System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving information of an applicant; means for analyzing and evaluating the received information by a generative artificial intelligence; means for calculating skill matching of the applicant based on the evaluation; and means for outputting a result of the skill matching.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The traditional recruitment process had the problem of requiring a great deal of man-hours and costs to select personnel who fit a company's needs from a large number of applicants. Furthermore, mismatches between companies and applicants frequently occurred during document screening and interviews to select suitable candidates, resulting in early turnover and a decline in work motivation after hiring. Furthermore, the large number of manpower required to accurately evaluate applicants' skills and experience increased the burden on recruiters. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means for receiving applicant information is provided. This means transmits information entered by the applicant via a web form or the like to a server. Next, a means for analyzing and evaluating the received information using generative artificial intelligence is provided. This automatically analyzes the applicant's work history and skill set and evaluates their suitability. Furthermore, a means for calculating the applicant's skill matching based on the evaluation is provided. This means quantifies and objectively evaluates the degree to which the applicant's skills match the company's needs. Finally, a means for outputting the results of the skill matching is provided, notifying human resources personnel of the evaluation results and enabling efficient candidate selection. Furthermore, by adding a means for conducting a simulation of a first interview and a means for analyzing and evaluating the results of the simulation, mismatches at the interview stage are reduced. In addition, a means for creating and outputting evaluation results and reasons for recommendation, and a means for notifying human resources personnel of the results, is provided, supporting comprehensive evaluation and smooth decision-making.

[0006] "Applicant Information" refers to personal information provided by applicants, such as name, contact details, educational background, work history, and skills.

[0007] "Means of receiving" refers to the system components and functions used to obtain information provided by applicants, such as web forms and APIs.

[0008] "Generative AI" is an AI technology that analyzes applicant information and evaluates it.

[0009] The "means of analysis" refers to the process or algorithm used to classify and evaluate applicant information using generative artificial intelligence.

[0010] The "means for calculating skill matching" is a calculation method for quantifying the applicant's skills and experience based on the analysis results and evaluating the degree of match with the company's needs.

[0011] "Evaluation results" are information indicating the applicant's skills and aptitude based on the results of analysis by the generative artificial intelligence.

[0012] "Means of output" refers to the means for notifying the human resources personnel of the evaluation results, including generating a report or sending an email.

[0013] A "means for conducting a simulated first interview" is a system or algorithm that uses artificial intelligence to generate interview questions, present them to applicants, and collect and evaluate their responses.

[0014] "Means for analyzing and evaluating the results of the simulation" refers to a method for analyzing the responses to the first interview simulation and evaluating the aptitude and skills of the applicant.

[0015] "Means for creating and outputting evaluation results and reasons for recommendation" refers to a process or system for outputting the reasons for recommendation as written or electronic data based on the results of analysis and evaluation.

[0016] "Means of notifying HR personnel" refers to the means of informing HR personnel of the evaluation results and reasons for recommendation, and specifically includes email, dashboard notifications, etc. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[0039] 1. Receiving applicant information

[0040] A user fills in a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[0041] The terminal sends the entered application information to the server, which receives the information and stores it in a database.

[0042] For example, a user enters his name "Yamada Taro," his work experience "5 years in software development," and his skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0043] 2. Analysis of application information

[0044] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[0045] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[0046] 3. Skill Matching Calculation

[0047] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0048] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0049] 4. First interview simulation

[0050] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[0051] For example, the AI ​​generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The server analyzes this answer and reflects it in the evaluation results.

[0052] 5. Output and notification of evaluation results

[0053] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the human resources manager.

[0054] As a specific example, the server generates an evaluation report stating, "Yamada Taro has 5 years of experience with Python and 2 years of experience in project management, so he received a high skill matching score," and sends it to the human resources manager by email.

[0055] 6. Applicant evaluation feedback storage

[0056] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[0057] As a specific example, the server stores feedback information such as "Yamada Taro passed the first interview because he met the skill requirements" in a database so that it can be referenced during the next selection process.

[0058] Such a system will efficiently carry out the entire process of receiving, analyzing, evaluating, and providing feedback on applicants, reducing the burden on human resources personnel and reducing mismatches between companies and applicants.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] A user fills out a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[0062] Step 2:

[0063] The device sends the entered application information to the server. Specifically, the data is sent using an HTTP POST request. The application information is sent to the server in JSON format.

[0064] Step 3:

[0065] The server receives the application information and stores it in a database. The received information is stored in the database in an appropriate format.

[0066] Step 4:

[0067] The server periodically checks for new application information and extracts it if new application information is found.

[0068] Step 5:

[0069] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[0070] Step 6:

[0071] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[0072] Step 7:

[0073] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[0074] Step 8:

[0075] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[0076] Step 9:

[0077] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[0078] Step 10:

[0079] The server receives the applicant's answers and sends them to the generating AI for analysis. After receiving the analysis results, it incorporates them into the evaluation process.

[0080] Step 11:

[0081] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation. The evaluation results and reasons for recommendation are summarized in a concrete format.

[0082] Step 12:

[0083] The server then sends the evaluation report to the HR personnel, notifying them via email or a dedicated management dashboard.

[0084] Step 13:

[0085] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[0086] This series of steps allows the entire process to be carried out efficiently, from receiving applicant information to analyzing, evaluating, notifying, and storing feedback.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] In conventional recruitment systems, the process from collecting applicant information to analyzing, evaluating, and providing feedback is not carried out efficiently, placing a heavy burden on HR personnel and making it difficult to achieve appropriate skill matching. In addition, preparing for and evaluating the first interview is cumbersome, making it easy for mismatches to occur between companies and applicants. These issues need to be resolved.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze the received information, means for calculating the applicant's skill matching based on the results of the analysis, means for generating questions for the first interview and collecting and analyzing the applicant's responses, means for reflecting the results of the skill matching and interview questions in the evaluation results, and means for outputting the evaluation results. This not only enables efficient reception, analysis, evaluation, and feedback of applicant information, but also realizes skill matching that meets the needs of the company, improving the efficiency of preparation for and evaluation of the first interview.

[0092] "Generative artificial intelligence" refers to the advanced algorithms and machine learning models used to analyze and evaluate received information.

[0093] "Skills matching" refers to the process of analyzing an applicant's skills and work history and comparing them with the company's requirements to evaluate their suitability.

[0094] "First-stage interview questions" refer to interview questions generated by generative artificial intelligence to evaluate an applicant's abilities and aptitude.

[0095] "Analysis results" refers to the data and evaluation regarding work history and skill sets obtained by the generative AI analyzing the applicant's information.

[0096] "Evaluation results" refers to the results of a comprehensive evaluation of the applicant's skill matching and answers to interview questions.

[0097] "Feedback" refers to the evaluation and recommendations provided to applicants based on the evaluation results.

[0098] "Database" refers to an electronic storage device used by the server to store and manage applicant information, analysis results, and evaluation results.

[0099] "Generating questions" refers to the process in which generative artificial intelligence uses a specific algorithm to automatically create questions to be asked to applicants.

[0100] An "evaluation report" is a document prepared by the server based on the applicant's skill matching and the results of the first interview, and is presented to the human resources personnel.

[0101] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[0102] Receiving applicant information

[0103] A user enters application information into a web form and presses the submit button. This information includes personal information such as name, contact details, educational background, work history, and skills. The device sends the entered application information to the server, which receives this information and stores it in a database.

[0104] For example, a user enters their name "Applicant A," work experience "5 years in software development," and skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0105] Analysis of application information

[0106] The server retrieves application information from a database, then invokes a generative AI model (e.g., OpenAI's GPT-4) to analyze the received information, which then evaluates the applicant's work history and skill set.

[0107] For example, the server passes the applicant's resume to a generator AI and sends the following prompt:

[0108] Analyze applicant information to assess work history and skill sets.

[0109] Name: Applicant A

[0110] Work experience: 5 years in software development

[0111] Skills: Python, Java

[0112] The generative AI returns analysis results such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[0113] Skill Matching Calculation

[0114] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0115] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0116] First interview simulation

[0117] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[0118] As a specific example, the generation AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The device sends this answer to the server, which then reflects it in the evaluation results based on the analysis results.

[0119] Specific prompt examples:

[0120] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[0121] Output and notification of evaluation results

[0122] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the relevant parties.

[0123] As a specific example, the server generates an evaluation report stating, "Applicant A has 5 years of Python experience and 2 years of project management experience, so he received a high skill matching score," and sends it to the relevant parties by email.

[0124] Applicant evaluation feedback storage

[0125] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[0126] As a specific example, the server stores feedback information such as "Applicant A meets the skill requirements and therefore passed the first interview" in a database so that it can be referenced during the next selection process.

[0127] This system allows for an efficient process from receiving applicant information to analyzing, evaluating, and providing feedback, thereby reducing mismatches between companies and applicants.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1: Enter and submit your application information

[0130] A user enters personal information such as name, contact details, educational background, work history, and skills into a web form. When the user presses the submit button, the terminal sends the application information to a server. The input data is "Name: Applicant A, Work history: 5 years in software development, Skills: Python, Java," and this data is sent to the server as output.

[0131] Step 2: Receiving and storing applicant information

[0132] The server receives the application information sent from the terminal and stores it in a database. The server receives the application information as input and stores it in a database, thereby permanently retaining the information. The input data is "Name: Applicant A, Work Experience: 5 years in software development, Skills: Python, Java", and is stored in the database as output.

[0133] Step 3: Acquire and analyze application information

[0134] The server retrieves applicant information from the database. Then it launches a generative AI model (e.g., OpenAI's GPT-4) and sends a prompt to the generative AI to analyze the application information. The specific prompt is as follows:

[0135] Analyze applicant information to assess work history and skill sets.

[0136] Name: Applicant A

[0137] Work experience: 5 years in software development

[0138] Skills: Python, Java

[0139] Application information is provided as input, and the generating AI outputs an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[0140] Step 4: Calculate skill matching

[0141] The server receives the analysis results and retrieves the company's needs information from the database. Next, it compares the analysis results with the company's needs and calculates a skill matching score. This evaluates how well the applicant matches the company's skill requirements. The company's needs, "3+ years of Python experience, 1+ years of project management experience," are used as input, and the skill matching score is obtained as output.

[0142] Step 5: Generate questions and collect answers for the first interview

[0143] The server uses a generation AI to generate questions for the first interview. The specific prompts are as follows:

[0144] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[0145] The generated question is presented to the user, and the device collects the user's answer. The user's answer is sent to the server via the device. The input is the question obtained from the generation AI and the user's answer, "Delay in the project schedule," and the output is saved on the server.

[0146] Step 6: Analyze the first interview responses

[0147] The server sends the user's answers back to the generation AI and requests analysis. The generation AI analyzes the answers and returns the interview evaluation results. The user's answers are provided as input, and the evaluation result, such as "high schedule management ability," is obtained as output.

[0148] Step 7: Generate evaluation results and recommendations

[0149] The server creates a report summarizing the evaluation results and reasons for recommendation based on the applicant's skill matching score and the results of the first interview. The report is notified to the relevant parties. Based on the skill matching score and the results of the first interview as input, an evaluation report is generated as output and sent to the relevant parties by email.

[0150] Step 8: Storing the assessment results and feedback

[0151] The server stores the evaluation results and feedback in a database, and organizes and stores the information for future recruitment activities. The evaluation results and reasons for recommendation are provided as input, and are stored in the database as output.

[0152] This series of processes enables efficient reception, analysis, evaluation and feedback of applicant information, reducing mismatches between companies and applicants.

[0153] (Application example 1)

[0154] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0155] Conventional systems that analyze and evaluate applicant information make it difficult to efficiently allocate and schedule workers in specific fields. They also lack the means to collect and evaluate feedback for work efficiency and use it for future allocations. This can lead to reduced work efficiency within factories and potential mismatches in personnel allocation.

[0156] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0157] In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the skill matching of the applicant based on the evaluation, means for outputting the results of the skill matching, means for receiving worker information and evaluating the received information, means for optimally allocating workers based on the evaluation, and means for outputting the allocation results, thereby enabling optimal allocation and scheduling of workers.

[0158] The "means for receiving applicant information" refers to a method or device for acquiring data such as personal information, skill set, and work history provided by the applicant and incorporating it into the system.

[0159] "Means for analyzing and evaluating information received by generative artificial intelligence" refers to a method or device that uses AI technology to analyze data received from applicants and evaluate the applicants' skills and aptitude based on the results.

[0160] The "means for calculating the skill matching of the applicant based on the evaluation" refers to a method or device for calculating the degree of match between the applicant's skills and the requirements required by the company based on the analysis results.

[0161] The "means for outputting the skill matching result" refers to a method or device for displaying or transmitting the calculated skill matching result to another system.

[0162] The "means for receiving worker information" refers to a method or device for acquiring information such as skill sets and available working hours provided by workers in a factory and incorporating this information into the system.

[0163] The "means for evaluating received information" refers to a method or device for evaluating the capabilities and aptitude of a worker based on data received from the worker.

[0164] The "means for optimally allocating workers based on the evaluation" refers to a method or device for allocating workers to the most suitable tasks within the factory based on the evaluation results.

[0165] The "means for outputting the allocation results" refers to a method or device for displaying information about optimally allocated workers or transmitting it to another system.

[0166] The system that embodies this invention receives applicant and worker information, analyzes it using a generation AI, and performs appropriate placement and matching based on the evaluation results. This system consists of the following elements:

[0167] Hardware and software environment

[0168] Hardware:

[0169] Factory robots (e.g., general industrial robots)

[0170] Server (e.g., general server products)

[0171] software:

[0172] Generative AI models (e.g., OpenAI GPT-3)

[0173] Database (e.g. PostgreSQL)

[0174] Programming language (e.g. Python)

[0175] The system's server first receives information from applicants and workers, such as personal information, skill sets, and work history. This includes functions for factory robots to collect information from workers and for applicants to provide information through web forms. This information is then sent to the server and stored in a database.

[0176] The server then passes the received information to a generative AI model, which analyzes the data. The analysis results include the applicant's skills and work history, as well as the worker's skill set and work history. Based on the analysis results, the server calculates skill matching and performs optimal placement.

[0177] After the analysis and evaluation are complete, the server outputs the results and makes appropriate placement decisions. For example, it determines whether the applicant's skills match the company's requirements and which job in the factory the worker is best suited for. Along with the evaluation results, the system also includes a function to notify the reasons for the recommendation and provide feedback as needed. This feedback can be used for future placement and scheduling.

[0178] Examples:

[0179] Worker acceptance and analysis

[0180] A factory robot receives information about worker Tanaka and sends it to a server. The server stores Tanaka's "welding" skill and available working hours in a database. The generative AI model analyzes the data and generates Tanaka's skills and evaluation results.

[0181] Scheduling and Deployment

[0182] Based on the needs of the factory, Tanaka is assigned to welding work from 09:00 to 12:00 based on the analysis results. The server outputs this information and sends the appropriate work schedule to the robot.

[0183] Prompt Sentence Examples

[0184] Enter Tanaka's work skill set and available hours:

[0185] Name: Tanaka

[0186] Skills: Welding

[0187] Availability: 09:00-18:00

[0188] Generate schedules based on factory needs:

[0189] Required Skills: Welding

[0190] Time Frame: 09:00-12:00

[0191] This allows for efficient implementation of a series of processes, from accepting workers to optimal allocation, scheduling, and feedback collection and evaluation, thereby improving work efficiency within the factory and reducing mismatches between workers and work.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] The user inputs application or worker information. The input data includes name, skill set, available working hours, work history, etc. The terminal acquires this information and sends it to the server.

[0195] Input: Data such as name, skill set, available hours, and work history

[0196] Output: Send information to the server

[0197] Step 2:

[0198] The server stores the received application and worker information in a database. The database stores all applicant and worker information. This data is later used for analysis by the generative AI model.

[0199] Input: Application information and worker information sent from the terminal

[0200] Output: Save information to a database

[0201] Step 3:

[0202] The server retrieves the stored application and worker information and passes it to the generative AI model, which analyzes this information and evaluates skillsets, work history, aptitude, etc.

[0203] Input: Applicant and worker information retrieved from the database

[0204] Output: Analysis results from the generative AI model

[0205] Step 4:

[0206] The server calculates the skill matching of applicants based on the analysis results received from the generative AI model, and also calculates the optimal allocation of workers based on the needs of the factory.

[0207] Input: Analysis results from generative AI model, factory needs

[0208] Output: Skill matching results, worker allocation calculation results

[0209] Step 5:

[0210] The server outputs the calculated skill matching results and worker allocation calculation results. The results are notified to the user or administrator as needed. The notification includes the skill matching score and the reason for allocation.

[0211] Input: Skill matching results, worker allocation calculation results

[0212] Output: Output and notification of results

[0213] Step 6:

[0214] The server collects and evaluates feedback. After completing the task, the robot records the progress and problems, which are then analyzed by the generative AI model. The evaluation results are used for the next placement and scheduling.

[0215] Input: Work progress data, problem records

[0216] Output: Feedback evaluation result

[0217] Step 7:

[0218] The server stores the results of the previous evaluation in a database and uses them for the next placement. The stored evaluation results serve as a reference for future scheduling and placement.

[0219] Input: Feedback evaluation result

[0220] Output: Save evaluation results to a database

[0221] Through the above processing steps, optimal placement and scheduling can be performed based on applicant information, improving work efficiency within the factory.

[0222] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0223] This system receives applicant information, analyzes and evaluates it using generative artificial intelligence (AI), and also combines it with an emotion engine that recognizes the user's emotions. The purpose of this system is to provide more accurate evaluations and reduce mismatches between companies and applicants.

[0224] 1. Receiving applicant information

[0225] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[0226] The device takes into account the entered application information and sends it to the server. The information is sent to the server in JSON format, and the server stores the received application information in a database.

[0227] For example, a user enters their name "Hanako Tanaka," their work experience "5 years as a systems engineer," and their skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0228] 2. Analysis of application information

[0229] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[0230] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[0231] 3. Skill Matching Calculation

[0232] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0233] For example, if a company prioritizes "3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0234] 4. Emotion analysis using an emotion engine

[0235] The server runs an emotion engine and analyzes emotions based on applicant information and responses during the simulated first interview. The analyzed emotion data is reflected in the skill matching evaluation.

[0236] For example, during a simulated first interview, when an applicant talks about their past successful project experiences, the emotion engine detects confidence from the applicant's facial expressions and tone of voice. This information is incorporated into the evaluation.

[0237] 5. First interview simulation

[0238] The server uses artificial intelligence to generate questions for the first interview. These questions are presented to applicants and responses are collected. The collected responses are simultaneously analyzed by an emotion engine.

[0239] For example, the generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The emotion engine analyzes the user's emotional changes and reflects them in the evaluation.

[0240] 6. Output and notification of evaluation results

[0241] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[0242] As a specific example, the server generates an evaluation report stating, "Hanako Tanaka has 5 years of experience with Python and 2 years of experience in project management, and was recognized for her confidence and sincerity during the first interview, which resulted in a high skill matching score," and sends it to the human resources manager by email.

[0243] 7. Applicant evaluation feedback storage

[0244] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[0245] As a specific example, the server stores feedback information such as "Tanaka Hanako meets the skill requirements and received high evaluations in the interview, so she passed the first interview" in a database, making it available for reference during the next selection process.

[0246] In this way, a system that combines an emotion engine can take applicants' emotions into consideration when evaluating them, enabling more accurate personnel selection and reducing mismatches between companies and applicants.

[0247] The processing flow will be explained below.

[0248] Step 1:

[0249] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[0250] Step 2:

[0251] The terminal sends the entered application information to the server in JSON format, and the server stores the received application information in a database.

[0252] Step 3:

[0253] The server periodically checks for new application information to see if there is any. If new application information is found, it extracts the information and proceeds to the next step.

[0254] Step 4:

[0255] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[0256] Step 5:

[0257] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[0258] Step 6:

[0259] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[0260] Step 7:

[0261] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[0262] Step 8:

[0263] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[0264] Step 9:

[0265] The server receives the applicant's responses and sends the data to the generation AI for analysis. The analysis results are scored and analyzed by the emotion engine.

[0266] Step 10:

[0267] The server runs an emotion engine, analyzes the emotions expressed in the user's responses, and reflects them in the evaluation. Specifically, the server evaluates emotions using facial expression recognition and voice analysis.

[0268] Step 11:

[0269] The server creates a report summarizing the applicant's overall evaluation results and the reasons for the recommendation. The server also summarizes the evaluation results and sentiment analysis results in a concrete format.

[0270] Step 12:

[0271] The server then sends the evaluation report to the HR personnel, who are then notified via email or a dedicated management dashboard.

[0272] Step 13:

[0273] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[0274] Example 2

[0275] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0276] Conventional talent evaluation systems only evaluated applicants' skills and experience, failing to fully consider their emotions and behavior during interviews, resulting in mismatches between companies and applicants. Furthermore, data storage and sharing was insufficient, making it impossible to effectively utilize past evaluations in future recruitment activities.

[0277] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze and evaluate the received information, means for calculating the applicant's skill matching based on the evaluation, means for analyzing the applicant's emotions using an emotion engine, means for reflecting the analyzed emotion data in the skill matching evaluation, and means for outputting the skill matching results. This enables highly accurate evaluation that takes into account not only the applicant's skills but also their emotions and interview behavior. Furthermore, by storing the evaluation results and feedback in a database, past evaluation data can be effectively utilized in future recruitment activities.

[0278] "Means of receiving applicant information" refers to the process of collecting data such as personal information, work history, and skill sets entered by applicants through web forms, etc.

[0279] "Means for launching a generative artificial intelligence to analyze and evaluate the received information" refers to the process of launching an artificial intelligence model running on a server, analyzing the collected applicant information, and appropriately evaluating it.

[0280] "Method of calculating the applicant's skill match" is a process of comparing the skills and requirements required by the company with the applicant's skills and experience, and numerically evaluating the degree of match.

[0281] "Means for analyzing the emotions of an applicant using an emotion engine" refers to a process for analyzing the applicant's facial expressions, tone of voice, etc. to identify the applicant's emotional state.

[0282] "Means for reflecting analyzed emotional data in the skill matching evaluation" refers to a process for incorporating the emotional data obtained by the emotion engine into the skill matching evaluation score to perform a comprehensive evaluation.

[0283] "Means for outputting the results of skill matching" refers to the process of creating a report to notify human resources personnel and others of the results of the skill matching evaluation, and providing it in various output formats.

[0284] The "means for conducting a simulated first interview" is the process of using a generative AI model to generate first interview questions, present them to applicants, and collect responses.

[0285] "Means for analyzing the results of the simulation using an emotion engine" refers to the process of analyzing the applicant's answers and reactions during the first interview simulation using an emotion engine.

[0286] The "means of collecting and evaluating responses during the initial interview" is the process of collecting applicant responses during the initial interview simulation and evaluating their content and quality.

[0287] "Means for creating and outputting evaluation results and reasons for recommendation" refers to the process of creating and outputting a report summarizing the applicant's evaluation results and the reasons for recommendation.

[0288] "Means for notifying the human resources personnel of the evaluation results and reasons for recommendation" refers to the process of notifying the human resources personnel by e-mail or other means of a report of the evaluation results and reasons for recommendation that has been created.

[0289] "Means for storing evaluation results and feedback in a database" refers to the process of storing the applicant's evaluation results and feedback information in a database so that they can be referenced in future recruitment activities.

[0290] This invention is a system that receives applicant information, analyzes it using generative artificial intelligence (AI), and evaluates it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system aims to perform more accurate evaluations and reduce mismatches between companies and applicants.

[0291] 1. Receiving applicant information

[0292] The user enters personal information such as name, contact details, educational background, work history, and skills into the web form and presses the submit button. The device converts the entered application information into JSON format and sends the data to the server. The server then parses the received JSON data and stores it in a database.

[0293] For example, a user enters their name "Hanako Tanaka," their work experience "System engineer for 5 years," and their skills "Python, Java" into a web form and presses the submit button. This information is sent from the device to the server in JSON format, and the server stores it in a database.

[0294] 2. Analysis of application information

[0295] The server retrieves application information from the database and analyzes it using a generative AI model. Specifically, it sends the received information about the applicant's work history and skills to the generative AI and receives the analysis results.

[0296] For example, when the server passes applicant data to the generation AI, the prompt statement is as follows: "Analyze the skills and experience of this applicant." The generation AI returns an analysis result such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[0297] 3. Skill Matching Calculation

[0298] The server uses the analysis results from the generative AI to calculate a score that matches the skill set the company is looking for, thereby evaluating the extent to which the applicant can meet the company's expectations.

[0299] Example: If a company is looking for "3+ years of Python experience and 1+ years of project management experience," the server will compare the applicant's skills with the company's requirements and calculate a skill matching score.

[0300] 4. Emotion analysis using an emotion engine

[0301] The server uses an emotion engine to analyze the applicant's emotions, and the analyzed emotion data (e.g., confidence, sincerity, etc.) is reflected in the skill matching evaluation.

[0302] Example: During a simulated first interview, if an applicant is asked about their past successful project experiences and responds, the emotion engine will analyze their facial expressions and tone of voice and detect "confidence."

[0303] 5. First interview simulation

[0304] The server uses a generative AI model to generate questions for the first interview. These questions are presented to applicants (users) and responses are collected. The collected responses are analyzed by an emotion engine.

[0305] Example: The generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." This answer is analyzed by the emotion engine, and changes in emotion (e.g., tension) are reflected in the evaluation.

[0306] 6. Output and notification of evaluation results

[0307] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[0308] Example: The server generates an evaluation report stating, "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skill matching score because she was perceived as confident and sincere during the first interview," and emails it to the HR manager.

[0309] 7. Applicant evaluation feedback storage

[0310] The server stores the evaluation results and feedback in a database, which is then managed so that the feedback can be referenced in future recruitment activities.

[0311] Example: The server stores feedback information such as "Hanako Tanaka meets the skill requirements and has a high interview evaluation, so she passed the first interview" in a database so that it can be referenced the next time the selection process is carried out.

[0312] In this way, by combining a generative AI model with an emotion engine, this system is able to make highly accurate evaluations that take into account both the skills and emotions of applicants, thereby eliminating mismatches between companies and applicants.

[0313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0314] The flow of this system's program processing

[0315] Step 1: Receiving applicant information

[0316] The user enters application information (name, contact details, educational background, work history, skills, etc.) into the web form and presses the submit button. The device converts the entered application information into JSON format and sends it to the server.

[0317] Input: User input information (e.g., "Hanako Tanaka", "Systems engineer 5th year", "Python, Java")

[0318] Data processing: Converts the information entered on the device into JSON format (e.g., {"name": "Hanako Tanaka", "experience": "System engineer 5 years", "skills": ["Python", "Java"]})

[0319] Output: The converted JSON format data is sent to the server.

[0320] Specific behavior: The user enters information into a form and submits it, and the device converts the information into JSON and sends it to the server.

[0321] Step 2: Save your information

[0322] The server stores the received application information in a database.

[0323] Input: Transformed JSON format application information

[0324] Data calculation: The server parses the JSON data and stores it in the database in the appropriate format.

[0325] Output: Application information is saved in the database

[0326] Specific operation: The server parses the received JSON data and writes the applicant information to the database.

[0327] Step 3: Analyze the application information

[0328] The server retrieves application information from a database and analyzes it using a generative AI model.

[0329] Input: Application information stored in the database

[0330] Data calculation: The server passes the information obtained from the database to the generation AI and obtains the analysis results.

[0331] Output: Analysis results from the generative AI (e.g., "5 years of Python experience, 3 years of Java experience, 2 years of project management experience")

[0332] Specific operation: The server sends the prompt "Analyze this applicant's skills and experience" when passing the applicant's data to the generation AI, and the generation AI returns the analysis results.

[0333] Step 4: Calculate skill matching

[0334] The server calculates a skill matching score based on the company's requirements using the analysis results from the generated AI.

[0335] Input: Analysis results from generative AI and the skill set desired by the company

[0336] Data calculation: The server compares the applicant's skills with the company's requirements and calculates a skill matching score

[0337] Output: Skill matching score (e.g. 90 points)

[0338] Specific operation: The server compares the analysis results with the company's requirements and calculates a skill matching score.

[0339] Step 5: Emotion analysis using the emotion engine

[0340] The server uses an emotion engine to analyze the emotions of applicants and reflects the analyzed data in skill matching.

[0341] Input: Applicant's video and audio data

[0342] Data calculation: The emotion engine analyzes facial expressions and voice tones to extract emotional data

[0343] Output: Extracted emotion data (e.g., confidence, sincerity, etc.)

[0344] Specific operation: The server analyzes the data during the first interview simulation using the emotion engine, and reflects the obtained emotion data in the evaluation.

[0345] Step 6: First interview simulation

[0346] The server uses the generative AI model to generate questions for the first interview, present them to the user, and collect responses.

[0347] Input: Company interview request

[0348] Data Computation: Generative AI Generates Interview Questions

[0349] Output: Interview question (e.g., "What was the most difficult problem you faced in your previous project?")

[0350] Specific operation: The generative AI generates a prompt sentence: "What was the most difficult problem you faced in your past projects?" and the user inputs an answer.

[0351] Step 7: Collect and evaluate responses

[0352] The server analyzes the collected responses using an emotion engine and makes an overall evaluation.

[0353] Input: User's answer

[0354] Data calculation: The server analyzes the answers using an emotion engine and reflects them in the evaluation.

[0355] Output: Overall evaluation result

[0356] Specific operation: The emotion engine analyzes the user's answers and incorporates the resulting emotion data into the skill matching evaluation.

[0357] Step 8: Output and notification of evaluation results

[0358] The server creates a report summarizing the overall evaluation results and reasons for recommendation and notifies the human resources officer.

[0359] Input: Skill matching score and sentiment analysis results

[0360] Data calculation: Create a report based on the evaluation results

[0361] Output: Assessment report

[0362] Specific Action: Generate an evaluation report stating "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skills matching score due to her confidence and honesty during the first interview" and send it to the HR manager via email.

[0363] Step 9: Archive the evaluation results

[0364] The server stores the evaluation results and feedback in a database and manages them so that they can be referenced in future recruitment activities.

[0365] Input: Evaluation results and feedback

[0366] Data calculation: Save to database

[0367] Output: Stored evaluation results and feedback

[0368] Specific operation: The server saves the evaluation results and feedback in a database, making them available for reference during the next selection process.

[0369] By combining a generative AI model with an emotion engine, this system enables highly accurate evaluations that take into account both the skills and emotions of applicants, reducing mismatches between companies and applicants.

[0370] (Application example 2)

[0371] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0372] Many modern recruitment systems evaluate applicants solely based on their skills and work history, resulting in frequent mismatches between companies and applicants. Applicants' emotions during interviews are also ignored, leading to inappropriate evaluations. This can result in companies missing out on talented candidates and making it difficult for applicants to find the right job. It can also make it difficult for brick-and-mortar stores to properly understand customer needs and recommend the best products, leading to lower customer satisfaction.

[0373] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the applicant's skill matching based on the evaluation, means for outputting the results of the skill matching, means for receiving customer information, analyzing it using a generative artificial intelligence, and recommending appropriate products, means including an emotion engine that recognizes and analyzes customer emotions, and means for displaying recommended products on a display device based on the analysis results. This enables evaluation and recommendations that take into account the applicant's skills and the company's needs, as well as emotions during interviews and emotions of customers in physical stores.

[0374] "Applicant" means a potential candidate for a particular position.

[0375] "Means for receiving information" refers to a system or interface for sending and receiving information input by a user to a server.

[0376] "Generative artificial intelligence" refers to a broad range of technologies, including machine learning models and AI software, that analyze and evaluate incoming information.

[0377] "Means for analyzing and evaluating" refers to the server or software that executes the process of analyzing received information and evaluating its content.

[0378] "Means for calculating skill matching" refers to algorithms or programs that compare the applicant's skills with the company's requirements and calculate the degree of match.

[0379] "Means for outputting skill matching results" means a system or interface for displaying or reporting the calculated skill matching results.

[0380] "Customer" means an individual or entity seeking a particular product or service.

[0381] "Means for recommending products" refers to systems and algorithms that suggest optimal products based on customer requirements and characteristics.

[0382] An "emotion engine that recognizes and analyzes emotions" refers to software and technology that analyzes the user's voice, facial expressions, etc. and recognizes their emotions.

[0383] "Display device" refers to a device (e.g., a smartphone, tablet, computer screen, etc.) for visually displaying analysis results, recommended products, etc.

[0384] The present invention is a system that receives applicant information, analyzes and evaluates it using generative AI, calculates skill matching, and outputs the results. As an application example, this system also includes a function to receive customer information and recommend appropriate products. It also incorporates an emotion engine that recognizes and analyzes customer emotions. Detailed embodiments of the present invention are described below.

[0385] Hardware and software used

[0386] In implementing the present invention, the following hardware and software are used.

[0387] 1. Hardware:

[0388] Server: Receives, analyzes and stores information.

[0389] Client terminal: A device (e.g., smartphone, tablet, or PC) through which a user enters application information or customer information.

[0390] Display device: A device (e.g., smartphone, tablet, or PC) used to display analysis results and recommended products.

[0391] 2. Software:

[0392] Generative AI (e.g., machine learning models such as OpenAI): Analyzes and evaluates application and customer information.

[0393] Emotion engine (e.g., emotion analysis API): Analyzes user emotions.

[0394] Cloud services (e.g. AWS): Manage data storage and server operations.

[0395] Programming language (e.g. Python): Builds the logic of the entire system.

[0396] Data processing and calculation

[0397] The server performs the following data processing and calculations.

[0398] 1. Receiving and storing applicant information:

[0399] A user inputs application information from a client terminal, and the server receives it.

[0400] The received information is sent to the server in JSON format and stored in a database.

[0401] 2. Analysis and Evaluation of Information:

[0402] The server retrieves application information from the database and launches the generative AI model.

[0403] The generative AI analyzes the information it receives and evaluates the applicant's skills and work history, extracting a skill set such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[0404] 3. Skill Matching Calculation:

[0405] The server calculates skill matching that matches the company's needs based on the analysis results, scores the degree of match with the skill requirements, and generates results.

[0406] 4. Emotion analysis:

[0407] The emotion engine analyzes applicant information and responses during the interview simulation to identify emotions (e.g., confidence, anxiety, sincerity, etc.).

[0408] This data is also reflected in the skill matching evaluation.

[0409] 5. Recommended products:

[0410] In physical stores, customers enter information about products using smartphones or other devices.

[0411] The generative AI analyzes the input information and recommends appropriate products.

[0412] Examples and prompts

[0413] As a concrete example, consider a case where a user uses their smartphone to type, "I want new wireless headphones." This information is sent to a server, where sentiment analysis is performed simultaneously.

[0414] Example prompts for generative AI models:

[0415] Customer Input: "I want new wireless headphones"

[0416] Generate recommended products.

[0417] Example prompts for the emotion engine:

[0418] Sentiment analysis target: "I was dissatisfied with the headphones I bought previously."

[0419] Analyze your emotions.

[0420] In this way, it is possible to analyze the user's input information and emotions and recommend the most suitable products, which also increases the satisfaction of applicants and customers.

[0421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0422] Step 1:

[0423] The user enters application or customer information from a client terminal, which receives it. For applicants, the information entered includes name, contact details, educational background, work history, skills, etc., while for customers, it includes desired product features and requests. The terminal sends this information to the server. The data format is JSON. For example, a user may enter a request such as "I want new wireless headphones."

[0424] Input: User-entered data

[0425] Output: JSON formatted transmission data

[0426] How it works: The device receives user input data and sends it to the server in JSON format.

[0427] Step 2:

[0428] The server stores the received information in a database, which allows the information to be retained for subsequent analysis and evaluation. The database is managed by a cloud service (e.g., AWS).

[0429] Input: User data in JSON format

[0430] Output: Data stored in the database

[0431] How it works: The server saves the received data in a database in JSON format.

[0432] Step 3:

[0433] The server retrieves application or customer information from the database and activates the generative AI model, which analyzes the received information and performs a detailed evaluation based on it, such as analyzing the applicant's skill set and work history, or the product characteristics based on the customer's request.

[0434] Input: User data retrieved from the database

[0435] Output: Analysis results by generative AI

[0436] How it works: The server analyzes the data using the generative AI model and generates an evaluation result.

[0437] Step 4:

[0438] Based on the analysis results of the generated AI model, the server calculates skill matching and product recommendations that match the company's needs and customer desires. It calculates a skill matching score or recommendation score.

[0439] Input: Analysis results by generative AI

[0440] Output: Scored matching results or recommendation results

[0441] How it works: The server calculates the score using a matching algorithm.

[0442] Step 5:

[0443] The server launches the emotion engine and analyzes the user's input information, answers during the interview simulation, and customer requests. Here, emotions are identified from the applicant's facial expressions, tone of voice, and customer text input. For example, dissatisfaction is detected from the input, "I was dissatisfied with the headphones I bought previously."

[0444] Input: Data to be analyzed for user sentiment

[0445] Output: Parsed emotion data

[0446] How it works: The emotion engine analyzes the input data and generates emotion data.

[0447] Step 6:

[0448] Based on the analysis results, the server outputs recommendation results and skill matching results and notifies the user. In addition, to visually display appropriate recommended products, the server sends the results in JSON format to the terminal. The response is then displayed on the user's client terminal.

[0449] Input: Analysis results and scored data

[0450] Output: Recommendation results or skill matching results displayed on the display device

[0451] Operation: The server sends the analysis results in JSON format to the device for visual display.

[0452] Step 7:

[0453] The analysis results and feedback information are stored in a database, and the stored data is used for future recruitment activities and to improve customer service.

[0454] Input: Analysis results and feedback data

[0455] Output: Historical data stored in a database

[0456] How it works: The server stores the analysis results and feedback in a database.

[0457] The above are the specific processing steps of the system for realizing the application example.

[0458] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0459] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0460] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0461] [Second embodiment]

[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0463] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0464] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0465] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0466] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0467] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0468] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0469] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0470] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0471] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0472] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0473] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0474] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[0475] 1. Receiving applicant information

[0476] A user fills in a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[0477] The terminal sends the entered application information to the server, which receives the information and stores it in a database.

[0478] For example, a user enters his name "Yamada Taro," his work experience "5 years in software development," and his skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0479] 2. Analysis of application information

[0480] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[0481] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[0482] 3. Skill Matching Calculation

[0483] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0484] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0485] 4. First interview simulation

[0486] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[0487] For example, the AI ​​generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The server analyzes this answer and reflects it in the evaluation results.

[0488] 5. Output and notification of evaluation results

[0489] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the human resources manager.

[0490] As a specific example, the server generates an evaluation report stating, "Yamada Taro has 5 years of experience with Python and 2 years of experience in project management, so he received a high skill matching score," and sends it to the human resources manager by email.

[0491] 6. Applicant evaluation feedback storage

[0492] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[0493] As a specific example, the server stores feedback information such as "Yamada Taro passed the first interview because he met the skill requirements" in a database so that it can be referenced during the next selection process.

[0494] Such a system will efficiently carry out the entire process of receiving, analyzing, evaluating, and providing feedback on applicants, reducing the burden on human resources personnel and reducing mismatches between companies and applicants.

[0495] The processing flow will be explained below.

[0496] Step 1:

[0497] A user fills out a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[0498] Step 2:

[0499] The device sends the entered application information to the server. Specifically, the data is sent using an HTTP POST request. The application information is sent to the server in JSON format.

[0500] Step 3:

[0501] The server receives the application information and stores it in a database. The received information is stored in the database in an appropriate format.

[0502] Step 4:

[0503] The server periodically checks for new application information and extracts it if new application information is found.

[0504] Step 5:

[0505] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[0506] Step 6:

[0507] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[0508] Step 7:

[0509] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[0510] Step 8:

[0511] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[0512] Step 9:

[0513] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[0514] Step 10:

[0515] The server receives the applicant's answers and sends them to the generating AI for analysis. After receiving the analysis results, it incorporates them into the evaluation process.

[0516] Step 11:

[0517] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation. The evaluation results and reasons for recommendation are summarized in a concrete format.

[0518] Step 12:

[0519] The server then sends the evaluation report to the HR personnel, notifying them via email or a dedicated management dashboard.

[0520] Step 13:

[0521] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[0522] This series of steps allows the entire process to be carried out efficiently, from receiving applicant information to analyzing, evaluating, notifying, and storing feedback.

[0523] Example 1

[0524] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0525] In conventional recruitment systems, the process from collecting applicant information to analyzing, evaluating, and providing feedback is not carried out efficiently, placing a heavy burden on HR personnel and making it difficult to achieve appropriate skill matching. In addition, preparing for and evaluating the first interview is cumbersome, making it easy for mismatches to occur between companies and applicants. These issues need to be resolved.

[0526] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0527] In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze the received information, means for calculating the applicant's skill matching based on the results of the analysis, means for generating questions for the first interview and collecting and analyzing the applicant's responses, means for reflecting the results of the skill matching and interview questions in the evaluation results, and means for outputting the evaluation results. This not only enables efficient reception, analysis, evaluation, and feedback of applicant information, but also realizes skill matching that meets the needs of the company, improving the efficiency of preparation for and evaluation of the first interview.

[0528] "Generative artificial intelligence" refers to the advanced algorithms and machine learning models used to analyze and evaluate received information.

[0529] "Skills matching" refers to the process of analyzing an applicant's skills and work history and comparing them with the company's requirements to evaluate their suitability.

[0530] "First-stage interview questions" refer to interview questions generated by generative artificial intelligence to evaluate an applicant's abilities and aptitude.

[0531] "Analysis results" refers to the data and evaluation regarding work history and skill sets obtained by the generative AI analyzing the applicant's information.

[0532] "Evaluation results" refers to the results of a comprehensive evaluation of the applicant's skill matching and answers to interview questions.

[0533] "Feedback" refers to the evaluation and recommendations provided to applicants based on the evaluation results.

[0534] "Database" refers to an electronic storage device used by the server to store and manage applicant information, analysis results, and evaluation results.

[0535] "Generating questions" refers to the process in which generative artificial intelligence uses a specific algorithm to automatically create questions to be asked to applicants.

[0536] An "evaluation report" is a document prepared by the server based on the applicant's skill matching and the results of the first interview, and is presented to the human resources personnel.

[0537] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[0538] Receiving applicant information

[0539] A user enters application information into a web form and presses the submit button. This information includes personal information such as name, contact details, educational background, work history, and skills. The device sends the entered application information to the server, which receives this information and stores it in a database.

[0540] For example, a user enters their name "Applicant A," work experience "5 years in software development," and skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0541] Analysis of application information

[0542] The server retrieves application information from a database, then invokes a generative AI model (e.g., OpenAI's GPT-4) to analyze the received information, which then evaluates the applicant's work history and skill set.

[0543] For example, the server passes the applicant's resume to a generator AI and sends the following prompt:

[0544] Analyze applicant information to assess work history and skill sets.

[0545] Name: Applicant A

[0546] Work experience: 5 years in software development

[0547] Skills: Python, Java

[0548] The generative AI returns analysis results such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[0549] Skill Matching Calculation

[0550] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0551] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0552] First interview simulation

[0553] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[0554] As a specific example, the generation AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The device sends this answer to the server, which then reflects it in the evaluation results based on the analysis results.

[0555] Specific prompt examples:

[0556] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[0557] Output and notification of evaluation results

[0558] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the relevant parties.

[0559] As a specific example, the server generates an evaluation report stating, "Applicant A has 5 years of Python experience and 2 years of project management experience, so he received a high skill matching score," and sends it to the relevant parties by email.

[0560] Applicant evaluation feedback storage

[0561] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[0562] As a specific example, the server stores feedback information such as "Applicant A meets the skill requirements and therefore passed the first interview" in a database so that it can be referenced during the next selection process.

[0563] This system allows for an efficient process from receiving applicant information to analyzing, evaluating, and providing feedback, thereby reducing mismatches between companies and applicants.

[0564] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0565] Step 1: Enter and submit your application information

[0566] A user enters personal information such as name, contact details, educational background, work history, and skills into a web form. When the user presses the submit button, the terminal sends the application information to a server. The input data is "Name: Applicant A, Work history: 5 years in software development, Skills: Python, Java," and this data is sent to the server as output.

[0567] Step 2: Receiving and storing applicant information

[0568] The server receives the application information sent from the terminal and stores it in a database. The server receives the application information as input and stores it in a database, thereby permanently retaining the information. The input data is "Name: Applicant A, Work Experience: 5 years in software development, Skills: Python, Java", and is stored in the database as output.

[0569] Step 3: Acquire and analyze application information

[0570] The server retrieves applicant information from the database. Then it launches a generative AI model (e.g., OpenAI's GPT-4) and sends a prompt to the generative AI to analyze the application information. The specific prompt is as follows:

[0571] Analyze applicant information to assess work history and skill sets.

[0572] Name: Applicant A

[0573] Work experience: 5 years in software development

[0574] Skills: Python, Java

[0575] Application information is provided as input, and the generating AI outputs an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[0576] Step 4: Calculate skill matching

[0577] The server receives the analysis results and retrieves the company's needs information from the database. Next, it compares the analysis results with the company's needs and calculates a skill matching score. This evaluates how well the applicant matches the company's skill requirements. The company's needs, "3+ years of Python experience, 1+ years of project management experience," are used as input, and the skill matching score is obtained as output.

[0578] Step 5: Generate questions and collect answers for the first interview

[0579] The server uses a generation AI to generate questions for the first interview. The specific prompts are as follows:

[0580] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[0581] The generated question is presented to the user, and the device collects the user's answer. The user's answer is sent to the server via the device. The input is the question obtained from the generation AI and the user's answer, "Delay in the project schedule," and the output is saved on the server.

[0582] Step 6: Analyze the first interview responses

[0583] The server sends the user's answers back to the generation AI and requests analysis. The generation AI analyzes the answers and returns the interview evaluation results. The user's answers are provided as input, and the evaluation result, such as "high schedule management ability," is obtained as output.

[0584] Step 7: Generate evaluation results and recommendations

[0585] The server creates a report summarizing the evaluation results and reasons for recommendation based on the applicant's skill matching score and the results of the first interview. The report is notified to the relevant parties. Based on the skill matching score and the results of the first interview as input, an evaluation report is generated as output and sent to the relevant parties by email.

[0586] Step 8: Storing the assessment results and feedback

[0587] The server stores the evaluation results and feedback in a database, and organizes and stores the information for future recruitment activities. The evaluation results and reasons for recommendation are provided as input, and are stored in the database as output.

[0588] This series of processes enables efficient reception, analysis, evaluation and feedback of applicant information, reducing mismatches between companies and applicants.

[0589] (Application example 1)

[0590] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0591] Conventional systems that analyze and evaluate applicant information make it difficult to efficiently allocate and schedule workers in specific fields. They also lack the means to collect and evaluate feedback for work efficiency and use it for future allocations. This can lead to reduced work efficiency within factories and potential mismatches in personnel allocation.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0593] In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the skill matching of the applicant based on the evaluation, means for outputting the results of the skill matching, means for receiving worker information and evaluating the received information, means for optimally allocating workers based on the evaluation, and means for outputting the allocation results, thereby enabling optimal allocation and scheduling of workers.

[0594] The "means for receiving applicant information" refers to a method or device for acquiring data such as personal information, skill set, and work history provided by the applicant and incorporating it into the system.

[0595] "Means for analyzing and evaluating information received by generative artificial intelligence" refers to a method or device that uses AI technology to analyze data received from applicants and evaluate the applicants' skills and aptitude based on the results.

[0596] The "means for calculating the skill matching of the applicant based on the evaluation" refers to a method or device for calculating the degree of match between the applicant's skills and the requirements required by the company based on the analysis results.

[0597] The "means for outputting the skill matching result" refers to a method or device for displaying or transmitting the calculated skill matching result to another system.

[0598] The "means for receiving worker information" refers to a method or device for acquiring information such as skill sets and available working hours provided by workers in a factory and incorporating this information into the system.

[0599] The "means for evaluating received information" refers to a method or device for evaluating the capabilities and aptitude of a worker based on data received from the worker.

[0600] The "means for optimally allocating workers based on the evaluation" refers to a method or device for allocating workers to the most suitable tasks within the factory based on the evaluation results.

[0601] The "means for outputting the allocation results" refers to a method or device for displaying information about optimally allocated workers or transmitting it to another system.

[0602] The system that embodies this invention receives applicant and worker information, analyzes it using a generation AI, and performs appropriate placement and matching based on the evaluation results. This system consists of the following elements:

[0603] Hardware and software environment

[0604] Hardware:

[0605] Factory robots (e.g., general industrial robots)

[0606] Server (e.g., general server products)

[0607] software:

[0608] Generative AI models (e.g., OpenAI GPT-3)

[0609] Database (e.g. PostgreSQL)

[0610] Programming language (e.g. Python)

[0611] The system's server first receives information from applicants and workers, such as personal information, skill sets, and work history. This includes functions for factory robots to collect information from workers and for applicants to provide information through web forms. This information is then sent to the server and stored in a database.

[0612] The server then passes the received information to a generative AI model, which analyzes the data. The analysis results include the applicant's skills and work history, as well as the worker's skill set and work history. Based on the analysis results, the server calculates skill matching and performs optimal placement.

[0613] After the analysis and evaluation are complete, the server outputs the results and makes appropriate placement decisions. For example, it determines whether the applicant's skills match the company's requirements and which job in the factory the worker is best suited for. Along with the evaluation results, the system also includes a function to notify the reasons for the recommendation and provide feedback as needed. This feedback can be used for future placement and scheduling.

[0614] Examples:

[0615] Worker acceptance and analysis

[0616] A factory robot receives information about worker Tanaka and sends it to a server. The server stores Tanaka's "welding" skill and available working hours in a database. The generative AI model analyzes the data and generates Tanaka's skills and evaluation results.

[0617] Scheduling and Deployment

[0618] Based on the needs of the factory, Tanaka is assigned to welding work from 09:00 to 12:00 based on the analysis results. The server outputs this information and sends the appropriate work schedule to the robot.

[0619] Prompt Sentence Examples

[0620] Enter Tanaka's work skill set and available hours:

[0621] Name: Tanaka

[0622] Skills: Welding

[0623] Availability: 09:00-18:00

[0624] Generate schedules based on factory needs:

[0625] Required Skills: Welding

[0626] Time Frame: 09:00-12:00

[0627] This allows for efficient implementation of a series of processes, from accepting workers to optimal allocation, scheduling, and feedback collection and evaluation, thereby improving work efficiency within the factory and reducing mismatches between workers and work.

[0628] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0629] Step 1:

[0630] The user inputs application or worker information. The input data includes name, skill set, available working hours, work history, etc. The terminal acquires this information and sends it to the server.

[0631] Input: Data such as name, skill set, available hours, and work history

[0632] Output: Send information to the server

[0633] Step 2:

[0634] The server stores the received application and worker information in a database. The database stores all applicant and worker information. This data is later used for analysis by the generative AI model.

[0635] Input: Application information and worker information sent from the terminal

[0636] Output: Save information to a database

[0637] Step 3:

[0638] The server retrieves the stored application and worker information and passes it to the generative AI model, which analyzes this information and evaluates skillsets, work history, aptitude, etc.

[0639] Input: Applicant and worker information retrieved from the database

[0640] Output: Analysis results from the generative AI model

[0641] Step 4:

[0642] The server calculates the skill matching of applicants based on the analysis results received from the generative AI model, and also calculates the optimal allocation of workers based on the needs of the factory.

[0643] Input: Analysis results from generative AI model, factory needs

[0644] Output: Skill matching results, worker allocation calculation results

[0645] Step 5:

[0646] The server outputs the calculated skill matching results and worker allocation calculation results. The results are notified to the user or administrator as needed. The notification includes the skill matching score and the reason for allocation.

[0647] Input: Skill matching results, worker allocation calculation results

[0648] Output: Output and notification of results

[0649] Step 6:

[0650] The server collects and evaluates feedback. After completing the task, the robot records the progress and problems, which are then analyzed by the generative AI model. The evaluation results are used for the next placement and scheduling.

[0651] Input: Work progress data, problem records

[0652] Output: Feedback evaluation result

[0653] Step 7:

[0654] The server stores the results of the previous evaluation in a database and uses them for the next placement. The stored evaluation results serve as a reference for future scheduling and placement.

[0655] Input: Feedback evaluation result

[0656] Output: Save evaluation results to a database

[0657] Through the above processing steps, optimal placement and scheduling can be performed based on applicant information, improving work efficiency within the factory.

[0658] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0659] This system receives applicant information, analyzes and evaluates it using generative artificial intelligence (AI), and also combines it with an emotion engine that recognizes the user's emotions. The purpose of this system is to provide more accurate evaluations and reduce mismatches between companies and applicants.

[0660] 1. Receiving applicant information

[0661] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[0662] The device takes into account the entered application information and sends it to the server. The information is sent to the server in JSON format, and the server stores the received application information in a database.

[0663] For example, a user enters their name "Hanako Tanaka," their work experience "5 years as a systems engineer," and their skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0664] 2. Analysis of application information

[0665] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[0666] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[0667] 3. Skill Matching Calculation

[0668] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0669] For example, if a company prioritizes "3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0670] 4. Emotion analysis using an emotion engine

[0671] The server runs an emotion engine and analyzes emotions based on applicant information and responses during the simulated first interview. The analyzed emotion data is reflected in the skill matching evaluation.

[0672] For example, during a simulated first interview, when an applicant talks about their past successful project experiences, the emotion engine detects confidence from the applicant's facial expressions and tone of voice. This information is incorporated into the evaluation.

[0673] 5. First interview simulation

[0674] The server uses artificial intelligence to generate questions for the first interview. These questions are presented to applicants and responses are collected. The collected responses are simultaneously analyzed by an emotion engine.

[0675] For example, the generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The emotion engine analyzes the user's emotional changes and reflects them in the evaluation.

[0676] 6. Output and notification of evaluation results

[0677] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[0678] As a specific example, the server generates an evaluation report stating, "Hanako Tanaka has 5 years of experience with Python and 2 years of experience in project management, and was recognized for her confidence and sincerity during the first interview, which resulted in a high skill matching score," and sends it to the human resources manager by email.

[0679] 7. Applicant evaluation feedback storage

[0680] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[0681] As a specific example, the server stores feedback information such as "Tanaka Hanako meets the skill requirements and received high evaluations in the interview, so she passed the first interview" in a database, making it available for reference during the next selection process.

[0682] In this way, a system that combines an emotion engine can take applicants' emotions into consideration when evaluating them, enabling more accurate personnel selection and reducing mismatches between companies and applicants.

[0683] The processing flow will be explained below.

[0684] Step 1:

[0685] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[0686] Step 2:

[0687] The terminal sends the entered application information to the server in JSON format, and the server stores the received application information in a database.

[0688] Step 3:

[0689] The server periodically checks for new application information to see if there is any. If new application information is found, it extracts the information and proceeds to the next step.

[0690] Step 4:

[0691] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[0692] Step 5:

[0693] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[0694] Step 6:

[0695] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[0696] Step 7:

[0697] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[0698] Step 8:

[0699] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[0700] Step 9:

[0701] The server receives the applicant's responses and sends the data to the generation AI for analysis. The analysis results are scored and analyzed by the emotion engine.

[0702] Step 10:

[0703] The server runs an emotion engine, analyzes the emotions expressed in the user's responses, and reflects them in the evaluation. Specifically, the server evaluates emotions using facial expression recognition and voice analysis.

[0704] Step 11:

[0705] The server creates a report summarizing the applicant's overall evaluation results and the reasons for the recommendation. The server also summarizes the evaluation results and sentiment analysis results in a concrete format.

[0706] Step 12:

[0707] The server then sends the evaluation report to the HR personnel, who are then notified via email or a dedicated management dashboard.

[0708] Step 13:

[0709] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[0710] Example 2

[0711] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0712] Conventional talent evaluation systems only evaluated applicants' skills and experience, failing to fully consider their emotions and behavior during interviews, resulting in mismatches between companies and applicants. Furthermore, data storage and sharing was insufficient, making it impossible to effectively utilize past evaluations in future recruitment activities.

[0713] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze and evaluate the received information, means for calculating the applicant's skill matching based on the evaluation, means for analyzing the applicant's emotions using an emotion engine, means for reflecting the analyzed emotion data in the skill matching evaluation, and means for outputting the skill matching results. This enables highly accurate evaluation that takes into account not only the applicant's skills but also their emotions and interview behavior. Furthermore, by storing the evaluation results and feedback in a database, past evaluation data can be effectively utilized in future recruitment activities.

[0714] "Means of receiving applicant information" refers to the process of collecting data such as personal information, work history, and skill sets entered by applicants through web forms, etc.

[0715] "Means for launching a generative artificial intelligence to analyze and evaluate the received information" refers to the process of launching an artificial intelligence model running on a server, analyzing the collected applicant information, and appropriately evaluating it.

[0716] "Method of calculating the applicant's skill match" is a process of comparing the skills and requirements required by the company with the applicant's skills and experience, and numerically evaluating the degree of match.

[0717] "Means for analyzing the emotions of an applicant using an emotion engine" refers to a process for analyzing the applicant's facial expressions, tone of voice, etc. to identify the applicant's emotional state.

[0718] "Means for reflecting analyzed emotional data in the skill matching evaluation" refers to a process for incorporating the emotional data obtained by the emotion engine into the skill matching evaluation score to perform a comprehensive evaluation.

[0719] "Means for outputting the results of skill matching" refers to the process of creating a report to notify human resources personnel and others of the results of the skill matching evaluation, and providing it in various output formats.

[0720] The "means for conducting a simulated first interview" is the process of using a generative AI model to generate first interview questions, present them to applicants, and collect responses.

[0721] "Means for analyzing the results of the simulation using an emotion engine" refers to the process of analyzing the applicant's answers and reactions during the first interview simulation using an emotion engine.

[0722] The "means of collecting and evaluating responses during the initial interview" is the process of collecting applicant responses during the initial interview simulation and evaluating their content and quality.

[0723] "Means for creating and outputting evaluation results and reasons for recommendation" refers to the process of creating and outputting a report summarizing the applicant's evaluation results and the reasons for recommendation.

[0724] "Means for notifying the human resources personnel of the evaluation results and reasons for recommendation" refers to the process of notifying the human resources personnel by e-mail or other means of a report of the evaluation results and reasons for recommendation that has been created.

[0725] "Means for storing evaluation results and feedback in a database" refers to the process of storing the applicant's evaluation results and feedback information in a database so that they can be referenced in future recruitment activities.

[0726] This invention is a system that receives applicant information, analyzes it using generative artificial intelligence (AI), and evaluates it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system aims to perform more accurate evaluations and reduce mismatches between companies and applicants.

[0727] 1. Receiving applicant information

[0728] The user enters personal information such as name, contact details, educational background, work history, and skills into the web form and presses the submit button. The device converts the entered application information into JSON format and sends the data to the server. The server then parses the received JSON data and stores it in a database.

[0729] For example, a user enters their name "Hanako Tanaka," their work experience "System engineer for 5 years," and their skills "Python, Java" into a web form and presses the submit button. This information is sent from the device to the server in JSON format, and the server stores it in a database.

[0730] 2. Analysis of application information

[0731] The server retrieves application information from the database and analyzes it using a generative AI model. Specifically, it sends the received information about the applicant's work history and skills to the generative AI and receives the analysis results.

[0732] For example, when the server passes applicant data to the generation AI, the prompt statement is as follows: "Analyze the skills and experience of this applicant." The generation AI returns an analysis result such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[0733] 3. Skill Matching Calculation

[0734] The server uses the analysis results from the generative AI to calculate a score that matches the skill set the company is looking for, thereby evaluating the extent to which the applicant can meet the company's expectations.

[0735] Example: If a company is looking for "3+ years of Python experience and 1+ years of project management experience," the server will compare the applicant's skills with the company's requirements and calculate a skill matching score.

[0736] 4. Emotion analysis using an emotion engine

[0737] The server uses an emotion engine to analyze the applicant's emotions, and the analyzed emotion data (e.g., confidence, sincerity, etc.) is reflected in the skill matching evaluation.

[0738] Example: During a simulated first interview, if an applicant is asked about their past successful project experiences and responds, the emotion engine will analyze their facial expressions and tone of voice and detect "confidence."

[0739] 5. First interview simulation

[0740] The server uses a generative AI model to generate questions for the first interview. These questions are presented to applicants (users) and responses are collected. The collected responses are analyzed by an emotion engine.

[0741] Example: The generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." This answer is analyzed by the emotion engine, and changes in emotion (e.g., tension) are reflected in the evaluation.

[0742] 6. Output and notification of evaluation results

[0743] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[0744] Example: The server generates an evaluation report stating, "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skill matching score because she was perceived as confident and sincere during the first interview," and emails it to the HR manager.

[0745] 7. Applicant evaluation feedback storage

[0746] The server stores the evaluation results and feedback in a database, which is then managed so that the feedback can be referenced in future recruitment activities.

[0747] Example: The server stores feedback information such as "Hanako Tanaka meets the skill requirements and has a high interview evaluation, so she passed the first interview" in a database so that it can be referenced the next time the selection process is carried out.

[0748] In this way, by combining a generative AI model with an emotion engine, this system is able to make highly accurate evaluations that take into account both the skills and emotions of applicants, thereby eliminating mismatches between companies and applicants.

[0749] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0750] The flow of this system's program processing

[0751] Step 1: Receiving applicant information

[0752] The user enters application information (name, contact details, educational background, work history, skills, etc.) into the web form and presses the submit button. The device converts the entered application information into JSON format and sends it to the server.

[0753] Input: User input information (e.g., "Hanako Tanaka", "Systems engineer 5th year", "Python, Java")

[0754] Data processing: Converts the information entered on the device into JSON format (e.g., {"name": "Hanako Tanaka", "experience": "System engineer 5 years", "skills": ["Python", "Java"]})

[0755] Output: The converted JSON format data is sent to the server.

[0756] Specific behavior: The user enters information into a form and submits it, and the device converts the information into JSON and sends it to the server.

[0757] Step 2: Save your information

[0758] The server stores the received application information in a database.

[0759] Input: Transformed JSON format application information

[0760] Data calculation: The server parses the JSON data and stores it in the database in the appropriate format.

[0761] Output: Application information is saved in the database

[0762] Specific operation: The server parses the received JSON data and writes the applicant information to the database.

[0763] Step 3: Analyze the application information

[0764] The server retrieves application information from a database and analyzes it using a generative AI model.

[0765] Input: Application information stored in the database

[0766] Data calculation: The server passes the information obtained from the database to the generation AI and obtains the analysis results.

[0767] Output: Analysis results from the generative AI (e.g., "5 years of Python experience, 3 years of Java experience, 2 years of project management experience")

[0768] Specific operation: The server sends the prompt "Analyze this applicant's skills and experience" when passing the applicant's data to the generation AI, and the generation AI returns the analysis results.

[0769] Step 4: Calculate skill matching

[0770] The server calculates a skill matching score based on the company's requirements using the analysis results from the generated AI.

[0771] Input: Analysis results from generative AI and the skill set desired by the company

[0772] Data calculation: The server compares the applicant's skills with the company's requirements and calculates a skill matching score

[0773] Output: Skill matching score (e.g. 90 points)

[0774] Specific operation: The server compares the analysis results with the company's requirements and calculates a skill matching score.

[0775] Step 5: Emotion analysis using the emotion engine

[0776] The server uses an emotion engine to analyze the emotions of applicants and reflects the analyzed data in skill matching.

[0777] Input: Applicant's video and audio data

[0778] Data calculation: The emotion engine analyzes facial expressions and voice tones to extract emotional data

[0779] Output: Extracted emotion data (e.g., confidence, sincerity, etc.)

[0780] Specific operation: The server analyzes the data during the first interview simulation using the emotion engine, and reflects the obtained emotion data in the evaluation.

[0781] Step 6: First interview simulation

[0782] The server uses the generative AI model to generate questions for the first interview, present them to the user, and collect responses.

[0783] Input: Company interview request

[0784] Data Computation: Generative AI Generates Interview Questions

[0785] Output: Interview question (e.g., "What was the most difficult problem you faced in your previous project?")

[0786] Specific operation: The generative AI generates a prompt sentence: "What was the most difficult problem you faced in your past projects?" and the user inputs an answer.

[0787] Step 7: Collect and evaluate responses

[0788] The server analyzes the collected responses using an emotion engine and makes an overall evaluation.

[0789] Input: User's answer

[0790] Data calculation: The server analyzes the answers using an emotion engine and reflects them in the evaluation.

[0791] Output: Overall evaluation result

[0792] Specific operation: The emotion engine analyzes the user's answers and incorporates the resulting emotion data into the skill matching evaluation.

[0793] Step 8: Output and notification of evaluation results

[0794] The server creates a report summarizing the overall evaluation results and reasons for recommendation and notifies the human resources officer.

[0795] Input: Skill matching score and sentiment analysis results

[0796] Data calculation: Create a report based on the evaluation results

[0797] Output: Assessment report

[0798] Specific Action: Generate an evaluation report stating "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skills matching score due to her confidence and honesty during the first interview" and send it to the HR manager via email.

[0799] Step 9: Archive the evaluation results

[0800] The server stores the evaluation results and feedback in a database and manages them so that they can be referenced in future recruitment activities.

[0801] Input: Evaluation results and feedback

[0802] Data calculation: Save to database

[0803] Output: Stored evaluation results and feedback

[0804] Specific operation: The server saves the evaluation results and feedback in a database, making them available for reference during the next selection process.

[0805] By combining a generative AI model with an emotion engine, this system enables highly accurate evaluations that take into account both the skills and emotions of applicants, reducing mismatches between companies and applicants.

[0806] (Application example 2)

[0807] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0808] Many modern recruitment systems evaluate applicants solely based on their skills and work history, resulting in frequent mismatches between companies and applicants. Applicants' emotions during interviews are also ignored, leading to inappropriate evaluations. This can result in companies missing out on talented candidates and making it difficult for applicants to find the right job. It can also make it difficult for brick-and-mortar stores to properly understand customer needs and recommend the best products, leading to lower customer satisfaction.

[0809] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the applicant's skill matching based on the evaluation, means for outputting the results of the skill matching, means for receiving customer information, analyzing it using a generative artificial intelligence, and recommending appropriate products, means including an emotion engine that recognizes and analyzes customer emotions, and means for displaying recommended products on a display device based on the analysis results. This enables evaluation and recommendations that take into account the applicant's skills and the company's needs, as well as emotions during interviews and emotions of customers in physical stores.

[0810] "Applicant" means a potential candidate for a particular position.

[0811] "Means for receiving information" refers to a system or interface for sending and receiving information input by a user to a server.

[0812] "Generative artificial intelligence" refers to a broad range of technologies, including machine learning models and AI software, that analyze and evaluate incoming information.

[0813] "Means for analyzing and evaluating" refers to the server or software that executes the process of analyzing received information and evaluating its content.

[0814] "Means for calculating skill matching" refers to algorithms or programs that compare the applicant's skills with the company's requirements and calculate the degree of match.

[0815] "Means for outputting skill matching results" means a system or interface for displaying or reporting the calculated skill matching results.

[0816] "Customer" means an individual or entity seeking a particular product or service.

[0817] "Means for recommending products" refers to systems and algorithms that suggest optimal products based on customer requirements and characteristics.

[0818] An "emotion engine that recognizes and analyzes emotions" refers to software and technology that analyzes the user's voice, facial expressions, etc. and recognizes their emotions.

[0819] "Display device" refers to a device (e.g., a smartphone, tablet, computer screen, etc.) for visually displaying analysis results, recommended products, etc.

[0820] The present invention is a system that receives applicant information, analyzes and evaluates it using generative AI, calculates skill matching, and outputs the results. As an application example, this system also includes a function to receive customer information and recommend appropriate products. It also incorporates an emotion engine that recognizes and analyzes customer emotions. Detailed embodiments of the present invention are described below.

[0821] Hardware and software used

[0822] In implementing the present invention, the following hardware and software are used.

[0823] 1. Hardware:

[0824] Server: Receives, analyzes and stores information.

[0825] Client terminal: A device (e.g., smartphone, tablet, or PC) through which a user enters application information or customer information.

[0826] Display device: A device (e.g., smartphone, tablet, or PC) used to display analysis results and recommended products.

[0827] 2. Software:

[0828] Generative AI (e.g., machine learning models such as OpenAI): Analyzes and evaluates application and customer information.

[0829] Emotion engine (e.g., emotion analysis API): Analyzes user emotions.

[0830] Cloud services (e.g. AWS): Manage data storage and server operations.

[0831] Programming language (e.g. Python): Builds the logic of the entire system.

[0832] Data processing and calculation

[0833] The server performs the following data processing and calculations.

[0834] 1. Receiving and storing applicant information:

[0835] A user inputs application information from a client terminal, and the server receives it.

[0836] The received information is sent to the server in JSON format and stored in a database.

[0837] 2. Analysis and Evaluation of Information:

[0838] The server retrieves application information from the database and launches the generative AI model.

[0839] The generative AI analyzes the information it receives and evaluates the applicant's skills and work history, extracting a skill set such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[0840] 3. Skill Matching Calculation:

[0841] The server calculates skill matching that matches the company's needs based on the analysis results, scores the degree of match with the skill requirements, and generates results.

[0842] 4. Emotion analysis:

[0843] The emotion engine analyzes applicant information and responses during the interview simulation to identify emotions (e.g., confidence, anxiety, sincerity, etc.).

[0844] This data is also reflected in the skill matching evaluation.

[0845] 5. Recommended products:

[0846] In physical stores, customers enter information about products using smartphones or other devices.

[0847] The generative AI analyzes the input information and recommends appropriate products.

[0848] Examples and prompts

[0849] As a concrete example, consider a case where a user uses their smartphone to type, "I want new wireless headphones." This information is sent to a server, where sentiment analysis is performed simultaneously.

[0850] Example prompts for generative AI models:

[0851] Customer Input: "I want new wireless headphones"

[0852] Generate recommended products.

[0853] Example prompts for the emotion engine:

[0854] Sentiment analysis target: "I was dissatisfied with the headphones I bought previously."

[0855] Analyze your emotions.

[0856] In this way, it is possible to analyze the user's input information and emotions and recommend the most suitable products, which also increases the satisfaction of applicants and customers.

[0857] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0858] Step 1:

[0859] The user enters application or customer information from a client terminal, which receives it. For applicants, the information entered includes name, contact details, educational background, work history, skills, etc., while for customers, it includes desired product features and requests. The terminal sends this information to the server. The data format is JSON. For example, a user may enter a request such as "I want new wireless headphones."

[0860] Input: User-entered data

[0861] Output: JSON formatted transmission data

[0862] How it works: The device receives user input data and sends it to the server in JSON format.

[0863] Step 2:

[0864] The server stores the received information in a database, which allows the information to be retained for subsequent analysis and evaluation. The database is managed by a cloud service (e.g., AWS).

[0865] Input: User data in JSON format

[0866] Output: Data stored in the database

[0867] How it works: The server saves the received data in a database in JSON format.

[0868] Step 3:

[0869] The server retrieves application or customer information from the database and activates the generative AI model, which analyzes the received information and performs a detailed evaluation based on it, such as analyzing the applicant's skill set and work history, or the product characteristics based on the customer's request.

[0870] Input: User data retrieved from the database

[0871] Output: Analysis results by generative AI

[0872] How it works: The server analyzes the data using the generative AI model and generates an evaluation result.

[0873] Step 4:

[0874] Based on the analysis results of the generated AI model, the server calculates skill matching and product recommendations that match the company's needs and customer desires. It calculates a skill matching score or recommendation score.

[0875] Input: Analysis results by generative AI

[0876] Output: Scored matching results or recommendation results

[0877] How it works: The server calculates the score using a matching algorithm.

[0878] Step 5:

[0879] The server launches the emotion engine and analyzes the user's input information, answers during the interview simulation, and customer requests. Here, emotions are identified from the applicant's facial expressions, tone of voice, and customer text input. For example, dissatisfaction is detected from the input, "I was dissatisfied with the headphones I bought previously."

[0880] Input: Data to be analyzed for user sentiment

[0881] Output: Parsed emotion data

[0882] How it works: The emotion engine analyzes the input data and generates emotion data.

[0883] Step 6:

[0884] Based on the analysis results, the server outputs recommendation results and skill matching results and notifies the user. In addition, to visually display appropriate recommended products, the server sends the results in JSON format to the terminal. The response is then displayed on the user's client terminal.

[0885] Input: Analysis results and scored data

[0886] Output: Recommendation results or skill matching results displayed on the display device

[0887] Operation: The server sends the analysis results in JSON format to the device for visual display.

[0888] Step 7:

[0889] The analysis results and feedback information are stored in a database, and the stored data is used for future recruitment activities and to improve customer service.

[0890] Input: Analysis results and feedback data

[0891] Output: Historical data stored in a database

[0892] How it works: The server stores the analysis results and feedback in a database.

[0893] The above are the specific processing steps of the system for realizing the application example.

[0894] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0895] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0896] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0897] [Third embodiment]

[0898] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0899] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0900] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0901] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0902] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0903] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0904] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0905] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0906] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0907] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0908] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0909] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0910] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[0911] 1. Receiving applicant information

[0912] A user fills in a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[0913] The terminal sends the entered application information to the server, which receives the information and stores it in a database.

[0914] For example, a user enters his name "Yamada Taro," his work experience "5 years in software development," and his skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0915] 2. Analysis of application information

[0916] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[0917] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[0918] 3. Skill Matching Calculation

[0919] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0920] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0921] 4. First interview simulation

[0922] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[0923] For example, the AI ​​generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The server analyzes this answer and reflects it in the evaluation results.

[0924] 5. Output and notification of evaluation results

[0925] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the human resources manager.

[0926] As a specific example, the server generates an evaluation report stating, "Yamada Taro has 5 years of experience with Python and 2 years of experience in project management, so he received a high skill matching score," and sends it to the human resources manager by email.

[0927] 6. Applicant evaluation feedback storage

[0928] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[0929] As a specific example, the server stores feedback information such as "Yamada Taro passed the first interview because he met the skill requirements" in a database so that it can be referenced during the next selection process.

[0930] Such a system will efficiently carry out the entire process of receiving, analyzing, evaluating, and providing feedback on applicants, reducing the burden on human resources personnel and reducing mismatches between companies and applicants.

[0931] The processing flow will be explained below.

[0932] Step 1:

[0933] A user fills out a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[0934] Step 2:

[0935] The device sends the entered application information to the server. Specifically, the data is sent using an HTTP POST request. The application information is sent to the server in JSON format.

[0936] Step 3:

[0937] The server receives the application information and stores it in a database. The received information is stored in the database in an appropriate format.

[0938] Step 4:

[0939] The server periodically checks for new application information and extracts it if new application information is found.

[0940] Step 5:

[0941] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[0942] Step 6:

[0943] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[0944] Step 7:

[0945] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[0946] Step 8:

[0947] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[0948] Step 9:

[0949] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[0950] Step 10:

[0951] The server receives the applicant's answers and sends them to the generating AI for analysis. After receiving the analysis results, it incorporates them into the evaluation process.

[0952] Step 11:

[0953] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation. The evaluation results and reasons for recommendation are summarized in a concrete format.

[0954] Step 12:

[0955] The server then sends the evaluation report to the HR personnel, notifying them via email or a dedicated management dashboard.

[0956] Step 13:

[0957] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[0958] This series of steps allows the entire process to be carried out efficiently, from receiving applicant information to analyzing, evaluating, notifying, and storing feedback.

[0959] Example 1

[0960] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0961] In conventional recruitment systems, the process from collecting applicant information to analyzing, evaluating, and providing feedback is not carried out efficiently, placing a heavy burden on HR personnel and making it difficult to achieve appropriate skill matching. In addition, preparing for and evaluating the first interview is cumbersome, making it easy for mismatches to occur between companies and applicants. These issues need to be resolved.

[0962] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0963] In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze the received information, means for calculating the applicant's skill matching based on the results of the analysis, means for generating questions for the first interview and collecting and analyzing the applicant's responses, means for reflecting the results of the skill matching and interview questions in the evaluation results, and means for outputting the evaluation results. This not only enables efficient reception, analysis, evaluation, and feedback of applicant information, but also realizes skill matching that meets the needs of the company, improving the efficiency of preparation for and evaluation of the first interview.

[0964] "Generative artificial intelligence" refers to the advanced algorithms and machine learning models used to analyze and evaluate received information.

[0965] "Skills matching" refers to the process of analyzing an applicant's skills and work history and comparing them with the company's requirements to evaluate their suitability.

[0966] "First-stage interview questions" refer to interview questions generated by generative artificial intelligence to evaluate an applicant's abilities and aptitude.

[0967] "Analysis results" refers to the data and evaluation regarding work history and skill sets obtained by the generative AI analyzing the applicant's information.

[0968] "Evaluation results" refers to the results of a comprehensive evaluation of the applicant's skill matching and answers to interview questions.

[0969] "Feedback" refers to the evaluation and recommendations provided to applicants based on the evaluation results.

[0970] "Database" refers to an electronic storage device used by the server to store and manage applicant information, analysis results, and evaluation results.

[0971] "Generating questions" refers to the process in which generative artificial intelligence uses a specific algorithm to automatically create questions to be asked to applicants.

[0972] An "evaluation report" is a document prepared by the server based on the applicant's skill matching and the results of the first interview, and is presented to the human resources personnel.

[0973] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[0974] Receiving applicant information

[0975] A user enters application information into a web form and presses the submit button. This information includes personal information such as name, contact details, educational background, work history, and skills. The device sends the entered application information to the server, which receives this information and stores it in a database.

[0976] For example, a user enters their name "Applicant A," work experience "5 years in software development," and skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[0977] Analysis of application information

[0978] The server retrieves application information from a database, then invokes a generative AI model (e.g., OpenAI's GPT-4) to analyze the received information, which then evaluates the applicant's work history and skill set.

[0979] For example, the server passes the applicant's resume to a generator AI and sends the following prompt:

[0980] Analyze applicant information to assess work history and skill sets.

[0981] Name: Applicant A

[0982] Work experience: 5 years in software development

[0983] Skills: Python, Java

[0984] The generative AI returns analysis results such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[0985] Skill Matching Calculation

[0986] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[0987] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[0988] First interview simulation

[0989] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[0990] As a specific example, the generation AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The device sends this answer to the server, which then reflects it in the evaluation results based on the analysis results.

[0991] Specific prompt examples:

[0992] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[0993] Output and notification of evaluation results

[0994] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the relevant parties.

[0995] As a specific example, the server generates an evaluation report stating, "Applicant A has 5 years of Python experience and 2 years of project management experience, so he received a high skill matching score," and sends it to the relevant parties by email.

[0996] Applicant evaluation feedback storage

[0997] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[0998] As a specific example, the server stores feedback information such as "Applicant A meets the skill requirements and therefore passed the first interview" in a database so that it can be referenced during the next selection process.

[0999] This system allows for an efficient process from receiving applicant information to analyzing, evaluating, and providing feedback, thereby reducing mismatches between companies and applicants.

[1000] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1001] Step 1: Enter and submit your application information

[1002] A user enters personal information such as name, contact details, educational background, work history, and skills into a web form. When the user presses the submit button, the terminal sends the application information to a server. The input data is "Name: Applicant A, Work history: 5 years in software development, Skills: Python, Java," and this data is sent to the server as output.

[1003] Step 2: Receiving and storing applicant information

[1004] The server receives the application information sent from the terminal and stores it in a database. The server receives the application information as input and stores it in a database, thereby permanently retaining the information. The input data is "Name: Applicant A, Work Experience: 5 years in software development, Skills: Python, Java", and is stored in the database as output.

[1005] Step 3: Acquire and analyze application information

[1006] The server retrieves applicant information from the database. Then it launches a generative AI model (e.g., OpenAI's GPT-4) and sends a prompt to the generative AI to analyze the application information. The specific prompt is as follows:

[1007] Analyze applicant information to assess work history and skill sets.

[1008] Name: Applicant A

[1009] Work experience: 5 years in software development

[1010] Skills: Python, Java

[1011] Application information is provided as input, and the generating AI outputs an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[1012] Step 4: Calculate skill matching

[1013] The server receives the analysis results and retrieves the company's needs information from the database. Next, it compares the analysis results with the company's needs and calculates a skill matching score. This evaluates how well the applicant matches the company's skill requirements. The company's needs, "3+ years of Python experience, 1+ years of project management experience," are used as input, and the skill matching score is obtained as output.

[1014] Step 5: Generate questions and collect answers for the first interview

[1015] The server uses a generation AI to generate questions for the first interview. The specific prompts are as follows:

[1016] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[1017] The generated question is presented to the user, and the device collects the user's answer. The user's answer is sent to the server via the device. The input is the question obtained from the generation AI and the user's answer, "Delay in the project schedule," and the output is saved on the server.

[1018] Step 6: Analyze the first interview responses

[1019] The server sends the user's answers back to the generation AI and requests analysis. The generation AI analyzes the answers and returns the interview evaluation results. The user's answers are provided as input, and the evaluation result, such as "high schedule management ability," is obtained as output.

[1020] Step 7: Generate evaluation results and recommendations

[1021] The server creates a report summarizing the evaluation results and reasons for recommendation based on the applicant's skill matching score and the results of the first interview. The report is notified to the relevant parties. Based on the skill matching score and the results of the first interview as input, an evaluation report is generated as output and sent to the relevant parties by email.

[1022] Step 8: Storing the assessment results and feedback

[1023] The server stores the evaluation results and feedback in a database, and organizes and stores the information for future recruitment activities. The evaluation results and reasons for recommendation are provided as input, and are stored in the database as output.

[1024] This series of processes enables efficient reception, analysis, evaluation and feedback of applicant information, reducing mismatches between companies and applicants.

[1025] (Application example 1)

[1026] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1027] Conventional systems that analyze and evaluate applicant information make it difficult to efficiently allocate and schedule workers in specific fields. They also lack the means to collect and evaluate feedback for work efficiency and use it for future allocations. This can lead to reduced work efficiency within factories and potential mismatches in personnel allocation.

[1028] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1029] In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the skill matching of the applicant based on the evaluation, means for outputting the results of the skill matching, means for receiving worker information and evaluating the received information, means for optimally allocating workers based on the evaluation, and means for outputting the allocation results, thereby enabling optimal allocation and scheduling of workers.

[1030] The "means for receiving applicant information" refers to a method or device for acquiring data such as personal information, skill set, and work history provided by the applicant and incorporating it into the system.

[1031] "Means for analyzing and evaluating information received by generative artificial intelligence" refers to a method or device that uses AI technology to analyze data received from applicants and evaluate the applicants' skills and aptitude based on the results.

[1032] The "means for calculating the skill matching of the applicant based on the evaluation" refers to a method or device for calculating the degree of match between the applicant's skills and the requirements required by the company based on the analysis results.

[1033] The "means for outputting the skill matching result" refers to a method or device for displaying or transmitting the calculated skill matching result to another system.

[1034] The "means for receiving worker information" refers to a method or device for acquiring information such as skill sets and available working hours provided by workers in a factory and incorporating this information into the system.

[1035] The "means for evaluating received information" refers to a method or device for evaluating the capabilities and aptitude of a worker based on data received from the worker.

[1036] The "means for optimally allocating workers based on the evaluation" refers to a method or device for allocating workers to the most suitable tasks within the factory based on the evaluation results.

[1037] The "means for outputting the allocation results" refers to a method or device for displaying information about optimally allocated workers or transmitting it to another system.

[1038] The system that embodies this invention receives applicant and worker information, analyzes it using a generation AI, and performs appropriate placement and matching based on the evaluation results. This system consists of the following elements:

[1039] Hardware and software environment

[1040] Hardware:

[1041] Factory robots (e.g., general industrial robots)

[1042] Server (e.g., general server products)

[1043] software:

[1044] Generative AI models (e.g., OpenAI GPT-3)

[1045] Database (e.g. PostgreSQL)

[1046] Programming language (e.g. Python)

[1047] The system's server first receives information from applicants and workers, such as personal information, skill sets, and work history. This includes functions for factory robots to collect information from workers and for applicants to provide information through web forms. This information is then sent to the server and stored in a database.

[1048] The server then passes the received information to a generative AI model, which analyzes the data. The analysis results include the applicant's skills and work history, as well as the worker's skill set and work history. Based on the analysis results, the server calculates skill matching and performs optimal placement.

[1049] After the analysis and evaluation are complete, the server outputs the results and makes appropriate placement decisions. For example, it determines whether the applicant's skills match the company's requirements and which job in the factory the worker is best suited for. Along with the evaluation results, the system also includes a function to notify the reasons for the recommendation and provide feedback as needed. This feedback can be used for future placement and scheduling.

[1050] Examples:

[1051] Worker acceptance and analysis

[1052] A factory robot receives information about worker Tanaka and sends it to a server. The server stores Tanaka's "welding" skill and available working hours in a database. The generative AI model analyzes the data and generates Tanaka's skills and evaluation results.

[1053] Scheduling and Deployment

[1054] Based on the needs of the factory, Tanaka is assigned to welding work from 09:00 to 12:00 based on the analysis results. The server outputs this information and sends the appropriate work schedule to the robot.

[1055] Prompt Sentence Examples

[1056] Enter Tanaka's work skill set and available hours:

[1057] Name: Tanaka

[1058] Skills: Welding

[1059] Availability: 09:00-18:00

[1060] Generate schedules based on factory needs:

[1061] Required Skills: Welding

[1062] Time Frame: 09:00-12:00

[1063] This allows for efficient implementation of a series of processes, from accepting workers to optimal allocation, scheduling, and feedback collection and evaluation, thereby improving work efficiency within the factory and reducing mismatches between workers and work.

[1064] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1065] Step 1:

[1066] The user inputs application or worker information. The input data includes name, skill set, available working hours, work history, etc. The terminal acquires this information and sends it to the server.

[1067] Input: Data such as name, skill set, available hours, and work history

[1068] Output: Send information to the server

[1069] Step 2:

[1070] The server stores the received application and worker information in a database. The database stores all applicant and worker information. This data is later used for analysis by the generative AI model.

[1071] Input: Application information and worker information sent from the terminal

[1072] Output: Save information to a database

[1073] Step 3:

[1074] The server retrieves the stored application and worker information and passes it to the generative AI model, which analyzes this information and evaluates skillsets, work history, aptitude, etc.

[1075] Input: Applicant and worker information retrieved from the database

[1076] Output: Analysis results from the generative AI model

[1077] Step 4:

[1078] The server calculates the skill matching of applicants based on the analysis results received from the generative AI model, and also calculates the optimal allocation of workers based on the needs of the factory.

[1079] Input: Analysis results from generative AI model, factory needs

[1080] Output: Skill matching results, worker allocation calculation results

[1081] Step 5:

[1082] The server outputs the calculated skill matching results and worker allocation calculation results. The results are notified to the user or administrator as needed. The notification includes the skill matching score and the reason for allocation.

[1083] Input: Skill matching results, worker allocation calculation results

[1084] Output: Output and notification of results

[1085] Step 6:

[1086] The server collects and evaluates feedback. After completing the task, the robot records the progress and problems, which are then analyzed by the generative AI model. The evaluation results are used for the next placement and scheduling.

[1087] Input: Work progress data, problem records

[1088] Output: Feedback evaluation result

[1089] Step 7:

[1090] The server stores the results of the previous evaluation in a database and uses them for the next placement. The stored evaluation results serve as a reference for future scheduling and placement.

[1091] Input: Feedback evaluation result

[1092] Output: Save evaluation results to a database

[1093] Through the above processing steps, optimal placement and scheduling can be performed based on applicant information, improving work efficiency within the factory.

[1094] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1095] This system receives applicant information, analyzes and evaluates it using generative artificial intelligence (AI), and also combines it with an emotion engine that recognizes the user's emotions. The purpose of this system is to provide more accurate evaluations and reduce mismatches between companies and applicants.

[1096] 1. Receiving applicant information

[1097] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[1098] The device takes into account the entered application information and sends it to the server. The information is sent to the server in JSON format, and the server stores the received application information in a database.

[1099] For example, a user enters their name "Hanako Tanaka," their work experience "5 years as a systems engineer," and their skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[1100] 2. Analysis of application information

[1101] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[1102] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[1103] 3. Skill Matching Calculation

[1104] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[1105] For example, if a company prioritizes "3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[1106] 4. Emotion analysis using an emotion engine

[1107] The server runs an emotion engine and analyzes emotions based on applicant information and responses during the simulated first interview. The analyzed emotion data is reflected in the skill matching evaluation.

[1108] For example, during a simulated first interview, when an applicant talks about their past successful project experiences, the emotion engine detects confidence from the applicant's facial expressions and tone of voice. This information is incorporated into the evaluation.

[1109] 5. First interview simulation

[1110] The server uses artificial intelligence to generate questions for the first interview. These questions are presented to applicants and responses are collected. The collected responses are simultaneously analyzed by an emotion engine.

[1111] For example, the generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The emotion engine analyzes the user's emotional changes and reflects them in the evaluation.

[1112] 6. Output and notification of evaluation results

[1113] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[1114] As a specific example, the server generates an evaluation report stating, "Hanako Tanaka has 5 years of experience with Python and 2 years of experience in project management, and was recognized for her confidence and sincerity during the first interview, which resulted in a high skill matching score," and sends it to the human resources manager by email.

[1115] 7. Applicant evaluation feedback storage

[1116] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[1117] As a specific example, the server stores feedback information such as "Tanaka Hanako meets the skill requirements and received high evaluations in the interview, so she passed the first interview" in a database, making it available for reference during the next selection process.

[1118] In this way, a system that combines an emotion engine can take applicants' emotions into consideration when evaluating them, enabling more accurate personnel selection and reducing mismatches between companies and applicants.

[1119] The processing flow will be explained below.

[1120] Step 1:

[1121] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[1122] Step 2:

[1123] The terminal sends the entered application information to the server in JSON format, and the server stores the received application information in a database.

[1124] Step 3:

[1125] The server periodically checks for new application information to see if there is any. If new application information is found, it extracts the information and proceeds to the next step.

[1126] Step 4:

[1127] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[1128] Step 5:

[1129] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[1130] Step 6:

[1131] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[1132] Step 7:

[1133] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[1134] Step 8:

[1135] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[1136] Step 9:

[1137] The server receives the applicant's responses and sends the data to the generation AI for analysis. The analysis results are scored and analyzed by the emotion engine.

[1138] Step 10:

[1139] The server runs an emotion engine, analyzes the emotions expressed in the user's responses, and reflects them in the evaluation. Specifically, the server evaluates emotions using facial expression recognition and voice analysis.

[1140] Step 11:

[1141] The server creates a report summarizing the applicant's overall evaluation results and the reasons for the recommendation. The server also summarizes the evaluation results and sentiment analysis results in a concrete format.

[1142] Step 12:

[1143] The server then sends the evaluation report to the HR personnel, who are then notified via email or a dedicated management dashboard.

[1144] Step 13:

[1145] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[1146] Example 2

[1147] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1148] Conventional talent evaluation systems only evaluated applicants' skills and experience, failing to fully consider their emotions and behavior during interviews, resulting in mismatches between companies and applicants. Furthermore, data storage and sharing was insufficient, making it impossible to effectively utilize past evaluations in future recruitment activities.

[1149] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze and evaluate the received information, means for calculating the applicant's skill matching based on the evaluation, means for analyzing the applicant's emotions using an emotion engine, means for reflecting the analyzed emotion data in the skill matching evaluation, and means for outputting the skill matching results. This enables highly accurate evaluation that takes into account not only the applicant's skills but also their emotions and interview behavior. Furthermore, by storing the evaluation results and feedback in a database, past evaluation data can be effectively utilized in future recruitment activities.

[1150] "Means of receiving applicant information" refers to the process of collecting data such as personal information, work history, and skill sets entered by applicants through web forms, etc.

[1151] "Means for launching a generative artificial intelligence to analyze and evaluate the received information" refers to the process of launching an artificial intelligence model running on a server, analyzing the collected applicant information, and appropriately evaluating it.

[1152] "Method of calculating the applicant's skill match" is a process of comparing the skills and requirements required by the company with the applicant's skills and experience, and numerically evaluating the degree of match.

[1153] "Means for analyzing the emotions of an applicant using an emotion engine" refers to a process for analyzing the applicant's facial expressions, tone of voice, etc. to identify the applicant's emotional state.

[1154] "Means for reflecting analyzed emotional data in the skill matching evaluation" refers to a process for incorporating the emotional data obtained by the emotion engine into the skill matching evaluation score to perform a comprehensive evaluation.

[1155] "Means for outputting the results of skill matching" refers to the process of creating a report to notify human resources personnel and others of the results of the skill matching evaluation, and providing it in various output formats.

[1156] The "means for conducting a simulated first interview" is the process of using a generative AI model to generate first interview questions, present them to applicants, and collect responses.

[1157] "Means for analyzing the results of the simulation using an emotion engine" refers to the process of analyzing the applicant's answers and reactions during the first interview simulation using an emotion engine.

[1158] The "means of collecting and evaluating responses during the initial interview" is the process of collecting applicant responses during the initial interview simulation and evaluating their content and quality.

[1159] "Means for creating and outputting evaluation results and reasons for recommendation" refers to the process of creating and outputting a report summarizing the applicant's evaluation results and the reasons for recommendation.

[1160] "Means for notifying the human resources personnel of the evaluation results and reasons for recommendation" refers to the process of notifying the human resources personnel by e-mail or other means of a report of the evaluation results and reasons for recommendation that has been created.

[1161] "Means for storing evaluation results and feedback in a database" refers to the process of storing the applicant's evaluation results and feedback information in a database so that they can be referenced in future recruitment activities.

[1162] This invention is a system that receives applicant information, analyzes it using generative artificial intelligence (AI), and evaluates it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system aims to perform more accurate evaluations and reduce mismatches between companies and applicants.

[1163] 1. Receiving applicant information

[1164] The user enters personal information such as name, contact details, educational background, work history, and skills into the web form and presses the submit button. The device converts the entered application information into JSON format and sends the data to the server. The server then parses the received JSON data and stores it in a database.

[1165] For example, a user enters their name "Hanako Tanaka," their work experience "System engineer for 5 years," and their skills "Python, Java" into a web form and presses the submit button. This information is sent from the device to the server in JSON format, and the server stores it in a database.

[1166] 2. Analysis of application information

[1167] The server retrieves application information from the database and analyzes it using a generative AI model. Specifically, it sends the received information about the applicant's work history and skills to the generative AI and receives the analysis results.

[1168] For example, when the server passes applicant data to the generation AI, the prompt statement is as follows: "Analyze the skills and experience of this applicant." The generation AI returns an analysis result such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[1169] 3. Skill Matching Calculation

[1170] The server uses the analysis results from the generative AI to calculate a score that matches the skill set the company is looking for, thereby evaluating the extent to which the applicant can meet the company's expectations.

[1171] Example: If a company is looking for "3+ years of Python experience and 1+ years of project management experience," the server will compare the applicant's skills with the company's requirements and calculate a skill matching score.

[1172] 4. Emotion analysis using an emotion engine

[1173] The server uses an emotion engine to analyze the applicant's emotions, and the analyzed emotion data (e.g., confidence, sincerity, etc.) is reflected in the skill matching evaluation.

[1174] Example: During a simulated first interview, if an applicant is asked about their past successful project experiences and responds, the emotion engine will analyze their facial expressions and tone of voice and detect "confidence."

[1175] 5. First interview simulation

[1176] The server uses a generative AI model to generate questions for the first interview. These questions are presented to applicants (users) and responses are collected. The collected responses are analyzed by an emotion engine.

[1177] Example: The generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." This answer is analyzed by the emotion engine, and changes in emotion (e.g., tension) are reflected in the evaluation.

[1178] 6. Output and notification of evaluation results

[1179] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[1180] Example: The server generates an evaluation report stating, "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skill matching score because she was perceived as confident and sincere during the first interview," and emails it to the HR manager.

[1181] 7. Applicant evaluation feedback storage

[1182] The server stores the evaluation results and feedback in a database, which is then managed so that the feedback can be referenced in future recruitment activities.

[1183] Example: The server stores feedback information such as "Hanako Tanaka meets the skill requirements and has a high interview evaluation, so she passed the first interview" in a database so that it can be referenced the next time the selection process is carried out.

[1184] In this way, by combining a generative AI model with an emotion engine, this system is able to make highly accurate evaluations that take into account both the skills and emotions of applicants, thereby eliminating mismatches between companies and applicants.

[1185] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1186] The flow of this system's program processing

[1187] Step 1: Receiving applicant information

[1188] The user enters application information (name, contact details, educational background, work history, skills, etc.) into the web form and presses the submit button. The device converts the entered application information into JSON format and sends it to the server.

[1189] Input: User input information (e.g., "Hanako Tanaka", "Systems engineer 5th year", "Python, Java")

[1190] Data processing: Converts the information entered on the device into JSON format (e.g., {"name": "Hanako Tanaka", "experience": "System engineer 5 years", "skills": ["Python", "Java"]})

[1191] Output: The converted JSON format data is sent to the server.

[1192] Specific behavior: The user enters information into a form and submits it, and the device converts the information into JSON and sends it to the server.

[1193] Step 2: Save your information

[1194] The server stores the received application information in a database.

[1195] Input: Transformed JSON format application information

[1196] Data calculation: The server parses the JSON data and stores it in the database in the appropriate format.

[1197] Output: Application information is saved in the database

[1198] Specific operation: The server parses the received JSON data and writes the applicant information to the database.

[1199] Step 3: Analyze the application information

[1200] The server retrieves application information from a database and analyzes it using a generative AI model.

[1201] Input: Application information stored in the database

[1202] Data calculation: The server passes the information obtained from the database to the generation AI and obtains the analysis results.

[1203] Output: Analysis results from the generative AI (e.g., "5 years of Python experience, 3 years of Java experience, 2 years of project management experience")

[1204] Specific operation: The server sends the prompt "Analyze this applicant's skills and experience" when passing the applicant's data to the generation AI, and the generation AI returns the analysis results.

[1205] Step 4: Calculate skill matching

[1206] The server calculates a skill matching score based on the company's requirements using the analysis results from the generated AI.

[1207] Input: Analysis results from generative AI and the skill set desired by the company

[1208] Data calculation: The server compares the applicant's skills with the company's requirements and calculates a skill matching score

[1209] Output: Skill matching score (e.g. 90 points)

[1210] Specific operation: The server compares the analysis results with the company's requirements and calculates a skill matching score.

[1211] Step 5: Emotion analysis using the emotion engine

[1212] The server uses an emotion engine to analyze the emotions of applicants and reflects the analyzed data in skill matching.

[1213] Input: Applicant's video and audio data

[1214] Data calculation: The emotion engine analyzes facial expressions and voice tones to extract emotional data

[1215] Output: Extracted emotion data (e.g., confidence, sincerity, etc.)

[1216] Specific operation: The server analyzes the data during the first interview simulation using the emotion engine, and reflects the obtained emotion data in the evaluation.

[1217] Step 6: First interview simulation

[1218] The server uses the generative AI model to generate questions for the first interview, present them to the user, and collect responses.

[1219] Input: Company interview request

[1220] Data Computation: Generative AI Generates Interview Questions

[1221] Output: Interview question (e.g., "What was the most difficult problem you faced in your previous project?")

[1222] Specific operation: The generative AI generates a prompt sentence: "What was the most difficult problem you faced in your past projects?" and the user inputs an answer.

[1223] Step 7: Collect and evaluate responses

[1224] The server analyzes the collected responses using an emotion engine and makes an overall evaluation.

[1225] Input: User's answer

[1226] Data calculation: The server analyzes the answers using an emotion engine and reflects them in the evaluation.

[1227] Output: Overall evaluation result

[1228] Specific operation: The emotion engine analyzes the user's answers and incorporates the resulting emotion data into the skill matching evaluation.

[1229] Step 8: Output and notification of evaluation results

[1230] The server creates a report summarizing the overall evaluation results and reasons for recommendation and notifies the human resources officer.

[1231] Input: Skill matching score and sentiment analysis results

[1232] Data calculation: Create a report based on the evaluation results

[1233] Output: Assessment report

[1234] Specific Action: Generate an evaluation report stating "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skills matching score due to her confidence and honesty during the first interview" and send it to the HR manager via email.

[1235] Step 9: Archive the evaluation results

[1236] The server stores the evaluation results and feedback in a database and manages them so that they can be referenced in future recruitment activities.

[1237] Input: Evaluation results and feedback

[1238] Data calculation: Save to database

[1239] Output: Stored evaluation results and feedback

[1240] Specific operation: The server saves the evaluation results and feedback in a database, making them available for reference during the next selection process.

[1241] By combining a generative AI model with an emotion engine, this system enables highly accurate evaluations that take into account both the skills and emotions of applicants, reducing mismatches between companies and applicants.

[1242] (Application example 2)

[1243] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1244] Many modern recruitment systems evaluate applicants solely based on their skills and work history, resulting in frequent mismatches between companies and applicants. Applicants' emotions during interviews are also ignored, leading to inappropriate evaluations. This can result in companies missing out on talented candidates and making it difficult for applicants to find the right job. It can also make it difficult for brick-and-mortar stores to properly understand customer needs and recommend the best products, leading to lower customer satisfaction.

[1245] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the applicant's skill matching based on the evaluation, means for outputting the results of the skill matching, means for receiving customer information, analyzing it using a generative artificial intelligence, and recommending appropriate products, means including an emotion engine that recognizes and analyzes customer emotions, and means for displaying recommended products on a display device based on the analysis results. This enables evaluation and recommendations that take into account the applicant's skills and the company's needs, as well as emotions during interviews and emotions of customers in physical stores.

[1246] "Applicant" means a potential candidate for a particular position.

[1247] "Means for receiving information" refers to a system or interface for sending and receiving information input by a user to a server.

[1248] "Generative artificial intelligence" refers to a broad range of technologies, including machine learning models and AI software, that analyze and evaluate incoming information.

[1249] "Means for analyzing and evaluating" refers to the server or software that executes the process of analyzing received information and evaluating its content.

[1250] "Means for calculating skill matching" refers to algorithms or programs that compare the applicant's skills with the company's requirements and calculate the degree of match.

[1251] "Means for outputting skill matching results" means a system or interface for displaying or reporting the calculated skill matching results.

[1252] "Customer" means an individual or entity seeking a particular product or service.

[1253] "Means for recommending products" refers to systems and algorithms that suggest optimal products based on customer requirements and characteristics.

[1254] An "emotion engine that recognizes and analyzes emotions" refers to software and technology that analyzes the user's voice, facial expressions, etc. and recognizes their emotions.

[1255] "Display device" refers to a device (e.g., a smartphone, tablet, computer screen, etc.) for visually displaying analysis results, recommended products, etc.

[1256] The present invention is a system that receives applicant information, analyzes and evaluates it using generative AI, calculates skill matching, and outputs the results. As an application example, this system also includes a function to receive customer information and recommend appropriate products. It also incorporates an emotion engine that recognizes and analyzes customer emotions. Detailed embodiments of the present invention are described below.

[1257] Hardware and software used

[1258] In implementing the present invention, the following hardware and software are used.

[1259] 1. Hardware:

[1260] Server: Receives, analyzes and stores information.

[1261] Client terminal: A device (e.g., smartphone, tablet, or PC) through which a user enters application information or customer information.

[1262] Display device: A device (e.g., smartphone, tablet, or PC) used to display analysis results and recommended products.

[1263] 2. Software:

[1264] Generative AI (e.g., machine learning models such as OpenAI): Analyzes and evaluates application and customer information.

[1265] Emotion engine (e.g., emotion analysis API): Analyzes user emotions.

[1266] Cloud services (e.g. AWS): Manage data storage and server operations.

[1267] Programming language (e.g. Python): Builds the logic of the entire system.

[1268] Data processing and calculation

[1269] The server performs the following data processing and calculations.

[1270] 1. Receiving and storing applicant information:

[1271] A user inputs application information from a client terminal, and the server receives it.

[1272] The received information is sent to the server in JSON format and stored in a database.

[1273] 2. Analysis and Evaluation of Information:

[1274] The server retrieves application information from the database and launches the generative AI model.

[1275] The generative AI analyzes the information it receives and evaluates the applicant's skills and work history, extracting a skill set such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[1276] 3. Skill Matching Calculation:

[1277] The server calculates skill matching that matches the company's needs based on the analysis results, scores the degree of match with the skill requirements, and generates results.

[1278] 4. Emotion analysis:

[1279] The emotion engine analyzes applicant information and responses during the interview simulation to identify emotions (e.g., confidence, anxiety, sincerity, etc.).

[1280] This data is also reflected in the skill matching evaluation.

[1281] 5. Recommended products:

[1282] In physical stores, customers enter information about products using smartphones or other devices.

[1283] The generative AI analyzes the input information and recommends appropriate products.

[1284] Examples and prompts

[1285] As a concrete example, consider a case where a user uses their smartphone to type, "I want new wireless headphones." This information is sent to a server, where sentiment analysis is performed simultaneously.

[1286] Example prompts for generative AI models:

[1287] Customer Input: "I want new wireless headphones"

[1288] Generate recommended products.

[1289] Example prompts for the emotion engine:

[1290] Sentiment analysis target: "I was dissatisfied with the headphones I bought previously."

[1291] Analyze your emotions.

[1292] In this way, it is possible to analyze the user's input information and emotions and recommend the most suitable products, which also increases the satisfaction of applicants and customers.

[1293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1294] Step 1:

[1295] The user enters application or customer information from a client terminal, which receives it. For applicants, the information entered includes name, contact details, educational background, work history, skills, etc., while for customers, it includes desired product features and requests. The terminal sends this information to the server. The data format is JSON. For example, a user may enter a request such as "I want new wireless headphones."

[1296] Input: User-entered data

[1297] Output: JSON formatted transmission data

[1298] How it works: The device receives user input data and sends it to the server in JSON format.

[1299] Step 2:

[1300] The server stores the received information in a database, which allows the information to be retained for subsequent analysis and evaluation. The database is managed by a cloud service (e.g., AWS).

[1301] Input: User data in JSON format

[1302] Output: Data stored in the database

[1303] How it works: The server saves the received data in a database in JSON format.

[1304] Step 3:

[1305] The server retrieves application or customer information from the database and activates the generative AI model, which analyzes the received information and performs a detailed evaluation based on it, such as analyzing the applicant's skill set and work history, or the product characteristics based on the customer's request.

[1306] Input: User data retrieved from the database

[1307] Output: Analysis results by generative AI

[1308] How it works: The server analyzes the data using the generative AI model and generates an evaluation result.

[1309] Step 4:

[1310] Based on the analysis results of the generated AI model, the server calculates skill matching and product recommendations that match the company's needs and customer desires. It calculates a skill matching score or recommendation score.

[1311] Input: Analysis results by generative AI

[1312] Output: Scored matching results or recommendation results

[1313] How it works: The server calculates the score using a matching algorithm.

[1314] Step 5:

[1315] The server launches the emotion engine and analyzes the user's input information, answers during the interview simulation, and customer requests. Here, emotions are identified from the applicant's facial expressions, tone of voice, and customer text input. For example, dissatisfaction is detected from the input, "I was dissatisfied with the headphones I bought previously."

[1316] Input: Data to be analyzed for user sentiment

[1317] Output: Parsed emotion data

[1318] How it works: The emotion engine analyzes the input data and generates emotion data.

[1319] Step 6:

[1320] Based on the analysis results, the server outputs recommendation results and skill matching results and notifies the user. In addition, to visually display appropriate recommended products, the server sends the results in JSON format to the terminal. The response is then displayed on the user's client terminal.

[1321] Input: Analysis results and scored data

[1322] Output: Recommendation results or skill matching results displayed on the display device

[1323] Operation: The server sends the analysis results in JSON format to the device for visual display.

[1324] Step 7:

[1325] The analysis results and feedback information are stored in a database, and the stored data is used for future recruitment activities and to improve customer service.

[1326] Input: Analysis results and feedback data

[1327] Output: Historical data stored in a database

[1328] How it works: The server stores the analysis results and feedback in a database.

[1329] The above are the specific processing steps of the system for realizing the application example.

[1330] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1331] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1332] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1333] [Fourth embodiment]

[1334] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1335] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1336] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1337] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1338] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1339] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1340] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1341] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1342] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1343] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1344] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1345] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1346] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1347] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[1348] 1. Receiving applicant information

[1349] A user fills in a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[1350] The terminal sends the entered application information to the server, which receives the information and stores it in a database.

[1351] For example, a user enters his name "Yamada Taro," his work experience "5 years in software development," and his skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[1352] 2. Analysis of application information

[1353] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[1354] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[1355] 3. Skill Matching Calculation

[1356] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[1357] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[1358] 4. First interview simulation

[1359] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[1360] For example, the AI ​​generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The server analyzes this answer and reflects it in the evaluation results.

[1361] 5. Output and notification of evaluation results

[1362] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the human resources manager.

[1363] As a specific example, the server generates an evaluation report stating, "Yamada Taro has 5 years of experience with Python and 2 years of experience in project management, so he received a high skill matching score," and sends it to the human resources manager by email.

[1364] 6. Applicant evaluation feedback storage

[1365] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[1366] As a specific example, the server stores feedback information such as "Yamada Taro passed the first interview because he met the skill requirements" in a database so that it can be referenced during the next selection process.

[1367] Such a system will efficiently carry out the entire process of receiving, analyzing, evaluating, and providing feedback on applicants, reducing the burden on human resources personnel and reducing mismatches between companies and applicants.

[1368] The processing flow will be explained below.

[1369] Step 1:

[1370] A user fills out a web form with application information and presses the submit button. This information includes personal information such as name, contact details, education history, work history, and skills.

[1371] Step 2:

[1372] The device sends the entered application information to the server. Specifically, the data is sent using an HTTP POST request. The application information is sent to the server in JSON format.

[1373] Step 3:

[1374] The server receives the application information and stores it in a database. The received information is stored in the database in an appropriate format.

[1375] Step 4:

[1376] The server periodically checks for new application information and extracts it if new application information is found.

[1377] Step 5:

[1378] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[1379] Step 6:

[1380] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[1381] Step 7:

[1382] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[1383] Step 8:

[1384] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[1385] Step 9:

[1386] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[1387] Step 10:

[1388] The server receives the applicant's answers and sends them to the generating AI for analysis. After receiving the analysis results, it incorporates them into the evaluation process.

[1389] Step 11:

[1390] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation. The evaluation results and reasons for recommendation are summarized in a concrete format.

[1391] Step 12:

[1392] The server then sends the evaluation report to the HR personnel, notifying them via email or a dedicated management dashboard.

[1393] Step 13:

[1394] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[1395] This series of steps allows the entire process to be carried out efficiently, from receiving applicant information to analyzing, evaluating, notifying, and storing feedback.

[1396] Example 1

[1397] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1398] In conventional recruitment systems, the process from collecting applicant information to analyzing, evaluating, and providing feedback is not carried out efficiently, placing a heavy burden on HR personnel and making it difficult to achieve appropriate skill matching. In addition, preparing for and evaluating the first interview is cumbersome, making it easy for mismatches to occur between companies and applicants. These issues need to be resolved.

[1399] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1400] In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze the received information, means for calculating the applicant's skill matching based on the results of the analysis, means for generating questions for the first interview and collecting and analyzing the applicant's responses, means for reflecting the results of the skill matching and interview questions in the evaluation results, and means for outputting the evaluation results. This not only enables efficient reception, analysis, evaluation, and feedback of applicant information, but also realizes skill matching that meets the needs of the company, improving the efficiency of preparation for and evaluation of the first interview.

[1401] "Generative artificial intelligence" refers to the advanced algorithms and machine learning models used to analyze and evaluate received information.

[1402] "Skills matching" refers to the process of analyzing an applicant's skills and work history and comparing them with the company's requirements to evaluate their suitability.

[1403] "First-stage interview questions" refer to interview questions generated by generative artificial intelligence to evaluate an applicant's abilities and aptitude.

[1404] "Analysis results" refers to the data and evaluation regarding work history and skill sets obtained by the generative AI analyzing the applicant's information.

[1405] "Evaluation results" refers to the results of a comprehensive evaluation of the applicant's skill matching and answers to interview questions.

[1406] "Feedback" refers to the evaluation and recommendations provided to applicants based on the evaluation results.

[1407] "Database" refers to an electronic storage device used by the server to store and manage applicant information, analysis results, and evaluation results.

[1408] "Generating questions" refers to the process in which generative artificial intelligence uses a specific algorithm to automatically create questions to be asked to applicants.

[1409] An "evaluation report" is a document prepared by the server based on the applicant's skill matching and the results of the first interview, and is presented to the human resources personnel.

[1410] The system for implementing the present invention includes a series of processes for receiving applicant information and analyzing and evaluating that information using generative artificial intelligence (AI). Each element of the system is described in detail below.

[1411] Receiving applicant information

[1412] A user enters application information into a web form and presses the submit button. This information includes personal information such as name, contact details, educational background, work history, and skills. The device sends the entered application information to the server, which receives this information and stores it in a database.

[1413] For example, a user enters their name "Applicant A," work experience "5 years in software development," and skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[1414] Analysis of application information

[1415] The server retrieves application information from a database, then invokes a generative AI model (e.g., OpenAI's GPT-4) to analyze the received information, which then evaluates the applicant's work history and skill set.

[1416] For example, the server passes the applicant's resume to a generator AI and sends the following prompt:

[1417] Analyze applicant information to assess work history and skill sets.

[1418] Name: Applicant A

[1419] Work experience: 5 years in software development

[1420] Skills: Python, Java

[1421] The generative AI returns analysis results such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[1422] Skill Matching Calculation

[1423] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[1424] For example, if a company values ​​"3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[1425] First interview simulation

[1426] The server uses generation AI to generate questions for the first interview, presents these questions to applicants, collects their answers, analyzes the collected answers, and reflects them in the evaluation report.

[1427] As a specific example, the generation AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The device sends this answer to the server, which then reflects it in the evaluation results based on the analysis results.

[1428] Specific prompt examples:

[1429] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[1430] Output and notification of evaluation results

[1431] The server creates a report summarizing the applicant's evaluation results and the reasons for recommendation, and notifies the relevant parties.

[1432] As a specific example, the server generates an evaluation report stating, "Applicant A has 5 years of Python experience and 2 years of project management experience, so he received a high skill matching score," and sends it to the relevant parties by email.

[1433] Applicant evaluation feedback storage

[1434] The server stores the assessment results and feedback in a database, which organizes and stores this information for future recruitment activities.

[1435] As a specific example, the server stores feedback information such as "Applicant A meets the skill requirements and therefore passed the first interview" in a database so that it can be referenced during the next selection process.

[1436] This system allows for an efficient process from receiving applicant information to analyzing, evaluating, and providing feedback, thereby reducing mismatches between companies and applicants.

[1437] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1438] Step 1: Enter and submit your application information

[1439] A user enters personal information such as name, contact details, educational background, work history, and skills into a web form. When the user presses the submit button, the terminal sends the application information to a server. The input data is "Name: Applicant A, Work history: 5 years in software development, Skills: Python, Java," and this data is sent to the server as output.

[1440] Step 2: Receiving and storing applicant information

[1441] The server receives the application information sent from the terminal and stores it in a database. The server receives the application information as input and stores it in a database, thereby permanently retaining the information. The input data is "Name: Applicant A, Work Experience: 5 years in software development, Skills: Python, Java", and is stored in the database as output.

[1442] Step 3: Acquire and analyze application information

[1443] The server retrieves applicant information from the database. Then it launches a generative AI model (e.g., OpenAI's GPT-4) and sends a prompt to the generative AI to analyze the application information. The specific prompt is as follows:

[1444] Analyze applicant information to assess work history and skill sets.

[1445] Name: Applicant A

[1446] Work experience: 5 years in software development

[1447] Skills: Python, Java

[1448] Application information is provided as input, and the generating AI outputs an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[1449] Step 4: Calculate skill matching

[1450] The server receives the analysis results and retrieves the company's needs information from the database. Next, it compares the analysis results with the company's needs and calculates a skill matching score. This evaluates how well the applicant matches the company's skill requirements. The company's needs, "3+ years of Python experience, 1+ years of project management experience," are used as input, and the skill matching score is obtained as output.

[1451] Step 5: Generate questions and collect answers for the first interview

[1452] The server uses a generation AI to generate questions for the first interview. The specific prompts are as follows:

[1453] Generate questions for your first interview, such as "What was the most challenging problem you faced in your previous project?"

[1454] The generated question is presented to the user, and the device collects the user's answer. The user's answer is sent to the server via the device. The input is the question obtained from the generation AI and the user's answer, "Delay in the project schedule," and the output is saved on the server.

[1455] Step 6: Analyze the first interview responses

[1456] The server sends the user's answers back to the generation AI and requests analysis. The generation AI analyzes the answers and returns the interview evaluation results. The user's answers are provided as input, and the evaluation result, such as "high schedule management ability," is obtained as output.

[1457] Step 7: Generate evaluation results and recommendations

[1458] The server creates a report summarizing the evaluation results and reasons for recommendation based on the applicant's skill matching score and the results of the first interview. The report is notified to the relevant parties. Based on the skill matching score and the results of the first interview as input, an evaluation report is generated as output and sent to the relevant parties by email.

[1459] Step 8: Storing the assessment results and feedback

[1460] The server stores the evaluation results and feedback in a database, and organizes and stores the information for future recruitment activities. The evaluation results and reasons for recommendation are provided as input, and are stored in the database as output.

[1461] This series of processes enables efficient reception, analysis, evaluation and feedback of applicant information, reducing mismatches between companies and applicants.

[1462] (Application example 1)

[1463] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1464] Conventional systems that analyze and evaluate applicant information make it difficult to efficiently allocate and schedule workers in specific fields. They also lack the means to collect and evaluate feedback for work efficiency and use it for future allocations. This can lead to reduced work efficiency within factories and potential mismatches in personnel allocation.

[1465] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1466] In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the skill matching of the applicant based on the evaluation, means for outputting the results of the skill matching, means for receiving worker information and evaluating the received information, means for optimally allocating workers based on the evaluation, and means for outputting the allocation results, thereby enabling optimal allocation and scheduling of workers.

[1467] The "means for receiving applicant information" refers to a method or device for acquiring data such as personal information, skill set, and work history provided by the applicant and incorporating it into the system.

[1468] "Means for analyzing and evaluating information received by generative artificial intelligence" refers to a method or device that uses AI technology to analyze data received from applicants and evaluate the applicants' skills and aptitude based on the results.

[1469] The "means for calculating the skill matching of the applicant based on the evaluation" refers to a method or device for calculating the degree of match between the applicant's skills and the requirements required by the company based on the analysis results.

[1470] The "means for outputting the skill matching result" refers to a method or device for displaying or transmitting the calculated skill matching result to another system.

[1471] The "means for receiving worker information" refers to a method or device for acquiring information such as skill sets and available working hours provided by workers in a factory and incorporating this information into the system.

[1472] The "means for evaluating received information" refers to a method or device for evaluating the capabilities and aptitude of a worker based on data received from the worker.

[1473] The "means for optimally allocating workers based on the evaluation" refers to a method or device for allocating workers to the most suitable tasks within the factory based on the evaluation results.

[1474] The "means for outputting the allocation results" refers to a method or device for displaying information about optimally allocated workers or transmitting it to another system.

[1475] The system that embodies this invention receives applicant and worker information, analyzes it using a generation AI, and performs appropriate placement and matching based on the evaluation results. This system consists of the following elements:

[1476] Hardware and software environment

[1477] Hardware:

[1478] Factory robots (e.g., general industrial robots)

[1479] Server (e.g., general server products)

[1480] software:

[1481] Generative AI models (e.g., OpenAI GPT-3)

[1482] Database (e.g. PostgreSQL)

[1483] Programming language (e.g. Python)

[1484] The system's server first receives information from applicants and workers, such as personal information, skill sets, and work history. This includes functions for factory robots to collect information from workers and for applicants to provide information through web forms. This information is then sent to the server and stored in a database.

[1485] The server then passes the received information to a generative AI model, which analyzes the data. The analysis results include the applicant's skills and work history, as well as the worker's skill set and work history. Based on the analysis results, the server calculates skill matching and performs optimal placement.

[1486] After the analysis and evaluation are complete, the server outputs the results and makes appropriate placement decisions. For example, it determines whether the applicant's skills match the company's requirements and which job in the factory the worker is best suited for. Along with the evaluation results, the system also includes a function to notify the reasons for the recommendation and provide feedback as needed. This feedback can be used for future placement and scheduling.

[1487] Examples:

[1488] Worker acceptance and analysis

[1489] A factory robot receives information about worker Tanaka and sends it to a server. The server stores Tanaka's "welding" skill and available working hours in a database. The generative AI model analyzes the data and generates Tanaka's skills and evaluation results.

[1490] Scheduling and Deployment

[1491] Based on the needs of the factory, Tanaka is assigned to welding work from 09:00 to 12:00 based on the analysis results. The server outputs this information and sends the appropriate work schedule to the robot.

[1492] Prompt Sentence Examples

[1493] Enter Tanaka's work skill set and available hours:

[1494] Name: Tanaka

[1495] Skills: Welding

[1496] Availability: 09:00-18:00

[1497] Generate schedules based on factory needs:

[1498] Required Skills: Welding

[1499] Time Frame: 09:00-12:00

[1500] This allows for efficient implementation of a series of processes, from accepting workers to optimal allocation, scheduling, and feedback collection and evaluation, thereby improving work efficiency within the factory and reducing mismatches between workers and work.

[1501] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1502] Step 1:

[1503] The user inputs application or worker information. The input data includes name, skill set, available working hours, work history, etc. The terminal acquires this information and sends it to the server.

[1504] Input: Data such as name, skill set, available hours, and work history

[1505] Output: Send information to the server

[1506] Step 2:

[1507] The server stores the received application and worker information in a database. The database stores all applicant and worker information. This data is later used for analysis by the generative AI model.

[1508] Input: Application information and worker information sent from the terminal

[1509] Output: Save information to a database

[1510] Step 3:

[1511] The server retrieves the stored application and worker information and passes it to the generative AI model, which analyzes this information and evaluates skillsets, work history, aptitude, etc.

[1512] Input: Applicant and worker information retrieved from the database

[1513] Output: Analysis results from the generative AI model

[1514] Step 4:

[1515] The server calculates the skill matching of applicants based on the analysis results received from the generative AI model, and also calculates the optimal allocation of workers based on the needs of the factory.

[1516] Input: Analysis results from generative AI model, factory needs

[1517] Output: Skill matching results, worker allocation calculation results

[1518] Step 5:

[1519] The server outputs the calculated skill matching results and worker allocation calculation results. The results are notified to the user or administrator as needed. The notification includes the skill matching score and the reason for allocation.

[1520] Input: Skill matching results, worker allocation calculation results

[1521] Output: Output and notification of results

[1522] Step 6:

[1523] The server collects and evaluates feedback. After completing the task, the robot records the progress and problems, which are then analyzed by the generative AI model. The evaluation results are used for the next placement and scheduling.

[1524] Input: Work progress data, problem records

[1525] Output: Feedback evaluation result

[1526] Step 7:

[1527] The server stores the results of the previous evaluation in a database and uses them for the next placement. The stored evaluation results serve as a reference for future scheduling and placement.

[1528] Input: Feedback evaluation result

[1529] Output: Save evaluation results to a database

[1530] Through the above processing steps, optimal placement and scheduling can be performed based on applicant information, improving work efficiency within the factory.

[1531] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1532] This system receives applicant information, analyzes and evaluates it using generative artificial intelligence (AI), and also combines it with an emotion engine that recognizes the user's emotions. The purpose of this system is to provide more accurate evaluations and reduce mismatches between companies and applicants.

[1533] 1. Receiving applicant information

[1534] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[1535] The device takes into account the entered application information and sends it to the server. The information is sent to the server in JSON format, and the server stores the received application information in a database.

[1536] For example, a user enters their name "Hanako Tanaka," their work experience "5 years as a systems engineer," and their skills "Python, Java" into a web form and submits it. The device sends this information to the server, which then stores it in a database.

[1537] 2. Analysis of application information

[1538] The server retrieves application information from the database, activates the generation AI, and analyzes the received information, which evaluates the applicant's work history and skill set.

[1539] As a specific example, the server passes the applicant's resume to a generation AI, which then returns an analysis result such as "5 years of Python experience, 3 years of Java experience, 2 years of project management experience."

[1540] 3. Skill Matching Calculation

[1541] The server calculates skill matching that matches the company's needs based on the analysis results from the generated AI, and evaluates how well the applicant matches the company's requirements based on the calculated score.

[1542] For example, if a company prioritizes "3+ years of Python experience and 1+ years of project management experience," the applicant's skill matching score will be higher.

[1543] 4. Emotion analysis using an emotion engine

[1544] The server runs an emotion engine and analyzes emotions based on applicant information and responses during the simulated first interview. The analyzed emotion data is reflected in the skill matching evaluation.

[1545] For example, during a simulated first interview, when an applicant talks about their past successful project experiences, the emotion engine detects confidence from the applicant's facial expressions and tone of voice. This information is incorporated into the evaluation.

[1546] 5. First interview simulation

[1547] The server uses artificial intelligence to generate questions for the first interview. These questions are presented to applicants and responses are collected. The collected responses are simultaneously analyzed by an emotion engine.

[1548] For example, the generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." The emotion engine analyzes the user's emotional changes and reflects them in the evaluation.

[1549] 6. Output and notification of evaluation results

[1550] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[1551] As a specific example, the server generates an evaluation report stating, "Hanako Tanaka has 5 years of experience with Python and 2 years of experience in project management, and was recognized for her confidence and sincerity during the first interview, which resulted in a high skill matching score," and sends it to the human resources manager by email.

[1552] 7. Applicant evaluation feedback storage

[1553] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[1554] As a specific example, the server stores feedback information such as "Tanaka Hanako meets the skill requirements and received high evaluations in the interview, so she passed the first interview" in a database, making it available for reference during the next selection process.

[1555] In this way, a system that combines an emotion engine can take applicants' emotions into consideration when evaluating them, enabling more accurate personnel selection and reducing mismatches between companies and applicants.

[1556] The processing flow will be explained below.

[1557] Step 1:

[1558] A user enters application information into a web form and presses the submit button. The information entered includes personal information such as name, contact details, educational background, work history, and skills.

[1559] Step 2:

[1560] The terminal sends the entered application information to the server in JSON format, and the server stores the received application information in a database.

[1561] Step 3:

[1562] The server periodically checks for new application information to see if there is any. If new application information is found, it extracts the information and proceeds to the next step.

[1563] Step 4:

[1564] The server sends the application information to the generation AI and requests analysis. Specifically, it sends an HTTP POST request with the JSON-formatted application information to the generation AI's analysis endpoint.

[1565] Step 5:

[1566] The server receives the analysis results from the generation AI, which include an evaluation of the applicant's skills and experience.

[1567] Step 6:

[1568] The server calculates skill matching based on the analysis results. Specifically, it compares the evaluation results obtained from the generation AI with the company's needs to calculate a skill matching score.

[1569] Step 7:

[1570] The server sends a request to the AI ​​to generate questions to simulate a first interview. After the questions are generated, they are presented to the applicant.

[1571] Step 8:

[1572] The user answers the questions in the first interview and sends the answers to the server. Specifically, the user enters the answers to the questions in a web form and presses the submit button.

[1573] Step 9:

[1574] The server receives the applicant's responses and sends the data to the generation AI for analysis. The analysis results are scored and analyzed by the emotion engine.

[1575] Step 10:

[1576] The server runs an emotion engine, analyzes the emotions expressed in the user's responses, and reflects them in the evaluation. Specifically, the server evaluates emotions using facial expression recognition and voice analysis.

[1577] Step 11:

[1578] The server creates a report summarizing the applicant's overall evaluation results and the reasons for the recommendation. The server also summarizes the evaluation results and sentiment analysis results in a concrete format.

[1579] Step 12:

[1580] The server then sends the evaluation report to the HR personnel, who are then notified via email or a dedicated management dashboard.

[1581] Step 13:

[1582] The server stores the evaluation results and feedback in a database, which is then managed so that it can be referenced in future recruitment activities.

[1583] Example 2

[1584] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1585] Conventional talent evaluation systems only evaluated applicants' skills and experience, failing to fully consider their emotions and behavior during interviews, resulting in mismatches between companies and applicants. Furthermore, data storage and sharing was insufficient, making it impossible to effectively utilize past evaluations in future recruitment activities.

[1586] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for activating a generative artificial intelligence to analyze and evaluate the received information, means for calculating the applicant's skill matching based on the evaluation, means for analyzing the applicant's emotions using an emotion engine, means for reflecting the analyzed emotion data in the skill matching evaluation, and means for outputting the skill matching results. This enables highly accurate evaluation that takes into account not only the applicant's skills but also their emotions and interview behavior. Furthermore, by storing the evaluation results and feedback in a database, past evaluation data can be effectively utilized in future recruitment activities.

[1587] "Means of receiving applicant information" refers to the process of collecting data such as personal information, work history, and skill sets entered by applicants through web forms, etc.

[1588] "Means for launching a generative artificial intelligence to analyze and evaluate the received information" refers to the process of launching an artificial intelligence model running on a server, analyzing the collected applicant information, and appropriately evaluating it.

[1589] "Method of calculating the applicant's skill match" is a process of comparing the skills and requirements required by the company with the applicant's skills and experience, and numerically evaluating the degree of match.

[1590] "Means for analyzing the emotions of an applicant using an emotion engine" refers to a process for analyzing the applicant's facial expressions, tone of voice, etc. to identify the applicant's emotional state.

[1591] "Means for reflecting analyzed emotional data in the skill matching evaluation" refers to a process for incorporating the emotional data obtained by the emotion engine into the skill matching evaluation score to perform a comprehensive evaluation.

[1592] "Means for outputting the results of skill matching" refers to the process of creating a report to notify human resources personnel and others of the results of the skill matching evaluation, and providing it in various output formats.

[1593] The "means for conducting a simulated first interview" is the process of using a generative AI model to generate first interview questions, present them to applicants, and collect responses.

[1594] "Means for analyzing the results of the simulation using an emotion engine" refers to the process of analyzing the applicant's answers and reactions during the first interview simulation using an emotion engine.

[1595] The "means of collecting and evaluating responses during the initial interview" is the process of collecting applicant responses during the initial interview simulation and evaluating their content and quality.

[1596] "Means for creating and outputting evaluation results and reasons for recommendation" refers to the process of creating and outputting a report summarizing the applicant's evaluation results and the reasons for recommendation.

[1597] "Means for notifying the human resources personnel of the evaluation results and reasons for recommendation" refers to the process of notifying the human resources personnel by e-mail or other means of a report of the evaluation results and reasons for recommendation that has been created.

[1598] "Means for storing evaluation results and feedback in a database" refers to the process of storing the applicant's evaluation results and feedback information in a database so that they can be referenced in future recruitment activities.

[1599] This invention is a system that receives applicant information, analyzes it using generative artificial intelligence (AI), and evaluates it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system aims to perform more accurate evaluations and reduce mismatches between companies and applicants.

[1600] 1. Receiving applicant information

[1601] The user enters personal information such as name, contact details, educational background, work history, and skills into the web form and presses the submit button. The device converts the entered application information into JSON format and sends the data to the server. The server then parses the received JSON data and stores it in a database.

[1602] For example, a user enters their name "Hanako Tanaka," their work experience "System engineer for 5 years," and their skills "Python, Java" into a web form and presses the submit button. This information is sent from the device to the server in JSON format, and the server stores it in a database.

[1603] 2. Analysis of application information

[1604] The server retrieves application information from the database and analyzes it using a generative AI model. Specifically, it sends the received information about the applicant's work history and skills to the generative AI and receives the analysis results.

[1605] For example, when the server passes applicant data to the generation AI, the prompt statement is as follows: "Analyze the skills and experience of this applicant." The generation AI returns an analysis result such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[1606] 3. Skill Matching Calculation

[1607] The server uses the analysis results from the generative AI to calculate a score that matches the skill set the company is looking for, thereby evaluating the extent to which the applicant can meet the company's expectations.

[1608] Example: If a company is looking for "3+ years of Python experience and 1+ years of project management experience," the server will compare the applicant's skills with the company's requirements and calculate a skill matching score.

[1609] 4. Emotion analysis using an emotion engine

[1610] The server uses an emotion engine to analyze the applicant's emotions, and the analyzed emotion data (e.g., confidence, sincerity, etc.) is reflected in the skill matching evaluation.

[1611] Example: During a simulated first interview, if an applicant is asked about their past successful project experiences and responds, the emotion engine will analyze their facial expressions and tone of voice and detect "confidence."

[1612] 5. First interview simulation

[1613] The server uses a generative AI model to generate questions for the first interview. These questions are presented to applicants (users) and responses are collected. The collected responses are analyzed by an emotion engine.

[1614] Example: The generative AI generates the question, "What was the most difficult problem in your past projects?", and the user answers, "Delays in the project schedule." This answer is analyzed by the emotion engine, and changes in emotion (e.g., tension) are reflected in the evaluation.

[1615] 6. Output and notification of evaluation results

[1616] The server creates a report summarizing the applicant's overall evaluation results and the reasons for recommendation, and notifies the HR personnel. The evaluation results include a skill matching score and the results of the emotion engine analysis.

[1617] Example: The server generates an evaluation report stating, "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skill matching score because she was perceived as confident and sincere during the first interview," and emails it to the HR manager.

[1618] 7. Applicant evaluation feedback storage

[1619] The server stores the evaluation results and feedback in a database, which is then managed so that the feedback can be referenced in future recruitment activities.

[1620] Example: The server stores feedback information such as "Hanako Tanaka meets the skill requirements and has a high interview evaluation, so she passed the first interview" in a database so that it can be referenced the next time the selection process is carried out.

[1621] In this way, by combining a generative AI model with an emotion engine, this system is able to make highly accurate evaluations that take into account both the skills and emotions of applicants, thereby eliminating mismatches between companies and applicants.

[1622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1623] The flow of this system's program processing

[1624] Step 1: Receiving applicant information

[1625] The user enters application information (name, contact details, educational background, work history, skills, etc.) into the web form and presses the submit button. The device converts the entered application information into JSON format and sends it to the server.

[1626] Input: User input information (e.g., "Hanako Tanaka", "Systems engineer 5th year", "Python, Java")

[1627] Data processing: Converts the information entered on the device into JSON format (e.g., {"name": "Hanako Tanaka", "experience": "System engineer 5 years", "skills": ["Python", "Java"]})

[1628] Output: The converted JSON format data is sent to the server.

[1629] Specific behavior: The user enters information into a form and submits it, and the device converts the information into JSON and sends it to the server.

[1630] Step 2: Save your information

[1631] The server stores the received application information in a database.

[1632] Input: Transformed JSON format application information

[1633] Data calculation: The server parses the JSON data and stores it in the database in the appropriate format.

[1634] Output: Application information is saved in the database

[1635] Specific operation: The server parses the received JSON data and writes the applicant information to the database.

[1636] Step 3: Analyze the application information

[1637] The server retrieves application information from a database and analyzes it using a generative AI model.

[1638] Input: Application information stored in the database

[1639] Data calculation: The server passes the information obtained from the database to the generation AI and obtains the analysis results.

[1640] Output: Analysis results from the generative AI (e.g., "5 years of Python experience, 3 years of Java experience, 2 years of project management experience")

[1641] Specific operation: The server sends the prompt "Analyze this applicant's skills and experience" when passing the applicant's data to the generation AI, and the generation AI returns the analysis results.

[1642] Step 4: Calculate skill matching

[1643] The server calculates a skill matching score based on the company's requirements using the analysis results from the generated AI.

[1644] Input: Analysis results from generative AI and the skill set desired by the company

[1645] Data calculation: The server compares the applicant's skills with the company's requirements and calculates a skill matching score

[1646] Output: Skill matching score (e.g. 90 points)

[1647] Specific operation: The server compares the analysis results with the company's requirements and calculates a skill matching score.

[1648] Step 5: Emotion analysis using the emotion engine

[1649] The server uses an emotion engine to analyze the emotions of applicants and reflects the analyzed data in skill matching.

[1650] Input: Applicant's video and audio data

[1651] Data calculation: The emotion engine analyzes facial expressions and voice tones to extract emotional data

[1652] Output: Extracted emotion data (e.g., confidence, sincerity, etc.)

[1653] Specific operation: The server analyzes the data during the first interview simulation using the emotion engine, and reflects the obtained emotion data in the evaluation.

[1654] Step 6: First interview simulation

[1655] The server uses the generative AI model to generate questions for the first interview, present them to the user, and collect responses.

[1656] Input: Company interview request

[1657] Data Computation: Generative AI Generates Interview Questions

[1658] Output: Interview question (e.g., "What was the most difficult problem you faced in your previous project?")

[1659] Specific operation: The generative AI generates a prompt sentence: "What was the most difficult problem you faced in your past projects?" and the user inputs an answer.

[1660] Step 7: Collect and evaluate responses

[1661] The server analyzes the collected responses using an emotion engine and makes an overall evaluation.

[1662] Input: User's answer

[1663] Data calculation: The server analyzes the answers using an emotion engine and reflects them in the evaluation.

[1664] Output: Overall evaluation result

[1665] Specific operation: The emotion engine analyzes the user's answers and incorporates the resulting emotion data into the skill matching evaluation.

[1666] Step 8: Output and notification of evaluation results

[1667] The server creates a report summarizing the overall evaluation results and reasons for recommendation and notifies the human resources officer.

[1668] Input: Skill matching score and sentiment analysis results

[1669] Data calculation: Create a report based on the evaluation results

[1670] Output: Assessment report

[1671] Specific Action: Generate an evaluation report stating "Hanako Tanaka has 5 years of Python experience, 2 years of project management experience, and received a high skills matching score due to her confidence and honesty during the first interview" and send it to the HR manager via email.

[1672] Step 9: Archive the evaluation results

[1673] The server stores the evaluation results and feedback in a database and manages them so that they can be referenced in future recruitment activities.

[1674] Input: Evaluation results and feedback

[1675] Data calculation: Save to database

[1676] Output: Stored evaluation results and feedback

[1677] Specific operation: The server saves the evaluation results and feedback in a database, making them available for reference during the next selection process.

[1678] By combining a generative AI model with an emotion engine, this system enables highly accurate evaluations that take into account both the skills and emotions of applicants, reducing mismatches between companies and applicants.

[1679] (Application example 2)

[1680] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1681] Many modern recruitment systems evaluate applicants solely based on their skills and work history, resulting in frequent mismatches between companies and applicants. Applicants' emotions during interviews are also ignored, leading to inappropriate evaluations. This can result in companies missing out on talented candidates and making it difficult for applicants to find the right job. It can also make it difficult for brick-and-mortar stores to properly understand customer needs and recommend the best products, leading to lower customer satisfaction.

[1682] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving applicant information, means for analyzing and evaluating the received information using a generative artificial intelligence, means for calculating the applicant's skill matching based on the evaluation, means for outputting the results of the skill matching, means for receiving customer information, analyzing it using a generative artificial intelligence, and recommending appropriate products, means including an emotion engine that recognizes and analyzes customer emotions, and means for displaying recommended products on a display device based on the analysis results. This enables evaluation and recommendations that take into account the applicant's skills and the company's needs, as well as emotions during interviews and emotions of customers in physical stores.

[1683] "Applicant" means a potential candidate for a particular position.

[1684] "Means for receiving information" refers to a system or interface for sending and receiving information input by a user to a server.

[1685] "Generative artificial intelligence" refers to a broad range of technologies, including machine learning models and AI software, that analyze and evaluate incoming information.

[1686] "Means for analyzing and evaluating" refers to the server or software that executes the process of analyzing received information and evaluating its content.

[1687] "Means for calculating skill matching" refers to algorithms or programs that compare the applicant's skills with the company's requirements and calculate the degree of match.

[1688] "Means for outputting skill matching results" means a system or interface for displaying or reporting the calculated skill matching results.

[1689] "Customer" means an individual or entity seeking a particular product or service.

[1690] "Means for recommending products" refers to systems and algorithms that suggest optimal products based on customer requirements and characteristics.

[1691] An "emotion engine that recognizes and analyzes emotions" refers to software and technology that analyzes the user's voice, facial expressions, etc. and recognizes their emotions.

[1692] "Display device" refers to a device (e.g., a smartphone, tablet, computer screen, etc.) for visually displaying analysis results, recommended products, etc.

[1693] The present invention is a system that receives applicant information, analyzes and evaluates it using generative AI, calculates skill matching, and outputs the results. As an application example, this system also includes a function to receive customer information and recommend appropriate products. It also incorporates an emotion engine that recognizes and analyzes customer emotions. Detailed embodiments of the present invention are described below.

[1694] Hardware and software used

[1695] In implementing the present invention, the following hardware and software are used.

[1696] 1. Hardware:

[1697] Server: Receives, analyzes and stores information.

[1698] Client terminal: A device (e.g., smartphone, tablet, or PC) through which a user enters application information or customer information.

[1699] Display device: A device (e.g., smartphone, tablet, or PC) used to display analysis results and recommended products.

[1700] 2. Software:

[1701] Generative AI (e.g., machine learning models such as OpenAI): Analyzes and evaluates application and customer information.

[1702] Emotion engine (e.g., emotion analysis API): Analyzes user emotions.

[1703] Cloud services (e.g. AWS): Manage data storage and server operations.

[1704] Programming language (e.g. Python): Builds the logic of the entire system.

[1705] Data processing and calculation

[1706] The server performs the following data processing and calculations.

[1707] 1. Receiving and storing applicant information:

[1708] A user inputs application information from a client terminal, and the server receives it.

[1709] The received information is sent to the server in JSON format and stored in a database.

[1710] 2. Analysis and Evaluation of Information:

[1711] The server retrieves application information from the database and launches the generative AI model.

[1712] The generative AI analyzes the information it receives and evaluates the applicant's skills and work history, extracting a skill set such as "5 years of Python experience, 3 years of Java experience, and 2 years of project management experience."

[1713] 3. Skill Matching Calculation:

[1714] The server calculates skill matching that matches the company's needs based on the analysis results, scores the degree of match with the skill requirements, and generates results.

[1715] 4. Emotion analysis:

[1716] The emotion engine analyzes applicant information and responses during the interview simulation to identify emotions (e.g., confidence, anxiety, sincerity, etc.).

[1717] This data is also reflected in the skill matching evaluation.

[1718] 5. Recommended products:

[1719] In physical stores, customers enter information about products using smartphones or other devices.

[1720] The generative AI analyzes the input information and recommends appropriate products.

[1721] Examples and prompts

[1722] As a concrete example, consider a case where a user uses their smartphone to type, "I want new wireless headphones." This information is sent to a server, where sentiment analysis is performed simultaneously.

[1723] Example prompts for generative AI models:

[1724] Customer Input: "I want new wireless headphones"

[1725] Generate recommended products.

[1726] Example prompts for the emotion engine:

[1727] Sentiment analysis target: "I was dissatisfied with the headphones I bought previously."

[1728] Analyze your emotions.

[1729] In this way, it is possible to analyze the user's input information and emotions and recommend the most suitable products, which also increases the satisfaction of applicants and customers.

[1730] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1731] Step 1:

[1732] The user enters application or customer information from a client terminal, which receives it. For applicants, the information entered includes name, contact details, educational background, work history, skills, etc., while for customers, it includes desired product features and requests. The terminal sends this information to the server. The data format is JSON. For example, a user may enter a request such as "I want new wireless headphones."

[1733] Input: User-entered data

[1734] Output: JSON formatted transmission data

[1735] How it works: The device receives user input data and sends it to the server in JSON format.

[1736] Step 2:

[1737] The server stores the received information in a database, which allows the information to be retained for subsequent analysis and evaluation. The database is managed by a cloud service (e.g., AWS).

[1738] Input: User data in JSON format

[1739] Output: Data stored in the database

[1740] How it works: The server saves the received data in a database in JSON format.

[1741] Step 3:

[1742] The server retrieves application or customer information from the database and activates the generative AI model, which analyzes the received information and performs a detailed evaluation based on it, such as analyzing the applicant's skill set and work history, or the product characteristics based on the customer's request.

[1743] Input: User data retrieved from the database

[1744] Output: Analysis results by generative AI

[1745] How it works: The server analyzes the data using the generative AI model and generates an evaluation result.

[1746] Step 4:

[1747] Based on the analysis results of the generated AI model, the server calculates skill matching and product recommendations that match the company's needs and customer desires. It calculates a skill matching score or recommendation score.

[1748] Input: Analysis results by generative AI

[1749] Output: Scored matching results or recommendation results

[1750] How it works: The server calculates the score using a matching algorithm.

[1751] Step 5:

[1752] The server launches the emotion engine and analyzes the user's input information, answers during the interview simulation, and customer requests. Here, emotions are identified from the applicant's facial expressions, tone of voice, and customer text input. For example, dissatisfaction is detected from the input, "I was dissatisfied with the headphones I bought previously."

[1753] Input: Data to be analyzed for user sentiment

[1754] Output: Parsed emotion data

[1755] How it works: The emotion engine analyzes the input data and generates emotion data.

[1756] Step 6:

[1757] Based on the analysis results, the server outputs recommendation results and skill matching results and notifies the user. In addition, to visually display appropriate recommended products, the server sends the results in JSON format to the terminal. The response is then displayed on the user's client terminal.

[1758] Input: Analysis results and scored data

[1759] Output: Recommendation results or skill matching results displayed on the display device

[1760] Operation: The server sends the analysis results in JSON format to the device for visual display.

[1761] Step 7:

[1762] The analysis results and feedback information are stored in a database, and the stored data is used for future recruitment activities and to improve customer service.

[1763] Input: Analysis results and feedback data

[1764] Output: Historical data stored in a database

[1765] How it works: The server stores the analysis results and feedback in a database.

[1766] The above are the specific processing steps of the system for realizing the application example.

[1767] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1768] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1769] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1770] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1771] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1772] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1773] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1774] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1775] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1776] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1777] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1778] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1779] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1780] 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.

[1781] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1782] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1783] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1784] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1785] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1786] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1787] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1788] The following is further disclosed regarding the above embodiment.

[1789] (Claim 1)

[1790] a means for receiving applicant information;

[1791] means for analyzing and evaluating the received information by the generative artificial intelligence;

[1792] means for calculating a skill match for the applicant based on said assessment;

[1793] means for outputting the result of the skill matching;

[1794] A system including:

[1795] (Claim 2)

[1796] A means of conducting a simulation of the first interview;

[1797] means for analyzing and evaluating the results of said simulation;

[1798] The system of claim 1 further comprising:

[1799] (Claim 3)

[1800] A means for creating and outputting evaluation results and reasons for recommendation;

[1801] a means for notifying a human resources person of the evaluation results and the reasons for the recommendation;

[1802] The system of claim 1 further comprising:

[1803] "Example 1"

[1804] (Claim 1)

[1805] a means for receiving applicant information;

[1806] means for activating a generative artificial intelligence to analyze the received information;

[1807] means for calculating a skill match of the applicant based on the results of said analysis;

[1808] a means for generating initial interview questions and collecting and analyzing applicant responses;

[1809] A means for reflecting the results of the skill matching and interview questions in the evaluation results;

[1810] means for outputting the evaluation results;

[1811] A system including:

[1812] (Claim 2)

[1813] A means of conducting a simulated first interview and generating questions;

[1814] means for analyzing and evaluating the results of said simulation;

[1815] The system of claim 1 further comprising:

[1816] (Claim 3)

[1817] A means for creating and outputting evaluation results and reasons for recommendation;

[1818] a means for notifying the relevant parties of the evaluation results and the reasons for the recommendation;

[1819] The system of claim 1 further comprising:

[1820] "Application Example 1"

[1821] (Claim 1)

[1822] a means for receiving applicant information;

[1823] means for analyzing and evaluating the received information by the generative artificial intelligence;

[1824] means for calculating a skill match for the applicant based on said assessment;

[1825] means for outputting the result of the skill matching;

[1826] means for receiving worker information and evaluating the received information;

[1827] a means for optimally allocating workers based on the evaluation;

[1828] a means for outputting the placement result;

[1829] A system including:

[1830] (Claim 2)

[1831] A means of conducting a simulation of the first interview;

[1832] means for analyzing and evaluating the results of said simulation;

[1833] A means of matching and scheduling workers based on the needs of the factory;

[1834] The system of claim 1 further comprising:

[1835] (Claim 3)

[1836] A means for creating and outputting evaluation results and reasons for recommendation;

[1837] a means for notifying the user of the evaluation results and the reason for recommendation;

[1838] A means of collecting and evaluating feedback to improve work efficiency;

[1839] A means to store the results of previous assessments to aid in future placements;

[1840] The system of claim 1 further comprising:

[1841] "Example 2: Combining Emotion Engines"

[1842] (Claim 1)

[1843] a means for receiving applicant information;

[1844] means for invoking a generative artificial intelligence to analyze and evaluate the received information;

[1845] means for calculating a skill match for the applicant based on said assessment;

[1846] a means for analyzing applicant sentiment using a sentiment engine;

[1847] A means for reflecting the analyzed emotion data in the evaluation of skill matching;

[1848] means for outputting the result of the skill matching;

[1849] A system including:

[1850] (Claim 2)

[1851] A means of conducting a simulation of the first interview;

[1852] means for analyzing the results of the simulation using an emotion engine;

[1853] a means of collecting and evaluating responses during the initial interview;

[1854] The system of claim 1 further comprising:

[1855] (Claim 3)

[1856] A means for creating and outputting evaluation results and reasons for recommendation;

[1857] a means for notifying a human resources person of the evaluation results and the reasons for the recommendation;

[1858] a means of storing the assess...

Claims

1. a means for receiving applicant information; means for analyzing and evaluating the received information by the generative artificial intelligence; means for calculating a skill match for the applicant based on said assessment; means for outputting the result of the skill matching; A system including:

2. A means of conducting a simulation of the first interview; means for analyzing and evaluating the results of said simulation; The system of claim 1 further comprising:

3. A means for creating and outputting evaluation results and reasons for recommendation; a means for notifying a human resources person of the evaluation results and the reasons for the recommendation; The system of claim 1 further comprising:

Images