system

Abstract

Provide a system. [Solution] A means to quantify the skills of all employees and create a skills database, A method for analyzing the necessary requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from a skills database; A means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format; A system including:

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] In today's corporate environment, it is extremely important to properly evaluate the skills and experience of all employees and assign them to the most appropriate tasks. However, manual skill matching and employee evaluation is time-consuming and inefficient. Employees themselves also lack the means to objectively understand their own market value. In such a situation, it is difficult to assign the right people to the right jobs, hindering the company's business efficiency and success rate. [Means for solving the problem]

[0005] To address these challenges, the present invention provides a system that quantifies the skills of all employees and creates a skills database. Specifically, it uses a generative artificial intelligence model to analyze the requirements for a job and extract the most suitable employees from the skills database. It also includes a means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format. Furthermore, it includes a means for analyzing keywords in job requirements and evaluating the suitability of skills by comparing them with information in the skills database, and a means for acquiring affiliation information from an external database via an API. This allows the system to calculate an overall score based on the skill attributes and work experience of suitable employees, providing more accurate ranking results. This allows companies to quickly and accurately find the right employees, improving business efficiency and success rates.

[0006] The "skills database" is a database that stores the registered data of employees' skill information, which has been converted into numerical values.

[0007] A "generative artificial intelligence model" is a type of artificial intelligence that generates, analyzes, and extracts information based on human instructions.

[0008] "Business requirements" means the conditions and elements necessary to carry out a specific business.

[0009] The "best fit employee" refers to the employee with the skills and experience that best fit the job requirements.

[0010] "Affiliation information" is information relating to an employee's position within an organization, such as department name and job title.

[0011] "Ranking format" means a format in which items are prioritized and arranged based on specific criteria.

[0012] "Skill attributes" refer to the types and characteristics of specific skills and abilities that an employee possesses.

[0013] "Work experience" refers to the employee's past work history and career.

[0014] "Total score" refers to a comprehensive evaluation score calculated by adding up multiple evaluation criteria.

[0015] "Keywords" are words or phrases that contain important information and describe a particular task or condition.

[0016] "Conformance" is a measure of conformance to specific criteria or requirements.

[0017] "API" stands for Application Programming Interface, an interface for using functions and data between software. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present employees who are suitable for specific tasks.

[0040] Initializing the Skills Database

[0041] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. The entered skill information is registered on the server and saved in a database. Here, numerical data is registered for each type of skill.

[0042] Enter business requirements

[0043] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[0044] Identifying the best employees

[0045] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[0046] Acquisition of affiliation information

[0047] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources system) via API. This information is used to create a ranking of suitable employees.

[0048] Presented in ranking format

[0049] Based on the acquired skill scores and affiliation information, the server creates a ranking list of suitable employees. This ranking is based on the overall score, with employees who are most suited to the job requirements ranked at the top.

[0050] Displaying and Using the Results

[0051] Finally, the terminal displays the ranking results to the user, who then assigns the work to the selected employee based on the presented list. This process enables efficient and appropriate personnel allocation, improving the success rate of the work.

[0052] Specific examples

[0053] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is set to have "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[0054] This system can significantly improve a company's operational efficiency by quickly and accurately matching employee skills with job requirements.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[0058] Step 2:

[0059] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[0060] Step 3:

[0061] The user inputs the requirements for a specific task. For example, they enter keywords such as "seminar," "digital transformation use cases," "for large companies," and "online" into the input interface.

[0062] Step 4:

[0063] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[0064] Step 5:

[0065] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[0066] Step 6:

[0067] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[0068] Step 7:

[0069] After the employee who best meets the business requirements is extracted, the server retrieves affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[0070] Step 8:

[0071] Based on the affiliation information acquired by the server, a total score is calculated in combination with the skill scores of suitable employees, and a ranking is created.

[0072] Step 9:

[0073] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[0074] Step 10:

[0075] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[0076] In this way, the system of the present invention automates a series of processes from managing the skill information of all employees to matching with business requirements, and supports efficient and appropriate personnel allocation.

[0077] Example 1

[0078] 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."

[0079] Companies face challenges in efficiently identifying the skills of each employee and quickly assigning the best personnel for specific tasks. Traditional manual skill matching takes time and effort, making it difficult to select the right personnel. In addition, obtaining employee affiliation information and presenting it in a ranking format is complex and cumbersome, so an efficient system to solve these issues was needed.

[0080] 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.

[0081] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative AI model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, means for analyzing keywords in job requirements and evaluating the suitability of the skills by comparing them with information in the skills database, and means for transferring job requirements entered using a terminal to the server. This makes it possible to quickly grasp the skills of each employee and efficiently select and assign the most suitable personnel for a specific job.

[0082] An "employee" is an individual who belongs to a company or organization and performs specific tasks or roles.

[0083] The "skills database" is a database that quantifies and centrally manages various employee skills.

[0084] A "generative AI model" is an artificial intelligence model that analyzes natural language and patterns based on input data and generates and provides appropriate information.

[0085] "Job Requirements" refers to the skills, experience, and other conditions required for a particular job or project.

[0086] The "ranking format" is a format in which multiple items are ranked based on an overall score or specific criteria and listed in order from top to bottom.

[0087] "Fitness" is the degree to which something matches or conforms to a particular condition or standard.

[0088] "API" stands for Application Programming Interface, an interface that allows different software systems to communicate with each other and exchange data.

[0089] A "terminal" is a computer or device through which a user accesses a system and inputs or outputs data.

[0090] A "server" is a computer system that stores and processes data and provides services to other computers.

[0091] The present invention relates to a talent management system that builds a database in which the skills of all employees are quantified, and uses a generative artificial intelligence model to extract and present employees suitable for specific tasks.

[0092] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. For example, the user might enter numerical information such as "Programming skills: 75," "Sales skills: 60," and "Project management skills: 80." This entered skill information is sent to the server and saved in a database. The database is organized by skill type and stores the numerical data.

[0093] Next, the user inputs the requirements for a specific task. For example, "Project name: New DX project" and "Requirements: DX use case, for large companies, online" are entered through the device's input interface. The device receives these inputs and transfers them to the server according to the format.

[0094] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements. For example, it analyzes requirements such as "DX use cases," "for large companies," and "online" and extracts related keywords. Based on this, it compares the results with a skills database and evaluates each employee's skill score. For example, if employee B is recorded as "DX skills: 80" and "project management: 85," this is taken into account when assigning a score.

[0095] For the extracted employees, the server sends an API request to the external HR system to obtain their affiliation information. For example, the user obtains information such as "XX department, senior manager" and adds it to the scoring results.

[0096] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees. For example, employees with the highest overall score are listed in descending order. This ranking is adjusted so that employees who are best suited to the job requirements are placed at the top.

[0097] Finally, the terminal displays the ranking results to the user. The user then selects the most suitable employee from the displayed list and assigns the work. For example, the user can ask Employee B, who is ranked highly, to participate in a project. This process enables efficient and appropriate personnel allocation, improving the company's operational efficiency.

[0098] As a concrete example, if a user needs to find an employee to work on a new DX project, they enter the requirements of "DX use case," "for large companies," and "online" into an input form. The server analyzes this and determines that Employee B is the best fit. The server then obtains Employee B's affiliation information through the HR system API and displays it on the terminal in a ranking format. Based on the displayed results, the user can assign the work to Employee B.

[0099] The system uses generative AI models to quickly and accurately match employees with job requirements, significantly improving business efficiency.

[0100] Example prompt sentence:

[0101] "Project name: New DX Project"

[0102] "Requirements: DX use case, for large companies, online"

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1:

[0105] The user inputs the skill information of all employees, specifically numerical data such as "Programming Skills: 75," "Sales Skills: 60," and "Project Management Skills: 80," into the terminal.

[0106] Input: Employee skill data (e.g., "Programming Skills: 75")

[0107] Output: Skill data sent to the server

[0108] Specific operation: The user enters skill information into the input form on the terminal and clicks the send button. The terminal sends the entered skill information to the server. The server stores the received skill data in the database.

[0109] Step 2:

[0110] Users input the requirements for a specific business into the terminal, such as "DX use case," "for large companies," and "online."

[0111] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[0112] Output: Business requirement data sent to the server

[0113] Specific operation: The user enters business requirements into the requirements input form and clicks the send button. The terminal transfers the entered business requirements to the server according to the format. The server puts the received requirements data into a state where it is ready to be analyzed.

[0114] Step 3:

[0115] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements, thereby extracting relevant keywords.

[0116] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[0117] Output: Extracted keywords (e.g., "DX," "large company," "online," etc.)

[0118] Specific operation: The server feeds the requirements data to the generative AI model, and extracts keywords related to the requirements as an analysis result. These keywords are used in the skill database and matching process.

[0119] Step 4:

[0120] The server compares the extracted keywords with the employee skill database and evaluates and scores each employee's skill score.

[0121] Input: Extracted keywords and skill database

[0122] Output: A list of employees with relevance scores

[0123] Specific operation: The server uses the extracted keywords to match each employee's skills in the skills database and calculates a compatibility score, which indicates how well the employee's skills match the job requirements.

[0124] Step 5:

[0125] The server sends an API request to an external human resources system to obtain affiliation information for employees with high suitability scores.

[0126] Input: A list of employees with relevance scores

[0127] Output: Employee list with affiliation information added

[0128] Specific operation: The server sends a request to an external human resources system via API, obtains employee affiliation information (e.g., department name, job title, etc.), and adds it to the employee list.

[0129] Step 6:

[0130] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees.

[0131] Input: Employee list with added affiliation information

[0132] Output: A list of employees organized in rank order

[0133] Specific operation: The server sorts the employee list by overall score and generates a ranking list, which is adjusted to rank employees who are best suited to the job requirements.

[0134] Step 7:

[0135] The terminal displays the ranking results to the user, who can then select the most suitable employee based on the displayed list and assign the work to them.

[0136] Input: A list of employees organized in a ranked format

[0137] Output: Ranking results displayed to the user

[0138] Specific operation: The server sends the ranking results to the terminal, which then displays them to the user. The user selects the most suitable person from the displayed list and, if necessary, proceeds with the procedure to request the work.

[0139] (Application example 1)

[0140] 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."

[0141] Currently, many companies face the challenge of accurately understanding the skills of their employees and assigning them to appropriate tasks. Particularly on factory production lines, quickly identifying personnel with excellent specific skills and optimally assigning them directly leads to improved productivity and quality. Conventional systems cannot efficiently solve this issue, and there is a problem that appropriate personnel assignment takes time and costs.

[0142] 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.

[0143] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, and means for recommending the most suitable personnel for a specific task on a factory production line. This makes it possible to quickly select and assign the most suitable personnel for a specific job on a factory production line, etc.

[0144] "All employees" refers to all employees of a company or organization.

[0145] "Quantifying skills" means evaluating the various skills that employees possess and expressing their level numerically.

[0146] A "skills database" refers to a database that collects and stores employees' quantified skill information.

[0147] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes existing data and information and generates new information and suggestions.

[0148] "Job requirements" refer to the skills and conditions required to complete a specific job.

[0149] "Extraction" refers to retrieving relevant information or data based on specific conditions.

[0150] "Affiliation information" refers to information about the organization, such as the department and position to which an employee belongs.

[0151] "Ranking format" refers to a format in which evaluation results are ranked and displayed.

[0152] A "suitable employee" is an employee who is judged to have the most suitable skills for a particular job.

[0153] A "production line" refers to a series of equipment and systems used to manufacture products in a factory or other facility.

[0154] "Specific tasks" refer to specific tasks or roles on a production line or in business operations.

[0155] A "recommendation" is a suggestion of a particular option or course of action, particularly a superior option.

[0156] This invention is a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present the employees best suited to specific tasks. This system is particularly applicable to optimal personnel allocation on factory production lines.

[0157] First, the server registers the skill information of all employees in a skills database. This skill information is quantified based on various skills such as maintenance skills, programming skills, and quality control skills, and is stored in the database. Furthermore, a generative AI model is used to analyze the requirements for each job. Based on the results of this analysis, the server compares them with the information in the skills database to select the most suitable employees.

[0158] The specific program is processed as follows: First, the user inputs the requirements for a specific job. For example, the job requirements might be "product quality inspection," "online," and "quality control skill: 80." Next, the server analyzes these requirements and extracts employees who fit the job requirements from the skills database.

[0159] For the extracted employees, affiliation information is obtained from an external database (for example, the organization's human resources system) via API. This information is used to create a ranking of the most suitable employees, with the most suitable employees positioned at the top. The ranking results are finally displayed on the device, and the user can use this list to assign tasks to employees deemed suitable.

[0160] The following hardware and software are used to implement this system:

[0161] Hardware: Control PC, factory production line management terminal.

[0162] Software: Python, Gensim (Word2Vec), API (integration with HR system).

[0163] Specific examples

[0164] For example, suppose a factory needs to find the best staff member to perform product quality inspections. The user inputs the following job requirements into the system: "product quality inspection," "online," and "quality control skill: 80." The server then analyzes this and extracts employees with the corresponding skills from the skills database. For example, if employee B is set to have "quality control skill: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via API and displays it on the terminal as a ranking of the most suitable employees. After viewing this display, the user can request employee B to perform quality inspection work.

[0165] Prompt example

[0166] "What skills are needed to inspect product quality? Please list the skills that are required for the job."

[0167] This enables quick and accurate selection of employees best suited to specific tasks in the factory, enabling effective personnel deployment.

[0168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0169] Step 1:

[0170] A user logs in to the system and inputs the requirements for a specific job. Through the input interface, the user enters requirements such as "product quality inspection," "online," and "quality control skill: 80" into a form. This input data is sent to the server.

[0171] Step 2:

[0172] The server receives the input business requirements and analyzes them using a generative artificial intelligence model (GPT). Specifically, the text data of the business requirements is input into GPT as a prompt, and relevant keywords based on the requirements are extracted. The input here is the text data of the business requirements, and the output is a list of keywords based on the requirements.

[0173] Step 3:

[0174] Based on the keyword list obtained from the generative AI model, the server compares it with a skills database, which stores quantified skill information for all employees. As a result of the comparison, a list of employees who best meet the business requirements is generated. The input data is the keyword list and the skills database, and the output data is a tentative list of optimal employees.

[0175] Step 4:

[0176] For each employee in the provisional list, the server accesses an external database (the organization's human resources system) via API to obtain the employee's affiliation information. The obtained affiliation information includes the employee's job title and department name. The input data is the employee ID, and the output data is an employee list with the affiliation information added.

[0177] Step 5:

[0178] The server creates a ranking of the most suitable employees based on the acquired affiliation information and skill scores. The ranking is based on the suitability of skills for the job requirements and job title information. The input data is an employee list with affiliation information added, and the output data is a ranked list of suitable employees.

[0179] Step 6:

[0180] The server sends the generated ranked list of suitable employees to the terminal. The terminal displays the ranking results to the user. The user can refer to the displayed results and assign the work to the employee deemed most suitable. The input data is the ranked list of suitable employees, and the output data is the ranking results displayed on the terminal.

[0181] 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.

[0182] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model and an emotion engine to extract and present employees who are suitable for specific tasks.

[0183] Initializing the Skills Database

[0184] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[0185] Enter business requirements

[0186] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[0187] Identifying the best employees

[0188] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[0189] Recognizing user emotions using an emotion engine

[0190] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0191] Acquisition of affiliation information

[0192] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources information system) via API. This information is used to create a ranking of suitable employees.

[0193] Emotion-based ranking presentation

[0194] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees.

[0195] Displaying and Using the Results

[0196] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then uses the list to request work from the selected employee. Requests are made via email or internal company tools.

[0197] Specific examples

[0198] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then uses an emotion engine to recognize the user's emotions and adjusts how the best employees are displayed based on the user's state. Finally, the server obtains employee B's affiliation information through an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[0199] The system quickly and accurately matches employee skills with job requirements, and also takes user emotions into account to achieve more optimal personnel allocation.

[0200] The processing flow will be explained below.

[0201] Step 1:

[0202] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[0203] Step 2:

[0204] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[0205] Step 3:

[0206] The user inputs the requirements for a specific task, such as "seminar," "digital transformation use case," "for large companies," and "online" into the input interface.

[0207] Step 4:

[0208] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[0209] Step 5:

[0210] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[0211] Step 6:

[0212] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[0213] Step 7:

[0214] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0215] Step 8:

[0216] For employees who are deemed the most suitable server, the server obtains affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[0217] Step 9:

[0218] Based on the acquired affiliation information, the server calculates an overall score and ranks the employees by combining it with the skill scores of the suitable employees. Furthermore, the acquired emotional data is reflected and the ranking format is adjusted according to the user's emotions.

[0219] Step 10:

[0220] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[0221] Step 11:

[0222] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[0223] As a concrete example, consider the case of finding the right person to launch a new DX project at a company. The user inputs requirements, such as "DX use case," "for large companies," and "online," into the system. The server analyzes this and extracts employees with the appropriate skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. Next, the server uses an emotion engine to recognize the user's emotions. If the user is feeling stressed, it adjusts the display method to prioritize experienced employees and optimize the display of the most suitable employees. Finally, the server obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After viewing this display, the user can request employee B to participate in the project. This system quickly and accurately matches employee skills with business requirements and also takes user emotions into account, achieving more optimal personnel allocation.

[0224] Example 2

[0225] 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."

[0226] Traditional talent management systems lacked efficiency and accuracy in selecting personnel, requiring significant time and resources for manual processes, especially when managing large amounts of employee data. Furthermore, they selected the most suitable employees without taking into account the user's emotional state, which could result in increased user stress. Furthermore, they lacked sufficient integration with external data, making it difficult to obtain the latest employee affiliation information. A system that can solve these issues is needed.

[0227] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0228] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, emotion recognition means for recognizing the emotional state of the user and adjusting the presented ranking based on that, and means for providing a user interface and supporting the input of job requirements. This enables more optimal personnel allocation by quickly and accurately matching employee skills with job requirements and further taking the user's emotions into consideration.

[0229] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[0230] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes given data and extracts the requirements necessary for a specific task.

[0231] The "ranking format" is a format for presenting results in an order based on specific conditions.

[0232] "Emotion recognition means" is a technology for grasping the user's emotional state and adjusting the content presented based on that.

[0233] A "user interface" is the means by which a user interacts with a system and inputs required information.

[0234] An "API" is an interface for data exchange with external databases and other systems.

[0235] "Scoring" is the process of quantifying an object's evaluation based on specific criteria.

[0236] This invention relates to a talent management system that builds a database that quantifies the skills of all employees, extracts employees suitable for specific tasks using a generative artificial intelligence model and an emotion engine, and presents the optimal employees to the user in a ranking format. The system quickly and accurately identifies employees with the most suitable skills and supports the user in selecting the optimal employee based on the task requirements.

[0237] This system consists of hardware such as a server, a terminal, and an input interface operated by the user. The software uses a database system (e.g., MySQL (registered trademark), PostgreSQL), a generative artificial intelligence model (e.g., natural language processing technology such as GPT-4 (registered trademark)), and an emotion recognition engine (e.g., Microsoft (registered trademark) Azure (registered trademark) Cognitive Services, Google (registered trademark) Cloud AI).

[0238] Initializing the Skills Database

[0239] 1. The user enters the skill information of all employees. For example, the user can enter each employee's skill type (e.g., programming, project management, sales) and the corresponding skill level as a numerical value. This allows employee A to have specific skill data such as "Programming: 90, Project Management: 80."

[0240] 2. The device receives the entered skill information and sends it to the server.

[0241] 3. The server stores the received information in a database (e.g., MySQL, PostgreSQL) to create a skills database.

[0242] Enter business requirements

[0243] 1. The user enters the requirements necessary for the business. For example, they select requirements such as "Seminar," "DX Use Case," "For Large Companies," and "Online."

[0244] 2. The terminal receives the business requirements entered by the user and provides an input interface. An example of a prompt is "To find the best employee for your DX project, please enter the following requirements: seminar, DX use case, for large companies, online."

[0245] 3. The terminal sends the input requirements to the server.

[0246] Identifying the best employees

[0247] 1. The server analyzes the received business requirements using a generative artificial intelligence model (e.g., GPT-4).

[0248] 2. Matching with the skills database is performed based on the keywords extracted through analysis. For example, employees who match the requirements of "DX use cases" and "online" are extracted from the skills database.

[0249] 3. The server will score the most suitable employee based on the matching results. For example, if employee B has "DX Skill: 80" and "Online Experience: 90", he will receive a high score.

[0250] Recognizing user emotions using an emotion engine

[0251] 1. The server launches an emotion recognition engine, which uses speech recognition and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services).

[0252] 2. Using the device's camera and microphone, the voice and facial expressions of the user are captured in real time when they enter business requirements or view ranking results.

[0253] 3. The server analyzes this data and determines the user's emotional state. For example, it determines whether the user is feeling stressed.

[0254] Acquisition of affiliation information

[0255] 1. The server requests employee affiliation information from an external human resources information system via an API, which is designed as a RESTful API.

[0256] 2. Obtain the affiliation information (e.g., department name, position, etc.) returned from the external system.

[0257] 3. The server uses the information obtained to create a ranking.

[0258] Emotion-based ranking presentation

[0259] 1. The server evaluates the user's emotional state and adjusts the ranking results accordingly.

[0260] 2. For example, if a user is feeling stressed, more experienced employees will be displayed first.

[0261] Displaying and Using the Results

[0262] 1. The terminal displays the final ranking results to the user in a visually easy-to-understand format (e.g., using HTML and CSS).

[0263] 2. The user selects the most suitable employee from the presented ranking results and makes a work request. The request is made via internal tools or email.

[0264] In this way, the system of the present invention quickly and accurately matches employee skills with job requirements, and by taking user sentiment into consideration, achieves more effective personnel allocation.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1: User enters skill information

[0267] The user inputs the skill information of each employee (e.g., skill type such as programming, project management, sales, etc., and each skill level) in numerical form. The terminal receives this information through an input interface (e.g., HTML form) and formats it as input data.

[0268] Input: Skill type and skill level for each employee

[0269] Output: Formatted skill data

[0270] How it works: When the device receives the input skill information, it formats it in the appropriate format (e.g., JSON, XML) and sends it to the server.

[0271] Step 2: Creating a skills database

[0272] The server receives the skill information sent from the device and stores it in a database (e.g., MySQL, PostgreSQL).

[0273] Input: Formatted skill data

[0274] Output: Skill information stored in the database

[0275] How it works: The server validates the received skill information and, if there are no errors, executes a SQL query to insert the information into the database. For example, it executes a query like "INSERT INTO skill_table (employee_id, skill_type, skill_level) VALUES (...)".

[0276] Step 3: Enter business requirements

[0277] The user enters the requirements for a specific task (e.g., "seminar," "DX use case," "for large companies," "online") using an input interface. The device receives this information and converts it into the appropriate data format.

[0278] Input: Business requirements

[0279] Output: Formatted business requirements data

[0280] Operation: The terminal validates the requirements entered by the user, converts them into the appropriate format, and sends them to the server.

[0281] Step 4: Requirements analysis and matching

[0282] The server analyzes the business requirements sent from the device using a generative artificial intelligence model (e.g., GPT-4). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database.

[0283] Input: Business requirements data

[0284] Output: Requirement keywords and matching results

[0285] Operation: The server inputs job requirements data into a generative AI model and searches the skills database using the resulting keyword list. For example, it retrieves employees with scores such as "Programming 90" and "Online Support 85."

[0286] Step 5: Scoring and ranking

[0287] The server scores the most suitable employees based on the matching, taking into account skill attributes and work experience, and assigns a score to each employee.

[0288] Input: Matching results

[0289] Output: Employee score list

[0290] How it works: The server runs a scoring algorithm on the list of employees that match the criteria, assigning each employee a score and ranking them.

[0291] Step 6: Emotion Recognition

[0292] The server activates an emotion engine to recognize the user's emotional state, and uses the device's camera and microphone to capture voice, facial expressions, and text input.

[0293] Input: User's voice, facial expressions, and text data

[0294] Output: User's emotional state data

[0295] Operation: The device records the user's facial expressions and voice using a camera and microphone while the user is entering business requirements and displaying ranking results. This data is then sent to the server in real time.

[0296] Step 7: Sentiment-aware ranking adjustment

[0297] The server analyzes the acquired emotional state data and adjusts the ranking order according to the user's emotions.

[0298] Input: User's emotional state data

[0299] Output: Adjusted ranking results

[0300] How it works: The server analyzes the user's emotional data and optimizes the ranking, for example, by placing more experienced employees at the top if the user is under high stress.

[0301] Step 8: View results and submit work

[0302] The terminal displays the adjusted ranking results to the user, allowing the user to select the most suitable employee and request the work.

[0303] Input: Adjusted ranking results

[0304] Output: Ranking results displayed to the user

[0305] Operation: The terminal displays the ranking results to the user in a visually easy-to-understand format (e.g., HTML, CSS). The user can select the target employee from the screen and request work via email or internal tools.

[0306] The above is the specific processing flow in this system.

[0307] (Application example 2)

[0308] 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."

[0309] Conventional talent management systems require time and effort to match employee skills with job requirements, making optimal personnel placement difficult. Furthermore, because they select personnel suited to job requirements without considering the user's feelings, users may be dissatisfied with the selection results. There is a need to solve these issues and apply them to task management using factory robots.

[0310] The identification process 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 quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees or workers from the skills database, means for acquiring the affiliation information of the extracted employees or workers and presenting the most suitable employees or workers in a ranking format, means for applying the extracted most suitable employees or workers to task management by factory robots, and means for analyzing the emotional state of a user using an emotion recognition engine and reflecting the analysis results in scoring. This enables fast and accurate matching of personnel and jobs, improving user satisfaction and enabling efficient task management by factory robots.

[0311] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[0312] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes business requirements and extracts the most suitable employees or workers from a skills database.

[0313] "Job requirements" refers to information that indicates the skills and conditions required for a specific job.

[0314] "Best fit employee or worker" refers to the employee or worker who best fits the job requirements based on the skills database.

[0315] The "ranking format" is a format in which the extracted employees or workers are ranked and presented based on their suitability.

[0316] A "factory robot" is a robot used to automate work within a factory.

[0317] "Task management" is the process of managing the progress of work and assigning it to the appropriate people or machines.

[0318] An "emotion recognition engine" is an engine for analyzing the user's emotional state.

[0319] "Emotional state" is information that indicates the user's current emotional and psychological state.

[0320] "Scoring" is the process of evaluating or ranking based on specific criteria.

[0321] This invention relates to a talent management system that quantifies the skills of all employees, builds a skills database, and uses a generative artificial intelligence model and an emotion recognition engine to extract and present employees or workers suitable for specific tasks.Furthermore, it realizes efficient task management using factory robots.

[0322] Initializing the Skills Database

[0323] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[0324] Enter business requirements

[0325] Next, the user inputs the requirements for a specific task, such as "packaging," "complexity level: 3," and "deadline: 2023-12-01," into the form. At this stage, the terminal provides an input interface to help the user easily input the task requirements.

[0326] Identifying the best employees or workers

[0327] The server analyzes the input business requirements using a generative AI model. As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. Based on information such as skill attributes and work experience, the server scores the most suitable employee or worker.

[0328] Recognizing user emotions using an emotion recognition engine

[0329] The server activates an emotion recognition engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0330] Acquisition of affiliation information

[0331] For employees or workers who are deemed the most suitable, the server obtains their affiliation information (department name, job title, etc.) from an external database via API. This information is used to create a ranking of suitable employees or workers.

[0332] Emotion-based ranking presentation

[0333] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees or workers.

[0334] Displaying and Using the Results

[0335] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then selects the employee or worker from the list and assigns the task. The request is made via email or internal company tools.

[0336] Specific examples

[0337] For example, suppose a "packaging task" arises at a factory, and the factory manager inputs this requirement into the system. The task requirements, "packaging," "complexity level: 3," and "deadline: 2023-12-01," are analyzed using a generative AI model. Based on the analysis results, employees or workers with the most appropriate skills are extracted from a skills database, and the user's emotions are analyzed using an emotion recognition engine. For example, a prompt such as "Find the most appropriate worker based on the following criteria: Task type: packaging, complexity level: 3, deadline: 2023-12-01" is input into the generative AI model. Based on this information, the server presents the appropriate employees or workers to the user in a ranked format, and ultimately the task is requested.

[0338] This system quickly and accurately matches employee skills with work requirements, and also takes user emotions into account to achieve more optimal personnel allocation. It also enables efficient task management by factory robots.

[0339] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0340] Step 1:

[0341] The user inputs the skill information of all employees. The skill type and skill level of each employee are converted into numerical values ​​and registered in the system through an input interface. Specifically, data such as "Skill type: Programming" and "Skill level: 80" is entered for each employee. The input data is sent to the server and saved in the skill database. Input: Employee skill information, Output: Registration in the skill database.

[0342] Step 2:

[0343] The user inputs the requirements for a specific task. For example, requirements such as "packaging," "complexity level: 3," and "deadline: 2023-12-01" are entered into a form. The terminal provides this input interface, and the input requirements are sent to the server. Input: Task requirements, Output: Send to server.

[0344] Step 3:

[0345] The server uses a generative artificial intelligence model to analyze the input business requirements. As a result of the analysis, keywords that match the requirements are extracted. For example, based on the requirements "packaging" and "complexity level: 3," keywords for matching skills are generated. Input: Business requirements, Output: Keywords that match the requirements.

[0346] Step 4:

[0347] The server matches the generated keywords with a skills database to extract the most suitable employees or workers. For example, it extracts employees with "packaging" and "high skill level." Skill attributes and work experience are also taken into consideration. Input: Keywords that match the requirements, Output: A list of the most suitable employees or workers.

[0348] Step 5:

[0349] The server starts an emotion recognition engine and analyzes the user's emotional state. It analyzes the user's voice, facial expression, text input, etc. to obtain the user's emotional data. Input: User's voice, facial expression, text, Output: Emotional data.

[0350] Step 6:

[0351] The server obtains the affiliation information of the extracted employees or workers. It obtains the affiliation information (department name and position) from the external database via API and creates a ranking of the most suitable employees or workers. Input: Employee ID, Output: Affiliation information

[0352] Step 7:

[0353] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking order. For example, if the user is feeling stressed, the server adjusts the ranking order to give priority to more experienced employees. Input: Emotion data, Output: Adjusted ranking order.

[0354] Step 8:

[0355] The terminal displays the ranking results to the user in a format that corresponds to the emotion. For example, it may display the results in the format "Ranking 1: Employee B (Skill: 80, Project Management: 85, Position: IT Department Manager)." The user can assign tasks to the selected employee or worker based on the presented list. Input: Adjusted ranking, Output: Display of ranking results.

[0356] 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.

[0357] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0358] 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.

[0359] [Second embodiment]

[0360] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0361] 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.

[0362] 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).

[0363] 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.

[0364] 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.

[0365] 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).

[0366] 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. 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.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] In the smart glasses 214, 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.

[0371] 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."

[0372] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present employees who are suitable for specific tasks.

[0373] Initializing the Skills Database

[0374] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. The entered skill information is registered on the server and saved in a database. Here, numerical data is registered for each type of skill.

[0375] Enter business requirements

[0376] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[0377] Identifying the best employees

[0378] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[0379] Acquisition of affiliation information

[0380] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources system) via API. This information is used to create a ranking of suitable employees.

[0381] Presented in ranking format

[0382] Based on the acquired skill scores and affiliation information, the server creates a ranking list of suitable employees. This ranking is based on the overall score, with employees who are most suited to the job requirements ranked at the top.

[0383] Displaying and Using the Results

[0384] Finally, the terminal displays the ranking results to the user, who then assigns the work to the selected employee based on the presented list. This process enables efficient and appropriate personnel allocation, improving the success rate of the work.

[0385] Specific examples

[0386] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is set to have "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[0387] This system can significantly improve a company's operational efficiency by quickly and accurately matching employee skills with job requirements.

[0388] The processing flow will be explained below.

[0389] Step 1:

[0390] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[0391] Step 2:

[0392] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[0393] Step 3:

[0394] The user inputs the requirements for a specific task. For example, they enter keywords such as "seminar," "digital transformation use cases," "for large companies," and "online" into the input interface.

[0395] Step 4:

[0396] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[0397] Step 5:

[0398] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[0399] Step 6:

[0400] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[0401] Step 7:

[0402] After the employee who best meets the business requirements is extracted, the server retrieves affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[0403] Step 8:

[0404] Based on the affiliation information acquired by the server, a total score is calculated in combination with the skill scores of suitable employees, and a ranking is created.

[0405] Step 9:

[0406] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[0407] Step 10:

[0408] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[0409] In this way, the system of the present invention automates a series of processes from managing the skill information of all employees to matching with business requirements, and supports efficient and appropriate personnel allocation.

[0410] Example 1

[0411] 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."

[0412] Companies face challenges in efficiently identifying the skills of each employee and quickly assigning the best personnel for specific tasks. Traditional manual skill matching takes time and effort, making it difficult to select the right personnel. In addition, obtaining employee affiliation information and presenting it in a ranking format is complex and cumbersome, so an efficient system to solve these issues was needed.

[0413] 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.

[0414] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative AI model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, means for analyzing keywords in job requirements and evaluating the suitability of the skills by comparing them with information in the skills database, and means for transferring job requirements entered using a terminal to the server. This makes it possible to quickly grasp the skills of each employee and efficiently select and assign the most suitable personnel for a specific job.

[0415] An "employee" is an individual who belongs to a company or organization and performs specific tasks or roles.

[0416] The "skills database" is a database that quantifies and centrally manages various employee skills.

[0417] A "generative AI model" is an artificial intelligence model that analyzes natural language and patterns based on input data and generates and provides appropriate information.

[0418] "Job Requirements" refers to the skills, experience, and other conditions required for a particular job or project.

[0419] The "ranking format" is a format in which multiple items are ranked based on an overall score or specific criteria and listed in order from top to bottom.

[0420] "Fitness" is the degree to which something matches or conforms to a particular condition or standard.

[0421] "API" stands for Application Programming Interface, an interface that allows different software systems to communicate with each other and exchange data.

[0422] A "terminal" is a computer or device through which a user accesses a system and inputs or outputs data.

[0423] A "server" is a computer system that stores and processes data and provides services to other computers.

[0424] The present invention relates to a talent management system that builds a database in which the skills of all employees are quantified, and uses a generative artificial intelligence model to extract and present employees suitable for specific tasks.

[0425] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. For example, the user might enter numerical information such as "Programming skills: 75," "Sales skills: 60," and "Project management skills: 80." This entered skill information is sent to the server and saved in a database. The database is organized by skill type and stores the numerical data.

[0426] Next, the user inputs the requirements for a specific task. For example, "Project name: New DX project" and "Requirements: DX use case, for large companies, online" are entered through the device's input interface. The device receives these inputs and transfers them to the server according to the format.

[0427] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements. For example, it analyzes requirements such as "DX use cases," "for large companies," and "online" and extracts related keywords. Based on this, it compares the results with a skills database and evaluates each employee's skill score. For example, if employee B is recorded as "DX skills: 80" and "project management: 85," this is taken into account when assigning a score.

[0428] For the extracted employees, the server sends an API request to the external HR system to obtain their affiliation information. For example, the user obtains information such as "XX department, senior manager" and adds it to the scoring results.

[0429] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees. For example, employees with the highest overall score are listed in descending order. This ranking is adjusted so that employees who are best suited to the job requirements are placed at the top.

[0430] Finally, the terminal displays the ranking results to the user. The user then selects the most suitable employee from the displayed list and assigns the work. For example, the user can ask Employee B, who is ranked highly, to participate in a project. This process enables efficient and appropriate personnel allocation, improving the company's operational efficiency.

[0431] As a concrete example, if a user needs to find an employee to work on a new DX project, they enter the requirements of "DX use case," "for large companies," and "online" into an input form. The server analyzes this and determines that Employee B is the best fit. The server then obtains Employee B's affiliation information through the HR system API and displays it on the terminal in a ranking format. Based on the displayed results, the user can assign the work to Employee B.

[0432] The system uses generative AI models to quickly and accurately match employees with job requirements, significantly improving business efficiency.

[0433] Example prompt sentence:

[0434] "Project name: New DX Project"

[0435] "Requirements: DX use case, for large companies, online"

[0436] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0437] Step 1:

[0438] The user inputs the skill information of all employees, specifically numerical data such as "Programming Skills: 75," "Sales Skills: 60," and "Project Management Skills: 80," into the terminal.

[0439] Input: Employee skill data (e.g., "Programming Skills: 75")

[0440] Output: Skill data sent to the server

[0441] Specific operation: The user enters skill information into the input form on the terminal and clicks the send button. The terminal sends the entered skill information to the server. The server stores the received skill data in the database.

[0442] Step 2:

[0443] Users input the requirements for a specific business into the terminal, such as "DX use case," "for large companies," and "online."

[0444] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[0445] Output: Business requirement data sent to the server

[0446] Specific operation: The user enters business requirements into the requirements input form and clicks the send button. The terminal transfers the entered business requirements to the server according to the format. The server puts the received requirements data into a state where it is ready to be analyzed.

[0447] Step 3:

[0448] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements, thereby extracting relevant keywords.

[0449] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[0450] Output: Extracted keywords (e.g., "DX," "large company," "online," etc.)

[0451] Specific operation: The server feeds the requirements data to the generative AI model, and extracts keywords related to the requirements as an analysis result. These keywords are used in the skill database and matching process.

[0452] Step 4:

[0453] The server compares the extracted keywords with the employee skill database and evaluates and scores each employee's skill score.

[0454] Input: Extracted keywords and skill database

[0455] Output: A list of employees with relevance scores

[0456] Specific operation: The server uses the extracted keywords to match each employee's skills in the skills database and calculates a compatibility score, which indicates how well the employee's skills match the job requirements.

[0457] Step 5:

[0458] The server sends an API request to an external human resources system to obtain affiliation information for employees with high suitability scores.

[0459] Input: A list of employees with relevance scores

[0460] Output: Employee list with affiliation information added

[0461] Specific operation: The server sends a request to an external human resources system via API, obtains employee affiliation information (e.g., department name, job title, etc.), and adds it to the employee list.

[0462] Step 6:

[0463] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees.

[0464] Input: Employee list with added affiliation information

[0465] Output: A list of employees organized in rank order

[0466] Specific operation: The server sorts the employee list by overall score and generates a ranking list, which is adjusted to rank employees who are best suited to the job requirements.

[0467] Step 7:

[0468] The terminal displays the ranking results to the user, who can then select the most suitable employee based on the displayed list and assign the work to them.

[0469] Input: A list of employees organized in a ranked format

[0470] Output: Ranking results displayed to the user

[0471] Specific operation: The server sends the ranking results to the terminal, which then displays them to the user. The user selects the most suitable person from the displayed list and, if necessary, proceeds with the procedure to request the work.

[0472] (Application example 1)

[0473] 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."

[0474] Currently, many companies face the challenge of accurately understanding the skills of their employees and assigning them to appropriate tasks. Particularly on factory production lines, quickly identifying personnel with excellent specific skills and optimally assigning them directly leads to improved productivity and quality. Conventional systems cannot efficiently solve this issue, and there is a problem that appropriate personnel assignment takes time and costs.

[0475] 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.

[0476] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, and means for recommending the most suitable personnel for a specific task on a factory production line. This makes it possible to quickly select and assign the most suitable personnel for a specific job on a factory production line, etc.

[0477] "All employees" refers to all employees of a company or organization.

[0478] "Quantifying skills" means evaluating the various skills that employees possess and expressing their level numerically.

[0479] A "skills database" refers to a database that collects and stores employees' quantified skill information.

[0480] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes existing data and information and generates new information and suggestions.

[0481] "Job requirements" refer to the skills and conditions required to complete a specific job.

[0482] "Extraction" refers to retrieving relevant information or data based on specific conditions.

[0483] "Affiliation information" refers to information about the organization, such as the department and position to which an employee belongs.

[0484] "Ranking format" refers to a format in which evaluation results are ranked and displayed.

[0485] A "suitable employee" is an employee who is judged to have the most suitable skills for a particular job.

[0486] A "production line" refers to a series of equipment and systems used to manufacture products in a factory or other facility.

[0487] "Specific tasks" refer to specific tasks or roles on a production line or in business operations.

[0488] A "recommendation" is a suggestion of a particular option or course of action, particularly a superior option.

[0489] This invention is a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present the employees best suited to specific tasks. This system is particularly applicable to optimal personnel allocation on factory production lines.

[0490] First, the server registers the skill information of all employees in a skills database. This skill information is quantified based on various skills such as maintenance skills, programming skills, and quality control skills, and is stored in the database. Furthermore, a generative AI model is used to analyze the requirements for each job. Based on the results of this analysis, the server compares them with the information in the skills database to select the most suitable employees.

[0491] The specific program is processed as follows: First, the user inputs the requirements for a specific job. For example, the job requirements might be "product quality inspection," "online," and "quality control skill: 80." Next, the server analyzes these requirements and extracts employees who fit the job requirements from the skills database.

[0492] For the extracted employees, affiliation information is obtained from an external database (for example, the organization's human resources system) via API. This information is used to create a ranking of the most suitable employees, with the most suitable employees positioned at the top. The ranking results are finally displayed on the device, and the user can use this list to assign tasks to employees deemed suitable.

[0493] The following hardware and software are used to implement this system:

[0494] Hardware: Control PC, factory production line management terminal.

[0495] Software: Python, Gensim (Word2Vec), API (integration with HR system).

[0496] Specific examples

[0497] For example, suppose a factory needs to find the best staff member to perform product quality inspections. The user inputs the following job requirements into the system: "product quality inspection," "online," and "quality control skill: 80." The server then analyzes this and extracts employees with the corresponding skills from the skills database. For example, if employee B is set to have "quality control skill: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via API and displays it on the terminal as a ranking of the most suitable employees. After viewing this display, the user can request employee B to perform quality inspection work.

[0498] Prompt example

[0499] "What skills are needed to inspect product quality? Please list the skills that are required for the job."

[0500] This enables quick and accurate selection of employees best suited to specific tasks in the factory, enabling effective personnel deployment.

[0501] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0502] Step 1:

[0503] A user logs in to the system and inputs the requirements for a specific job. Through the input interface, the user enters requirements such as "product quality inspection," "online," and "quality control skill: 80" into a form. This input data is sent to the server.

[0504] Step 2:

[0505] The server receives the input business requirements and analyzes them using a generative artificial intelligence model (GPT). Specifically, the text data of the business requirements is input into GPT as a prompt, and relevant keywords based on the requirements are extracted. The input here is the text data of the business requirements, and the output is a list of keywords based on the requirements.

[0506] Step 3:

[0507] Based on the keyword list obtained from the generative AI model, the server compares it with a skills database, which stores quantified skill information for all employees. As a result of the comparison, a list of employees who best meet the business requirements is generated. The input data is the keyword list and the skills database, and the output data is a tentative list of optimal employees.

[0508] Step 4:

[0509] For each employee in the provisional list, the server accesses an external database (the organization's human resources system) via API to obtain the employee's affiliation information. The obtained affiliation information includes the employee's job title and department name. The input data is the employee ID, and the output data is an employee list with the affiliation information added.

[0510] Step 5:

[0511] The server creates a ranking of the most suitable employees based on the acquired affiliation information and skill scores. The ranking is based on the suitability of skills for the job requirements and job title information. The input data is an employee list with affiliation information added, and the output data is a ranked list of suitable employees.

[0512] Step 6:

[0513] The server sends the generated ranked list of suitable employees to the terminal. The terminal displays the ranking results to the user. The user can refer to the displayed results and assign the work to the employee deemed most suitable. The input data is the ranked list of suitable employees, and the output data is the ranking results displayed on the terminal.

[0514] 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.

[0515] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model and an emotion engine to extract and present employees who are suitable for specific tasks.

[0516] Initializing the Skills Database

[0517] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[0518] Enter business requirements

[0519] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[0520] Identifying the best employees

[0521] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[0522] Recognizing user emotions using an emotion engine

[0523] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0524] Acquisition of affiliation information

[0525] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources information system) via API. This information is used to create a ranking of suitable employees.

[0526] Emotion-based ranking presentation

[0527] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees.

[0528] Displaying and Using the Results

[0529] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then uses the list to request work from the selected employee. Requests are made via email or internal company tools.

[0530] Specific examples

[0531] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then uses an emotion engine to recognize the user's emotions and adjusts how the best employees are displayed based on the user's state. Finally, the server obtains employee B's affiliation information through an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[0532] The system quickly and accurately matches employee skills with job requirements, and also takes user emotions into account to achieve more optimal personnel allocation.

[0533] The processing flow will be explained below.

[0534] Step 1:

[0535] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[0536] Step 2:

[0537] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[0538] Step 3:

[0539] The user inputs the requirements for a specific task, such as "seminar," "digital transformation use case," "for large companies," and "online" into the input interface.

[0540] Step 4:

[0541] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[0542] Step 5:

[0543] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[0544] Step 6:

[0545] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[0546] Step 7:

[0547] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0548] Step 8:

[0549] For employees who are deemed the most suitable server, the server obtains affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[0550] Step 9:

[0551] Based on the acquired affiliation information, the server calculates an overall score and ranks the employees by combining it with the skill scores of the suitable employees. Furthermore, the acquired emotional data is reflected and the ranking format is adjusted according to the user's emotions.

[0552] Step 10:

[0553] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[0554] Step 11:

[0555] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[0556] As a concrete example, consider the case of finding the right person to launch a new DX project at a company. The user inputs requirements, such as "DX use case," "for large companies," and "online," into the system. The server analyzes this and extracts employees with the appropriate skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. Next, the server uses an emotion engine to recognize the user's emotions. If the user is feeling stressed, it adjusts the display method to prioritize experienced employees and optimize the display of the most suitable employees. Finally, the server obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After viewing this display, the user can request employee B to participate in the project. This system quickly and accurately matches employee skills with business requirements and also takes user emotions into account, achieving more optimal personnel allocation.

[0557] Example 2

[0558] 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."

[0559] Traditional talent management systems lacked efficiency and accuracy in selecting personnel, requiring significant time and resources for manual processes, especially when managing large amounts of employee data. Furthermore, they selected the most suitable employees without taking into account the user's emotional state, which could result in increased user stress. Furthermore, they lacked sufficient integration with external data, making it difficult to obtain the latest employee affiliation information. A system that can solve these issues is needed.

[0560] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0561] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, emotion recognition means for recognizing the emotional state of the user and adjusting the presented ranking based on that, and means for providing a user interface and supporting the input of job requirements. This enables more optimal personnel allocation by quickly and accurately matching employee skills with job requirements and further taking the user's emotions into consideration.

[0562] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[0563] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes given data and extracts the requirements necessary for a specific task.

[0564] The "ranking format" is a format for presenting results in an order based on specific conditions.

[0565] "Emotion recognition means" is a technology for grasping the user's emotional state and adjusting the content presented based on that.

[0566] A "user interface" is the means by which a user interacts with a system and inputs required information.

[0567] An "API" is an interface for data exchange with external databases and other systems.

[0568] "Scoring" is the process of quantifying an object's evaluation based on specific criteria.

[0569] This invention relates to a talent management system that builds a database that quantifies the skills of all employees, extracts employees suitable for specific tasks using a generative artificial intelligence model and an emotion engine, and presents the optimal employees to the user in a ranking format. The system quickly and accurately identifies employees with the most suitable skills and supports the user in selecting the optimal employee based on the task requirements.

[0570] This system consists of hardware such as a server, a terminal, and an input interface operated by the user. The software uses a database system (e.g., MySQL, PostgreSQL), a generative artificial intelligence model (e.g., natural language processing technology such as GPT-4), and an emotion recognition engine (e.g., Microsoft Azure Cognitive Services, Google Cloud AI).

[0571] Initializing the Skills Database

[0572] 1. The user enters the skill information of all employees. For example, the user can enter each employee's skill type (e.g., programming, project management, sales) and the corresponding skill level as a numerical value. This allows employee A to have specific skill data such as "Programming: 90, Project Management: 80."

[0573] 2. The device receives the entered skill information and sends it to the server.

[0574] 3. The server stores the received information in a database (e.g., MySQL, PostgreSQL) to create a skills database.

[0575] Enter business requirements

[0576] 1. The user enters the requirements necessary for the business. For example, they select requirements such as "Seminar," "DX Use Case," "For Large Companies," and "Online."

[0577] 2. The terminal receives the business requirements entered by the user and provides an input interface. An example of a prompt is "To find the best employee for your DX project, please enter the following requirements: seminar, DX use case, for large companies, online."

[0578] 3. The terminal sends the input requirements to the server.

[0579] Identifying the best employees

[0580] 1. The server analyzes the received business requirements using a generative artificial intelligence model (e.g., GPT-4).

[0581] 2. Matching with the skills database is performed based on the keywords extracted through analysis. For example, employees who match the requirements of "DX use cases" and "online" are extracted from the skills database.

[0582] 3. The server will score the most suitable employee based on the matching results. For example, if employee B has "DX Skill: 80" and "Online Experience: 90", he will receive a high score.

[0583] Recognizing user emotions using an emotion engine

[0584] 1. The server launches an emotion recognition engine, which uses speech recognition and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services).

[0585] 2. Using the device's camera and microphone, the voice and facial expressions of the user are captured in real time when they enter business requirements or view ranking results.

[0586] 3. The server analyzes this data and determines the user's emotional state. For example, it determines whether the user is feeling stressed.

[0587] Acquisition of affiliation information

[0588] 1. The server requests employee affiliation information from an external human resources information system via an API, which is designed as a RESTful API.

[0589] 2. Obtain the affiliation information (e.g., department name, position, etc.) returned from the external system.

[0590] 3. The server uses the information obtained to create a ranking.

[0591] Emotion-based ranking presentation

[0592] 1. The server evaluates the user's emotional state and adjusts the ranking results accordingly.

[0593] 2. For example, if a user is feeling stressed, more experienced employees will be displayed first.

[0594] Displaying and Using the Results

[0595] 1. The terminal displays the final ranking results to the user in a visually easy-to-understand format (e.g., using HTML and CSS).

[0596] 2. The user selects the most suitable employee from the presented ranking results and makes a work request. The request is made via internal tools or email.

[0597] In this way, the system of the present invention quickly and accurately matches employee skills with job requirements, and by taking user sentiment into consideration, achieves more effective personnel allocation.

[0598] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0599] Step 1: User enters skill information

[0600] The user inputs the skill information of each employee (e.g., skill type such as programming, project management, sales, etc., and each skill level) in numerical form. The terminal receives this information through an input interface (e.g., HTML form) and formats it as input data.

[0601] Input: Skill type and skill level for each employee

[0602] Output: Formatted skill data

[0603] How it works: When the device receives the input skill information, it formats it in the appropriate format (e.g., JSON, XML) and sends it to the server.

[0604] Step 2: Creating a skills database

[0605] The server receives the skill information sent from the device and stores it in a database (e.g., MySQL, PostgreSQL).

[0606] Input: Formatted skill data

[0607] Output: Skill information stored in the database

[0608] How it works: The server validates the received skill information and, if there are no errors, executes a SQL query to insert the information into the database. For example, it executes a query like "INSERT INTO skill_table (employee_id, skill_type, skill_level) VALUES (...)".

[0609] Step 3: Enter business requirements

[0610] The user enters the requirements for a specific task (e.g., "seminar," "DX use case," "for large companies," "online") using an input interface. The device receives this information and converts it into the appropriate data format.

[0611] Input: Business requirements

[0612] Output: Formatted business requirements data

[0613] Operation: The terminal validates the requirements entered by the user, converts them into the appropriate format, and sends them to the server.

[0614] Step 4: Requirements analysis and matching

[0615] The server analyzes the business requirements sent from the device using a generative artificial intelligence model (e.g., GPT-4). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database.

[0616] Input: Business requirements data

[0617] Output: Requirement keywords and matching results

[0618] Operation: The server inputs job requirements data into a generative AI model and searches the skills database using the resulting keyword list. For example, it retrieves employees with scores such as "Programming 90" and "Online Support 85."

[0619] Step 5: Scoring and ranking

[0620] The server scores the most suitable employees based on the matching, taking into account skill attributes and work experience, and assigns a score to each employee.

[0621] Input: Matching results

[0622] Output: Employee score list

[0623] How it works: The server runs a scoring algorithm on the list of employees that match the criteria, assigning each employee a score and ranking them.

[0624] Step 6: Emotion Recognition

[0625] The server activates an emotion engine to recognize the user's emotional state, and uses the device's camera and microphone to capture voice, facial expressions, and text input.

[0626] Input: User's voice, facial expressions, and text data

[0627] Output: User's emotional state data

[0628] Operation: The device records the user's facial expressions and voice using a camera and microphone while the user is entering business requirements and displaying ranking results. This data is then sent to the server in real time.

[0629] Step 7: Sentiment-aware ranking adjustment

[0630] The server analyzes the acquired emotional state data and adjusts the ranking order according to the user's emotions.

[0631] Input: User's emotional state data

[0632] Output: Adjusted ranking results

[0633] How it works: The server analyzes the user's emotional data and optimizes the ranking, for example, by placing more experienced employees at the top if the user is under high stress.

[0634] Step 8: View results and submit work

[0635] The terminal displays the adjusted ranking results to the user, allowing the user to select the most suitable employee and request the work.

[0636] Input: Adjusted ranking results

[0637] Output: Ranking results displayed to the user

[0638] Operation: The terminal displays the ranking results to the user in a visually easy-to-understand format (e.g., HTML, CSS). The user can select the target employee from the screen and request work via email or internal tools.

[0639] The above is the specific processing flow in this system.

[0640] (Application example 2)

[0641] 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."

[0642] Conventional talent management systems require time and effort to match employee skills with job requirements, making optimal personnel placement difficult. Furthermore, because they select personnel suited to job requirements without considering the user's feelings, users may be dissatisfied with the selection results. There is a need to solve these issues and apply them to task management using factory robots.

[0643] The identification process 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 quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees or workers from the skills database, means for acquiring the affiliation information of the extracted employees or workers and presenting the most suitable employees or workers in a ranking format, means for applying the extracted most suitable employees or workers to task management by factory robots, and means for analyzing the emotional state of a user using an emotion recognition engine and reflecting the analysis results in scoring. This enables fast and accurate matching of personnel and jobs, improving user satisfaction and enabling efficient task management by factory robots.

[0644] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[0645] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes business requirements and extracts the most suitable employees or workers from a skills database.

[0646] "Job requirements" refers to information that indicates the skills and conditions required for a specific job.

[0647] "Best fit employee or worker" refers to the employee or worker who best fits the job requirements based on the skills database.

[0648] The "ranking format" is a format in which the extracted employees or workers are ranked and presented based on their suitability.

[0649] A "factory robot" is a robot used to automate work within a factory.

[0650] "Task management" is the process of managing the progress of work and assigning it to the appropriate people or machines.

[0651] An "emotion recognition engine" is an engine for analyzing the user's emotional state.

[0652] "Emotional state" is information that indicates the user's current emotional and psychological state.

[0653] "Scoring" is the process of evaluating or ranking based on specific criteria.

[0654] This invention relates to a talent management system that quantifies the skills of all employees, builds a skills database, and uses a generative artificial intelligence model and an emotion recognition engine to extract and present employees or workers suitable for specific tasks.Furthermore, it realizes efficient task management using factory robots.

[0655] Initializing the Skills Database

[0656] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[0657] Enter business requirements

[0658] Next, the user inputs the requirements for a specific task, such as "packaging," "complexity level: 3," and "deadline: 2023-12-01," into the form. At this stage, the terminal provides an input interface to help the user easily input the task requirements.

[0659] Identifying the best employees or workers

[0660] The server analyzes the input business requirements using a generative AI model. As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. Based on information such as skill attributes and work experience, the server scores the most suitable employee or worker.

[0661] Recognizing user emotions using an emotion recognition engine

[0662] The server activates an emotion recognition engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0663] Acquisition of affiliation information

[0664] For employees or workers who are deemed the most suitable, the server obtains their affiliation information (department name, job title, etc.) from an external database via API. This information is used to create a ranking of suitable employees or workers.

[0665] Emotion-based ranking presentation

[0666] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees or workers.

[0667] Displaying and Using the Results

[0668] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then selects the employee or worker from the list and assigns the task. The request is made via email or internal company tools.

[0669] Specific examples

[0670] For example, suppose a "packaging task" arises at a factory, and the factory manager inputs this requirement into the system. The task requirements, "packaging," "complexity level: 3," and "deadline: 2023-12-01," are analyzed using a generative AI model. Based on the analysis results, employees or workers with the most appropriate skills are extracted from a skills database, and the user's emotions are analyzed using an emotion recognition engine. For example, a prompt such as "Find the most appropriate worker based on the following criteria: Task type: packaging, complexity level: 3, deadline: 2023-12-01" is input into the generative AI model. Based on this information, the server presents the appropriate employees or workers to the user in a ranked format, and ultimately the task is requested.

[0671] This system quickly and accurately matches employee skills with work requirements, and also takes user emotions into account to achieve more optimal personnel allocation. It also enables efficient task management by factory robots.

[0672] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0673] Step 1:

[0674] The user inputs the skill information of all employees. The skill type and skill level of each employee are converted into numerical values ​​and registered in the system through an input interface. Specifically, data such as "Skill type: Programming" and "Skill level: 80" is entered for each employee. The input data is sent to the server and saved in the skill database. Input: Employee skill information, Output: Registration in the skill database.

[0675] Step 2:

[0676] The user inputs the requirements for a specific task. For example, requirements such as "packaging," "complexity level: 3," and "deadline: 2023-12-01" are entered into a form. The terminal provides this input interface, and the input requirements are sent to the server. Input: Task requirements, Output: Send to server.

[0677] Step 3:

[0678] The server uses a generative artificial intelligence model to analyze the input business requirements. As a result of the analysis, keywords that match the requirements are extracted. For example, based on the requirements "packaging" and "complexity level: 3," keywords for matching skills are generated. Input: Business requirements, Output: Keywords that match the requirements.

[0679] Step 4:

[0680] The server matches the generated keywords with a skills database to extract the most suitable employees or workers. For example, it extracts employees with "packaging" and "high skill level." Skill attributes and work experience are also taken into consideration. Input: Keywords that match the requirements, Output: A list of the most suitable employees or workers.

[0681] Step 5:

[0682] The server starts an emotion recognition engine and analyzes the user's emotional state. It analyzes the user's voice, facial expression, text input, etc. to obtain the user's emotional data. Input: User's voice, facial expression, text, Output: Emotional data.

[0683] Step 6:

[0684] The server obtains the affiliation information of the extracted employees or workers. It obtains the affiliation information (department name and position) from the external database via API and creates a ranking of the most suitable employees or workers. Input: Employee ID, Output: Affiliation information

[0685] Step 7:

[0686] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking order. For example, if the user is feeling stressed, the server adjusts the ranking order to give priority to more experienced employees. Input: Emotion data, Output: Adjusted ranking order.

[0687] Step 8:

[0688] The terminal displays the ranking results to the user in a format that corresponds to the emotion. For example, it may display the results in the format "Ranking 1: Employee B (Skill: 80, Project Management: 85, Position: IT Department Manager)." The user can assign tasks to the selected employee or worker based on the presented list. Input: Adjusted ranking, Output: Display of ranking results.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Third embodiment]

[0693] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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. 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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."

[0705] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present employees who are suitable for specific tasks.

[0706] Initializing the Skills Database

[0707] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. The entered skill information is registered on the server and saved in a database. Here, numerical data is registered for each type of skill.

[0708] Enter business requirements

[0709] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[0710] Identifying the best employees

[0711] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[0712] Acquisition of affiliation information

[0713] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources system) via API. This information is used to create a ranking of suitable employees.

[0714] Presented in ranking format

[0715] Based on the acquired skill scores and affiliation information, the server creates a ranking list of suitable employees. This ranking is based on the overall score, with employees who are most suited to the job requirements ranked at the top.

[0716] Displaying and Using the Results

[0717] Finally, the terminal displays the ranking results to the user, who then assigns the work to the selected employee based on the presented list. This process enables efficient and appropriate personnel allocation, improving the success rate of the work.

[0718] Specific examples

[0719] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is set to have "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[0720] This system can significantly improve a company's operational efficiency by quickly and accurately matching employee skills with job requirements.

[0721] The processing flow will be explained below.

[0722] Step 1:

[0723] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[0724] Step 2:

[0725] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[0726] Step 3:

[0727] The user inputs the requirements for a specific task. For example, they enter keywords such as "seminar," "digital transformation use cases," "for large companies," and "online" into the input interface.

[0728] Step 4:

[0729] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[0730] Step 5:

[0731] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[0732] Step 6:

[0733] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[0734] Step 7:

[0735] After the employee who best meets the business requirements is extracted, the server retrieves affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[0736] Step 8:

[0737] Based on the affiliation information acquired by the server, a total score is calculated in combination with the skill scores of suitable employees, and a ranking is created.

[0738] Step 9:

[0739] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[0740] Step 10:

[0741] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[0742] In this way, the system of the present invention automates a series of processes from managing the skill information of all employees to matching with business requirements, and supports efficient and appropriate personnel allocation.

[0743] Example 1

[0744] 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."

[0745] Companies face challenges in efficiently identifying the skills of each employee and quickly assigning the best personnel for specific tasks. Traditional manual skill matching takes time and effort, making it difficult to select the right personnel. In addition, obtaining employee affiliation information and presenting it in a ranking format is complex and cumbersome, so an efficient system to solve these issues was needed.

[0746] 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.

[0747] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative AI model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, means for analyzing keywords in job requirements and evaluating the suitability of the skills by comparing them with information in the skills database, and means for transferring job requirements entered using a terminal to the server. This makes it possible to quickly grasp the skills of each employee and efficiently select and assign the most suitable personnel for a specific job.

[0748] An "employee" is an individual who belongs to a company or organization and performs specific tasks or roles.

[0749] The "skills database" is a database that quantifies and centrally manages various employee skills.

[0750] A "generative AI model" is an artificial intelligence model that analyzes natural language and patterns based on input data and generates and provides appropriate information.

[0751] "Job Requirements" refers to the skills, experience, and other conditions required for a particular job or project.

[0752] The "ranking format" is a format in which multiple items are ranked based on an overall score or specific criteria and listed in order from top to bottom.

[0753] "Fitness" is the degree to which something matches or conforms to a particular condition or standard.

[0754] "API" stands for Application Programming Interface, an interface that allows different software systems to communicate with each other and exchange data.

[0755] A "terminal" is a computer or device through which a user accesses a system and inputs or outputs data.

[0756] A "server" is a computer system that stores and processes data and provides services to other computers.

[0757] The present invention relates to a talent management system that builds a database in which the skills of all employees are quantified, and uses a generative artificial intelligence model to extract and present employees suitable for specific tasks.

[0758] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. For example, the user might enter numerical information such as "Programming skills: 75," "Sales skills: 60," and "Project management skills: 80." This entered skill information is sent to the server and saved in a database. The database is organized by skill type and stores the numerical data.

[0759] Next, the user inputs the requirements for a specific task. For example, "Project name: New DX project" and "Requirements: DX use case, for large companies, online" are entered through the device's input interface. The device receives these inputs and transfers them to the server according to the format.

[0760] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements. For example, it analyzes requirements such as "DX use cases," "for large companies," and "online" and extracts related keywords. Based on this, it compares the results with a skills database and evaluates each employee's skill score. For example, if employee B is recorded as "DX skills: 80" and "project management: 85," this is taken into account when assigning a score.

[0761] For the extracted employees, the server sends an API request to the external HR system to obtain their affiliation information. For example, the user obtains information such as "XX department, senior manager" and adds it to the scoring results.

[0762] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees. For example, employees with the highest overall score are listed in descending order. This ranking is adjusted so that employees who are best suited to the job requirements are placed at the top.

[0763] Finally, the terminal displays the ranking results to the user. The user then selects the most suitable employee from the displayed list and assigns the work. For example, the user can ask Employee B, who is ranked highly, to participate in a project. This process enables efficient and appropriate personnel allocation, improving the company's operational efficiency.

[0764] As a concrete example, if a user needs to find an employee to work on a new DX project, they enter the requirements of "DX use case," "for large companies," and "online" into an input form. The server analyzes this and determines that Employee B is the best fit. The server then obtains Employee B's affiliation information through the HR system API and displays it on the terminal in a ranking format. Based on the displayed results, the user can assign the work to Employee B.

[0765] The system uses generative AI models to quickly and accurately match employees with job requirements, significantly improving business efficiency.

[0766] Example prompt sentence:

[0767] "Project name: New DX Project"

[0768] "Requirements: DX use case, for large companies, online"

[0769] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0770] Step 1:

[0771] The user inputs the skill information of all employees, specifically numerical data such as "Programming Skills: 75," "Sales Skills: 60," and "Project Management Skills: 80," into the terminal.

[0772] Input: Employee skill data (e.g., "Programming Skills: 75")

[0773] Output: Skill data sent to the server

[0774] Specific operation: The user enters skill information into the input form on the terminal and clicks the send button. The terminal sends the entered skill information to the server. The server stores the received skill data in the database.

[0775] Step 2:

[0776] Users input the requirements for a specific business into the terminal, such as "DX use case," "for large companies," and "online."

[0777] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[0778] Output: Business requirement data sent to the server

[0779] Specific operation: The user enters business requirements into the requirements input form and clicks the send button. The terminal transfers the entered business requirements to the server according to the format. The server puts the received requirements data into a state where it is ready to be analyzed.

[0780] Step 3:

[0781] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements, thereby extracting relevant keywords.

[0782] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[0783] Output: Extracted keywords (e.g., "DX," "large company," "online," etc.)

[0784] Specific operation: The server feeds the requirements data to the generative AI model, and extracts keywords related to the requirements as an analysis result. These keywords are used in the skill database and matching process.

[0785] Step 4:

[0786] The server compares the extracted keywords with the employee skill database and evaluates and scores each employee's skill score.

[0787] Input: Extracted keywords and skill database

[0788] Output: A list of employees with relevance scores

[0789] Specific operation: The server uses the extracted keywords to match each employee's skills in the skills database and calculates a compatibility score, which indicates how well the employee's skills match the job requirements.

[0790] Step 5:

[0791] The server sends an API request to an external human resources system to obtain affiliation information for employees with high suitability scores.

[0792] Input: A list of employees with relevance scores

[0793] Output: Employee list with affiliation information added

[0794] Specific operation: The server sends a request to an external human resources system via API, obtains employee affiliation information (e.g., department name, job title, etc.), and adds it to the employee list.

[0795] Step 6:

[0796] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees.

[0797] Input: Employee list with added affiliation information

[0798] Output: A list of employees organized in rank order

[0799] Specific operation: The server sorts the employee list by overall score and generates a ranking list, which is adjusted to rank employees who are best suited to the job requirements.

[0800] Step 7:

[0801] The terminal displays the ranking results to the user, who can then select the most suitable employee based on the displayed list and assign the work to them.

[0802] Input: A list of employees organized in a ranked format

[0803] Output: Ranking results displayed to the user

[0804] Specific operation: The server sends the ranking results to the terminal, which then displays them to the user. The user selects the most suitable person from the displayed list and, if necessary, proceeds with the procedure to request the work.

[0805] (Application example 1)

[0806] 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."

[0807] Currently, many companies face the challenge of accurately understanding the skills of their employees and assigning them to appropriate tasks. Particularly on factory production lines, quickly identifying personnel with excellent specific skills and optimally assigning them directly leads to improved productivity and quality. Conventional systems cannot efficiently solve this issue, and there is a problem that appropriate personnel assignment takes time and costs.

[0808] 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.

[0809] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, and means for recommending the most suitable personnel for a specific task on a factory production line. This makes it possible to quickly select and assign the most suitable personnel for a specific job on a factory production line, etc.

[0810] "All employees" refers to all employees of a company or organization.

[0811] "Quantifying skills" means evaluating the various skills that employees possess and expressing their level numerically.

[0812] A "skills database" refers to a database that collects and stores employees' quantified skill information.

[0813] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes existing data and information and generates new information and suggestions.

[0814] "Job requirements" refer to the skills and conditions required to complete a specific job.

[0815] "Extraction" refers to retrieving relevant information or data based on specific conditions.

[0816] "Affiliation information" refers to information about the organization, such as the department and position to which an employee belongs.

[0817] "Ranking format" refers to a format in which evaluation results are ranked and displayed.

[0818] A "suitable employee" is an employee who is judged to have the most suitable skills for a particular job.

[0819] A "production line" refers to a series of equipment and systems used to manufacture products in a factory or other facility.

[0820] "Specific tasks" refer to specific tasks or roles on a production line or in business operations.

[0821] A "recommendation" is a suggestion of a particular option or course of action, particularly a superior option.

[0822] This invention is a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present the employees best suited to specific tasks. This system is particularly applicable to optimal personnel allocation on factory production lines.

[0823] First, the server registers the skill information of all employees in a skills database. This skill information is quantified based on various skills such as maintenance skills, programming skills, and quality control skills, and is stored in the database. Furthermore, a generative AI model is used to analyze the requirements for each job. Based on the results of this analysis, the server compares them with the information in the skills database to select the most suitable employees.

[0824] The specific program is processed as follows: First, the user inputs the requirements for a specific job. For example, the job requirements might be "product quality inspection," "online," and "quality control skill: 80." Next, the server analyzes these requirements and extracts employees who fit the job requirements from the skills database.

[0825] For the extracted employees, affiliation information is obtained from an external database (for example, the organization's human resources system) via API. This information is used to create a ranking of the most suitable employees, with the most suitable employees positioned at the top. The ranking results are finally displayed on the device, and the user can use this list to assign tasks to employees deemed suitable.

[0826] The following hardware and software are used to implement this system:

[0827] Hardware: Control PC, factory production line management terminal.

[0828] Software: Python, Gensim (Word2Vec), API (integration with HR system).

[0829] Specific examples

[0830] For example, suppose a factory needs to find the best staff member to perform product quality inspections. The user inputs the following job requirements into the system: "product quality inspection," "online," and "quality control skill: 80." The server then analyzes this and extracts employees with the corresponding skills from the skills database. For example, if employee B is set to have "quality control skill: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via API and displays it on the terminal as a ranking of the most suitable employees. After viewing this display, the user can request employee B to perform quality inspection work.

[0831] Prompt example

[0832] "What skills are needed to inspect product quality? Please list the skills that are required for the job."

[0833] This enables quick and accurate selection of employees best suited to specific tasks in the factory, enabling effective personnel deployment.

[0834] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0835] Step 1:

[0836] A user logs in to the system and inputs the requirements for a specific job. Through the input interface, the user enters requirements such as "product quality inspection," "online," and "quality control skill: 80" into a form. This input data is sent to the server.

[0837] Step 2:

[0838] The server receives the input business requirements and analyzes them using a generative artificial intelligence model (GPT). Specifically, the text data of the business requirements is input into GPT as a prompt, and relevant keywords based on the requirements are extracted. The input here is the text data of the business requirements, and the output is a list of keywords based on the requirements.

[0839] Step 3:

[0840] Based on the keyword list obtained from the generative AI model, the server compares it with a skills database, which stores quantified skill information for all employees. As a result of the comparison, a list of employees who best meet the business requirements is generated. The input data is the keyword list and the skills database, and the output data is a tentative list of optimal employees.

[0841] Step 4:

[0842] For each employee in the provisional list, the server accesses an external database (the organization's human resources system) via API to obtain the employee's affiliation information. The obtained affiliation information includes the employee's job title and department name. The input data is the employee ID, and the output data is an employee list with the affiliation information added.

[0843] Step 5:

[0844] The server creates a ranking of the most suitable employees based on the acquired affiliation information and skill scores. The ranking is based on the suitability of skills for the job requirements and job title information. The input data is an employee list with affiliation information added, and the output data is a ranked list of suitable employees.

[0845] Step 6:

[0846] The server sends the generated ranked list of suitable employees to the terminal. The terminal displays the ranking results to the user. The user can refer to the displayed results and assign the work to the employee deemed most suitable. The input data is the ranked list of suitable employees, and the output data is the ranking results displayed on the terminal.

[0847] 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.

[0848] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model and an emotion engine to extract and present employees who are suitable for specific tasks.

[0849] Initializing the Skills Database

[0850] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[0851] Enter business requirements

[0852] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[0853] Identifying the best employees

[0854] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[0855] Recognizing user emotions using an emotion engine

[0856] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0857] Acquisition of affiliation information

[0858] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources information system) via API. This information is used to create a ranking of suitable employees.

[0859] Emotion-based ranking presentation

[0860] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees.

[0861] Displaying and Using the Results

[0862] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then uses the list to request work from the selected employee. Requests are made via email or internal company tools.

[0863] Specific examples

[0864] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then uses an emotion engine to recognize the user's emotions and adjusts how the best employees are displayed based on the user's state. Finally, the server obtains employee B's affiliation information through an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[0865] The system quickly and accurately matches employee skills with job requirements, and also takes user emotions into account to achieve more optimal personnel allocation.

[0866] The processing flow will be explained below.

[0867] Step 1:

[0868] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[0869] Step 2:

[0870] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[0871] Step 3:

[0872] The user inputs the requirements for a specific task, such as "seminar," "digital transformation use case," "for large companies," and "online" into the input interface.

[0873] Step 4:

[0874] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[0875] Step 5:

[0876] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[0877] Step 6:

[0878] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[0879] Step 7:

[0880] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0881] Step 8:

[0882] For employees who are deemed the most suitable server, the server obtains affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[0883] Step 9:

[0884] Based on the acquired affiliation information, the server calculates an overall score and ranks the employees by combining it with the skill scores of the suitable employees. Furthermore, the acquired emotional data is reflected and the ranking format is adjusted according to the user's emotions.

[0885] Step 10:

[0886] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[0887] Step 11:

[0888] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[0889] As a concrete example, consider the case of finding the right person to launch a new DX project at a company. The user inputs requirements, such as "DX use case," "for large companies," and "online," into the system. The server analyzes this and extracts employees with the appropriate skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. Next, the server uses an emotion engine to recognize the user's emotions. If the user is feeling stressed, it adjusts the display method to prioritize experienced employees and optimize the display of the most suitable employees. Finally, the server obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After viewing this display, the user can request employee B to participate in the project. This system quickly and accurately matches employee skills with business requirements and also takes user emotions into account, achieving more optimal personnel allocation.

[0890] Example 2

[0891] 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."

[0892] Traditional talent management systems lacked efficiency and accuracy in selecting personnel, requiring significant time and resources for manual processes, especially when managing large amounts of employee data. Furthermore, they selected the most suitable employees without taking into account the user's emotional state, which could result in increased user stress. Furthermore, they lacked sufficient integration with external data, making it difficult to obtain the latest employee affiliation information. A system that can solve these issues is needed.

[0893] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0894] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, emotion recognition means for recognizing the emotional state of the user and adjusting the presented ranking based on that, and means for providing a user interface and supporting the input of job requirements. This enables more optimal personnel allocation by quickly and accurately matching employee skills with job requirements and further taking the user's emotions into consideration.

[0895] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[0896] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes given data and extracts the requirements necessary for a specific task.

[0897] The "ranking format" is a format for presenting results in an order based on specific conditions.

[0898] "Emotion recognition means" is a technology for grasping the user's emotional state and adjusting the content presented based on that.

[0899] A "user interface" is the means by which a user interacts with a system and inputs required information.

[0900] An "API" is an interface for data exchange with external databases and other systems.

[0901] "Scoring" is the process of quantifying an object's evaluation based on specific criteria.

[0902] This invention relates to a talent management system that builds a database that quantifies the skills of all employees, extracts employees suitable for specific tasks using a generative artificial intelligence model and an emotion engine, and presents the optimal employees to the user in a ranking format. The system quickly and accurately identifies employees with the most suitable skills and supports the user in selecting the optimal employee based on the task requirements.

[0903] This system consists of hardware such as a server, a terminal, and an input interface operated by the user. The software uses a database system (e.g., MySQL, PostgreSQL), a generative artificial intelligence model (e.g., natural language processing technology such as GPT-4), and an emotion recognition engine (e.g., Microsoft Azure Cognitive Services, Google Cloud AI).

[0904] Initializing the Skills Database

[0905] 1. The user enters the skill information of all employees. For example, the user can enter each employee's skill type (e.g., programming, project management, sales) and the corresponding skill level as a numerical value. This allows employee A to have specific skill data such as "Programming: 90, Project Management: 80."

[0906] 2. The device receives the entered skill information and sends it to the server.

[0907] 3. The server stores the received information in a database (e.g., MySQL, PostgreSQL) to create a skills database.

[0908] Enter business requirements

[0909] 1. The user enters the requirements necessary for the business. For example, they select requirements such as "Seminar," "DX Use Case," "For Large Companies," and "Online."

[0910] 2. The terminal receives the business requirements entered by the user and provides an input interface. An example of a prompt is "To find the best employee for your DX project, please enter the following requirements: seminar, DX use case, for large companies, online."

[0911] 3. The terminal sends the input requirements to the server.

[0912] Identifying the best employees

[0913] 1. The server analyzes the received business requirements using a generative artificial intelligence model (e.g., GPT-4).

[0914] 2. Matching with the skills database is performed based on the keywords extracted through analysis. For example, employees who match the requirements of "DX use cases" and "online" are extracted from the skills database.

[0915] 3. The server will score the most suitable employee based on the matching results. For example, if employee B has "DX Skill: 80" and "Online Experience: 90", he will receive a high score.

[0916] Recognizing user emotions using an emotion engine

[0917] 1. The server launches an emotion recognition engine, which uses speech recognition and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services).

[0918] 2. Using the device's camera and microphone, the voice and facial expressions of the user are captured in real time when they enter business requirements or view ranking results.

[0919] 3. The server analyzes this data and determines the user's emotional state. For example, it determines whether the user is feeling stressed.

[0920] Acquisition of affiliation information

[0921] 1. The server requests employee affiliation information from an external human resources information system via an API, which is designed as a RESTful API.

[0922] 2. Obtain the affiliation information (e.g., department name, position, etc.) returned from the external system.

[0923] 3. The server uses the information obtained to create a ranking.

[0924] Emotion-based ranking presentation

[0925] 1. The server evaluates the user's emotional state and adjusts the ranking results accordingly.

[0926] 2. For example, if a user is feeling stressed, more experienced employees will be displayed first.

[0927] Displaying and Using the Results

[0928] 1. The terminal displays the final ranking results to the user in a visually easy-to-understand format (e.g., using HTML and CSS).

[0929] 2. The user selects the most suitable employee from the presented ranking results and makes a work request. The request is made via internal tools or email.

[0930] In this way, the system of the present invention quickly and accurately matches employee skills with job requirements, and by taking user sentiment into consideration, achieves more effective personnel allocation.

[0931] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0932] Step 1: User enters skill information

[0933] The user inputs the skill information of each employee (e.g., skill type such as programming, project management, sales, etc., and each skill level) in numerical form. The terminal receives this information through an input interface (e.g., HTML form) and formats it as input data.

[0934] Input: Skill type and skill level for each employee

[0935] Output: Formatted skill data

[0936] How it works: When the device receives the input skill information, it formats it in the appropriate format (e.g., JSON, XML) and sends it to the server.

[0937] Step 2: Creating a skills database

[0938] The server receives the skill information sent from the device and stores it in a database (e.g., MySQL, PostgreSQL).

[0939] Input: Formatted skill data

[0940] Output: Skill information stored in the database

[0941] How it works: The server validates the received skill information and, if there are no errors, executes a SQL query to insert the information into the database. For example, it executes a query like "INSERT INTO skill_table (employee_id, skill_type, skill_level) VALUES (...)".

[0942] Step 3: Enter business requirements

[0943] The user enters the requirements for a specific task (e.g., "seminar," "DX use case," "for large companies," "online") using an input interface. The device receives this information and converts it into the appropriate data format.

[0944] Input: Business requirements

[0945] Output: Formatted business requirements data

[0946] Operation: The terminal validates the requirements entered by the user, converts them into the appropriate format, and sends them to the server.

[0947] Step 4: Requirements analysis and matching

[0948] The server analyzes the business requirements sent from the device using a generative artificial intelligence model (e.g., GPT-4). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database.

[0949] Input: Business requirements data

[0950] Output: Requirement keywords and matching results

[0951] Operation: The server inputs job requirements data into a generative AI model and searches the skills database using the resulting keyword list. For example, it retrieves employees with scores such as "Programming 90" and "Online Support 85."

[0952] Step 5: Scoring and ranking

[0953] The server scores the most suitable employees based on the matching, taking into account skill attributes and work experience, and assigns a score to each employee.

[0954] Input: Matching results

[0955] Output: Employee score list

[0956] How it works: The server runs a scoring algorithm on the list of employees that match the criteria, assigning each employee a score and ranking them.

[0957] Step 6: Emotion Recognition

[0958] The server activates an emotion engine to recognize the user's emotional state, and uses the device's camera and microphone to capture voice, facial expressions, and text input.

[0959] Input: User's voice, facial expressions, and text data

[0960] Output: User's emotional state data

[0961] Operation: The device records the user's facial expressions and voice using a camera and microphone while the user is entering business requirements and displaying ranking results. This data is then sent to the server in real time.

[0962] Step 7: Sentiment-aware ranking adjustment

[0963] The server analyzes the acquired emotional state data and adjusts the ranking order according to the user's emotions.

[0964] Input: User's emotional state data

[0965] Output: Adjusted ranking results

[0966] How it works: The server analyzes the user's emotional data and optimizes the ranking, for example, by placing more experienced employees at the top if the user is under high stress.

[0967] Step 8: View results and submit work

[0968] The terminal displays the adjusted ranking results to the user, allowing the user to select the most suitable employee and request the work.

[0969] Input: Adjusted ranking results

[0970] Output: Ranking results displayed to the user

[0971] Operation: The terminal displays the ranking results to the user in a visually easy-to-understand format (e.g., HTML, CSS). The user can select the target employee from the screen and request work via email or internal tools.

[0972] The above is the specific processing flow in this system.

[0973] (Application example 2)

[0974] 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."

[0975] Conventional talent management systems require time and effort to match employee skills with job requirements, making optimal personnel placement difficult. Furthermore, because they select personnel suited to job requirements without considering the user's feelings, users may be dissatisfied with the selection results. There is a need to solve these issues and apply them to task management using factory robots.

[0976] The identification process 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 quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees or workers from the skills database, means for acquiring the affiliation information of the extracted employees or workers and presenting the most suitable employees or workers in a ranking format, means for applying the extracted most suitable employees or workers to task management by factory robots, and means for analyzing the emotional state of a user using an emotion recognition engine and reflecting the analysis results in scoring. This enables fast and accurate matching of personnel and jobs, improving user satisfaction and enabling efficient task management by factory robots.

[0977] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[0978] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes business requirements and extracts the most suitable employees or workers from a skills database.

[0979] "Job requirements" refers to information that indicates the skills and conditions required for a specific job.

[0980] "Best fit employee or worker" refers to the employee or worker who best fits the job requirements based on the skills database.

[0981] The "ranking format" is a format in which the extracted employees or workers are ranked and presented based on their suitability.

[0982] A "factory robot" is a robot used to automate work within a factory.

[0983] "Task management" is the process of managing the progress of work and assigning it to the appropriate people or machines.

[0984] An "emotion recognition engine" is an engine for analyzing the user's emotional state.

[0985] "Emotional state" is information that indicates the user's current emotional and psychological state.

[0986] "Scoring" is the process of evaluating or ranking based on specific criteria.

[0987] This invention relates to a talent management system that quantifies the skills of all employees, builds a skills database, and uses a generative artificial intelligence model and an emotion recognition engine to extract and present employees or workers suitable for specific tasks.Furthermore, it realizes efficient task management using factory robots.

[0988] Initializing the Skills Database

[0989] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[0990] Enter business requirements

[0991] Next, the user inputs the requirements for a specific task, such as "packaging," "complexity level: 3," and "deadline: 2023-12-01," into the form. At this stage, the terminal provides an input interface to help the user easily input the task requirements.

[0992] Identifying the best employees or workers

[0993] The server analyzes the input business requirements using a generative AI model. As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. Based on information such as skill attributes and work experience, the server scores the most suitable employee or worker.

[0994] Recognizing user emotions using an emotion recognition engine

[0995] The server activates an emotion recognition engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[0996] Acquisition of affiliation information

[0997] For employees or workers who are deemed the most suitable, the server obtains their affiliation information (department name, job title, etc.) from an external database via API. This information is used to create a ranking of suitable employees or workers.

[0998] Emotion-based ranking presentation

[0999] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees or workers.

[1000] Displaying and Using the Results

[1001] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then selects the employee or worker from the list and assigns the task. The request is made via email or internal company tools.

[1002] Specific examples

[1003] For example, suppose a "packaging task" arises at a factory, and the factory manager inputs this requirement into the system. The task requirements, "packaging," "complexity level: 3," and "deadline: 2023-12-01," are analyzed using a generative AI model. Based on the analysis results, employees or workers with the most appropriate skills are extracted from a skills database, and the user's emotions are analyzed using an emotion recognition engine. For example, a prompt such as "Find the most appropriate worker based on the following criteria: Task type: packaging, complexity level: 3, deadline: 2023-12-01" is input into the generative AI model. Based on this information, the server presents the appropriate employees or workers to the user in a ranked format, and ultimately the task is requested.

[1004] This system quickly and accurately matches employee skills with work requirements, and also takes user emotions into account to achieve more optimal personnel allocation. It also enables efficient task management by factory robots.

[1005] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1006] Step 1:

[1007] The user inputs the skill information of all employees. The skill type and skill level of each employee are converted into numerical values ​​and registered in the system through an input interface. Specifically, data such as "Skill type: Programming" and "Skill level: 80" is entered for each employee. The input data is sent to the server and saved in the skill database. Input: Employee skill information, Output: Registration in the skill database.

[1008] Step 2:

[1009] The user inputs the requirements for a specific task. For example, requirements such as "packaging," "complexity level: 3," and "deadline: 2023-12-01" are entered into a form. The terminal provides this input interface, and the input requirements are sent to the server. Input: Task requirements, Output: Send to server.

[1010] Step 3:

[1011] The server uses a generative artificial intelligence model to analyze the input business requirements. As a result of the analysis, keywords that match the requirements are extracted. For example, based on the requirements "packaging" and "complexity level: 3," keywords for matching skills are generated. Input: Business requirements, Output: Keywords that match the requirements.

[1012] Step 4:

[1013] The server matches the generated keywords with a skills database to extract the most suitable employees or workers. For example, it extracts employees with "packaging" and "high skill level." Skill attributes and work experience are also taken into consideration. Input: Keywords that match the requirements, Output: A list of the most suitable employees or workers.

[1014] Step 5:

[1015] The server starts an emotion recognition engine and analyzes the user's emotional state. It analyzes the user's voice, facial expression, text input, etc. to obtain the user's emotional data. Input: User's voice, facial expression, text, Output: Emotional data.

[1016] Step 6:

[1017] The server obtains the affiliation information of the extracted employees or workers. It obtains the affiliation information (department name and position) from the external database via API and creates a ranking of the most suitable employees or workers. Input: Employee ID, Output: Affiliation information

[1018] Step 7:

[1019] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking order. For example, if the user is feeling stressed, the server adjusts the ranking order to give priority to more experienced employees. Input: Emotion data, Output: Adjusted ranking order.

[1020] Step 8:

[1021] The terminal displays the ranking results to the user in a format that corresponds to the emotion. For example, it may display the results in the format "Ranking 1: Employee B (Skill: 80, Project Management: 85, Position: IT Department Manager)." The user can assign tasks to the selected employee or worker based on the presented list. Input: Adjusted ranking, Output: Display of ranking results.

[1022] 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.

[1023] 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.

[1024] 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.

[1025] [Fourth embodiment]

[1026] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1027] 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.

[1028] 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).

[1029] 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.

[1030] 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.

[1031] 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).

[1032] 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. 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.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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."

[1039] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present employees who are suitable for specific tasks.

[1040] Initializing the Skills Database

[1041] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. The entered skill information is registered on the server and saved in a database. Here, numerical data is registered for each type of skill.

[1042] Enter business requirements

[1043] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[1044] Identifying the best employees

[1045] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[1046] Acquisition of affiliation information

[1047] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources system) via API. This information is used to create a ranking of suitable employees.

[1048] Presented in ranking format

[1049] Based on the acquired skill scores and affiliation information, the server creates a ranking list of suitable employees. This ranking is based on the overall score, with employees who are most suited to the job requirements ranked at the top.

[1050] Displaying and Using the Results

[1051] Finally, the terminal displays the ranking results to the user, who then assigns the work to the selected employee based on the presented list. This process enables efficient and appropriate personnel allocation, improving the success rate of the work.

[1052] Specific examples

[1053] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is set to have "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[1054] This system can significantly improve a company's operational efficiency by quickly and accurately matching employee skills with job requirements.

[1055] The processing flow will be explained below.

[1056] Step 1:

[1057] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[1058] Step 2:

[1059] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[1060] Step 3:

[1061] The user inputs the requirements for a specific task. For example, they enter keywords such as "seminar," "digital transformation use cases," "for large companies," and "online" into the input interface.

[1062] Step 4:

[1063] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[1064] Step 5:

[1065] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[1066] Step 6:

[1067] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[1068] Step 7:

[1069] After the employee who best meets the business requirements is extracted, the server retrieves affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[1070] Step 8:

[1071] Based on the affiliation information acquired by the server, a total score is calculated in combination with the skill scores of suitable employees, and a ranking is created.

[1072] Step 9:

[1073] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[1074] Step 10:

[1075] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[1076] In this way, the system of the present invention automates a series of processes from managing the skill information of all employees to matching with business requirements, and supports efficient and appropriate personnel allocation.

[1077] Example 1

[1078] 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."

[1079] Companies face challenges in efficiently identifying the skills of each employee and quickly assigning the best personnel for specific tasks. Traditional manual skill matching takes time and effort, making it difficult to select the right personnel. In addition, obtaining employee affiliation information and presenting it in a ranking format is complex and cumbersome, so an efficient system to solve these issues was needed.

[1080] 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.

[1081] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative AI model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, means for analyzing keywords in job requirements and evaluating the suitability of the skills by comparing them with information in the skills database, and means for transferring job requirements entered using a terminal to the server. This makes it possible to quickly grasp the skills of each employee and efficiently select and assign the most suitable personnel for a specific job.

[1082] An "employee" is an individual who belongs to a company or organization and performs specific tasks or roles.

[1083] The "skills database" is a database that quantifies and centrally manages various employee skills.

[1084] A "generative AI model" is an artificial intelligence model that analyzes natural language and patterns based on input data and generates and provides appropriate information.

[1085] "Job Requirements" refers to the skills, experience, and other conditions required for a particular job or project.

[1086] The "ranking format" is a format in which multiple items are ranked based on an overall score or specific criteria and listed in order from top to bottom.

[1087] "Fitness" is the degree to which something matches or conforms to a particular condition or standard.

[1088] "API" stands for Application Programming Interface, an interface that allows different software systems to communicate with each other and exchange data.

[1089] A "terminal" is a computer or device through which a user accesses a system and inputs or outputs data.

[1090] A "server" is a computer system that stores and processes data and provides services to other computers.

[1091] The present invention relates to a talent management system that builds a database in which the skills of all employees are quantified, and uses a generative artificial intelligence model to extract and present employees suitable for specific tasks.

[1092] First, the user enters the skill information of all employees. Specifically, this involves entering data that scores various skills such as employees' programming skills, sales skills, and project management skills. For example, the user might enter numerical information such as "Programming skills: 75," "Sales skills: 60," and "Project management skills: 80." This entered skill information is sent to the server and saved in a database. The database is organized by skill type and stores the numerical data.

[1093] Next, the user inputs the requirements for a specific task. For example, "Project name: New DX project" and "Requirements: DX use case, for large companies, online" are entered through the device's input interface. The device receives these inputs and transfers them to the server according to the format.

[1094] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements. For example, it analyzes requirements such as "DX use cases," "for large companies," and "online" and extracts related keywords. Based on this, it compares the results with a skills database and evaluates each employee's skill score. For example, if employee B is recorded as "DX skills: 80" and "project management: 85," this is taken into account when assigning a score.

[1095] For the extracted employees, the server sends an API request to the external HR system to obtain their affiliation information. For example, the user obtains information such as "XX department, senior manager" and adds it to the scoring results.

[1096] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees. For example, employees with the highest overall score are listed in descending order. This ranking is adjusted so that employees who are best suited to the job requirements are placed at the top.

[1097] Finally, the terminal displays the ranking results to the user. The user then selects the most suitable employee from the displayed list and assigns the work. For example, the user can ask Employee B, who is ranked highly, to participate in a project. This process enables efficient and appropriate personnel allocation, improving the company's operational efficiency.

[1098] As a concrete example, if a user needs to find an employee to work on a new DX project, they enter the requirements of "DX use case," "for large companies," and "online" into an input form. The server analyzes this and determines that Employee B is the best fit. The server then obtains Employee B's affiliation information through the HR system API and displays it on the terminal in a ranking format. Based on the displayed results, the user can assign the work to Employee B.

[1099] The system uses generative AI models to quickly and accurately match employees with job requirements, significantly improving business efficiency.

[1100] Example prompt sentence:

[1101] "Project name: New DX Project"

[1102] "Requirements: DX use case, for large companies, online"

[1103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1104] Step 1:

[1105] The user inputs the skill information of all employees, specifically numerical data such as "Programming Skills: 75," "Sales Skills: 60," and "Project Management Skills: 80," into the terminal.

[1106] Input: Employee skill data (e.g., "Programming Skills: 75")

[1107] Output: Skill data sent to the server

[1108] Specific operation: The user enters skill information into the input form on the terminal and clicks the send button. The terminal sends the entered skill information to the server. The server stores the received skill data in the database.

[1109] Step 2:

[1110] Users input the requirements for a specific business into the terminal, such as "DX use case," "for large companies," and "online."

[1111] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[1112] Output: Business requirement data sent to the server

[1113] Specific operation: The user enters business requirements into the requirements input form and clicks the send button. The terminal transfers the entered business requirements to the server according to the format. The server puts the received requirements data into a state where it is ready to be analyzed.

[1114] Step 3:

[1115] The server uses a generative AI model (e.g., GPT) to analyze the received business requirements, thereby extracting relevant keywords.

[1116] Input: Business requirements data (e.g., "DX use cases," "for large companies," "online," etc.)

[1117] Output: Extracted keywords (e.g., "DX," "large company," "online," etc.)

[1118] Specific operation: The server feeds the requirements data to the generative AI model, and extracts keywords related to the requirements as an analysis result. These keywords are used in the skill database and matching process.

[1119] Step 4:

[1120] The server compares the extracted keywords with the employee skill database and evaluates and scores each employee's skill score.

[1121] Input: Extracted keywords and skill database

[1122] Output: A list of employees with relevance scores

[1123] Specific operation: The server uses the extracted keywords to match each employee's skills in the skills database and calculates a compatibility score, which indicates how well the employee's skills match the job requirements.

[1124] Step 5:

[1125] The server sends an API request to an external human resources system to obtain affiliation information for employees with high suitability scores.

[1126] Input: A list of employees with relevance scores

[1127] Output: Employee list with affiliation information added

[1128] Specific operation: The server sends a request to an external human resources system via API, obtains employee affiliation information (e.g., department name, job title, etc.), and adds it to the employee list.

[1129] Step 6:

[1130] Based on the acquired skill scores and affiliation information, the server creates a ranking of employees.

[1131] Input: Employee list with added affiliation information

[1132] Output: A list of employees organized in rank order

[1133] Specific operation: The server sorts the employee list by overall score and generates a ranking list, which is adjusted to rank employees who are best suited to the job requirements.

[1134] Step 7:

[1135] The terminal displays the ranking results to the user, who can then select the most suitable employee based on the displayed list and assign the work to them.

[1136] Input: A list of employees organized in a ranked format

[1137] Output: Ranking results displayed to the user

[1138] Specific operation: The server sends the ranking results to the terminal, which then displays them to the user. The user selects the most suitable person from the displayed list and, if necessary, proceeds with the procedure to request the work.

[1139] (Application example 1)

[1140] 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."

[1141] Currently, many companies face the challenge of accurately understanding the skills of their employees and assigning them to appropriate tasks. Particularly on factory production lines, quickly identifying personnel with excellent specific skills and optimally assigning them directly leads to improved productivity and quality. Conventional systems cannot efficiently solve this issue, and there is a problem that appropriate personnel assignment takes time and costs.

[1142] 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.

[1143] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, and means for recommending the most suitable personnel for a specific task on a factory production line. This makes it possible to quickly select and assign the most suitable personnel for a specific job on a factory production line, etc.

[1144] "All employees" refers to all employees of a company or organization.

[1145] "Quantifying skills" means evaluating the various skills that employees possess and expressing their level numerically.

[1146] A "skills database" refers to a database that collects and stores employees' quantified skill information.

[1147] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes existing data and information and generates new information and suggestions.

[1148] "Job requirements" refer to the skills and conditions required to complete a specific job.

[1149] "Extraction" refers to retrieving relevant information or data based on specific conditions.

[1150] "Affiliation information" refers to information about the organization, such as the department and position to which an employee belongs.

[1151] "Ranking format" refers to a format in which evaluation results are ranked and displayed.

[1152] A "suitable employee" is an employee who is judged to have the most suitable skills for a particular job.

[1153] A "production line" refers to a series of equipment and systems used to manufacture products in a factory or other facility.

[1154] "Specific tasks" refer to specific tasks or roles on a production line or in business operations.

[1155] A "recommendation" is a suggestion of a particular option or course of action, particularly a superior option.

[1156] This invention is a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model to extract and present the employees best suited to specific tasks. This system is particularly applicable to optimal personnel allocation on factory production lines.

[1157] First, the server registers the skill information of all employees in a skills database. This skill information is quantified based on various skills such as maintenance skills, programming skills, and quality control skills, and is stored in the database. Furthermore, a generative AI model is used to analyze the requirements for each job. Based on the results of this analysis, the server compares them with the information in the skills database to select the most suitable employees.

[1158] The specific program is processed as follows: First, the user inputs the requirements for a specific job. For example, the job requirements might be "product quality inspection," "online," and "quality control skill: 80." Next, the server analyzes these requirements and extracts employees who fit the job requirements from the skills database.

[1159] For the extracted employees, affiliation information is obtained from an external database (for example, the organization's human resources system) via API. This information is used to create a ranking of the most suitable employees, with the most suitable employees positioned at the top. The ranking results are finally displayed on the device, and the user can use this list to assign tasks to employees deemed suitable.

[1160] The following hardware and software are used to implement this system:

[1161] Hardware: Control PC, factory production line management terminal.

[1162] Software: Python, Gensim (Word2Vec), API (integration with HR system).

[1163] Specific examples

[1164] For example, suppose a factory needs to find the best staff member to perform product quality inspections. The user inputs the following job requirements into the system: "product quality inspection," "online," and "quality control skill: 80." The server then analyzes this and extracts employees with the corresponding skills from the skills database. For example, if employee B is set to have "quality control skill: 85," the server determines that employee B is the best fit. The server then obtains employee B's affiliation information via API and displays it on the terminal as a ranking of the most suitable employees. After viewing this display, the user can request employee B to perform quality inspection work.

[1165] Prompt example

[1166] "What skills are needed to inspect product quality? Please list the skills that are required for the job."

[1167] This enables quick and accurate selection of employees best suited to specific tasks in the factory, enabling effective personnel deployment.

[1168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1169] Step 1:

[1170] A user logs in to the system and inputs the requirements for a specific job. Through the input interface, the user enters requirements such as "product quality inspection," "online," and "quality control skill: 80" into a form. This input data is sent to the server.

[1171] Step 2:

[1172] The server receives the input business requirements and analyzes them using a generative artificial intelligence model (GPT). Specifically, the text data of the business requirements is input into GPT as a prompt, and relevant keywords based on the requirements are extracted. The input here is the text data of the business requirements, and the output is a list of keywords based on the requirements.

[1173] Step 3:

[1174] Based on the keyword list obtained from the generative AI model, the server compares it with a skills database, which stores quantified skill information for all employees. As a result of the comparison, a list of employees who best meet the business requirements is generated. The input data is the keyword list and the skills database, and the output data is a tentative list of optimal employees.

[1175] Step 4:

[1176] For each employee in the provisional list, the server accesses an external database (the organization's human resources system) via API to obtain the employee's affiliation information. The obtained affiliation information includes the employee's job title and department name. The input data is the employee ID, and the output data is an employee list with the affiliation information added.

[1177] Step 5:

[1178] The server creates a ranking of the most suitable employees based on the acquired affiliation information and skill scores. The ranking is based on the suitability of skills for the job requirements and job title information. The input data is an employee list with affiliation information added, and the output data is a ranked list of suitable employees.

[1179] Step 6:

[1180] The server sends the generated ranked list of suitable employees to the terminal. The terminal displays the ranking results to the user. The user can refer to the displayed results and assign the work to the employee deemed most suitable. The input data is the ranked list of suitable employees, and the output data is the ranking results displayed on the terminal.

[1181] 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.

[1182] The present invention relates to a talent management system that builds a database that quantifies the skills of all employees and uses a generative artificial intelligence model and an emotion engine to extract and present employees who are suitable for specific tasks.

[1183] Initializing the Skills Database

[1184] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[1185] Enter business requirements

[1186] Next, the user enters the requirements for a specific task. For example, requirements such as "seminar," "digital transformation use case," "for large companies," and "online" are entered into a form. At this stage, the device provides an input interface to help the user easily enter the task requirements.

[1187] Identifying the best employees

[1188] The server analyzes the input job requirements using a generative artificial intelligence model (GPT). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. The server scores the most suitable employees based on information such as skill attributes and work experience.

[1189] Recognizing user emotions using an emotion engine

[1190] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[1191] Acquisition of affiliation information

[1192] For employees who are deemed the most suitable, the server retrieves their affiliation information (such as department name and job title) from an external database (e.g., the organization's human resources information system) via API. This information is used to create a ranking of suitable employees.

[1193] Emotion-based ranking presentation

[1194] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees.

[1195] Displaying and Using the Results

[1196] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then uses the list to request work from the selected employee. Requests are made via email or internal company tools.

[1197] Specific examples

[1198] For example, suppose a company needs to find the right person to launch a new DX project. The user enters the requirements "DX use case," "for large companies," and "online" into the system. The server analyzes this and extracts employees with the relevant skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. The server then uses an emotion engine to recognize the user's emotions and adjusts how the best employees are displayed based on the user's state. Finally, the server obtains employee B's affiliation information through an API and displays the results in a ranking format on the device. After seeing this display, the user can ask employee B to participate in the project.

[1199] The system quickly and accurately matches employee skills with job requirements, and also takes user emotions into account to achieve more optimal personnel allocation.

[1200] The processing flow will be explained below.

[1201] Step 1:

[1202] The user enters the skill information of all employees. Specifically, each employee's skill type (e.g., programming, project management, sales) and their skill level are quantified and registered in the system.

[1203] Step 2:

[1204] The server receives the entered skill information and stores it in a skills database, allowing the skill information of all employees to be managed centrally.

[1205] Step 3:

[1206] The user inputs the requirements for a specific task, such as "seminar," "digital transformation use case," "for large companies," and "online" into the input interface.

[1207] Step 4:

[1208] The terminal displays a form for the user to enter business requirements, where requirements can be entered using pull-down menus and text input fields.

[1209] Step 5:

[1210] The server receives the business requirements entered by the user and analyzes them using a generative artificial intelligence model (GPT). This analysis extracts keywords and necessary skill sets that match the business requirements.

[1211] Step 6:

[1212] The server compares the analyzed keywords with the employee skill information in the skills database and calculates a compatibility score for each employee, taking into account their skill attributes and work experience.

[1213] Step 7:

[1214] The server activates an emotion engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[1215] Step 8:

[1216] For employees who are deemed the most suitable server, the server obtains affiliation information (such as department name and job title) from an external database (for example, the organization's human resources information system) via an API.

[1217] Step 9:

[1218] Based on the acquired affiliation information, the server calculates an overall score and ranks the employees by combining it with the skill scores of the suitable employees. Furthermore, the acquired emotional data is reflected and the ranking format is adjusted according to the user's emotions.

[1219] Step 10:

[1220] The device will display the ranking results to the user. For example, it will be displayed in the form of "Ranking 1: Employee B (DX Skills: 80, Project Management: 85, Position: IT Department Manager)."

[1221] Step 11:

[1222] Users refer to the ranking results and assign tasks to employees deemed most suitable. Requests are made via email or internal company tools.

[1223] As a concrete example, consider the case of finding the right person to launch a new DX project at a company. The user inputs requirements, such as "DX use case," "for large companies," and "online," into the system. The server analyzes this and extracts employees with the appropriate skills from the skills database. For example, if employee B is configured with "DX skills: 80" and "project management: 85," the server determines that employee B is the best fit. Next, the server uses an emotion engine to recognize the user's emotions. If the user is feeling stressed, it adjusts the display method to prioritize experienced employees and optimize the display of the most suitable employees. Finally, the server obtains employee B's affiliation information via an API and displays the results in a ranking format on the device. After viewing this display, the user can request employee B to participate in the project. This system quickly and accurately matches employee skills with business requirements and also takes user emotions into account, achieving more optimal personnel allocation.

[1224] Example 2

[1225] 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."

[1226] Traditional talent management systems lacked efficiency and accuracy in selecting personnel, requiring significant time and resources for manual processes, especially when managing large amounts of employee data. Furthermore, they selected the most suitable employees without taking into account the user's emotional state, which could result in increased user stress. Furthermore, they lacked sufficient integration with external data, making it difficult to obtain the latest employee affiliation information. A system that can solve these issues is needed.

[1227] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1228] In this invention, the server includes means for quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from the skills database, means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format, emotion recognition means for recognizing the emotional state of the user and adjusting the presented ranking based on that, and means for providing a user interface and supporting the input of job requirements. This enables more optimal personnel allocation by quickly and accurately matching employee skills with job requirements and further taking the user's emotions into consideration.

[1229] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[1230] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes given data and extracts the requirements necessary for a specific task.

[1231] The "ranking format" is a format for presenting results in an order based on specific conditions.

[1232] "Emotion recognition means" is a technology for grasping the user's emotional state and adjusting the content presented based on that.

[1233] A "user interface" is the means by which a user interacts with a system and inputs required information.

[1234] An "API" is an interface for data exchange with external databases and other systems.

[1235] "Scoring" is the process of quantifying an object's evaluation based on specific criteria.

[1236] This invention relates to a talent management system that builds a database that quantifies the skills of all employees, extracts employees suitable for specific tasks using a generative artificial intelligence model and an emotion engine, and presents the optimal employees to the user in a ranking format. The system quickly and accurately identifies employees with the most suitable skills and supports the user in selecting the optimal employee based on the task requirements.

[1237] This system consists of hardware such as a server, a terminal, and an input interface operated by the user. The software uses a database system (e.g., MySQL, PostgreSQL), a generative artificial intelligence model (e.g., natural language processing technology such as GPT-4), and an emotion recognition engine (e.g., Microsoft Azure Cognitive Services, Google Cloud AI).

[1238] Initializing the Skills Database

[1239] 1. The user enters the skill information of all employees. For example, the user can enter each employee's skill type (e.g., programming, project management, sales) and the corresponding skill level as a numerical value. This allows employee A to have specific skill data such as "Programming: 90, Project Management: 80."

[1240] 2. The device receives the entered skill information and sends it to the server.

[1241] 3. The server stores the received information in a database (e.g., MySQL, PostgreSQL) to create a skills database.

[1242] Enter business requirements

[1243] 1. The user enters the requirements necessary for the business. For example, they select requirements such as "Seminar," "DX Use Case," "For Large Companies," and "Online."

[1244] 2. The terminal receives the business requirements entered by the user and provides an input interface. An example of a prompt is "To find the best employee for your DX project, please enter the following requirements: seminar, DX use case, for large companies, online."

[1245] 3. The terminal sends the input requirements to the server.

[1246] Identifying the best employees

[1247] 1. The server analyzes the received business requirements using a generative artificial intelligence model (e.g., GPT-4).

[1248] 2. Matching with the skills database is performed based on the keywords extracted through analysis. For example, employees who match the requirements of "DX use cases" and "online" are extracted from the skills database.

[1249] 3. The server will score the most suitable employee based on the matching results. For example, if employee B has "DX Skill: 80" and "Online Experience: 90", he will receive a high score.

[1250] Recognizing user emotions using an emotion engine

[1251] 1. The server launches an emotion recognition engine, which uses speech recognition and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services).

[1252] 2. Using the device's camera and microphone, the voice and facial expressions of the user are captured in real time when they enter business requirements or view ranking results.

[1253] 3. The server analyzes this data and determines the user's emotional state. For example, it determines whether the user is feeling stressed.

[1254] Acquisition of affiliation information

[1255] 1. The server requests employee affiliation information from an external human resources information system via an API, which is designed as a RESTful API.

[1256] 2. Obtain the affiliation information (e.g., department name, position, etc.) returned from the external system.

[1257] 3. The server uses the information obtained to create a ranking.

[1258] Emotion-based ranking presentation

[1259] 1. The server evaluates the user's emotional state and adjusts the ranking results accordingly.

[1260] 2. For example, if a user is feeling stressed, more experienced employees will be displayed first.

[1261] Displaying and Using the Results

[1262] 1. The terminal displays the final ranking results to the user in a visually easy-to-understand format (e.g., using HTML and CSS).

[1263] 2. The user selects the most suitable employee from the presented ranking results and makes a work request. The request is made via internal tools or email.

[1264] In this way, the system of the present invention quickly and accurately matches employee skills with job requirements, and by taking user sentiment into consideration, achieves more effective personnel allocation.

[1265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1266] Step 1: User enters skill information

[1267] The user inputs the skill information of each employee (e.g., skill type such as programming, project management, sales, etc., and each skill level) in numerical form. The terminal receives this information through an input interface (e.g., HTML form) and formats it as input data.

[1268] Input: Skill type and skill level for each employee

[1269] Output: Formatted skill data

[1270] How it works: When the device receives the input skill information, it formats it in the appropriate format (e.g., JSON, XML) and sends it to the server.

[1271] Step 2: Creating a skills database

[1272] The server receives the skill information sent from the device and stores it in a database (e.g., MySQL, PostgreSQL).

[1273] Input: Formatted skill data

[1274] Output: Skill information stored in the database

[1275] How it works: The server validates the received skill information and, if there are no errors, executes a SQL query to insert the information into the database. For example, it executes a query like "INSERT INTO skill_table (employee_id, skill_type, skill_level) VALUES (...)".

[1276] Step 3: Enter business requirements

[1277] The user enters the requirements for a specific task (e.g., "seminar," "DX use case," "for large companies," "online") using an input interface. The device receives this information and converts it into the appropriate data format.

[1278] Input: Business requirements

[1279] Output: Formatted business requirements data

[1280] Operation: The terminal validates the requirements entered by the user, converts them into the appropriate format, and sends them to the server.

[1281] Step 4: Requirements analysis and matching

[1282] The server analyzes the business requirements sent from the device using a generative artificial intelligence model (e.g., GPT-4). As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database.

[1283] Input: Business requirements data

[1284] Output: Requirement keywords and matching results

[1285] Operation: The server inputs job requirements data into a generative AI model and searches the skills database using the resulting keyword list. For example, it retrieves employees with scores such as "Programming 90" and "Online Support 85."

[1286] Step 5: Scoring and ranking

[1287] The server scores the most suitable employees based on the matching, taking into account skill attributes and work experience, and assigns a score to each employee.

[1288] Input: Matching results

[1289] Output: Employee score list

[1290] How it works: The server runs a scoring algorithm on the list of employees that match the criteria, assigning each employee a score and ranking them.

[1291] Step 6: Emotion Recognition

[1292] The server activates an emotion engine to recognize the user's emotional state, and uses the device's camera and microphone to capture voice, facial expressions, and text input.

[1293] Input: User's voice, facial expressions, and text data

[1294] Output: User's emotional state data

[1295] Operation: The device records the user's facial expressions and voice using a camera and microphone while the user is entering business requirements and displaying ranking results. This data is then sent to the server in real time.

[1296] Step 7: Sentiment-aware ranking adjustment

[1297] The server analyzes the acquired emotional state data and adjusts the ranking order according to the user's emotions.

[1298] Input: User's emotional state data

[1299] Output: Adjusted ranking results

[1300] How it works: The server analyzes the user's emotional data and optimizes the ranking, for example, by placing more experienced employees at the top if the user is under high stress.

[1301] Step 8: View results and submit work

[1302] The terminal displays the adjusted ranking results to the user, allowing the user to select the most suitable employee and request the work.

[1303] Input: Adjusted ranking results

[1304] Output: Ranking results displayed to the user

[1305] Operation: The terminal displays the ranking results to the user in a visually easy-to-understand format (e.g., HTML, CSS). The user can select the target employee from the screen and request work via email or internal tools.

[1306] The above is the specific processing flow in this system.

[1307] (Application example 2)

[1308] 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."

[1309] Conventional talent management systems require time and effort to match employee skills with job requirements, making optimal personnel placement difficult. Furthermore, because they select personnel suited to job requirements without considering the user's feelings, users may be dissatisfied with the selection results. There is a need to solve these issues and apply them to task management using factory robots.

[1310] The identification process 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 quantifying the skills of all employees and creating a skills database, means for analyzing the requirements for a job using a generative artificial intelligence model and extracting the most suitable employees or workers from the skills database, means for acquiring the affiliation information of the extracted employees or workers and presenting the most suitable employees or workers in a ranking format, means for applying the extracted most suitable employees or workers to task management by factory robots, and means for analyzing the emotional state of a user using an emotion recognition engine and reflecting the analysis results in scoring. This enables fast and accurate matching of personnel and jobs, improving user satisfaction and enabling efficient task management by factory robots.

[1311] The "skills database" is a database that quantifies and centrally manages the skill information of all employees.

[1312] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes business requirements and extracts the most suitable employees or workers from a skills database.

[1313] "Job requirements" refers to information that indicates the skills and conditions required for a specific job.

[1314] "Best fit employee or worker" refers to the employee or worker who best fits the job requirements based on the skills database.

[1315] The "ranking format" is a format in which the extracted employees or workers are ranked and presented based on their suitability.

[1316] A "factory robot" is a robot used to automate work within a factory.

[1317] "Task management" is the process of managing the progress of work and assigning it to the appropriate people or machines.

[1318] An "emotion recognition engine" is an engine for analyzing the user's emotional state.

[1319] "Emotional state" is information that indicates the user's current emotional and psychological state.

[1320] "Scoring" is the process of evaluating or ranking based on specific criteria.

[1321] This invention relates to a talent management system that quantifies the skills of all employees, builds a skills database, and uses a generative artificial intelligence model and an emotion recognition engine to extract and present employees or workers suitable for specific tasks.Furthermore, it realizes efficient task management using factory robots.

[1322] Initializing the Skills Database

[1323] First, the user enters the skill information of all employees. Specifically, the skill type (e.g., programming, project management, sales) for each employee and their skill level are quantified and registered in the system. The entered skill information is registered on the server and saved in a database. This allows for centralized management of employee skill information.

[1324] Enter business requirements

[1325] Next, the user inputs the requirements for a specific task, such as "packaging," "complexity level: 3," and "deadline: 2023-12-01," into the form. At this stage, the terminal provides an input interface to help the user easily input the task requirements.

[1326] Identifying the best employees or workers

[1327] The server analyzes the input business requirements using a generative AI model. As a result of the analysis, keywords that match the requirements are extracted and matched with a skills database. Based on information such as skill attributes and work experience, the server scores the most suitable employee or worker.

[1328] Recognizing user emotions using an emotion recognition engine

[1329] The server activates an emotion recognition engine to recognize the user's emotions. When the user is entering business requirements or displaying ranking results, the server analyzes the user's voice, facial expressions, text input, etc. to understand the user's emotional state.

[1330] Acquisition of affiliation information

[1331] For employees or workers who are deemed the most suitable, the server obtains their affiliation information (department name, job title, etc.) from an external database via API. This information is used to create a ranking of suitable employees or workers.

[1332] Emotion-based ranking presentation

[1333] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking accordingly. For example, if the user is feeling stressed, the server will adjust the ranking to prioritize the display of more experienced employees or workers.

[1334] Displaying and Using the Results

[1335] Finally, the device displays the ranking results to the user in a format that corresponds to their emotions. For example, it might show "Ranking 1: Employee B (Skills: 80, Project Management: 85, Position: IT Department Manager)." The user then selects the employee or worker from the list and assigns the task. The request is made via email or internal company tools.

[1336] Specific examples

[1337] For example, suppose a "packaging task" arises at a factory, and the factory manager inputs this requirement into the system. The task requirements, "packaging," "complexity level: 3," and "deadline: 2023-12-01," are analyzed using a generative AI model. Based on the analysis results, employees or workers with the most appropriate skills are extracted from a skills database, and the user's emotions are analyzed using an emotion recognition engine. For example, a prompt such as "Find the most appropriate worker based on the following criteria: Task type: packaging, complexity level: 3, deadline: 2023-12-01" is input into the generative AI model. Based on this information, the server presents the appropriate employees or workers to the user in a ranked format, and ultimately the task is requested.

[1338] This system quickly and accurately matches employee skills with work requirements, and also takes user emotions into account to achieve more optimal personnel allocation. It also enables efficient task management by factory robots.

[1339] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1340] Step 1:

[1341] The user inputs the skill information of all employees. The skill type and skill level of each employee are converted into numerical values ​​and registered in the system through an input interface. Specifically, data such as "Skill type: Programming" and "Skill level: 80" is entered for each employee. The input data is sent to the server and saved in the skill database. Input: Employee skill information, Output: Registration in the skill database.

[1342] Step 2:

[1343] The user inputs the requirements for a specific task. For example, requirements such as "packaging," "complexity level: 3," and "deadline: 2023-12-01" are entered into a form. The terminal provides this input interface, and the input requirements are sent to the server. Input: Task requirements, Output: Send to server.

[1344] Step 3:

[1345] The server uses a generative artificial intelligence model to analyze the input business requirements. As a result of the analysis, keywords that match the requirements are extracted. For example, based on the requirements "packaging" and "complexity level: 3," keywords for matching skills are generated. Input: Business requirements, Output: Keywords that match the requirements.

[1346] Step 4:

[1347] The server matches the generated keywords with a skills database to extract the most suitable employees or workers. For example, it extracts employees with "packaging" and "high skill level." Skill attributes and work experience are also taken into consideration. Input: Keywords that match the requirements, Output: A list of the most suitable employees or workers.

[1348] Step 5:

[1349] The server starts an emotion recognition engine and analyzes the user's emotional state. It analyzes the user's voice, facial expression, text input, etc. to obtain the user's emotional data. Input: User's voice, facial expression, text, Output: Emotional data.

[1350] Step 6:

[1351] The server obtains the affiliation information of the extracted employees or workers. It obtains the affiliation information (department name and position) from the external database via API and creates a ranking of the most suitable employees or workers. Input: Employee ID, Output: Affiliation information

[1352] Step 7:

[1353] The server analyzes the acquired emotion data, calculates the degree of suitability according to the user's emotion, and adjusts the ranking order. For example, if the user is feeling stressed, the server adjusts the ranking order to give priority to more experienced employees. Input: Emotion data, Output: Adjusted ranking order.

[1354] Step 8:

[1355] The terminal displays the ranking results to the user in a format that corresponds to the emotion. For example, it may display the results in the format "Ranking 1: Employee B (Skill: 80, Project Management: 85, Position: IT Department Manager)." The user can assign tasks to the selected employee or worker based on the presented list. Input: Adjusted ranking, Output: Display of ranking results.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] FIG. 9 is a diagram illustrating 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 actions 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.

[1361] 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.

[1362] 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).

[1363] 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.

[1364] 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."

[1365] 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.

[1366] 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).

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] The following is further disclosed regarding the above embodiment.

[1378] Propose draft claims according to the following format:

[1379] (Claim 1)

[1380] A means to quantify the skills of all employees and create a skills database,

[1381] A method for analyzing the necessary requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from a skills database;

[1382] A means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format;

[1383] A system including:

[1384] (Claim 2)

[1385] 10. The system of claim 1, further comprising means for analyzing keywords in the job requirements and evaluating the suitability of the skills against information in the skills database.

[1386] (Claim 3)

[1387] 2. The system according to claim 1, further comprising means for acquiring the extracted employee affiliation information from an external database via an API.

[1388] (Claim 4)

[1389] The system of claim 1, further comprising means for calculating an overall score based on the skill attributes and work experience of employees extracted by the generative artificial intelligence model, and presenting the score in a ranking format.

[1390] "Example 1"

[1391] (Claim 1)

[1392] A means to quantify the skills of all employees and create a skills database;

[1393] A means for analyzing the necessary requirements for a job using a generative AI model and extracting the most suitable employees from a skills database;

[1394] A means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format;

[1395] A means for analyzing keywords in job requirements and evaluating the suitability of skills by comparing them with information in a skills database;

[1396] means for transferring business requirements inputted using a terminal to a server;

[1397] A system including:

[1398] (Claim 2)

[1399] 10. The system of claim 1, further comprising means for acquiring the extracted employee affiliation information from an external database through an API.

[1400] (Claim 3)

[1401] 10. The system according to claim 1, further comprising means for displaying information on the qualified employees presented in a ranked format on a terminal.

[1402] "Application Example 1"

[1403] (Claim 1)

[1404] A means to quantify the skills of all employees and create a skills database,

[1405] A method for analyzing the necessary requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from a skills database;

[1406] A means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format;

[1407] A means of recommending the best people for specific tasks on a factory production line;

[1408] A system including:

[1409] (Claim 2)

[1410] 10. The system of claim 1, further comprising means for analyzing keywords in the job requirements and evaluating the suitability of the skills against information in the skills database.

[1411] (Claim 3)

[1412] 2. The system according to claim 1, further comprising means for acquiring the extracted employee affiliation information from an external database via an API.

[1413] "Example 2: Combining Emotion Engines"

[1414] (Claim 1)

[1415] A means to quantify the skills of all employees and create a skills database,

[1416] A method for analyzing the necessary requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from a skills database;

[1417] A means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format;

[1418] an emotion recognition means for recognizing the emotional state of a user and adjusting the rankings presented based on the emotional state of the user;

[1419] A means for providing a user interface and assisting in inputting business requirements;

[1420] A system including:

[1421] (Claim 2)

[1422] 10. The system of claim 1, further comprising means for analyzing keywords in the job requirements and evaluating the suitability of the skills against information in the skills database.

[1423] (Claim 3)

[1424] 2. The system according to claim 1, further comprising means for acquiring the extracted employee affiliation information from an external database via an API.

[1425] "Application example 2 when combining emotion engines"

[1426] (Claim 1)

[1427] A means to quantify the skills of all employees and create a skills database,

[1428] A means for analyzing the necessary requirements for a job using a generative artificial intelligence model and extracting the most suitable employee or worker from a skill database;

[1429] A means for acquiring the affiliation information of the extracted employees or workers and presenting the most suitable employees or workers in a ranking format;

[1430] A means for applying the extracted optimal employees or workers to task management by factory robots;

[1431] A means for analyzing the emotional state of a user using an emotion recognition engine and reflecting the analysis result in scoring;

[1432] A system including:

[1433] (Claim 2)

[1434] 10. The system of claim 1, further comprising means for analyzing keywords in the job requirements and evaluating the suitability of the skills against information in the skills database.

[1435] (Claim 3)

[1436] 10. The system of claim 1, further comprising means for acquiring affiliation information of the extracted employees or workers from an external database via an API. [Explanation of symbols]

[1437] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to quantify the skills of all employees and create a skills database, A method for analyzing the necessary requirements for a job using a generative artificial intelligence model and extracting the most suitable employees from a skills database; A means for acquiring the affiliation information of the extracted employees and presenting the most suitable employees in a ranking format; A system including:

2. 2. The system according to claim 1, further comprising means for analyzing keywords in the job requirements and evaluating the suitability of the skills by comparing them with information in the skills database.

3. The system according to claim 1, further comprising means for acquiring the extracted employee affiliation information from an external database via an API.

4. The system according to claim 1, further comprising means for calculating a total score based on the skill attributes and work experience of employees extracted by the generative artificial intelligence model, and presenting the score in a ranking format.

Images