server analyzes the received information. First, it uses a generative AI model to extract the job seeker's skills, experience, and value from their work history information using natural language processing techniques. The input is work history information, and the output is the analyzed skill set. This analysis involves the process of textual analysis of the data.

[0408] Step 3:

[0409] The server then uses an emotion engine to evaluate the job seeker's emotional characteristics. Input is work history information, and voice and facial expression data may also be required. The output is an emotional characteristic score. This process involves data calculations called emotion analysis.

[0410] Step 4:

[0411] The server matches company job postings with analyzed job seeker data in real time, calculates technical and emotional fit scores, and lists the best candidates. The input is the analyzed data (output from the previous step) and the company job postings. The output is a list of job seekers with a high degree of matching. This operation involves information matching and fit calculation.

[0412] Step 5:

[0413] The device supports communication between companies and job seekers for scheduling interviews. Users propose interview dates, and both parties are notified. This is done through the sharing of the proposed date and time.

[0414] Step 6:

[0415] In the electronic payment process, the server analyzes the user's emotions in real time from their facial image and voice data, and dynamically adjusts the user interface displayed on the terminal based on the results. The input is real-time data including emotions, and the output is the modified interface state. This step involves emotion analysis and interface updating.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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".

[0432] This invention is a system that efficiently matches job seekers with job postings from companies using generation AI. To implement this system, the following configuration is adopted.

[0433] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0434] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. For example, keywords such as "Python programming experience" and "data analysis skills" are identified from the job seeker's resume.

[0435] The server then matches the analyzed job seeker data with the company's job postings. Based on the requirements entered by the company, such as "3+ years of data analysis experience" or "team leadership skills," the server selects candidates and evaluates their suitability. This process is performed in real time, and a list of suitable candidates is generated immediately.

[0436] Company representatives, as users, can view the candidate list through their terminals. If a suitable candidate is found, they can immediately request to schedule an interview. This request is transmitted to the job seeker via the server, and the job seeker can indicate a convenient date and time.

[0437] The server also provides a feedback function, allowing companies to input evaluations of job applicants after interviews. This feedback is shared with the job applicants, facilitating information exchange to help them move on to the next step.

[0438] As a concrete example, consider a case where a company is recruiting data scientists. The company enters job information from a terminal, and the server automatically lists job seekers with data science skills based on those requirements. This list is sent to the company's representative, and once suitable candidates are selected, interview dates are immediately scheduled. This entire process is efficiently realized through interaction between the server, terminal, and user.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The terminal provides a data entry interface for both companies and job seekers. Companies enter job requirements, and job seekers upload their resumes and work histories.

[0442] Step 2:

[0443] The server stores the data received from the terminals in a database. Here, company job postings and detailed work histories of job seekers are reliably recorded.

[0444] Step 3:

[0445] The server uses a generative AI model to analyze job seekers' work history data. This analysis utilizes natural language processing techniques to extract elements such as skills, experience, and values.

[0446] Step 4:

[0447] The server matches the analyzed job seeker data with the company's job postings and executes the matching process. It lists and prioritizes candidates who match the company's requirements in real time.

[0448] Step 5:

[0449] The server generates a list of candidates and sends it to the user, who is the company representative. The list includes information on each candidate's suitability and skills.

[0450] Step 6:

[0451] The user reviews the list of candidates sent via their device and schedules interviews with suitable candidates. Scheduling is done by entering preferred interview dates and times.

[0452] Step 7:

[0453] The server receives the interview scheduling request and notifies the job seeker. Once the job seeker selects a convenient date and time, that information is fed back to the company.

[0454] Step 8:

[0455] Users (companies) enter feedback from their terminals after interviews. This feedback is shared with job seekers via the server and used in further selection processes.

[0456] (Example 1)

[0457] 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."

[0458] The current job-seeking and company matching process often suffers from a mismatch between job seekers' skills and values ​​and companies' recruitment requirements, making efficient matching difficult. Furthermore, scheduling interviews and sharing feedback is time-consuming, leading to inefficient communication. As a result, companies struggle to find suitable talent, and job seekers have difficulty finding a company that fits their needs.

[0459] 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.

[0460] This invention includes a server that acquires job seekers' work history information and analyzes their abilities, experience, and value using natural language processing technology; a server that matches company job postings with the analyzed job seekers' information in real time to achieve the best possible match; and a server that supports communication between companies and job seekers to coordinate interview schedules and share evaluation opinions. This enables efficient and accurate matching between job seekers and companies, and allows for rapid scheduling of interviews and sharing of feedback.

[0461] "Work history information" refers to information that includes the work a job seeker has performed in the past, the content of that work, and the skills and experience gained through that work.

[0462] "Natural language processing technology" is a technology that uses computers to analyze and understand human language and extract its meaning.

[0463] "Job postings" refer to information that companies are recruiting for, including the types of jobs they are looking for, the skills and experience they require, and the working conditions.

[0464] "Analytical information" refers to evaluation results based on skills, experience, and values ​​extracted from the job seeker's work history information.

[0465] "Real-time matching" is a process that instantly compares job seekers' information with the requirements of companies and evaluates the degree of match.

[0466] "Adjusting the interview schedule" is the process of determining a mutually convenient date for both the company and the job seeker.

[0467] "Evaluation feedback" refers to the evaluation and feedback that a company provides to a job applicant after an interview.

[0468] "Supporting communication" means providing the necessary functions to facilitate smooth information exchange between companies and job seekers.

[0469] This invention is a system that efficiently matches job seekers with job postings from companies using a generative AI model. This system mainly consists of a server, terminals, and users (company representatives and job seekers).

[0470] The terminal provides an interface for receiving data input from both companies and job seekers. Company representatives use the terminal to input job information specifying the required duties and skills for job seekers. Job seekers also upload their work history information, including past work experience and acquired skills. This information is transmitted to the server via a secure protocol.

[0471] The server plays a primary role in processing the received data. First, it uses generative AI models and natural language processing techniques to analyze the job seeker's work history information. This analysis utilizes natural language processing libraries (e.g., spaCy and NLTK) to extract specific skills and experience from job seekers, thereby identifying actual job duties and possible roles. Based on these analysis results, the server matches the requirements sought by companies and uses advanced algorithms to select the most suitable candidates.

[0472] The company representative, as the user, is instantly shown a list of optimal candidates generated by the server on their device. Based on this list, the company representative can quickly make decisions and create interview offers for suitable candidates. Furthermore, interview schedules are coordinated with job seekers via the server, and a calendar API is used to harmonize the schedules of both parties.

[0473] For example, when a company is recruiting data scientists, the server analyzes the company's requirements, such as "data analysis" and "Python skills," and lists job seekers who possess those skills. This list is sent to the company representative in real time.

[0474] Example of a prompt:

[0475] "Please list suitable candidates for the data scientist position."

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The terminal accepts data input from both companies and job seekers. Company representatives use the terminal's input form to enter job information such as the job title, required skills, and years of experience. Job seekers upload their resumes and work histories through the terminal. This input data is standardized based on a sample format and sent to the server.

[0479] Step 2:

[0480] The server uses generative AI models and natural language processing techniques to analyze the received work history information. Specifically, it uses natural language processing libraries (e.g., spaCy and NLTK) to analyze text data and extract keywords related to important skills and experience. For example, it extracts skills such as "Python" and "data analysis" from resumes and saves them as analyzed data.

[0481] Step 3:

[0482] The server matches the analyzed job seeker data with the company's job postings. This process compares the requirements entered by the company (e.g., skills, years of experience) with the analyzed job seeker data, applying a matching algorithm to identify the most suitable candidates. As a result of the matching, a list of highly suitable candidates is generated, and evaluation scores are calculated.

[0483] Step 4:

[0484] The company representative, acting as the user, views a list of candidates provided by the server on their terminal. Based on this list, the company representative selects interview candidates and enters a request to schedule interviews. The interview request is immediately sent to the server, and the job seeker is notified.

[0485] Step 5:

[0486] When the server receives an interview request from a company representative, it notifies the job seeker and retrieves their response. At this point, the server uses a calendar API to automate the process of coordinating convenient interview dates and synchronizes the schedules of both parties.

[0487] Step 6:

[0488] The server receives post-interview feedback from companies and shares it with job seekers via the system. Company representatives input feedback via their terminals, and the server transmits this information to job seekers. This allows job seekers to learn about their interview evaluation 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] In the job search process, there is a need for a system that enables efficient and appropriate matching between job seekers and companies, and facilitates smooth progress through the initial hiring procedures. However, current systems often struggle to accurately match job seekers' skills with company requirements, and post-hiring procedures are frequently cumbersome. Therefore, a method is needed to quickly select the most suitable candidates and streamline the entire recruitment process.

[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 job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology; means for comparing company job data with the analyzed job seeker data in real time to perform optimal matching; means for supporting information exchange between companies and job seekers to coordinate interview schedules and share evaluation results; and means for supporting job seekers with the initial procedures required after being hired using e-commerce technology. This improves the efficiency of matching job seekers and companies and streamlines the entire recruitment process.

[0494] "Job seeker's work history data" refers to information that shows what kind of work a job seeker has done in the past and what skills and knowledge they possess.

[0495] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for document analysis and the extraction of specific information.

[0496] "Company recruitment data" refers to information about job titles, required skills, working conditions, and other requirements that companies present when recruiting new employees.

[0497] "Real-time matching" refers to a process that processes data immediately upon receipt and performs matching based on current conditions.

[0498] "Optimal matching" means evaluating how well a job seeker's skills and experience align with a company's requirements and selecting the most suitable candidate.

[0499] "Scheduling an interview" refers to the process where the company and the job seeker confirm each other's availability and set an interview date and time that is appropriate.

[0500] "Evaluation results" refer to the company's assessment and opinions of job applicants obtained through interviews and document screening.

[0501] "Supporting information exchange" means enabling both parties to exchange necessary information quickly and accurately.

[0502] "Initial procedures" refer to the necessary procedures related to contracts and joining the company when a job seeker is hired.

[0503] "Electronic commerce technology" refers to technologies that enable various commercial transactions online and are used for payment and contract procedures.

[0504] The server receives work history data from job seekers and analyzes it using natural language processing technology with a generative AI model. From the data obtained through the analysis, information such as the job seeker's skills, experience, and values ​​is extracted and compared in real time with the company's job postings. Based on this, the company can obtain the most suitable candidates.

[0505] The server also includes a function to assist in scheduling interviews between the company and job seekers, providing an interface to streamline communication and ensure smooth exchange of necessary information. This allows both parties to easily determine interview dates and times.

[0506] Furthermore, if a candidate is selected, the server uses e-commerce technology to assist with the initial hiring procedures for the job seeker. This allows the job seeker to expedite the hiring process.

[0507] As a concrete example, an AI model generated on a server extracts keywords such as data analysis skills and leadership experience from job seekers' resume data, calculates the degree of matching with the company's job requirements, and lists highly matching candidates. This entire process allows companies to quickly find the most suitable talent.

[0508] An example of a prompt message would be: "Consider the applicant's past experience and skill set, evaluate whether they are the best fit for the company's job posting, and show how training costs will be paid if hired."

[0509] This system utilizes Python libraries and APIs on cloud services to enable real-time data processing.

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The terminal receives work history data (resumes and work history documents) from job seekers. This data includes basic information, experience, and skill sets entered by the job seekers. The terminal sends this data to the server. It receives work history data as input and generates data in a format that is sent to the server as output.

[0513] Step 2:

[0514] The server inputs the received work history data into a generating AI model, which then analyzes it using natural language processing technology. This process extracts information such as the job seeker's skills, experience, and values. The input is the received work history data, which is then analyzed by the generating AI model and output as structured data. In this extraction process, the focus is on specific skills, such as "experience programming in Python."

[0515] Step 3:

[0516] The server matches structured analytical data with company job posting data to achieve the best possible match. Input requires analyzed job seeker data and company request data. In this step, the server compares the received analytical data with the job posting data in real time, calculates a matching score based on the items with the highest degree of match, and outputs it. Specifically, filtering is performed using database queries.

[0517] Step 4:

[0518] The user (company representative) uses a terminal to view a list of matching candidates sent from the server. The list of matching candidates is prioritized based on scores. The input is a list of candidates sent from the server, and the output is the selection of interviewees based on this list. Specific actions include using a GUI to view information about the candidates on the list.

[0519] Step 5:

[0520] The server assists in scheduling interviews between companies and job seekers, facilitating smooth information exchange by prompting users as needed. It takes the schedule information of both companies and job seekers as input and generates a pre-arranged interview schedule as output. This operation uses prompts such as "Considering the job seeker's past experience and skill set..." to suggest a date and time that works for both parties.

[0521] Step 6:

[0522] If a candidate is selected, the server uses e-commerce technology to provide the job seeker with the necessary initial procedural information. Inputs include the selected candidate information and a list of required procedures, while outputs include payment options and procedural steps presented to the candidate. Specific actions include online payment procedures for accepting the job offer and subsequent training costs.

[0523] 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.

[0524] This invention incorporates an emotion engine that recognizes user emotions into a system that efficiently matches job seekers with company job postings using generative AI. The system has the following configuration.

[0525] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0526] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. Simultaneously, the server uses an emotion engine to analyze the job seeker's emotional characteristics from the data and incorporates this into the matching evaluation.

[0527] The server then compares the analyzed job seeker data with the company's job postings and executes the matching process. Here, it lists candidates who match the company's requirements in real time and adjusts the fit based on the sentiment analysis results, so that not only documented skills but also emotional fit is included in the evaluation.

[0528] The company representative, acting as the user, can review the candidate list via their terminal and select candidates, including evaluating emotional compatibility. Once a suitable candidate is found, they can request to schedule an interview. This request is transmitted to the job seeker via the server, who can then indicate a convenient date and time.

[0529] During the interview process, the server uses an emotion engine to analyze the emotions of both the company and the job seeker in real time. This information is fed back to the interviewer to help them appropriately adjust their responses and questions during the interview.

[0530] As a concrete example, consider a case where a company is recruiting sales staff with strong customer service skills. In this scenario, the server analyzes not only the job applicant's work experience but also their emotional characteristics related to customer service (e.g., empathy, stress tolerance), and lists candidates who match the company's desired profile. Through this series of interactions, the company can effectively find candidates who are emotionally and skillfully suitable.

[0531] The following describes the processing flow.

[0532] Step 1:

[0533] The terminal provides an interface for easy input from both companies and job seekers. Companies enter job requirements and desired conditions, while job seekers upload their resumes and work histories. This data is then transferred to the server.

[0534] Step 2:

[0535] The server stores the received data in a database. This ensures that company job postings and job seeker work history data are accurately recorded and available for subsequent processing.

[0536] Step 3:

[0537] The server uses a generative AI model to analyze job seekers' work history data. This analysis uses natural language processing techniques to extract the job seeker's skills, experience, values, and emotional characteristics. For example, attributes such as "leadership," "stress tolerance," and "cooperativeness" are identified.

[0538] Step 4:

[0539] The server integrates company job posting data and job seeker analysis data to perform real-time matching. Here, user emotional characteristics are also taken into consideration, and the degree of suitability is adjusted by an emotion engine.

[0540] Step 5:

[0541] The server generates a list of matching candidates, which is then provided to the user, who is the company representative. This is a detailed list that includes not only the candidate's skill set but also an assessment of emotional compatibility.

[0542] Step 6:

[0543] The user reviews the candidate list provided through their device, selects the candidate they deem most suitable, and schedules an interview. The user confirms the candidate's emotional characteristics on their device while finalizing the interview schedule.

[0544] Step 7:

[0545] The server uses an emotion engine to perform emotional analysis during interviews, evaluating the real-time emotional state of both the company and the job seeker. This evaluation is fed back to the interviewer, who can use it to adjust the questions and their demeanor during the interview.

[0546] Step 8:

[0547] After an interview, the user (company) enters feedback, registering their evaluation and emotional observations about the job seeker on the server. The server then uses this feedback for further analysis and prepares to proceed to the next selection step.

[0548] (Example 2)

[0549] 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."

[0550] In the labor market, a challenge lies in the difficulty of quickly and optimally matching job seekers with companies, taking into account skills, values, and emotional compatibility. Traditional systems are limited to matching skills and experience, and are unable to assess overall compatibility, including emotional aspects, thus hindering the establishment of long-term employment relationships and the streamlining of short-term recruitment processes.

[0551] 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.

[0552] In this invention, the server includes means for analyzing the skills, experience, and values ​​of job seekers using natural language processing; means for using sentiment analysis technology to analyze the emotional characteristics of job seekers; and means for matching the job requirements of employers with the analyzed information of job seekers in real time to perform optimal matching. This makes it possible to make a comprehensive suitability judgment that takes both skills and emotions into consideration, and promotes the efficient matching of the most suitable personnel.

[0553] "Job seeker's work history information" refers to records of the jobs and duties an individual has performed to date, and serves as basic data for evaluating their skill set and achievements.

[0554] "Natural language processing" is a general term for technologies that enable computers to understand and analyze human language and extract useful information.

[0555] "Emotional analysis technology" refers to technology that analyzes and identifies an individual's emotional state from text, voice, and facial expressions.

[0556] "Job requirements" are a compilation of information outlining the skills, experience, personality traits, and other requirements that a company seeks from its employees.

[0557] "Real-time matching" refers to the process of instantly comparing and evaluating information on job seekers and companies, and analyzing the degree of compatibility.

[0558] "Fit" is an indicator that shows the degree to which a job seeker's skills and emotional characteristics match the requirements and culture of a company.

[0559] "Communication support means" refers to methods that provide tools and protocols for efficiently sending and receiving information.

[0560] "Real-time analysis during interviews" refers to a technology that analyzes participants' emotions and reactions in real time during an interview and provides necessary information immediately.

[0561] This invention is a system that supports the optimal matching of job seekers and companies. The system mainly consists of terminals, servers, and users.

[0562] The terminal provides an interface for companies and job seekers to input data. Company users can enter recruitment information for required personnel into the terminal's form, while job seekers can upload career information such as resumes and work histories. This data is transmitted to the server via the SSL / TLS protocol.

[0563] The server is responsible for the core processing of this system. It uses a generative AI model and performs natural language processing to analyze the received job seeker's work history information. This analysis extracts the job seeker's skills, experience, and values ​​and converts them into structured data. Furthermore, the server employs sentiment analysis technology to analyze emotional characteristics from the job seeker's writing. This allows for the measurement of not only skills but also emotional compatibility.

[0564] After the analysis is complete, the server matches the data against the company's job requirements and compares and evaluates both sets of data in real time. The resulting candidate list is then prioritized based on factors such as emotional compatibility and skill match.

[0565] Each company representative, acting as a user, can view a list of candidates sent from the server via their terminal. This list includes skill and emotional compatibility scores for each candidate, allowing company representatives to select candidates and schedule interviews. The determined interview schedule is then notified to the job seeker via the server. During the interview, the server analyzes the emotions of the interviewees in real time and provides this information as feedback to the interviewer.

[0566] As a concrete example, consider a company looking for highly skilled customer support personnel. In this case, the server analyzes not only the job applicant's work experience but also their emotional characteristics (e.g., empathy, stress tolerance) and lists the applicants who best match the company's desired profile. This interaction allows the company to quickly and effectively find the right talent.

[0567] An example of a prompt for a generative AI model is: "Analyze the following work history data and extract the job seeker's skills and emotional characteristics."

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

[0569] Step 1:

[0570] The terminal receives input data from both the company user and the job seeker. Company users enter job requirements, and job seeker users upload their resumes and work histories. The input data at this time consists of the company's job requirements and the job seeker's work history information. As output, the input data is securely transmitted to the server using the SSL / TLS protocol.

[0571] Step 2:

[0572] The server analyzes the job seeker's work history information that it receives. Using a generative AI model, it performs natural language processing to extract the job seeker's skills, experience, and values ​​from the input work history. The input here is the job seeker's work history information, and the output is structured data such as the job seeker's skill set obtained through analysis.

[0573] Step 3:

[0574] The server uses emotion analysis technology to evaluate the emotional characteristics of job applicants. It takes written information submitted by the applicant as input, analyzes their emotional state from that text, and quantifies characteristics such as empathy and stress tolerance. The output is data representing these emotional characteristics.

[0575] Step 4:

[0576] The server matches job requirements with analyzed information on job seekers in real time. It uses the job requirements provided by companies and analyzed data on job seekers as input, and calculates a confidence score based on a matching algorithm. The output is a list of job seekers with a high degree of matching.

[0577] Step 5:

[0578] The user, a company representative, reviews the candidate list sent from the server via their terminal. The input is a list of job seekers and their suitability ratings, and the company representative selects candidates to interview based on this. The output is a list of job seekers whose selection process is progressing.

[0579] Step 6:

[0580] The server collects and analyzes emotional data between the company and the job seeker using emotion analysis technology during the interview process. It uses audio and video data from the interview as input to accurately measure emotional states in real time. The output provides this emotional information as feedback to the interviewer, supporting them in adjusting questions and responses.

[0581] (Application Example 2)

[0582] 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."

[0583] In modern recruitment processes, emotional compatibility is just as important as a candidate's technical skills and experience. However, traditional systems struggle to effectively assess the emotional fit between candidates and companies, making it difficult to find the best talent. Similarly, electronic payment systems may fail to provide an appropriate interface that responds to user emotions, potentially compromising user satisfaction.

[0584] 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.

[0585] In this invention, the server includes means for receiving job seekers' work history information and analyzing their abilities, experience, and value using natural language processing technology; means for matching company job postings with the analyzed job seeker information in real time to achieve the best possible match; means for supporting communication between companies and job seekers to coordinate interview schedules and share opinions; and means for analyzing the emotions of decision-makers and dynamically adjusting the user interface based on the results. This enables technically and emotionally optimal matching for both job seekers and companies, and allows for flexible responses to user emotions in electronic payments.

[0586] "Work history information" refers to detailed data about a job seeker's past work experience, demonstrating their skills and abilities.

[0587] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0588] "Company job postings" refer to information about the personnel requirements and job descriptions that companies are looking for.

[0589] "Real-time matching" is a process that instantly compares received data and determines whether it matches.

[0590] "Communication for sharing and exchanging opinions" refers to a means of communication that allows for the two-way exchange of news and ideas.

[0591] "Emotional analysis" refers to the analytical process used to determine and evaluate an individual's emotional state.

[0592] A "user interface" is the screen configuration that allows the user and the system to interact with each other.

[0593] "Dynamic adjustment" means that settings and displays are changed as needed depending on the situation.

[0594] This invention is a system for achieving optimal matching between job seekers and companies, and is capable of comprehensively evaluating the emotional and technical characteristics of job seekers. The system mainly consists of three elements: a server, a terminal, and a user.

[0595] First, the terminal provides an interface for collecting input information from companies and job seekers. Companies enter job postings through the terminal, and job seekers upload their work history information. This information is then sent to the server.

[0596] Next, the server analyzes the received information. Here, a generative AI model is used, and natural language processing techniques are employed to extract the job seeker's abilities, experience, and value. Simultaneously, an emotion engine is used to evaluate the job seeker's emotional characteristics, and emotional compatibility is incorporated into the matching process.

[0597] Furthermore, in electronic payments, the server analyzes the user's emotions in real time. Based on the analysis results, the user interface design is dynamically adapted. This allows for the provision of an optimal interface tailored to the user's emotions. Specifically, if the user is feeling anxious, the screen's colors are changed to calmer tones to promote a sense of security.

[0598] In implementing this system, we will use emotion recognition APIs (e.g., Microsoft Azure Emotion API) and the React Native framework to enable the development of highly versatile applications.

[0599] For example, if a company is looking for someone with excellent communication skills, the system will analyze the applicant's past work experience and emotional characteristics to list the most suitable candidates. An example of a prompt to the generative AI model is, "Suggest the best UI theme and navigation message for when the user is feeling anxious."

[0600] In this way, a system is built in which servers, terminals, and users work together to achieve both technical and emotional matching.

[0601] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0602] Step 1:

[0603] The terminal receives job postings entered by companies and work history information uploaded by job seekers. The input information is collected via user forms and sent to the server. This is the process of delivering relevant information to the server through the act of data transmission.

[0604] Step 2:

[0605] The server analyzes the received information. First, it uses a generative AI model to extract the job seeker's skills, experience, and value from their work history information using natural language processing techniques. The input is work history information, and the output is the analyzed skill set. This analysis involves the process of textual analysis of the data.

[0606] Step 3:

[0607] The server then uses an emotion engine to evaluate the job seeker's emotional characteristics. Input is work history information, and voice and facial expression data may also be required. The output is an emotional characteristic score. This process involves data calculations called emotion analysis.

[0608] Step 4:

[0609] The server matches company job postings with analyzed job seeker data in real time, calculates technical and emotional fit scores, and lists the best candidates. The input is the analyzed data (output from the previous step) and the company job postings. The output is a list of job seekers with a high degree of matching. This operation involves information matching and fit calculation.

[0610] Step 5:

[0611] The device supports communication between companies and job seekers for scheduling interviews. Users propose interview dates, and both parties are notified. This is done through the sharing of the proposed date and time.

[0612] Step 6:

[0613] In the electronic payment process, the server analyzes the user's emotions in real time from their facial image and voice data, and dynamically adjusts the user interface displayed on the terminal based on the results. The input is real-time data including emotions, and the output is the modified interface state. This step involves emotion analysis and interface updating.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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".

[0631] This invention is a system that efficiently matches job seekers with job postings from companies using generation AI. To implement this system, the following configuration is adopted.

[0632] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0633] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. For example, keywords such as "Python programming experience" and "data analysis skills" are identified from the job seeker's resume.

[0634] The server then matches the analyzed job seeker data with the company's job postings. Based on the requirements entered by the company, such as "3+ years of data analysis experience" or "team leadership skills," the server selects candidates and evaluates their suitability. This process is performed in real time, and a list of suitable candidates is generated immediately.

[0635] Company representatives, as users, can view the candidate list through their terminals. If a suitable candidate is found, they can immediately request to schedule an interview. This request is transmitted to the job seeker via the server, and the job seeker can indicate a convenient date and time.

[0636] The server also provides a feedback function, allowing companies to input evaluations of job applicants after interviews. This feedback is shared with the job applicants, facilitating information exchange to help them move on to the next step.

[0637] As a concrete example, consider a case where a company is recruiting data scientists. The company enters job information from a terminal, and the server automatically lists job seekers with data science skills based on those requirements. This list is sent to the company's representative, and once suitable candidates are selected, interview dates are immediately scheduled. This entire process is efficiently realized through interaction between the server, terminal, and user.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] The terminal provides a data entry interface for both companies and job seekers. Companies enter job requirements, and job seekers upload their resumes and work histories.

[0641] Step 2:

[0642] The server stores the data received from the terminals in a database. Here, company job postings and detailed work histories of job seekers are reliably recorded.

[0643] Step 3:

[0644] The server uses a generative AI model to analyze job seekers' work history data. This analysis utilizes natural language processing techniques to extract elements such as skills, experience, and values.

[0645] Step 4:

[0646] The server matches the analyzed job seeker data with the company's job postings and executes the matching process. It lists and prioritizes candidates who match the company's requirements in real time.

[0647] Step 5:

[0648] The server generates a list of candidates and sends it to the user, who is the company representative. The list includes information on each candidate's suitability and skills.

[0649] Step 6:

[0650] The user reviews the list of candidates sent via their device and schedules interviews with suitable candidates. Scheduling is done by entering preferred interview dates and times.

[0651] Step 7:

[0652] The server receives the interview scheduling request and notifies the job seeker. Once the job seeker selects a convenient date and time, that information is fed back to the company.

[0653] Step 8:

[0654] Users (companies) enter feedback from their terminals after interviews. This feedback is shared with job seekers via the server and used in further selection processes.

[0655] (Example 1)

[0656] 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".

[0657] The current job-seeking and company matching process often suffers from a mismatch between job seekers' skills and values ​​and companies' recruitment requirements, making efficient matching difficult. Furthermore, scheduling interviews and sharing feedback is time-consuming, leading to inefficient communication. As a result, companies struggle to find suitable talent, and job seekers have difficulty finding a company that fits their needs.

[0658] 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.

[0659] This invention includes a server that acquires job seekers' work history information and analyzes their abilities, experience, and value using natural language processing technology; a server that matches company job postings with the analyzed job seekers' information in real time to achieve the best possible match; and a server that supports communication between companies and job seekers to coordinate interview schedules and share evaluation opinions. This enables efficient and accurate matching between job seekers and companies, and allows for rapid scheduling of interviews and sharing of feedback.

[0660] "Work history information" refers to information that includes the work a job seeker has performed in the past, the content of that work, and the skills and experience gained through that work.

[0661] "Natural language processing technology" is a technology that uses computers to analyze and understand human language and extract its meaning.

[0662] "Job postings" refer to information that companies are recruiting for, including the types of jobs they are looking for, the skills and experience they require, and the working conditions.

[0663] "Analytical information" refers to evaluation results based on skills, experience, and values ​​extracted from the job seeker's work history information.

[0664] "Real-time matching" is a process that instantly compares job seekers' information with the requirements of companies and evaluates the degree of match.

[0665] "Adjusting the interview schedule" is the process of determining a mutually convenient date for both the company and the job seeker.

[0666] "Evaluation feedback" refers to the evaluation and feedback that a company provides to a job applicant after an interview.

[0667] "Supporting communication" means providing the necessary functions to facilitate smooth information exchange between companies and job seekers.

[0668] This invention is a system that efficiently matches job seekers with job postings from companies using a generative AI model. This system mainly consists of a server, terminals, and users (company representatives and job seekers).

[0669] The terminal provides an interface for receiving data input from both companies and job seekers. Company representatives use the terminal to input job information specifying the required duties and skills for job seekers. Job seekers also upload their work history information, including past work experience and acquired skills. This information is transmitted to the server via a secure protocol.

[0670] The server plays a primary role in processing the received data. First, it uses generative AI models and natural language processing techniques to analyze the job seeker's work history information. This analysis utilizes natural language processing libraries (e.g., spaCy and NLTK) to extract specific skills and experience from job seekers, thereby identifying actual job duties and possible roles. Based on these analysis results, the server matches the requirements sought by companies and uses advanced algorithms to select the most suitable candidates.

[0671] The company representative, as the user, is instantly shown a list of optimal candidates generated by the server on their device. Based on this list, the company representative can quickly make decisions and create interview offers for suitable candidates. Furthermore, interview schedules are coordinated with job seekers via the server, and a calendar API is used to harmonize the schedules of both parties.

[0672] For example, when a company is recruiting data scientists, the server analyzes the company's requirements, such as "data analysis" and "Python skills," and lists job seekers who possess those skills. This list is sent to the company representative in real time.

[0673] Example of a prompt:

[0674] "Please list suitable candidates for the data scientist position."

[0675] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0676] Step 1:

[0677] The terminal accepts data input from both companies and job seekers. Company representatives use the terminal's input form to enter job information such as the job title, required skills, and years of experience. Job seekers upload their resumes and work histories through the terminal. This input data is standardized based on a sample format and sent to the server.

[0678] Step 2:

[0679] The server uses generative AI models and natural language processing techniques to analyze the received work history information. Specifically, it uses natural language processing libraries (e.g., spaCy and NLTK) to analyze text data and extract keywords related to important skills and experience. For example, it extracts skills such as "Python" and "data analysis" from resumes and saves them as analyzed data.

[0680] Step 3:

[0681] The server matches the analyzed job seeker data with the company's job postings. This process compares the requirements entered by the company (e.g., skills, years of experience) with the analyzed job seeker data, applying a matching algorithm to identify the most suitable candidates. As a result of the matching, a list of highly suitable candidates is generated, and evaluation scores are calculated.

[0682] Step 4:

[0683] The company representative, acting as the user, views a list of candidates provided by the server on their terminal. Based on this list, the company representative selects interview candidates and enters a request to schedule interviews. The interview request is immediately sent to the server, and the job seeker is notified.

[0684] Step 5:

[0685] When the server receives an interview request from a company representative, it notifies the job seeker and retrieves their response. At this point, the server uses a calendar API to automate the process of coordinating convenient interview dates and synchronizes the schedules of both parties.

[0686] Step 6:

[0687] The server receives post-interview feedback from companies and shares it with job seekers via the system. Company representatives input feedback via their terminals, and the server transmits this information to job seekers. This allows job seekers to learn about their interview evaluation and areas for improvement.

[0688] (Application Example 1)

[0689] 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".

[0690] In the job search process, there is a need for a system that enables efficient and appropriate matching between job seekers and companies, and facilitates smooth progress through the initial hiring procedures. However, current systems often struggle to accurately match job seekers' skills with company requirements, and post-hiring procedures are frequently cumbersome. Therefore, a method is needed to quickly select the most suitable candidates and streamline the entire recruitment process.

[0691] 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.

[0692] In this invention, the server includes means for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology; means for comparing company job data with the analyzed job seeker data in real time to perform optimal matching; means for supporting information exchange between companies and job seekers to coordinate interview schedules and share evaluation results; and means for supporting job seekers with the initial procedures required after being hired using e-commerce technology. This improves the efficiency of matching job seekers and companies and streamlines the entire recruitment process.

[0693] "Job seeker's work history data" refers to information that shows what kind of work a job seeker has done in the past and what skills and knowledge they possess.

[0694] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used for document analysis and the extraction of specific information.

[0695] "Company recruitment data" refers to information about job titles, required skills, working conditions, and other requirements that companies present when recruiting new employees.

[0696] "Real-time matching" refers to a process that processes data immediately upon receipt and performs matching based on current conditions.

[0697] "Optimal matching" means evaluating how well a job seeker's skills and experience align with a company's requirements and selecting the most suitable candidate.

[0698] "Scheduling an interview" refers to the process where the company and the job seeker confirm each other's availability and set an interview date and time that is appropriate.

[0699] "Evaluation results" refer to the company's assessment and opinions of job applicants obtained through interviews and document screening.

[0700] "Supporting information exchange" means enabling both parties to exchange necessary information quickly and accurately.

[0701] "Initial procedures" refer to the necessary procedures related to contracts and joining the company when a job seeker is hired.

[0702] "Electronic commerce technology" refers to technologies that enable various commercial transactions online and are used for payment and contract procedures.

[0703] The server receives work history data from job seekers and analyzes it using natural language processing technology with a generative AI model. From the data obtained through the analysis, information such as the job seeker's skills, experience, and values ​​is extracted and compared in real time with the company's job postings. Based on this, the company can obtain the most suitable candidates.

[0704] The server also includes a function to assist in scheduling interviews between the company and job seekers, providing an interface to streamline communication and ensure smooth exchange of necessary information. This allows both parties to easily determine interview dates and times.

[0705] Furthermore, if a candidate is selected, the server uses e-commerce technology to assist with the initial hiring procedures for the job seeker. This allows the job seeker to expedite the hiring process.

[0706] As a concrete example, an AI model generated on a server extracts keywords such as data analysis skills and leadership experience from job seekers' resume data, calculates the degree of matching with the company's job requirements, and lists highly matching candidates. This entire process allows companies to quickly find the most suitable talent.

[0707] An example of a prompt message would be: "Consider the applicant's past experience and skill set, evaluate whether they are the best fit for the company's job posting, and show how training costs will be paid if hired."

[0708] This system utilizes Python libraries and APIs on cloud services to enable real-time data processing.

[0709] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0710] Step 1:

[0711] The terminal receives work history data (resumes and work history documents) from job seekers. This data includes basic information, experience, and skill sets entered by the job seekers. The terminal sends this data to the server. It receives work history data as input and generates data in a format that is sent to the server as output.

[0712] Step 2:

[0713] The server inputs the received work history data into a generating AI model, which then analyzes it using natural language processing technology. This process extracts information such as the job seeker's skills, experience, and values. The input is the received work history data, which is then analyzed by the generating AI model and output as structured data. In this extraction process, the focus is on specific skills, such as "experience programming in Python."

[0714] Step 3:

[0715] The server matches structured analytical data with company job posting data to achieve the best possible match. Input requires analyzed job seeker data and company request data. In this step, the server compares the received analytical data with the job posting data in real time, calculates a matching score based on the items with the highest degree of match, and outputs it. Specifically, filtering is performed using database queries.

[0716] Step 4:

[0717] The user (company representative) uses a terminal to view a list of matching candidates sent from the server. The list of matching candidates is prioritized based on scores. The input is a list of candidates sent from the server, and the output is the selection of interviewees based on this list. Specific actions include using a GUI to view information about the candidates on the list.

[0718] Step 5:

[0719] The server assists in scheduling interviews between companies and job seekers, facilitating smooth information exchange by prompting users as needed. It takes the schedule information of both companies and job seekers as input and generates a pre-arranged interview schedule as output. This operation uses prompts such as "Considering the job seeker's past experience and skill set..." to suggest a date and time that works for both parties.

[0720] Step 6:

[0721] If a candidate is selected, the server uses e-commerce technology to provide the job seeker with the necessary initial procedural information. Inputs include the selected candidate information and a list of required procedures, while outputs include payment options and procedural steps presented to the candidate. Specific actions include online payment procedures for accepting the job offer and subsequent training costs.

[0722] 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.

[0723] This invention incorporates an emotion engine that recognizes user emotions into a system that efficiently matches job seekers with company job postings using generative AI. The system has the following configuration.

[0724] First, the terminal provides an interface for receiving input data from companies and job seekers. Companies can enter job requirements on the terminal, and job seekers can upload their resumes and work histories. This information is then sent to the server.

[0725] Next, the server analyzes the job seeker's work history data. A generative AI model is used, employing natural language processing techniques to extract the job seeker's skills, experience, and values. Simultaneously, the server uses an emotion engine to analyze the job seeker's emotional characteristics from the data and incorporates this into the matching evaluation.

[0726] The server then compares the analyzed job seeker data with the company's job postings and executes the matching process. Here, it lists candidates who match the company's requirements in real time and adjusts the fit based on the sentiment analysis results, so that not only documented skills but also emotional fit is included in the evaluation.

[0727] The company representative, acting as the user, can review the candidate list via their terminal and select candidates, including evaluating emotional compatibility. Once a suitable candidate is found, they can request to schedule an interview. This request is transmitted to the job seeker via the server, who can then indicate a convenient date and time.

[0728] During the interview process, the server uses an emotion engine to analyze the emotions of both the company and the job seeker in real time. This information is fed back to the interviewer to help them appropriately adjust their responses and questions during the interview.

[0729] As a concrete example, consider a case where a company is recruiting sales staff with strong customer service skills. In this scenario, the server analyzes not only the job applicant's work experience but also their emotional characteristics related to customer service (e.g., empathy, stress tolerance), and lists candidates who match the company's desired profile. Through this series of interactions, the company can effectively find candidates who are emotionally and skillfully suitable.

[0730] The following describes the processing flow.

[0731] Step 1:

[0732] The terminal provides an interface for easy input from both companies and job seekers. Companies enter job requirements and desired conditions, while job seekers upload their resumes and work histories. This data is then transferred to the server.

[0733] Step 2:

[0734] The server stores the received data in a database. This ensures that company job postings and job seeker work history data are accurately recorded and available for subsequent processing.

[0735] Step 3:

[0736] The server uses a generative AI model to analyze job seekers' work history data. This analysis uses natural language processing techniques to extract the job seeker's skills, experience, values, and emotional characteristics. For example, attributes such as "leadership," "stress tolerance," and "cooperativeness" are identified.

[0737] Step 4:

[0738] The server integrates company job posting data and job seeker analysis data to perform real-time matching. Here, user emotional characteristics are also taken into consideration, and the degree of suitability is adjusted by an emotion engine.

[0739] Step 5:

[0740] The server generates a list of matching candidates, which is then provided to the user, who is the company representative. This is a detailed list that includes not only the candidate's skill set but also an assessment of emotional compatibility.

[0741] Step 6:

[0742] The user reviews the candidate list provided through their device, selects the candidate they deem most suitable, and schedules an interview. The user confirms the candidate's emotional characteristics on their device while finalizing the interview schedule.

[0743] Step 7:

[0744] The server uses an emotion engine to perform emotional analysis during interviews, evaluating the real-time emotional state of both the company and the job seeker. This evaluation is fed back to the interviewer, who can use it to adjust the questions and their demeanor during the interview.

[0745] Step 8:

[0746] After an interview, the user (company) enters feedback, registering their evaluation and emotional observations about the job seeker on the server. The server then uses this feedback for further analysis and prepares to proceed to the next selection step.

[0747] (Example 2)

[0748] 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".

[0749] In the labor market, a challenge lies in the difficulty of quickly and optimally matching job seekers with companies, taking into account skills, values, and emotional compatibility. Traditional systems are limited to matching skills and experience, and are unable to assess overall compatibility, including emotional aspects, thus hindering the establishment of long-term employment relationships and the streamlining of short-term recruitment processes.

[0750] 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.

[0751] In this invention, the server includes means for analyzing the skills, experience, and values ​​of job seekers using natural language processing; means for using sentiment analysis technology to analyze the emotional characteristics of job seekers; and means for matching the job requirements of employers with the analyzed information of job seekers in real time to perform optimal matching. This makes it possible to make a comprehensive suitability judgment that takes both skills and emotions into consideration, and promotes the efficient matching of the most suitable personnel.

[0752] "Job seeker's work history information" refers to records of the jobs and duties an individual has performed to date, and serves as basic data for evaluating their skill set and achievements.

[0753] "Natural language processing" is a general term for technologies that enable computers to understand and analyze human language and extract useful information.

[0754] "Emotional analysis technology" refers to technology that analyzes and identifies an individual's emotional state from text, voice, and facial expressions.

[0755] "Job requirements" are a compilation of information outlining the skills, experience, personality traits, and other requirements that a company seeks from its employees.

[0756] "Real-time matching" refers to the process of instantly comparing and evaluating information on job seekers and companies, and analyzing the degree of compatibility.

[0757] "Fit" is an indicator that shows the degree to which a job seeker's skills and emotional characteristics match the requirements and culture of a company.

[0758] "Communication support means" refers to methods that provide tools and protocols for efficiently sending and receiving information.

[0759] "Real-time analysis during interviews" refers to a technology that analyzes participants' emotions and reactions in real time during an interview and provides necessary information immediately.

[0760] This invention is a system that supports the optimal matching of job seekers and companies. The system mainly consists of terminals, servers, and users.

[0761] The terminal provides an interface for companies and job seekers to input data. Company users can enter recruitment information for required personnel into the terminal's form, while job seekers can upload career information such as resumes and work histories. This data is transmitted to the server via the SSL / TLS protocol.

[0762] The server is responsible for the core processing of this system. It uses a generative AI model and performs natural language processing to analyze the received job seeker's work history information. This analysis extracts the job seeker's skills, experience, and values ​​and converts them into structured data. Furthermore, the server employs sentiment analysis technology to analyze emotional characteristics from the job seeker's writing. This allows for the measurement of not only skills but also emotional compatibility.

[0763] After the analysis is complete, the server matches the data against the company's job requirements and compares and evaluates both sets of data in real time. The resulting candidate list is then prioritized based on factors such as emotional compatibility and skill match.

[0764] Each company representative, acting as a user, can view a list of candidates sent from the server via their terminal. This list includes skill and emotional compatibility scores for each candidate, allowing company representatives to select candidates and schedule interviews. The determined interview schedule is then notified to the job seeker via the server. During the interview, the server analyzes the emotions of the interviewees in real time and provides this information as feedback to the interviewer.

[0765] As a concrete example, consider a company looking for highly skilled customer support personnel. In this case, the server analyzes not only the job applicant's work experience but also their emotional characteristics (e.g., empathy, stress tolerance) and lists the applicants who best match the company's desired profile. This interaction allows the company to quickly and effectively find the right talent.

[0766] An example of a prompt for a generative AI model is: "Analyze the following work history data and extract the job seeker's skills and emotional characteristics."

[0767] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0768] Step 1:

[0769] The terminal receives input data from both the company user and the job seeker. Company users enter job requirements, and job seeker users upload their resumes and work histories. The input data at this time consists of the company's job requirements and the job seeker's work history information. As output, the input data is securely transmitted to the server using the SSL / TLS protocol.

[0770] Step 2:

[0771] The server analyzes the job seeker's work history information that it receives. Using a generative AI model, it performs natural language processing to extract the job seeker's skills, experience, and values ​​from the input work history. The input here is the job seeker's work history information, and the output is structured data such as the job seeker's skill set obtained through analysis.

[0772] Step 3:

[0773] The server uses emotion analysis technology to evaluate the emotional characteristics of job applicants. It takes written information submitted by the applicant as input, analyzes their emotional state from that text, and quantifies characteristics such as empathy and stress tolerance. The output is data representing these emotional characteristics.

[0774] Step 4:

[0775] The server matches job requirements with analyzed information on job seekers in real time. It uses the job requirements provided by companies and analyzed data on job seekers as input, and calculates a confidence score based on a matching algorithm. The output is a list of job seekers with a high degree of matching.

[0776] Step 5:

[0777] The user, a company representative, reviews the candidate list sent from the server via their terminal. The input is a list of job seekers and their suitability ratings, and the company representative selects candidates to interview based on this. The output is a list of job seekers whose selection process is progressing.

[0778] Step 6:

[0779] The server collects and analyzes emotional data between the company and the job seeker using emotion analysis technology during the interview process. It uses audio and video data from the interview as input to accurately measure emotional states in real time. The output provides this emotional information as feedback to the interviewer, supporting them in adjusting questions and responses.

[0780] (Application Example 2)

[0781] 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".

[0782] In modern recruitment processes, emotional compatibility is just as important as a candidate's technical skills and experience. However, traditional systems struggle to effectively assess the emotional fit between candidates and companies, making it difficult to find the best talent. Similarly, electronic payment systems may fail to provide an appropriate interface that responds to user emotions, potentially compromising user satisfaction.

[0783] 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.

[0784] In this invention, the server includes means for receiving job seekers' work history information and analyzing their abilities, experience, and value using natural language processing technology; means for matching company job postings with the analyzed job seeker information in real time to achieve the best possible match; means for supporting communication between companies and job seekers to coordinate interview schedules and share opinions; and means for analyzing the emotions of decision-makers and dynamically adjusting the user interface based on the results. This enables technically and emotionally optimal matching for both job seekers and companies, and allows for flexible responses to user emotions in electronic payments.

[0785] "Work history information" refers to detailed data about a job seeker's past work experience, demonstrating their skills and abilities.

[0786] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0787] "Company job postings" refer to information about the personnel requirements and job descriptions that companies are looking for.

[0788] "Real-time matching" is a process that instantly compares received data and determines whether it matches.

[0789] "Communication for sharing and exchanging opinions" refers to a means of communication that allows for the two-way exchange of news and ideas.

[0790] "Emotional analysis" refers to the analytical process used to determine and evaluate an individual's emotional state.

[0791] A "user interface" is the screen configuration that allows the user and the system to interact with each other.

[0792] "Dynamic adjustment" means that settings and displays are changed as needed depending on the situation.

[0793] This invention is a system for achieving optimal matching between job seekers and companies, and is capable of comprehensively evaluating the emotional and technical characteristics of job seekers. The system mainly consists of three elements: a server, a terminal, and a user.

[0794] First, the terminal provides an interface for collecting input information from companies and job seekers. Companies enter job postings through the terminal, and job seekers upload their work history information. This information is then sent to the server.

[0795] Next, the server analyzes the received information. Here, a generative AI model is used, and natural language processing techniques are employed to extract the job seeker's abilities, experience, and value. Simultaneously, an emotion engine is used to evaluate the job seeker's emotional characteristics, and emotional compatibility is incorporated into the matching process.

[0796] Furthermore, in electronic payments, the server analyzes the user's emotions in real time. Based on the analysis results, the user interface design is dynamically adapted. This allows for the provision of an optimal interface tailored to the user's emotions. Specifically, if the user is feeling anxious, the screen's colors are changed to calmer tones to promote a sense of security.

[0797] In implementing this system, we will use emotion recognition APIs (e.g., Microsoft Azure Emotion API) and the React Native framework to enable the development of highly versatile applications.

[0798] For example, if a company is looking for someone with excellent communication skills, the system will analyze the applicant's past work experience and emotional characteristics to list the most suitable candidates. An example of a prompt to the generative AI model is, "Suggest the best UI theme and navigation message for when the user is feeling anxious."

[0799] In this way, a system is built in which servers, terminals, and users work together to achieve both technical and emotional matching.

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

[0801] Step 1:

[0802] The terminal receives job postings entered by companies and work history information uploaded by job seekers. The input information is collected via user forms and sent to the server. This is the process of delivering relevant information to the server through the act of data transmission.

[0803] Step 2:

[0804] The server analyzes the received information. First, it uses a generative AI model to extract the job seeker's skills, experience, and value from their work history information using natural language processing techniques. The input is work history information, and the output is the analyzed skill set. This analysis involves the process of textual analysis of the data.

[0805] Step 3:

[0806] The server then uses an emotion engine to evaluate the job seeker's emotional characteristics. Input is work history information, and voice and facial expression data may also be required. The output is an emotional characteristic score. This process involves data calculations called emotion analysis.

[0807] Step 4:

[0808] The server matches company job postings with analyzed job seeker data in real time, calculates technical and emotional fit scores, and lists the best candidates. The input is the analyzed data (output from the previous step) and the company job postings. The output is a list of job seekers with a high degree of matching. This operation involves information matching and fit calculation.

[0809] Step 5:

[0810] The device supports communication between companies and job seekers for scheduling interviews. Users propose interview dates, and both parties are notified. This is done through the sharing of the proposed date and time.

[0811] Step 6:

[0812] In the electronic payment process, the server analyzes the user's emotions in real time from their facial image and voice data, and dynamically adjusts the user interface displayed on the terminal based on the results. The input is real-time data including emotions, and the output is the modified interface state. This step involves emotion analysis and interface updating.

[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 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 method for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology,

[0837] A method for matching company job posting data with job seeker analysis data in real time to achieve optimal matching,

[0838] A means of supporting communication between companies and job seekers for scheduling interviews and sharing feedback,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, comprising means for evaluating long-term suitability and recommending the most suitable candidate, taking into account the degree of alignment between the applicant's analytical data and the company's values ​​and culture.

[0842] (Claim 3)

[0843] The system according to claim 1, comprising means for prioritizing the filtering of job seekers' skill sets based on company requirements and generating a list of candidates based on the degree of matching.

[0844] "Example 1"

[0845] (Claim 1)

[0846] A method for obtaining job seekers' work history information and analyzing their abilities, experience, and value using natural language processing technology,

[0847] A means to match company job postings with job seeker analysis information in real time to achieve the best possible match,

[0848] A means of supporting communication between companies and job seekers to coordinate interview schedules and share evaluation opinions,

[0849] A means of providing job seeker feedback to companies and making it available for review on a server,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, comprising means for evaluating long-term suitability and recommending the best candidate, taking into account analytical information of job seekers and the degree of alignment with the company's values ​​and culture.

[0853] (Claim 3)

[0854] The system according to claim 1, comprising means for prioritizing the selection of job seekers' skill sets based on the requirements of a company and creating a list of candidates based on the degree of matching.

[0855] "Application Example 1"

[0856] (Claim 1)

[0857] A method for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology,

[0858] A method for matching company job posting data with job seeker analysis data in real time to achieve optimal matching,

[0859] A means to support the exchange of information between companies and job seekers for coordinating interview schedules and sharing evaluation results,

[0860] A means of supporting job seekers with the initial procedures required after being hired, using e-commerce technology,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, comprising means for evaluating long-term suitability and recommending the most suitable candidate, taking into account the degree of alignment between the applicant's analytical data and the company's values ​​and culture.

[0864] (Claim 3)

[0865] The system according to claim 1, comprising means for prioritizing the filtering of job seekers' skills based on the requirements of a company and generating a list of candidates based on the degree of matching.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] A means of receiving job seekers' work history information and analyzing their skills, experience, and values ​​using natural language processing,

[0869] A means of using emotion analysis technology to analyze the emotional characteristics of job seekers,

[0870] A means to perform optimal matching by comparing the job requirements of employers with the analytical information of job seekers in real time,

[0871] A communication support tool for coordinating and sharing interview schedules and feedback between employers and job seekers,

[0872] A means of analyzing the emotions of employers and job seekers during interviews in real time and providing feedback based on that information,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, comprising means for evaluating long-term suitability by considering the degree of alignment between the analytical information of job seekers and the values ​​and culture of the employer, and recommending the most suitable candidate.

[0876] (Claim 3)

[0877] The system according to claim 1, comprising means for prioritizing and filtering the skill sets of job seekers based on the requirements of the business operator, and generating a list of candidates based on the degree of matching.

[0878] "Application example 2 when combining with an emotional engine"

[0879] (Claim 1)

[0880] A means of receiving job seekers' work history information and analyzing their abilities, experience, and value using natural language processing technology,

[0881] A method for matching company job postings with job seeker analysis information in real time to achieve the best possible match,

[0882] A means of supporting communication between companies and job seekers to coordinate interview schedules and share opinions,

[0883] A means of analyzing the emotions of decision-makers and dynamically adjusting the user interface based on the results,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, comprising means for evaluating long-term suitability and recommending the most suitable candidate, taking into account analytical information of job seekers and the degree of alignment with the company's values ​​and culture.

[0887] (Claim 3)

[0888] The system according to claim 1, comprising means for prioritizing the filtering of job seekers' skills based on the requirements of a company and generating a list of candidates based on the degree of matching. [Explanation of symbols]

[0889] 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 method for receiving job seekers' work history data and analyzing their skills, experience, and values ​​using natural language processing technology, A method for matching company job posting data with job seeker analysis data in real time to achieve optimal matching, A means of supporting communication between companies and job seekers for scheduling interviews and sharing feedback, A system that includes this.

2. The system according to claim 1, comprising means for evaluating long-term suitability and recommending the most suitable candidate, taking into account the degree of alignment between the applicant's analytical data and the company's values ​​and culture.

3. The system according to claim 1, comprising means for prioritizing the filtering of job seekers' skill sets based on the requirements of a company and generating a list of candidates based on the degree of matching.

Images