System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring employee data of a large company, employee demand data, company data of a small company, and required personnel data, a means for standardizing the acquired data and registering the data in a database, a means for matching the employees of the large company with the small companies based on the standardized data, and a means for notifying the employees of the large company and the small companies of the matching results.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Small and medium-sized enterprises (SMEs) face a serious problem of labor shortages, and it is particularly difficult to secure experienced personnel. Meanwhile, large companies are seeking to revitalize senior employees to promote the transfer of their skills to younger employees while effectively utilizing their skills and experience. The present invention aims to simultaneously solve the two issues of labor shortages in SMEs and the revitalization of senior employees in large companies. [Means for solving the problem]

[0005] The present invention is a system that includes a means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired human resources data, a means for standardizing the acquired data and registering it in a database, a means for matching employees of large companies with small and medium-sized enterprises based on the standardized data, and a means for notifying employees of large companies and small and medium-sized enterprises of the matching results (Claim 1).

[0006] Furthermore, by including a means for adjusting secondment contracts at SMEs for matched employees of large companies (Claim 2), secondment procedures can be smoothly carried out. Also, by including a means for monitoring the performance of employees of large companies who are seconded (Claim 3), it becomes possible to grasp the status of work execution at the secondment destination and provide necessary support.

[0007] This will enable small and medium-sized enterprises to secure immediately effective personnel while reducing labor costs, and large companies to effectively utilize the experience and skills of senior employees, thereby revitalizing the entire company.

[0008] "Employee data" refers to information about employees of large companies, such as their backgrounds, skills, qualifications, and work experience.

[0009] "Employee request data" refers to information including the desired working style, work location, job content, etc. of employees of large companies.

[0010] "Company data" refers to data such as basic information about a company, its business activities, size, and location.

[0011] "Desired talent data" refers to information such as the skill sets, experience, job titles, salary ranges, and working conditions of the personnel that SMEs require.

[0012] "Standardization" refers to converting data collected in different formats and content into a unified format, making it easier to analyze and process.

[0013] "Database" refers to a digital system designed to store information systematically so that it can be quickly accessed, updated, and retrieved as needed.

[0014] "Matching algorithm" refers to a set of calculation methods and procedures for optimal matching based on collected data.

[0015] "Notification" refers to the act of communicating system-generated information or results to a specific user.

[0016] A "secondment contract" refers to a contract that an employee of a large company enters into to work for a small or medium-sized company for a certain period of time.

[0017] "Performance monitoring" refers to the activity of regularly observing and evaluating the work performance of employees on secondment. [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 is a system for seconding senior employees of large companies to small and medium-sized enterprises, and specifically operates through the collaboration of a server, terminals, and users. The mechanism and specific operation of the system will be described in detail below.

[0040] server

[0041] Data collection

[0042] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, collected via each company's database or API.

[0043] Examples:

[0044] "The server collects employee A's background, skills, and preferred working arrangements from a large company's database."

[0045] "The server collects the desired personnel requirements from a database of small and medium-sized enterprises."

[0046] Data Standardization

[0047] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[0048] Examples:

[0049] "The server standardizes employee data for large corporations into backgrounds, skill sets, and working conditions."

[0050] "The server standardizes the personnel data required by small and medium-sized enterprises into experience, skills, and working conditions."

[0051] Executing the matching algorithm

[0052] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies, taking into account their career history, skill set, and working conditions to make the best possible match.

[0053] Examples:

[0054] "The server uses AI to compare the skills required by small and medium-sized company B with the skills of employee A of large company, and selects the candidate with the highest match rate."

[0055] Notification of results

[0056] The matching results are communicated to employees of large companies and small and medium-sized enterprises, and the results are summarized in a report and sent via email and dashboard.

[0057] Examples:

[0058] The server notifies Employee A and Small Business B of the matching results and sends detailed information by email.

[0059] Terminal

[0060] Data Entry

[0061] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input the necessary information, which is then sent to a server for further processing.

[0062] Examples:

[0063] "Employee A enters his / her career history and desired conditions into the terminal and sends it to the server."

[0064] "Managers of small and medium-sized enterprises input the personnel requirements into a terminal and send them to a server."

[0065] Confirming results and arranging interviews

[0066] The matching results are checked on the terminal, and interviews and transfer contracts are arranged. Specific interview dates, times, and locations are also set on the terminal.

[0067] Examples:

[0068] "The manager of the small and medium-sized enterprise checks the matching results on the terminal and schedules an interview date and time with Employee A."

[0069] "Employee A checks the interview date and time on the terminal and approves it."

[0070] User

[0071] Senior Employees

[0072] Senior employees enter their information through a terminal, check the matching results, and then undergo an interview. If approved, they will begin their secondment to a small or medium-sized company.

[0073] Examples:

[0074] "Senior employee A enters his / her skill set and desired conditions into the terminal, and confirms the matching results when they are notified."

[0075] "Senior employee A interviews with small and medium-sized company B and officially signs a secondment contract."

[0076] small business manager

[0077] Managers of small and medium-sized enterprises can input the desired personnel requirements through the terminal, check the matching results, and also arrange interviews and process transfer contracts.

[0078] Examples:

[0079] "Enter the skill set desired by the manager of SME B into the terminal and check the matching results."

[0080] "Manager of SME B arranges an interview with Senior Employee A and concludes a secondment contract."

[0081] This system allows small and medium-sized enterprises to quickly and efficiently secure work-ready personnel, while large companies can effectively utilize the skills of senior employees, providing significant benefits to both parties.

[0082] The processing flow will be explained below.

[0083] Step 1: Data collection

[0084] The server collects employee data from the database of a large company, specifically information such as employee background, skills, qualifications, work experience, preferred work arrangements and locations.

[0085] The server collects company data and desired personnel data from a database of small and medium-sized enterprises, specifically, basic information about the company, business details, desired skill sets, job details, salary range, working hours, etc.

[0086] Step 2: Standardize the data

[0087] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, etc. By organizing data stored in different formats into a unified format, subsequent processing becomes easier.

[0088] The server also converts the human resources data required by small and medium-sized enterprises into a standard format, standardizing the required skills, experience, job title, salary range, working conditions, etc.

[0089] Step 3: Register with the database

[0090] The server registers the standardized data in a database, creating an index that enables rapid data search and AI analysis.

[0091] Data on employees of large companies and the personnel data required by small and medium-sized enterprises is stored in a database, and appropriate tags are added to make it easy to search.

[0092] Step 4: Run the matching algorithm

[0093] The server passes the standardized data from the database to the AI, which runs a matching algorithm to match the employee's skill set and desired conditions with the skill sets and working conditions required by the small and medium-sized enterprise, and finds the best match.

[0094] The server reviews the AI ​​results and lists the most relevant matches.

[0095] Step 5: Notification of results

[0096] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized companies by sending the results via email or an online dashboard.

[0097] The server will send a notification with detailed information about the match, including contact information.

[0098] Step 6: Data entry

[0099] Using the terminals, employees of large companies and managers of small and medium-sized enterprises input the necessary information. Employees input their career history, skills, and desired conditions, while managers of small and medium-sized enterprises input the desired skill sets and job content.

[0100] The entered data is sent to the server in real time and used for subsequent processing.

[0101] Step 7: Check the results and arrange an interview

[0102] The matching results are checked on the terminal and the interview and secondment contract are arranged. The manager of the SME checks the detailed information of the matched senior employee and sets the interview date and time.

[0103] Senior employees check the interview date and time on the terminal and make any changes or approvals as necessary.

[0104] Step 8: Interview and decision

[0105] The senior employee as the user will have an interview with the SME. As a result of the interview, the SME will decide whether to officially hire the senior employee who wishes to be seconded.

[0106] A small or medium-sized enterprise enters into a secondment contract and registers the contract details on a server.

[0107] Step 9: Commencement and monitoring

[0108] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[0109] Regularly collect and monitor performance data from senior staff on secondment and provide any support required.

[0110] As a result, this system will alleviate the labor shortages of small and medium-sized enterprises and effectively utilize the experience and skills of senior employees at large companies, providing a mutually beneficial solution.

[0111] Example 1

[0112] 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."

[0113] In recent years, there has been a demand for increased mobility of human resources between large and small organizations. However, many large organizations have limited opportunities to effectively utilize the skills of senior employees, while small organizations have difficulty securing human resources who can immediately contribute. To solve these issues, a system is needed that accurately matches the needs of both parties and quickly and efficiently dispatches human resources.

[0114] 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.

[0115] In this invention, the server includes means for acquiring employee information of the large organization, employee preference information, company information of the small organization, and necessary human resources information, means for verifying and standardizing the acquired data and registering it in a database, means for executing an artificial intelligence model to match employees of the large organization with small organizations based on the standardized data, and means for notifying employees of the large organization and the small organization of the matching results, thereby enabling senior employees of the large organization to be dispatched to the small organization quickly and efficiently.

[0116] A "large organization" is a company with a large number of employees and multiple business divisions and processes.

[0117] "Employee Information" means data related to an employee, such as an employee's background, skill set, job title, work history, and evaluation information.

[0118] "Employee preference information" refers to data that indicates an employee's individual preferences and conditions, such as desired working style, work location, job content, and working hours.

[0119] A "small organization" is a business or organization with a small number of employees and limited resources.

[0120] "Company information" refers to general information related to a company, such as the company's size, industry, location, business activities, and the type of personnel it is seeking.

[0121] "Required human resources information" refers to data that indicates the specific job requirements, such as the skill set, experience, qualifications, and working conditions that a company is looking for.

[0122] "Means of acquisition" refers to the methods and processes for obtaining the required data through a database or API.

[0123] "Validation and standardization" refers to the process of converting data stored in different formats into a unified format to ensure data consistency and accuracy.

[0124] A "database" refers to a system for efficiently storing, managing, and searching large amounts of data.

[0125] An "artificial intelligence model" refers to an algorithm that uses machine learning or deep learning to analyze data and perform a specific task (in this case, matching).

[0126] "Matching" refers to the process of finding the right match based on specific criteria, which in this case means matching employees from larger organizations with smaller organizations.

[0127] "Means of notification" refers to the method by which matching results are communicated to relevant parties, such as through email, dashboards, notification systems, etc.

[0128] The present invention is a system for dispatching senior employees of a large organization to a small organization, and specifically, a mechanism in which a server, a terminal, and a user work together. Specific embodiments of the system are described in detail below.

[0129] First, the server collects employee information and preference information from large organizations, company information from small organizations, and necessary human resources information. This data is obtained via each company's database or API. For example, the server calls the large organization's HR system API to obtain employee backgrounds and skill sets, and uses the small organization's job information API to collect company recruitment requirements.

[0130] The server validates and standardizes the collected data, which is often stored in different formats. Standardizing the data into a specific format facilitates subsequent analysis. For example, the server converts employee data from a large organization into a standard format based on background, skill set, and working conditions.

[0131] Next, the server uses this standardized data to match employees from large organizations with smaller organizations using an artificial intelligence model. The AI ​​model is an algorithm that incorporates machine learning and deep learning, and comprehensively evaluates each employee's skill set, background, and desired conditions to make the optimal match. For example, the server loads the AI ​​model, provides background, skills, and working conditions as input data, analyzes the model's execution results, and selects highly suitable candidates.

[0132] The server notifies the employees of the large organization and the small organization of the matching results. The results are summarized in a report format and sent via email or dashboard. For example, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be displayed when logged in.

[0133] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. The entered data is then sent to a server and used in subsequent processes. For example, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation.

[0134] The device also provides an interface for checking matching results and arranging interviews and temporary employment contracts. Specific interview dates, times, and locations can also be set on the device. For example, an administrator at a small organization can log in from the device and check the details of the matching results, and employee A can then check the interview date and time on the device and press the approval button to complete the interview arrangement.

[0135] Example of input prompt for generative AI model

[0136] The following prompts can be used to provide the necessary input to the generative AI model:

[0137] "Please explain in detail the process by which your server collects employee data for a large organization."

[0138] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[0139] This system allows senior employees of large organizations to be quickly and efficiently dispatched to smaller organizations, making effective use of their skills, while at the same time allowing smaller organizations to quickly secure work-ready personnel.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1: Data collection

[0142] server

[0143] Input: Employee data for large organizations, employee preference data, company data for small organizations, human resources data

[0144] Specifically, the server collects the necessary data through each company's database and API. The server calls the HR system API of a large organization to obtain employee backgrounds and skill sets, and uses the job information API of a small organization to collect company recruitment requirements.

[0145] Output: Raw employee data, company data, talent data

[0146] Step 2: Data validation and standardization

[0147] server

[0148] Inputs: Raw employee data, company data, talent data

[0149] The server then validates and standardizes the data it receives, preprocessing it to detect and complete missing or incorrect data. Specifically, the server converts employee data from large companies into a standard format based on background, skill set, and working conditions.

[0150] Output: Standardized employee data, company data, and talent data

[0151] Step 3: Register with the database

[0152] server

[0153] Inputs: Standardized employee data, company data, talent data

[0154] The server registers the validated and standardized data in a database, making it easily accessible for subsequent processing. Specifically, the server stores the standardized data in the database with an index.

[0155] Output: Employee data, company data, and human resources data stored in a database

[0156] Step 4: Run the matching algorithm

[0157] server

[0158] Input: Employee data, company data, and human resources data stored in a database

[0159] The server uses an AI algorithm to perform optimal matching based on standardized data. The AI ​​model uses machine learning and deep learning to comprehensively evaluate each employee's skill set, background, and desired conditions. Specifically, the server loads the AI ​​model and provides background, skills, and working conditions as input data. The model's execution results are then analyzed to evaluate and select highly suitable candidates.

[0160] Output: Matching result data

[0161] Step 5: Notification of results

[0162] server

[0163] Input: Matching result data

[0164] The server notifies the matching results to the employees of the large organization and the small organization. The results are summarized in a report format and sent via email or dashboard. Specifically, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be viewed when logged in.

[0165] Output: Notified matching results

[0166] Step 6: Data entry

[0167] Terminal

[0168] Input: Employee data from users, desired data, and data on the personnel required by companies

[0169] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. Specifically, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation. The data is sent to the server and used for subsequent processing.

[0170] Output: Employee data, preference data, and talent data sent to the server

[0171] Step 7: Check the results and arrange an interview

[0172] Terminal

[0173] Input: Notified matching result data

[0174] The matching results are checked on the terminal, and the interview and dispatch contract are arranged. Detailed interview date and time and location can also be set on the terminal. Specifically, the administrator of the small organization logs in from the terminal, checks the details of the matching results, and employee A checks the interview date and time on the terminal and presses the approval button, completing the interview arrangement.

[0175] Output: Confirmed interview date, time and location data

[0176] Example of input prompt for generative AI model

[0177] The following prompts can be used to provide the necessary input to the generative AI model:

[0178] "Please explain in detail the process by which your server collects employee data for a large organization."

[0179] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[0180] (Application example 1)

[0181] 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."

[0182] When seconding senior employees from large companies to small and medium-sized enterprises, there is a problem in matching personnel, as it is difficult to quickly and efficiently find personnel with the appropriate skill sets and experience. Furthermore, the procedures for arranging interviews and signing secondment contracts after matching are complicated, making it difficult for the parties involved to communicate smoothly. Furthermore, there is a problem in that a lack of performance monitoring during the secondment makes it difficult to maximize the benefits of the secondment.

[0183] 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.

[0184] In this invention, the server includes: means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired talent data; means for standardizing the acquired data and registering it in a database; means for matching employees of large companies with small and medium-sized enterprises based on the standardized data; means for notifying employees of large companies and small and medium-sized enterprises of the matching results; and means for matched employees of large companies and managers of small and medium-sized enterprises to arrange interviews and conclude secondment contracts via an application. This enables quick and efficient matching of talent with appropriate skill sets and experience, and smooth subsequent procedures and collaboration. Furthermore, performance monitoring during the secondment maximizes the effectiveness of the secondment.

[0185] A "large company" refers to a company that has a large number of employees and conducts large-scale business activities.

[0186] "Small and medium-sized enterprises" refer to companies that conduct business activities on a relatively small scale and whose number of employees and sales revenue do not meet certain standards.

[0187] "Employee data" refers to data that includes information about an employee's background, skills, working conditions, etc.

[0188] "Employee request data" refers to data regarding employees' desired working style, work location, job content, and other requests.

[0189] "Company data" refers to data that includes basic information about the company, business activities, and the desired personnel requirements.

[0190] "Desired talent data" refers to data such as the skill sets, experience, and working conditions that companies are looking for.

[0191] "Data standardization" refers to the process of converting data stored in different formats into a unified format.

[0192] A "database" is a system for storing and managing data according to certain rules.

[0193] "Matching" refers to the process of connecting suitable candidates with companies based on certain criteria.

[0194] "Notification" refers to the act of conveying information such as matching results to relevant parties.

[0195] "Interview arrangement" refers to the process of arranging the date, time, and location of an interview between the candidate and the company after a match has been made.

[0196] A "secondment contract" refers to a contract under which an employee works for another company for a certain period of time.

[0197] "Application" refers to a software program that a user uses for a specific purpose.

[0198] "Performance monitoring" refers to the act of monitoring and evaluating the work performance of employees on secondment.

[0199] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and operates in cooperation with a server, terminals, and users. The specific mechanism and operation of this system will be described in detail below.

[0200] server

[0201] Data collection

[0202] The server acquires employee data from large companies, employee request data, company data from small and medium-sized enterprises, and desired talent data. This data is collected via the company's database or API. For example, "The server collects employee backgrounds, skills, and desired working arrangements from the large company's database," or "The server collects the desired talent conditions from the small and medium-sized enterprise's database."

[0203] Data Standardization

[0204] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for generative AI models to analyze it. Specifically, the server standardizes employee data from large companies into career history, skill sets, and working conditions, and the server standardizes the human resources data required by small and medium-sized enterprises into experience, skills, and working conditions.

[0205] Executing the matching algorithm

[0206] Based on standardized data, a generative AI model is used to match employees of large companies with small and medium-sized companies. The model makes an optimal match by comprehensively assessing backgrounds, skill sets, and working conditions. For example, "the server uses AI to match the skills required by small and medium-sized companies with the skills of employees at large companies and selects candidates with a high match rate."

[0207] Notification of results

[0208] The matching results are notified to employees of large companies and small and medium-sized enterprises. The results are compiled in a report format and sent via email or dashboard. Specifically, "the server notifies employees and small and medium-sized enterprises of the matching results and sends detailed information by email."

[0209] Interview arrangement and contract

[0210] The matched employees of the large company and the managers of the SMEs then arrange interviews and conclude secondment contracts through the application. For example, "the server arranges interview dates and times between the employees and the SMEs, and provides an interface for concluding secondment contracts."

[0211] Terminal

[0212] Data Entry

[0213] The terminal provides an interface for employees of large corporations and managers of small and medium-sized enterprises to input the necessary information. The input data is sent to a server and used for subsequent processing. For example, "an employee enters their career history and desired qualifications into the terminal and sends it to the server," or "a manager of a small or medium-sized enterprise enters the qualifications of the personnel they are looking for into the terminal and sends it to the server."

[0214] Confirming results and arranging interviews

[0215] The matching results are checked on the terminal, and interviews and secondment contracts are arranged. Specific interview dates, times, and locations are also set on the terminal. For example, "The manager of a small or medium-sized enterprise checks the matching results on the terminal and sets the interview date and time with the employee," or "The employee checks the interview date and time on the terminal and approves it."

[0216] User

[0217] Senior Employees

[0218] Senior employees enter their own information through the terminal and check the matching results. They then undergo an interview and, if approved, begin their secondment to the SME. For example, "senior employees enter their own skill set and desired conditions into the terminal, and check the matching results when they are notified," or "senior employees interview with the SME and formally sign a secondment contract."

[0219] small business manager

[0220] Managers of small and medium-sized enterprises use the terminal to input the desired personnel criteria and check the matching results. They also arrange interviews and process secondment contracts. For example, "Managers of small and medium-sized enterprises input the desired skill set into the terminal and check the matching results" or "Managers of small and medium-sized enterprises arrange interviews with senior employees and conclude secondment contracts."

[0221] Prompt Sentence Examples

[0222] Create a Python function that accesses the API to retrieve employee data from large companies and the talent data required by small and medium-sized enterprises, and perform matching using a generative AI model. Write a script to notify the matching results by email.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] The server collects employee data from large companies, employee requirements data, company data from small and medium-sized companies, and desired talent data via APIs. This involves connecting to corporate databases and external data sources. The input to this process is the API or database query, and the output is the retrieved raw data. Specifically, the server executes the query to extract the relevant data and receives it in JSON format.

[0226] Step 2:

[0227] The server standardizes the data it receives. If the data is stored in a different format, it converts it into a consistent format. The input is the raw data it received, and the output is the standardized data. Specifically, it uses the pandas library to convert the data into a data frame and then converts it to the required schema.

[0228] Step 3:

[0229] The server registers the standardized data in the database. The input of this process is the standardized data, and the output is the data stored in the database. Specifically, the server uses an SQL query to store the data in the database with an INSERT statement.

[0230] Step 4:

[0231] The server uses a generative AI model based on standardized data to match employees of large companies with small and medium-sized enterprises. The input is standardized employee data of large companies and the talent data desired by small and medium-sized enterprises, and the output is the matching results. Specifically, the scikit-learn library is used to analyze the data using algorithms such as nearest neighbor methods to generate optimal matching pairs.

[0232] Step 5:

[0233] The server notifies the matching results. The input of this process is the generated matching results, and the output is sending a notification. Specifically, the server uses the SMTP protocol to send emails to notify each employee and the manager of the small business of the matching results.

[0234] Step 6:

[0235] The terminal provides an interface for employees of large companies and managers of small and medium-sized companies to arrange interviews and sign secondment contracts. The input is a notification of the matching results from the server, and the output is the completion of the interview arrangement or secondment contract. Specifically, the calendar function on the terminal is used to select a date and time, and the arrangement is completed by pressing the confirmation button.

[0236] Step 7:

[0237] Users (senior employees and managers of small and medium-sized enterprises) use the terminal to enter their own information and check the matching results. The input is a notification from the server, and the output is the confirmed information and the completion of the interview and contract. Specifically, senior employees enter their own skill set and desired conditions, and the manager enters the desired skill set. Based on this, the matching results are confirmed and the interview date and time are set.

[0238] 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.

[0239] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[0240] server

[0241] Data collection

[0242] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, small and medium-sized companies, collected via each company's database or API, and then connects with an emotion engine to collect user emotion data.

[0243] Examples:

[0244] "The server collects Employee A's background, skills, and preferred working style from a large company's database. It then uses an emotion engine to obtain Employee A's current emotional state."

[0245] "The server collects the desired personnel requirements from the database of small and medium-sized enterprises. Then, it uses an emotion engine to obtain emotional data on the requests of the managers of small and medium-sized enterprises."

[0246] Data Standardization

[0247] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[0248] Examples:

[0249] "The server standardizes employee data from large corporations into backgrounds, skill sets, desired working conditions, and sentiment data."

[0250] "The server standardizes SMEs' talent needs data into required skills, experience, job title, salary range, and sentiment data."

[0251] Registering in the database

[0252] Standardized data is registered in a database and indexed to enable rapid search and analysis.

[0253] Examples:

[0254] "The server registers the standardized data in a database, storing data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data."

[0255] Executing the matching algorithm

[0256] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies. By taking emotional data into account, more accurate matching becomes possible.

[0257] Examples:

[0258] The server uses AI to match the skills required by the SME with employee A's skills and emotional data, and selects the candidate with a high match rate.

[0259] Notification of results

[0260] The matching results are communicated to employees of large companies and managers of small and medium-sized businesses in a detailed report that includes sentiment data.

[0261] Examples:

[0262] The server notifies Employee A and SME B of the matching results and sends detailed information in a report format via email or dashboard.

[0263] Terminal

[0264] Data Entry

[0265] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input necessary information. Through the emotion engine, it is possible to obtain the user's emotional state in real time.

[0266] Examples:

[0267] "Employee A uses a device to input his / her career history and desired conditions, and records his / her emotional state at that time based on feedback from the emotion engine."

[0268] "Managers of small and medium-sized enterprises input the desired personnel conditions into a terminal, and at the same time, the emotion engine provides the manager's emotional data, which is then sent to the server."

[0269] Confirming results and arranging interviews

[0270] The matching results can be checked on the device, and the interview and secondment contract can be adjusted. By taking emotional data into consideration, the interview date and time and procedures can be flexibly adjusted.

[0271] Examples:

[0272] "The manager of the small and medium-sized enterprise checks the matching results on a terminal and schedules an interview date and time with Employee A based on the emotional data."

[0273] "Employee A checks the interview date and time on their device and approves or changes it based on their emotional state."

[0274] User

[0275] Senior Employees

[0276] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their own emotional state in real time while adjusting their transfer and interview schedules.

[0277] Examples:

[0278] "Senior employee A enters his / her skill set and desired conditions into the terminal, and the emotion engine also records his / her current emotional state."

[0279] "Senior employee A interviews with small and medium-sized company B and proposes the optimal schedule based on emotional data."

[0280] small business manager

[0281] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to efficiently proceed with interviews and secondment contract procedures.

[0282] Examples:

[0283] "The manager of SME B inputs the desired skill set into the terminal and also records his / her own emotional data provided by the emotion engine."

[0284] "Manager of SME B arranges an interview with Senior Employee A and uses the emotional data as a reference when concluding a secondment contract."

[0285] Monitoring and Support

[0286] Server-based emotion monitoring and support

[0287] The system monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[0288] Examples:

[0289] "The server monitors the emotional data of Senior Employee A, who is on loan, in real time, and provides appropriate support if a high stress level is detected."

[0290] As described above, by combining this system with an emotion engine, it is possible to achieve highly accurate matching that takes into account the user's emotional state and to monitor performance during secondment. This allows small and medium-sized enterprises to secure the most suitable personnel, and senior employees of large companies to smoothly perform at their seconded companies.

[0291] The processing flow will be explained below.

[0292] Step 1: Data collection

[0293] The server collects employee data from a large company's database, specifically, information such as employees' career history, skills, qualifications, work experience, desired work style and location, etc. It also obtains the employee's current emotional data via an emotion engine.

[0294] The server collects company data and desired personnel data from the SME database, specifically, basic information about the SME, business activities, desired skill sets, job duties, salary range, working hours, etc. Next, it collects emotion data from SME managers via an emotion engine.

[0295] Step 2: Standardize the data

[0296] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, and sentiment data. By unifying data stored in different formats, subsequent processing becomes easier.

[0297] The server also converts the human resource data required by small and medium-sized enterprises into a standard format, standardizing it into required skills, experience, job title, salary range, working conditions, and emotional data.

[0298] Step 3: Register with the database

[0299] The server registers the standardized data in a database, which then creates an index for rapid search and analysis.

[0300] Data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data are stored in a database, and appropriate tags are added to make it easy to search.

[0301] Step 4: Run the matching algorithm

[0302] The server passes the standardized data to the AI, which runs a matching algorithm that compares the employee's skill set and desired conditions with the skill sets and working conditions required by small and medium-sized enterprises, and also takes emotional data into account to make the optimal match.

[0303] The server reviews the AI ​​results and lists candidates with high suitability.

[0304] Step 5: Notification of results

[0305] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized enterprises, including specific suggestions that take into account the sentiment data.

[0306] The server will send you a notification via email and / or dashboard with detailed match results.

[0307] Step 6: Data entry

[0308] Employees of large companies and managers of small and medium-sized enterprises use terminals to input the necessary information: employees enter their backgrounds, skills, and desired qualifications, and emotional data is also provided based on feedback from the emotion engine.

[0309] Managers of small and medium-sized enterprises also enter the required skill sets and job descriptions on the terminal, and emotional data is also sent to the server.

[0310] Step 7: Check the results and arrange an interview

[0311] The matching results can be checked on the device, and interviews and secondment contracts can be arranged. Interview dates and procedures can be flexibly adjusted based on emotional data.

[0312] Managers of small and medium-sized enterprises review the matching results and decide on interview dates and times with suitable employees. Using an emotion engine, the system suggests optimal schedules based on the emotional state of both parties.

[0313] Senior employees check the interview date and time on their devices and approve or change the date depending on their emotional state.

[0314] Step 8: Interview and decision

[0315] Senior employees act as users, conducting interviews with small and medium-sized enterprises and proposing optimal schedules based on emotional data.

[0316] The small and medium-sized enterprise evaluates the interview results and, taking into consideration the emotional data, decides whether to officially hire the most suitable candidate. A secondment contract is concluded and the details of the contract are registered on the server.

[0317] Step 9: Commencement and monitoring

[0318] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[0319] The server periodically collects performance data from senior employees on loan and uses an emotion engine to monitor their emotional state in real time. If high stress levels or a decline in satisfaction are detected, appropriate support is provided.

[0320] By combining this with an emotion engine, this system achieves highly accurate matching that takes into account the user's emotional state and monitors performance during secondment. This allows small and medium-sized enterprises to secure the best talent, and senior employees of large companies to smoothly perform at their seconded companies.

[0321] Example 2

[0322] 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."

[0323] Conventional matching systems have problems with low matching accuracy and insufficient performance monitoring after transfer when seconding senior employees of large companies to SMEs. Furthermore, they are unable to take into account the emotional state of employees and managers of SMEs, making it difficult to smoothly adjust matching and secondment contracts.

[0324] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee data of large companies, employee request data, data on small and medium-sized organizations, and data on desired human resources, means for acquiring emotion data using an emotion engine, means for analyzing and standardizing the acquired data and emotion data, means for registering the standardized data in a database and creating an index, means for matching employees of large companies with small and medium-sized organizations using a generative AI model based on the standardized data, and means for notifying employees of large companies and small and medium-sized organizations of the matching results and emotion data in the form of a detailed report. This enables high-precision matching based on emotion data and performance monitoring after secondment.

[0325] "Large company employee data" refers to information about employees employed by large companies, including their career history, skill sets, working conditions, etc.

[0326] "Employee request data" refers to data on the working conditions, career paths, work locations, and other requests of employees of large companies.

[0327] "Data on small and medium-sized organizations" refers to information on small and medium-sized enterprises, including the type of industry, business activities, location, size, and so on.

[0328] "Desired talent data" refers to data on the skills, experience, job title, salary range, etc. of the talent that SMEs require.

[0329] An "emotion engine" is a software or hardware system that analyzes a user's emotional state and measures stress levels, satisfaction, motivation, etc.

[0330] "Emotion data" is data relating to the user's emotional state obtained using an emotion engine, and includes indicators such as stress level, happiness level, and concentration level.

[0331] "Generative AI models" refer to algorithms and machine learning models that use artificial intelligence technology to perform data analysis and predictions.

[0332] "Standardization" is the process of converting data of different formats and structures into a uniform form.

[0333] A "database" is a system for storing collected data and making it easy to search and analyze.

[0334] An "index" is a structure for quickly searching data in a database.

[0335] "Matching" refers to comparing collected employee data from large companies with the personnel data required by small and medium-sized enterprises to find the optimal combination.

[0336] "Notification" is the process of sending information such as matching results and emotion data to the user.

[0337] A means of adjusting a "secondment contract" is a method or system for adjusting the contract content and schedule for an employee of a large company to be seconded to a small or medium-sized company.

[0338] "Monitoring" is the process of continuously observing the performance and emotional state of an employee while on secondment.

[0339] "Support" means providing necessary assistance and responses based on the monitoring results.

[0340] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[0341] System Overview

[0342] This system collects and analyzes employee data from large companies and the human resources data required by small and medium-sized enterprises, uses an emotion engine to obtain emotional data, performs highly accurate matching using a generative AI model, and also monitors the emotional state of employees on secondment and provides support as needed.

[0343] Processing performed by the server

[0344] Data collection

[0345] The server first obtains employee data, employee request data, and company data and desired talent data for large companies and SMEs. This data is collected via each company's database or API. It also uses an emotion engine to collect emotion data from employees and SME managers.

[0346] Examples:

[0347] The server collects Employee A's career history, skills, and desired working style from a large company's database, and uses an emotion engine to obtain Employee A's current emotional state.

[0348] The server collects the conditions of the desired personnel from the database of small and medium-sized enterprises, and obtains the emotional data of the managers of the small and medium-sized enterprises using an emotion engine.

[0349] Data Standardization

[0350] The server analyzes the acquired data and converts it into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[0351] Examples:

[0352] A server standardizes employee data from a large corporation into background, skill sets, desired working conditions, and sentiment data.

[0353] The server standardizes the talent data required by small and medium-sized businesses into required skills, experience, job title, salary range, and sentiment data.

[0354] Registering in the database

[0355] The server registers the standardized data in a database and creates an index to enable quick searches and analysis.

[0356] Examples:

[0357] The server registers the standardized data in a database, storing data on employees of large companies, data on the personnel sought by small and medium-sized enterprises, and emotional data.

[0358] Executing the matching algorithm

[0359] The server uses generative AI models based on standardized data to match employees of large companies with small and medium-sized businesses. By taking into account emotional data, it is possible to achieve even more accurate matching.

[0360] Examples:

[0361] The server uses the generated AI model to match the skills required by the SME with Employee A's skills and emotional data, and selects the candidate with a high match rate.

[0362] Notification of results

[0363] The server then sends detailed reports containing matching results and sentiment data to employees of large companies and managers of small and medium-sized enterprises, allowing them to provide appropriate feedback.

[0364] Examples:

[0365] The server notifies Employee A and SME B of the matching results and sends detailed information in report format via email or dashboard.

[0366] Processing performed by the device

[0367] Data Entry

[0368] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input necessary information, and the emotional state of the user can be obtained in real time through an emotion engine.

[0369] Examples:

[0370] Employee A uses a terminal to enter his or her career history and desired conditions, and also records his or her emotional state at that time based on feedback from the emotion engine.

[0371] Managers of small and medium-sized enterprises input the desired personnel conditions into a terminal, and at the same time, the manager's emotional data provided by the emotion engine is also sent to the server.

[0372] Confirming results and arranging interviews

[0373] The matching results can be checked on the device, and the interview and secondment contract can be adjusted. By taking emotional data into consideration, the interview date and time and procedures can be flexibly adjusted.

[0374] Examples:

[0375] The manager of the small or medium-sized enterprise checks the matching results on a terminal and sets the interview date and time with employee A based on the emotional data.

[0376] Employee A checks the interview date and time on a terminal and approves or changes the appointment based on their emotional state.

[0377] User Roles and Actions

[0378] Senior Employees

[0379] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their emotional state in real time, while adjusting schedules for transfers and interviews.

[0380] Examples:

[0381] Senior employee A enters his / her skill set and desired conditions into the terminal, and the emotion engine also records his / her current emotional state.

[0382] Senior employee A interviews with small and medium-sized company B and proposes the optimal schedule based on emotional data.

[0383] small business manager

[0384] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to smoothly proceed with interviews and secondment contract procedures.

[0385] Examples:

[0386] The manager of SME B inputs the desired skill set into the terminal and also records his / her own emotional data provided by the emotion engine.

[0387] A manager at a small or medium-sized company, B, arranges an interview with senior employee A and uses the emotional data as a reference when concluding a secondment contract.

[0388] Emotional monitoring and support

[0389] Server-based emotion monitoring and support

[0390] The server monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[0391] Examples:

[0392] The server monitors the emotional data of senior employee A, who is on secondment, in real time and provides appropriate support if a high stress level is detected.

[0393] As described above, by combining this system with an emotion engine, it is possible to achieve highly accurate matching that takes into account the user's emotional state and to monitor performance during secondment. This allows small and medium-sized enterprises to secure the most suitable personnel, and senior employees of large companies to smoothly perform at their seconded companies.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] Step 1: Data collection

[0396] The server sends an API request to retrieve employee backgrounds, skills, and preferred working arrangements from a large company's database. The input is the employee ID, and the output is the employee data in JSON format.

[0397] The server sends a request to the emotion engine's API to obtain the emotion data of employees and small business managers. The input is text or audio data to be analyzed, and the output is data indicating the emotional state. Specifically, the server sends a "POST / emotion / analyze" request to the emotion engine and analyzes the obtained data.

[0398] Step 2: Standardize the data

[0399] The server converts the acquired employee data of a large company into a standard format. The input is raw employee data, and the output is standardized data. Specifically, the data is divided into fields such as career history, skill set, desired working conditions, and emotional data.

[0400] Example: Employee data for a large company is divided into "work history," "skill set," "desired working conditions," and "emotional data," and then formatted in JSON.

[0401] Step 3: Register with the database

[0402] The server inserts the standardized data into the database and creates an index to improve searchability. The input is the standardized data, and the output is the saved status in the database. Specifically, it executes commands such as "db.employees.insert({ ...})" and "db.employees.createIndex({ skill_set: 1})".

[0403] Step 4: Run the matching algorithm

[0404] The server performs matching using a generative AI model based on standardized data. The input is employee data from large companies and the human resources data required by small and medium-sized enterprises, and the output is the matching results. Specifically, a prompt such as "model.predict({ employee_id: ..., company_id: ...})" is input into the generative AI model to obtain the scoring results.

[0405] Example: "Enter data on employee A and company B into the AI ​​model and select the combination with the highest matching rate."

[0406] Step 5: Notification of results

[0407] The server notifies the matching results to employees of large companies and administrators of small and medium-sized companies. The input is the matching results, and the output is the notification sending status. Specifically, notifications are sent using an email sending API (e.g., SendGrid) or WebSocket. Commands such as "sendMail({ to: ..., subject: ..., content: ...})" or "webSocket.send({ type: 'MATCH_RESULT', data: { ...}})" are executed.

[0408] Step 6: Emotional monitoring and support

[0409] The server monitors the emotional data of senior employees on loan in real time and provides support as needed. The input is a real-time stream of emotional data, and the output is a support action. Specifically, it periodically executes a "GET / emotion / monitor / {employee_id}" request and provides appropriate support if the stress level is high.

[0410] Example: "The server monitors emotional data and suggests counseling services if high stress levels are detected."

[0411] These steps enable the system to perform highly accurate matching that takes into account emotional data and effectively monitor the performance of employees after secondment.

[0412] (Application example 2)

[0413] 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."

[0414] The secondment of senior employees to logistics centers is important for utilizing their experience and skills, but conventional matching systems lack the ability to monitor performance and emotional state at the destination, making it difficult to find the best match and providing insufficient support during the secondment. Furthermore, when senior employees feel stressed or dissatisfied, this information is not collected in a timely manner, which can delay appropriate responses.

[0415] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0416] In this invention, the server includes means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired human resources data, means for standardizing the acquired data and registering it in a database, means for matching employees of large companies with small and medium-sized enterprises based on the standardized data, means for notifying employees of large companies and small and medium-sized enterprises of the matching results, means for utilizing an emotion engine that collects employee emotional states in real time, and means for monitoring the emotional states of employees on secondment and providing necessary support. This improves the accuracy of matching senior employees at logistics centers with their secondment destinations, making it possible to monitor the emotional states of employees on secondment and provide appropriate support.

[0417] "Employee data of large companies" refers to information such as the work history, skills, and desired working conditions of employees of large companies.

[0418] "Employee request data" refers to information regarding employees' desired working style, salary, job content, and other requests.

[0419] "Company data for small and medium-sized enterprises" refers to basic information about small and medium-sized enterprises, such as industry, number of employees, and work location.

[0420] "Desired talent data" refers to information such as the skills, experience, job title, and salary range required by SMEs for the talent they are recruiting.

[0421] "Data standardization" refers to the process of converting data acquired in different formats into a unified format.

[0422] "Registering in a database" refers to storing standardized data and making it possible to quickly search and analyze it.

[0423] "Matching" refers to using AI and algorithms to match employees of large companies with the human resource requirements of small and medium-sized enterprises to find the most suitable combination.

[0424] An "emotion engine" refers to a technology or system that collects and analyzes a user's emotional state in real time.

[0425] "Emotional state monitoring" refers to observing changes in employees' emotions in real time and obtaining information such as stress levels and satisfaction.

[0426] "Providing necessary support" refers to providing expert counseling tailored to the individual's emotional state and arranging appropriate resources.

[0427] This invention is a system for seconding senior employees of large companies to logistics centers of small and medium-sized enterprises, and in particular, by combining it with an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[0428] server

[0429] The server performs the following process:

[0430] Data collection and input

[0431] The server first collects employee data from large companies, employee request data, company data from small and medium-sized companies, and desired talent data. This data is collected via each company's database or API. It also works with an emotion engine to collect user emotion data. The collected data is standardized and registered in a database.

[0432] Examples:

[0433] Obtain the work history, skills, desired working conditions, and current emotional state of employee A of a large company using an emotion engine.

[0434] Obtain the personnel requirements and emotional data required by small and medium-sized enterprises.

[0435] Data Standardization and Matching

[0436] The acquired data is analyzed and converted into a standard format. The standardized data is registered in a database, and AI is used to match employees of large companies with small and medium-sized enterprises. By taking emotional data into account, even more accurate matching becomes possible.

[0437] Examples:

[0438] The system compares the skill requirements, experience, and sentiment data of employee A of a large company with employee B of a small or medium-sized company, and performs a highly accurate match.

[0439] Notification of results

[0440] The matching results are communicated to employees of large companies and small and medium-sized enterprises, and detailed reports including sentiment data are provided.

[0441] Terminal

[0442] The terminal performs the following process:

[0443] Data entry and confirmation

[0444] It provides an interface for employees of large companies and managers of small and medium-sized enterprises to input the necessary information. Through an emotion engine, it is possible to obtain the user's emotional state in real time. Matching results and information for interview arrangements are also notified in real time.

[0445] Examples:

[0446] Employee A uses a terminal to input and confirm his / her skills, desired conditions, and emotional state.

[0447] Managers of small and medium-sized enterprises enter the desired personnel requirements into a terminal, and emotional data generated by an emotion engine is also sent to the server.

[0448] User

[0449] The user performs the following process.

[0450] Response from senior employees

[0451] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their own emotional state in real time while adjusting their transfer and interview schedules.

[0452] Examples:

[0453] Senior employee A inputs his / her skill set and desired conditions, and the emotion engine records his / her current emotional state.

[0454] How small business managers respond

[0455] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to efficiently proceed with interviews and secondment contract procedures.

[0456] Examples:

[0457] The manager of SME B inputs the desired skill set and emotional data, arranges an interview with senior employee A, and uses the emotional data as a reference when concluding a secondment contract.

[0458] Monitoring and Support

[0459] Server-based emotion monitoring and support

[0460] The system monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[0461] Examples:

[0462] The server monitors the emotional data of senior employee A, who is on secondment, in real time and provides appropriate support if a high stress level is detected.

[0463] Applications of generative AI models

[0464] Example prompt sentence:

[0465] "Recommend the best distribution center for Senior Employee A based on the following criteria:

[0466] Skill Set: IT Support, Data Analysis

[0467] Desired working conditions: Full-time, working from home

[0468] Emotional data: Medium stress level, high satisfaction

[0469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0470] Step 1:

[0471] The server obtains employee data from large companies, employee request data, company data from small and medium-sized companies, and desired talent data. This data is collected via each company's database or API. It uses each company's database access information and API key as input, and obtains data in a standardizable format as output.

[0472] Step 2:

[0473] The server standardizes the acquired data. Specifically, it converts data stored in different formats into a unified format (for example, JSON or CSV). It uses information about each company's data format as input and obtains data in a unified format as output. For example, it can classify employee skill sets into unified categories.

[0474] Step 3:

[0475] The server registers the standardized data in a database, indexes it, and makes it available for rapid searching and analysis. It uses the standardized data as input and gets indexed database entries as output.

[0476] Step 4:

[0477] The server uses the emotion engine to collect the user's emotion data, for example, obtains the user's emotional state in real time through the emotion engine API. It uses the user's real-time data and API key as input and obtains the emotion data as output.

[0478] Step 5:

[0479] The server runs a matching algorithm based on the standardized data and emotional data. It uses AI to match employees of large companies with small and medium-sized companies. It uses the standardized data and emotional data as input and obtains the optimal matching result as output.

[0480] Step 6:

[0481] The server notifies employees of large companies and small and medium-sized businesses of the matching results, providing them as detailed reports including emotional data. The server uses the matching result data as input and obtains notification messages and reports as output.

[0482] Step 7:

[0483] The terminal provides an interface for employees of large corporations and managers of small and medium-sized enterprises to input the necessary information. Through an emotion engine, it is also possible to obtain the user's emotional state in real time. It uses the information entered by the user as input and obtains data in a standard format as output to be sent to the server.

[0484] Step 8:

[0485] The terminal notifies the user of the matching results and information for interview arrangement in real time. It uses notification data from the server as input and obtains notification messages for the user as output.

[0486] Step 9:

[0487] The user adjusts the schedule for a transfer or interview while understanding their own emotional state in real time using the emotion engine. The emotion engine data is used as input, and appropriate schedule adjustment proposals are obtained as output.

[0488] Step 10:

[0489] The server monitors the emotional state of the senior employee on secondment and provides necessary support based on that. It uses real-time emotional data as input and gets support response suggestions and resource allocation plans as output.

[0490] Example prompt sentence:

[0491] "Recommend the best distribution center for senior employees based on the following criteria:

[0492] Skill Set: IT Support, Data Analysis

[0493] Desired working conditions: Full-time, working from home

[0494] Emotional data: Medium stress level, high satisfaction

[0495] 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.

[0496] 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.

[0497] 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.

[0498] [Second embodiment]

[0499] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0500] 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.

[0501] 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).

[0502] 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.

[0503] 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.

[0504] 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).

[0505] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0506] 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.

[0507] 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.

[0508] 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.

[0509] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0510] 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."

[0511] The present invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and specifically operates through the collaboration of a server, terminals, and users. The mechanism and specific operation of the system will be described in detail below.

[0512] server

[0513] Data collection

[0514] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, collected via each company's database or API.

[0515] Examples:

[0516] "The server collects employee A's background, skills, and preferred working arrangements from a large company's database."

[0517] "The server collects the desired personnel requirements from a database of small and medium-sized enterprises."

[0518] Data Standardization

[0519] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[0520] Examples:

[0521] "The server standardizes employee data for large corporations into backgrounds, skill sets, and working conditions."

[0522] "The server standardizes the personnel data required by small and medium-sized enterprises into experience, skills, and working conditions."

[0523] Executing the matching algorithm

[0524] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies, taking into account their career history, skill set, and working conditions to make the best possible match.

[0525] Examples:

[0526] "The server uses AI to compare the skills required by small and medium-sized company B with the skills of employee A of large company, and selects the candidate with the highest match rate."

[0527] Notification of results

[0528] The matching results are communicated to employees of large companies and small and medium-sized enterprises, and the results are summarized in a report and sent via email and dashboard.

[0529] Examples:

[0530] The server notifies Employee A and Small Business B of the matching results and sends detailed information by email.

[0531] Terminal

[0532] Data Entry

[0533] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input the necessary information, which is then sent to a server for further processing.

[0534] Examples:

[0535] "Employee A enters his / her career history and desired conditions into the terminal and sends it to the server."

[0536] "Managers of small and medium-sized enterprises input the personnel requirements into a terminal and send them to a server."

[0537] Confirming results and arranging interviews

[0538] The matching results are checked on the terminal, and interviews and transfer contracts are arranged. Specific interview dates, times, and locations are also set on the terminal.

[0539] Examples:

[0540] "The manager of the small and medium-sized enterprise checks the matching results on the terminal and schedules an interview date and time with Employee A."

[0541] "Employee A checks the interview date and time on the terminal and approves it."

[0542] User

[0543] Senior Employees

[0544] Senior employees enter their information through a terminal, check the matching results, and then undergo an interview. If approved, they will begin their secondment to a small or medium-sized company.

[0545] Examples:

[0546] "Senior employee A enters his / her skill set and desired conditions into the terminal, and confirms the matching results when they are notified."

[0547] "Senior employee A interviews with small and medium-sized company B and officially signs a secondment contract."

[0548] small business manager

[0549] Managers of small and medium-sized enterprises can input the desired personnel requirements through the terminal, check the matching results, and also arrange interviews and process transfer contracts.

[0550] Examples:

[0551] "Enter the skill set desired by the manager of SME B into the terminal and check the matching results."

[0552] "Manager of SME B arranges an interview with Senior Employee A and concludes a secondment contract."

[0553] This system allows small and medium-sized enterprises to quickly and efficiently secure work-ready personnel, while large companies can effectively utilize the skills of senior employees, providing significant benefits to both parties.

[0554] The processing flow will be explained below.

[0555] Step 1: Data collection

[0556] The server collects employee data from the database of a large company, specifically information such as employee background, skills, qualifications, work experience, preferred work arrangements and locations.

[0557] The server collects company data and desired personnel data from a database of small and medium-sized enterprises, specifically, basic information about the company, business details, desired skill sets, job details, salary range, working hours, etc.

[0558] Step 2: Standardize the data

[0559] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, etc. By organizing data stored in different formats into a unified format, subsequent processing becomes easier.

[0560] The server also converts the human resources data required by small and medium-sized enterprises into a standard format, standardizing the required skills, experience, job title, salary range, working conditions, etc.

[0561] Step 3: Register with the database

[0562] The server registers the standardized data in a database, creating an index that enables rapid data search and AI analysis.

[0563] Data on employees of large companies and the personnel data required by small and medium-sized enterprises is stored in a database, and appropriate tags are added to make it easy to search.

[0564] Step 4: Run the matching algorithm

[0565] The server passes the standardized data from the database to the AI, which runs a matching algorithm to match the employee's skill set and desired conditions with the skill sets and working conditions required by the small and medium-sized enterprise, and finds the best match.

[0566] The server reviews the AI ​​results and lists the most relevant matches.

[0567] Step 5: Notification of results

[0568] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized companies by sending the results via email or an online dashboard.

[0569] The server will send a notification with detailed information about the match, including contact information.

[0570] Step 6: Data entry

[0571] Using the terminals, employees of large companies and managers of small and medium-sized enterprises input the necessary information. Employees input their career history, skills, and desired conditions, while managers of small and medium-sized enterprises input the desired skill sets and job content.

[0572] The entered data is sent to the server in real time and used for subsequent processing.

[0573] Step 7: Check the results and arrange an interview

[0574] The matching results are checked on the terminal and the interview and secondment contract are arranged. The manager of the SME checks the detailed information of the matched senior employee and sets the interview date and time.

[0575] Senior employees check the interview date and time on the terminal and make any changes or approvals as necessary.

[0576] Step 8: Interview and decision

[0577] The senior employee as the user will have an interview with the SME. As a result of the interview, the SME will decide whether to officially hire the senior employee who wishes to be seconded.

[0578] A small or medium-sized enterprise enters into a secondment contract and registers the contract details on a server.

[0579] Step 9: Commencement and monitoring

[0580] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[0581] Regularly collect and monitor performance data from senior staff on secondment and provide any support required.

[0582] As a result, this system will alleviate the labor shortages of small and medium-sized enterprises and effectively utilize the experience and skills of senior employees at large companies, providing a mutually beneficial solution.

[0583] Example 1

[0584] 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."

[0585] In recent years, there has been a demand for increased mobility of human resources between large and small organizations. However, many large organizations have limited opportunities to effectively utilize the skills of senior employees, while small organizations have difficulty securing human resources who can immediately contribute. To solve these issues, a system is needed that accurately matches the needs of both parties and quickly and efficiently dispatches human resources.

[0586] 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.

[0587] In this invention, the server includes means for acquiring employee information of the large organization, employee preference information, company information of the small organization, and necessary human resources information, means for verifying and standardizing the acquired data and registering it in a database, means for executing an artificial intelligence model to match employees of the large organization with small organizations based on the standardized data, and means for notifying employees of the large organization and the small organization of the matching results, thereby enabling senior employees of the large organization to be dispatched to the small organization quickly and efficiently.

[0588] A "large organization" is a company with a large number of employees and multiple business divisions and processes.

[0589] "Employee Information" means data related to an employee, such as an employee's background, skill set, job title, work history, and evaluation information.

[0590] "Employee preference information" refers to data that indicates an employee's individual preferences and conditions, such as desired working style, work location, job content, and working hours.

[0591] A "small organization" is a business or organization with a small number of employees and limited resources.

[0592] "Company information" refers to general information related to a company, such as the company's size, industry, location, business activities, and the type of personnel it is seeking.

[0593] "Required human resources information" refers to data that indicates the specific job requirements, such as the skill set, experience, qualifications, and working conditions that a company is looking for.

[0594] "Means of acquisition" refers to the methods and processes for obtaining the required data through a database or API.

[0595] "Validation and standardization" refers to the process of converting data stored in different formats into a unified format to ensure data consistency and accuracy.

[0596] A "database" refers to a system for efficiently storing, managing, and searching large amounts of data.

[0597] An "artificial intelligence model" refers to an algorithm that uses machine learning or deep learning to analyze data and perform a specific task (in this case, matching).

[0598] "Matching" refers to the process of finding the right match based on specific criteria, which in this case means matching employees from larger organizations with smaller organizations.

[0599] "Means of notification" refers to the method by which matching results are communicated to relevant parties, such as through email, dashboards, notification systems, etc.

[0600] The present invention is a system for dispatching senior employees of a large organization to a small organization, and specifically, a mechanism in which a server, a terminal, and a user work together. Specific embodiments of the system are described in detail below.

[0601] First, the server collects employee information and preference information from large organizations, company information from small organizations, and necessary human resources information. This data is obtained via each company's database or API. For example, the server calls the large organization's HR system API to obtain employee backgrounds and skill sets, and uses the small organization's job information API to collect company recruitment requirements.

[0602] The server validates and standardizes the collected data, which is often stored in different formats. Standardizing the data into a specific format facilitates subsequent analysis. For example, the server converts employee data from a large organization into a standard format based on background, skill set, and working conditions.

[0603] Next, the server uses this standardized data to match employees from large organizations with smaller organizations using an artificial intelligence model. The AI ​​model is an algorithm that incorporates machine learning and deep learning, and comprehensively evaluates each employee's skill set, background, and desired conditions to make the optimal match. For example, the server loads the AI ​​model, provides background, skills, and working conditions as input data, analyzes the model's execution results, and selects highly suitable candidates.

[0604] The server notifies the employees of the large organization and the small organization of the matching results. The results are summarized in a report format and sent via email or dashboard. For example, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be displayed when logged in.

[0605] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. The entered data is then sent to a server and used in subsequent processes. For example, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation.

[0606] The device also provides an interface for checking matching results and arranging interviews and temporary employment contracts. Specific interview dates, times, and locations can also be set on the device. For example, an administrator at a small organization can log in from the device and check the details of the matching results, and employee A can then check the interview date and time on the device and press the approval button to complete the interview arrangement.

[0607] Example of input prompt for generative AI model

[0608] The following prompts can be used to provide the necessary input to the generative AI model:

[0609] "Please explain in detail the process by which your server collects employee data for a large organization."

[0610] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[0611] This system allows senior employees of large organizations to be quickly and efficiently dispatched to smaller organizations, making effective use of their skills, while at the same time allowing smaller organizations to quickly secure work-ready personnel.

[0612] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0613] Step 1: Data collection

[0614] server

[0615] Input: Employee data for large organizations, employee preference data, company data for small organizations, human resources data

[0616] Specifically, the server collects the necessary data through each company's database and API. The server calls the HR system API of a large organization to obtain employee backgrounds and skill sets, and uses the job information API of a small organization to collect company recruitment requirements.

[0617] Output: Raw employee data, company data, talent data

[0618] Step 2: Data validation and standardization

[0619] server

[0620] Inputs: Raw employee data, company data, talent data

[0621] The server then validates and standardizes the data it receives, preprocessing it to detect and complete missing or incorrect data. Specifically, the server converts employee data from large companies into a standard format based on background, skill set, and working conditions.

[0622] Output: Standardized employee data, company data, and talent data

[0623] Step 3: Register with the database

[0624] server

[0625] Inputs: Standardized employee data, company data, talent data

[0626] The server registers the validated and standardized data in a database, making it easily accessible for subsequent processing. Specifically, the server stores the standardized data in the database with an index.

[0627] Output: Employee data, company data, and human resources data stored in a database

[0628] Step 4: Run the matching algorithm

[0629] server

[0630] Input: Employee data, company data, and human resources data stored in a database

[0631] The server uses an AI algorithm to perform optimal matching based on standardized data. The AI ​​model uses machine learning and deep learning to comprehensively evaluate each employee's skill set, background, and desired conditions. Specifically, the server loads the AI ​​model and provides background, skills, and working conditions as input data. The model's execution results are then analyzed to evaluate and select highly suitable candidates.

[0632] Output: Matching result data

[0633] Step 5: Notification of results

[0634] server

[0635] Input: Matching result data

[0636] The server notifies the matching results to the employees of the large organization and the small organization. The results are summarized in a report format and sent via email or dashboard. Specifically, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be viewed when logged in.

[0637] Output: Notified matching results

[0638] Step 6: Data entry

[0639] Terminal

[0640] Input: Employee data from users, desired data, and data on the personnel required by companies

[0641] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. Specifically, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation. The data is sent to the server and used for subsequent processing.

[0642] Output: Employee data, preference data, and talent data sent to the server

[0643] Step 7: Check the results and arrange an interview

[0644] Terminal

[0645] Input: Notified matching result data

[0646] The matching results are checked on the terminal, and the interview and dispatch contract are arranged. Detailed interview date and time and location can also be set on the terminal. Specifically, the administrator of the small organization logs in from the terminal, checks the details of the matching results, and employee A checks the interview date and time on the terminal and presses the approval button, completing the interview arrangement.

[0647] Output: Confirmed interview date, time and location data

[0648] Example of input prompt for generative AI model

[0649] The following prompts can be used to provide the necessary input to the generative AI model:

[0650] "Please explain in detail the process by which your server collects employee data for a large organization."

[0651] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[0652] (Application example 1)

[0653] 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."

[0654] When seconding senior employees from large companies to small and medium-sized enterprises, there is a problem in matching personnel, as it is difficult to quickly and efficiently find personnel with the appropriate skill sets and experience. Furthermore, the procedures for arranging interviews and signing secondment contracts after matching are complicated, making it difficult for the parties involved to communicate smoothly. Furthermore, there is a problem in that a lack of performance monitoring during the secondment makes it difficult to maximize the benefits of the secondment.

[0655] 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.

[0656] In this invention, the server includes: means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired talent data; means for standardizing the acquired data and registering it in a database; means for matching employees of large companies with small and medium-sized enterprises based on the standardized data; means for notifying employees of large companies and small and medium-sized enterprises of the matching results; and means for matched employees of large companies and managers of small and medium-sized enterprises to arrange interviews and conclude secondment contracts via an application. This enables quick and efficient matching of talent with appropriate skill sets and experience, and smooth subsequent procedures and collaboration. Furthermore, performance monitoring during the secondment maximizes the effectiveness of the secondment.

[0657] A "large company" refers to a company that has a large number of employees and conducts large-scale business activities.

[0658] "Small and medium-sized enterprises" refer to companies that conduct business activities on a relatively small scale and whose number of employees and sales revenue do not meet certain standards.

[0659] "Employee data" refers to data that includes information about an employee's background, skills, working conditions, etc.

[0660] "Employee request data" refers to data regarding employees' desired working style, work location, job content, and other requests.

[0661] "Company data" refers to data that includes basic information about the company, business activities, and the desired personnel requirements.

[0662] "Desired talent data" refers to data such as the skill sets, experience, and working conditions that companies are looking for.

[0663] "Data standardization" refers to the process of converting data stored in different formats into a unified format.

[0664] A "database" is a system for storing and managing data according to certain rules.

[0665] "Matching" refers to the process of connecting suitable candidates with companies based on certain criteria.

[0666] "Notification" refers to the act of conveying information such as matching results to relevant parties.

[0667] "Interview arrangement" refers to the process of arranging the date, time, and location of an interview between the candidate and the company after a match has been made.

[0668] A "secondment contract" refers to a contract under which an employee works for another company for a certain period of time.

[0669] "Application" refers to a software program that a user uses for a specific purpose.

[0670] "Performance monitoring" refers to the act of monitoring and evaluating the work performance of employees on secondment.

[0671] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and operates in cooperation with a server, terminals, and users. The specific mechanism and operation of this system will be described in detail below.

[0672] server

[0673] Data collection

[0674] The server acquires employee data from large companies, employee request data, company data from small and medium-sized enterprises, and desired talent data. This data is collected via the company's database or API. For example, "The server collects employee backgrounds, skills, and desired working arrangements from the large company's database," or "The server collects the desired talent conditions from the small and medium-sized enterprise's database."

[0675] Data Standardization

[0676] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for generative AI models to analyze it. Specifically, the server standardizes employee data from large companies into career history, skill sets, and working conditions, and the server standardizes the human resources data required by small and medium-sized enterprises into experience, skills, and working conditions.

[0677] Executing the matching algorithm

[0678] Based on standardized data, a generative AI model is used to match employees of large companies with small and medium-sized companies. The model makes an optimal match by comprehensively assessing backgrounds, skill sets, and working conditions. For example, "the server uses AI to match the skills required by small and medium-sized companies with the skills of employees at large companies and selects candidates with a high match rate."

[0679] Notification of results

[0680] The matching results are notified to employees of large companies and small and medium-sized enterprises. The results are compiled in a report format and sent via email or dashboard. Specifically, "the server notifies employees and small and medium-sized enterprises of the matching results and sends detailed information by email."

[0681] Interview arrangement and contract

[0682] The matched employees of the large company and the managers of the SMEs then arrange interviews and conclude secondment contracts through the application. For example, "the server arranges interview dates and times between the employees and the SMEs, and provides an interface for concluding secondment contracts."

[0683] Terminal

[0684] Data Entry

[0685] The terminal provides an interface for employees of large corporations and managers of small and medium-sized enterprises to input the necessary information. The input data is sent to a server and used for subsequent processing. For example, "an employee enters their career history and desired qualifications into the terminal and sends it to the server," or "a manager of a small or medium-sized enterprise enters the qualifications of the personnel they are looking for into the terminal and sends it to the server."

[0686] Confirming results and arranging interviews

[0687] The matching results are checked on the terminal, and interviews and secondment contracts are arranged. Specific interview dates, times, and locations are also set on the terminal. For example, "The manager of a small or medium-sized enterprise checks the matching results on the terminal and sets the interview date and time with the employee," or "The employee checks the interview date and time on the terminal and approves it."

[0688] User

[0689] Senior Employees

[0690] Senior employees enter their own information through the terminal and check the matching results. They then undergo an interview and, if approved, begin their secondment to the SME. For example, "senior employees enter their own skill set and desired conditions into the terminal, and check the matching results when they are notified," or "senior employees interview with the SME and formally sign a secondment contract."

[0691] small business manager

[0692] Managers of small and medium-sized enterprises use the terminal to input the desired personnel criteria and check the matching results. They also arrange interviews and process secondment contracts. For example, "Managers of small and medium-sized enterprises input the desired skill set into the terminal and check the matching results" or "Managers of small and medium-sized enterprises arrange interviews with senior employees and conclude secondment contracts."

[0693] Prompt Sentence Examples

[0694] Create a Python function that accesses the API to retrieve employee data from large companies and the talent data required by small and medium-sized enterprises, and perform matching using a generative AI model. Write a script to notify the matching results by email.

[0695] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0696] Step 1:

[0697] The server collects employee data from large companies, employee requirements data, company data from small and medium-sized companies, and desired talent data via APIs. This involves connecting to corporate databases and external data sources. The input to this process is the API or database query, and the output is the retrieved raw data. Specifically, the server executes the query to extract the relevant data and receives it in JSON format.

[0698] Step 2:

[0699] The server standardizes the data it receives. If the data is stored in a different format, it converts it into a consistent format. The input is the raw data it received, and the output is the standardized data. Specifically, it uses the pandas library to convert the data into a data frame and then converts it to the required schema.

[0700] Step 3:

[0701] The server registers the standardized data in the database. The input of this process is the standardized data, and the output is the data stored in the database. Specifically, the server uses an SQL query to store the data in the database with an INSERT statement.

[0702] Step 4:

[0703] The server uses a generative AI model based on standardized data to match employees of large companies with small and medium-sized enterprises. The input is standardized employee data of large companies and the talent data desired by small and medium-sized enterprises, and the output is the matching results. Specifically, the scikit-learn library is used to analyze the data using algorithms such as nearest neighbor methods to generate optimal matching pairs.

[0704] Step 5:

[0705] The server notifies the matching results. The input of this process is the generated matching results, and the output is sending a notification. Specifically, the server uses the SMTP protocol to send emails to notify each employee and the manager of the small business of the matching results.

[0706] Step 6:

[0707] The terminal provides an interface for employees of large companies and managers of small and medium-sized companies to arrange interviews and sign secondment contracts. The input is a notification of the matching results from the server, and the output is the completion of the interview arrangement or secondment contract. Specifically, the calendar function on the terminal is used to select a date and time, and the arrangement is completed by pressing the confirmation button.

[0708] Step 7:

[0709] Users (senior employees and managers of small and medium-sized enterprises) use the terminal to enter their own information and check the matching results. The input is a notification from the server, and the output is the confirmed information and the completion of the interview and contract. Specifically, senior employees enter their own skill set and desired conditions, and the manager enters the desired skill set. Based on this, the matching results are confirmed and the interview date and time are set.

[0710] 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.

[0711] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[0712] server

[0713] Data collection

[0714] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, small and medium-sized companies, collected via each company's database or API, and then connects with an emotion engine to collect user emotion data.

[0715] Examples:

[0716] "The server collects Employee A's background, skills, and preferred working style from a large company's database. It then uses an emotion engine to obtain Employee A's current emotional state."

[0717] "The server collects the desired personnel requirements from the database of small and medium-sized enterprises. Then, it uses an emotion engine to obtain emotional data on the requests of the managers of small and medium-sized enterprises."

[0718] Data Standardization

[0719] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[0720] Examples:

[0721] "The server standardizes employee data from large corporations into backgrounds, skill sets, desired working conditions, and sentiment data."

[0722] "The server standardizes SMEs' talent needs data into required skills, experience, job title, salary range, and sentiment data."

[0723] Registering in the database

[0724] Standardized data is registered in a database and indexed to enable rapid search and analysis.

[0725] Examples:

[0726] "The server registers the standardized data in a database, storing data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data."

[0727] Executing the matching algorithm

[0728] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies. By taking emotional data into account, more accurate matching becomes possible.

[0729] Examples:

[0730] The server uses AI to match the skills required by the SME with employee A's skills and emotional data, and selects the candidate with a high match rate.

[0731] Notification of results

[0732] The matching results are communicated to employees of large companies and managers of small and medium-sized businesses in a detailed report that includes sentiment data.

[0733] Examples:

[0734] The server notifies Employee A and SME B of the matching results and sends detailed information in a report format via email or dashboard.

[0735] Terminal

[0736] Data Entry

[0737] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input necessary information. Through the emotion engine, it is possible to obtain the user's emotional state in real time.

[0738] Examples:

[0739] "Employee A uses a device to input his / her career history and desired conditions, and records his / her emotional state at that time based on feedback from the emotion engine."

[0740] "Managers of small and medium-sized enterprises input the desired personnel conditions into a terminal, and at the same time, the emotion engine provides the manager's emotional data, which is then sent to the server."

[0741] Confirming results and arranging interviews

[0742] The matching results can be checked on the device, and the interview and secondment contract can be adjusted. By taking emotional data into consideration, the interview date and time and procedures can be flexibly adjusted.

[0743] Examples:

[0744] "The manager of the small and medium-sized enterprise checks the matching results on a terminal and schedules an interview date and time with Employee A based on the emotional data."

[0745] "Employee A checks the interview date and time on their device and approves or changes it based on their emotional state."

[0746] User

[0747] Senior Employees

[0748] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their own emotional state in real time while adjusting their transfer and interview schedules.

[0749] Examples:

[0750] "Senior employee A enters his / her skill set and desired conditions into the terminal, and the emotion engine also records his / her current emotional state."

[0751] "Senior employee A interviews with small and medium-sized company B and proposes the optimal schedule based on emotional data."

[0752] small business manager

[0753] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to efficiently proceed with interviews and secondment contract procedures.

[0754] Examples:

[0755] "The manager of SME B inputs the desired skill set into the terminal and also records his / her own emotional data provided by the emotion engine."

[0756] "Manager of SME B arranges an interview with Senior Employee A and uses the emotional data as a reference when concluding a secondment contract."

[0757] Monitoring and Support

[0758] Server-based emotion monitoring and support

[0759] The system monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[0760] Examples:

[0761] "The server monitors the emotional data of Senior Employee A, who is on loan, in real time, and provides appropriate support if a high stress level is detected."

[0762] As described above, by combining this system with an emotion engine, it is possible to achieve highly accurate matching that takes into account the user's emotional state and to monitor performance during secondment. This allows small and medium-sized enterprises to secure the most suitable personnel, and senior employees of large companies to smoothly perform at their seconded companies.

[0763] The processing flow will be explained below.

[0764] Step 1: Data collection

[0765] The server collects employee data from a large company's database, specifically, information such as employees' career history, skills, qualifications, work experience, desired work style and location, etc. It also obtains the employee's current emotional data via an emotion engine.

[0766] The server collects company data and desired personnel data from the SME database, specifically, basic information about the SME, business activities, desired skill sets, job duties, salary range, working hours, etc. Next, it collects emotion data from SME managers via an emotion engine.

[0767] Step 2: Standardize the data

[0768] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, and sentiment data. By unifying data stored in different formats, subsequent processing becomes easier.

[0769] The server also converts the human resource data required by small and medium-sized enterprises into a standard format, standardizing it into required skills, experience, job title, salary range, working conditions, and emotional data.

[0770] Step 3: Register with the database

[0771] The server registers the standardized data in a database, which then creates an index for rapid search and analysis.

[0772] Data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data are stored in a database, and appropriate tags are added to make it easy to search.

[0773] Step 4: Run the matching algorithm

[0774] The server passes the standardized data to the AI, which runs a matching algorithm that compares the employee's skill set and desired conditions with the skill sets and working conditions required by small and medium-sized enterprises, and also takes emotional data into account to make the optimal match.

[0775] The server reviews the AI ​​results and lists candidates with high suitability.

[0776] Step 5: Notification of results

[0777] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized enterprises, including specific suggestions that take into account the sentiment data.

[0778] The server will send you a notification via email and / or dashboard with detailed match results.

[0779] Step 6: Data entry

[0780] Employees of large companies and managers of small and medium-sized enterprises use terminals to input the necessary information: employees enter their backgrounds, skills, and desired qualifications, and emotional data is also provided based on feedback from the emotion engine.

[0781] Managers of small and medium-sized enterprises also enter the required skill sets and job descriptions on the terminal, and emotional data is also sent to the server.

[0782] Step 7: Check the results and arrange an interview

[0783] The matching results can be checked on the device, and interviews and secondment contracts can be arranged. Interview dates and procedures can be flexibly adjusted based on emotional data.

[0784] Managers of small and medium-sized enterprises review the matching results and decide on interview dates and times with suitable employees. Using an emotion engine, the system suggests optimal schedules based on the emotional state of both parties.

[0785] Senior employees check the interview date and time on their devices and approve or change the date depending on their emotional state.

[0786] Step 8: Interview and decision

[0787] Senior employees act as users, conducting interviews with small and medium-sized enterprises and proposing optimal schedules based on emotional data.

[0788] The small and medium-sized enterprise evaluates the interview results and, taking into consideration the emotional data, decides whether to officially hire the most suitable candidate. A secondment contract is concluded and the details of the contract are registered on the server.

[0789] Step 9: Commencement and monitoring

[0790] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[0791] The server periodically collects performance data from senior employees on loan and uses an emotion engine to monitor their emotional state in real time. If high stress levels or a decline in satisfaction are detected, appropriate support is provided.

[0792] By combining this with an emotion engine, this system achieves highly accurate matching that takes into account the user's emotional state and monitors performance during secondment. This allows small and medium-sized enterprises to secure the best talent, and senior employees of large companies to smoothly perform at their seconded companies.

[0793] Example 2

[0794] 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."

[0795] Conventional matching systems have problems with low matching accuracy and insufficient performance monitoring after transfer when seconding senior employees of large companies to SMEs. Furthermore, they are unable to take into account the emotional state of employees and managers of SMEs, making it difficult to smoothly adjust matching and secondment contracts.

[0796] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee data of large companies, employee request data, data on small and medium-sized organizations, and data on desired human resources, means for acquiring emotion data using an emotion engine, means for analyzing and standardizing the acquired data and emotion data, means for registering the standardized data in a database and creating an index, means for matching employees of large companies with small and medium-sized organizations using a generative AI model based on the standardized data, and means for notifying employees of large companies and small and medium-sized organizations of the matching results and emotion data in the form of a detailed report. This enables high-precision matching based on emotion data and performance monitoring after secondment.

[0797] "Large company employee data" refers to information about employees employed by large companies, including their career history, skill sets, working conditions, etc.

[0798] "Employee request data" refers to data on the working conditions, career paths, work locations, and other requests of employees of large companies.

[0799] "Data on small and medium-sized organizations" refers to information on small and medium-sized enterprises, including the type of industry, business activities, location, size, and so on.

[0800] "Desired talent data" refers to data on the skills, experience, job title, salary range, etc. of the talent that SMEs require.

[0801] An "emotion engine" is a software or hardware system that analyzes a user's emotional state and measures stress levels, satisfaction, motivation, etc.

[0802] "Emotion data" is data relating to the user's emotional state obtained using an emotion engine, and includes indicators such as stress level, happiness level, and concentration level.

[0803] "Generative AI models" refer to algorithms and machine learning models that use artificial intelligence technology to perform data analysis and predictions.

[0804] "Standardization" is the process of converting data of different formats and structures into a uniform form.

[0805] A "database" is a system for storing collected data and making it easy to search and analyze.

[0806] An "index" is a structure for quickly searching data in a database.

[0807] "Matching" refers to comparing collected employee data from large companies with the personnel data required by small and medium-sized enterprises to find the optimal combination.

[0808] "Notification" is the process of sending information such as matching results and emotion data to the user.

[0809] A means of adjusting a "secondment contract" is a method or system for adjusting the contract content and schedule for an employee of a large company to be seconded to a small or medium-sized company.

[0810] "Monitoring" is the process of continuously observing the performance and emotional state of an employee while on secondment.

[0811] "Support" means providing necessary assistance and responses based on the monitoring results.

[0812] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[0813] System Overview

[0814] This system collects and analyzes employee data from large companies and the human resources data required by small and medium-sized enterprises, uses an emotion engine to obtain emotional data, performs highly accurate matching using a generative AI model, and also monitors the emotional state of employees on secondment and provides support as needed.

[0815] Processing performed by the server

[0816] Data collection

[0817] The server first obtains employee data, employee request data, and company data and desired talent data for large companies and SMEs. This data is collected via each company's database or API. It also uses an emotion engine to collect emotion data from employees and SME managers.

[0818] Examples:

[0819] The server collects Employee A's career history, skills, and desired working style from a large company's database, and uses an emotion engine to obtain Employee A's current emotional state.

[0820] The server collects the conditions of the desired personnel from the database of small and medium-sized enterprises, and obtains the emotional data of the managers of the small and medium-sized enterprises using an emotion engine.

[0821] Data Standardization

[0822] The server analyzes the acquired data and converts it into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[0823] Examples:

[0824] A server standardizes employee data from a large corporation into background, skill sets, desired working conditions, and sentiment data.

[0825] The server standardizes the talent data required by small and medium-sized businesses into required skills, experience, job title, salary range, and sentiment data.

[0826] Registering in the database

[0827] The server registers the standardized data in a database and creates an index to enable quick searches and analysis.

[0828] Examples:

[0829] The server registers the standardized data in a database, storing data on employees of large companies, data on the personnel sought by small and medium-sized enterprises, and emotional data.

[0830] Executing the matching algorithm

[0831] The server uses generative AI models based on standardized data to match employees of large companies with small and medium-sized businesses. By taking into account emotional data, it is possible to achieve even more accurate matching.

[0832] Examples:

[0833] The server uses the generated AI model to match the skills required by the SME with Employee A's skills and emotional data, and selects the candidate with a high match rate.

[0834] Notification of results

[0835] The server then sends detailed reports containing matching results and sentiment data to employees of large companies and managers of small and medium-sized enterprises, allowing them to provide appropriate feedback.

[0836] Examples:

[0837] The server notifies Employee A and SME B of the matching results and sends detailed information in report format via email or dashboard.

[0838] Processing performed by the device

[0839] Data Entry

[0840] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input necessary information, and the emotional state of the user can be obtained in real time through an emotion engine.

[0841] Examples:

[0842] Employee A uses a terminal to enter his or her career history and desired conditions, and also records his or her emotional state at that time based on feedback from the emotion engine.

[0843] Managers of small and medium-sized enterprises input the desired personnel conditions into a terminal, and at the same time, the manager's emotional data provided by the emotion engine is also sent to the server.

[0844] Confirming results and arranging interviews

[0845] The matching results can be checked on the device, and the interview and secondment contract can be adjusted. By taking emotional data into consideration, the interview date and time and procedures can be flexibly adjusted.

[0846] Examples:

[0847] The manager of the small or medium-sized enterprise checks the matching results on a terminal and sets the interview date and time with employee A based on the emotional data.

[0848] Employee A checks the interview date and time on a terminal and approves or changes the appointment based on their emotional state.

[0849] User Roles and Actions

[0850] Senior Employees

[0851] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their emotional state in real time, while adjusting schedules for transfers and interviews.

[0852] Examples:

[0853] Senior employee A enters his / her skill set and desired conditions into the terminal, and the emotion engine also records his / her current emotional state.

[0854] Senior employee A interviews with small and medium-sized company B and proposes the optimal schedule based on emotional data.

[0855] small business manager

[0856] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to smoothly proceed with interviews and secondment contract procedures.

[0857] Examples:

[0858] The manager of SME B inputs the desired skill set into the terminal and also records his / her own emotional data provided by the emotion engine.

[0859] A manager at a small or medium-sized company, B, arranges an interview with senior employee A and uses the emotional data as a reference when concluding a secondment contract.

[0860] Emotional monitoring and support

[0861] Server-based emotion monitoring and support

[0862] The server monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[0863] Examples:

[0864] The server monitors the emotional data of senior employee A, who is on secondment, in real time and provides appropriate support if a high stress level is detected.

[0865] As described above, by combining this system with an emotion engine, it is possible to achieve highly accurate matching that takes into account the user's emotional state and to monitor performance during secondment. This allows small and medium-sized enterprises to secure the most suitable personnel, and senior employees of large companies to smoothly perform at their seconded companies.

[0866] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0867] Step 1: Data collection

[0868] The server sends an API request to retrieve employee backgrounds, skills, and preferred working arrangements from a large company's database. The input is the employee ID, and the output is the employee data in JSON format.

[0869] The server sends a request to the emotion engine's API to obtain the emotion data of employees and small business managers. The input is text or audio data to be analyzed, and the output is data indicating the emotional state. Specifically, the server sends a "POST / emotion / analyze" request to the emotion engine and analyzes the obtained data.

[0870] Step 2: Standardize the data

[0871] The server converts the acquired employee data of a large company into a standard format. The input is raw employee data, and the output is standardized data. Specifically, the data is divided into fields such as career history, skill set, desired working conditions, and emotional data.

[0872] Example: Employee data for a large company is divided into "work history," "skill set," "desired working conditions," and "emotional data," and then formatted in JSON.

[0873] Step 3: Register with the database

[0874] The server inserts the standardized data into the database and creates an index to improve searchability. The input is the standardized data, and the output is the saved status in the database. Specifically, it executes commands such as "db.employees.insert({ ...})" and "db.employees.createIndex({ skill_set: 1})".

[0875] Step 4: Run the matching algorithm

[0876] The server performs matching using a generative AI model based on standardized data. The input is employee data from large companies and the human resources data required by small and medium-sized enterprises, and the output is the matching results. Specifically, a prompt such as "model.predict({ employee_id: ..., company_id: ...})" is input into the generative AI model to obtain the scoring results.

[0877] Example: "Enter data on employee A and company B into the AI ​​model and select the combination with the highest matching rate."

[0878] Step 5: Notification of results

[0879] The server notifies the matching results to employees of large companies and administrators of small and medium-sized companies. The input is the matching results, and the output is the notification sending status. Specifically, notifications are sent using an email sending API (e.g., SendGrid) or WebSocket. Commands such as "sendMail({ to: ..., subject: ..., content: ...})" or "webSocket.send({ type: 'MATCH_RESULT', data: { ...}})" are executed.

[0880] Step 6: Emotional monitoring and support

[0881] The server monitors the emotional data of senior employees on loan in real time and provides support as needed. The input is a real-time stream of emotional data, and the output is a support action. Specifically, it periodically executes a "GET / emotion / monitor / {employee_id}" request and provides appropriate support if the stress level is high.

[0882] Example: "The server monitors emotional data and suggests counseling services if high stress levels are detected."

[0883] These steps enable the system to perform highly accurate matching that takes into account emotional data and effectively monitor the performance of employees after secondment.

[0884] (Application example 2)

[0885] 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."

[0886] The secondment of senior employees to logistics centers is important for utilizing their experience and skills, but conventional matching systems lack the ability to monitor performance and emotional state at the destination, making it difficult to find the best match and providing insufficient support during the secondment. Furthermore, when senior employees feel stressed or dissatisfied, this information is not collected in a timely manner, which can delay appropriate responses.

[0887] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0888] In this invention, the server includes means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired human resources data, means for standardizing the acquired data and registering it in a database, means for matching employees of large companies with small and medium-sized enterprises based on the standardized data, means for notifying employees of large companies and small and medium-sized enterprises of the matching results, means for utilizing an emotion engine that collects employee emotional states in real time, and means for monitoring the emotional states of employees on secondment and providing necessary support. This improves the accuracy of matching senior employees at logistics centers with their secondment destinations, making it possible to monitor the emotional states of employees on secondment and provide appropriate support.

[0889] "Employee data of large companies" refers to information such as the work history, skills, and desired working conditions of employees of large companies.

[0890] "Employee request data" refers to information regarding employees' desired working style, salary, job content, and other requests.

[0891] "Company data for small and medium-sized enterprises" refers to basic information about small and medium-sized enterprises, such as industry, number of employees, and work location.

[0892] "Desired talent data" refers to information such as the skills, experience, job title, and salary range required by SMEs for the talent they are recruiting.

[0893] "Data standardization" refers to the process of converting data acquired in different formats into a unified format.

[0894] "Registering in a database" refers to storing standardized data and making it possible to quickly search and analyze it.

[0895] "Matching" refers to using AI and algorithms to match employees of large companies with the human resource requirements of small and medium-sized enterprises to find the most suitable combination.

[0896] An "emotion engine" refers to a technology or system that collects and analyzes a user's emotional state in real time.

[0897] "Emotional state monitoring" refers to observing changes in employees' emotions in real time and obtaining information such as stress levels and satisfaction.

[0898] "Providing necessary support" refers to providing expert counseling tailored to the individual's emotional state and arranging appropriate resources.

[0899] This invention is a system for seconding senior employees of large companies to logistics centers of small and medium-sized enterprises, and in particular, by combining it with an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[0900] server

[0901] The server performs the following process:

[0902] Data collection and input

[0903] The server first collects employee data from large companies, employee request data, company data from small and medium-sized companies, and desired talent data. This data is collected via each company's database or API. It also works with an emotion engine to collect user emotion data. The collected data is standardized and registered in a database.

[0904] Examples:

[0905] Obtain the work history, skills, desired working conditions, and current emotional state of employee A of a large company using an emotion engine.

[0906] Obtain the personnel requirements and emotional data required by small and medium-sized enterprises.

[0907] Data Standardization and Matching

[0908] The acquired data is analyzed and converted into a standard format. The standardized data is registered in a database, and AI is used to match employees of large companies with small and medium-sized enterprises. By taking emotional data into account, even more accurate matching becomes possible.

[0909] Examples:

[0910] The system compares the skill requirements, experience, and sentiment data of employee A of a large company with employee B of a small or medium-sized company, and performs a highly accurate match.

[0911] Notification of results

[0912] The matching results are communicated to employees of large companies and small and medium-sized enterprises, and detailed reports including sentiment data are provided.

[0913] Terminal

[0914] The terminal performs the following process:

[0915] Data entry and confirmation

[0916] It provides an interface for employees of large companies and managers of small and medium-sized enterprises to input the necessary information. Through an emotion engine, it is possible to obtain the user's emotional state in real time. Matching results and information for interview arrangements are also notified in real time.

[0917] Examples:

[0918] Employee A uses a terminal to input and confirm his / her skills, desired conditions, and emotional state.

[0919] Managers of small and medium-sized enterprises enter the desired personnel requirements into a terminal, and emotional data generated by an emotion engine is also sent to the server.

[0920] User

[0921] The user performs the following process.

[0922] Response from senior employees

[0923] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their own emotional state in real time while adjusting their transfer and interview schedules.

[0924] Examples:

[0925] Senior employee A inputs his / her skill set and desired conditions, and the emotion engine records his / her current emotional state.

[0926] How small business managers respond

[0927] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to efficiently proceed with interviews and secondment contract procedures.

[0928] Examples:

[0929] The manager of SME B inputs the desired skill set and emotional data, arranges an interview with senior employee A, and uses the emotional data as a reference when concluding a secondment contract.

[0930] Monitoring and Support

[0931] Server-based emotion monitoring and support

[0932] The system monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[0933] Examples:

[0934] The server monitors the emotional data of senior employee A, who is on secondment, in real time and provides appropriate support if a high stress level is detected.

[0935] Applications of generative AI models

[0936] Example prompt sentence:

[0937] "Recommend the best distribution center for Senior Employee A based on the following criteria:

[0938] Skill Set: IT Support, Data Analysis

[0939] Desired working conditions: Full-time, working from home

[0940] Emotional data: Medium stress level, high satisfaction

[0941] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0942] Step 1:

[0943] The server obtains employee data from large companies, employee request data, company data from small and medium-sized companies, and desired talent data. This data is collected via each company's database or API. It uses each company's database access information and API key as input, and obtains data in a standardizable format as output.

[0944] Step 2:

[0945] The server standardizes the acquired data. Specifically, it converts data stored in different formats into a unified format (for example, JSON or CSV). It uses information about each company's data format as input and obtains data in a unified format as output. For example, it can classify employee skill sets into unified categories.

[0946] Step 3:

[0947] The server registers the standardized data in a database, indexes it, and makes it available for rapid searching and analysis. It uses the standardized data as input and gets indexed database entries as output.

[0948] Step 4:

[0949] The server uses the emotion engine to collect the user's emotion data, for example, obtains the user's emotional state in real time through the emotion engine API. It uses the user's real-time data and API key as input and obtains the emotion data as output.

[0950] Step 5:

[0951] The server runs a matching algorithm based on the standardized data and emotional data. It uses AI to match employees of large companies with small and medium-sized companies. It uses the standardized data and emotional data as input and obtains the optimal matching result as output.

[0952] Step 6:

[0953] The server notifies employees of large companies and small and medium-sized businesses of the matching results, providing them as detailed reports including emotional data. The server uses the matching result data as input and obtains notification messages and reports as output.

[0954] Step 7:

[0955] The terminal provides an interface for employees of large corporations and managers of small and medium-sized enterprises to input the necessary information. Through an emotion engine, it is also possible to obtain the user's emotional state in real time. It uses the information entered by the user as input and obtains data in a standard format as output to be sent to the server.

[0956] Step 8:

[0957] The terminal notifies the user of the matching results and information for interview arrangement in real time. It uses notification data from the server as input and obtains notification messages for the user as output.

[0958] Step 9:

[0959] The user adjusts the schedule for a transfer or interview while understanding their own emotional state in real time using the emotion engine. The emotion engine data is used as input, and appropriate schedule adjustment proposals are obtained as output.

[0960] Step 10:

[0961] The server monitors the emotional state of the senior employee on secondment and provides necessary support based on that. It uses real-time emotional data as input and gets support response suggestions and resource allocation plans as output.

[0962] Example prompt sentence:

[0963] "Recommend the best distribution center for senior employees based on the following criteria:

[0964] Skill Set: IT Support, Data Analysis

[0965] Desired working conditions: Full-time, working from home

[0966] Emotional data: Medium stress level, high satisfaction

[0967] 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.

[0968] 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.

[0969] 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.

[0970] [Third embodiment]

[0971] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0972] 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.

[0973] 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).

[0974] 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.

[0975] 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.

[0976] 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).

[0977] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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."

[0983] The present invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and specifically operates through the collaboration of a server, terminals, and users. The mechanism and specific operation of the system will be described in detail below.

[0984] server

[0985] Data collection

[0986] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, collected via each company's database or API.

[0987] Examples:

[0988] "The server collects employee A's background, skills, and preferred working arrangements from a large company's database."

[0989] "The server collects the desired personnel requirements from a database of small and medium-sized enterprises."

[0990] Data Standardization

[0991] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[0992] Examples:

[0993] "The server standardizes employee data for large corporations into backgrounds, skill sets, and working conditions."

[0994] "The server standardizes the personnel data required by small and medium-sized enterprises into experience, skills, and working conditions."

[0995] Executing the matching algorithm

[0996] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies, taking into account their career history, skill set, and working conditions to make the best possible match.

[0997] Examples:

[0998] "The server uses AI to compare the skills required by small and medium-sized company B with the skills of employee A of large company, and selects the candidate with the highest match rate."

[0999] Notification of results

[1000] The matching results are communicated to employees of large companies and small and medium-sized enterprises, and the results are summarized in a report and sent via email and dashboard.

[1001] Examples:

[1002] The server notifies Employee A and Small Business B of the matching results and sends detailed information by email.

[1003] Terminal

[1004] Data Entry

[1005] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input the necessary information, which is then sent to a server for further processing.

[1006] Examples:

[1007] "Employee A enters his / her career history and desired conditions into the terminal and sends it to the server."

[1008] "Managers of small and medium-sized enterprises input the personnel requirements into a terminal and send them to a server."

[1009] Confirming results and arranging interviews

[1010] The matching results are checked on the terminal, and interviews and transfer contracts are arranged. Specific interview dates, times, and locations are also set on the terminal.

[1011] Examples:

[1012] "The manager of the small and medium-sized enterprise checks the matching results on the terminal and schedules an interview date and time with Employee A."

[1013] "Employee A checks the interview date and time on the terminal and approves it."

[1014] User

[1015] Senior Employees

[1016] Senior employees enter their information through a terminal, check the matching results, and then undergo an interview. If approved, they will begin their secondment to a small or medium-sized company.

[1017] Examples:

[1018] "Senior employee A enters his / her skill set and desired conditions into the terminal, and confirms the matching results when they are notified."

[1019] "Senior employee A interviews with small and medium-sized company B and officially signs a secondment contract."

[1020] small business manager

[1021] Managers of small and medium-sized enterprises can input the desired personnel requirements through the terminal, check the matching results, and also arrange interviews and process transfer contracts.

[1022] Examples:

[1023] "Enter the skill set desired by the manager of SME B into the terminal and check the matching results."

[1024] "Manager of SME B arranges an interview with Senior Employee A and concludes a secondment contract."

[1025] This system allows small and medium-sized enterprises to quickly and efficiently secure work-ready personnel, while large companies can effectively utilize the skills of senior employees, providing significant benefits to both parties.

[1026] The processing flow will be explained below.

[1027] Step 1: Data collection

[1028] The server collects employee data from the database of a large company, specifically information such as employee background, skills, qualifications, work experience, preferred work arrangements and locations.

[1029] The server collects company data and desired personnel data from a database of small and medium-sized enterprises, specifically, basic information about the company, business details, desired skill sets, job details, salary range, working hours, etc.

[1030] Step 2: Standardize the data

[1031] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, etc. By organizing data stored in different formats into a unified format, subsequent processing becomes easier.

[1032] The server also converts the human resources data required by small and medium-sized enterprises into a standard format, standardizing the required skills, experience, job title, salary range, working conditions, etc.

[1033] Step 3: Register with the database

[1034] The server registers the standardized data in a database, creating an index that enables rapid data search and AI analysis.

[1035] Data on employees of large companies and the personnel data required by small and medium-sized enterprises is stored in a database, and appropriate tags are added to make it easy to search.

[1036] Step 4: Run the matching algorithm

[1037] The server passes the standardized data from the database to the AI, which runs a matching algorithm to match the employee's skill set and desired conditions with the skill sets and working conditions required by the small and medium-sized enterprise, and finds the best match.

[1038] The server reviews the AI ​​results and lists the most relevant matches.

[1039] Step 5: Notification of results

[1040] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized companies by sending the results via email or an online dashboard.

[1041] The server will send a notification with detailed information about the match, including contact information.

[1042] Step 6: Data entry

[1043] Using the terminals, employees of large companies and managers of small and medium-sized enterprises input the necessary information. Employees input their career history, skills, and desired conditions, while managers of small and medium-sized enterprises input the desired skill sets and job content.

[1044] The entered data is sent to the server in real time and used for subsequent processing.

[1045] Step 7: Check the results and arrange an interview

[1046] The matching results are checked on the terminal and the interview and secondment contract are arranged. The manager of the SME checks the detailed information of the matched senior employee and sets the interview date and time.

[1047] Senior employees check the interview date and time on the terminal and make any changes or approvals as necessary.

[1048] Step 8: Interview and decision

[1049] The senior employee as the user will have an interview with the SME. As a result of the interview, the SME will decide whether to officially hire the senior employee who wishes to be seconded.

[1050] A small or medium-sized enterprise enters into a secondment contract and registers the contract details on a server.

[1051] Step 9: Commencement and monitoring

[1052] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[1053] Regularly collect and monitor performance data from senior staff on secondment and provide any support required.

[1054] As a result, this system will alleviate the labor shortages of small and medium-sized enterprises and effectively utilize the experience and skills of senior employees at large companies, providing a mutually beneficial solution.

[1055] Example 1

[1056] 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."

[1057] In recent years, there has been a demand for increased mobility of human resources between large and small organizations. However, many large organizations have limited opportunities to effectively utilize the skills of senior employees, while small organizations have difficulty securing human resources who can immediately contribute. To solve these issues, a system is needed that accurately matches the needs of both parties and quickly and efficiently dispatches human resources.

[1058] 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.

[1059] In this invention, the server includes means for acquiring employee information of the large organization, employee preference information, company information of the small organization, and necessary human resources information, means for verifying and standardizing the acquired data and registering it in a database, means for executing an artificial intelligence model to match employees of the large organization with small organizations based on the standardized data, and means for notifying employees of the large organization and the small organization of the matching results, thereby enabling senior employees of the large organization to be dispatched to the small organization quickly and efficiently.

[1060] A "large organization" is a company with a large number of employees and multiple business divisions and processes.

[1061] "Employee Information" means data related to an employee, such as an employee's background, skill set, job title, work history, and evaluation information.

[1062] "Employee preference information" refers to data that indicates an employee's individual preferences and conditions, such as desired working style, work location, job content, and working hours.

[1063] A "small organization" is a business or organization with a small number of employees and limited resources.

[1064] "Company information" refers to general information related to a company, such as the company's size, industry, location, business activities, and the type of personnel it is seeking.

[1065] "Required human resources information" refers to data that indicates the specific job requirements, such as the skill set, experience, qualifications, and working conditions that a company is looking for.

[1066] "Means of acquisition" refers to the methods and processes for obtaining the required data through a database or API.

[1067] "Validation and standardization" refers to the process of converting data stored in different formats into a unified format to ensure data consistency and accuracy.

[1068] A "database" refers to a system for efficiently storing, managing, and searching large amounts of data.

[1069] An "artificial intelligence model" refers to an algorithm that uses machine learning or deep learning to analyze data and perform a specific task (in this case, matching).

[1070] "Matching" refers to the process of finding the right match based on specific criteria, which in this case means matching employees from larger organizations with smaller organizations.

[1071] "Means of notification" refers to the method by which matching results are communicated to relevant parties, such as through email, dashboards, notification systems, etc.

[1072] The present invention is a system for dispatching senior employees of a large organization to a small organization, and specifically, a mechanism in which a server, a terminal, and a user work together. Specific embodiments of the system are described in detail below.

[1073] First, the server collects employee information and preference information from large organizations, company information from small organizations, and necessary human resources information. This data is obtained via each company's database or API. For example, the server calls the large organization's HR system API to obtain employee backgrounds and skill sets, and uses the small organization's job information API to collect company recruitment requirements.

[1074] The server validates and standardizes the collected data, which is often stored in different formats. Standardizing the data into a specific format facilitates subsequent analysis. For example, the server converts employee data from a large organization into a standard format based on background, skill set, and working conditions.

[1075] Next, the server uses this standardized data to match employees from large organizations with smaller organizations using an artificial intelligence model. The AI ​​model is an algorithm that incorporates machine learning and deep learning, and comprehensively evaluates each employee's skill set, background, and desired conditions to make the optimal match. For example, the server loads the AI ​​model, provides background, skills, and working conditions as input data, analyzes the model's execution results, and selects highly suitable candidates.

[1076] The server notifies the employees of the large organization and the small organization of the matching results. The results are summarized in a report format and sent via email or dashboard. For example, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be displayed when logged in.

[1077] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. The entered data is then sent to a server and used in subsequent processes. For example, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation.

[1078] The device also provides an interface for checking matching results and arranging interviews and temporary employment contracts. Specific interview dates, times, and locations can also be set on the device. For example, an administrator at a small organization can log in from the device and check the details of the matching results, and employee A can then check the interview date and time on the device and press the approval button to complete the interview arrangement.

[1079] Example of input prompt for generative AI model

[1080] The following prompts can be used to provide the necessary input to the generative AI model:

[1081] "Please explain in detail the process by which your server collects employee data for a large organization."

[1082] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[1083] This system allows senior employees of large organizations to be quickly and efficiently dispatched to smaller organizations, making effective use of their skills, while at the same time allowing smaller organizations to quickly secure work-ready personnel.

[1084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1085] Step 1: Data collection

[1086] server

[1087] Input: Employee data for large organizations, employee preference data, company data for small organizations, human resources data

[1088] Specifically, the server collects the necessary data through each company's database and API. The server calls the HR system API of a large organization to obtain employee backgrounds and skill sets, and uses the job information API of a small organization to collect company recruitment requirements.

[1089] Output: Raw employee data, company data, talent data

[1090] Step 2: Data validation and standardization

[1091] server

[1092] Inputs: Raw employee data, company data, talent data

[1093] The server then validates and standardizes the data it receives, preprocessing it to detect and complete missing or incorrect data. Specifically, the server converts employee data from large companies into a standard format based on background, skill set, and working conditions.

[1094] Output: Standardized employee data, company data, and talent data

[1095] Step 3: Register with the database

[1096] server

[1097] Inputs: Standardized employee data, company data, talent data

[1098] The server registers the validated and standardized data in a database, making it easily accessible for subsequent processing. Specifically, the server stores the standardized data in the database with an index.

[1099] Output: Employee data, company data, and human resources data stored in a database

[1100] Step 4: Run the matching algorithm

[1101] server

[1102] Input: Employee data, company data, and human resources data stored in a database

[1103] The server uses an AI algorithm to perform optimal matching based on standardized data. The AI ​​model uses machine learning and deep learning to comprehensively evaluate each employee's skill set, background, and desired conditions. Specifically, the server loads the AI ​​model and provides background, skills, and working conditions as input data. The model's execution results are then analyzed to evaluate and select highly suitable candidates.

[1104] Output: Matching result data

[1105] Step 5: Notification of results

[1106] server

[1107] Input: Matching result data

[1108] The server notifies the matching results to the employees of the large organization and the small organization. The results are summarized in a report format and sent via email or dashboard. Specifically, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be viewed when logged in.

[1109] Output: Notified matching results

[1110] Step 6: Data entry

[1111] Terminal

[1112] Input: Employee data from users, desired data, and data on the personnel required by companies

[1113] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. Specifically, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation. The data is sent to the server and used for subsequent processing.

[1114] Output: Employee data, preference data, and talent data sent to the server

[1115] Step 7: Check the results and arrange an interview

[1116] Terminal

[1117] Input: Notified matching result data

[1118] The matching results are checked on the terminal, and the interview and dispatch contract are arranged. Detailed interview date and time and location can also be set on the terminal. Specifically, the administrator of the small organization logs in from the terminal, checks the details of the matching results, and employee A checks the interview date and time on the terminal and presses the approval button, completing the interview arrangement.

[1119] Output: Confirmed interview date, time and location data

[1120] Example of input prompt for generative AI model

[1121] The following prompts can be used to provide the necessary input to the generative AI model:

[1122] "Please explain in detail the process by which your server collects employee data for a large organization."

[1123] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[1124] (Application example 1)

[1125] 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."

[1126] When seconding senior employees from large companies to small and medium-sized enterprises, there is a problem in matching personnel, as it is difficult to quickly and efficiently find personnel with the appropriate skill sets and experience. Furthermore, the procedures for arranging interviews and signing secondment contracts after matching are complicated, making it difficult for the parties involved to communicate smoothly. Furthermore, there is a problem in that a lack of performance monitoring during the secondment makes it difficult to maximize the benefits of the secondment.

[1127] 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.

[1128] In this invention, the server includes: means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired talent data; means for standardizing the acquired data and registering it in a database; means for matching employees of large companies with small and medium-sized enterprises based on the standardized data; means for notifying employees of large companies and small and medium-sized enterprises of the matching results; and means for matched employees of large companies and managers of small and medium-sized enterprises to arrange interviews and conclude secondment contracts via an application. This enables quick and efficient matching of talent with appropriate skill sets and experience, and smooth subsequent procedures and collaboration. Furthermore, performance monitoring during the secondment maximizes the effectiveness of the secondment.

[1129] A "large company" refers to a company that has a large number of employees and conducts large-scale business activities.

[1130] "Small and medium-sized enterprises" refer to companies that conduct business activities on a relatively small scale and whose number of employees and sales revenue do not meet certain standards.

[1131] "Employee data" refers to data that includes information about an employee's background, skills, working conditions, etc.

[1132] "Employee request data" refers to data regarding employees' desired working style, work location, job content, and other requests.

[1133] "Company data" refers to data that includes basic information about the company, business activities, and the desired personnel requirements.

[1134] "Desired talent data" refers to data such as the skill sets, experience, and working conditions that companies are looking for.

[1135] "Data standardization" refers to the process of converting data stored in different formats into a unified format.

[1136] A "database" is a system for storing and managing data according to certain rules.

[1137] "Matching" refers to the process of connecting suitable candidates with companies based on certain criteria.

[1138] "Notification" refers to the act of conveying information such as matching results to relevant parties.

[1139] "Interview arrangement" refers to the process of arranging the date, time, and location of an interview between the candidate and the company after a match has been made.

[1140] A "secondment contract" refers to a contract under which an employee works for another company for a certain period of time.

[1141] "Application" refers to a software program that a user uses for a specific purpose.

[1142] "Performance monitoring" refers to the act of monitoring and evaluating the work performance of employees on secondment.

[1143] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and operates in cooperation with a server, terminals, and users. The specific mechanism and operation of this system will be described in detail below.

[1144] server

[1145] Data collection

[1146] The server acquires employee data from large companies, employee request data, company data from small and medium-sized enterprises, and desired talent data. This data is collected via the company's database or API. For example, "The server collects employee backgrounds, skills, and desired working arrangements from the large company's database," or "The server collects the desired talent conditions from the small and medium-sized enterprise's database."

[1147] Data Standardization

[1148] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for generative AI models to analyze it. Specifically, the server standardizes employee data from large companies into career history, skill sets, and working conditions, and the server standardizes the human resources data required by small and medium-sized enterprises into experience, skills, and working conditions.

[1149] Executing the matching algorithm

[1150] Based on standardized data, a generative AI model is used to match employees of large companies with small and medium-sized companies. The model makes an optimal match by comprehensively assessing backgrounds, skill sets, and working conditions. For example, "the server uses AI to match the skills required by small and medium-sized companies with the skills of employees at large companies and selects candidates with a high match rate."

[1151] Notification of results

[1152] The matching results are notified to employees of large companies and small and medium-sized enterprises. The results are compiled in a report format and sent via email or dashboard. Specifically, "the server notifies employees and small and medium-sized enterprises of the matching results and sends detailed information by email."

[1153] Interview arrangement and contract

[1154] The matched employees of the large company and the managers of the SMEs then arrange interviews and conclude secondment contracts through the application. For example, "the server arranges interview dates and times between the employees and the SMEs, and provides an interface for concluding secondment contracts."

[1155] Terminal

[1156] Data Entry

[1157] The terminal provides an interface for employees of large corporations and managers of small and medium-sized enterprises to input the necessary information. The input data is sent to a server and used for subsequent processing. For example, "an employee enters their career history and desired qualifications into the terminal and sends it to the server," or "a manager of a small or medium-sized enterprise enters the qualifications of the personnel they are looking for into the terminal and sends it to the server."

[1158] Confirming results and arranging interviews

[1159] The matching results are checked on the terminal, and interviews and secondment contracts are arranged. Specific interview dates, times, and locations are also set on the terminal. For example, "The manager of a small or medium-sized enterprise checks the matching results on the terminal and sets the interview date and time with the employee," or "The employee checks the interview date and time on the terminal and approves it."

[1160] User

[1161] Senior Employees

[1162] Senior employees enter their own information through the terminal and check the matching results. They then undergo an interview and, if approved, begin their secondment to the SME. For example, "senior employees enter their own skill set and desired conditions into the terminal, and check the matching results when they are notified," or "senior employees interview with the SME and formally sign a secondment contract."

[1163] small business manager

[1164] Managers of small and medium-sized enterprises use the terminal to input the desired personnel criteria and check the matching results. They also arrange interviews and process secondment contracts. For example, "Managers of small and medium-sized enterprises input the desired skill set into the terminal and check the matching results" or "Managers of small and medium-sized enterprises arrange interviews with senior employees and conclude secondment contracts."

[1165] Prompt Sentence Examples

[1166] Create a Python function that accesses the API to retrieve employee data from large companies and the talent data required by small and medium-sized enterprises, and perform matching using a generative AI model. Write a script to notify the matching results by email.

[1167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1168] Step 1:

[1169] The server collects employee data from large companies, employee requirements data, company data from small and medium-sized companies, and desired talent data via APIs. This involves connecting to corporate databases and external data sources. The input to this process is the API or database query, and the output is the retrieved raw data. Specifically, the server executes the query to extract the relevant data and receives it in JSON format.

[1170] Step 2:

[1171] The server standardizes the data it receives. If the data is stored in a different format, it converts it into a consistent format. The input is the raw data it received, and the output is the standardized data. Specifically, it uses the pandas library to convert the data into a data frame and then converts it to the required schema.

[1172] Step 3:

[1173] The server registers the standardized data in the database. The input of this process is the standardized data, and the output is the data stored in the database. Specifically, the server uses an SQL query to store the data in the database with an INSERT statement.

[1174] Step 4:

[1175] The server uses a generative AI model based on standardized data to match employees of large companies with small and medium-sized enterprises. The input is standardized employee data of large companies and the talent data desired by small and medium-sized enterprises, and the output is the matching results. Specifically, the scikit-learn library is used to analyze the data using algorithms such as nearest neighbor methods to generate optimal matching pairs.

[1176] Step 5:

[1177] The server notifies the matching results. The input of this process is the generated matching results, and the output is sending a notification. Specifically, the server uses the SMTP protocol to send emails to notify each employee and the manager of the small business of the matching results.

[1178] Step 6:

[1179] The terminal provides an interface for employees of large companies and managers of small and medium-sized companies to arrange interviews and sign secondment contracts. The input is a notification of the matching results from the server, and the output is the completion of the interview arrangement or secondment contract. Specifically, the calendar function on the terminal is used to select a date and time, and the arrangement is completed by pressing the confirmation button.

[1180] Step 7:

[1181] Users (senior employees and managers of small and medium-sized enterprises) use the terminal to enter their own information and check the matching results. The input is a notification from the server, and the output is the confirmed information and the completion of the interview and contract. Specifically, senior employees enter their own skill set and desired conditions, and the manager enters the desired skill set. Based on this, the matching results are confirmed and the interview date and time are set.

[1182] 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.

[1183] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[1184] server

[1185] Data collection

[1186] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, small and medium-sized companies, collected via each company's database or API, and then connects with an emotion engine to collect user emotion data.

[1187] Examples:

[1188] "The server collects Employee A's background, skills, and preferred working style from a large company's database. It then uses an emotion engine to obtain Employee A's current emotional state."

[1189] "The server collects the desired personnel requirements from the database of small and medium-sized enterprises. Then, it uses an emotion engine to obtain emotional data on the requests of the managers of small and medium-sized enterprises."

[1190] Data Standardization

[1191] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[1192] Examples:

[1193] "The server standardizes employee data from large corporations into backgrounds, skill sets, desired working conditions, and sentiment data."

[1194] "The server standardizes SMEs' talent needs data into required skills, experience, job title, salary range, and sentiment data."

[1195] Registering in the database

[1196] Standardized data is registered in a database and indexed to enable rapid search and analysis.

[1197] Examples:

[1198] "The server registers the standardized data in a database, storing data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data."

[1199] Executing the matching algorithm

[1200] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies. By taking emotional data into account, more accurate matching becomes possible.

[1201] Examples:

[1202] The server uses AI to match the skills required by the SME with employee A's skills and emotional data, and selects the candidate with a high match rate.

[1203] Notification of results

[1204] The matching results are communicated to employees of large companies and managers of small and medium-sized businesses in a detailed report that includes sentiment data.

[1205] Examples:

[1206] The server notifies Employee A and SME B of the matching results and sends detailed information in a report format via email or dashboard.

[1207] Terminal

[1208] Data Entry

[1209] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input necessary information. Through the emotion engine, it is possible to obtain the user's emotional state in real time.

[1210] Examples:

[1211] "Employee A uses a device to input his / her career history and desired conditions, and records his / her emotional state at that time based on feedback from the emotion engine."

[1212] "Managers of small and medium-sized enterprises input the desired personnel conditions into a terminal, and at the same time, the emotion engine provides the manager's emotional data, which is then sent to the server."

[1213] Confirming results and arranging interviews

[1214] The matching results can be checked on the device, and the interview and secondment contract can be adjusted. By taking emotional data into consideration, the interview date and time and procedures can be flexibly adjusted.

[1215] Examples:

[1216] "The manager of the small and medium-sized enterprise checks the matching results on a terminal and schedules an interview date and time with Employee A based on the emotional data."

[1217] "Employee A checks the interview date and time on their device and approves or changes it based on their emotional state."

[1218] User

[1219] Senior Employees

[1220] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their own emotional state in real time while adjusting their transfer and interview schedules.

[1221] Examples:

[1222] "Senior employee A enters his / her skill set and desired conditions into the terminal, and the emotion engine also records his / her current emotional state."

[1223] "Senior employee A interviews with small and medium-sized company B and proposes the optimal schedule based on emotional data."

[1224] small business manager

[1225] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to efficiently proceed with interviews and secondment contract procedures.

[1226] Examples:

[1227] "The manager of SME B inputs the desired skill set into the terminal and also records his / her own emotional data provided by the emotion engine."

[1228] "Manager of SME B arranges an interview with Senior Employee A and uses the emotional data as a reference when concluding a secondment contract."

[1229] Monitoring and Support

[1230] Server-based emotion monitoring and support

[1231] The system monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[1232] Examples:

[1233] "The server monitors the emotional data of Senior Employee A, who is on loan, in real time, and provides appropriate support if a high stress level is detected."

[1234] As described above, by combining this system with an emotion engine, it is possible to achieve highly accurate matching that takes into account the user's emotional state and to monitor performance during secondment. This allows small and medium-sized enterprises to secure the most suitable personnel, and senior employees of large companies to smoothly perform at their seconded companies.

[1235] The processing flow will be explained below.

[1236] Step 1: Data collection

[1237] The server collects employee data from a large company's database, specifically, information such as employees' career history, skills, qualifications, work experience, desired work style and location, etc. It also obtains the employee's current emotional data via an emotion engine.

[1238] The server collects company data and desired personnel data from the SME database, specifically, basic information about the SME, business activities, desired skill sets, job duties, salary range, working hours, etc. Next, it collects emotion data from SME managers via an emotion engine.

[1239] Step 2: Standardize the data

[1240] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, and sentiment data. By unifying data stored in different formats, subsequent processing becomes easier.

[1241] The server also converts the human resource data required by small and medium-sized enterprises into a standard format, standardizing it into required skills, experience, job title, salary range, working conditions, and emotional data.

[1242] Step 3: Register with the database

[1243] The server registers the standardized data in a database, which then creates an index for rapid search and analysis.

[1244] Data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data are stored in a database, and appropriate tags are added to make it easy to search.

[1245] Step 4: Run the matching algorithm

[1246] The server passes the standardized data to the AI, which runs a matching algorithm that compares the employee's skill set and desired conditions with the skill sets and working conditions required by small and medium-sized enterprises, and also takes emotional data into account to make the optimal match.

[1247] The server reviews the AI ​​results and lists candidates with high suitability.

[1248] Step 5: Notification of results

[1249] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized enterprises, including specific suggestions that take into account the sentiment data.

[1250] The server will send you a notification via email and / or dashboard with detailed match results.

[1251] Step 6: Data entry

[1252] Employees of large companies and managers of small and medium-sized enterprises use terminals to input the necessary information: employees enter their backgrounds, skills, and desired qualifications, and emotional data is also provided based on feedback from the emotion engine.

[1253] Managers of small and medium-sized enterprises also enter the required skill sets and job descriptions on the terminal, and emotional data is also sent to the server.

[1254] Step 7: Check the results and arrange an interview

[1255] The matching results can be checked on the device, and interviews and secondment contracts can be arranged. Interview dates and procedures can be flexibly adjusted based on emotional data.

[1256] Managers of small and medium-sized enterprises review the matching results and decide on interview dates and times with suitable employees. Using an emotion engine, the system suggests optimal schedules based on the emotional state of both parties.

[1257] Senior employees check the interview date and time on their devices and approve or change the date depending on their emotional state.

[1258] Step 8: Interview and decision

[1259] Senior employees act as users, conducting interviews with small and medium-sized enterprises and proposing optimal schedules based on emotional data.

[1260] The small and medium-sized enterprise evaluates the interview results and, taking into consideration the emotional data, decides whether to officially hire the most suitable candidate. A secondment contract is concluded and the details of the contract are registered on the server.

[1261] Step 9: Commencement and monitoring

[1262] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[1263] The server periodically collects performance data from senior employees on loan and uses an emotion engine to monitor their emotional state in real time. If high stress levels or a decline in satisfaction are detected, appropriate support is provided.

[1264] By combining this with an emotion engine, this system achieves highly accurate matching that takes into account the user's emotional state and monitors performance during secondment. This allows small and medium-sized enterprises to secure the best talent, and senior employees of large companies to smoothly perform at their seconded companies.

[1265] Example 2

[1266] 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."

[1267] Conventional matching systems have problems with low matching accuracy and insufficient performance monitoring after transfer when seconding senior employees of large companies to SMEs. Furthermore, they are unable to take into account the emotional state of employees and managers of SMEs, making it difficult to smoothly adjust matching and secondment contracts.

[1268] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee data of large companies, employee request data, data on small and medium-sized organizations, and data on desired human resources, means for acquiring emotion data using an emotion engine, means for analyzing and standardizing the acquired data and emotion data, means for registering the standardized data in a database and creating an index, means for matching employees of large companies with small and medium-sized organizations using a generative AI model based on the standardized data, and means for notifying employees of large companies and small and medium-sized organizations of the matching results and emotion data in the form of a detailed report. This enables high-precision matching based on emotion data and performance monitoring after secondment.

[1269] "Large company employee data" refers to information about employees employed by large companies, including their career history, skill sets, working conditions, etc.

[1270] "Employee request data" refers to data on the working conditions, career paths, work locations, and other requests of employees of large companies.

[1271] "Data on small and medium-sized organizations" refers to information on small and medium-sized enterprises, including the type of industry, business activities, location, size, and so on.

[1272] "Desired talent data" refers to data on the skills, experience, job title, salary range, etc. of the talent that SMEs require.

[1273] An "emotion engine" is a software or hardware system that analyzes a user's emotional state and measures stress levels, satisfaction, motivation, etc.

[1274] "Emotion data" is data relating to the user's emotional state obtained using an emotion engine, and includes indicators such as stress level, happiness level, and concentration level.

[1275] "Generative AI models" refer to algorithms and machine learning models that use artificial intelligence technology to perform data analysis and predictions.

[1276] "Standardization" is the process of converting data of different formats and structures into a uniform form.

[1277] A "database" is a system for storing collected data and making it easy to search and analyze.

[1278] An "index" is a structure for quickly searching data in a database.

[1279] "Matching" refers to comparing collected employee data from large companies with the personnel data required by small and medium-sized enterprises to find the optimal combination.

[1280] "Notification" is the process of sending information such as matching results and emotion data to the user.

[1281] A means of adjusting a "secondment contract" is a method or system for adjusting the contract content and schedule for an employee of a large company to be seconded to a small or medium-sized company.

[1282] "Monitoring" is the process of continuously observing the performance and emotional state of an employee while on secondment.

[1283] "Support" means providing necessary assistance and responses based on the monitoring results.

[1284] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[1285] System Overview

[1286] This system collects and analyzes employee data from large companies and the human resources data required by small and medium-sized enterprises, uses an emotion engine to obtain emotional data, performs highly accurate matching using a generative AI model, and also monitors the emotional state of employees on secondment and provides support as needed.

[1287] Processing performed by the server

[1288] Data collection

[1289] The server first obtains employee data, employee request data, and company data and desired talent data for large companies and SMEs. This data is collected via each company's database or API. It also uses an emotion engine to collect emotion data from employees and SME managers.

[1290] Examples:

[1291] The server collects Employee A's career history, skills, and desired working style from a large company's database, and uses an emotion engine to obtain Employee A's current emotional state.

[1292] The server collects the conditions of the desired personnel from the database of small and medium-sized enterprises, and obtains the emotional data of the managers of the small and medium-sized enterprises using an emotion engine.

[1293] Data Standardization

[1294] The server analyzes the acquired data and converts it into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[1295] Examples:

[1296] A server standardizes employee data from a large corporation into background, skill sets, desired working conditions, and sentiment data.

[1297] The server standardizes the talent data required by small and medium-sized businesses into required skills, experience, job title, salary range, and sentiment data.

[1298] Registering in the database

[1299] The server registers the standardized data in a database and creates an index to enable quick searches and analysis.

[1300] Examples:

[1301] The server registers the standardized data in a database, storing data on employees of large companies, data on the personnel sought by small and medium-sized enterprises, and emotional data.

[1302] Executing the matching algorithm

[1303] The server uses generative AI models based on standardized data to match employees of large companies with small and medium-sized businesses. By taking into account emotional data, it is possible to achieve even more accurate matching.

[1304] Examples:

[1305] The server uses the generated AI model to match the skills required by the SME with Employee A's skills and emotional data, and selects the candidate with a high match rate.

[1306] Notification of results

[1307] The server then sends detailed reports containing matching results and sentiment data to employees of large companies and managers of small and medium-sized enterprises, allowing them to provide appropriate feedback.

[1308] Examples:

[1309] The server notifies Employee A and SME B of the matching results and sends detailed information in report format via email or dashboard.

[1310] Processing performed by the device

[1311] Data Entry

[1312] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input necessary information, and the emotional state of the user can be obtained in real time through an emotion engine.

[1313] Examples:

[1314] Employee A uses a terminal to enter his or her career history and desired conditions, and also records his or her emotional state at that time based on feedback from the emotion engine.

[1315] Managers of small and medium-sized enterprises input the desired personnel conditions into a terminal, and at the same time, the manager's emotional data provided by the emotion engine is also sent to the server.

[1316] Confirming results and arranging interviews

[1317] The matching results can be checked on the device, and the interview and secondment contract can be adjusted. By taking emotional data into consideration, the interview date and time and procedures can be flexibly adjusted.

[1318] Examples:

[1319] The manager of the small or medium-sized enterprise checks the matching results on a terminal and sets the interview date and time with employee A based on the emotional data.

[1320] Employee A checks the interview date and time on a terminal and approves or changes the appointment based on their emotional state.

[1321] User Roles and Actions

[1322] Senior Employees

[1323] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their emotional state in real time, while adjusting schedules for transfers and interviews.

[1324] Examples:

[1325] Senior employee A enters his / her skill set and desired conditions into the terminal, and the emotion engine also records his / her current emotional state.

[1326] Senior employee A interviews with small and medium-sized company B and proposes the optimal schedule based on emotional data.

[1327] small business manager

[1328] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to smoothly proceed with interviews and secondment contract procedures.

[1329] Examples:

[1330] The manager of SME B inputs the desired skill set into the terminal and also records his / her own emotional data provided by the emotion engine.

[1331] A manager at a small or medium-sized company, B, arranges an interview with senior employee A and uses the emotional data as a reference when concluding a secondment contract.

[1332] Emotional monitoring and support

[1333] Server-based emotion monitoring and support

[1334] The server monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[1335] Examples:

[1336] The server monitors the emotional data of senior employee A, who is on secondment, in real time and provides appropriate support if a high stress level is detected.

[1337] As described above, by combining this system with an emotion engine, it is possible to achieve highly accurate matching that takes into account the user's emotional state and to monitor performance during secondment. This allows small and medium-sized enterprises to secure the most suitable personnel, and senior employees of large companies to smoothly perform at their seconded companies.

[1338] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1339] Step 1: Data collection

[1340] The server sends an API request to retrieve employee backgrounds, skills, and preferred working arrangements from a large company's database. The input is the employee ID, and the output is the employee data in JSON format.

[1341] The server sends a request to the emotion engine's API to obtain the emotion data of employees and small business managers. The input is text or audio data to be analyzed, and the output is data indicating the emotional state. Specifically, the server sends a "POST / emotion / analyze" request to the emotion engine and analyzes the obtained data.

[1342] Step 2: Standardize the data

[1343] The server converts the acquired employee data of a large company into a standard format. The input is raw employee data, and the output is standardized data. Specifically, the data is divided into fields such as career history, skill set, desired working conditions, and emotional data.

[1344] Example: Employee data for a large company is divided into "work history," "skill set," "desired working conditions," and "emotional data," and then formatted in JSON.

[1345] Step 3: Register with the database

[1346] The server inserts the standardized data into the database and creates an index to improve searchability. The input is the standardized data, and the output is the saved status in the database. Specifically, it executes commands such as "db.employees.insert({ ...})" and "db.employees.createIndex({ skill_set: 1})".

[1347] Step 4: Run the matching algorithm

[1348] The server performs matching using a generative AI model based on standardized data. The input is employee data from large companies and the human resources data required by small and medium-sized enterprises, and the output is the matching results. Specifically, a prompt such as "model.predict({ employee_id: ..., company_id: ...})" is input into the generative AI model to obtain the scoring results.

[1349] Example: "Enter data on employee A and company B into the AI ​​model and select the combination with the highest matching rate."

[1350] Step 5: Notification of results

[1351] The server notifies the matching results to employees of large companies and administrators of small and medium-sized companies. The input is the matching results, and the output is the notification sending status. Specifically, notifications are sent using an email sending API (e.g., SendGrid) or WebSocket. Commands such as "sendMail({ to: ..., subject: ..., content: ...})" or "webSocket.send({ type: 'MATCH_RESULT', data: { ...}})" are executed.

[1352] Step 6: Emotional monitoring and support

[1353] The server monitors the emotional data of senior employees on loan in real time and provides support as needed. The input is a real-time stream of emotional data, and the output is a support action. Specifically, it periodically executes a "GET / emotion / monitor / {employee_id}" request and provides appropriate support if the stress level is high.

[1354] Example: "The server monitors emotional data and suggests counseling services if high stress levels are detected."

[1355] These steps enable the system to perform highly accurate matching that takes into account emotional data and effectively monitor the performance of employees after secondment.

[1356] (Application example 2)

[1357] 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."

[1358] The secondment of senior employees to logistics centers is important for utilizing their experience and skills, but conventional matching systems lack the ability to monitor performance and emotional state at the destination, making it difficult to find the best match and providing insufficient support during the secondment. Furthermore, when senior employees feel stressed or dissatisfied, this information is not collected in a timely manner, which can delay appropriate responses.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1360] In this invention, the server includes means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired human resources data, means for standardizing the acquired data and registering it in a database, means for matching employees of large companies with small and medium-sized enterprises based on the standardized data, means for notifying employees of large companies and small and medium-sized enterprises of the matching results, means for utilizing an emotion engine that collects employee emotional states in real time, and means for monitoring the emotional states of employees on secondment and providing necessary support. This improves the accuracy of matching senior employees at logistics centers with their secondment destinations, making it possible to monitor the emotional states of employees on secondment and provide appropriate support.

[1361] "Employee data of large companies" refers to information such as the work history, skills, and desired working conditions of employees of large companies.

[1362] "Employee request data" refers to information regarding employees' desired working style, salary, job content, and other requests.

[1363] "Company data for small and medium-sized enterprises" refers to basic information about small and medium-sized enterprises, such as industry, number of employees, and work location.

[1364] "Desired talent data" refers to information such as the skills, experience, job title, and salary range required by SMEs for the talent they are recruiting.

[1365] "Data standardization" refers to the process of converting data acquired in different formats into a unified format.

[1366] "Registering in a database" refers to storing standardized data and making it possible to quickly search and analyze it.

[1367] "Matching" refers to using AI and algorithms to match employees of large companies with the human resource requirements of small and medium-sized enterprises to find the most suitable combination.

[1368] An "emotion engine" refers to a technology or system that collects and analyzes a user's emotional state in real time.

[1369] "Emotional state monitoring" refers to observing changes in employees' emotions in real time and obtaining information such as stress levels and satisfaction.

[1370] "Providing necessary support" refers to providing expert counseling tailored to the individual's emotional state and arranging appropriate resources.

[1371] This invention is a system for seconding senior employees of large companies to logistics centers of small and medium-sized enterprises, and in particular, by combining it with an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[1372] server

[1373] The server performs the following process:

[1374] Data collection and input

[1375] The server first collects employee data from large companies, employee request data, company data from small and medium-sized companies, and desired talent data. This data is collected via each company's database or API. It also works with an emotion engine to collect user emotion data. The collected data is standardized and registered in a database.

[1376] Examples:

[1377] Obtain the work history, skills, desired working conditions, and current emotional state of employee A of a large company using an emotion engine.

[1378] Obtain the personnel requirements and emotional data required by small and medium-sized enterprises.

[1379] Data Standardization and Matching

[1380] The acquired data is analyzed and converted into a standard format. The standardized data is registered in a database, and AI is used to match employees of large companies with small and medium-sized enterprises. By taking emotional data into account, even more accurate matching becomes possible.

[1381] Examples:

[1382] The system compares the skill requirements, experience, and sentiment data of employee A of a large company with employee B of a small or medium-sized company, and performs a highly accurate match.

[1383] Notification of results

[1384] The matching results are communicated to employees of large companies and small and medium-sized enterprises, and detailed reports including sentiment data are provided.

[1385] Terminal

[1386] The terminal performs the following process:

[1387] Data entry and confirmation

[1388] It provides an interface for employees of large companies and managers of small and medium-sized enterprises to input the necessary information. Through an emotion engine, it is possible to obtain the user's emotional state in real time. Matching results and information for interview arrangements are also notified in real time.

[1389] Examples:

[1390] Employee A uses a terminal to input and confirm his / her skills, desired conditions, and emotional state.

[1391] Managers of small and medium-sized enterprises enter the desired personnel requirements into a terminal, and emotional data generated by an emotion engine is also sent to the server.

[1392] User

[1393] The user performs the following process.

[1394] Response from senior employees

[1395] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their own emotional state in real time while adjusting their transfer and interview schedules.

[1396] Examples:

[1397] Senior employee A inputs his / her skill set and desired conditions, and the emotion engine records his / her current emotional state.

[1398] How small business managers respond

[1399] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to efficiently proceed with interviews and secondment contract procedures.

[1400] Examples:

[1401] The manager of SME B inputs the desired skill set and emotional data, arranges an interview with senior employee A, and uses the emotional data as a reference when concluding a secondment contract.

[1402] Monitoring and Support

[1403] Server-based emotion monitoring and support

[1404] The system monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[1405] Examples:

[1406] The server monitors the emotional data of senior employee A, who is on secondment, in real time and provides appropriate support if a high stress level is detected.

[1407] Applications of generative AI models

[1408] Example prompt sentence:

[1409] "Recommend the best distribution center for Senior Employee A based on the following criteria:

[1410] Skill Set: IT Support, Data Analysis

[1411] Desired working conditions: Full-time, working from home

[1412] Emotional data: Medium stress level, high satisfaction

[1413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1414] Step 1:

[1415] The server obtains employee data from large companies, employee request data, company data from small and medium-sized companies, and desired talent data. This data is collected via each company's database or API. It uses each company's database access information and API key as input, and obtains data in a standardizable format as output.

[1416] Step 2:

[1417] The server standardizes the acquired data. Specifically, it converts data stored in different formats into a unified format (for example, JSON or CSV). It uses information about each company's data format as input and obtains data in a unified format as output. For example, it can classify employee skill sets into unified categories.

[1418] Step 3:

[1419] The server registers the standardized data in a database, indexes it, and makes it available for rapid searching and analysis. It uses the standardized data as input and gets indexed database entries as output.

[1420] Step 4:

[1421] The server uses the emotion engine to collect the user's emotion data, for example, obtains the user's emotional state in real time through the emotion engine API. It uses the user's real-time data and API key as input and obtains the emotion data as output.

[1422] Step 5:

[1423] The server runs a matching algorithm based on the standardized data and emotional data. It uses AI to match employees of large companies with small and medium-sized companies. It uses the standardized data and emotional data as input and obtains the optimal matching result as output.

[1424] Step 6:

[1425] The server notifies employees of large companies and small and medium-sized businesses of the matching results, providing them as detailed reports including emotional data. The server uses the matching result data as input and obtains notification messages and reports as output.

[1426] Step 7:

[1427] The terminal provides an interface for employees of large corporations and managers of small and medium-sized enterprises to input the necessary information. Through an emotion engine, it is also possible to obtain the user's emotional state in real time. It uses the information entered by the user as input and obtains data in a standard format as output to be sent to the server.

[1428] Step 8:

[1429] The terminal notifies the user of the matching results and information for interview arrangement in real time. It uses notification data from the server as input and obtains notification messages for the user as output.

[1430] Step 9:

[1431] The user adjusts the schedule for a transfer or interview while understanding their own emotional state in real time using the emotion engine. The emotion engine data is used as input, and appropriate schedule adjustment proposals are obtained as output.

[1432] Step 10:

[1433] The server monitors the emotional state of the senior employee on secondment and provides necessary support based on that. It uses real-time emotional data as input and gets support response suggestions and resource allocation plans as output.

[1434] Example prompt sentence:

[1435] "Recommend the best distribution center for senior employees based on the following criteria:

[1436] Skill Set: IT Support, Data Analysis

[1437] Desired working conditions: Full-time, working from home

[1438] Emotional data: Medium stress level, high satisfaction

[1439] 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.

[1440] 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.

[1441] 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.

[1442] [Fourth embodiment]

[1443] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1444] 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.

[1445] 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).

[1446] 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.

[1447] 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.

[1448] 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).

[1449] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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."

[1456] The present invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and specifically operates through the collaboration of a server, terminals, and users. The mechanism and specific operation of the system will be described in detail below.

[1457] server

[1458] Data collection

[1459] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, collected via each company's database or API.

[1460] Examples:

[1461] "The server collects employee A's background, skills, and preferred working arrangements from a large company's database."

[1462] "The server collects the desired personnel requirements from a database of small and medium-sized enterprises."

[1463] Data Standardization

[1464] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[1465] Examples:

[1466] "The server standardizes employee data for large corporations into backgrounds, skill sets, and working conditions."

[1467] "The server standardizes the personnel data required by small and medium-sized enterprises into experience, skills, and working conditions."

[1468] Executing the matching algorithm

[1469] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies, taking into account their career history, skill set, and working conditions to make the best possible match.

[1470] Examples:

[1471] "The server uses AI to compare the skills required by small and medium-sized company B with the skills of employee A of large company, and selects the candidate with the highest match rate."

[1472] Notification of results

[1473] The matching results are communicated to employees of large companies and small and medium-sized enterprises, and the results are summarized in a report and sent via email and dashboard.

[1474] Examples:

[1475] The server notifies Employee A and Small Business B of the matching results and sends detailed information by email.

[1476] Terminal

[1477] Data Entry

[1478] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input the necessary information, which is then sent to a server for further processing.

[1479] Examples:

[1480] "Employee A enters his / her career history and desired conditions into the terminal and sends it to the server."

[1481] "Managers of small and medium-sized enterprises input the personnel requirements into a terminal and send them to a server."

[1482] Confirming results and arranging interviews

[1483] The matching results are checked on the terminal, and interviews and transfer contracts are arranged. Specific interview dates, times, and locations are also set on the terminal.

[1484] Examples:

[1485] "The manager of the small and medium-sized enterprise checks the matching results on the terminal and schedules an interview date and time with Employee A."

[1486] "Employee A checks the interview date and time on the terminal and approves it."

[1487] User

[1488] Senior Employees

[1489] Senior employees enter their information through a terminal, check the matching results, and then undergo an interview. If approved, they will begin their secondment to a small or medium-sized company.

[1490] Examples:

[1491] "Senior employee A enters his / her skill set and desired conditions into the terminal, and confirms the matching results when they are notified."

[1492] "Senior employee A interviews with small and medium-sized company B and officially signs a secondment contract."

[1493] small business manager

[1494] Managers of small and medium-sized enterprises can input the desired personnel requirements through the terminal, check the matching results, and also arrange interviews and process transfer contracts.

[1495] Examples:

[1496] "Enter the skill set desired by the manager of SME B into the terminal and check the matching results."

[1497] "Manager of SME B arranges an interview with Senior Employee A and concludes a secondment contract."

[1498] This system allows small and medium-sized enterprises to quickly and efficiently secure work-ready personnel, while large companies can effectively utilize the skills of senior employees, providing significant benefits to both parties.

[1499] The processing flow will be explained below.

[1500] Step 1: Data collection

[1501] The server collects employee data from the database of a large company, specifically information such as employee background, skills, qualifications, work experience, preferred work arrangements and locations.

[1502] The server collects company data and desired personnel data from a database of small and medium-sized enterprises, specifically, basic information about the company, business details, desired skill sets, job details, salary range, working hours, etc.

[1503] Step 2: Standardize the data

[1504] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, etc. By organizing data stored in different formats into a unified format, subsequent processing becomes easier.

[1505] The server also converts the human resources data required by small and medium-sized enterprises into a standard format, standardizing the required skills, experience, job title, salary range, working conditions, etc.

[1506] Step 3: Register with the database

[1507] The server registers the standardized data in a database, creating an index that enables rapid data search and AI analysis.

[1508] Data on employees of large companies and the personnel data required by small and medium-sized enterprises is stored in a database, and appropriate tags are added to make it easy to search.

[1509] Step 4: Run the matching algorithm

[1510] The server passes the standardized data from the database to the AI, which runs a matching algorithm to match the employee's skill set and desired conditions with the skill sets and working conditions required by the small and medium-sized enterprise, and finds the best match.

[1511] The server reviews the AI ​​results and lists the most relevant matches.

[1512] Step 5: Notification of results

[1513] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized companies by sending the results via email or an online dashboard.

[1514] The server will send a notification with detailed information about the match, including contact information.

[1515] Step 6: Data entry

[1516] Using the terminals, employees of large companies and managers of small and medium-sized enterprises input the necessary information. Employees input their career history, skills, and desired conditions, while managers of small and medium-sized enterprises input the desired skill sets and job content.

[1517] The entered data is sent to the server in real time and used for subsequent processing.

[1518] Step 7: Check the results and arrange an interview

[1519] The matching results are checked on the terminal and the interview and secondment contract are arranged. The manager of the SME checks the detailed information of the matched senior employee and sets the interview date and time.

[1520] Senior employees check the interview date and time on the terminal and make any changes or approvals as necessary.

[1521] Step 8: Interview and decision

[1522] The senior employee as the user will have an interview with the SME. As a result of the interview, the SME will decide whether to officially hire the senior employee who wishes to be seconded.

[1523] A small or medium-sized enterprise enters into a secondment contract and registers the contract details on a server.

[1524] Step 9: Commencement and monitoring

[1525] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[1526] Regularly collect and monitor performance data from senior staff on secondment and provide any support required.

[1527] As a result, this system will alleviate the labor shortages of small and medium-sized enterprises and effectively utilize the experience and skills of senior employees at large companies, providing a mutually beneficial solution.

[1528] Example 1

[1529] 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."

[1530] In recent years, there has been a demand for increased mobility of human resources between large and small organizations. However, many large organizations have limited opportunities to effectively utilize the skills of senior employees, while small organizations have difficulty securing human resources who can immediately contribute. To solve these issues, a system is needed that accurately matches the needs of both parties and quickly and efficiently dispatches human resources.

[1531] 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.

[1532] In this invention, the server includes means for acquiring employee information of the large organization, employee preference information, company information of the small organization, and necessary human resources information, means for verifying and standardizing the acquired data and registering it in a database, means for executing an artificial intelligence model to match employees of the large organization with small organizations based on the standardized data, and means for notifying employees of the large organization and the small organization of the matching results, thereby enabling senior employees of the large organization to be dispatched to the small organization quickly and efficiently.

[1533] A "large organization" is a company with a large number of employees and multiple business divisions and processes.

[1534] "Employee Information" means data related to an employee, such as an employee's background, skill set, job title, work history, and evaluation information.

[1535] "Employee preference information" refers to data that indicates an employee's individual preferences and conditions, such as desired working style, work location, job content, and working hours.

[1536] A "small organization" is a business or organization with a small number of employees and limited resources.

[1537] "Company information" refers to general information related to a company, such as the company's size, industry, location, business activities, and the type of personnel it is seeking.

[1538] "Required human resources information" refers to data that indicates the specific job requirements, such as the skill set, experience, qualifications, and working conditions that a company is looking for.

[1539] "Means of acquisition" refers to the methods and processes for obtaining the required data through a database or API.

[1540] "Validation and standardization" refers to the process of converting data stored in different formats into a unified format to ensure data consistency and accuracy.

[1541] A "database" refers to a system for efficiently storing, managing, and searching large amounts of data.

[1542] An "artificial intelligence model" refers to an algorithm that uses machine learning or deep learning to analyze data and perform a specific task (in this case, matching).

[1543] "Matching" refers to the process of finding the right match based on specific criteria, which in this case means matching employees from larger organizations with smaller organizations.

[1544] "Means of notification" refers to the method by which matching results are communicated to relevant parties, such as through email, dashboards, notification systems, etc.

[1545] The present invention is a system for dispatching senior employees of a large organization to a small organization, and specifically, a mechanism in which a server, a terminal, and a user work together. Specific embodiments of the system are described in detail below.

[1546] First, the server collects employee information and preference information from large organizations, company information from small organizations, and necessary human resources information. This data is obtained via each company's database or API. For example, the server calls the large organization's HR system API to obtain employee backgrounds and skill sets, and uses the small organization's job information API to collect company recruitment requirements.

[1547] The server validates and standardizes the collected data, which is often stored in different formats. Standardizing the data into a specific format facilitates subsequent analysis. For example, the server converts employee data from a large organization into a standard format based on background, skill set, and working conditions.

[1548] Next, the server uses this standardized data to match employees from large organizations with smaller organizations using an artificial intelligence model. The AI ​​model is an algorithm that incorporates machine learning and deep learning, and comprehensively evaluates each employee's skill set, background, and desired conditions to make the optimal match. For example, the server loads the AI ​​model, provides background, skills, and working conditions as input data, analyzes the model's execution results, and selects highly suitable candidates.

[1549] The server notifies the employees of the large organization and the small organization of the matching results. The results are summarized in a report format and sent via email or dashboard. For example, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be displayed when logged in.

[1550] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. The entered data is then sent to a server and used in subsequent processes. For example, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation.

[1551] The device also provides an interface for checking matching results and arranging interviews and temporary employment contracts. Specific interview dates, times, and locations can also be set on the device. For example, an administrator at a small organization can log in from the device and check the details of the matching results, and employee A can then check the interview date and time on the device and press the approval button to complete the interview arrangement.

[1552] Example of input prompt for generative AI model

[1553] The following prompts can be used to provide the necessary input to the generative AI model:

[1554] "Please explain in detail the process by which your server collects employee data for a large organization."

[1555] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[1556] This system allows senior employees of large organizations to be quickly and efficiently dispatched to smaller organizations, making effective use of their skills, while at the same time allowing smaller organizations to quickly secure work-ready personnel.

[1557] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1558] Step 1: Data collection

[1559] server

[1560] Input: Employee data for large organizations, employee preference data, company data for small organizations, human resources data

[1561] Specifically, the server collects the necessary data through each company's database and API. The server calls the HR system API of a large organization to obtain employee backgrounds and skill sets, and uses the job information API of a small organization to collect company recruitment requirements.

[1562] Output: Raw employee data, company data, talent data

[1563] Step 2: Data validation and standardization

[1564] server

[1565] Inputs: Raw employee data, company data, talent data

[1566] The server then validates and standardizes the data it receives, preprocessing it to detect and complete missing or incorrect data. Specifically, the server converts employee data from large companies into a standard format based on background, skill set, and working conditions.

[1567] Output: Standardized employee data, company data, and talent data

[1568] Step 3: Register with the database

[1569] server

[1570] Inputs: Standardized employee data, company data, talent data

[1571] The server registers the validated and standardized data in a database, making it easily accessible for subsequent processing. Specifically, the server stores the standardized data in the database with an index.

[1572] Output: Employee data, company data, and human resources data stored in a database

[1573] Step 4: Run the matching algorithm

[1574] server

[1575] Input: Employee data, company data, and human resources data stored in a database

[1576] The server uses an AI algorithm to perform optimal matching based on standardized data. The AI ​​model uses machine learning and deep learning to comprehensively evaluate each employee's skill set, background, and desired conditions. Specifically, the server loads the AI ​​model and provides background, skills, and working conditions as input data. The model's execution results are then analyzed to evaluate and select highly suitable candidates.

[1577] Output: Matching result data

[1578] Step 5: Notification of results

[1579] server

[1580] Input: Matching result data

[1581] The server notifies the matching results to the employees of the large organization and the small organization. The results are summarized in a report format and sent via email or dashboard. Specifically, the server compiles the matching results into a report and sends it to employee A and the administrator of the small organization via email, and also uploads it to the dashboard so that it can be viewed when logged in.

[1582] Output: Notified matching results

[1583] Step 6: Data entry

[1584] Terminal

[1585] Input: Employee data from users, desired data, and data on the personnel required by companies

[1586] The terminal provides an interface for employees of large organizations and managers of small organizations to enter the necessary information. Specifically, Employee A enters his / her career history, skills, and desired working conditions into a form on the terminal, and the manager enters the desired personnel conditions into the terminal and submits them after confirmation. The data is sent to the server and used for subsequent processing.

[1587] Output: Employee data, preference data, and talent data sent to the server

[1588] Step 7: Check the results and arrange an interview

[1589] Terminal

[1590] Input: Notified matching result data

[1591] The matching results are checked on the terminal, and the interview and dispatch contract are arranged. Detailed interview date and time and location can also be set on the terminal. Specifically, the administrator of the small organization logs in from the terminal, checks the details of the matching results, and employee A checks the interview date and time on the terminal and presses the approval button, completing the interview arrangement.

[1592] Output: Confirmed interview date, time and location data

[1593] Example of input prompt for generative AI model

[1594] The following prompts can be used to provide the necessary input to the generative AI model:

[1595] "Please explain in detail the process by which your server collects employee data for a large organization."

[1596] "Please tell me specifically what kind of data the user inputs on the terminal and how it is processed."

[1597] (Application example 1)

[1598] 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."

[1599] When seconding senior employees from large companies to small and medium-sized enterprises, there is a problem in matching personnel, as it is difficult to quickly and efficiently find personnel with the appropriate skill sets and experience. Furthermore, the procedures for arranging interviews and signing secondment contracts after matching are complicated, making it difficult for the parties involved to communicate smoothly. Furthermore, there is a problem in that a lack of performance monitoring during the secondment makes it difficult to maximize the benefits of the secondment.

[1600] 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.

[1601] In this invention, the server includes: means for acquiring employee data of large companies, employee request data, company data of small and medium-sized enterprises, and desired talent data; means for standardizing the acquired data and registering it in a database; means for matching employees of large companies with small and medium-sized enterprises based on the standardized data; means for notifying employees of large companies and small and medium-sized enterprises of the matching results; and means for matched employees of large companies and managers of small and medium-sized enterprises to arrange interviews and conclude secondment contracts via an application. This enables quick and efficient matching of talent with appropriate skill sets and experience, and smooth subsequent procedures and collaboration. Furthermore, performance monitoring during the secondment maximizes the effectiveness of the secondment.

[1602] A "large company" refers to a company that has a large number of employees and conducts large-scale business activities.

[1603] "Small and medium-sized enterprises" refer to companies that conduct business activities on a relatively small scale and whose number of employees and sales revenue do not meet certain standards.

[1604] "Employee data" refers to data that includes information about an employee's background, skills, working conditions, etc.

[1605] "Employee request data" refers to data regarding employees' desired working style, work location, job content, and other requests.

[1606] "Company data" refers to data that includes basic information about the company, business activities, and the desired personnel requirements.

[1607] "Desired talent data" refers to data such as the skill sets, experience, and working conditions that companies are looking for.

[1608] "Data standardization" refers to the process of converting data stored in different formats into a unified format.

[1609] A "database" is a system for storing and managing data according to certain rules.

[1610] "Matching" refers to the process of connecting suitable candidates with companies based on certain criteria.

[1611] "Notification" refers to the act of conveying information such as matching results to relevant parties.

[1612] "Interview arrangement" refers to the process of arranging the date, time, and location of an interview between the candidate and the company after a match has been made.

[1613] A "secondment contract" refers to a contract under which an employee works for another company for a certain period of time.

[1614] "Application" refers to a software program that a user uses for a specific purpose.

[1615] "Performance monitoring" refers to the act of monitoring and evaluating the work performance of employees on secondment.

[1616] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and operates in cooperation with a server, terminals, and users. The specific mechanism and operation of this system will be described in detail below.

[1617] server

[1618] Data collection

[1619] The server acquires employee data from large companies, employee request data, company data from small and medium-sized enterprises, and desired talent data. This data is collected via the company's database or API. For example, "The server collects employee backgrounds, skills, and desired working arrangements from the large company's database," or "The server collects the desired talent conditions from the small and medium-sized enterprise's database."

[1620] Data Standardization

[1621] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for generative AI models to analyze it. Specifically, the server standardizes employee data from large companies into career history, skill sets, and working conditions, and the server standardizes the human resources data required by small and medium-sized enterprises into experience, skills, and working conditions.

[1622] Executing the matching algorithm

[1623] Based on standardized data, a generative AI model is used to match employees of large companies with small and medium-sized companies. The model makes an optimal match by comprehensively assessing backgrounds, skill sets, and working conditions. For example, "the server uses AI to match the skills required by small and medium-sized companies with the skills of employees at large companies and selects candidates with a high match rate."

[1624] Notification of results

[1625] The matching results are notified to employees of large companies and small and medium-sized enterprises. The results are compiled in a report format and sent via email or dashboard. Specifically, "the server notifies employees and small and medium-sized enterprises of the matching results and sends detailed information by email."

[1626] Interview arrangement and contract

[1627] The matched employees of the large company and the managers of the SMEs then arrange interviews and conclude secondment contracts through the application. For example, "the server arranges interview dates and times between the employees and the SMEs, and provides an interface for concluding secondment contracts."

[1628] Terminal

[1629] Data Entry

[1630] The terminal provides an interface for employees of large corporations and managers of small and medium-sized enterprises to input the necessary information. The input data is sent to a server and used for subsequent processing. For example, "an employee enters their career history and desired qualifications into the terminal and sends it to the server," or "a manager of a small or medium-sized enterprise enters the qualifications of the personnel they are looking for into the terminal and sends it to the server."

[1631] Confirming results and arranging interviews

[1632] The matching results are checked on the terminal, and interviews and secondment contracts are arranged. Specific interview dates, times, and locations are also set on the terminal. For example, "The manager of a small or medium-sized enterprise checks the matching results on the terminal and sets the interview date and time with the employee," or "The employee checks the interview date and time on the terminal and approves it."

[1633] User

[1634] Senior Employees

[1635] Senior employees enter their own information through the terminal and check the matching results. They then undergo an interview and, if approved, begin their secondment to the SME. For example, "senior employees enter their own skill set and desired conditions into the terminal, and check the matching results when they are notified," or "senior employees interview with the SME and formally sign a secondment contract."

[1636] small business manager

[1637] Managers of small and medium-sized enterprises use the terminal to input the desired personnel criteria and check the matching results. They also arrange interviews and process secondment contracts. For example, "Managers of small and medium-sized enterprises input the desired skill set into the terminal and check the matching results" or "Managers of small and medium-sized enterprises arrange interviews with senior employees and conclude secondment contracts."

[1638] Prompt Sentence Examples

[1639] Create a Python function that accesses the API to retrieve employee data from large companies and the talent data required by small and medium-sized enterprises, and perform matching using a generative AI model. Write a script to notify the matching results by email.

[1640] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1641] Step 1:

[1642] The server collects employee data from large companies, employee requirements data, company data from small and medium-sized companies, and desired talent data via APIs. This involves connecting to corporate databases and external data sources. The input to this process is the API or database query, and the output is the retrieved raw data. Specifically, the server executes the query to extract the relevant data and receives it in JSON format.

[1643] Step 2:

[1644] The server standardizes the data it receives. If the data is stored in a different format, it converts it into a consistent format. The input is the raw data it received, and the output is the standardized data. Specifically, it uses the pandas library to convert the data into a data frame and then converts it to the required schema.

[1645] Step 3:

[1646] The server registers the standardized data in the database. The input of this process is the standardized data, and the output is the data stored in the database. Specifically, the server uses an SQL query to store the data in the database with an INSERT statement.

[1647] Step 4:

[1648] The server uses a generative AI model based on standardized data to match employees of large companies with small and medium-sized enterprises. The input is standardized employee data of large companies and the talent data desired by small and medium-sized enterprises, and the output is the matching results. Specifically, the scikit-learn library is used to analyze the data using algorithms such as nearest neighbor methods to generate optimal matching pairs.

[1649] Step 5:

[1650] The server notifies the matching results. The input of this process is the generated matching results, and the output is sending a notification. Specifically, the server uses the SMTP protocol to send emails to notify each employee and the manager of the small business of the matching results.

[1651] Step 6:

[1652] The terminal provides an interface for employees of large companies and managers of small and medium-sized companies to arrange interviews and sign secondment contracts. The input is a notification of the matching results from the server, and the output is the completion of the interview arrangement or secondment contract. Specifically, the calendar function on the terminal is used to select a date and time, and the arrangement is completed by pressing the confirmation button.

[1653] Step 7:

[1654] Users (senior employees and managers of small and medium-sized enterprises) use the terminal to enter their own information and check the matching results. The input is a notification from the server, and the output is the confirmed information and the completion of the interview and contract. Specifically, senior employees enter their own skill set and desired conditions, and the manager enters the desired skill set. Based on this, the matching results are confirmed and the interview date and time are set.

[1655] 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.

[1656] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[1657] server

[1658] Data collection

[1659] The server first obtains employee data, employee request data, company data, and desired talent data from large companies, small and medium-sized companies, collected via each company's database or API, and then connects with an emotion engine to collect user emotion data.

[1660] Examples:

[1661] "The server collects Employee A's background, skills, and preferred working style from a large company's database. It then uses an emotion engine to obtain Employee A's current emotional state."

[1662] "The server collects the desired personnel requirements from the database of small and medium-sized enterprises. Then, it uses an emotion engine to obtain emotional data on the requests of the managers of small and medium-sized enterprises."

[1663] Data Standardization

[1664] The acquired data is analyzed and converted into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[1665] Examples:

[1666] "The server standardizes employee data from large corporations into backgrounds, skill sets, desired working conditions, and sentiment data."

[1667] "The server standardizes SMEs' talent needs data into required skills, experience, job title, salary range, and sentiment data."

[1668] Registering in the database

[1669] Standardized data is registered in a database and indexed to enable rapid search and analysis.

[1670] Examples:

[1671] "The server registers the standardized data in a database, storing data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data."

[1672] Executing the matching algorithm

[1673] Based on standardized data, AI is used to match employees of large companies with small and medium-sized companies. By taking emotional data into account, more accurate matching becomes possible.

[1674] Examples:

[1675] The server uses AI to match the skills required by the SME with employee A's skills and emotional data, and selects the candidate with a high match rate.

[1676] Notification of results

[1677] The matching results are communicated to employees of large companies and managers of small and medium-sized businesses in a detailed report that includes sentiment data.

[1678] Examples:

[1679] The server notifies Employee A and SME B of the matching results and sends detailed information in a report format via email or dashboard.

[1680] Terminal

[1681] Data Entry

[1682] The terminal provides an interface for employees of large companies and managers of small and medium-sized enterprises to input necessary information. Through the emotion engine, it is possible to obtain the user's emotional state in real time.

[1683] Examples:

[1684] "Employee A uses a device to input his / her career history and desired conditions, and records his / her emotional state at that time based on feedback from the emotion engine."

[1685] "Managers of small and medium-sized enterprises input the desired personnel conditions into a terminal, and at the same time, the emotion engine provides the manager's emotional data, which is then sent to the server."

[1686] Confirming results and arranging interviews

[1687] The matching results can be checked on the device, and the interview and secondment contract can be adjusted. By taking emotional data into consideration, the interview date and time and procedures can be flexibly adjusted.

[1688] Examples:

[1689] "The manager of the small and medium-sized enterprise checks the matching results on a terminal and schedules an interview date and time with Employee A based on the emotional data."

[1690] "Employee A checks the interview date and time on their device and approves or changes it based on their emotional state."

[1691] User

[1692] Senior Employees

[1693] Senior employees can input their information through a terminal, check the matching results, and use an emotion engine to understand their own emotional state in real time while adjusting their transfer and interview schedules.

[1694] Examples:

[1695] "Senior employee A enters his / her skill set and desired conditions into the terminal, and the emotion engine also records his / her current emotional state."

[1696] "Senior employee A interviews with small and medium-sized company B and proposes the optimal schedule based on emotional data."

[1697] small business manager

[1698] Managers of small and medium-sized enterprises can input the desired personnel requirements through a terminal, check the matching results, and use the emotion engine to efficiently proceed with interviews and secondment contract procedures.

[1699] Examples:

[1700] "The manager of SME B inputs the desired skill set into the terminal and also records his / her own emotional data provided by the emotion engine."

[1701] "Manager of SME B arranges an interview with Senior Employee A and uses the emotional data as a reference when concluding a secondment contract."

[1702] Monitoring and Support

[1703] Server-based emotion monitoring and support

[1704] The system monitors the emotional state of senior employees on secondment and provides necessary support based on that. The emotion engine analyzes stress levels and satisfaction in real time and provides information that contributes to improving performance.

[1705] Examples:

[1706] "The server monitors the emotional data of Senior Employee A, who is on loan, in real time, and provides appropriate support if a high stress level is detected."

[1707] As described above, by combining this system with an emotion engine, it is possible to achieve highly accurate matching that takes into account the user's emotional state and to monitor performance during secondment. This allows small and medium-sized enterprises to secure the most suitable personnel, and senior employees of large companies to smoothly perform at their seconded companies.

[1708] The processing flow will be explained below.

[1709] Step 1: Data collection

[1710] The server collects employee data from a large company's database, specifically, information such as employees' career history, skills, qualifications, work experience, desired work style and location, etc. It also obtains the employee's current emotional data via an emotion engine.

[1711] The server collects company data and desired personnel data from the SME database, specifically, basic information about the SME, business activities, desired skill sets, job duties, salary range, working hours, etc. Next, it collects emotion data from SME managers via an emotion engine.

[1712] Step 2: Standardize the data

[1713] The server converts employee data from large companies into a standard format, organizing each item into career history, skill set, desired working conditions, and sentiment data. By unifying data stored in different formats, subsequent processing becomes easier.

[1714] The server also converts the human resource data required by small and medium-sized enterprises into a standard format, standardizing it into required skills, experience, job title, salary range, working conditions, and emotional data.

[1715] Step 3: Register with the database

[1716] The server registers the standardized data in a database, which then creates an index for rapid search and analysis.

[1717] Data on employees of large companies, data on the talent needs of small and medium-sized enterprises, and emotional data are stored in a database, and appropriate tags are added to make it easy to search.

[1718] Step 4: Run the matching algorithm

[1719] The server passes the standardized data to the AI, which runs a matching algorithm that compares the employee's skill set and desired conditions with the skill sets and working conditions required by small and medium-sized enterprises, and also takes emotional data into account to make the optimal match.

[1720] The server reviews the AI ​​results and lists candidates with high suitability.

[1721] Step 5: Notification of results

[1722] The server generates a report of the matching results and notifies employees of large companies and managers of small and medium-sized enterprises, including specific suggestions that take into account the sentiment data.

[1723] The server will send you a notification via email and / or dashboard with detailed match results.

[1724] Step 6: Data entry

[1725] Employees of large companies and managers of small and medium-sized enterprises use terminals to input the necessary information: employees enter their backgrounds, skills, and desired qualifications, and emotional data is also provided based on feedback from the emotion engine.

[1726] Managers of small and medium-sized enterprises also enter the required skill sets and job descriptions on the terminal, and emotional data is also sent to the server.

[1727] Step 7: Check the results and arrange an interview

[1728] The matching results can be checked on the device, and interviews and secondment contracts can be arranged. Interview dates and procedures can be flexibly adjusted based on emotional data.

[1729] Managers of small and medium-sized enterprises review the matching results and decide on interview dates and times with suitable employees. Using an emotion engine, the system suggests optimal schedules based on the emotional state of both parties.

[1730] Senior employees check the interview date and time on their devices and approve or change the date depending on their emotional state.

[1731] Step 8: Interview and decision

[1732] Senior employees act as users, conducting interviews with small and medium-sized enterprises and proposing optimal schedules based on emotional data.

[1733] The small and medium-sized enterprise evaluates the interview results and, taking into consideration the emotional data, decides whether to officially hire the most suitable candidate. A secondment contract is concluded and the details of the contract are registered on the server.

[1734] Step 9: Commencement and monitoring

[1735] The server notifies the senior employee and the SME of the start date of the transfer and related procedural information, allowing the senior employee to begin working for the SME.

[1736] The server periodically collects performance data from senior employees on loan and uses an emotion engine to monitor their emotional state in real time. If high stress levels or a decline in satisfaction are detected, appropriate support is provided.

[1737] By combining this with an emotion engine, this system achieves highly accurate matching that takes into account the user's emotional state and monitors performance during secondment. This allows small and medium-sized enterprises to secure the best talent, and senior employees of large companies to smoothly perform at their seconded companies.

[1738] Example 2

[1739] 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."

[1740] Conventional matching systems have problems with low matching accuracy and insufficient performance monitoring after transfer when seconding senior employees of large companies to SMEs. Furthermore, they are unable to take into account the emotional state of employees and managers of SMEs, making it difficult to smoothly adjust matching and secondment contracts.

[1741] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee data of large companies, employee request data, data on small and medium-sized organizations, and data on desired human resources, means for acquiring emotion data using an emotion engine, means for analyzing and standardizing the acquired data and emotion data, means for registering the standardized data in a database and creating an index, means for matching employees of large companies with small and medium-sized organizations using a generative AI model based on the standardized data, and means for notifying employees of large companies and small and medium-sized organizations of the matching results and emotion data in the form of a detailed report. This enables high-precision matching based on emotion data and performance monitoring after secondment.

[1742] "Large company employee data" refers to information about employees employed by large companies, including their career history, skill sets, working conditions, etc.

[1743] "Employee request data" refers to data on the working conditions, career paths, work locations, and other requests of employees of large companies.

[1744] "Data on small and medium-sized organizations" refers to information on small and medium-sized enterprises, including the type of industry, business activities, location, size, and so on.

[1745] "Desired talent data" refers to data on the skills, experience, job title, salary range, etc. of the talent that SMEs require.

[1746] An "emotion engine" is a software or hardware system that analyzes a user's emotional state and measures stress levels, satisfaction, motivation, etc.

[1747] "Emotion data" is data relating to the user's emotional state obtained using an emotion engine, and includes indicators such as stress level, happiness level, and concentration level.

[1748] "Generative AI models" refer to algorithms and machine learning models that use artificial intelligence technology to perform data analysis and predictions.

[1749] "Standardization" is the process of converting data of different formats and structures into a uniform form.

[1750] A "database" is a system for storing collected data and making it easy to search and analyze.

[1751] An "index" is a structure for quickly searching data in a database.

[1752] "Matching" refers to comparing collected employee data from large companies with the personnel data required by small and medium-sized enterprises to find the optimal combination.

[1753] "Notification" is the process of sending information such as matching results and emotion data to the user.

[1754] A means of adjusting a "secondment contract" is a method or system for adjusting the contract content and schedule for an employee of a large company to be seconded to a small or medium-sized company.

[1755] "Monitoring" is the process of continuously observing the performance and emotional state of an employee while on secondment.

[1756] "Support" means providing necessary assistance and responses based on the monitoring results.

[1757] This invention is a system for seconding senior employees of large companies to small and medium-sized enterprises, and in particular, by combining an emotion engine, it improves the accuracy of matching results and monitors performance during the secondment. The mechanism and specific operation of this system are described in detail below.

[1758] System Overview

[1759] This system collects and analyzes employee data from large companies and the human resources data required by small and medium-sized enterprises, uses an emotion engine to obtain emotional data, performs highly accurate matching using a generative AI model, and also monitors the emotional state of employees on secondment and provides support as needed.

[1760] Processing performed by the server

[1761] Data collection

[1762] The server first obtains employee data, employee request data, and company data and desired talent data for large companies and SMEs. This data is collected via each company's database or API. It also uses an emotion engine to collect emotion data from employees and SME managers.

[1763] Examples:

[1764] The server collects Employee A's career history, skills, and desired working style from a large company's database, and uses an emotion engine to obtain Employee A's current emotional state.

[1765] The server collects the conditions of the desired personnel from the database of small and medium-sized enterprises, and obtains the emotional data of the managers of the small and medium-sized enterprises using an emotion engine.

[1766] Data Standardization

[1767] The server analyzes the acquired data and converts it into a standard format. By unifying data stored in different formats, it becomes easier for AI to analyze it.

[1768] Examples:

[1769] A server standardizes employee data from a large corporation into background, skill sets, desired working conditions, and sentiment data.

[1770] The server standardizes the talent data required by small and medium-sized businesses into required skills, experience, job title, salary range, and sentiment data.

[1771] Registering in the database

[1772] The server registers the standardized data in a database and creates an index to enable quick searches and analysis.

[1773] Examples:

[1774] The server registers the standardized data in a database, storing data on employees of large companies, data on the personnel sought by small and medium-sized enterprises, and emotional data.

[1775] Executing the matching algorithm

[1776] The server uses generative AI models based on standardized data to match employees of large companies with small and medium-sized businesses. By taking into account emotional data, it is possible to achieve even more accurate matching.

[1777] Examples:

[1778] The server uses the generated AI model to match the skills required by the SME with Employee A's skills and emotional data, and selects the candidate with a high match rate.

[1779] Notification of results

[1780] The server then sends detailed reports containing matching results and sentiment data to employees of large companies and managers of small and medium-sized enterprises, allowing them to provide appropriate feedback.

[1781] Examples:

[1782] The server notifies Employee A and SME B of the matching results and sends detailed information in report format ...

Claims

1. A means of obtaining employee data from large companies, employee request data, company data from small and medium-sized enterprises, and desired personnel data; A means of standardizing the acquired data and registering it in a database; A means of matching employees of large companies with small and medium-sized enterprises based on standardized data, A means of notifying employees of large companies and small and medium-sized enterprises of the results of the matching; A system including:

2. The system of claim 1 further comprising means for coordinating a secondment contract at a small or medium-sized company for a matched employee of the large company.

3. 10. The system of claim 1, further comprising means for monitoring the performance of employees of a large corporation on loan.

Images