system

Abstract

Provide a system. 【Solution means】 Means for receiving applicant information and storing it in an information warehouse, Means for analyzing applicant information using a generative AI model and extracting skills and experience, Means for comparing the extracted content with job requirements and evaluating candidates, Means for listing suitable candidates based on the evaluation, Means for obtaining the available time of administrators and candidates and proposing interview schedules, Means for communicating the confirmed schedule, Means for evaluating and scoring the suitability of candidates to select candidates suitable for industrial facilities, Means for an administrator to select candidates and propose interviews using a smartphone, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The conventional adoption process consumes a lot of time and resources, and there is a need for efficiency improvement, especially in resume analysis, selection of suitable candidates, and interview scheduling. As a result, companies need a method to quickly and accurately discover excellent talents and smoothly conduct the interview procedure.

Means for Solving the Problems

[0005] This invention provides a system for receiving and storing applicant data and analyzing that data using a generative model. Through this analysis, it extracts the applicant's skills and experience and evaluates candidates by comparing them with job requirements. Furthermore, it solves these problems by building a system that lists suitable candidates based on the evaluation, automatically proposes an interview schedule considering the availability of recruiters and candidates, and notifies relevant parties of the confirmed schedule.

[0006] "Applicant data" refers to all the information contained in an individual's resume and work history provided during the recruitment process.

[0007] A "generative model" is a type of algorithm that uses machine learning to analyze text and generate specific patterns or information.

[0008] "Skills" refer to elements that an applicant lists on their resume that demonstrate specific expertise, skills, or abilities.

[0009] "Experience" refers to the practical activity history gained from the job or duties the applicant has previously held.

[0010] "Job requirements" refer to the standards and conditions, such as abilities, qualifications, and experience, that a company seeks in candidates during its recruitment process.

[0011] "Evaluating candidates" refers to the process of comparing the skills and experience of selected applicants against the job requirements to determine their suitability and usefulness.

[0012] An "interview schedule" refers to a plan outlining the dates and times for interviews between the company and the applicant during the selection process.

[0013] "Notifying the finalized schedule" refers to the act of formally informing all parties involved of the finally agreed-upon interview dates. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] Shows an emotion map to which multiple emotions are mapped. [Figure 10] Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system designed to streamline the recruitment process and is specifically implemented in the following manner.

[0036] Receiving and storing applicant data:

[0037] Users (applicants) can submit their resumes through the web portal. Submitted resumes are received by the server and automatically and securely stored in the database.

[0038] Resume analysis:

[0039] The server analyzes the contents of the stored resumes using a generative model. This process uses NLP techniques to extract the applicant's skills and work experience from the text and stores it as structured data.

[0040] Skill and experience assessment:

[0041] Based on the analyzed data, the server matches the applicant's skills and experience against the company's job requirements. This comparison allows the server to score the applicant and assess the candidate's suitability.

[0042] Listing candidates:

[0043] Based on the evaluation results, the server lists suitable candidates and notifies recruiters (users) of this information, thereby supporting a rapid selection process.

[0044] Proposed and finalized interview schedule:

[0045] Users (recruiters) can enter their interview preferences for listed candidates into the system. The server retrieves the availability of both parties from the calendar system and suggests the most suitable interview date and time. The suggested schedule is notified to both the candidate and the recruiter, and if approved, it is officially announced to everyone.

[0046] Specific example:

[0047] For example, suppose a company is recruiting programmers, and the user (recruiter) manages a large number of resumes through an AI system. Let's say one applicant has a skill set including "Java® programming" and "5 years of full-stack development experience." The server analyzes this information and determines that it matches the company's requirement of "5 years or more of Java experience," and lists the candidate as a high-scoring candidate. The recruiter reviews and approves the interview date and time suggested by the AI ​​system, and the candidate is then notified of the interview schedule.

[0048] Thus, the present invention automates a key part of the recruitment process, enabling efficient talent selection and interview scheduling.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] Users (applicants) submit their resumes through a web portal. The resumes contain information about the applicant's skills and work experience in text format.

[0052] Step 2:

[0053] The server receives resumes submitted by applicants. The received data is securely stored in a database according to security protocols.

[0054] Step 3:

[0055] The server analyzes the stored resume data using a generative model. This analysis utilizes natural language processing (NLP) techniques to extract applicants' skills, qualifications, and work experience from the text and stores them in a database as quantified indicators.

[0056] Step 4:

[0057] The server comprehensively matches the analyzed applicants' skills and experience with the job requirements provided by the company. It then scores the applicants' suitability and selects candidates with high scores.

[0058] Step 5:

[0059] The server lists the selected candidates and notifies the recruiter (user) of the candidate list. The notification includes an overview of the candidates' main skills and experience.

[0060] Step 6:

[0061] The user (recruiter) reviews the candidate list and selects the candidates they wish to interview. The selection results are entered into the system.

[0062] Step 7:

[0063] The server retrieves calendar information from both recruiters and candidates, checks their availability, and automatically generates and suggests the optimal interview date and time.

[0064] Step 8:

[0065] The server notifies the recruiter and candidate of the proposed interview schedule and requests their approval. Approved schedules are then added to the calendar as official events.

[0066] Step 9:

[0067] Users (recruiters and candidates) review the proposed schedule and provide feedback if approval or adjustments are needed. The interview schedule is finalized through this process.

[0068] (Example 1)

[0069] 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."

[0070] In modern recruitment processes, a challenge is to quickly and efficiently select the best candidates from a large pool of applicants. Traditional methods involve the burdensome manual review of resumes and scheduling interviews, which requires significant time and resources from company representatives.

[0071] 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.

[0072] In this invention, the server includes means for receiving and storing applicant information, means for analyzing the applicant information using a generative AI model and extracting abilities and experience, and means for comparing the extracted information with job requirements and evaluating candidates. This automates the talent selection process and enables efficient candidate evaluation and interview planning.

[0073] A "device with the function of receiving and storing applicant information" is a device that has the ability to correctly receive applicant data transmitted from an external source and store it securely and efficiently on a recording medium.

[0074] A "device that uses a generative AI model to analyze applicant information and extract their abilities and experience" is a device that utilizes artificial intelligence technology to extract applicants' skills and backgrounds from text data and convert them into a useful format.

[0075] A "device that compares extracted information with job requirements and evaluates candidates" is a device that can compare an applicant's abilities and experience with job requirements and evaluate the candidate's suitability based on the degree of matching.

[0076] A "device that acquires the available time of company representatives and candidates and presents an interview plan" is a device that reads calendar information and schedules, calculates a convenient time for both parties, and presents the optimal interview date and time.

[0077] A "device with the function of notifying confirmed plans" is a device that has the ability to quickly and accurately communicate agreed-upon schedules and plans to all relevant parties.

[0078] This invention is a system for achieving efficient personnel selection and interview scheduling. Specific embodiments of the invention are described below.

[0079] First, the applicant, as the user, accesses the web portal using their device and fills out their resume in an online form. The server establishes a secure connection (such as SSL / TLS) to receive this information and stores the received data on a storage device. The database system used here enables secure and rapid data access.

[0080] Next, the server analyzes the applicant's stored resume using a generative AI model. Specifically, it leverages NLP techniques to automatically extract skills and work experience from the resume text and reorganize it as structured data. Open-source natural language processing libraries are often used for this task. An example of a prompt given to the model is, "Extract skills and experience from this text."

[0081] Furthermore, the server uses the extracted information to perform a process that compares the job requirements sought by the company with the applicant's skill set and experience. This process quantifies and scores how well the applicant matches the requirements.

[0082] Once the evaluation is complete, the server uses the scoring results to list suitable candidates for the company representative. This list is displayed in real time on the company representative's dashboard to support rapid decision-making.

[0083] Furthermore, company representatives can enter their preferred interview dates into the system, and the server checks the availability of both parties via a calendar API. It then proposes the optimal date and time, and the agreed-upon plan is notified to all stakeholders, enabling smooth scheduling. This notification process, conducted via email and application notifications, significantly reduces scheduling errors.

[0084] The introduction of this system eliminates the need for users to manually process a vast number of resumes, shortening the hiring process and saving resources.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] Applicants, as users, access the web portal using their device and fill out and submit their resume information in an online form. The input data includes skills, work experience, and contact information in text format. The device aggregates this data into the form and sends it to the server. The server receives the applicant's data and stores it in a database using a secure protocol. The output is a confirmation message for the saved data.

[0088] Step 2:

[0089] The server uses a generative AI model to analyze data based on the stored resume information. It receives the stored text data as input and prompts the generative AI model with the message, "Extract skills and experience from this text." For data processing, NLP techniques are used to extract the applicant's skills and work experience from the text and store it in a structured format in the database. The output is structured skills and experience data.

[0090] Step 3:

[0091] The server compares a company's job requirements with the applicant's skill set and experience based on structured data obtained through analysis. It receives structured data of applicants and job requirements provided by the company as input. The server uses a specific algorithm to match the two and perform scoring. As part of the data processing, it numerically evaluates the degree of match with the requirements and determines a score for each applicant. The output is the evaluation score for each applicant.

[0092] Step 4:

[0093] The server lists suitable candidates based on the scoring results. It receives evaluation scores as input and selects applicants who meet or exceed a specific threshold. The listed candidate information is reflected on the company representative's dashboard. Specifically, the candidate list is notified to the company representative in real time via email and the dashboard. The output is information about the listed candidates.

[0094] Step 5:

[0095] The user, a company representative, enters their preferred interview dates into the system. The server retrieves the calendar information of both the company representative and the candidate via an API and calculates the optimal interview date and time. It receives the availability of both the company representative and the candidate as input and generates the optimal schedule through calculation. Specifically, the proposed date and time are sent via email or notification for confirmation by both parties. The output is the proposed interview date and time.

[0096] Step 6:

[0097] The server notifies all stakeholders of the confirmed interview schedule. It receives agreed-upon interview dates and times as input and communicates the schedule via email and app notifications as output. Specifically, the notification includes links and detailed information for review. This process minimizes misunderstandings and schedule changes.

[0098] (Application Example 1)

[0099] 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."

[0100] Currently, there are challenges in selecting suitable robot operators for industrial facilities, including the difficulty of quickly and accurately identifying the right person and effectively scheduling interviews. In particular, finding the optimal candidate from a large pool of applicants is time-consuming and places a significant burden on managers. Therefore, there is a need for a method that automates applicant data analysis and scheduling, thereby streamlining the recruitment process for industrial facilities.

[0101] 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.

[0102] In this invention, the server includes means for receiving applicant information and storing it in an information warehouse, means for analyzing the applicant information using a generative AI model and extracting skills and experience, and means for evaluating and scoring the suitability of candidates in order to select candidates suitable for industrial facilities. This enables the automation of efficient personnel selection and interview proposals in industrial facilities.

[0103] An "applicant" refers to a person who wishes to engage in operational work at an industrial facility.

[0104] An "information warehouse" refers to a database system used to store data about applicants.

[0105] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to perform data analysis.

[0106] "Technical skills and experience" refers to the job skills and past work history of the applicant.

[0107] "Industrial facilities" refer to production bases where manufacturing, processing, and other related industries take place.

[0108] A "candidate" refers to a suitable individual selected from among the applicants based on specific criteria.

[0109] "Fit" refers to an indicator that shows how well a candidate's skills and experience match the job requirements.

[0110] "Scoring" refers to the process of evaluating candidates and assigning them numerical scores.

[0111] An "interview appointment" refers to a date and time set aside for a candidate and a recruiter to meet in person.

[0112] The term "administrator" refers to the person responsible for selecting personnel in an industrial facility.

[0113] "Communication" refers to the exchange of notifications and information using a system.

[0114] This invention provides a system for efficiently selecting personnel and automatically scheduling interviews in industrial facilities. The system mainly consists of a server, an administrator terminal (smartphone or personal computer), and cloud-based software.

[0115] The server receives applicant information and securely stores it in a database acting as an information repository. The applicant information is analyzed using a generative AI model to extract skills and experience. This process utilizes the Google® Cloud NLP API to analyze text data. The extracted information is scored for its suitability to the needs of the industrial facility, and appropriate candidates are listed.

[0116] The administrator terminal receives data from the server and provides an interface for administrators to review candidates. This interface allows administrators to use their smartphones to review and approve candidates and interview schedules suggested based on a generated AI model.

[0117] This system streamlines the personnel selection process in industrial facilities and reduces the burden on managers. For example, when a factory hires a new robot operator, an applicant's experience of "5 years of robot arm operation" is compared against the factory's requirement of "3 years or more of operation experience," and they are given a high score and automatically added to the candidate list.

[0118] An example of a prompt message might be, "Enter the applicant's operational skills and list suitable operator candidates." This prompt serves as a criterion for how the system operates and selects applicants.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server receives job application data from applicant terminals and stores it in a database that functions as an information repository. The input consists of resumes and profile information submitted by applicants, and the purpose is to store this information securely. The output is a status indicating successful saving.

[0122] Step 2:

[0123] The server uses a generative AI model based on stored data to analyze text data. The input is text data from resumes stored in a database, and the Google Cloud NLP API is used to extract applicant skills and experience. The output is structured skills and experience data.

[0124] Step 3:

[0125] The server compares the extracted skills and experience with the job requirements of industrial facilities. The inputs for this process are analyzed skill data and pre-registered job requirement data. A generating AI model evaluates the fit and assigns a score to each candidate. The output is the candidate's fit score.

[0126] Step 4:

[0127] The server lists suitable candidates based on the evaluation results. The input is scored candidate data, and applicants whose scores exceed a certain value are selected. The output of this process is a list of candidates.

[0128] Step 5:

[0129] The administrator terminal receives and displays the list results from the server. The administrator uses the terminal to review candidate information and schedule interviews. The input is the listed candidate data, and the output is the decision to approve or reject interviews with the candidates.

[0130] Step 6:

[0131] The server, upon receiving administrator selection, automatically suggests interview schedules by referencing the candidate's and administrator's calendar data. The input consists of the administrator's and candidate's available time data. The server calculates the optimal date and time and provides the interview schedule as output.

[0132] 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.

[0133] This invention provides an improved system that understands user emotions in the recruitment process and supports decision-making during the selection process. The system incorporates an AI-powered emotion engine that can analyze the emotions of candidates and recruiters in real time during the interview process.

[0134] Receiving and storing applicant data:

[0135] Users (applicants) submit their resumes through a web portal following standard procedures. The server receives this information and stores it in a database as structured data.

[0136] Data analysis and evaluation:

[0137] In addition to conventional application data analysis, the server uses an emotion engine to extract emotional nuances from applicants' resumes. These analysis results are compared with job requirements along with extracted skills and experience information. Furthermore, by including emotional characteristics in the scoring, the suitability of applicants is evaluated from a more multifaceted perspective.

[0138] Listing and notifying candidates:

[0139] The server lists suitable candidates based on the scoring results and notifies the recruiter (user). This notification includes not only technical skills but also notable features based on sentiment recognition.

[0140] Sentimental analysis of the interview process:

[0141] The user (recruiter) can utilize an emotional interface to collect emotional data in real time during interviews. The terminal sends this information to a server, which uses an emotional engine to analyze the candidate's emotions and generates an evaluation report based on the results.

[0142] Proposed interview schedule:

[0143] The server considers emotional data and technical capabilities to suggest the optimal interview timing for each candidate. It also collects and analyzes post-interview feedback, referencing the recruiter's emotional data, to predict the success or failure of the interview and the next steps.

[0144] Specific example:

[0145] A company is recruiting for sales positions, and the user (recruiter) selects a few candidates from a large pool of applicants. During this process, the server uses an emotion engine to extract emotional elements from the candidates' submitted presentation materials and self-introductions, predicting their adaptability to the company culture. During the interview, the terminal analyzes the candidate's tone of voice and facial expressions in real time, drawing conclusions based on emotional factors such as flexibility and stress tolerance. Based on this comprehensive evaluation, the recruiter can make more accurate decisions.

[0146] Thus, the present invention provides an advanced recruitment support system that captures the emotional characteristics of candidates and improves the quality and efficiency of recruitment.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] Users (applicants) upload their resumes and related documents through a web portal. This may include work experience summaries and self-introduction videos.

[0150] Step 2:

[0151] The server stores the received applicant data in a secure database. Simultaneously, it begins the process of analyzing the resume and related documents.

[0152] Step 3:

[0153] The server uses a generative model to extract applicants' skills and experience from submitted materials. Furthermore, it uses an emotion engine to analyze emotional nuances from videos and audio, generating indicators such as positive, negative, and neutral.

[0154] Step 4:

[0155] The server matches job requirements with candidate analysis results and scores candidates based on their technical skills and emotional compatibility. This score indicates the overall suitability and serves as the criterion for listing candidates.

[0156] Step 5:

[0157] The server generates a list of high-scoring candidates and notifies the recruiter (user). This notification includes a detailed report based on skills and sentiment analysis.

[0158] Step 6:

[0159] The user (recruiter) selects candidates to proceed to interviews based on the information received from the system. This selection result is then fed back into the system.

[0160] Step 7:

[0161] During the interview, the device collects data such as the candidate's voice, facial expressions, and gestures in real time. This data is sent to a server and analyzed by an emotion engine.

[0162] Step 8:

[0163] The server collects emotional analysis data from the interview and evaluates the candidate's stress level and adaptability. This evaluation is reflected in the final candidate report provided by the system.

[0164] Step 9:

[0165] After the interview process is complete, the server provides the hiring manager with the analysis results, including a final evaluation of the candidate and recommendations for the next steps. The user can then use this information to make their final hiring decision.

[0166] (Example 2)

[0167] 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 will be referred to as the "terminal."

[0168] Traditional recruitment processes tend to focus heavily on evaluating applicants' technical skills and experience, failing to adequately consider emotional compatibility and suitability for the company culture. Furthermore, there are limited means of understanding candidates' psychological states in real time during interviews, highlighting the need for improved quality and efficiency in recruitment.

[0169] 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.

[0170] This invention includes a server that receives, structures, and stores applicant information; a server that extracts and comprehensively evaluates the applicant's emotional characteristics using generative AI technology; and a server that optimizes interview schedules between recruiters and candidates. This enables a multifaceted evaluation through emotional analysis, significantly improving the quality and efficiency of the recruitment process.

[0171] "Means for receiving and storing applicant information" refers to a function that acquires data provided by applicants and records it in digital format within the system.

[0172] "Means of storing applicant information in a structured format" refers to a function in a database that organizes and stores applicant information based on certain rules and formats.

[0173] "A means of analyzing applicant information and extracting emotional characteristics using generative AI technology" refers to a function that uses artificial intelligence technology, such as natural language processing, to analyze and identify emotional information from the applicant's submitted materials.

[0174] "Means of evaluating technical skills and emotional characteristics in comparison to job requirements" refers to a function that comprehensively assesses an applicant's technical skills and emotional aspects in light of the requirements sought by the company.

[0175] "A means of listing suitable applicants and notifying recruiters" refers to a function that selects applicants who meet the criteria based on the evaluation results and notifies them in list format.

[0176] "A means of analyzing the available time of recruiters and candidates and proposing the most suitable interview schedule" refers to a function that combines the schedules of both parties to calculate and provide the optimal interview date and time.

[0177] "Means of notifying confirmed schedules" refers to a function that communicates optimized interview dates and times to each party.

[0178] "A means of collecting and analyzing candidate emotional data in real time during an interview" refers to a function that acquires emotional data during an interview and immediately analyzes and evaluates it.

[0179] "Means of providing post-interview evaluation results" refers to a function that reports evaluations based on the data collected during interviews to relevant parties at a later date.

[0180] This invention is a system that understands the emotions of applicants and recruiters in the recruitment process and supports selection decision-making. This system uses the following hardware and software.

[0181] The server runs on a cloud computing platform and uses an engine incorporating AI technology. This AI engine is equipped with natural language processing (NLP) technology and integrates with external services such as the Google Cloud Natural Language API and IBM Watson® Natural Language Understanding.

[0182] The devices are typical personal computers or tablet devices. They have built-in webcams and microphones and are used to collect audio and video data during interviews. The software on the devices has the capability to transmit this data to a server in real time.

[0183] Users include applicants and recruiters. Recruiters receive notifications from the system and review evaluation results to advance their recruitment activities. During interviews, they can gain a deeper understanding of candidates based on real-time sentiment analysis information provided by the server.

[0184] This system begins with applicants submitting their resumes through a web portal. The server receives this data and stores it in a structured format. Next, AI technology is used to extract the applicant's emotional characteristics and comprehensively evaluate them by comparing their technical skills and emotional information with the job requirements. Based on this evaluation, the server lists suitable candidates and notifies the user via email.

[0185] As a concrete example, when a company recruits for a sales position, the server analyzes the emotional characteristics of the presentation materials and self-introductions received from applicants, and uses the results to evaluate their adaptability to the company culture. During the interview, the terminal transmits the candidate's voice and facial expression data to the server for real-time analysis. Based on this information, the recruiter makes a decision considering factors such as the applicant's flexibility and stress tolerance.

[0186] An example of a prompt to input into the generating AI model is: "Analyze the emotional characteristics of applicants suitable for sales positions, evaluate their adaptability to the company culture, and create a report."

[0187] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0188] Step 1:

[0189] The user (applicant) submits their resume through a web portal. The information received includes the applicant's name, contact information, work history, educational background, and a self-introduction. This data is then sent to the server.

[0190] Step 2:

[0191] The server receives resume data from applicants and stores it in a structured format in the database. It analyzes the entered resume information and organizes it into individual fields for each applicant. This process yields structured data output.

[0192] Step 3:

[0193] The server applies an emotion engine using generative AI technology to the stored applicant data. The input consists of descriptions from self-introduction statements and work histories, and emotional characteristics are extracted using natural language processing. After extraction, emotion scoring is performed, and the results are output.

[0194] Step 4:

[0195] The server compares emotional scores and technical skills data with job requirements. It uses job requirements and extracted skills data as input. After the comparison, it evaluates the degree of fit and generates a list of overall candidate ratings as output.

[0196] Step 5:

[0197] The server creates a list of suitable applicants based on the overall evaluation and notifies the user (recruiter). The notification uses an email service, and the output includes the list of candidates and detailed evaluation information.

[0198] Step 6:

[0199] The device collects the candidate's audio and video in real time during the interview. Here, it uses the camera and microphone to send non-verbal data (voice tone, facial expressions) as input to the server.

[0200] Step 7:

[0201] The server analyzes the data sent from the terminal in real time. Using an emotion engine, it generates emotional data such as the candidate's level of relaxation and tension, and outputs this as an evaluation report.

[0202] Step 8:

[0203] The server provides feedback to the user (recruiter) based on the evaluation results after the interview. It also suggests appropriate interview schedules to guide the next selection step. The output includes a feedback message and an optimal interview schedule.

[0204] (Application Example 2)

[0205] 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".

[0206] Traditional recruitment processes have limitations in evaluating applicants based on their skills and experience, making it difficult to adequately assess emotional compatibility and adaptability to the company culture. Furthermore, increased stress due to a lack of communication within the family and the inability to understand and appropriately respond to family members' emotions has been identified as a problem.

[0207] 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.

[0208] In this invention, the server includes means for determining the user's emotional state using emotion analysis technology in a mobile device and optimizing suggestions; means for receiving and storing applicant data; and means for analyzing applicant data using a generative model and extracting skills and experience. This enables more efficient recruitment processes and allows home robots to understand the emotions of family members.

[0209] "Applicant data" refers to the resume, work history, and related information provided by an applicant for a specific job.

[0210] A "generative model" refers to an algorithm or framework used to analyze data using artificial intelligence technology, and is particularly used in natural language processing and pattern recognition.

[0211] "Skills and experience" refers to the knowledge, abilities, past work history, and achievements that an applicant possesses in relation to a specific job.

[0212] "Evaluating" means analyzing and judging an applicant's suitability and potential based on various criteria.

[0213] "Listing" refers to the process of compiling and clearly identifying individuals who have been selected based on specific criteria.

[0214] "Mobile devices" refer to devices such as household robots and smart devices that have the ability to collect and process information while operating in different locations.

[0215] "Emotional analysis technology" refers to technology used to automatically analyze emotions and psychological states from voice and facial expression data.

[0216] "Optimizing suggestions" refers to the process of presenting the most suitable actions and options based on the user's situation and needs.

[0217] This invention is a system that receives applicant data and evaluates that data using emotion analysis technology. Furthermore, it enables the analysis of emotional states in mobile devices within the home, such as household robots, and provides optimal suggestions.

[0218] The server receives and stores applicant data from users. This data includes resumes and work histories and is stored as structured data within the server. The server analyzes this data using a generative model to extract the applicant's skills and experience. During the analysis process, an AI-powered sentiment analysis engine is used to extract emotional nuances from the applicant's data and to evaluate the applicant's suitability from multiple perspectives.

[0219] In mobile devices, the system collects user voice and facial expression data via cameras and microphones, and analyzes their emotional state in real time. Specifically, it runs an emotion analysis model using Python and TENSORFLOW® on an embedded platform such as Raspberry Pi. Based on the analyzed emotion data, the mobile device can make appropriate suggestions to the user.

[0220] A concrete example is a scenario where a home robot understands the user's emotions and makes a suggestion such as, "You seem a little tired today, shall I make you some tea?" This is achieved by the mobile robot determining the user's emotions from facial expression data and voice analysis, and then generating a response. An example of a prompt to the generating AI model would be, "Please tell me how a home robot can use emotion analysis to optimize communication with family members."

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The server receives and stores applicant data from users. This input data includes resumes and work history documents. The server stores this data as structured data in a database so that it can be used for later analysis.

[0224] Step 2:

[0225] The server retrieves applicant data from the database and analyzes it using a generative AI model. Specifically, the data includes information about skills and experience, and the model extracts these elements, along with analyzing emotional nuances. The output of this process is a structure of skills, experience, and emotional evaluations.

[0226] Step 3:

[0227] The server compares the analysis results obtained in Step 2 with the job requirements. The input provided is a structured list of the applicant's skills and experience, along with the requirements sought by the company. The server then evaluates the applicant's suitability and performs scoring. The output generates an evaluation list of suitable candidates.

[0228] Step 4:

[0229] The device collects sensor data to analyze the user's emotions in a mobile home environment. Specifically, it collects facial expression data using a camera and acquires audio data using a microphone. This sensor data is input into the system and processed in real time.

[0230] Step 5:

[0231] The device processes collected sensor data using emotion analysis technology. Based on the input data, the mobile device analyzes the user's current emotional state and makes suggestions based on the analysis results. The output consists of specific action suggestions and communication content for the user.

[0232] Step 6:

[0233] Suggestions are made to the user. For example, a mobile object might say, "You seem a little tired today, shall I make you some tea?" and an appropriate response is taken based on sentiment analysis. This prompt is generated based on sentiment analysis data.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] [Second Embodiment]

[0238] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0239] 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.

[0240] 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).

[0241] 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.

[0242] 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.

[0243] 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).

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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".

[0250] This invention is a system designed to streamline the recruitment process and is specifically implemented in the following manner.

[0251] Receiving and storing applicant data:

[0252] Users (applicants) can submit their resumes through the web portal. Submitted resumes are received by the server and automatically and securely stored in the database.

[0253] Resume analysis:

[0254] The server analyzes the contents of the stored resumes using a generative model. This process uses NLP techniques to extract the applicant's skills and work experience from the text and stores it as structured data.

[0255] Skill and experience assessment:

[0256] Based on the analyzed data, the server matches the applicant's skills and experience against the company's job requirements. This comparison allows the server to score the applicant and assess the candidate's suitability.

[0257] Listing candidates:

[0258] Based on the evaluation results, the server lists suitable candidates and notifies recruiters (users) of this information, thereby supporting a rapid selection process.

[0259] Proposed and finalized interview schedule:

[0260] Users (recruiters) can enter their interview preferences for listed candidates into the system. The server retrieves the availability of both parties from the calendar system and suggests the most suitable interview date and time. The suggested schedule is notified to both the candidate and the recruiter, and if approved, it is officially announced to everyone.

[0261] Specific example:

[0262] For example, suppose a company is recruiting programmers, and the user (recruiter) manages a large number of resumes through an AI system. Let's say one applicant has a skill set of "Java programming" and "5 years of full-stack development experience." The server analyzes this information and determines that it matches the company's requirement of "5 years or more of Java experience," and lists the candidate as a high-scoring candidate. The recruiter reviews and approves the interview date and time suggested by the AI ​​system, and the candidate is notified of the interview date.

[0263] Thus, the present invention automates a key part of the recruitment process, enabling efficient talent selection and interview scheduling.

[0264] The following describes the processing flow.

[0265] Step 1:

[0266] Users (applicants) submit their resumes through a web portal. The resumes contain information about the applicant's skills and work experience in text format.

[0267] Step 2:

[0268] The server receives resumes submitted by applicants. The received data is securely stored in a database according to security protocols.

[0269] Step 3:

[0270] The server analyzes the stored resume data using a generative model. This analysis utilizes natural language processing (NLP) techniques to extract applicants' skills, qualifications, and work experience from the text and stores them in a database as quantified indicators.

[0271] Step 4:

[0272] The server comprehensively matches the analyzed applicants' skills and experience with the job requirements provided by the company. It then scores the applicants' suitability and selects candidates with high scores.

[0273] Step 5:

[0274] The server lists the selected candidates and notifies the recruiter (user) of the candidate list. The notification includes an overview of the candidates' main skills and experience.

[0275] Step 6:

[0276] The user (recruitment staff) refers to the candidate list and selects the candidates who wish to have an interview. The selection results are input into the system.

[0277] Step 7:

[0278] The server obtains the calendar information of the recruitment staff and candidates, checks the availability of both parties, automatically generates and proposes the optimal interview date and time.

[0279] Step 8:

[0280] The server notifies the proposed interview schedule to the recruitment staff and candidates and requests approval. The approved schedule is registered in the calendar as an official event.

[0281] Step 9:

[0282] The users (recruitment staff and candidates) respectively check the proposed schedule and give feedback if approval or adjustment is required. Through this process, the interview schedule is finally determined.

[0283] (Example 1)

[0284] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In modern recruitment processes, it is a challenge to quickly and efficiently select the optimal talent from a large number of applicants. In conventional methods, there are problems such as a large burden on manual resume checking and interview schedule adjustment, which require time and resources for corporate staff.

[0286] <( The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0287] In this invention, the server includes means for receiving and storing applicant information, means for analyzing the applicant information using a generative AI model and extracting abilities and experience, and means for comparing the extracted information with job requirements and evaluating candidates. This automates the talent selection process and enables efficient candidate evaluation and interview planning.

[0288] A "device with the function of receiving and storing applicant information" is a device that has the ability to correctly receive applicant data transmitted from an external source and store it securely and efficiently on a recording medium.

[0289] A "device that uses a generative AI model to analyze applicant information and extract their abilities and experience" is a device that utilizes artificial intelligence technology to extract applicants' skills and backgrounds from text data and convert them into a useful format.

[0290] A "device that compares extracted information with job requirements and evaluates candidates" is a device that can compare an applicant's abilities and experience with job requirements and evaluate the candidate's suitability based on the degree of matching.

[0291] A "device that acquires the available time of company representatives and candidates and presents an interview plan" is a device that reads calendar information and schedules, calculates a convenient time for both parties, and presents the optimal interview date and time.

[0292] A "device with the function of notifying confirmed plans" is a device that has the ability to quickly and accurately communicate agreed-upon schedules and plans to all relevant parties.

[0293] This invention is a system for achieving efficient personnel selection and interview scheduling. Specific embodiments of the invention are described below.

[0294] First, the applicant, as the user, accesses the web portal using their device and fills out their resume in an online form. The server establishes a secure connection (such as SSL / TLS) to receive this information and stores the received data on a storage device. The database system used here enables secure and rapid data access.

[0295] Next, the server analyzes the applicant's stored resume using a generative AI model. Specifically, it leverages NLP techniques to automatically extract skills and work experience from the resume text and reorganize it as structured data. Open-source natural language processing libraries are often used for this task. An example of a prompt given to the model is, "Extract skills and experience from this text."

[0296] Furthermore, the server uses the extracted information to perform a process that compares the job requirements sought by the company with the applicant's skill set and experience. This process quantifies and scores how well the applicant matches the requirements.

[0297] Once the evaluation is complete, the server uses the scoring results to list suitable candidates for the company representative. This list is displayed in real time on the company representative's dashboard to support rapid decision-making.

[0298] Furthermore, company representatives can enter their preferred interview dates into the system, and the server checks the availability of both parties via a calendar API. It then proposes the optimal date and time, and the agreed-upon plan is notified to all stakeholders, enabling smooth scheduling. This notification process, conducted via email and application notifications, significantly reduces scheduling errors.

[0299] The introduction of this system eliminates the need for users to manually process a vast number of resumes, shortening the hiring process and saving resources.

[0300] The process flow of the specific process in Example 1 will be described using FIG. 11.

[0301] Step 1:

[0302] The applicant, who is the user, uses a terminal to access the web portal and enters and submits resume information in an online form. The input data includes skills, work experience, and contact information in text format. The terminal aggregates these data into the form and sends them to the server. The server receives the applicant's data and stores it in the database using a secure protocol. The output is a confirmation message of the stored data.

[0303] Step 2:

[0304] Based on the stored resume information, the server uses a generative AI model to analyze the data. It receives the stored text data as input and performs analysis on the generative AI model using a prompt sentence "Please extract skills and experience from this text". As data processing, NLP technology is used to extract the applicant's skills and work experience from the text and store them in the database in a structured format. The output is structured skill and experience data.

[0305] Step 3:

[0306] Based on the data structured by the analysis, the server compares the job requirements of the company with the applicant's skill set and experience. It receives the applicant's structured data and the job requirements provided by the company as input. The server uses a specific algorithm to match the two and perform scoring. As data processing, the degree of match with the requirements is numerically evaluated to determine the score for each applicant. The output is the evaluation score for each applicant.

[0307] Step 4:

[0308] The server lists suitable candidates based on the scoring results. It receives evaluation scores as input and selects applicants who meet or exceed a specific threshold. The listed candidate information is reflected on the company representative's dashboard. Specifically, the candidate list is notified to the company representative in real time via email and the dashboard. The output is information about the listed candidates.

[0309] Step 5:

[0310] The user, a company representative, enters their preferred interview dates into the system. The server retrieves the calendar information of both the company representative and the candidate via an API and calculates the optimal interview date and time. It receives the availability of both the company representative and the candidate as input and generates the optimal schedule through calculation. Specifically, the proposed date and time are sent via email or notification for confirmation by both parties. The output is the proposed interview date and time.

[0311] Step 6:

[0312] The server notifies all stakeholders of the confirmed interview schedule. It receives agreed-upon interview dates and times as input and communicates the schedule via email and app notifications as output. Specifically, the notification includes links and detailed information for review. This process minimizes misunderstandings and schedule changes.

[0313] (Application Example 1)

[0314] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0315] Currently, there are challenges in selecting suitable robot operators for industrial facilities, including the difficulty of quickly and accurately identifying the right person and effectively scheduling interviews. In particular, finding the optimal candidate from a large pool of applicants is time-consuming and places a significant burden on managers. Therefore, there is a need for a method that automates applicant data analysis and scheduling, thereby streamlining the recruitment process for industrial facilities.

[0316] 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.

[0317] In this invention, the server includes means for receiving applicant information and storing it in an information warehouse, means for analyzing the applicant information using a generative AI model and extracting skills and experience, and means for evaluating and scoring the suitability of candidates in order to select candidates suitable for industrial facilities. This enables the automation of efficient personnel selection and interview proposals in industrial facilities.

[0318] An "applicant" refers to a person who wishes to engage in operational work at an industrial facility.

[0319] An "information warehouse" refers to a database system used to store data about applicants.

[0320] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to perform data analysis.

[0321] "Technical skills and experience" refers to the job skills and past work history of the applicant.

[0322] "Industrial facilities" refer to production bases where manufacturing, processing, and other related industries take place.

[0323] A "candidate" refers to a suitable individual selected from among the applicants based on specific criteria.

[0324] "Fit" refers to an indicator that shows how well a candidate's skills and experience match the job requirements.

[0325] "Scoring" refers to the process of evaluating candidates and assigning them numerical scores.

[0326] An "interview appointment" refers to a date and time set aside for a candidate and a recruiter to meet in person.

[0327] The term "administrator" refers to the person responsible for selecting personnel in an industrial facility.

[0328] "Communication" refers to the exchange of notifications and information using a system.

[0329] This invention provides a system for efficiently selecting personnel and automatically scheduling interviews in industrial facilities. The system mainly consists of a server, an administrator terminal (smartphone or personal computer), and cloud-based software.

[0330] The server receives applicant information and securely stores it in a database acting as an information repository. The applicant information is analyzed using a generative AI model to extract skills and experience. This process utilizes the Google Cloud NLP API to analyze text data. The extracted information is then scored for suitability to the needs of the industrial facility, and a list of appropriate candidates is compiled.

[0331] The administrator terminal receives data from the server and provides an interface for administrators to review candidates. This interface allows administrators to use their smartphones to review and approve candidates and interview schedules suggested based on a generated AI model.

[0332] This system streamlines the personnel selection process in industrial facilities and reduces the burden on managers. For example, when a factory hires a new robot operator, an applicant's experience of "5 years of robot arm operation" is compared against the factory's requirement of "3 years or more of operation experience," and they are given a high score and automatically added to the candidate list.

[0333] An example of a prompt message might be, "Enter the applicant's operational skills and list suitable operator candidates." This prompt serves as a criterion for how the system operates and selects applicants.

[0334] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0335] Step 1:

[0336] The server receives job application data from applicant terminals and stores it in a database that functions as an information repository. The input consists of resumes and profile information submitted by applicants, and the purpose is to store this information securely. The output is a status indicating successful saving.

[0337] Step 2:

[0338] The server uses a generative AI model based on stored data to analyze text data. The input is text data from resumes stored in a database, and the Google Cloud NLP API is used to extract applicant skills and experience. The output is structured skills and experience data.

[0339] Step 3:

[0340] The server compares the extracted skills and experience with the job requirements of industrial facilities. The inputs for this process are analyzed skill data and pre-registered job requirement data. A generating AI model evaluates the fit and assigns a score to each candidate. The output is the candidate's fit score.

[0341] Step 4:

[0342] The server lists suitable candidates based on the evaluation results. The input is scored candidate data, and applicants whose scores exceed a certain value are selected. The output of this process is a list of candidates.

[0343] Step 5:

[0344] The administrator terminal receives and displays the list results from the server. The administrator uses the terminal to review candidate information and schedule interviews. The input is the listed candidate data, and the output is the decision to approve or reject interviews with the candidates.

[0345] Step 6:

[0346] The server, upon receiving administrator selection, automatically suggests interview schedules by referencing the candidate's and administrator's calendar data. The input consists of the administrator's and candidate's available time data. The server calculates the optimal date and time and provides the interview schedule as output.

[0347] 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.

[0348] This invention provides an improved system that understands user emotions in the recruitment process and supports decision-making during the selection process. The system incorporates an AI-powered emotion engine that can analyze the emotions of candidates and recruiters in real time during the interview process.

[0349] Receiving and storing applicant data:

[0350] Users (applicants) submit their resumes through a web portal following standard procedures. The server receives this information and stores it in a database as structured data.

[0351] Data analysis and evaluation:

[0352] In addition to conventional application data analysis, the server uses an emotion engine to extract emotional nuances from applicants' resumes. These analysis results are compared with job requirements along with extracted skills and experience information. Furthermore, by including emotional characteristics in the scoring, the suitability of applicants is evaluated from a more multifaceted perspective.

[0353] Listing and notifying candidates:

[0354] The server lists suitable candidates based on the scoring results and notifies the recruiter (user). This notification includes not only technical skills but also notable features based on sentiment recognition.

[0355] Sentimental analysis of the interview process:

[0356] The user (recruiter) can utilize an emotional interface to collect emotional data in real time during interviews. The terminal sends this information to a server, which uses an emotional engine to analyze the candidate's emotions and generates an evaluation report based on the results.

[0357] Proposed interview schedule:

[0358] The server considers emotional data and technical capabilities to suggest the optimal interview timing for each candidate. It also collects and analyzes post-interview feedback, referencing the recruiter's emotional data, to predict the success or failure of the interview and the next steps.

[0359] Specific example:

[0360] A company is recruiting for sales positions, and the user (recruiter) selects a few candidates from a large pool of applicants. During this process, the server uses an emotion engine to extract emotional elements from the candidates' submitted presentation materials and self-introductions, predicting their adaptability to the company culture. During the interview, the terminal analyzes the candidate's tone of voice and facial expressions in real time, drawing conclusions based on emotional factors such as flexibility and stress tolerance. Based on this comprehensive evaluation, the recruiter can make more accurate decisions.

[0361] Thus, the present invention provides an advanced recruitment support system that captures the emotional characteristics of candidates and improves the quality and efficiency of recruitment.

[0362] The following describes the processing flow.

[0363] Step 1:

[0364] Users (applicants) upload their resumes and related documents through a web portal. This may include work experience summaries and self-introduction videos.

[0365] Step 2:

[0366] The server stores the received applicant data in a secure database. Simultaneously, it begins the process of analyzing the resume and related documents.

[0367] Step 3:

[0368] The server uses a generative model to extract applicants' skills and experience from submitted materials. Furthermore, it uses an emotion engine to analyze emotional nuances from videos and audio, generating indicators such as positive, negative, and neutral.

[0369] Step 4:

[0370] The server matches job requirements with candidate analysis results and scores candidates based on their technical skills and emotional compatibility. This score indicates the overall suitability and serves as the criterion for listing candidates.

[0371] Step 5:

[0372] The server generates a list of high-scoring candidates and notifies the recruiter (user). This notification includes a detailed report based on skills and sentiment analysis.

[0373] Step 6:

[0374] The user (recruiter) selects candidates to proceed to interviews based on the information received from the system. This selection result is then fed back into the system.

[0375] Step 7:

[0376] During the interview, the device collects data such as the candidate's voice, facial expressions, and gestures in real time. This data is sent to a server and analyzed by an emotion engine.

[0377] Step 8:

[0378] The server collects emotional analysis data from the interview and evaluates the candidate's stress level and adaptability. This evaluation is reflected in the final candidate report provided by the system.

[0379] Step 9:

[0380] After the interview process is complete, the server provides the hiring manager with the analysis results, including a final evaluation of the candidate and recommendations for the next steps. The user can then use this information to make their final hiring decision.

[0381] (Example 2)

[0382] 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".

[0383] Traditional recruitment processes tend to focus heavily on evaluating applicants' technical skills and experience, failing to adequately consider emotional compatibility and suitability for the company culture. Furthermore, there are limited means of understanding candidates' psychological states in real time during interviews, highlighting the need for improved quality and efficiency in recruitment.

[0384] 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.

[0385] This invention includes a server that receives, structures, and stores applicant information; a server that extracts and comprehensively evaluates the applicant's emotional characteristics using generative AI technology; and a server that optimizes interview schedules between recruiters and candidates. This enables a multifaceted evaluation through emotional analysis, significantly improving the quality and efficiency of the recruitment process.

[0386] "Means for receiving and storing applicant information" refers to a function that acquires data provided by applicants and records it in digital format within the system.

[0387] "Means of storing applicant information in a structured format" refers to a function in a database that organizes and stores applicant information based on certain rules and formats.

[0388] "A means of analyzing applicant information and extracting emotional characteristics using generative AI technology" refers to a function that uses artificial intelligence technology, such as natural language processing, to analyze and identify emotional information from the applicant's submitted materials.

[0389] "Means of evaluating technical skills and emotional characteristics in comparison to job requirements" refers to a function that comprehensively assesses an applicant's technical skills and emotional aspects in light of the requirements sought by the company.

[0390] "A means of listing suitable applicants and notifying recruiters" refers to a function that selects applicants who meet the criteria based on the evaluation results and notifies them in list format.

[0391] "A means of analyzing the available time of recruiters and candidates and proposing the most suitable interview schedule" refers to a function that combines the schedules of both parties to calculate and provide the optimal interview date and time.

[0392] "Means of notifying confirmed schedules" refers to a function that communicates optimized interview dates and times to each party.

[0393] "A means of collecting and analyzing candidate emotional data in real time during an interview" refers to a function that acquires emotional data during an interview and immediately analyzes and evaluates it.

[0394] "Means of providing post-interview evaluation results" refers to a function that reports evaluations based on the data collected during interviews to relevant parties at a later date.

[0395] This invention is a system that understands the emotions of applicants and recruiters in the recruitment process and supports selection decision-making. This system uses the following hardware and software.

[0396] The server runs on a cloud computing platform and uses an engine incorporating AI technology. This AI engine is equipped with natural language processing (NLP) technology and interacts with external services such as the Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0397] The devices are typical personal computers or tablet devices. They have built-in webcams and microphones and are used to collect audio and video data during interviews. The software on the devices has the capability to transmit this data to a server in real time.

[0398] Users include applicants and recruiters. Recruiters receive notifications from the system and review evaluation results to advance their recruitment activities. During interviews, they can gain a deeper understanding of candidates based on real-time sentiment analysis information provided by the server.

[0399] This system begins with applicants submitting their resumes through a web portal. The server receives this data and stores it in a structured format. Next, AI technology is used to extract the applicant's emotional characteristics and comprehensively evaluate them by comparing their technical skills and emotional information with the job requirements. Based on this evaluation, the server lists suitable candidates and notifies the user via email.

[0400] As a concrete example, when a company recruits for a sales position, the server analyzes the emotional characteristics of the presentation materials and self-introductions received from applicants, and uses the results to evaluate their adaptability to the company culture. During the interview, the terminal transmits the candidate's voice and facial expression data to the server for real-time analysis. Based on this information, the recruiter makes a decision considering factors such as the applicant's flexibility and stress tolerance.

[0401] An example of a prompt to input into the generating AI model is: "Analyze the emotional characteristics of applicants suitable for sales positions, evaluate their adaptability to the company culture, and create a report."

[0402] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0403] Step 1:

[0404] The user (applicant) submits their resume through a web portal. The information received includes the applicant's name, contact information, work history, educational background, and a self-introduction. This data is then sent to the server.

[0405] Step 2:

[0406] The server receives resume data from applicants and stores it in a structured format in the database. It analyzes the entered resume information and organizes it into individual fields for each applicant. This process yields structured data output.

[0407] Step 3:

[0408] The server applies an emotion engine using generative AI technology to the stored applicant data. The input consists of descriptions from self-introduction statements and work histories, and emotional characteristics are extracted using natural language processing. After extraction, emotion scoring is performed, and the results are output.

[0409] Step 4:

[0410] The server compares emotional scores and technical skills data with job requirements. It uses job requirements and extracted skills data as input. After the comparison, it evaluates the degree of fit and generates a list of overall candidate ratings as output.

[0411] Step 5:

[0412] The server creates a list of suitable applicants based on the overall evaluation and notifies the user (recruiter). The notification uses an email service, and the output includes the list of candidates and detailed evaluation information.

[0413] Step 6:

[0414] The device collects the candidate's audio and video in real time during the interview. Here, it uses the camera and microphone to send non-verbal data (voice tone, facial expressions) as input to the server.

[0415] Step 7:

[0416] The server analyzes the data sent from the terminal in real time. Using an emotion engine, it generates emotional data such as the candidate's level of relaxation and tension, and outputs this as an evaluation report.

[0417] Step 8:

[0418] The server provides feedback to the user (recruiter) based on the evaluation results after the interview. It also suggests appropriate interview schedules to guide the next selection step. The output includes a feedback message and an optimal interview schedule.

[0419] (Application Example 2)

[0420] 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."

[0421] Traditional recruitment processes have limitations in evaluating applicants based on their skills and experience, making it difficult to adequately assess emotional compatibility and adaptability to the company culture. Furthermore, increased stress due to a lack of communication within the family and the inability to understand and appropriately respond to family members' emotions has been identified as a problem.

[0422] 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.

[0423] In this invention, the server includes means for determining the user's emotional state using emotion analysis technology in a mobile device and optimizing suggestions; means for receiving and storing applicant data; and means for analyzing applicant data using a generative model and extracting skills and experience. This enables more efficient recruitment processes and allows home robots to understand the emotions of family members.

[0424] "Applicant data" refers to the resume, work history, and related information provided by an applicant for a specific job.

[0425] A "generative model" refers to an algorithm or framework used to analyze data using artificial intelligence technology, and is particularly used in natural language processing and pattern recognition.

[0426] "Skills and experience" refers to the knowledge, abilities, past work history, and achievements that an applicant possesses in relation to a specific job.

[0427] "Evaluating" means analyzing and judging an applicant's suitability and potential based on various criteria.

[0428] "Listing" refers to the process of compiling and clearly identifying individuals who have been selected based on specific criteria.

[0429] "Mobile devices" refer to devices such as household robots and smart devices that have the ability to collect and process information while operating in different locations.

[0430] "Emotional analysis technology" refers to technology used to automatically analyze emotions and psychological states from voice and facial expression data.

[0431] "Optimizing suggestions" refers to the process of presenting the most suitable actions and options based on the user's situation and needs.

[0432] This invention is a system that receives applicant data and evaluates that data using emotion analysis technology. Furthermore, it enables the analysis of emotional states in mobile devices within the home, such as household robots, and provides optimal suggestions.

[0433] The server receives and stores applicant data from users. This data includes resumes and work histories and is stored as structured data within the server. The server analyzes this data using a generative model to extract the applicant's skills and experience. During the analysis process, an AI-powered sentiment analysis engine is used to extract emotional nuances from the applicant's data and to evaluate the applicant's suitability from multiple perspectives.

[0434] In mobile devices, the system collects user voice and facial expression data via cameras and microphones, and analyzes their emotional state in real time. Specifically, it runs an emotion analysis model using Python and TensorFlow on an embedded platform such as a Raspberry Pi. Based on the analyzed emotion data, the mobile device can make appropriate suggestions to the user.

[0435] A concrete example is a scenario where a home robot understands the user's emotions and makes a suggestion such as, "You seem a little tired today, shall I make you some tea?" This is achieved by the mobile robot determining the user's emotions from facial expression data and voice analysis, and then generating a response. An example of a prompt to the generating AI model would be, "Please tell me how a home robot can use emotion analysis to optimize communication with family members."

[0436] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0437] Step 1:

[0438] The server receives and stores applicant data from users. This input data includes resumes and work history documents. The server stores this data as structured data in a database so that it can be used for later analysis.

[0439] Step 2:

[0440] The server retrieves applicant data from the database and analyzes it using a generative AI model. Specifically, the data includes information about skills and experience, and the model extracts these elements, along with analyzing emotional nuances. The output of this process is a structure of skills, experience, and emotional evaluations.

[0441] Step 3:

[0442] The server compares the analysis results obtained in Step 2 with the job requirements. The input provided is a structured list of the applicant's skills and experience, along with the requirements sought by the company. The server then evaluates the applicant's suitability and performs scoring. The output generates an evaluation list of suitable candidates.

[0443] Step 4:

[0444] The device collects sensor data to analyze the user's emotions in a mobile home environment. Specifically, it collects facial expression data using a camera and acquires audio data using a microphone. This sensor data is input into the system and processed in real time.

[0445] Step 5:

[0446] The device processes collected sensor data using emotion analysis technology. Based on the input data, the mobile device analyzes the user's current emotional state and makes suggestions based on the analysis results. The output consists of specific action suggestions and communication content for the user.

[0447] Step 6:

[0448] Suggestions are made to the user. For example, a mobile object might say, "You seem a little tired today, shall I make you some tea?" and an appropriate response is taken based on sentiment analysis. This prompt is generated based on sentiment analysis data.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] [Third Embodiment]

[0453] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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".

[0465] This invention is a system designed to streamline the recruitment process and is specifically implemented in the following manner.

[0466] Receiving and storing applicant data:

[0467] Users (applicants) can submit their resumes through the web portal. Submitted resumes are received by the server and automatically and securely stored in the database.

[0468] Resume analysis:

[0469] The server analyzes the contents of the stored resumes using a generative model. This process uses NLP techniques to extract the applicant's skills and work experience from the text and stores it as structured data.

[0470] Skill and experience assessment:

[0471] Based on the analyzed data, the server matches the applicant's skills and experience against the company's job requirements. This comparison allows the server to score the applicant and assess the candidate's suitability.

[0472] Listing candidates:

[0473] Based on the evaluation results, the server lists suitable candidates and notifies recruiters (users) of this information, thereby supporting a rapid selection process.

[0474] Proposed and finalized interview schedule:

[0475] Users (recruiters) can enter their interview preferences for listed candidates into the system. The server retrieves the availability of both parties from the calendar system and suggests the most suitable interview date and time. The suggested schedule is notified to both the candidate and the recruiter, and if approved, it is officially announced to everyone.

[0476] Specific example:

[0477] For example, suppose a company is recruiting programmers, and the user (recruiter) manages a large number of resumes through an AI system. Let's say one applicant has a skill set of "Java programming" and "5 years of full-stack development experience." The server analyzes this information and determines that it matches the company's requirement of "5 years or more of Java experience," and lists the candidate as a high-scoring candidate. The recruiter reviews and approves the interview date and time suggested by the AI ​​system, and the candidate is notified of the interview date.

[0478] Thus, the present invention automates a key part of the recruitment process, enabling efficient talent selection and interview scheduling.

[0479] The following describes the processing flow.

[0480] Step 1:

[0481] Users (applicants) submit their resumes through a web portal. The resumes contain information about the applicant's skills and work experience in text format.

[0482] Step 2:

[0483] The server receives resumes submitted by applicants. The received data is securely stored in a database according to security protocols.

[0484] Step 3:

[0485] The server analyzes the stored resume data using a generative model. This analysis utilizes natural language processing (NLP) techniques to extract applicants' skills, qualifications, and work experience from the text and stores them in a database as quantified indicators.

[0486] Step 4:

[0487] The server comprehensively matches the analyzed applicants' skills and experience with the job requirements provided by the company. It then scores the applicants' suitability and selects candidates with high scores.

[0488] Step 5:

[0489] The server lists the selected candidates and notifies the recruiter (user) of the candidate list. The notification includes an overview of the candidates' main skills and experience.

[0490] Step 6:

[0491] The user (recruiter) reviews the candidate list and selects the candidates they wish to interview. The selection results are entered into the system.

[0492] Step 7:

[0493] The server retrieves calendar information from both recruiters and candidates, checks their availability, and automatically generates and suggests the optimal interview date and time.

[0494] Step 8:

[0495] The server notifies the recruiter and candidate of the proposed interview schedule and requests their approval. Approved schedules are then added to the calendar as official events.

[0496] Step 9:

[0497] Users (recruiters and candidates) review the proposed schedule and provide feedback if approval or adjustments are needed. The interview schedule is finalized through this process.

[0498] (Example 1)

[0499] 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."

[0500] In modern recruitment processes, a challenge is to quickly and efficiently select the best candidates from a large pool of applicants. Traditional methods involve the burdensome manual review of resumes and scheduling interviews, which requires significant time and resources from company representatives.

[0501] 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.

[0502] In this invention, the server includes means for receiving and storing applicant information, means for analyzing the applicant information using a generative AI model and extracting abilities and experience, and means for comparing the extracted information with job requirements and evaluating candidates. This automates the talent selection process and enables efficient candidate evaluation and interview planning.

[0503] A "device with the function of receiving and storing applicant information" is a device that has the ability to correctly receive applicant data transmitted from an external source and store it securely and efficiently on a recording medium.

[0504] A "device that uses a generative AI model to analyze applicant information and extract their abilities and experience" is a device that utilizes artificial intelligence technology to extract applicants' skills and backgrounds from text data and convert them into a useful format.

[0505] A "device that compares extracted information with job requirements and evaluates candidates" is a device that can compare an applicant's abilities and experience with job requirements and evaluate the candidate's suitability based on the degree of matching.

[0506] A "device that acquires the available time of company representatives and candidates and presents an interview plan" is a device that reads calendar information and schedules, calculates a convenient time for both parties, and presents the optimal interview date and time.

[0507] A "device with the function of notifying confirmed plans" is a device that has the ability to quickly and accurately communicate agreed-upon schedules and plans to all relevant parties.

[0508] This invention is a system for achieving efficient personnel selection and interview scheduling. Specific embodiments of the invention are described below.

[0509] First, the applicant, as the user, accesses the web portal using their device and fills out their resume in an online form. The server establishes a secure connection (such as SSL / TLS) to receive this information and stores the received data on a storage device. The database system used here enables secure and rapid data access.

[0510] Next, the server analyzes the applicant's stored resume using a generative AI model. Specifically, it leverages NLP techniques to automatically extract skills and work experience from the resume text and reorganize it as structured data. Open-source natural language processing libraries are often used for this task. An example of a prompt given to the model is, "Extract skills and experience from this text."

[0511] Furthermore, the server uses the extracted information to perform a process that compares the job requirements sought by the company with the applicant's skill set and experience. This process quantifies and scores how well the applicant matches the requirements.

[0512] Once the evaluation is complete, the server uses the scoring results to list suitable candidates for the company representative. This list is displayed in real time on the company representative's dashboard to support rapid decision-making.

[0513] Furthermore, company representatives can enter their preferred interview dates into the system, and the server checks the availability of both parties via a calendar API. It then proposes the optimal date and time, and the agreed-upon plan is notified to all stakeholders, enabling smooth scheduling. This notification process, conducted via email and application notifications, significantly reduces scheduling errors.

[0514] The introduction of this system eliminates the need for users to manually process a vast number of resumes, shortening the hiring process and saving resources.

[0515] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0516] Step 1:

[0517] Applicants, as users, access the web portal using their device and fill out and submit their resume information in an online form. The input data includes skills, work experience, and contact information in text format. The device aggregates this data into the form and sends it to the server. The server receives the applicant's data and stores it in a database using a secure protocol. The output is a confirmation message for the saved data.

[0518] Step 2:

[0519] The server uses a generative AI model to analyze data based on the stored resume information. It receives the stored text data as input and prompts the generative AI model with the message, "Extract skills and experience from this text." For data processing, NLP techniques are used to extract the applicant's skills and work experience from the text and store it in a structured format in the database. The output is structured skills and experience data.

[0520] Step 3:

[0521] The server compares a company's job requirements with the applicant's skill set and experience based on structured data obtained through analysis. It receives structured data of applicants and job requirements provided by the company as input. The server uses a specific algorithm to match the two and perform scoring. As part of the data processing, it numerically evaluates the degree of match with the requirements and determines a score for each applicant. The output is the evaluation score for each applicant.

[0522] Step 4:

[0523] The server lists suitable candidates based on the scoring results. It receives evaluation scores as input and selects applicants who meet or exceed a specific threshold. The listed candidate information is reflected on the company representative's dashboard. Specifically, the candidate list is notified to the company representative in real time via email and the dashboard. The output is information about the listed candidates.

[0524] Step 5:

[0525] The user, a company representative, enters their preferred interview dates into the system. The server retrieves the calendar information of both the company representative and the candidate via an API and calculates the optimal interview date and time. It receives the availability of both the company representative and the candidate as input and generates the optimal schedule through calculation. Specifically, the proposed date and time are sent via email or notification for confirmation by both parties. The output is the proposed interview date and time.

[0526] Step 6:

[0527] The server notifies all stakeholders of the confirmed interview schedule. It receives agreed-upon interview dates and times as input and communicates the schedule via email and app notifications as output. Specifically, the notification includes links and detailed information for review. This process minimizes misunderstandings and schedule changes.

[0528] (Application Example 1)

[0529] 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."

[0530] Currently, there are challenges in selecting suitable robot operators for industrial facilities, including the difficulty of quickly and accurately identifying the right person and effectively scheduling interviews. In particular, finding the optimal candidate from a large pool of applicants is time-consuming and places a significant burden on managers. Therefore, there is a need for a method that automates applicant data analysis and scheduling, thereby streamlining the recruitment process for industrial facilities.

[0531] 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.

[0532] In this invention, the server includes means for receiving applicant information and storing it in an information warehouse, means for analyzing the applicant information using a generative AI model and extracting skills and experience, and means for evaluating and scoring the suitability of candidates in order to select candidates suitable for industrial facilities. This enables the automation of efficient personnel selection and interview proposals in industrial facilities.

[0533] An "applicant" refers to a person who wishes to engage in operational work at an industrial facility.

[0534] An "information warehouse" refers to a database system used to store data about applicants.

[0535] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to perform data analysis.

[0536] "Technical skills and experience" refers to the job skills and past work history of the applicant.

[0537] "Industrial facilities" refer to production bases where manufacturing, processing, and other related industries take place.

[0538] A "candidate" refers to a suitable individual selected from among the applicants based on specific criteria.

[0539] "Fit" refers to an indicator that shows how well a candidate's skills and experience match the job requirements.

[0540] "Scoring" refers to the process of evaluating candidates and assigning them numerical scores.

[0541] An "interview appointment" refers to a date and time set aside for a candidate and a recruiter to meet in person.

[0542] The term "administrator" refers to the person responsible for selecting personnel in an industrial facility.

[0543] "Communication" refers to the exchange of notifications and information using a system.

[0544] This invention provides a system for efficiently selecting personnel and automatically scheduling interviews in industrial facilities. The system mainly consists of a server, an administrator terminal (smartphone or personal computer), and cloud-based software.

[0545] The server receives applicant information and securely stores it in a database acting as an information repository. The applicant information is analyzed using a generative AI model to extract skills and experience. This process utilizes the Google Cloud NLP API to analyze text data. The extracted information is then scored for suitability to the needs of the industrial facility, and a list of appropriate candidates is compiled.

[0546] The administrator terminal receives data from the server and provides an interface for administrators to review candidates. This interface allows administrators to use their smartphones to review and approve candidates and interview schedules suggested based on a generated AI model.

[0547] This system streamlines the personnel selection process in industrial facilities and reduces the burden on managers. For example, when a factory hires a new robot operator, an applicant's experience of "5 years of robot arm operation" is compared against the factory's requirement of "3 years or more of operation experience," and they are given a high score and automatically added to the candidate list.

[0548] An example of a prompt message might be, "Enter the applicant's operational skills and list suitable operator candidates." This prompt serves as a criterion for how the system operates and selects applicants.

[0549] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0550] Step 1:

[0551] The server receives job application data from applicant terminals and stores it in a database that functions as an information repository. The input consists of resumes and profile information submitted by applicants, and the purpose is to store this information securely. The output is a status indicating successful saving.

[0552] Step 2:

[0553] The server uses a generative AI model based on stored data to analyze text data. The input is text data from resumes stored in a database, and the Google Cloud NLP API is used to extract applicant skills and experience. The output is structured skills and experience data.

[0554] Step 3:

[0555] The server compares the extracted skills and experience with the job requirements of industrial facilities. The inputs for this process are analyzed skill data and pre-registered job requirement data. A generating AI model evaluates the fit and assigns a score to each candidate. The output is the candidate's fit score.

[0556] Step 4:

[0557] The server lists suitable candidates based on the evaluation results. The input is scored candidate data, and applicants whose scores exceed a certain value are selected. The output of this process is a list of candidates.

[0558] Step 5:

[0559] The administrator terminal receives and displays the list results from the server. The administrator uses the terminal to review candidate information and schedule interviews. The input is the listed candidate data, and the output is the decision to approve or reject interviews with the candidates.

[0560] Step 6:

[0561] The server, upon receiving administrator selection, automatically suggests interview schedules by referencing the candidate's and administrator's calendar data. The input consists of the administrator's and candidate's available time data. The server calculates the optimal date and time and provides the interview schedule as output.

[0562] 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.

[0563] This invention provides an improved system that understands user emotions in the recruitment process and supports decision-making during the selection process. The system incorporates an AI-powered emotion engine that can analyze the emotions of candidates and recruiters in real time during the interview process.

[0564] Receiving and storing applicant data:

[0565] Users (applicants) submit their resumes through a web portal following standard procedures. The server receives this information and stores it in a database as structured data.

[0566] Data analysis and evaluation:

[0567] In addition to conventional application data analysis, the server uses an emotion engine to extract emotional nuances from applicants' resumes. These analysis results are compared with job requirements along with extracted skills and experience information. Furthermore, by including emotional characteristics in the scoring, the suitability of applicants is evaluated from a more multifaceted perspective.

[0568] Listing and notifying candidates:

[0569] The server lists suitable candidates based on the scoring results and notifies the recruiter (user). This notification includes not only technical skills but also notable features based on sentiment recognition.

[0570] Sentimental analysis of the interview process:

[0571] The user (recruiter) can utilize an emotional interface to collect emotional data in real time during interviews. The terminal sends this information to a server, which uses an emotional engine to analyze the candidate's emotions and generates an evaluation report based on the results.

[0572] Proposed interview schedule:

[0573] The server considers emotional data and technical capabilities to suggest the optimal interview timing for each candidate. It also collects and analyzes post-interview feedback, referencing the recruiter's emotional data, to predict the success or failure of the interview and the next steps.

[0574] Specific example:

[0575] A company is recruiting for sales positions, and the user (recruiter) selects a few candidates from a large pool of applicants. During this process, the server uses an emotion engine to extract emotional elements from the candidates' submitted presentation materials and self-introductions, predicting their adaptability to the company culture. During the interview, the terminal analyzes the candidate's tone of voice and facial expressions in real time, drawing conclusions based on emotional factors such as flexibility and stress tolerance. Based on this comprehensive evaluation, the recruiter can make more accurate decisions.

[0576] Thus, the present invention provides an advanced recruitment support system that captures the emotional characteristics of candidates and improves the quality and efficiency of recruitment.

[0577] The following describes the processing flow.

[0578] Step 1:

[0579] Users (applicants) upload their resumes and related documents through a web portal. This may include work experience summaries and self-introduction videos.

[0580] Step 2:

[0581] The server stores the received applicant data in a secure database. Simultaneously, it begins the process of analyzing the resume and related documents.

[0582] Step 3:

[0583] The server uses a generative model to extract applicants' skills and experience from submitted materials. Furthermore, it uses an emotion engine to analyze emotional nuances from videos and audio, generating indicators such as positive, negative, and neutral.

[0584] Step 4:

[0585] The server matches job requirements with candidate analysis results and scores candidates based on their technical skills and emotional compatibility. This score indicates the overall suitability and serves as the criterion for listing candidates.

[0586] Step 5:

[0587] The server generates a list of high-scoring candidates and notifies the recruiter (user). This notification includes a detailed report based on skills and sentiment analysis.

[0588] Step 6:

[0589] The user (recruiter) selects candidates to proceed to interviews based on the information received from the system. This selection result is then fed back into the system.

[0590] Step 7:

[0591] During the interview, the device collects data such as the candidate's voice, facial expressions, and gestures in real time. This data is sent to a server and analyzed by an emotion engine.

[0592] Step 8:

[0593] The server collects emotional analysis data from the interview and evaluates the candidate's stress level and adaptability. This evaluation is reflected in the final candidate report provided by the system.

[0594] Step 9:

[0595] After the interview process is complete, the server provides the hiring manager with the analysis results, including a final evaluation of the candidate and recommendations for the next steps. The user can then use this information to make their final hiring decision.

[0596] (Example 2)

[0597] 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."

[0598] Traditional recruitment processes tend to focus heavily on evaluating applicants' technical skills and experience, failing to adequately consider emotional compatibility and suitability for the company culture. Furthermore, there are limited means of understanding candidates' psychological states in real time during interviews, highlighting the need for improved quality and efficiency in recruitment.

[0599] 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.

[0600] This invention includes a server that receives, structures, and stores applicant information; a server that extracts and comprehensively evaluates the applicant's emotional characteristics using generative AI technology; and a server that optimizes interview schedules between recruiters and candidates. This enables a multifaceted evaluation through emotional analysis, significantly improving the quality and efficiency of the recruitment process.

[0601] "Means for receiving and storing applicant information" refers to a function that acquires data provided by applicants and records it in digital format within the system.

[0602] "Means of storing applicant information in a structured format" refers to a function in a database that organizes and stores applicant information based on certain rules and formats.

[0603] "A means of analyzing applicant information and extracting emotional characteristics using generative AI technology" refers to a function that uses artificial intelligence technology, such as natural language processing, to analyze and identify emotional information from the applicant's submitted materials.

[0604] "Means of evaluating technical skills and emotional characteristics in comparison to job requirements" refers to a function that comprehensively assesses an applicant's technical skills and emotional aspects in light of the requirements sought by the company.

[0605] "A means of listing suitable applicants and notifying recruiters" refers to a function that selects applicants who meet the criteria based on the evaluation results and notifies them in list format.

[0606] "A means of analyzing the available time of recruiters and candidates and proposing the most suitable interview schedule" refers to a function that combines the schedules of both parties to calculate and provide the optimal interview date and time.

[0607] "Means of notifying confirmed schedules" refers to a function that communicates optimized interview dates and times to each party.

[0608] "A means of collecting and analyzing candidate emotional data in real time during an interview" refers to a function that acquires emotional data during an interview and immediately analyzes and evaluates it.

[0609] "Means of providing post-interview evaluation results" refers to a function that reports evaluations based on the data collected during interviews to relevant parties at a later date.

[0610] This invention is a system that understands the emotions of applicants and recruiters in the recruitment process and supports selection decision-making. This system uses the following hardware and software.

[0611] The server runs on a cloud computing platform and uses an engine incorporating AI technology. This AI engine is equipped with natural language processing (NLP) technology and interacts with external services such as the Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0612] The devices are typical personal computers or tablet devices. They have built-in webcams and microphones and are used to collect audio and video data during interviews. The software on the devices has the capability to transmit this data to a server in real time.

[0613] Users include applicants and recruiters. Recruiters receive notifications from the system and review evaluation results to advance their recruitment activities. During interviews, they can gain a deeper understanding of candidates based on real-time sentiment analysis information provided by the server.

[0614] This system begins with applicants submitting their resumes through a web portal. The server receives this data and stores it in a structured format. Next, AI technology is used to extract the applicant's emotional characteristics and comprehensively evaluate them by comparing their technical skills and emotional information with the job requirements. Based on this evaluation, the server lists suitable candidates and notifies the user via email.

[0615] As a concrete example, when a company recruits for a sales position, the server analyzes the emotional characteristics of the presentation materials and self-introductions received from applicants, and uses the results to evaluate their adaptability to the company culture. During the interview, the terminal transmits the candidate's voice and facial expression data to the server for real-time analysis. Based on this information, the recruiter makes a decision considering factors such as the applicant's flexibility and stress tolerance.

[0616] An example of a prompt to input into the generating AI model is: "Analyze the emotional characteristics of applicants suitable for sales positions, evaluate their adaptability to the company culture, and create a report."

[0617] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0618] Step 1:

[0619] The user (applicant) submits their resume through a web portal. The information received includes the applicant's name, contact information, work history, educational background, and a self-introduction. This data is then sent to the server.

[0620] Step 2:

[0621] The server receives resume data from applicants and stores it in a structured format in the database. It analyzes the entered resume information and organizes it into individual fields for each applicant. This process yields structured data output.

[0622] Step 3:

[0623] The server applies an emotion engine using generative AI technology to the stored applicant data. The input consists of descriptions from self-introduction statements and work histories, and emotional characteristics are extracted using natural language processing. After extraction, emotion scoring is performed, and the results are output.

[0624] Step 4:

[0625] The server compares emotional scores and technical skills data with job requirements. It uses job requirements and extracted skills data as input. After the comparison, it evaluates the degree of fit and generates a list of overall candidate ratings as output.

[0626] Step 5:

[0627] The server creates a list of suitable applicants based on the overall evaluation and notifies the user (recruiter). The notification uses an email service, and the output includes the list of candidates and detailed evaluation information.

[0628] Step 6:

[0629] The device collects the candidate's audio and video in real time during the interview. Here, it uses the camera and microphone to send non-verbal data (voice tone, facial expressions) as input to the server.

[0630] Step 7:

[0631] The server analyzes the data sent from the terminal in real time. Using an emotion engine, it generates emotional data such as the candidate's level of relaxation and tension, and outputs this as an evaluation report.

[0632] Step 8:

[0633] The server provides feedback to the user (recruiter) based on the evaluation results after the interview. It also suggests appropriate interview schedules to guide the next selection step. The output includes a feedback message and an optimal interview schedule.

[0634] (Application Example 2)

[0635] 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."

[0636] Traditional recruitment processes have limitations in evaluating applicants based on their skills and experience, making it difficult to adequately assess emotional compatibility and adaptability to the company culture. Furthermore, increased stress due to a lack of communication within the family and the inability to understand and appropriately respond to family members' emotions has been identified as a problem.

[0637] 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.

[0638] In this invention, the server includes means for determining the user's emotional state using emotion analysis technology in a mobile device and optimizing suggestions; means for receiving and storing applicant data; and means for analyzing applicant data using a generative model and extracting skills and experience. This enables more efficient recruitment processes and allows home robots to understand the emotions of family members.

[0639] "Applicant data" refers to the resume, work history, and related information provided by an applicant for a specific job.

[0640] A "generative model" refers to an algorithm or framework used to analyze data using artificial intelligence technology, and is particularly used in natural language processing and pattern recognition.

[0641] "Skills and experience" refers to the knowledge, abilities, past work history, and achievements that an applicant possesses in relation to a specific job.

[0642] "Evaluating" means analyzing and judging an applicant's suitability and potential based on various criteria.

[0643] "Listing" refers to the process of compiling and clearly identifying individuals who have been selected based on specific criteria.

[0644] "Mobile devices" refer to devices such as household robots and smart devices that have the ability to collect and process information while operating in different locations.

[0645] "Emotional analysis technology" refers to technology used to automatically analyze emotions and psychological states from voice and facial expression data.

[0646] "Optimizing suggestions" refers to the process of presenting the most suitable actions and options based on the user's situation and needs.

[0647] This invention is a system that receives applicant data and evaluates that data using emotion analysis technology. Furthermore, it enables the analysis of emotional states in mobile devices within the home, such as household robots, and provides optimal suggestions.

[0648] The server receives and stores applicant data from users. This data includes resumes and work histories and is stored as structured data within the server. The server analyzes this data using a generative model to extract the applicant's skills and experience. During the analysis process, an AI-powered sentiment analysis engine is used to extract emotional nuances from the applicant's data and to evaluate the applicant's suitability from multiple perspectives.

[0649] In mobile devices, the system collects user voice and facial expression data via cameras and microphones, and analyzes their emotional state in real time. Specifically, it runs an emotion analysis model using Python and TensorFlow on an embedded platform such as a Raspberry Pi. Based on the analyzed emotion data, the mobile device can make appropriate suggestions to the user.

[0650] A concrete example is a scenario where a home robot understands the user's emotions and makes a suggestion such as, "You seem a little tired today, shall I make you some tea?" This is achieved by the mobile robot determining the user's emotions from facial expression data and voice analysis, and then generating a response. An example of a prompt to the generating AI model would be, "Please tell me how a home robot can use emotion analysis to optimize communication with family members."

[0651] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0652] Step 1:

[0653] The server receives and stores applicant data from users. This input data includes resumes and work history documents. The server stores this data as structured data in a database so that it can be used for later analysis.

[0654] Step 2:

[0655] The server retrieves applicant data from the database and analyzes it using a generative AI model. Specifically, the data includes information about skills and experience, and the model extracts these elements, along with analyzing emotional nuances. The output of this process is a structure of skills, experience, and emotional evaluations.

[0656] Step 3:

[0657] The server compares the analysis results obtained in Step 2 with the job requirements. The input provided is a structured list of the applicant's skills and experience, along with the requirements sought by the company. The server then evaluates the applicant's suitability and performs scoring. The output generates an evaluation list of suitable candidates.

[0658] Step 4:

[0659] The device collects sensor data to analyze the user's emotions in a mobile home environment. Specifically, it collects facial expression data using a camera and acquires audio data using a microphone. This sensor data is input into the system and processed in real time.

[0660] Step 5:

[0661] The device processes collected sensor data using emotion analysis technology. Based on the input data, the mobile device analyzes the user's current emotional state and makes suggestions based on the analysis results. The output consists of specific action suggestions and communication content for the user.

[0662] Step 6:

[0663] Suggestions are made to the user. For example, a mobile object might say, "You seem a little tired today, shall I make you some tea?" and an appropriate response is taken based on sentiment analysis. This prompt is generated based on sentiment analysis data.

[0664] 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.

[0665] 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.

[0666] 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.

[0667] [Fourth Embodiment]

[0668] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0669] 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.

[0670] 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).

[0671] 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.

[0672] 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.

[0673] 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).

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] 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".

[0681] This invention is a system designed to streamline the recruitment process and is specifically implemented in the following manner.

[0682] Receiving and storing applicant data:

[0683] Users (applicants) can submit their resumes through the web portal. Submitted resumes are received by the server and automatically and securely stored in the database.

[0684] Resume analysis:

[0685] The server analyzes the contents of the stored resumes using a generative model. This process uses NLP techniques to extract the applicant's skills and work experience from the text and stores it as structured data.

[0686] Skill and experience assessment:

[0687] Based on the analyzed data, the server matches the applicant's skills and experience against the company's job requirements. This comparison allows the server to score the applicant and assess the candidate's suitability.

[0688] Listing candidates:

[0689] Based on the evaluation results, the server lists suitable candidates and notifies recruiters (users) of this information, thereby supporting a rapid selection process.

[0690] Proposed and finalized interview schedule:

[0691] Users (recruiters) can enter their interview preferences for listed candidates into the system. The server retrieves the availability of both parties from the calendar system and suggests the most suitable interview date and time. The suggested schedule is notified to both the candidate and the recruiter, and if approved, it is officially announced to everyone.

[0692] Specific example:

[0693] For example, suppose a company is recruiting programmers, and the user (recruiter) manages a large number of resumes through an AI system. Let's say one applicant has a skill set of "Java programming" and "5 years of full-stack development experience." The server analyzes this information and determines that it matches the company's requirement of "5 years or more of Java experience," and lists the candidate as a high-scoring candidate. The recruiter reviews and approves the interview date and time suggested by the AI ​​system, and the candidate is notified of the interview date.

[0694] Thus, the present invention automates a key part of the recruitment process, enabling efficient talent selection and interview scheduling.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] Users (applicants) submit their resumes through a web portal. The resumes contain information about the applicant's skills and work experience in text format.

[0698] Step 2:

[0699] The server receives resumes submitted by applicants. The received data is securely stored in a database according to security protocols.

[0700] Step 3:

[0701] The server analyzes the stored resume data using a generative model. This analysis utilizes natural language processing (NLP) techniques to extract applicants' skills, qualifications, and work experience from the text and stores them in a database as quantified indicators.

[0702] Step 4:

[0703] The server comprehensively matches the analyzed applicants' skills and experience with the job requirements provided by the company. It then scores the applicants' suitability and selects candidates with high scores.

[0704] Step 5:

[0705] The server lists the selected candidates and notifies the recruiter (user) of the candidate list. The notification includes an overview of the candidates' main skills and experience.

[0706] Step 6:

[0707] The user (recruiter) reviews the candidate list and selects the candidates they wish to interview. The selection results are entered into the system.

[0708] Step 7:

[0709] The server retrieves calendar information from both recruiters and candidates, checks their availability, and automatically generates and suggests the optimal interview date and time.

[0710] Step 8:

[0711] The server notifies the recruiter and candidate of the proposed interview schedule and requests their approval. Approved schedules are then added to the calendar as official events.

[0712] Step 9:

[0713] Users (recruiters and candidates) review the proposed schedule and provide feedback if approval or adjustments are needed. The interview schedule is finalized through this process.

[0714] (Example 1)

[0715] 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".

[0716] In modern recruitment processes, a challenge is to quickly and efficiently select the best candidates from a large pool of applicants. Traditional methods involve the burdensome manual review of resumes and scheduling interviews, which requires significant time and resources from company representatives.

[0717] 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.

[0718] In this invention, the server includes means for receiving and storing applicant information, means for analyzing the applicant information using a generative AI model and extracting abilities and experience, and means for comparing the extracted information with job requirements and evaluating candidates. This automates the talent selection process and enables efficient candidate evaluation and interview planning.

[0719] A "device with the function of receiving and storing applicant information" is a device that has the ability to correctly receive applicant data transmitted from an external source and store it securely and efficiently on a recording medium.

[0720] A "device that uses a generative AI model to analyze applicant information and extract their abilities and experience" is a device that utilizes artificial intelligence technology to extract applicants' skills and backgrounds from text data and convert them into a useful format.

[0721] A "device that compares extracted information with job requirements and evaluates candidates" is a device that can compare an applicant's abilities and experience with job requirements and evaluate the candidate's suitability based on the degree of matching.

[0722] A "device that acquires the available time of company representatives and candidates and presents an interview plan" is a device that reads calendar information and schedules, calculates a convenient time for both parties, and presents the optimal interview date and time.

[0723] A "device with the function of notifying confirmed plans" is a device that has the ability to quickly and accurately communicate agreed-upon schedules and plans to all relevant parties.

[0724] This invention is a system for achieving efficient personnel selection and interview scheduling. Specific embodiments of the invention are described below.

[0725] First, the applicant, as the user, accesses the web portal using their device and fills out their resume in an online form. The server establishes a secure connection (such as SSL / TLS) to receive this information and stores the received data on a storage device. The database system used here enables secure and rapid data access.

[0726] Next, the server analyzes the applicant's stored resume using a generative AI model. Specifically, it leverages NLP techniques to automatically extract skills and work experience from the resume text and reorganize it as structured data. Open-source natural language processing libraries are often used for this task. An example of a prompt given to the model is, "Extract skills and experience from this text."

[0727] Furthermore, the server uses the extracted information to perform a process that compares the job requirements sought by the company with the applicant's skill set and experience. This process quantifies and scores how well the applicant matches the requirements.

[0728] Once the evaluation is complete, the server uses the scoring results to list suitable candidates for the company representative. This list is displayed in real time on the company representative's dashboard to support rapid decision-making.

[0729] Furthermore, company representatives can enter their preferred interview dates into the system, and the server checks the availability of both parties via a calendar API. It then proposes the optimal date and time, and the agreed-upon plan is notified to all stakeholders, enabling smooth scheduling. This notification process, conducted via email and application notifications, significantly reduces scheduling errors.

[0730] The introduction of this system eliminates the need for users to manually process a vast number of resumes, shortening the hiring process and saving resources.

[0731] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0732] Step 1:

[0733] Applicants, as users, access the web portal using their device and fill out and submit their resume information in an online form. The input data includes skills, work experience, and contact information in text format. The device aggregates this data into the form and sends it to the server. The server receives the applicant's data and stores it in a database using a secure protocol. The output is a confirmation message for the saved data.

[0734] Step 2:

[0735] The server uses a generative AI model to analyze data based on the stored resume information. It receives the stored text data as input and prompts the generative AI model with the message, "Extract skills and experience from this text." For data processing, NLP techniques are used to extract the applicant's skills and work experience from the text and store it in a structured format in the database. The output is structured skills and experience data.

[0736] Step 3:

[0737] The server compares a company's job requirements with the applicant's skill set and experience based on structured data obtained through analysis. It receives structured data of applicants and job requirements provided by the company as input. The server uses a specific algorithm to match the two and perform scoring. As part of the data processing, it numerically evaluates the degree of match with the requirements and determines a score for each applicant. The output is the evaluation score for each applicant.

[0738] Step 4:

[0739] The server lists suitable candidates based on the scoring results. It receives evaluation scores as input and selects applicants who meet or exceed a specific threshold. The listed candidate information is reflected on the company representative's dashboard. Specifically, the candidate list is notified to the company representative in real time via email and the dashboard. The output is information about the listed candidates.

[0740] Step 5:

[0741] The user, a company representative, enters their preferred interview dates into the system. The server retrieves the calendar information of both the company representative and the candidate via an API and calculates the optimal interview date and time. It receives the availability of both the company representative and the candidate as input and generates the optimal schedule through calculation. Specifically, the proposed date and time are sent via email or notification for confirmation by both parties. The output is the proposed interview date and time.

[0742] Step 6:

[0743] The server notifies all stakeholders of the confirmed interview schedule. It receives agreed-upon interview dates and times as input and communicates the schedule via email and app notifications as output. Specifically, the notification includes links and detailed information for review. This process minimizes misunderstandings and schedule changes.

[0744] (Application Example 1)

[0745] 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".

[0746] Currently, there are challenges in selecting suitable robot operators for industrial facilities, including the difficulty of quickly and accurately identifying the right person and effectively scheduling interviews. In particular, finding the optimal candidate from a large pool of applicants is time-consuming and places a significant burden on managers. Therefore, there is a need for a method that automates applicant data analysis and scheduling, thereby streamlining the recruitment process for industrial facilities.

[0747] 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.

[0748] In this invention, the server includes means for receiving applicant information and storing it in an information warehouse, means for analyzing the applicant information using a generative AI model and extracting skills and experience, and means for evaluating and scoring the suitability of candidates in order to select candidates suitable for industrial facilities. This enables the automation of efficient personnel selection and interview proposals in industrial facilities.

[0749] An "applicant" refers to a person who wishes to engage in operational work at an industrial facility.

[0750] An "information warehouse" refers to a database system used to store data about applicants.

[0751] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to perform data analysis.

[0752] "Technical skills and experience" refers to the job skills and past work history of the applicant.

[0753] "Industrial facilities" refer to production bases where manufacturing, processing, and other related industries take place.

[0754] A "candidate" refers to a suitable individual selected from among the applicants based on specific criteria.

[0755] "Fit" refers to an indicator that shows how well a candidate's skills and experience match the job requirements.

[0756] "Scoring" refers to the process of evaluating candidates and assigning them numerical scores.

[0757] An "interview appointment" refers to a date and time set aside for a candidate and a recruiter to meet in person.

[0758] The term "administrator" refers to the person responsible for selecting personnel in an industrial facility.

[0759] "Communication" refers to the exchange of notifications and information using a system.

[0760] This invention provides a system for efficiently selecting personnel and automatically scheduling interviews in industrial facilities. The system mainly consists of a server, an administrator terminal (smartphone or personal computer), and cloud-based software.

[0761] The server receives applicant information and securely stores it in a database acting as an information repository. The applicant information is analyzed using a generative AI model to extract skills and experience. This process utilizes the Google Cloud NLP API to analyze text data. The extracted information is then scored for suitability to the needs of the industrial facility, and a list of appropriate candidates is compiled.

[0762] The administrator terminal receives data from the server and provides an interface for administrators to review candidates. This interface allows administrators to use their smartphones to review and approve candidates and interview schedules suggested based on a generated AI model.

[0763] This system streamlines the personnel selection process in industrial facilities and reduces the burden on managers. For example, when a factory hires a new robot operator, an applicant's experience of "5 years of robot arm operation" is compared against the factory's requirement of "3 years or more of operation experience," and they are given a high score and automatically added to the candidate list.

[0764] An example of a prompt message might be, "Enter the applicant's operational skills and list suitable operator candidates." This prompt serves as a criterion for how the system operates and selects applicants.

[0765] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0766] Step 1:

[0767] The server receives job application data from applicant terminals and stores it in a database that functions as an information repository. The input consists of resumes and profile information submitted by applicants, and the purpose is to store this information securely. The output is a status indicating successful saving.

[0768] Step 2:

[0769] The server uses a generative AI model based on stored data to analyze text data. The input is text data from resumes stored in a database, and the Google Cloud NLP API is used to extract applicant skills and experience. The output is structured skills and experience data.

[0770] Step 3:

[0771] The server compares the extracted skills and experience with the job requirements of industrial facilities. The inputs for this process are analyzed skill data and pre-registered job requirement data. A generating AI model evaluates the fit and assigns a score to each candidate. The output is the candidate's fit score.

[0772] Step 4:

[0773] The server lists suitable candidates based on the evaluation results. The input is scored candidate data, and applicants whose scores exceed a certain value are selected. The output of this process is a list of candidates.

[0774] Step 5:

[0775] The administrator terminal receives and displays the list results from the server. The administrator uses the terminal to review candidate information and schedule interviews. The input is the listed candidate data, and the output is the decision to approve or reject interviews with the candidates.

[0776] Step 6:

[0777] The server, upon receiving administrator selection, automatically suggests interview schedules by referencing the candidate's and administrator's calendar data. The input consists of the administrator's and candidate's available time data. The server calculates the optimal date and time and provides the interview schedule as output.

[0778] 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.

[0779] This invention provides an improved system that understands user emotions in the recruitment process and supports decision-making during the selection process. The system incorporates an AI-powered emotion engine that can analyze the emotions of candidates and recruiters in real time during the interview process.

[0780] Receiving and storing applicant data:

[0781] Users (applicants) submit their resumes through a web portal following standard procedures. The server receives this information and stores it in a database as structured data.

[0782] Data analysis and evaluation:

[0783] In addition to conventional application data analysis, the server uses an emotion engine to extract emotional nuances from applicants' resumes. These analysis results are compared with job requirements along with extracted skills and experience information. Furthermore, by including emotional characteristics in the scoring, the suitability of applicants is evaluated from a more multifaceted perspective.

[0784] Listing and notifying candidates:

[0785] The server lists suitable candidates based on the scoring results and notifies the recruiter (user). This notification includes not only technical skills but also notable features based on sentiment recognition.

[0786] Sentimental analysis of the interview process:

[0787] The user (recruiter) can utilize an emotional interface to collect emotional data in real time during interviews. The terminal sends this information to a server, which uses an emotional engine to analyze the candidate's emotions and generates an evaluation report based on the results.

[0788] Proposed interview schedule:

[0789] The server considers emotional data and technical capabilities to suggest the optimal interview timing for each candidate. It also collects and analyzes post-interview feedback, referencing the recruiter's emotional data, to predict the success or failure of the interview and the next steps.

[0790] Specific example:

[0791] A company is recruiting for sales positions, and the user (recruiter) selects a few candidates from a large pool of applicants. During this process, the server uses an emotion engine to extract emotional elements from the candidates' submitted presentation materials and self-introductions, predicting their adaptability to the company culture. During the interview, the terminal analyzes the candidate's tone of voice and facial expressions in real time, drawing conclusions based on emotional factors such as flexibility and stress tolerance. Based on this comprehensive evaluation, the recruiter can make more accurate decisions.

[0792] Thus, the present invention provides an advanced recruitment support system that captures the emotional characteristics of candidates and improves the quality and efficiency of recruitment.

[0793] The following describes the processing flow.

[0794] Step 1:

[0795] Users (applicants) upload their resumes and related documents through a web portal. This may include work experience summaries and self-introduction videos.

[0796] Step 2:

[0797] The server stores the received applicant data in a secure database. Simultaneously, it begins the process of analyzing the resume and related documents.

[0798] Step 3:

[0799] The server uses a generative model to extract applicants' skills and experience from submitted materials. Furthermore, it uses an emotion engine to analyze emotional nuances from videos and audio, generating indicators such as positive, negative, and neutral.

[0800] Step 4:

[0801] The server matches job requirements with candidate analysis results and scores candidates based on their technical skills and emotional compatibility. This score indicates the overall suitability and serves as the criterion for listing candidates.

[0802] Step 5:

[0803] The server generates a list of high-scoring candidates and notifies the recruiter (user). This notification includes a detailed report based on skills and sentiment analysis.

[0804] Step 6:

[0805] The user (recruiter) selects candidates to proceed to interviews based on the information received from the system. This selection result is then fed back into the system.

[0806] Step 7:

[0807] During the interview, the device collects data such as the candidate's voice, facial expressions, and gestures in real time. This data is sent to a server and analyzed by an emotion engine.

[0808] Step 8:

[0809] The server collects emotional analysis data from the interview and evaluates the candidate's stress level and adaptability. This evaluation is reflected in the final candidate report provided by the system.

[0810] Step 9:

[0811] After the interview process is complete, the server provides the hiring manager with the analysis results, including a final evaluation of the candidate and recommendations for the next steps. The user can then use this information to make their final hiring decision.

[0812] (Example 2)

[0813] 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".

[0814] Traditional recruitment processes tend to focus heavily on evaluating applicants' technical skills and experience, failing to adequately consider emotional compatibility and suitability for the company culture. Furthermore, there are limited means of understanding candidates' psychological states in real time during interviews, highlighting the need for improved quality and efficiency in recruitment.

[0815] 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.

[0816] This invention includes a server that receives, structures, and stores applicant information; a server that extracts and comprehensively evaluates the applicant's emotional characteristics using generative AI technology; and a server that optimizes interview schedules between recruiters and candidates. This enables a multifaceted evaluation through emotional analysis, significantly improving the quality and efficiency of the recruitment process.

[0817] "Means for receiving and storing applicant information" refers to a function that acquires data provided by applicants and records it in digital format within the system.

[0818] "Means of storing applicant information in a structured format" refers to a function in a database that organizes and stores applicant information based on certain rules and formats.

[0819] "A means of analyzing applicant information and extracting emotional characteristics using generative AI technology" refers to a function that uses artificial intelligence technology, such as natural language processing, to analyze and identify emotional information from the applicant's submitted materials.

[0820] "Means of evaluating technical skills and emotional characteristics in comparison to job requirements" refers to a function that comprehensively assesses an applicant's technical skills and emotional aspects in light of the requirements sought by the company.

[0821] "A means of listing suitable applicants and notifying recruiters" refers to a function that selects applicants who meet the criteria based on the evaluation results and notifies them in list format.

[0822] "A means of analyzing the available time of recruiters and candidates and proposing the most suitable interview schedule" refers to a function that combines the schedules of both parties to calculate and provide the optimal interview date and time.

[0823] "Means of notifying confirmed schedules" refers to a function that communicates optimized interview dates and times to each party.

[0824] "A means of collecting and analyzing candidate emotional data in real time during an interview" refers to a function that acquires emotional data during an interview and immediately analyzes and evaluates it.

[0825] "Means of providing post-interview evaluation results" refers to a function that reports evaluations based on the data collected during interviews to relevant parties at a later date.

[0826] This invention is a system that understands the emotions of applicants and recruiters in the recruitment process and supports selection decision-making. This system uses the following hardware and software.

[0827] The server runs on a cloud computing platform and uses an engine incorporating AI technology. This AI engine is equipped with natural language processing (NLP) technology and interacts with external services such as the Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0828] The devices are typical personal computers or tablet devices. They have built-in webcams and microphones and are used to collect audio and video data during interviews. The software on the devices has the capability to transmit this data to a server in real time.

[0829] Users include applicants and recruiters. Recruiters receive notifications from the system and review evaluation results to advance their recruitment activities. During interviews, they can gain a deeper understanding of candidates based on real-time sentiment analysis information provided by the server.

[0830] This system begins with applicants submitting their resumes through a web portal. The server receives this data and stores it in a structured format. Next, AI technology is used to extract the applicant's emotional characteristics and comprehensively evaluate them by comparing their technical skills and emotional information with the job requirements. Based on this evaluation, the server lists suitable candidates and notifies the user via email.

[0831] As a concrete example, when a company recruits for a sales position, the server analyzes the emotional characteristics of the presentation materials and self-introductions received from applicants, and uses the results to evaluate their adaptability to the company culture. During the interview, the terminal transmits the candidate's voice and facial expression data to the server for real-time analysis. Based on this information, the recruiter makes a decision considering factors such as the applicant's flexibility and stress tolerance.

[0832] An example of a prompt to input into the generating AI model is: "Analyze the emotional characteristics of applicants suitable for sales positions, evaluate their adaptability to the company culture, and create a report."

[0833] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0834] Step 1:

[0835] The user (applicant) submits their resume through a web portal. The information received includes the applicant's name, contact information, work history, educational background, and a self-introduction. This data is then sent to the server.

[0836] Step 2:

[0837] The server receives resume data from applicants and stores it in a structured format in the database. It analyzes the entered resume information and organizes it into individual fields for each applicant. This process yields structured data output.

[0838] Step 3:

[0839] The server applies an emotion engine using generative AI technology to the stored applicant data. The input consists of descriptions from self-introduction statements and work histories, and emotional characteristics are extracted using natural language processing. After extraction, emotion scoring is performed, and the results are output.

[0840] Step 4:

[0841] The server compares emotional scores and technical skills data with job requirements. It uses job requirements and extracted skills data as input. After the comparison, it evaluates the degree of fit and generates a list of overall candidate ratings as output.

[0842] Step 5:

[0843] The server creates a list of suitable applicants based on the overall evaluation and notifies the user (recruiter). The notification uses an email service, and the output includes the list of candidates and detailed evaluation information.

[0844] Step 6:

[0845] The device collects the candidate's audio and video in real time during the interview. Here, it uses the camera and microphone to send non-verbal data (voice tone, facial expressions) as input to the server.

[0846] Step 7:

[0847] The server analyzes the data sent from the terminal in real time. Using an emotion engine, it generates emotional data such as the candidate's level of relaxation and tension, and outputs this as an evaluation report.

[0848] Step 8:

[0849] The server provides feedback to the user (recruiter) based on the evaluation results after the interview. It also suggests appropriate interview schedules to guide the next selection step. The output includes a feedback message and an optimal interview schedule.

[0850] (Application Example 2)

[0851] 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".

[0852] Traditional recruitment processes have limitations in evaluating applicants based on their skills and experience, making it difficult to adequately assess emotional compatibility and adaptability to the company culture. Furthermore, increased stress due to a lack of communication within the family and the inability to understand and appropriately respond to family members' emotions has been identified as a problem.

[0853] 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.

[0854] In this invention, the server includes means for determining the user's emotional state using emotion analysis technology in a mobile device and optimizing suggestions; means for receiving and storing applicant data; and means for analyzing applicant data using a generative model and extracting skills and experience. This enables more efficient recruitment processes and allows home robots to understand the emotions of family members.

[0855] "Applicant data" refers to the resume, work history, and related information provided by an applicant for a specific job.

[0856] A "generative model" refers to an algorithm or framework used to analyze data using artificial intelligence technology, and is particularly used in natural language processing and pattern recognition.

[0857] "Skills and experience" refers to the knowledge, abilities, past work history, and achievements that an applicant possesses in relation to a specific job.

[0858] "Evaluating" means analyzing and judging an applicant's suitability and potential based on various criteria.

[0859] "Listing" refers to the process of compiling and clearly identifying individuals who have been selected based on specific criteria.

[0860] "Mobile devices" refer to devices such as household robots and smart devices that have the ability to collect and process information while operating in different locations.

[0861] "Emotional analysis technology" refers to technology used to automatically analyze emotions and psychological states from voice and facial expression data.

[0862] "Optimizing suggestions" refers to the process of presenting the most suitable actions and options based on the user's situation and needs.

[0863] This invention is a system that receives applicant data and evaluates that data using emotion analysis technology. Furthermore, it enables the analysis of emotional states in mobile devices within the home, such as household robots, and provides optimal suggestions.

[0864] The server receives and stores applicant data from users. This data includes resumes and work histories and is stored as structured data within the server. The server analyzes this data using a generative model to extract the applicant's skills and experience. During the analysis process, an AI-powered sentiment analysis engine is used to extract emotional nuances from the applicant's data and to evaluate the applicant's suitability from multiple perspectives.

[0865] In mobile devices, the system collects user voice and facial expression data via cameras and microphones, and analyzes their emotional state in real time. Specifically, it runs an emotion analysis model using Python and TensorFlow on an embedded platform such as a Raspberry Pi. Based on the analyzed emotion data, the mobile device can make appropriate suggestions to the user.

[0866] A concrete example is a scenario where a home robot understands the user's emotions and makes a suggestion such as, "You seem a little tired today, shall I make you some tea?" This is achieved by the mobile robot determining the user's emotions from facial expression data and voice analysis, and then generating a response. An example of a prompt to the generating AI model would be, "Please tell me how a home robot can use emotion analysis to optimize communication with family members."

[0867] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0868] Step 1:

[0869] The server receives and stores applicant data from users. This input data includes resumes and work history documents. The server stores this data as structured data in a database so that it can be used for later analysis.

[0870] Step 2:

[0871] The server retrieves applicant data from the database and analyzes it using a generative AI model. Specifically, the data includes information about skills and experience, and the model extracts these elements, along with analyzing emotional nuances. The output of this process is a structure of skills, experience, and emotional evaluations.

[0872] Step 3:

[0873] The server compares the analysis results obtained in Step 2 with the job requirements. The input provided is a structured list of the applicant's skills and experience, along with the requirements sought by the company. The server then evaluates the applicant's suitability and performs scoring. The output generates an evaluation list of suitable candidates.

[0874] Step 4:

[0875] The device collects sensor data to analyze the user's emotions in a mobile home environment. Specifically, it collects facial expression data using a camera and acquires audio data using a microphone. This sensor data is input into the system and processed in real time.

[0876] Step 5:

[0877] The device processes collected sensor data using emotion analysis technology. Based on the input data, the mobile device analyzes the user's current emotional state and makes suggestions based on the analysis results. The output consists of specific action suggestions and communication content for the user.

[0878] Step 6:

[0879] Suggestions are made to the user. For example, a mobile object might say, "You seem a little tired today, shall I make you some tea?" and an appropriate response is taken based on sentiment analysis. This prompt is generated based on sentiment analysis data.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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."

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] The following is further disclosed regarding the embodiments described above.

[0902] (Claim 1)

[0903] A means of receiving and storing applicant data,

[0904] A method for analyzing applicant data using a generative model and extracting skills and experience,

[0905] A means of comparing extracted information with job requirements and evaluating candidates,

[0906] A means of listing suitable candidates based on evaluation,

[0907] A means of obtaining the available time of recruiters and candidates and proposing an interview schedule,

[0908] A means of notifying the confirmed schedule,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, which stores applicant data as structured data.

[0912] (Claim 3)

[0913] The system according to claim 1, which assigns scores to candidates based on job requirements.

[0914] "Example 1"

[0915] (Claim 1)

[0916] A device that has the function of receiving and storing applicant information,

[0917] A device that uses a generative AI model to analyze applicant information and extract their abilities and experience,

[0918] A device that has the function of comparing extracted information with job requirements and evaluating candidates,

[0919] A device that has the function of listing appropriate candidates based on evaluation,

[0920] A device that has the function of obtaining the available time of company representatives and candidates and presenting an interview schedule,

[0921] A device that has the function of notifying of the finalized plan,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, which stores applicant information in a structured format.

[0925] (Claim 3)

[0926] The system according to claim 1, which assigns scores to candidates based on job requirements.

[0927] "Application Example 1"

[0928] (Claim 1)

[0929] A means of receiving applicant information and storing it in an information warehouse,

[0930] A means of analyzing applicant information using a generative AI model and extracting their skills and experience,

[0931] A method for evaluating candidates by comparing the extracted content with the job requirements,

[0932] A means of listing suitable candidates based on evaluation,

[0933] A means of obtaining the available time of managers and candidates and proposing interview schedules,

[0934] A means of communicating confirmed schedules,

[0935] In order to select a suitable candidate for industrial facilities, a method for evaluating and scoring the suitability of candidates is required.

[0936] A method by which administrators use smartphones to select candidates and propose interviews,

[0937] A system that includes this.

[0938] (Claim 2)

[0939] The system according to claim 1, which stores applicant information as structured information.

[0940] (Claim 3)

[0941] The system according to claim 1, which assigns a score to a candidate based on the job requirements.

[0942] "Example 2 of combining an emotion engine"

[0943] (Claim 1)

[0944] A means of receiving and storing applicant information,

[0945] A means of storing applicant information in a structured format,

[0946] A method for analyzing applicant information using generative AI technology and extracting emotional characteristics,

[0947] A means of evaluating candidates from multiple perspectives by comparing extracted technical skills and emotional characteristics with job requirements,

[0948] A means of listing suitable applicants based on evaluations and notifying recruiters,

[0949] A means of analyzing the available time of recruiters and candidates and proposing the most optimal interview schedule,

[0950] A means of notifying the confirmed schedule,

[0951] A method for collecting and analyzing candidate emotional data in real time during interviews,

[0952] A means of providing evaluation results after the interview,

[0953] A system that includes this.

[0954] (Claim 2)

[0955] The system according to claim 1, which scores the adaptability of candidates using sentiment analysis.

[0956] (Claim 3)

[0957] The system according to claim 1, which optimizes responses during an interview based on emotional data collected in real time.

[0958] "Application example 2 when combining with an emotional engine"

[0959] (Claim 1)

[0960] A means of receiving and storing applicant data,

[0961] A method for analyzing applicant data using a generative model and extracting skills and experience,

[0962] A means of comparing extracted information with job requirements and evaluating candidates,

[0963] A means of listing suitable candidates based on evaluation,

[0964] A means for determining the emotional state of a user using emotion analysis technology in a mobile device and optimizing suggestions,

[0965] Methods for proposing an interview schedule,

[0966] A means of notifying the confirmed schedule,

[0967] A system that includes this.

[0968] (Claim 2)

[0969] The system according to claim 1, which stores applicant data as structured data.

[0970] (Claim 3)

[0971] The system according to claim 1, which assigns scores to candidates based on job requirements. [Explanation of Symbols]

[0972] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving applicant information and storing it in an information warehouse, A means of analyzing applicant information using a generative AI model and extracting their skills and experience, A method for evaluating candidates by comparing the extracted content with the job requirements, A means of listing suitable candidates based on evaluation, A means of obtaining the available time of managers and candidates and proposing interview schedules, A means of communicating confirmed schedules, In order to select a suitable candidate for industrial facilities, a method for evaluating and scoring the suitability of candidates is required. A method by which administrators use smartphones to select candidates and propose interviews, A system that includes this.

2. The system according to claim 1, which stores applicant information as structured information.

3. The system according to claim 1, which assigns a score to a candidate based on the job requirements.

Images