system

Abstract

We provide the system. [Solution] Means for receiving and analyzing corporate request information, A means for receiving and storing individual applicant information, A means for comparing the company's requirements with the applicant's individual information and calculating the degree of suitability, A means for selecting the best candidate based on the generated degree of fit, A means of determining and recommending the placement of selected candidates, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern recruitment market, mismatches between skills and corporate culture frequently occur between companies and job seekers, resulting in problems such as early resignation and a decline in the retention rate of employees. In particular, in the case of international recruitment, incompatibility due to cultural background differences has become an additional problem. In the conventional recruitment process, it is difficult to perform optimal matching considering all the characteristics of individual applicants. This leads to problems such as a decline in recruitment efficiency and difficulty in proper personnel placement, and as a result, there is a problem that it hinders the operation and growth of companies.

Means for Solving the Problems

[0005] This invention aims to solve the above problems by using generative AI technology that collects corporate requirements information and individual applicant information, and calculates the degree of suitability based on this information. Specifically, it provides a system that analyzes the requirements information received from companies and compares it with applicant information to select the most suitable candidates. It also includes means for evaluating applicants' abilities through automated online interviews and skills tests, and proposing appropriate assignments based on the results. In this way, it reduces mismatches between companies and job seekers, improving the efficiency and success rate of recruitment.

[0006] "Company requirements information" refers to information about the ideal candidate profile, necessary skill sets, and corporate culture that a company seeks.

[0007] "Applicant's individual information" refers to detailed personal information provided by the applicant, such as skills, experience, and personality traits.

[0008] "Fit" refers to a numerical indicator that evaluates and quantifies the degree to which a company's requirements match or fit with an applicant's individual information.

[0009] "Generative AI technology" refers to artificial intelligence technology that can analyze large amounts of data and find specific patterns or relationships.

[0010] An "online interview" refers to a form of communication conducted over the internet, used to evaluate a job seeker's abilities and suitability.

[0011] A "skills test" refers to an examination conducted to evaluate the skills and knowledge possessed by job applicants.

[0012] "Methods for determining and recommending assignments" refers to the process of recommending the job or department that best suits the applicant's characteristics based on the analysis results. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a tagged 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.

[0017] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a tagged 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.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a system for efficiently selecting and placing suitable personnel by matching the requirements of companies with the characteristics of applicants. This system centrally manages information gathering, analysis, suitability calculation, automation of interviews and tests, and final candidate selection and placement between companies and job seekers.

[0035] First, the server stores the request information received from the company in a database and uses an analysis engine to build a profile of the ideal candidate. This profile includes required skills, cultural adaptability, and communication abilities.

[0036] Next, the terminal receives resumes, qualifications, and skill assessment results entered by job seekers and stores them in a database as individual information. Each applicant's information is tagged and used in the subsequent matching process.

[0037] Furthermore, users (job seekers) participate in online interviews. During these interviews, a generating AI automatically asks questions and analyzes the applicants' responses. The server analyzes the interview and skills test results to calculate the job seeker's suitability.

[0038] The server then matches each job seeker's suitability score against the company's profile and lists the most suitable candidates. Furthermore, based on each applicant's characteristics, it recommends the most suitable job or department and outputs it as a plan.

[0039] For example, if a company is looking for a data scientist with global project experience, the server will receive this information and prioritize selecting candidates with experience in international projects or AI algorithm development from among the applicants. Furthermore, online interviews will assess English language proficiency and cultural adaptability.

[0040] In this way, companies can quickly and accurately recruit and appropriately assign the right talent for their purposes, improving overall recruitment efficiency.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives request information provided by companies. This includes details about required skills, company culture, and job responsibilities. This information is converted into a data format and stored in a database.

[0044] Step 2:

[0045] The server processes the received company request information into an analysis engine to generate an ideal candidate profile. This profile is structured to include required skills, years of experience, and personality traits.

[0046] Step 3:

[0047] The terminal receives personal information, resumes, and skills information entered by job seekers into the application system and stores it in a database. All information is tagged to enable efficient searching in subsequent processes.

[0048] Step 4:

[0049] The user (job seeker) receives an online interview link from the system and participates in the interview. During the interview, a generation AI generates questions and records the job seeker's responses.

[0050] Step 5:

[0051] The server analyzes information obtained through online interviews and tests to evaluate the applicant's characteristics and skill level. This evaluation is quantified and stored in a database.

[0052] Step 6:

[0053] The server compares the company's requirements with data obtained from job seekers and calculates a suitability score. This score indicates how well the job seeker matches the company's requirements.

[0054] Step 7:

[0055] The server selects the most suitable candidates based on the calculated suitability scores and creates a list. It also recommends the most appropriate placement for the job offered by the company and reports this to the company in a report format.

[0056] These specific processing steps enable the system to efficiently and accurately select and assign the most suitable personnel for the company.

[0057] (Example 1)

[0058] 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."

[0059] Quickly and accurately selecting and appropriately placing the talent an organization needs is a crucial challenge in efficient talent management. However, traditional systems struggle to effectively match applicant information with company requirements, resulting in time-consuming and labor-intensive processes. Furthermore, there is a lack of systems capable of automating online interviews and skills tests, and conducting appropriate talent evaluations based on these results. As a result, companies are expending considerable effort to find the best candidates.

[0060] 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.

[0061] In this invention, the server includes means for acquiring and analyzing organizational requirements information, means for collecting and storing applicant attribute information, and means for analyzing responses using a generative model. This enables automatic matching of applicant characteristics with organizational requirements, and allows for highly accurate suitability assessments based on interview and test results. As a result, organizations can significantly improve the efficiency of their talent selection process.

[0062] An "organization" refers to a company or group that needs or seeks human resources.

[0063] "Requirements information" refers to information about the skills, experience, and abilities that an organization requires for a particular job.

[0064] "Analysis" is the process of extracting meaningful knowledge from collected data.

[0065] An "applicant" is a person who expresses interest in a job at an organization and seeks employment.

[0066] "Attribute information" refers to information about the applicant's skills, qualifications, experience, and other characteristics.

[0067] The "fit index" is a numerical value that indicates how well an organization's requirements match the attributes of an applicant.

[0068] "Selection" means determining the most suitable candidate based on their degree of suitability.

[0069] "Assignment" refers to assigning selected personnel to specific duties or roles.

[0070] A "generative model" is software that uses natural language processing and machine learning to generate and analyze information in a way that mimics human behavior.

[0071] "Online communication" refers to interviews or conversations conducted via the internet.

[0072] This invention provides a system for efficiently selecting and optimally assigning personnel to organizations. Specifically, the server, terminal, and user elements collaborate to collect, analyze, and match information.

[0073] The server receives organizational request information via the network and stores it in a database. This data is analyzed using a parsing engine that enables natural language processing. Software such as NLTK and SpaCy, implemented in Python, are used as the parsing engine. The analyzed information is constructed in JSON format as a clear profile of the desired personnel.

[0074] The terminal receives resumes and qualification information entered by applicants via web forms. This information is scanned using OCR technology and stored as text data in a database. Tesseract OCR is a possible software used for this process. The terminal can tag the entered information to facilitate subsequent matching.

[0075] The user (job seeker) participates in an online interview. In this interview, a generative AI model automatically generates questions using prompts. For example, it might use a prompt such as, "Please tell me more about your experience in international projects." The user's answers to the generated questions are transcribed in real time using speech recognition technology. Speech recognition uses technologies such as Google® Speech-to-Text API. Based on these results, the server calculates a suitability score and compares it to the organization's profile to list the most suitable candidates.

[0076] For example, if a company is seeking a data scientist, the server can analyze the requirements and prioritize applicants with international project experience and knowledge of AI algorithms. The AI ​​used in online interviews automatically assesses the applicant's English language proficiency. In this way, organizations can quickly identify suitable talent and achieve efficient placement.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server receives request information from organizations via the network. Specifically, job postings received via an HTTP API are stored in the database as JSON data. The job postings, as input, include required skills, experience, and characteristics. The server uses a natural language processing engine (e.g., NLTK or SpaCy) to analyze the information and generates profiles of the desired personnel as output.

[0080] Step 2:

[0081] The terminal collects resumes and qualification information submitted by job seekers. Applicants provide this information digitally via an input form. The entered information is scanned using OCR technology (e.g., Tesseract OCR) and stored in a database as text data. At this time, the terminal tags attribute information to streamline subsequent matching. The output is a dataset of tagged attribute information.

[0082] Step 3:

[0083] The server matches the organization's profile with the applicant's attribute information. Using natural language processing algorithms, it evaluates the degree of skill and experience match from the input data. This calculates a suitability index and outputs a ranking of candidates. This output forms the basis for the subsequent selection process.

[0084] Step 4:

[0085] The user (job seeker) participates in an online interview using a generative AI model. The generative AI model automatically generates pre-set prompts (e.g., "Tell me about your project experience") and presents them to the user. The user's responses are transcribed in real time using speech recognition technology (e.g., Google Speech-to-Text API) and sent to the server. The input is the user's voice response, and the output is the transcribed response.

[0086] Step 5:

[0087] The server integrates interview results and skills test results to ultimately calculate the degree of suitability. It then implements multi-criteria analysis and uses the suitability index to generate a list of optimal candidates, which is then submitted to the organization. This results in a final list of candidates and recommendations for optimal placement.

[0088] (Application Example 1)

[0089] 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."

[0090] The appropriate allocation of personnel and machinery within a company is crucial for improving productivity and efficiency. However, traditional processes for selecting personnel and allocating machinery are often manual, making them time-consuming and costly. Furthermore, matching the characteristics of applicants with the company's needs and accurately evaluating the operational status of machinery are challenging.

[0091] 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.

[0092] In this invention, the server includes means for receiving and analyzing corporate request information, means for receiving and storing individual applicant information, means for comparing the corporate request information with the individual applicant information and calculating a degree of suitability, means for selecting the most suitable candidate based on the generated degree of suitability, means for determining and recommending the placement of the selected candidate, means for collecting and analyzing machine operation data, and means for evaluating the machine operation efficiency based on the analysis results and assigning the most suitable tasks. This enables the appropriate selection and placement of personnel and machines based on the needs of the company.

[0093] "Corporate requirements information" refers to data that specifically outlines the skills, experience, and characteristics that a company requires for a particular role or task.

[0094] "Applicant's individual information" refers to data that shows the individual characteristics of job seekers, such as resumes, qualifications, and skill assessment results.

[0095] "Methods for calculating suitability" refer to methods that analyze the company's requirements information and the applicant's individual information, and quantify the degree of matching.

[0096] "A method for selecting the optimal candidate" is a method of choosing the person best suited for the required role based on the calculated suitability score.

[0097] "Means for determining and recommending candidate placement" refers to a process that provides guidelines for assigning selected candidates to appropriate roles and departments within a company.

[0098] "Operational data" refers to all detection information generated by machines and robots during operation, and it serves as the basis for evaluating the performance and status of the machine.

[0099] "Means for evaluating operational efficiency and assigning optimal tasks" refers to a method that determines the efficiency of a machine based on analyzed operational data and automatically selects appropriate work content.

[0100] The server records the requirements information provided by the company in a database and uses an analysis engine to form a model of the ideal candidate. This model includes elements such as required skills, experience, and cultural adaptability. The hardware used includes high-performance processors and storage installed in a data center. The software used includes Python for data analysis and MySQL® for the database management system.

[0101] On the other hand, the terminal receives information such as resumes and skills test results submitted online by job seekers. This information is stored in a database and tagged. In this process, applicant information is prepared for analysis on the server.

[0102] Furthermore, job seekers, as users, undergo online interviews in which they answer questions generated by AI. Based on the analysis of these responses, the server analyzes the interview results and skills test results to calculate each job seeker's suitability. A machine learning model using TENSORFLOW® is utilized in this analysis process.

[0103] For example, when a machine's performance deteriorates, collecting its operational data reveals that wear and tear on parts is the cause. Based on this information, maintenance is recommended, and appropriate resources are reallocated.

[0104] An example of a prompt message for the generated AI model is, "Analyze the cause of the decreased efficiency of SN123-Robo and propose the optimal maintenance task." In this way, data exchange and appropriate processing are achieved between the server, terminal, and user.

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

[0106] Step 1:

[0107] The server receives request information provided by companies. As input, it receives information about the skills, experience, and characteristics that companies are looking for. This information is stored in a database, and an analysis engine is used to build a model of suitable candidates. This model quantifies the necessary characteristics based on the received attribute information and generates a profile.

[0108] Step 2:

[0109] The terminal receives resumes and qualification information from job seekers online. This input data is individually tagged and stored in a database. This makes the characteristics of each applicant immediately clear, preparing them for matching in later processes.

[0110] Step 3:

[0111] The job seeker, as the user, participates in an online interview. Here, they answer questions based on prompts provided by, for example, a generative AI model. This interview data is received by a server, where the answers are analyzed. Based on the provided answers, communication skills, adaptability, and other factors are evaluated, and a goodness-of-fit score is calculated as output.

[0112] Step 4:

[0113] The server compares the company profile generated in Step 1 with the suitability score of each applicant calculated in Step 3. Utilizing the information stored in the database, it performs quantitative matching to extract the most suitable candidates. The output is a list of the most suitable individuals.

[0114] Step 5:

[0115] The server ultimately creates a placement plan that recommends job roles and work locations based on the selected personnel. It uses the company's organizational structure and position information as input to calculate appropriate placements. The output is a detailed plan including recommended placements.

[0116] Step 6:

[0117] The server continuously receives and analyzes machine operation data. Sensor data and operation logs are provided as input, and the analysis engine evaluates the operational efficiency. Based on this efficiency, it proposes regular machine maintenance and optimal task reassignment. The output is a concrete action plan to improve efficiency.

[0118] 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.

[0119] This invention aims to achieve a more accurate talent selection process by incorporating emotion recognition technology into a system that matches corporate requirements with the characteristics of applicants. The system consists of the following elements:

[0120] First, the server receives request information from companies and stores it in a database. The company profile contains details about the ideal candidate they are looking for, including emotional adaptability and communication skills. The analysis engine uses this information to generate an ideal candidate profile.

[0121] Next, the terminal receives input from applicants, such as history information and skill data, and stores the individual information in a database. This data is tagged with sentiment data tags along with the usual application information tags.

[0122] The user (job seeker) participates in an online interview conducted by the system. During this interview, an emotion engine activates, analyzing the candidate's emotional state in real time based on their facial expressions, tone of voice, and speech content. This allows for the extraction of indicators such as the user's stress level, level of interest, and sincerity.

[0123] The server analyzes emotional data obtained from online interviews along with regular evaluation data to calculate the overall suitability of the job seeker. In this process, it assesses how emotions affect the applicant in specific situations and contributes to the estimation of cultural adaptability and interpersonal skills.

[0124] Furthermore, the server uses the suitability derived from emotional characteristics to perform optimal matching with company requirements and proposes provisional placements for candidates. This allows companies to find highly suitable personnel for appropriate environments, and is expected to significantly improve the success rate of recruitment.

[0125] For example, if a company prioritizes the ability to cope with high-stress environments, the Emotion Engine evaluates the applicant's stress indicators during online interviews and reflects this as a score. As a result, the applicant is recommended as a high-stress adaptable candidate, and placement in the appropriate department becomes more effective.

[0126] Technically, this system is realized by combining existing database management technology, generative AI, and sentiment analysis technology, and is particularly effective in improving accuracy during the selection process.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server receives request information from companies and forwards it to the analysis engine. Here, data on the skills, characteristics, and cultural adaptability required by the companies is stored in a database, and the necessary profiles are created.

[0130] Step 2:

[0131] The terminal receives personal information, resumes, and qualification data entered by job seekers and registers them in a database. At this point, skill tags and experience tags are assigned to the applicant's information and used in subsequent processing.

[0132] Step 3:

[0133] The user (job seeker) participates in an online interview with an integrated emotion engine. Here, facial expressions and voice are analyzed from the video feed to generate emotion recognition data.

[0134] Step 4:

[0135] The server sends emotional data obtained from online interviews to an analysis engine, which, along with the content of the responses, evaluates the job seeker's personality. This makes it possible to quantitatively assess the job seeker's interpersonal skills and stress tolerance.

[0136] Step 5:

[0137] The server calculates a suitability score for each candidate based on the analysis results. This score is based on both skills information and sentiment data, providing a more comprehensive evaluation.

[0138] Step 6:

[0139] The server lists the most suitable candidates based on their suitability scores and generates matching results for the company's talent requirements. This includes estimations of cultural adaptability and communication skills based on emotional states.

[0140] Step 7:

[0141] The server sends the final candidate list and recommended placement plans to the company. This allows the company to make personnel placement decisions that take emotional adaptability into consideration.

[0142] This process enables more precise matching and candidate selection using an emotion engine, contributing to an improved recruitment success rate.

[0143] (Example 2)

[0144] 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".

[0145] Traditional talent selection systems calculated suitability based only on company requirements and basic individual information of applicants, making it difficult to select the right talent. Furthermore, they failed to consider emotional states and their changes, potentially overlooking important factors such as integrity and stress tolerance. There is a need to address these challenges and achieve more accurate talent selection.

[0146] 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.

[0147] In this invention, the server includes means for storing corporate request information in a data storage means, means for analyzing user emotional information during online interviews, and means for selecting the most suitable candidate using a generative AI model. This enables highly accurate matching by combining corporate requirements with the emotional characteristics of applicants.

[0148] "Company requirements information" refers to detailed information about the ideal candidate that a company is looking for, including job responsibilities, necessary skills, emotional adaptability, and communication skills.

[0149] "Resume information" refers to information that shows the applicant's past experience and achievements, such as their educational background, work history, and qualifications.

[0150] "Skill data" refers to information about the applicant's skills and abilities, including specialized knowledge required for a specific job or industry.

[0151] "Data storage means" refers to a recording device or medium for storing received information, and includes database systems and the like.

[0152] "Emotional information" refers to information about the applicant's psychological and emotional state obtained from their facial expressions, tone of voice, and speech content during online interviews.

[0153] An "online interview" refers to a remote interview or meeting conducted via the internet, providing an opportunity to observe the applicant's real-time responses.

[0154] "Fit" is an indicator that shows how well an applicant's characteristics and skills match the company's requirements.

[0155] A "generative AI model" is an artificial intelligence program used to select the most suitable candidates based on collected data.

[0156] "Candidate placement" refers to assigning selected candidates to the most suitable roles or departments.

[0157] "Recommendation" is the act of communicating that a proposed item or option is the best choice.

[0158] This invention is a talent selection system for accurately matching corporate requirements with the characteristics of applicants. This system mainly consists of three components: a server, terminals, and users.

[0159] The server receives request information from companies through an interface and stores it in a data storage device. The stored information is managed as a company profile, including job description, required skills, emotional adaptability, and communication abilities. The server uses database management systems such as MySQL or PostgreSQL to store and manage the data.

[0160] The terminal is used to receive historical information and skill data from applicants. When collecting information through web forms and applications and storing it in a database, sentiment data tags are added to generate richer applicant profiles. For example, if an applicant's specific technical skills are evaluated, a corresponding tag is assigned.

[0161] When users (job seekers) participate in online interviews, their emotional state is analyzed in real time via an emotion engine. This involves video calls using technologies such as WebRTC, and further utilizes OpenCV for facial expression analysis and the Python Librosa library for voice tone analysis. This allows for the analysis of indicators such as stress level, level of interest, and sincerity based on the user's facial expressions, voice tone, and spoken content.

[0162] To select the most suitable candidates, the server uses a generative AI model. This calculates a degree of suitability based on applicant sentiment information, historical information, and company requirements. Machine learning libraries such as scikit-learn are used, and statistical models are employed for analysis.

[0163] For example, if a company is looking for "personnel who can adapt to working in a high-stress environment," the server uses an emotion engine to evaluate the applicant's stress tolerance and scores the result. This information is then input into a generative AI model, which generates prompts such as, "Consider the data on stress tolerance and suggest a way to match the company's requirements with the applicants," thereby assisting the AI's decision-making.

[0164] Through such a system, companies can obtain highly accurate talent matching, significantly improving the efficiency and effectiveness of their recruitment process.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The server receives request information from companies. Companies send information such as job descriptions, required skills, and desired characteristics via API. The server receives this information and stores it in a database. At this time, a MySQL database is used to organize the information and prepare it for later analysis. The received information includes job descriptions and ideal applicant profiles, and the server stores this information as structured data. The output is the company profile information stored in the database.

[0168] Step 2:

[0169] The terminal receives historical and skill data from applicants. Users input this information through a web form. The terminal tags the application information with emotional data and stores it in a database. In this process, emotional tags (e.g., communication skills) are provided along with regular application information (e.g., education and work history). The input is the applicant's basic information, and the output is a tagged applicant profile.

[0170] Step 3:

[0171] The user (job seeker) participates in an online interview. During this interview, the user's facial expressions, voice tone, and speech content are captured in real time and analyzed by an emotion engine. This process involves a video call via WebRTC. OpenCV is used for emotion analysis, and Librosa is used for voice tone analysis. The input is video call data, and the output is an emotion index indicating the user's stress level and level of interest.

[0172] Step 4:

[0173] The server receives sentiment data obtained from online interviews and integrates it with regular application information to calculate the applicant's suitability. The server utilizes scikit-learn and machine learning algorithms to analyze the suitability. In this process, all data is evaluated by statistical models, and the system obtains foundational information for selecting the most suitable candidates. The input is the integrated applicant data, and the output is the calculated suitability score.

[0174] Step 5:

[0175] The server uses a generative AI model to select the best candidates based on their fit. The AI ​​model analyzes the received data and generates prompts such as, "Consider data on stress tolerance and suggest how to match applicants with company requirements." Through this process, the AI ​​lists the best candidates and provides recommendations to the company. The input is the fit score, and the output is the final candidate list.

[0176] Step 6:

[0177] The server proposes provisional placements for selected candidates. Based on the candidate list generated by the AI ​​model, the server recommends appropriate placements to the company. This includes a process of communicating the results to the company via a notification system. The output is information on the provisional placement proposals sent to the company.

[0178] (Application Example 2)

[0179] 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".

[0180] In a company's recruitment process, the challenge is to improve the success rate of recruitment by enabling a comprehensive aptitude assessment based not only on applicants' skills and work history, but also on their emotional state, thereby ensuring that the right people are placed in the right positions.

[0181] 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.

[0182] In this invention, the server includes means for receiving and analyzing corporate request information, means for receiving and storing individual applicant information, and means for performing sentiment analysis during online interviews and evaluating the applicant's emotional state. This enables more accurate candidate suitability assessment and recommendations based on corporate requirements, while also taking into account the applicant's emotional state.

[0183] "Company requirements information" refers to information about the ideal candidate profile, necessary skills, emotional adaptability, and communication abilities that a company seeks.

[0184] "Applicant's individual information" refers to data including the applicant's resume, skills data, and emotional data collected during the interview.

[0185] A "means for calculating suitability" refers to a method of evaluating how well an applicant is suited to a company, based on the company's requirements and the applicant's individual information.

[0186] "Selection methods" refer to methods for determining the most suitable candidate for a company based on the calculated suitability score.

[0187] "Methods for performing emotional analysis" refer to technologies that analyze the applicant's facial expressions and tone of voice during online interviews to evaluate their emotional state, such as stress levels and level of interest, in real time.

[0188] "Methods for adjusting the degree of fit" refer to techniques that modify conventional scores based on the results of sentiment analysis to perform optimal personnel evaluation.

[0189] "Methods for determining and recommending placement" refers to a method of suggesting departments or roles within the company where applicants can best utilize their abilities, based on their suitability.

[0190] The system for realizing this invention supports a talent selection process involving companies and applicants. This system consists of a server, terminals, and an emotion engine connected to them.

[0191] The server receives request information sent from companies and stores it in a database. This request information includes details about the type of person the company is looking for, such as emotional adaptability and communication skills. Based on this information, the server generates an ideal candidate profile.

[0192] The terminal processes the application history and skill data submitted by applicants. Furthermore, this information is stored in a database and assigned emotional data tags along with the regular application data tags. The emotional data tags are obtained during online interviews.

[0193] Applicants, acting as users, participate in online interviews. During these interviews, an emotion engine activates, analyzing the applicant's facial expressions and tone of voice in real time. This analysis process utilizes libraries such as OpenCV and TensorFlow to evaluate emotional states, including stress levels and interest levels. This information is then used to further refine the applicant's suitability for the position.

[0194] For example, if a candidate applying for a security-related position demonstrates a high level of composure during the interview, their suitability will be evaluated positively, and based on that, they may be recommended for placement in a specific department within the company.

[0195] An example of a prompt when applying a generative AI model is: "We will analyze the applicant's facial expression data and return scores for calmness, stress, and interest. These will be used to determine their appropriate placement." Through this prompt, it becomes possible to place candidates based on their emotional adaptability.

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server receives request information from companies. This information, provided by companies, is input and includes the ideal candidate profile, skills, and emotional adaptability requirements. The server stores this in a database and generates an ideal candidate profile. This profile is output as matching data in subsequent processing steps.

[0199] Step 2:

[0200] The terminal receives historical and skill data from applicants. Inputs include resumes and qualification certificates submitted by the applicants. The terminal analyzes this information, creates individual profiles, and stores them in a database. This profile outputs initial sentiment data tags along with the usual application information tags.

[0201] Step 3:

[0202] Applicants, acting as users, participate in online interviews. During the interview, an emotion engine operates, collecting and analyzing the applicant's facial expressions and voice tone in real time. The input for this engine is data acquired from the camera and microphone. Using libraries such as OpenCV and TensorFlow, stress levels and interest levels are scored. This scoring data is output as emotion data tags.

[0203] Step 4:

[0204] The server receives data from the emotion engine and recalculates the suitability based on the applicant's profile and the company's requirements. Emotional states are used as input to adjust the suitability evaluation. In this process, a generative AI model is used to output emotion analysis results based on prompt sentences.

[0205] Step 5:

[0206] The server proposes optimal departmental placements based on the re-evaluated suitability. The updated suitability score is the input, and recommended departments are analyzed based on it. Finally, the recommendation results are notified to the hiring manager, leading to appropriate talent placement.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] This invention provides a system for efficiently selecting and placing suitable personnel by matching the requirements of companies with the characteristics of applicants. This system centrally manages information gathering, analysis, suitability calculation, automation of interviews and tests, and final candidate selection and placement between companies and job seekers.

[0224] First, the server stores the request information received from the company in a database and uses an analysis engine to build a profile of the ideal candidate. This profile includes required skills, cultural adaptability, and communication abilities.

[0225] Next, the terminal receives resumes, qualifications, and skill assessment results entered by job seekers and stores them in a database as individual information. Each applicant's information is tagged and used in the subsequent matching process.

[0226] Furthermore, users (job seekers) participate in online interviews. During these interviews, a generating AI automatically asks questions and analyzes the applicants' responses. The server analyzes the interview and skills test results to calculate the job seeker's suitability.

[0227] The server then matches each job seeker's suitability score against the company's profile and lists the most suitable candidates. Furthermore, based on each applicant's characteristics, it recommends the most suitable job or department and outputs it as a plan.

[0228] For example, if a company is looking for a data scientist with global project experience, the server will receive this information and prioritize selecting candidates with experience in international projects or AI algorithm development from among the applicants. Furthermore, online interviews will assess English language proficiency and cultural adaptability.

[0229] In this way, companies can quickly and accurately recruit and appropriately assign the right talent for their purposes, improving overall recruitment efficiency.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server receives request information provided by companies. This includes details about required skills, company culture, and job responsibilities. This information is converted into a data format and stored in a database.

[0233] Step 2:

[0234] The server processes the received company request information into an analysis engine to generate an ideal candidate profile. This profile is structured to include required skills, years of experience, and personality traits.

[0235] Step 3:

[0236] The terminal receives personal information, resumes, and skills information entered by job seekers into the application system and stores it in a database. All information is tagged to enable efficient searching in subsequent processes.

[0237] Step 4:

[0238] The user (job seeker) receives an online interview link from the system and participates in the interview. During the interview, a generation AI generates questions and records the job seeker's responses.

[0239] Step 5:

[0240] The server analyzes information obtained through online interviews and tests to evaluate the applicant's characteristics and skill level. This evaluation is quantified and stored in a database.

[0241] Step 6:

[0242] The server compares the company's requirements with data obtained from job seekers and calculates a suitability score. This score indicates how well the job seeker matches the company's requirements.

[0243] Step 7:

[0244] The server selects the most suitable candidates based on the calculated suitability scores and creates a list. It also recommends the most appropriate placement for the job offered by the company and reports this to the company in a report format.

[0245] These specific processing steps enable the system to efficiently and accurately select and assign the most suitable personnel for the company.

[0246] (Example 1)

[0247] 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."

[0248] Quickly and accurately selecting and appropriately placing the talent an organization needs is a crucial challenge in efficient talent management. However, traditional systems struggle to effectively match applicant information with company requirements, resulting in time-consuming and labor-intensive processes. Furthermore, there is a lack of systems capable of automating online interviews and skills tests, and conducting appropriate talent evaluations based on these results. As a result, companies are expending considerable effort to find the best candidates.

[0249] 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.

[0250] In this invention, the server includes means for acquiring and analyzing organizational requirements information, means for collecting and storing applicant attribute information, and means for analyzing responses using a generative model. This enables automatic matching of applicant characteristics with organizational requirements, and allows for highly accurate suitability assessments based on interview and test results. As a result, organizations can significantly improve the efficiency of their talent selection process.

[0251] An "organization" refers to a company or group that needs or seeks human resources.

[0252] "Requirements information" refers to information about the skills, experience, and abilities that an organization requires for a particular job.

[0253] "Analysis" is the process of extracting meaningful knowledge from collected data.

[0254] An "applicant" is a person who expresses interest in a job at an organization and seeks employment.

[0255] "Attribute information" refers to information about the applicant's skills, qualifications, experience, and other characteristics.

[0256] The "fit index" is a numerical value that indicates how well an organization's requirements match the attributes of an applicant.

[0257] "Selection" means determining the most suitable candidate based on their degree of suitability.

[0258] "Assignment" refers to assigning selected personnel to specific duties or roles.

[0259] A "generative model" is software that uses natural language processing and machine learning to generate and analyze information in a way that mimics human behavior.

[0260] "Online communication" refers to interviews or conversations conducted via the internet.

[0261] This invention provides a system for efficiently selecting and optimally assigning personnel to organizations. Specifically, the server, terminal, and user elements collaborate to collect, analyze, and match information.

[0262] The server receives organizational request information via the network and stores it in a database. This data is analyzed using a parsing engine that enables natural language processing. Software such as NLTK and SpaCy, implemented in Python, are used as the parsing engine. The analyzed information is constructed in JSON format as a clear profile of the desired personnel.

[0263] The terminal receives resumes and qualification information entered by applicants via web forms. This information is scanned using OCR technology and stored as text data in a database. Tesseract OCR is a possible software used for this process. The terminal can tag the entered information to facilitate subsequent matching.

[0264] The user (job seeker) participates in an online interview. In this interview, a generative AI model automatically generates questions using prompts. For example, it might use a prompt such as, "Please tell me more about your experience in international projects." The user's answers to the generated questions are transcribed in real time using speech recognition technology. The Google Speech-to-Text API is used for speech recognition. Based on these results, the server calculates a suitability score and compares it to the organization's profile to list the most suitable candidates.

[0265] For example, if a company is seeking a data scientist, the server can analyze the requirements and prioritize applicants with international project experience and knowledge of AI algorithms. The AI ​​used in online interviews automatically assesses the applicant's English language proficiency. In this way, organizations can quickly identify suitable talent and achieve efficient placement.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The server receives request information from organizations via the network. Specifically, job postings received via an HTTP API are stored in the database as JSON data. The job postings, as input, include required skills, experience, and characteristics. The server uses a natural language processing engine (e.g., NLTK or SpaCy) to analyze the information and generates profiles of the desired personnel as output.

[0269] Step 2:

[0270] The terminal collects resumes and qualification information submitted by job seekers. Applicants provide this information digitally via an input form. The entered information is scanned using OCR technology (e.g., Tesseract OCR) and stored in a database as text data. At this time, the terminal tags attribute information to streamline subsequent matching. The output is a dataset of tagged attribute information.

[0271] Step 3:

[0272] The server matches the organization's profile with the applicant's attribute information. Using natural language processing algorithms, it evaluates the degree of skill and experience match from the input data. This calculates a suitability index and outputs a ranking of candidates. This output forms the basis for the subsequent selection process.

[0273] Step 4:

[0274] The user (job seeker) participates in an online interview using a generative AI model. The generative AI model automatically generates pre-set prompts (e.g., "Tell me about your project experience") and presents them to the user. The user's responses are transcribed in real time using speech recognition technology (e.g., Google Speech-to-Text API) and sent to the server. The input is the user's voice response, and the output is the transcribed response.

[0275] Step 5:

[0276] The server integrates interview results and skills test results to ultimately calculate the degree of suitability. It then implements multi-criteria analysis and uses the suitability index to generate a list of optimal candidates, which is then submitted to the organization. This results in a final list of candidates and recommendations for optimal placement.

[0277] (Application Example 1)

[0278] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0279] The appropriate allocation of personnel and machinery in a company is extremely important for improving productivity and efficiency. However, the conventional processes for personnel selection and machinery allocation are often performed manually, which is time-consuming and costly. Also, it is difficult to match the characteristics of applicants with the needs of the company and to appropriately evaluate the operating conditions of machinery.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0281] In this invention, the server includes means for receiving and analyzing the company's requirement information, means for receiving and storing the individual information of applicants, means for collating the company's requirement information and the individual information of applicants to calculate the degree of suitability, means for selecting the optimal candidate based on the calculated degree of suitability, means for determining and recommending the placement of the selected candidate, means for collecting and analyzing the operation data of machinery, and means for evaluating the operation efficiency of machinery based on the analysis result and assigning the optimal task. Thereby, it becomes possible to appropriately select and allocate personnel and machinery based on the needs of the company.

[0282] The "company's requirement information" is data that specifically indicates the skills, experience, and characteristics required by the company for a specific role or task.

[0283] The "individual information of applicants" is data indicating individual characteristics such as resumes, qualification information, and skill evaluation results provided by job seekers.

[0284] The "means for calculating the degree of suitability" is a method of analyzing the company's requirement information and the individual information of applicants and quantifying the degree of their agreement.

[0285] The "means for selecting the optimal candidate" is a method of selecting the person most suitable for the required role based on the calculated degree of suitability.

[0286] The means for determining and recommending the placement of candidates is a process that provides guidelines for assigning the selected candidates to appropriate positions and departments within the company.

[0287] "Operation data" refers to all the detection information generated when a machine or robot is in operation, which serves as a basis for evaluating the performance and state of the machine.

[0288] The means for evaluating operation efficiency and assigning optimal tasks is a method that determines the efficiency of a machine based on the analyzed operation data and automatically selects appropriate work content.

[0289] The server records the request information provided by the company in the database and forms a model of the ideal candidate through an analysis engine. This model includes elements such as required skills, experience, and cultural adaptability. The hardware used includes high-performance processors and storage installed in the data center. For software, Python is used for data analysis and MySQL is used for the database management system.

[0290] On the other hand, the terminal receives information such as resumes and skill test results submitted online by job seekers. These are stored in the database and tagged. In this process, the information of the applicants is prepared for analysis on the server.

[0291] Also, the job seeker, who is the user, undergoes an online interview that can answer questions generated by AI. Based on the analysis of this response, the server analyzes the interview results and skill test results and calculates the suitability of each job seeker. In the analysis process at this time, a machine learning model using TensorFlow is utilized.

[0292] As a specific example, when the operation of a certain machine deteriorates, as a result of collecting its operation data, it is identified that the cause is wear of parts. Based on this information, maintenance is recommended and appropriate resource reallocation is carried out.

[0293] An example of a prompt message for the generated AI model is, "Analyze the cause of the decreased efficiency of SN123-Robo and propose the optimal maintenance task." In this way, data exchange and appropriate processing are achieved between the server, terminal, and user.

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The server receives request information provided by companies. As input, it receives information about the skills, experience, and characteristics that companies are looking for. This information is stored in a database, and an analysis engine is used to build a model of suitable candidates. This model quantifies the necessary characteristics based on the received attribute information and generates a profile.

[0297] Step 2:

[0298] The terminal receives resumes and qualification information from job seekers online. This input data is individually tagged and stored in a database. This makes the characteristics of each applicant immediately clear, preparing them for matching in later processes.

[0299] Step 3:

[0300] The job seeker, as the user, participates in an online interview. Here, they answer questions based on prompts provided by, for example, a generative AI model. This interview data is received by a server, where the answers are analyzed. Based on the provided answers, communication skills, adaptability, and other factors are evaluated, and a goodness-of-fit score is calculated as output.

[0301] Step 4:

[0302] The server collates the corporate profile generated in Step 1 with the fitness scores of each applicant calculated in Step 3. Utilizing the information stored in the database, it performs a quantitative matching process to extract the optimal candidates. The output is a list of the most suitable candidates.

[0303] Step 5:

[0304] Finally, the server creates an allocation plan that recommends job positions and work locations based on the selected candidates. Using the corporate organizational structure and position information as input, it calculates the appropriate allocations based on this. The output is a detailed plan including the recommended allocations.

[0305] Step 6:

[0306] The server continuously receives and analyzes the operation data of the machine. Sensor data and operation logs are provided as input, and the operation efficiency is evaluated by the analysis engine. Based on this movement efficiency, it proposes regular maintenance of the machine and reallocation of optimal tasks. The output is a specific action plan to improve efficiency.

[0307] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0308] The present invention realizes a more accurate talent selection process by incorporating emotion recognition technology into a system that matches corporate requirements with applicant characteristics. The system consists of the following elements.

[0309] First, the server receives the requirement information from the enterprise and stores it in the database. The corporate profile includes details about the ideal talent sought, including emotional adaptability and communication skills. The analysis engine generates an ideal candidate profile based on this information.

[0310] Next, the terminal receives input from applicants, such as history information and skill data, and stores the individual information in a database. This data is tagged with sentiment data tags along with the usual application information tags.

[0311] The user (job seeker) participates in an online interview conducted by the system. During this interview, an emotion engine activates, analyzing the candidate's emotional state in real time based on their facial expressions, tone of voice, and speech content. This allows for the extraction of indicators such as the user's stress level, level of interest, and sincerity.

[0312] The server analyzes emotional data obtained from online interviews along with regular evaluation data to calculate the overall suitability of the job seeker. In this process, it assesses how emotions affect the applicant in specific situations and contributes to the estimation of cultural adaptability and interpersonal skills.

[0313] Furthermore, the server uses the suitability derived from emotional characteristics to perform optimal matching with company requirements and proposes provisional placements for candidates. This allows companies to find highly suitable personnel for appropriate environments, and is expected to significantly improve the success rate of recruitment.

[0314] For example, if a company prioritizes the ability to cope with high-stress environments, the Emotion Engine evaluates the applicant's stress indicators during online interviews and reflects this as a score. As a result, the applicant is recommended as a high-stress adaptable candidate, and placement in the appropriate department becomes more effective.

[0315] Technically, this system is realized by combining existing database management technology, generative AI, and sentiment analysis technology, and is particularly effective in improving accuracy during the selection process.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] The server receives request information from companies and forwards it to the analysis engine. Here, data on the skills, characteristics, and cultural adaptability required by the companies is stored in a database, and the necessary profiles are created.

[0319] Step 2:

[0320] The terminal receives personal information, resumes, and qualification data entered by job seekers and registers them in a database. At this point, skill tags and experience tags are assigned to the applicant's information and used in subsequent processing.

[0321] Step 3:

[0322] The user (job seeker) participates in an online interview with an integrated emotion engine. Here, facial expressions and voice are analyzed from the video feed to generate emotion recognition data.

[0323] Step 4:

[0324] The server sends emotional data obtained from online interviews to an analysis engine, which, along with the content of the responses, evaluates the job seeker's personality. This makes it possible to quantitatively assess the job seeker's interpersonal skills and stress tolerance.

[0325] Step 5:

[0326] The server calculates a suitability score for each candidate based on the analysis results. This score is based on both skills information and sentiment data, providing a more comprehensive evaluation.

[0327] Step 6:

[0328] The server lists the most suitable candidates based on their suitability scores and generates matching results for the company's talent requirements. This includes estimations of cultural adaptability and communication skills based on emotional states.

[0329] Step 7:

[0330] The server sends the final candidate list and recommended placement plans to the company. This allows the company to make personnel placement decisions that take emotional adaptability into consideration.

[0331] This process enables more precise matching and candidate selection using an emotion engine, contributing to an improved recruitment success rate.

[0332] (Example 2)

[0333] 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".

[0334] Traditional talent selection systems calculated suitability based only on company requirements and basic individual information of applicants, making it difficult to select the right talent. Furthermore, they failed to consider emotional states and their changes, potentially overlooking important factors such as integrity and stress tolerance. There is a need to address these challenges and achieve more accurate talent selection.

[0335] 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.

[0336] In this invention, the server includes means for storing corporate request information in a data storage means, means for analyzing user emotional information during online interviews, and means for selecting the most suitable candidate using a generative AI model. This enables highly accurate matching by combining corporate requirements with the emotional characteristics of applicants.

[0337] "Company requirements information" refers to detailed information about the ideal candidate that a company is looking for, including job responsibilities, necessary skills, emotional adaptability, and communication skills.

[0338] "Resume information" refers to information that shows the applicant's past experience and achievements, such as their educational background, work history, and qualifications.

[0339] "Skill data" refers to information about the applicant's skills and abilities, including specialized knowledge required for a specific job or industry.

[0340] "Data storage means" refers to a recording device or medium for storing received information, and includes database systems and the like.

[0341] "Emotional information" refers to information about the applicant's psychological and emotional state obtained from their facial expressions, tone of voice, and speech content during online interviews.

[0342] An "online interview" refers to a remote interview or meeting conducted via the internet, providing an opportunity to observe the applicant's real-time responses.

[0343] "Fit" is an indicator that shows how well an applicant's characteristics and skills match the company's requirements.

[0344] A "generative AI model" is an artificial intelligence program used to select the most suitable candidates based on collected data.

[0345] "Candidate placement" refers to assigning selected candidates to the most suitable roles or departments.

[0346] "Recommendation" is the act of communicating that a proposed item or option is the best choice.

[0347] This invention is a talent selection system for accurately matching corporate requirements with the characteristics of applicants. This system mainly consists of three components: a server, terminals, and users.

[0348] The server receives request information from companies through an interface and stores it in a data storage device. The stored information is managed as a company profile, including job description, required skills, emotional adaptability, and communication abilities. The server uses database management systems such as MySQL or PostgreSQL to store and manage the data.

[0349] The terminal is used to receive historical information and skill data from applicants. When collecting information through web forms and applications and storing it in a database, sentiment data tags are added to generate richer applicant profiles. For example, if an applicant's specific technical skills are evaluated, a corresponding tag is assigned.

[0350] When users (job seekers) participate in online interviews, their emotional state is analyzed in real time via an emotion engine. This involves video calls using technologies such as WebRTC, and further utilizes OpenCV for facial expression analysis and the Python Librosa library for voice tone analysis. This allows for the analysis of indicators such as stress level, level of interest, and sincerity based on the user's facial expressions, voice tone, and spoken content.

[0351] To select the most suitable candidates, the server uses a generative AI model. This calculates a degree of suitability based on applicant sentiment information, historical information, and company requirements. Machine learning libraries such as scikit-learn are used, and statistical models are employed for analysis.

[0352] For example, if a company is looking for "personnel who can adapt to working in a high-stress environment," the server uses an emotion engine to evaluate the applicant's stress tolerance and scores the result. This information is then input into a generative AI model, which generates prompts such as, "Consider the data on stress tolerance and suggest a way to match the company's requirements with the applicants," thereby assisting the AI's decision-making.

[0353] Through such a system, companies can obtain highly accurate talent matching, significantly improving the efficiency and effectiveness of their recruitment process.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The server receives request information from companies. Companies send information such as job descriptions, required skills, and desired characteristics via API. The server receives this information and stores it in a database. At this time, a MySQL database is used to organize the information and prepare it for later analysis. The received information includes job descriptions and ideal applicant profiles, and the server stores this information as structured data. The output is the company profile information stored in the database.

[0357] Step 2:

[0358] The terminal receives historical and skill data from applicants. Users input this information through a web form. The terminal tags the application information with emotional data and stores it in a database. In this process, emotional tags (e.g., communication skills) are provided along with regular application information (e.g., education and work history). The input is the applicant's basic information, and the output is a tagged applicant profile.

[0359] Step 3:

[0360] The user (job seeker) participates in an online interview. During this interview, the user's facial expressions, voice tone, and speech content are captured in real time and analyzed by an emotion engine. This process involves a video call via WebRTC. OpenCV is used for emotion analysis, and Librosa is used for voice tone analysis. The input is video call data, and the output is an emotion index indicating the user's stress level and level of interest.

[0361] Step 4:

[0362] The server receives sentiment data obtained from online interviews and integrates it with regular application information to calculate the applicant's suitability. The server utilizes scikit-learn and machine learning algorithms to analyze the suitability. In this process, all data is evaluated by statistical models, and the system obtains foundational information for selecting the most suitable candidates. The input is the integrated applicant data, and the output is the calculated suitability score.

[0363] Step 5:

[0364] The server uses a generative AI model to select the best candidates based on their fit. The AI ​​model analyzes the received data and generates prompts such as, "Consider data on stress tolerance and suggest how to match applicants with company requirements." Through this process, the AI ​​lists the best candidates and provides recommendations to the company. The input is the fit score, and the output is the final candidate list.

[0365] Step 6:

[0366] The server proposes provisional placements for selected candidates. Based on the candidate list generated by the AI ​​model, the server recommends appropriate placements to the company. This includes a process of communicating the results to the company via a notification system. The output is information on the provisional placement proposals sent to the company.

[0367] (Application Example 2)

[0368] 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."

[0369] In a company's recruitment process, the challenge is to improve the success rate of recruitment by enabling a comprehensive aptitude assessment based not only on applicants' skills and work history, but also on their emotional state, thereby ensuring that the right people are placed in the right positions.

[0370] 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.

[0371] In this invention, the server includes means for receiving and analyzing corporate request information, means for receiving and storing individual applicant information, and means for performing sentiment analysis during online interviews and evaluating the applicant's emotional state. This enables more accurate candidate suitability assessment and recommendations based on corporate requirements, while also taking into account the applicant's emotional state.

[0372] "Company requirements information" refers to information about the ideal candidate profile, necessary skills, emotional adaptability, and communication abilities that a company seeks.

[0373] "Applicant's individual information" refers to data including the applicant's resume, skills data, and emotional data collected during the interview.

[0374] A "means for calculating suitability" refers to a method of evaluating how well an applicant is suited to a company, based on the company's requirements and the applicant's individual information.

[0375] "Selection methods" refer to methods for determining the most suitable candidate for a company based on the calculated suitability score.

[0376] "Methods for performing emotional analysis" refer to technologies that analyze the applicant's facial expressions and tone of voice during online interviews to evaluate their emotional state, such as stress levels and level of interest, in real time.

[0377] "Methods for adjusting the degree of fit" refer to techniques that modify conventional scores based on the results of sentiment analysis to perform optimal personnel evaluation.

[0378] "Methods for determining and recommending placement" refers to a method of suggesting departments or roles within the company where applicants can best utilize their abilities, based on their suitability.

[0379] The system for realizing this invention supports a talent selection process involving companies and applicants. This system consists of a server, terminals, and an emotion engine connected to them.

[0380] The server receives request information sent from companies and stores it in a database. This request information includes details about the type of person the company is looking for, such as emotional adaptability and communication skills. Based on this information, the server generates an ideal candidate profile.

[0381] The terminal processes the application history and skill data submitted by applicants. Furthermore, this information is stored in a database and assigned emotional data tags along with the regular application data tags. The emotional data tags are obtained during online interviews.

[0382] Applicants, acting as users, participate in online interviews. During these interviews, an emotion engine activates, analyzing the applicant's facial expressions and tone of voice in real time. This analysis process utilizes libraries such as OpenCV and TensorFlow to evaluate emotional states, including stress levels and interest levels. This information is then used to further refine the applicant's suitability for the position.

[0383] For example, if a candidate applying for a security-related position demonstrates a high level of composure during the interview, their suitability will be evaluated positively, and based on that, they may be recommended for placement in a specific department within the company.

[0384] An example of a prompt when applying a generative AI model is: "We will analyze the applicant's facial expression data and return scores for calmness, stress, and interest. These will be used to determine their appropriate placement." Through this prompt, it becomes possible to place candidates based on their emotional adaptability.

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server receives request information from companies. This information, provided by companies, is input and includes the ideal candidate profile, skills, and emotional adaptability requirements. The server stores this in a database and generates an ideal candidate profile. This profile is output as matching data in subsequent processing steps.

[0388] Step 2:

[0389] The terminal receives historical and skill data from applicants. Inputs include resumes and qualification certificates submitted by the applicants. The terminal analyzes this information, creates individual profiles, and stores them in a database. This profile outputs initial sentiment data tags along with the usual application information tags.

[0390] Step 3:

[0391] Applicants, acting as users, participate in online interviews. During the interview, an emotion engine operates, collecting and analyzing the applicant's facial expressions and voice tone in real time. The input for this engine is data acquired from the camera and microphone. Using libraries such as OpenCV and TensorFlow, stress levels and interest levels are scored. This scoring data is output as emotion data tags.

[0392] Step 4:

[0393] The server receives data from the emotion engine and recalculates the suitability based on the applicant's profile and the company's requirements. Emotional states are used as input to adjust the suitability evaluation. In this process, a generative AI model is used to output emotion analysis results based on prompt sentences.

[0394] Step 5:

[0395] The server proposes optimal departmental placements based on the re-evaluated suitability. The updated suitability score is the input, and recommended departments are analyzed based on it. Finally, the recommendation results are notified to the hiring manager, leading to appropriate talent placement.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] [Third Embodiment]

[0400] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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".

[0412] This invention provides a system for efficiently selecting and placing suitable personnel by matching the requirements of companies with the characteristics of applicants. This system centrally manages information gathering, analysis, suitability calculation, automation of interviews and tests, and final candidate selection and placement between companies and job seekers.

[0413] First, the server stores the request information received from the company in a database and uses an analysis engine to build a profile of the ideal candidate. This profile includes required skills, cultural adaptability, and communication abilities.

[0414] Next, the terminal receives resumes, qualifications, and skill assessment results entered by job seekers and stores them in a database as individual information. Each applicant's information is tagged and used in the subsequent matching process.

[0415] Furthermore, users (job seekers) participate in online interviews. During these interviews, a generating AI automatically asks questions and analyzes the applicants' responses. The server analyzes the interview and skills test results to calculate the job seeker's suitability.

[0416] The server then matches each job seeker's suitability score against the company's profile and lists the most suitable candidates. Furthermore, based on each applicant's characteristics, it recommends the most suitable job or department and outputs it as a plan.

[0417] For example, if a company is looking for a data scientist with global project experience, the server will receive this information and prioritize selecting candidates with experience in international projects or AI algorithm development from among the applicants. Furthermore, online interviews will assess English language proficiency and cultural adaptability.

[0418] In this way, companies can quickly and accurately recruit and appropriately assign the right talent for their purposes, improving overall recruitment efficiency.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] The server receives request information provided by companies. This includes details about required skills, company culture, and job responsibilities. This information is converted into a data format and stored in a database.

[0422] Step 2:

[0423] The server processes the received company request information into an analysis engine to generate an ideal candidate profile. This profile is structured to include required skills, years of experience, and personality traits.

[0424] Step 3:

[0425] The terminal receives personal information, resumes, and skills information entered by job seekers into the application system and stores it in a database. All information is tagged to enable efficient searching in subsequent processes.

[0426] Step 4:

[0427] The user (job seeker) receives an online interview link from the system and participates in the interview. During the interview, a generation AI generates questions and records the job seeker's responses.

[0428] Step 5:

[0429] The server analyzes information obtained through online interviews and tests to evaluate the applicant's characteristics and skill level. This evaluation is quantified and stored in a database.

[0430] Step 6:

[0431] The server compares the company's requirements with data obtained from job seekers and calculates a suitability score. This score indicates how well the job seeker matches the company's requirements.

[0432] Step 7:

[0433] The server selects the most suitable candidates based on the calculated suitability scores and creates a list. It also recommends the most appropriate placement for the job offered by the company and reports this to the company in a report format.

[0434] These specific processing steps enable the system to efficiently and accurately select and assign the most suitable personnel for the company.

[0435] (Example 1)

[0436] 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."

[0437] Quickly and accurately selecting and appropriately placing the talent an organization needs is a crucial challenge in efficient talent management. However, traditional systems struggle to effectively match applicant information with company requirements, resulting in time-consuming and labor-intensive processes. Furthermore, there is a lack of systems capable of automating online interviews and skills tests, and conducting appropriate talent evaluations based on these results. As a result, companies are expending considerable effort to find the best candidates.

[0438] 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.

[0439] In this invention, the server includes means for acquiring and analyzing organizational requirements information, means for collecting and storing applicant attribute information, and means for analyzing responses using a generative model. This enables automatic matching of applicant characteristics with organizational requirements, and allows for highly accurate suitability assessments based on interview and test results. As a result, organizations can significantly improve the efficiency of their talent selection process.

[0440] An "organization" refers to a company or group that needs or seeks human resources.

[0441] "Requirements information" refers to information about the skills, experience, and abilities that an organization requires for a particular job.

[0442] "Analysis" is the process of extracting meaningful knowledge from collected data.

[0443] An "applicant" is a person who expresses interest in a job at an organization and seeks employment.

[0444] "Attribute information" refers to information about the applicant's skills, qualifications, experience, and other characteristics.

[0445] The "fit index" is a numerical value that indicates how well an organization's requirements match the attributes of an applicant.

[0446] "Selection" means determining the most suitable candidate based on their degree of suitability.

[0447] "Assignment" refers to assigning selected personnel to specific duties or roles.

[0448] A "generative model" is software that uses natural language processing and machine learning to generate and analyze information in a way that mimics human behavior.

[0449] "Online communication" refers to interviews or conversations conducted via the internet.

[0450] This invention provides a system for efficiently selecting and optimally assigning personnel to organizations. Specifically, the server, terminal, and user elements collaborate to collect, analyze, and match information.

[0451] The server receives organizational request information via the network and stores it in a database. This data is analyzed using a parsing engine that enables natural language processing. Software such as NLTK and SpaCy, implemented in Python, are used as the parsing engine. The analyzed information is constructed in JSON format as a clear profile of the desired personnel.

[0452] The terminal receives resumes and qualification information entered by applicants via web forms. This information is scanned using OCR technology and stored as text data in a database. Tesseract OCR is a possible software used for this process. The terminal can tag the entered information to facilitate subsequent matching.

[0453] The user (job seeker) participates in an online interview. In this interview, a generative AI model automatically generates questions using prompts. For example, it might use a prompt such as, "Please tell me more about your experience in international projects." The user's answers to the generated questions are transcribed in real time using speech recognition technology. The Google Speech-to-Text API is used for speech recognition. Based on these results, the server calculates a suitability score and compares it to the organization's profile to list the most suitable candidates.

[0454] For example, if a company is seeking a data scientist, the server can analyze the requirements and prioritize applicants with international project experience and knowledge of AI algorithms. The AI ​​used in online interviews automatically assesses the applicant's English language proficiency. In this way, organizations can quickly identify suitable talent and achieve efficient placement.

[0455] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0456] Step 1:

[0457] The server receives request information from organizations via the network. Specifically, job postings received via an HTTP API are stored in the database as JSON data. The job postings, as input, include required skills, experience, and characteristics. The server uses a natural language processing engine (e.g., NLTK or SpaCy) to analyze the information and generates profiles of the desired personnel as output.

[0458] Step 2:

[0459] The terminal collects resumes and qualification information submitted by job seekers. Applicants provide this information digitally via an input form. The entered information is scanned using OCR technology (e.g., Tesseract OCR) and stored in a database as text data. At this time, the terminal tags attribute information to streamline subsequent matching. The output is a dataset of tagged attribute information.

[0460] Step 3:

[0461] The server matches the organization's profile with the applicant's attribute information. Using natural language processing algorithms, it evaluates the degree of skill and experience match from the input data. This calculates a suitability index and outputs a ranking of candidates. This output forms the basis for the subsequent selection process.

[0462] Step 4:

[0463] The user (job seeker) participates in an online interview using a generative AI model. The generative AI model automatically generates pre-set prompts (e.g., "Tell me about your project experience") and presents them to the user. The user's responses are transcribed in real time using speech recognition technology (e.g., Google Speech-to-Text API) and sent to the server. The input is the user's voice response, and the output is the transcribed response.

[0464] Step 5:

[0465] The server integrates interview results and skills test results to ultimately calculate the degree of suitability. It then implements multi-criteria analysis and uses the suitability index to generate a list of optimal candidates, which is then submitted to the organization. This results in a final list of candidates and recommendations for optimal placement.

[0466] (Application Example 1)

[0467] 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."

[0468] The appropriate allocation of personnel and machinery within a company is crucial for improving productivity and efficiency. However, traditional processes for selecting personnel and allocating machinery are often manual, making them time-consuming and costly. Furthermore, matching the characteristics of applicants with the company's needs and accurately evaluating the operational status of machinery are challenging.

[0469] 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.

[0470] In this invention, the server includes means for receiving and analyzing corporate request information, means for receiving and storing individual applicant information, means for comparing the corporate request information with the individual applicant information and calculating a degree of suitability, means for selecting the most suitable candidate based on the generated degree of suitability, means for determining and recommending the placement of the selected candidate, means for collecting and analyzing machine operation data, and means for evaluating the machine operation efficiency based on the analysis results and assigning the most suitable tasks. This enables the appropriate selection and placement of personnel and machines based on the needs of the company.

[0471] "Corporate requirements information" refers to data that specifically outlines the skills, experience, and characteristics that a company requires for a particular role or task.

[0472] "Applicant's individual information" refers to data that shows the individual characteristics of job seekers, such as resumes, qualifications, and skill assessment results.

[0473] "Methods for calculating suitability" refer to methods that analyze the company's requirements information and the applicant's individual information, and quantify the degree of matching.

[0474] "A method for selecting the optimal candidate" is a method of choosing the person best suited for the required role based on the calculated suitability score.

[0475] "Means for determining and recommending candidate placement" refers to a process that provides guidelines for assigning selected candidates to appropriate roles and departments within a company.

[0476] "Operational data" refers to all detection information generated by machines and robots during operation, and it serves as the basis for evaluating the performance and status of the machine.

[0477] "Means for evaluating operational efficiency and assigning optimal tasks" refers to a method that determines the efficiency of a machine based on analyzed operational data and automatically selects appropriate work content.

[0478] The server records the requirements information provided by the company in a database and uses an analysis engine to form a model of the ideal candidate. This model includes elements such as required skills, experience, and cultural adaptability. The hardware used includes high-performance processors and storage installed in a data center. For software, Python is used for data analysis and MySQL is used for the database management system.

[0479] On the other hand, the terminal receives information such as resumes and skills test results submitted online by job seekers. This information is stored in a database and tagged. In this process, applicant information is prepared for analysis on the server.

[0480] Furthermore, job seekers, as users, undergo online interviews where they answer questions generated by AI. Based on this response analysis, the server analyzes the interview results and skills test results to calculate each job seeker's suitability. A machine learning model using TensorFlow is utilized in this analysis process.

[0481] For example, when a machine's performance deteriorates, collecting its operational data reveals that wear and tear on parts is the cause. Based on this information, maintenance is recommended, and appropriate resources are reallocated.

[0482] An example of a prompt message for the generated AI model is, "Analyze the cause of the decreased efficiency of SN123-Robo and propose the optimal maintenance task." In this way, data exchange and appropriate processing are achieved between the server, terminal, and user.

[0483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0484] Step 1:

[0485] The server receives request information provided by companies. As input, it receives information about the skills, experience, and characteristics that companies are looking for. This information is stored in a database, and an analysis engine is used to build a model of suitable candidates. This model quantifies the necessary characteristics based on the received attribute information and generates a profile.

[0486] Step 2:

[0487] The terminal receives resumes and qualification information from job seekers online. This input data is individually tagged and stored in a database. This makes the characteristics of each applicant immediately clear, preparing them for matching in later processes.

[0488] Step 3:

[0489] The job seeker, as the user, participates in an online interview. Here, they answer questions based on prompts provided by, for example, a generative AI model. This interview data is received by a server, where the answers are analyzed. Based on the provided answers, communication skills, adaptability, and other factors are evaluated, and a goodness-of-fit score is calculated as output.

[0490] Step 4:

[0491] The server compares the company profile generated in Step 1 with the suitability score of each applicant calculated in Step 3. Utilizing the information stored in the database, it performs quantitative matching to extract the most suitable candidates. The output is a list of the most suitable individuals.

[0492] Step 5:

[0493] The server ultimately creates a placement plan that recommends job roles and work locations based on the selected personnel. It uses the company's organizational structure and position information as input to calculate appropriate placements. The output is a detailed plan including recommended placements.

[0494] Step 6:

[0495] The server continuously receives and analyzes machine operation data. Sensor data and operation logs are provided as input, and the analysis engine evaluates the operational efficiency. Based on this efficiency, it proposes regular machine maintenance and optimal task reassignment. The output is a concrete action plan to improve efficiency.

[0496] 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.

[0497] This invention aims to achieve a more accurate talent selection process by incorporating emotion recognition technology into a system that matches corporate requirements with the characteristics of applicants. The system consists of the following elements:

[0498] First, the server receives request information from companies and stores it in a database. The company profile contains details about the ideal candidate they are looking for, including emotional adaptability and communication skills. The analysis engine uses this information to generate an ideal candidate profile.

[0499] Next, the terminal receives input from applicants, such as history information and skill data, and stores the individual information in a database. This data is tagged with sentiment data tags along with the usual application information tags.

[0500] The user (job seeker) participates in an online interview conducted by the system. During this interview, an emotion engine activates, analyzing the candidate's emotional state in real time based on their facial expressions, tone of voice, and speech content. This allows for the extraction of indicators such as the user's stress level, level of interest, and sincerity.

[0501] The server analyzes emotional data obtained from online interviews along with regular evaluation data to calculate the overall suitability of the job seeker. In this process, it assesses how emotions affect the applicant in specific situations and contributes to the estimation of cultural adaptability and interpersonal skills.

[0502] Furthermore, the server uses the suitability derived from emotional characteristics to perform optimal matching with company requirements and proposes provisional placements for candidates. This allows companies to find highly suitable personnel for appropriate environments, and is expected to significantly improve the success rate of recruitment.

[0503] For example, if a company prioritizes the ability to cope with high-stress environments, the Emotion Engine evaluates the applicant's stress indicators during online interviews and reflects this as a score. As a result, the applicant is recommended as a high-stress adaptable candidate, and placement in the appropriate department becomes more effective.

[0504] Technically, this system is realized by combining existing database management technology, generative AI, and sentiment analysis technology, and is particularly effective in improving accuracy during the selection process.

[0505] The following describes the processing flow.

[0506] Step 1:

[0507] The server receives request information from companies and forwards it to the analysis engine. Here, data on the skills, characteristics, and cultural adaptability required by the companies is stored in a database, and the necessary profiles are created.

[0508] Step 2:

[0509] The terminal receives personal information, resumes, and qualification data entered by job seekers and registers them in a database. At this point, skill tags and experience tags are assigned to the applicant's information and used in subsequent processing.

[0510] Step 3:

[0511] The user (job seeker) participates in an online interview with an integrated emotion engine. Here, facial expressions and voice are analyzed from the video feed to generate emotion recognition data.

[0512] Step 4:

[0513] The server sends emotional data obtained from online interviews to an analysis engine, which, along with the content of the responses, evaluates the job seeker's personality. This makes it possible to quantitatively assess the job seeker's interpersonal skills and stress tolerance.

[0514] Step 5:

[0515] The server calculates a suitability score for each candidate based on the analysis results. This score is based on both skills information and sentiment data, providing a more comprehensive evaluation.

[0516] Step 6:

[0517] The server lists the most suitable candidates based on their suitability scores and generates matching results for the company's talent requirements. This includes estimations of cultural adaptability and communication skills based on emotional states.

[0518] Step 7:

[0519] The server sends the final candidate list and recommended placement plans to the company. This allows the company to make personnel placement decisions that take emotional adaptability into consideration.

[0520] This process enables more precise matching and candidate selection using an emotion engine, contributing to an improved recruitment success rate.

[0521] (Example 2)

[0522] 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."

[0523] Traditional talent selection systems calculated suitability based only on company requirements and basic individual information of applicants, making it difficult to select the right talent. Furthermore, they failed to consider emotional states and their changes, potentially overlooking important factors such as integrity and stress tolerance. There is a need to address these challenges and achieve more accurate talent selection.

[0524] 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.

[0525] In this invention, the server includes means for storing corporate request information in a data storage means, means for analyzing user emotional information during online interviews, and means for selecting the most suitable candidate using a generative AI model. This enables highly accurate matching by combining corporate requirements with the emotional characteristics of applicants.

[0526] "Company requirements information" refers to detailed information about the ideal candidate that a company is looking for, including job responsibilities, necessary skills, emotional adaptability, and communication skills.

[0527] "Resume information" refers to information that shows the applicant's past experience and achievements, such as their educational background, work history, and qualifications.

[0528] "Skill data" refers to information about the applicant's skills and abilities, including specialized knowledge required for a specific job or industry.

[0529] "Data storage means" refers to a recording device or medium for storing received information, and includes database systems and the like.

[0530] "Emotional information" refers to information about the applicant's psychological and emotional state obtained from their facial expressions, tone of voice, and speech content during online interviews.

[0531] An "online interview" refers to a remote interview or meeting conducted via the internet, providing an opportunity to observe the applicant's real-time responses.

[0532] "Fit" is an indicator that shows how well an applicant's characteristics and skills match the company's requirements.

[0533] A "generative AI model" is an artificial intelligence program used to select the most suitable candidates based on collected data.

[0534] "Candidate placement" refers to assigning selected candidates to the most suitable roles or departments.

[0535] "Recommendation" is the act of communicating that a proposed item or option is the best choice.

[0536] This invention is a talent selection system for accurately matching corporate requirements with the characteristics of applicants. This system mainly consists of three components: a server, terminals, and users.

[0537] The server receives request information from companies through an interface and stores it in a data storage device. The stored information is managed as a company profile, including job description, required skills, emotional adaptability, and communication abilities. The server uses database management systems such as MySQL or PostgreSQL to store and manage the data.

[0538] The terminal is used to receive historical information and skill data from applicants. When collecting information through web forms and applications and storing it in a database, sentiment data tags are added to generate richer applicant profiles. For example, if an applicant's specific technical skills are evaluated, a corresponding tag is assigned.

[0539] When users (job seekers) participate in online interviews, their emotional state is analyzed in real time via an emotion engine. This involves video calls using technologies such as WebRTC, and further utilizes OpenCV for facial expression analysis and the Python Librosa library for voice tone analysis. This allows for the analysis of indicators such as stress level, level of interest, and sincerity based on the user's facial expressions, voice tone, and spoken content.

[0540] To select the most suitable candidates, the server uses a generative AI model. This calculates a degree of suitability based on applicant sentiment information, historical information, and company requirements. Machine learning libraries such as scikit-learn are used, and statistical models are employed for analysis.

[0541] For example, if a company is looking for "personnel who can adapt to working in a high-stress environment," the server uses an emotion engine to evaluate the applicant's stress tolerance and scores the result. This information is then input into a generative AI model, which generates prompts such as, "Consider the data on stress tolerance and suggest a way to match the company's requirements with the applicants," thereby assisting the AI's decision-making.

[0542] Through such a system, companies can obtain highly accurate talent matching, significantly improving the efficiency and effectiveness of their recruitment process.

[0543] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0544] Step 1:

[0545] The server receives request information from companies. Companies send information such as job descriptions, required skills, and desired characteristics via API. The server receives this information and stores it in a database. At this time, a MySQL database is used to organize the information and prepare it for later analysis. The received information includes job descriptions and ideal applicant profiles, and the server stores this information as structured data. The output is the company profile information stored in the database.

[0546] Step 2:

[0547] The terminal receives historical and skill data from applicants. Users input this information through a web form. The terminal tags the application information with emotional data and stores it in a database. In this process, emotional tags (e.g., communication skills) are provided along with regular application information (e.g., education and work history). The input is the applicant's basic information, and the output is a tagged applicant profile.

[0548] Step 3:

[0549] The user (job seeker) participates in an online interview. During this interview, the user's facial expressions, voice tone, and speech content are captured in real time and analyzed by an emotion engine. This process involves a video call via WebRTC. OpenCV is used for emotion analysis, and Librosa is used for voice tone analysis. The input is video call data, and the output is an emotion index indicating the user's stress level and level of interest.

[0550] Step 4:

[0551] The server receives sentiment data obtained from online interviews and integrates it with regular application information to calculate the applicant's suitability. The server utilizes scikit-learn and machine learning algorithms to analyze the suitability. In this process, all data is evaluated by statistical models, and the system obtains foundational information for selecting the most suitable candidates. The input is the integrated applicant data, and the output is the calculated suitability score.

[0552] Step 5:

[0553] The server uses a generative AI model to select the best candidates based on their fit. The AI ​​model analyzes the received data and generates prompts such as, "Consider data on stress tolerance and suggest how to match applicants with company requirements." Through this process, the AI ​​lists the best candidates and provides recommendations to the company. The input is the fit score, and the output is the final candidate list.

[0554] Step 6:

[0555] The server proposes provisional placements for selected candidates. Based on the candidate list generated by the AI ​​model, the server recommends appropriate placements to the company. This includes a process of communicating the results to the company via a notification system. The output is information on the provisional placement proposals sent to the company.

[0556] (Application Example 2)

[0557] 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."

[0558] In a company's recruitment process, the challenge is to improve the success rate of recruitment by enabling a comprehensive aptitude assessment based not only on applicants' skills and work history, but also on their emotional state, thereby ensuring that the right people are placed in the right positions.

[0559] 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.

[0560] In this invention, the server includes means for receiving and analyzing corporate request information, means for receiving and storing individual applicant information, and means for performing sentiment analysis during online interviews and evaluating the applicant's emotional state. This enables more accurate candidate suitability assessment and recommendations based on corporate requirements, while also taking into account the applicant's emotional state.

[0561] "Company requirements information" refers to information about the ideal candidate profile, necessary skills, emotional adaptability, and communication abilities that a company seeks.

[0562] "Applicant's individual information" refers to data including the applicant's resume, skills data, and emotional data collected during the interview.

[0563] A "means for calculating suitability" refers to a method of evaluating how well an applicant is suited to a company, based on the company's requirements and the applicant's individual information.

[0564] "Selection methods" refer to methods for determining the most suitable candidate for a company based on the calculated suitability score.

[0565] "Methods for performing emotional analysis" refer to technologies that analyze the applicant's facial expressions and tone of voice during online interviews to evaluate their emotional state, such as stress levels and level of interest, in real time.

[0566] "Methods for adjusting the degree of fit" refer to techniques that modify conventional scores based on the results of sentiment analysis to perform optimal personnel evaluation.

[0567] "Methods for determining and recommending placement" refers to a method of suggesting departments or roles within the company where applicants can best utilize their abilities, based on their suitability.

[0568] The system for realizing this invention supports a talent selection process involving companies and applicants. This system consists of a server, terminals, and an emotion engine connected to them.

[0569] The server receives request information sent from companies and stores it in a database. This request information includes details about the type of person the company is looking for, such as emotional adaptability and communication skills. Based on this information, the server generates an ideal candidate profile.

[0570] The terminal processes the application history and skill data submitted by applicants. Furthermore, this information is stored in a database and assigned emotional data tags along with the regular application data tags. The emotional data tags are obtained during online interviews.

[0571] Applicants, acting as users, participate in online interviews. During these interviews, an emotion engine activates, analyzing the applicant's facial expressions and tone of voice in real time. This analysis process utilizes libraries such as OpenCV and TensorFlow to evaluate emotional states, including stress levels and interest levels. This information is then used to further refine the applicant's suitability for the position.

[0572] For example, if a candidate applying for a security-related position demonstrates a high level of composure during the interview, their suitability will be evaluated positively, and based on that, they may be recommended for placement in a specific department within the company.

[0573] An example of a prompt when applying a generative AI model is: "We will analyze the applicant's facial expression data and return scores for calmness, stress, and interest. These will be used to determine their appropriate placement." Through this prompt, it becomes possible to place candidates based on their emotional adaptability.

[0574] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0575] Step 1:

[0576] The server receives request information from companies. This information, provided by companies, is input and includes the ideal candidate profile, skills, and emotional adaptability requirements. The server stores this in a database and generates an ideal candidate profile. This profile is output as matching data in subsequent processing steps.

[0577] Step 2:

[0578] The terminal receives historical and skill data from applicants. Inputs include resumes and qualification certificates submitted by the applicants. The terminal analyzes this information, creates individual profiles, and stores them in a database. This profile outputs initial sentiment data tags along with the usual application information tags.

[0579] Step 3:

[0580] Applicants, acting as users, participate in online interviews. During the interview, an emotion engine operates, collecting and analyzing the applicant's facial expressions and voice tone in real time. The input for this engine is data acquired from the camera and microphone. Using libraries such as OpenCV and TensorFlow, stress levels and interest levels are scored. This scoring data is output as emotion data tags.

[0581] Step 4:

[0582] The server receives data from the emotion engine and recalculates the suitability based on the applicant's profile and the company's requirements. Emotional states are used as input to adjust the suitability evaluation. In this process, a generative AI model is used to output emotion analysis results based on prompt sentences.

[0583] Step 5:

[0584] The server proposes optimal departmental placements based on the re-evaluated suitability. The updated suitability score is the input, and recommended departments are analyzed based on it. Finally, the recommendation results are notified to the hiring manager, leading to appropriate talent placement.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] [Fourth Embodiment]

[0589] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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).

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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".

[0602] This invention provides a system for efficiently selecting and placing suitable personnel by matching the requirements of companies with the characteristics of applicants. This system centrally manages information gathering, analysis, suitability calculation, automation of interviews and tests, and final candidate selection and placement between companies and job seekers.

[0603] First, the server stores the request information received from the company in a database and uses an analysis engine to build a profile of the ideal candidate. This profile includes required skills, cultural adaptability, and communication abilities.

[0604] Next, the terminal receives resumes, qualifications, and skill assessment results entered by job seekers and stores them in a database as individual information. Each applicant's information is tagged and used in the subsequent matching process.

[0605] Furthermore, users (job seekers) participate in online interviews. During these interviews, a generating AI automatically asks questions and analyzes the applicants' responses. The server analyzes the interview and skills test results to calculate the job seeker's suitability.

[0606] The server then matches each job seeker's suitability score against the company's profile and lists the most suitable candidates. Furthermore, based on each applicant's characteristics, it recommends the most suitable job or department and outputs it as a plan.

[0607] For example, if a company is looking for a data scientist with global project experience, the server will receive this information and prioritize selecting candidates with experience in international projects or AI algorithm development from among the applicants. Furthermore, online interviews will assess English language proficiency and cultural adaptability.

[0608] In this way, companies can quickly and accurately recruit and appropriately assign the right talent for their purposes, improving overall recruitment efficiency.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] The server receives request information provided by companies. This includes details about required skills, company culture, and job responsibilities. This information is converted into a data format and stored in a database.

[0612] Step 2:

[0613] The server processes the received company request information into an analysis engine to generate an ideal candidate profile. This profile is structured to include required skills, years of experience, and personality traits.

[0614] Step 3:

[0615] The terminal receives personal information, resumes, and skills information entered by job seekers into the application system and stores it in a database. All information is tagged to enable efficient searching in subsequent processes.

[0616] Step 4:

[0617] The user (job seeker) receives an online interview link from the system and participates in the interview. During the interview, a generation AI generates questions and records the job seeker's responses.

[0618] Step 5:

[0619] The server analyzes information obtained through online interviews and tests to evaluate the applicant's characteristics and skill level. This evaluation is quantified and stored in a database.

[0620] Step 6:

[0621] The server compares the company's requirements with data obtained from job seekers and calculates a suitability score. This score indicates how well the job seeker matches the company's requirements.

[0622] Step 7:

[0623] The server selects the most suitable candidates based on the calculated suitability scores and creates a list. It also recommends the most appropriate placement for the job offered by the company and reports this to the company in a report format.

[0624] These specific processing steps enable the system to efficiently and accurately select and assign the most suitable personnel for the company.

[0625] (Example 1)

[0626] 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".

[0627] Quickly and accurately selecting and appropriately placing the talent an organization needs is a crucial challenge in efficient talent management. However, traditional systems struggle to effectively match applicant information with company requirements, resulting in time-consuming and labor-intensive processes. Furthermore, there is a lack of systems capable of automating online interviews and skills tests, and conducting appropriate talent evaluations based on these results. As a result, companies are expending considerable effort to find the best candidates.

[0628] 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.

[0629] In this invention, the server includes means for acquiring and analyzing organizational requirements information, means for collecting and storing applicant attribute information, and means for analyzing responses using a generative model. This enables automatic matching of applicant characteristics with organizational requirements, and allows for highly accurate suitability assessments based on interview and test results. As a result, organizations can significantly improve the efficiency of their talent selection process.

[0630] An "organization" refers to a company or group that needs or seeks human resources.

[0631] "Requirements information" refers to information about the skills, experience, and abilities that an organization requires for a particular job.

[0632] "Analysis" is the process of extracting meaningful knowledge from collected data.

[0633] An "applicant" is a person who expresses interest in a job at an organization and seeks employment.

[0634] "Attribute information" refers to information about the applicant's skills, qualifications, experience, and other characteristics.

[0635] The "fit index" is a numerical value that indicates how well an organization's requirements match the attributes of an applicant.

[0636] "Selection" means determining the most suitable candidate based on their degree of suitability.

[0637] "Assignment" refers to assigning selected personnel to specific duties or roles.

[0638] A "generative model" is software that uses natural language processing and machine learning to generate and analyze information in a way that mimics human behavior.

[0639] "Online communication" refers to interviews or conversations conducted via the internet.

[0640] This invention provides a system for efficiently selecting and optimally assigning personnel to organizations. Specifically, the server, terminal, and user elements collaborate to collect, analyze, and match information.

[0641] The server receives organizational request information via the network and stores it in a database. This data is analyzed using a parsing engine that enables natural language processing. Software such as NLTK and SpaCy, implemented in Python, are used as the parsing engine. The analyzed information is constructed in JSON format as a clear profile of the desired personnel.

[0642] The terminal receives resumes and qualification information entered by applicants via web forms. This information is scanned using OCR technology and stored as text data in a database. Tesseract OCR is a possible software used for this process. The terminal can tag the entered information to facilitate subsequent matching.

[0643] The user (job seeker) participates in an online interview. In this interview, a generative AI model automatically generates questions using prompts. For example, it might use a prompt such as, "Please tell me more about your experience in international projects." The user's answers to the generated questions are transcribed in real time using speech recognition technology. The Google Speech-to-Text API is used for speech recognition. Based on these results, the server calculates a suitability score and compares it to the organization's profile to list the most suitable candidates.

[0644] For example, if a company is seeking a data scientist, the server can analyze the requirements and prioritize applicants with international project experience and knowledge of AI algorithms. The AI ​​used in online interviews automatically assesses the applicant's English language proficiency. In this way, organizations can quickly identify suitable talent and achieve efficient placement.

[0645] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0646] Step 1:

[0647] The server receives request information from organizations via the network. Specifically, job postings received via an HTTP API are stored in the database as JSON data. The job postings, as input, include required skills, experience, and characteristics. The server uses a natural language processing engine (e.g., NLTK or SpaCy) to analyze the information and generates profiles of the desired personnel as output.

[0648] Step 2:

[0649] The terminal collects resumes and qualification information submitted by job seekers. Applicants provide this information digitally via an input form. The entered information is scanned using OCR technology (e.g., Tesseract OCR) and stored in a database as text data. At this time, the terminal tags attribute information to streamline subsequent matching. The output is a dataset of tagged attribute information.

[0650] Step 3:

[0651] The server matches the organization's profile with the applicant's attribute information. Using natural language processing algorithms, it evaluates the degree of skill and experience match from the input data. This calculates a suitability index and outputs a ranking of candidates. This output forms the basis for the subsequent selection process.

[0652] Step 4:

[0653] The user (job seeker) participates in an online interview using a generative AI model. The generative AI model automatically generates pre-set prompts (e.g., "Tell me about your project experience") and presents them to the user. The user's responses are transcribed in real time using speech recognition technology (e.g., Google Speech-to-Text API) and sent to the server. The input is the user's voice response, and the output is the transcribed response.

[0654] Step 5:

[0655] The server integrates interview results and skills test results to ultimately calculate the degree of suitability. It then implements multi-criteria analysis and uses the suitability index to generate a list of optimal candidates, which is then submitted to the organization. This results in a final list of candidates and recommendations for optimal placement.

[0656] (Application Example 1)

[0657] 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".

[0658] The appropriate allocation of personnel and machinery within a company is crucial for improving productivity and efficiency. However, traditional processes for selecting personnel and allocating machinery are often manual, making them time-consuming and costly. Furthermore, matching the characteristics of applicants with the company's needs and accurately evaluating the operational status of machinery are challenging.

[0659] 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.

[0660] In this invention, the server includes means for receiving and analyzing corporate request information, means for receiving and storing individual applicant information, means for comparing the corporate request information with the individual applicant information and calculating a degree of suitability, means for selecting the most suitable candidate based on the generated degree of suitability, means for determining and recommending the placement of the selected candidate, means for collecting and analyzing machine operation data, and means for evaluating the machine operation efficiency based on the analysis results and assigning the most suitable tasks. This enables the appropriate selection and placement of personnel and machines based on the needs of the company.

[0661] "Corporate requirements information" refers to data that specifically outlines the skills, experience, and characteristics that a company requires for a particular role or task.

[0662] "Applicant's individual information" refers to data that shows the individual characteristics of job seekers, such as resumes, qualifications, and skill assessment results.

[0663] "Methods for calculating suitability" refer to methods that analyze the company's requirements information and the applicant's individual information, and quantify the degree of matching.

[0664] "A method for selecting the optimal candidate" is a method of choosing the person best suited for the required role based on the calculated suitability score.

[0665] "Means for determining and recommending candidate placement" refers to a process that provides guidelines for assigning selected candidates to appropriate roles and departments within a company.

[0666] "Operational data" refers to all detection information generated by machines and robots during operation, and it serves as the basis for evaluating the performance and status of the machine.

[0667] "Means for evaluating operational efficiency and assigning optimal tasks" refers to a method that determines the efficiency of a machine based on analyzed operational data and automatically selects appropriate work content.

[0668] The server records the requirements information provided by the company in a database and uses an analysis engine to form a model of the ideal candidate. This model includes elements such as required skills, experience, and cultural adaptability. The hardware used includes high-performance processors and storage installed in a data center. For software, Python is used for data analysis and MySQL is used for the database management system.

[0669] On the other hand, the terminal receives information such as resumes and skills test results submitted online by job seekers. This information is stored in a database and tagged. In this process, applicant information is prepared for analysis on the server.

[0670] Furthermore, job seekers, as users, undergo online interviews where they answer questions generated by AI. Based on this response analysis, the server analyzes the interview results and skills test results to calculate each job seeker's suitability. A machine learning model using TensorFlow is utilized in this analysis process.

[0671] For example, when a machine's performance deteriorates, collecting its operational data reveals that wear and tear on parts is the cause. Based on this information, maintenance is recommended, and appropriate resources are reallocated.

[0672] An example of a prompt message for the generated AI model is, "Analyze the cause of the decreased efficiency of SN123-Robo and propose the optimal maintenance task." In this way, data exchange and appropriate processing are achieved between the server, terminal, and user.

[0673] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0674] Step 1:

[0675] The server receives request information provided by companies. As input, it receives information about the skills, experience, and characteristics that companies are looking for. This information is stored in a database, and an analysis engine is used to build a model of suitable candidates. This model quantifies the necessary characteristics based on the received attribute information and generates a profile.

[0676] Step 2:

[0677] The terminal receives resumes and qualification information from job seekers online. This input data is individually tagged and stored in a database. This makes the characteristics of each applicant immediately clear, preparing them for matching in later processes.

[0678] Step 3:

[0679] The job seeker, as the user, participates in an online interview. Here, they answer questions based on prompts provided by, for example, a generative AI model. This interview data is received by a server, where the answers are analyzed. Based on the provided answers, communication skills, adaptability, and other factors are evaluated, and a goodness-of-fit score is calculated as output.

[0680] Step 4:

[0681] The server compares the company profile generated in Step 1 with the suitability score of each applicant calculated in Step 3. Utilizing the information stored in the database, it performs quantitative matching to extract the most suitable candidates. The output is a list of the most suitable individuals.

[0682] Step 5:

[0683] The server ultimately creates a placement plan that recommends job roles and work locations based on the selected personnel. It uses the company's organizational structure and position information as input to calculate appropriate placements. The output is a detailed plan including recommended placements.

[0684] Step 6:

[0685] The server continuously receives and analyzes machine operation data. Sensor data and operation logs are provided as input, and the analysis engine evaluates the operational efficiency. Based on this efficiency, it proposes regular machine maintenance and optimal task reassignment. The output is a concrete action plan to improve efficiency.

[0686] 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.

[0687] This invention aims to achieve a more accurate talent selection process by incorporating emotion recognition technology into a system that matches corporate requirements with the characteristics of applicants. The system consists of the following elements:

[0688] First, the server receives request information from companies and stores it in a database. The company profile contains details about the ideal candidate they are looking for, including emotional adaptability and communication skills. The analysis engine uses this information to generate an ideal candidate profile.

[0689] Next, the terminal receives input from applicants, such as history information and skill data, and stores the individual information in a database. This data is tagged with sentiment data tags along with the usual application information tags.

[0690] The user (job seeker) participates in an online interview conducted by the system. During this interview, an emotion engine activates, analyzing the candidate's emotional state in real time based on their facial expressions, tone of voice, and speech content. This allows for the extraction of indicators such as the user's stress level, level of interest, and sincerity.

[0691] The server analyzes emotional data obtained from online interviews along with regular evaluation data to calculate the overall suitability of the job seeker. In this process, it assesses how emotions affect the applicant in specific situations and contributes to the estimation of cultural adaptability and interpersonal skills.

[0692] Furthermore, the server uses the suitability derived from emotional characteristics to perform optimal matching with company requirements and proposes provisional placements for candidates. This allows companies to find highly suitable personnel for appropriate environments, and is expected to significantly improve the success rate of recruitment.

[0693] For example, if a company prioritizes the ability to cope with high-stress environments, the Emotion Engine evaluates the applicant's stress indicators during online interviews and reflects this as a score. As a result, the applicant is recommended as a high-stress adaptable candidate, and placement in the appropriate department becomes more effective.

[0694] Technically, this system is realized by combining existing database management technology, generative AI, and sentiment analysis technology, and is particularly effective in improving accuracy during the selection process.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] The server receives request information from companies and forwards it to the analysis engine. Here, data on the skills, characteristics, and cultural adaptability required by the companies is stored in a database, and the necessary profiles are created.

[0698] Step 2:

[0699] The terminal receives personal information, resumes, and qualification data entered by job seekers and registers them in a database. At this point, skill tags and experience tags are assigned to the applicant's information and used in subsequent processing.

[0700] Step 3:

[0701] The user (job seeker) participates in an online interview with an integrated emotion engine. Here, facial expressions and voice are analyzed from the video feed to generate emotion recognition data.

[0702] Step 4:

[0703] The server sends emotional data obtained from online interviews to an analysis engine, which, along with the content of the responses, evaluates the job seeker's personality. This makes it possible to quantitatively assess the job seeker's interpersonal skills and stress tolerance.

[0704] Step 5:

[0705] The server calculates a suitability score for each candidate based on the analysis results. This score is based on both skills information and sentiment data, providing a more comprehensive evaluation.

[0706] Step 6:

[0707] The server lists the most suitable candidates based on their suitability scores and generates matching results for the company's talent requirements. This includes estimations of cultural adaptability and communication skills based on emotional states.

[0708] Step 7:

[0709] The server sends the final candidate list and recommended placement plans to the company. This allows the company to make personnel placement decisions that take emotional adaptability into consideration.

[0710] This process enables more precise matching and candidate selection using an emotion engine, contributing to an improved recruitment success rate.

[0711] (Example 2)

[0712] 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".

[0713] Traditional talent selection systems calculated suitability based only on company requirements and basic individual information of applicants, making it difficult to select the right talent. Furthermore, they failed to consider emotional states and their changes, potentially overlooking important factors such as integrity and stress tolerance. There is a need to address these challenges and achieve more accurate talent selection.

[0714] 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.

[0715] In this invention, the server includes means for storing corporate request information in a data storage means, means for analyzing user emotional information during online interviews, and means for selecting the most suitable candidate using a generative AI model. This enables highly accurate matching by combining corporate requirements with the emotional characteristics of applicants.

[0716] "Company requirements information" refers to detailed information about the ideal candidate that a company is looking for, including job responsibilities, necessary skills, emotional adaptability, and communication skills.

[0717] "Resume information" refers to information that shows the applicant's past experience and achievements, such as their educational background, work history, and qualifications.

[0718] "Skill data" refers to information about the applicant's skills and abilities, including specialized knowledge required for a specific job or industry.

[0719] "Data storage means" refers to a recording device or medium for storing received information, and includes database systems and the like.

[0720] "Emotional information" refers to information about the applicant's psychological and emotional state obtained from their facial expressions, tone of voice, and speech content during online interviews.

[0721] An "online interview" refers to a remote interview or meeting conducted via the internet, providing an opportunity to observe the applicant's real-time responses.

[0722] "Fit" is an indicator that shows how well an applicant's characteristics and skills match the company's requirements.

[0723] A "generative AI model" is an artificial intelligence program used to select the most suitable candidates based on collected data.

[0724] "Candidate placement" refers to assigning selected candidates to the most suitable roles or departments.

[0725] "Recommendation" is the act of communicating that a proposed item or option is the best choice.

[0726] This invention is a talent selection system for accurately matching corporate requirements with the characteristics of applicants. This system mainly consists of three components: a server, terminals, and users.

[0727] The server receives request information from companies through an interface and stores it in a data storage device. The stored information is managed as a company profile, including job description, required skills, emotional adaptability, and communication abilities. The server uses database management systems such as MySQL or PostgreSQL to store and manage the data.

[0728] The terminal is used to receive historical information and skill data from applicants. When collecting information through web forms and applications and storing it in a database, sentiment data tags are added to generate richer applicant profiles. For example, if an applicant's specific technical skills are evaluated, a corresponding tag is assigned.

[0729] When users (job seekers) participate in online interviews, their emotional state is analyzed in real time via an emotion engine. This involves video calls using technologies such as WebRTC, and further utilizes OpenCV for facial expression analysis and the Python Librosa library for voice tone analysis. This allows for the analysis of indicators such as stress level, level of interest, and sincerity based on the user's facial expressions, voice tone, and spoken content.

[0730] To select the most suitable candidates, the server uses a generative AI model. This calculates a degree of suitability based on applicant sentiment information, historical information, and company requirements. Machine learning libraries such as scikit-learn are used, and statistical models are employed for analysis.

[0731] For example, if a company is looking for "personnel who can adapt to working in a high-stress environment," the server uses an emotion engine to evaluate the applicant's stress tolerance and scores the result. This information is then input into a generative AI model, which generates prompts such as, "Consider the data on stress tolerance and suggest a way to match the company's requirements with the applicants," thereby assisting the AI's decision-making.

[0732] Through such a system, companies can obtain highly accurate talent matching, significantly improving the efficiency and effectiveness of their recruitment process.

[0733] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0734] Step 1:

[0735] The server receives request information from companies. Companies send information such as job descriptions, required skills, and desired characteristics via API. The server receives this information and stores it in a database. At this time, a MySQL database is used to organize the information and prepare it for later analysis. The received information includes job descriptions and ideal applicant profiles, and the server stores this information as structured data. The output is the company profile information stored in the database.

[0736] Step 2:

[0737] The terminal receives historical and skill data from applicants. Users input this information through a web form. The terminal tags the application information with emotional data and stores it in a database. In this process, emotional tags (e.g., communication skills) are provided along with regular application information (e.g., education and work history). The input is the applicant's basic information, and the output is a tagged applicant profile.

[0738] Step 3:

[0739] The user (job seeker) participates in an online interview. During this interview, the user's facial expressions, voice tone, and speech content are captured in real time and analyzed by an emotion engine. This process involves a video call via WebRTC. OpenCV is used for emotion analysis, and Librosa is used for voice tone analysis. The input is video call data, and the output is an emotion index indicating the user's stress level and level of interest.

[0740] Step 4:

[0741] The server receives sentiment data obtained from online interviews and integrates it with regular application information to calculate the applicant's suitability. The server utilizes scikit-learn and machine learning algorithms to analyze the suitability. In this process, all data is evaluated by statistical models, and the system obtains foundational information for selecting the most suitable candidates. The input is the integrated applicant data, and the output is the calculated suitability score.

[0742] Step 5:

[0743] The server uses a generative AI model to select the best candidates based on their fit. The AI ​​model analyzes the received data and generates prompts such as, "Consider data on stress tolerance and suggest how to match applicants with company requirements." Through this process, the AI ​​lists the best candidates and provides recommendations to the company. The input is the fit score, and the output is the final candidate list.

[0744] Step 6:

[0745] The server proposes provisional placements for selected candidates. Based on the candidate list generated by the AI ​​model, the server recommends appropriate placements to the company. This includes a process of communicating the results to the company via a notification system. The output is information on the provisional placement proposals sent to the company.

[0746] (Application Example 2)

[0747] 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".

[0748] In a company's recruitment process, the challenge is to improve the success rate of recruitment by enabling a comprehensive aptitude assessment based not only on applicants' skills and work history, but also on their emotional state, thereby ensuring that the right people are placed in the right positions.

[0749] 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.

[0750] In this invention, the server includes means for receiving and analyzing corporate request information, means for receiving and storing individual applicant information, and means for performing sentiment analysis during online interviews and evaluating the applicant's emotional state. This enables more accurate candidate suitability assessment and recommendations based on corporate requirements, while also taking into account the applicant's emotional state.

[0751] "Company requirements information" refers to information about the ideal candidate profile, necessary skills, emotional adaptability, and communication abilities that a company seeks.

[0752] "Applicant's individual information" refers to data including the applicant's resume, skills data, and emotional data collected during the interview.

[0753] A "means for calculating suitability" refers to a method of evaluating how well an applicant is suited to a company, based on the company's requirements and the applicant's individual information.

[0754] "Selection methods" refer to methods for determining the most suitable candidate for a company based on the calculated suitability score.

[0755] "Methods for performing emotional analysis" refer to technologies that analyze the applicant's facial expressions and tone of voice during online interviews to evaluate their emotional state, such as stress levels and level of interest, in real time.

[0756] "Methods for adjusting the degree of fit" refer to techniques that modify conventional scores based on the results of sentiment analysis to perform optimal personnel evaluation.

[0757] "Methods for determining and recommending placement" refers to a method of suggesting departments or roles within the company where applicants can best utilize their abilities, based on their suitability.

[0758] The system for realizing this invention supports a talent selection process involving companies and applicants. This system consists of a server, terminals, and an emotion engine connected to them.

[0759] The server receives request information sent from companies and stores it in a database. This request information includes details about the type of person the company is looking for, such as emotional adaptability and communication skills. Based on this information, the server generates an ideal candidate profile.

[0760] The terminal processes the application history and skill data submitted by applicants. Furthermore, this information is stored in a database and assigned emotional data tags along with the regular application data tags. The emotional data tags are obtained during online interviews.

[0761] Applicants, acting as users, participate in online interviews. During these interviews, an emotion engine activates, analyzing the applicant's facial expressions and tone of voice in real time. This analysis process utilizes libraries such as OpenCV and TensorFlow to evaluate emotional states, including stress levels and interest levels. This information is then used to further refine the applicant's suitability for the position.

[0762] For example, if a candidate applying for a security-related position demonstrates a high level of composure during the interview, their suitability will be evaluated positively, and based on that, they may be recommended for placement in a specific department within the company.

[0763] An example of a prompt when applying a generative AI model is: "We will analyze the applicant's facial expression data and return scores for calmness, stress, and interest. These will be used to determine their appropriate placement." Through this prompt, it becomes possible to place candidates based on their emotional adaptability.

[0764] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0765] Step 1:

[0766] The server receives request information from companies. This information, provided by companies, is input and includes the ideal candidate profile, skills, and emotional adaptability requirements. The server stores this in a database and generates an ideal candidate profile. This profile is output as matching data in subsequent processing steps.

[0767] Step 2:

[0768] The terminal receives historical and skill data from applicants. Inputs include resumes and qualification certificates submitted by the applicants. The terminal analyzes this information, creates individual profiles, and stores them in a database. This profile outputs initial sentiment data tags along with the usual application information tags.

[0769] Step 3:

[0770] Applicants, acting as users, participate in online interviews. During the interview, an emotion engine operates, collecting and analyzing the applicant's facial expressions and voice tone in real time. The input for this engine is data acquired from the camera and microphone. Using libraries such as OpenCV and TensorFlow, stress levels and interest levels are scored. This scoring data is output as emotion data tags.

[0771] Step 4:

[0772] The server receives data from the emotion engine and recalculates the suitability based on the applicant's profile and the company's requirements. Emotional states are used as input to adjust the suitability evaluation. In this process, a generative AI model is used to output emotion analysis results based on prompt sentences.

[0773] Step 5:

[0774] The server proposes optimal departmental placements based on the re-evaluated suitability. The updated suitability score is the input, and recommended departments are analyzed based on it. Finally, the recommendation results are notified to the hiring manager, leading to appropriate talent placement.

[0775] 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.

[0776] 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.

[0777] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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."

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] The following is further disclosed regarding the embodiments described above.

[0797] (Claim 1)

[0798] Means for receiving and analyzing corporate request information,

[0799] A means for receiving and storing individual applicant information,

[0800] A means for comparing the company's requirements with the applicant's individual information and calculating the degree of suitability,

[0801] A means for selecting the best candidate based on the generated degree of fit,

[0802] A means of determining and recommending the placement of selected candidates,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, further comprising means for automatically conducting online interviews or skills tests based on recruitment information and analyzing the results.

[0806] (Claim 3)

[0807] The system according to claim 1, further comprising means for adjusting candidate suitability scores based on criteria set by the company and generating a final list of candidates.

[0808] "Example 1"

[0809] (Claim 1)

[0810] Means for acquiring and analyzing organizational requirements information,

[0811] Means for collecting and storing applicant attribute information,

[0812] A means for comparing the aforementioned request information with the aforementioned attribute information and calculating a goodness of fit index,

[0813] A means for selecting the best candidate based on the generated goodness-of-fit index,

[0814] A means of determining and proposing the placement of selected candidates,

[0815] A means of evaluating candidates through online communication and analyzing their responses using a generative model,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, further comprising means for conducting an automated interview or technical test based on test information and evaluating the results thereof.

[0819] (Claim 3)

[0820] The system according to claim 1, further comprising means for adjusting the suitability index of candidates based on criteria set by the organization and creating a final list of candidates.

[0821] "Application Example 1"

[0822] (Claim 1)

[0823] Means for receiving and analyzing corporate request information,

[0824] A means for receiving and storing individual applicant information,

[0825] A means for comparing the company's requirements with the applicant's individual information and calculating the degree of suitability,

[0826] A means for selecting the best candidate based on the generated degree of fit,

[0827] A means of determining and recommending the placement of selected candidates,

[0828] A means of collecting and analyzing machine operation data,

[0829] A means for evaluating the machine's operational efficiency based on the aforementioned analysis results and assigning the optimal task,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, further comprising means for automatically conducting online interviews or skills tests based on recruitment information and analyzing the results.

[0833] (Claim 3)

[0834] The system according to claim 1, further comprising means for adjusting candidate suitability scores based on criteria set by the company and generating a final list of candidates.

[0835] "Example 2 of combining an emotion engine"

[0836] (Claim 1)

[0837] A means for storing corporate request information in a data storage device,

[0838] A means for receiving and storing applicants' history information and skill data,

[0839] A method for analyzing applicants' emotional information through online interviews,

[0840] A means for calculating the degree of suitability using the aforementioned company's requirements information, individual applicant information, and sentiment information,

[0841] A means for selecting the best candidate based on the generated fit using a generation AI model,

[0842] A means of determining and recommending the placement of selected candidates,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, further comprising means for analyzing the emotional state of users in real time based on recruitment information and calculating the degree of suitability with high accuracy using the results.

[0846] (Claim 3)

[0847] The system according to claim 1, further comprising means for adjusting candidate suitability scores based on criteria and emotional characteristics set by the company, and generating a final list of candidates.

[0848] "Application example 2 when combining with an emotional engine"

[0849] (Claim 1)

[0850] Means for receiving and analyzing corporate request information,

[0851] A means for receiving and storing individual applicant information,

[0852] A means for comparing the company's requirements with the applicant's individual information and calculating the degree of suitability,

[0853] A means for selecting the best candidate based on the generated degree of fit,

[0854] A method for conducting emotional analysis during online interviews to evaluate the emotional state of applicants,

[0855] A means of adjusting the fit based on the evaluated emotional state,

[0856] A means of determining and recommending the placement of selected candidates,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for automatically conducting online interviews or skills tests based on recruitment information, analyzing the results, and evaluating emotional states.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for adjusting candidate suitability scores in consideration of company-set criteria and emotional states, and for generating a final list of candidates. [Explanation of Symbols]

[0862] 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. Means for receiving and analyzing corporate request information, A means for receiving and storing individual applicant information, A means for comparing the company's requirements with the applicant's individual information and calculating the degree of suitability, A means for selecting the best candidate based on the generated degree of fit, A means of determining and recommending the placement of selected candidates, A system that includes this.

2. The system according to claim 1, further comprising means for automatically conducting online interviews or skills tests based on recruitment information and analyzing the results.

3. The system according to claim 1, further comprising means for adjusting candidate suitability scores based on criteria set by the company and generating a final list of candidates.

Images