system

Abstract

We provide the system. [Solution] A means of receiving data on requests from companies, Means for obtaining employee career and performance data, A means for analyzing the aforementioned request data and career data to extract features, Based on the extracted characteristics, a means for identifying employees who meet the requirements, means for outputting the information of the identified employee, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present invention aims to solve the problems of manpower shortage faced by enterprises and the issue of effective utilization of employees. In particular, it is difficult for small and medium-sized enterprises to quickly secure personnel with necessary skills, while large enterprises require activation and effective allocation of employees. In such a situation, a system for efficiently matching personnel according to the specific needs of enterprises is necessary.

Means for Solving the Problems

[0005] This invention provides a system that receives corporate request data and acquires employee career and performance data. This system includes means for analyzing the request and career data to extract necessary skills and experience. Furthermore, it enables the optimization of matching companies with talent by identifying employees who fit the corporate requirements based on the extracted characteristics and outputting that information. In addition, natural language processing technology is introduced into the analysis, and accuracy is improved by using a quantified degree of fit.

[0006] A "company" is an organization that engages in economic activities such as producing, providing, and selling goods and services.

[0007] "Required data" refers to data that indicates the conditions and information regarding the skills and personnel that a company needs.

[0008] "Employees" refers to individuals who are employed by a company and engaged in specific tasks.

[0009] "Career data" refers to data that includes information about the duties, positions, and projects an employee has worked on to date.

[0010] "Performance data" refers to information about the results and specific performance that employees have achieved in the past.

[0011] "Analysis" refers to the act of examining and evaluating data in detail to reveal the underlying patterns and characteristics.

[0012] "Feature extraction" refers to the process of identifying and extracting useful information and features from data.

[0013] "Natural language processing technology" is a technology that enables computers to understand and process human language.

[0014] "Fit" is a numerical representation of how well an employee's skills and experience match the company's requirements.

[0015] "Output" refers to the act of displaying processed information or results externally or transmitting them to other systems.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention relates to a system for efficiently matching companies with the personnel they need. Specifically, it involves a server receiving data on a company's requirements, collecting and analyzing employee career and performance data based on that data, and implementing a process to identify the most suitable personnel.

[0038] First, the user inputs the company's requirements data via a terminal. This requirements data includes the desired skills, job duties, location, and duration. The server receives this requirements data and retrieves employee history and performance data from its stored database.

[0039] Next, the server uses natural language processing technology to analyze the requirements data and career data. It quantifies the skills and experience of each employee and calculates how well they match the company's needs. This identifies the skill sets of employees that match the requirements data and calculates the degree of fit.

[0040] Once the optimal match is achieved, the server outputs the results to the user's terminal. Based on this output, the company user can make decisions to hire employees that meet their requirements.

[0041] As a concrete example, consider a small or medium-sized IT company seeking an employee with extensive programming experience for an AI project. When the user inputs the requirements data, the server searches the resumes of programmers who have previously participated in AI projects and selects the most suitable candidate. As a result, it becomes possible to quickly provide personnel that meet the company's needs. In this way, the present invention provides a system that solves the personnel shortage in companies and simultaneously promotes the effective utilization of employees.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The terminal receives the company's request data entered by the user. This request data includes required skills, experience, job description, work location, and planned start date.

[0045] Step 2:

[0046] The server formats the request data received from the terminal into a parseable format. This formatting involves data cleaning and standardization.

[0047] Step 3:

[0048] The server retrieves employee history and performance data from the database. This includes information about the employee's work history, skill set, and achievements.

[0049] Step 4:

[0050] The server analyzes request data and history data using natural language processing techniques. It extracts important keywords and features from each data set and converts them into structured data.

[0051] Step 5:

[0052] The server matches the conditions in the request data with the features in the history data and quantifies the degree of fit. This process uses cosine similarity and machine learning algorithms to evaluate how well they match.

[0053] Step 6:

[0054] The server lists the calculated suitability scores for all employees and identifies the most suitable candidate. It then selects the employee with the highest suitability score as the optimal candidate.

[0055] Step 7:

[0056] The server outputs information about the identified individual to the user's terminal. Here, a detailed profile and reasons for recommendation are presented.

[0057] Step 8:

[0058] Users review the information presented through their devices and make hiring decisions based on the matching results. At this stage, the user makes the final decision on whether or not to request secondment.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] When conducting efficient talent matching, a challenge exists in quickly and accurately identifying workers with the specific skills and experience required by companies. In particular, there is a need for flexible analytical methods that can appropriately address diverse requirements.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for receiving organizational request information, means for acquiring worker history and performance information, and means for analyzing the request information and history information using natural language processing technology. This makes it possible to quickly identify and provide the most suitable worker to meet the diverse needs of a company.

[0064] "Organizational requirements information" refers to data that includes conditions such as the skills, experience, job duties, work location, and length of employment that companies and organizations require from personnel who fulfill specific roles.

[0065] "Worker history and performance information" refers to data that shows the job duties, achievements, and skill sets that a particular individual has experienced to date.

[0066] "Methods for extracting features" refer to the process of identifying and extracting important elements from given request information and career information to address specific conditions and requirements.

[0067] "Natural language processing technology" refers to a set of technologies that enable computers to understand and analyze information written in human language.

[0068] "Means for calculating quantified fit" refers to the process of generating a quantitative score to measure the degree of agreement between the requirements information and the worker's experience information.

[0069] "Utilizing generative AI models" refers to the process of analyzing and predicting data using models based on artificial intelligence technology.

[0070] This invention relates to an information system for efficiently matching personnel to the needs of an organization. Its aim is to quickly identify and provide workers who meet the company's requirements.

[0071] Users input organizational requirements via a terminal. This requirements include detailed conditions such as required skills, job responsibilities, work location, and employment period. For example, if an organization is looking for someone with "experience in AI projects and over 5 years of development experience using Python," this information is entered into the terminal and sent to the server.

[0072] The server retrieves worker history and performance information from the database based on the received request information. The server further analyzes the request information and worker history information using natural language processing (NLP) techniques. During this process, the server uses NLP techniques to extract important features from unstructured data and performs calculations to quantify that information. A generative AI model is then applied to refine the interpretation of the data.

[0073] Based on the analysis results, the server identifies the worker who best matches the requirements. The degree of suitability is quantified and displayed as a score indicating which worker most closely fits the organization's requirements. Based on these results, the user can make a hiring decision.

[0074] This system allows organizations to quickly identify candidates with the required skill sets, enabling them to address talent shortages and utilize resources efficiently. An example prompt would be: "We are looking for a worker with experience in AI projects and over 5 years of experience using Python. Please provide candidates who meet these criteria."

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] Users input organizational requirements into a terminal. Specifically, they fill in detailed information such as required skills, job description, work location, and employment period in a form. This information is sent from the terminal to the server as initial input for the entire system. Based on the input, the requirements information is sent to the server and processing begins.

[0078] Step 2:

[0079] The server receives request information sent from the terminal. This request information is temporarily stored in a database in a structured format. Specifically, the server verifies the integrity of the data using a communication protocol and then performs the saving process. This process prepares the dataset for analysis.

[0080] Step 3:

[0081] The server retrieves and searches for worker history and performance information from its stored database. Database technologies such as SQL queries are used to narrow down the list of suitable candidates for the requested information. The retrieved information is then prepared for subsequent analysis processing within the server.

[0082] Step 4:

[0083] The server uses natural language processing technology to analyze the request information and acquired history information. This analysis employs a generative AI model to extract and quantify important features from unstructured data. Specifically, the natural language processing engine tokenizes the input text and converts it into features for skill matching. This process yields the analyzed dataset.

[0084] Step 5:

[0085] The server calculates the degree of fit based on the analysis results. Here, the degree of match with the requested information is numerically evaluated using a scoring model or machine learning model. Based on the resulting score, the server lists candidates with high fit.

[0086] Step 6:

[0087] The server outputs information on the most suitable worker to the user's terminal based on the calculated suitability score. The user receives these results and reviews the detailed profile to make a hiring decision. The output information is displayed visually in a UI format to support the decision-making process.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In today's digital market, companies are required to quickly and accurately identify workers with specific skills and experience. However, traditional systems lack mechanisms to efficiently match companies with personnel specialized in their specific requirements and market operations, making it difficult to select the right workers.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes a device for receiving corporate request data, a device for acquiring worker work history and performance data, and a device for providing an interface on which requirements for digital market operations can be entered. This makes it possible to quickly list and display workers best suited to the corporate digital market operations.

[0093] An "device" is a machine or mechanism designed to serve a specific purpose.

[0094] A "worker" is a person who engages in a specific job and possesses the skills and experience required for it.

[0095] "Work history" refers to historical information about the jobs and roles an employee has held in the past.

[0096] "Performance data" refers to information about the work results and achievements that an employee has made to date.

[0097] An "interface" is a means or environment for humans and systems to exchange information and interact with each other.

[0098] "Requirements" refer to the conditions or abilities necessary to achieve a specific goal.

[0099] "List view" is a method of displaying information in a bulleted list format, making it quick and easy to review visually.

[0100] "Analysis" is the process of breaking down and studying complex data and information in order to understand it and find meaning and patterns.

[0101] The system for realizing this invention consists of a server that performs cloud-based data processing, a user terminal for inputting and receiving user request data, and a program that utilizes natural language processing technology.

[0102] The server uses AWS® Relational Database Service (RDS) to receive labor-related request data from companies. Subsequently, the server retrieves workers' work history and performance data from the database. On the user's terminal, requests are entered through a dedicated application and sent to the server via the cloud.

[0103] The Google Cloud Natural Language API is used for data processing, analyzing the request data and the acquired worker data. Based on this information, the server identifies workers who meet the requirements and quantifies their degree of suitability to the company's needs. The optimized results are displayed in a list on the terminal interface, designed to allow the company's HR personnel to quickly review and select candidates.

[0104] As a concrete example, consider a scenario where an online retail company is planning to expand its digital marketing strategy and needs marketers skilled in consumer behavior data analysis. When the user inputs their requirements into the application from their terminal, the server provides a highly accurate list of candidates with similar project experience. This significantly improves the efficiency of the HR process.

[0105] Examples of prompts to input into a generative AI model:

[0106] "We are seeking candidates with the following characteristics: experience in consumer behavior data analysis, advertising campaign management, and SEO. Please identify individuals with these skills and at least 5 years of experience."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] Users use a terminal to input the requirements for the desired workers into a dedicated application. These requirements include specific skills, years of experience, and working conditions. This information is then sent directly to the server.

[0110] Step 2:

[0111] The server retrieves worker history and performance data from AWS's relational database service (RDS). Based on the requirements data received from the user, it searches relevant historical data and extracts candidates who may match the requirements. The input is the requirements data from the user, and the output is a list of candidates.

[0112] Step 3:

[0113] The server uses the Google Cloud Natural Language API to analyze the retrieved work history and experience data. This analysis step quantifies the candidate's skills and experience and calculates their suitability for the user's requirements. The input is work history data, and the output is a quantified suitability score. This process includes converting natural language sentences into structured data.

[0114] Step 4:

[0115] The server lists and presents the workers who best match the requirements based on the calculated suitability score. This list is sorted in descending order of suitability and displayed in a visually easy-to-view format on the user's terminal. Suitability data is taken as input, and the output is a list display.

[0116] Step 5:

[0117] Users can review a list of candidates presented through their device and select the most suitable worker. The selected information is immediately utilized in the company's recruitment process. Here, the user's selection information is output, forming the basis for HR personnel to make informed decisions.

[0118] The above processing steps enable a system that allows companies to quickly identify and select the most suitable workers.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention provides a more accurate talent recommendation system for companies and employees by combining it with an emotion engine that recognizes user emotions. This system utilizes emotion recognition technology in addition to existing functions that identify suitable employees based on company requirements.

[0121] First, the terminal receives the company's request data. At this time, the user's facial expressions and voice data are analyzed in real time by an emotion engine, and the user's emotional state is evaluated. The server considers both the received request data and the emotional data and performs analysis. For example, if the user feels it is urgent, it is possible to prioritize listing employees who can respond quickly.

[0122] Next, the server uses natural language processing technology to analyze the request data and match it with employee history and performance data. The importance of the requests and the way the matching results are presented are dynamically adjusted in response to changes in emotions.

[0123] As a concrete example, consider a situation where a corporate user is experiencing high levels of anxiety regarding the deadline when starting a new project. In this case, the emotion engine determines the user's emotion to be "anxious" and decides that a swift response is required. The server then proposes employees with high suitability who can immediately contribute, thus meeting the user's needs. Furthermore, information is presented in a concise and easy-to-understand manner to minimize user stress.

[0124] Thus, the present invention, through a system that combines emotion recognition, can improve the user experience and support flexible personnel allocation tailored to the needs of companies.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The terminal receives the company's request data entered by the user, and simultaneously captures the user's facial expressions and voice. This prepares the system for acquiring emotional data at the same time as the input.

[0128] Step 2:

[0129] The emotion engine analyzes captured user facial expressions and voice data to evaluate the user's emotional state in real time. For example, it can detect tension, anxiety, joy, and other emotions.

[0130] Step 3:

[0131] The server receives request data and sentiment data sent from the terminal and formats the request data into a parseable format. This formatting includes data cleaning and standardization.

[0132] Step 4:

[0133] The server retrieves employee career and performance data from the database. Here, it extracts employee work history, skill sets, and performance data.

[0134] Step 5:

[0135] The server uses natural language processing technology to analyze the formatted request data and employee data. It extracts important keywords and features from each data set and converts them into structured data.

[0136] Step 6:

[0137] The server adjusts the analysis results based on emotional data. For example, if a user is feeling stressed, it introduces evaluation criteria that prioritize speed, thereby prioritizing matching with employees who can immediately contribute.

[0138] Step 7:

[0139] The server calculates the degree of suitability for the request data and lists the most suitable employees. The degree of suitability is quantified, and the employee with the highest degree of suitability is selected.

[0140] Step 8:

[0141] The server outputs information about the identified employee to the user's terminal. Here, the information is displayed in a way that takes the user's emotional state into consideration, making it easy to understand.

[0142] Step 9:

[0143] Users review the personnel information presented through their terminals and make final decisions regarding employee selection and assignment requests as needed.

[0144] (Example 2)

[0145] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0146] While conventional talent matching systems select appropriate workers based on company requirements, they lack the ability to dynamically prioritize candidates based on the user's emotional state, limiting their potential for improving the user experience. Furthermore, the methods for providing worker information are fixed and not adjusted to the user's psychological state. This results in a challenge in responding quickly to stressful situations or situations requiring immediate action.

[0147] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0148] In this invention, the server includes means for acquiring corporate request information, means for acquiring worker history and performance information, and means for analyzing and evaluating the user's emotional state. This makes it possible to provide information that takes the user's emotions into consideration, and to dynamically adjust the priority of the requested information.

[0149] "Company requirements information" refers to data about the characteristics, skill sets, and job duties of workers that companies seek.

[0150] "Worker history and performance information" refers to data on a worker's past work experience, skills, achievements, and qualifications.

[0151] "Extracting characteristics" is the process of identifying and extracting the features and elements necessary for matching from the acquired information.

[0152] "User emotional state" refers to the psychological state of system users and is an emotional indicator obtained by analyzing facial expressions, voice, etc.

[0153] "Dynamic adjustment" refers to the process of changing settings and displays in real time according to data and circumstances.

[0154] This invention is a talent matching system for businesses that utilizes technology to recognize user emotions to provide more accurate worker recommendations. The system begins by receiving the company's request information and then analyzes it in combination with the worker's history and performance information. In addition, it has a function to identify the user's emotions and dynamically adjust the priority of the request information.

[0155] The server receives corporate request information via the internet. This includes job details, required skill sets, and urgency. The terminal functions to input this data through user input and send it to the server. Furthermore, an emotion engine analyzes the user's facial expressions and voice in real time to generate emotion data. Dedicated software, such as EmotionAPI, is used for this emotion analysis.

[0156] The server integrates this data, uses natural language processing techniques to analyze request information and historical data, and selects the most suitable worker. Google's Natural Language API may be used in this process. By incorporating sentiment data into the analysis, dynamic adjustments based on the user's state become possible, allowing for the recommendation of workers who can respond quickly to high-priority requests.

[0157] As a concrete example, consider a case where a company user is showing high levels of tension because they are in a hurry to implement a new project. In this case, the system will determine the tension as an "emotional state" and prioritize selecting workers who can immediately contribute. Furthermore, the list of proposed workers will be displayed simply and intuitively so as not to cause stress to the user.

[0158] An example of a prompt would be: "As a company prepares to launch a new project, we want to understand the needs of users who are feeling anxious and provide emotionally responsive personnel matching. Please explain in detail how to implement a system that analyzes users' emotions from their facial expressions and voices and quickly selects the most suitable employee." By inputting such prompts into the generating AI model, it becomes possible to explore more effective ways to use the system.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The terminal receives request information from corporate users. Users enter project start dates, required skill sets, and urgency into the terminal's form. The terminal organizes this data, converts it to a digital format, and sends it to the server. The process of transferring the request information to the server begins.

[0162] Step 2:

[0163] The device collects user emotional data. While the user inputs information, it uses the camera and microphone to collect facial expressions and voice in real time. Using emotion analysis software such as EmotionAPI, the device determines the user's emotional state based on the collected data. The analysis results are output as emotion labels such as "tense" or "relaxed."

[0164] Step 3:

[0165] The server integrates request information and sentiment data sent from the terminal. The server receives this data and compares it with past matching data stored in the database. If necessary, it analyzes the company's requests using natural language processing techniques based on the request information and extracts its characteristics. Google's Natural Language API and similar tools are used to output the characteristics of the request information.

[0166] Step 4:

[0167] The server compares the characteristics of the request information with the worker's history and performance information to generate a list of the most suitable workers. Emotional data is also used as a factor in the analysis. For example, if the emotional state is "stressed," workers who can respond immediately are prioritized. The server generates and outputs a list of suitable workers along with a numerical suitability score.

[0168] Step 5:

[0169] The server sends the worker matching results to the terminal. The terminal uses the received data to display the results in a user-friendly format. The information is presented concisely and clearly to minimize user stress. The user is then guided through the process of selecting their desired worker from the displayed results and making a final decision.

[0170] (Application Example 2)

[0171] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0172] In recent years, a challenge has arisen in that it is difficult for photographers on board autonomous vehicles to capture the optimal moment. In particular, the quality of a photograph is often influenced by the photographer's emotions, requiring real-time judgment on the appropriate timing for shooting. Conventional photography support systems lack dynamic advice that utilizes emotion recognition, and this could potentially help improve the quality of photography.

[0173] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0174] In this invention, the server includes means for receiving corporate request data, means for acquiring employee history and performance data, and means for evaluating the user's emotional state. This makes it possible to suggest the optimal shooting timing in real time based on the emotions of the photographer during shooting.

[0175] "Corporate requirements data" refers to information about employers' requirements or conditions regarding specific tasks or employee assignments.

[0176] "Employee history and performance data" refers to records of an employee's past work experience and achievements.

[0177] "Means of feature extraction" refers to processing steps or techniques for identifying and extracting meaningful patterns or attributes from data.

[0178] "Means for evaluating a user's emotional state" refers to technologies that use facial expression analysis, voice analysis, and other methods to determine an individual's current emotions.

[0179] "Means for dynamically adjusting the priority of identified employees" refers to a process for changing the importance of employees in the selection process in accordance with real-time changing conditions and requirements.

[0180] This invention is a matching system incorporating an emotion engine that flexibly selects employees suitable for a company's needs while evaluating the user's emotional state. The server has the function of receiving company request data and employee history and performance data, and further implements an emotion engine for analyzing the user's facial expressions and voice data. This emotion engine has the ability to determine the emotional state in real time using emotion recognition technology.

[0181] The hardware used will be smart glasses worn by the user. Specifically, devices such as Microsoft HoloLens® will be utilized to collect the user's visual and audio data. This data will be sent to emotion recognition software such as Affdex SDK to determine the user's emotions. The determined emotional state will influence the talent matching process on the server, dynamically adjusting factors such as urgency and importance.

[0182] The program uses natural language processing technology to perform integrated analysis of corporate needs data and sentiment data. Using tools such as Google Cloud Natural Language, it accurately grasps the intent behind the requests and provides feedback to the employee selection process. This system proposes the most suitable employees in a concise and easy-to-understand format for the user.

[0183] For example, when a company starts a new project, if the emotion engine detects that the company is feeling pressured by the deadline, this information is taken into consideration, and employees who can respond quickly are selected. Furthermore, the information presented is also provided in a way that reduces stress.

[0184] An example of a prompt for a generative AI model might be: "I want to capture the moment the sun sets from the top of this hill! Please create a system where smart glasses tell me the optimal shooting timing in real time based on the photographer's emotions." This example concretely demonstrates a function that improves the user experience by adapting to realistic situations.

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The terminal receives the company's requirements data. The input is the requirements data provided by the company, which includes project conditions and required skill sets. As output, the requirements data is sent to the server. The terminal converts this information into the required format and sends it to the server.

[0188] Step 2:

[0189] The server queries the employee history and performance database. The input is the history and performance database maintained by the server, and the output is a data list of employees that meet the specified criteria. The server uses queries such as SQL to extract the relevant data from the database.

[0190] Step 3:

[0191] The device analyzes the user's facial expressions and voice using an emotion engine. The input is the user's video and audio data collected by the device, and the output is the result of the emotion evaluation. The device uses the Affdex SDK to classify and quantify emotions in real time.

[0192] Step 4:

[0193] The server performs natural language processing based on request data, historical data, and sentiment ratings. The input is all the datasets obtained in the previous step, and the output is the feature extraction from the analysis results. The server uses Google Cloud Natural Language to pick out the meaning and importance of the requests.

[0194] Step 5:

[0195] The server adjusts employee priorities based on the evaluated emotional states. The input is extracted features and emotional state evaluations, and the output is a list of prioritized employees. The server dynamically adjusts each employee's goodness-of-fit score and reconstructs the rankings.

[0196] Step 6:

[0197] The server sends information about the most suitable employee to the terminal and displays it to the user. The input is a refined list of employees, and the output is screen information to be displayed to the user. The server packets the data and sends it, and the terminal integrates the received data into the UI and prepares it for display.

[0198] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0199] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0200] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0201] [Second Embodiment]

[0202] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0203] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0204] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0205] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0206] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0207] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0208] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0209] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0210] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0211] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0212] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0213] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0214] This invention relates to a system for efficiently matching companies with the personnel they need. Specifically, it involves a server receiving data on a company's requirements, collecting and analyzing employee career and performance data based on that data, and implementing a process to identify the most suitable personnel.

[0215] First, the user inputs the company's requirements data via a terminal. This requirements data includes the desired skills, job duties, location, and duration. The server receives this requirements data and retrieves employee history and performance data from its stored database.

[0216] Next, the server uses natural language processing technology to analyze the requirements data and career data. It quantifies the skills and experience of each employee and calculates how well they match the company's needs. This identifies the skill sets of employees that match the requirements data and calculates the degree of fit.

[0217] Once the optimal match is achieved, the server outputs the results to the user's terminal. Based on this output, the company user can make decisions to hire employees that meet their requirements.

[0218] As a concrete example, consider a small or medium-sized IT company seeking an employee with extensive programming experience for an AI project. When the user inputs the requirements data, the server searches the resumes of programmers who have previously participated in AI projects and selects the most suitable candidate. As a result, it becomes possible to quickly provide personnel that meet the company's needs. In this way, the present invention provides a system that solves the personnel shortage in companies and simultaneously promotes the effective utilization of employees.

[0219] The following describes the processing flow.

[0220] Step 1:

[0221] The terminal receives the company's request data entered by the user. This request data includes required skills, experience, job description, work location, and planned start date.

[0222] Step 2:

[0223] The server formats the request data received from the terminal into a parseable format. This formatting involves data cleaning and standardization.

[0224] Step 3:

[0225] The server retrieves employee history and performance data from the database. This includes information about the employee's work history, skill set, and achievements.

[0226] Step 4:

[0227] The server analyzes request data and history data using natural language processing techniques. It extracts important keywords and features from each data set and converts them into structured data.

[0228] Step 5:

[0229] The server matches the conditions in the request data with the features in the history data and quantifies the degree of fit. This process uses cosine similarity and machine learning algorithms to evaluate how well they match.

[0230] Step 6:

[0231] The server lists the calculated suitability scores for all employees and identifies the most suitable candidate. It then selects the employee with the highest suitability score as the optimal candidate.

[0232] Step 7:

[0233] The server outputs information about the identified individual to the user's terminal. Here, a detailed profile and reasons for recommendation are presented.

[0234] Step 8:

[0235] Users review the information presented through their devices and make hiring decisions based on the matching results. At this stage, the user makes the final decision on whether or not to request secondment.

[0236] (Example 1)

[0237] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0238] When conducting efficient talent matching, a challenge exists in quickly and accurately identifying workers with the specific skills and experience required by companies. In particular, there is a need for flexible analytical methods that can appropriately address diverse requirements.

[0239] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0240] In this invention, the server includes means for receiving organizational request information, means for acquiring worker history and performance information, and means for analyzing the request information and history information using natural language processing technology. This makes it possible to quickly identify and provide the most suitable worker to meet the diverse needs of a company.

[0241] "Organizational requirements information" refers to data that includes conditions such as the skills, experience, job duties, work location, and length of employment that companies and organizations require from personnel who fulfill specific roles.

[0242] "Worker history and performance information" refers to data that shows the job duties, achievements, and skill sets that a particular individual has experienced to date.

[0243] "Methods for extracting features" refer to the process of identifying and extracting important elements from given request information and career information to address specific conditions and requirements.

[0244] "Natural language processing technology" refers to a set of technologies that enable computers to understand and analyze information written in human language.

[0245] "Means for calculating quantified fit" refers to the process of generating a quantitative score to measure the degree of agreement between the requirements information and the worker's experience information.

[0246] "Utilizing generative AI models" refers to the process of analyzing and predicting data using models based on artificial intelligence technology.

[0247] This invention relates to an information system for efficiently matching personnel to the needs of an organization. Its aim is to quickly identify and provide workers who meet the company's requirements.

[0248] Users input organizational requirements via a terminal. This requirements include detailed conditions such as required skills, job responsibilities, work location, and employment period. For example, if an organization is looking for someone with "experience in AI projects and over 5 years of development experience using Python," this information is entered into the terminal and sent to the server.

[0249] The server retrieves worker history and performance information from the database based on the received request information. The server further analyzes the request information and worker history information using natural language processing (NLP) techniques. During this process, the server uses NLP techniques to extract important features from unstructured data and performs calculations to quantify that information. A generative AI model is then applied to refine the interpretation of the data.

[0250] Based on the analysis results, the server identifies the worker who best matches the requirements. The degree of suitability is quantified and displayed as a score indicating which worker most closely fits the organization's requirements. Based on these results, the user can make a hiring decision.

[0251] This system allows organizations to quickly identify candidates with the required skill sets, enabling them to address talent shortages and utilize resources efficiently. An example prompt would be: "We are looking for a worker with experience in AI projects and over 5 years of experience using Python. Please provide candidates who meet these criteria."

[0252] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0253] Step 1:

[0254] Users input organizational requirements into a terminal. Specifically, they fill in detailed information such as required skills, job description, work location, and employment period in a form. This information is sent from the terminal to the server as initial input for the entire system. Based on the input, the requirements information is sent to the server and processing begins.

[0255] Step 2:

[0256] The server receives request information sent from the terminal. This request information is temporarily stored in a database in a structured format. Specifically, the server verifies the integrity of the data using a communication protocol and then performs the saving process. This process prepares the dataset for analysis.

[0257] Step 3:

[0258] The server retrieves and searches for worker history and performance information from its stored database. Database technologies such as SQL queries are used to narrow down the list of suitable candidates for the requested information. The retrieved information is then prepared for subsequent analysis processing within the server.

[0259] Step 4:

[0260] The server uses natural language processing technology to analyze the request information and acquired history information. This analysis employs a generative AI model to extract and quantify important features from unstructured data. Specifically, the natural language processing engine tokenizes the input text and converts it into features for skill matching. This process yields the analyzed dataset.

[0261] Step 5:

[0262] The server calculates the degree of fit based on the analysis results. Here, the degree of match with the requested information is numerically evaluated using a scoring model or machine learning model. Based on the resulting score, the server lists candidates with high fit.

[0263] Step 6:

[0264] The server outputs information on the most suitable worker to the user's terminal based on the calculated suitability score. The user receives these results and reviews the detailed profile to make a hiring decision. The output information is displayed visually in a UI format to support the decision-making process.

[0265] (Application Example 1)

[0266] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0267] In today's digital market, companies are required to quickly and accurately identify workers with specific skills and experience. However, traditional systems lack mechanisms to efficiently match companies with personnel specialized in their specific requirements and market operations, making it difficult to select the right workers.

[0268] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0269] In this invention, the server includes a device for receiving corporate request data, a device for acquiring worker work history and performance data, and a device for providing an interface on which requirements for digital market operations can be entered. This makes it possible to quickly list and display workers best suited to the corporate digital market operations.

[0270] An "device" is a machine or mechanism designed to serve a specific purpose.

[0271] A "worker" is a person who engages in a specific job and possesses the skills and experience required for it.

[0272] "Work history" refers to historical information about the jobs and roles an employee has held in the past.

[0273] "Performance data" refers to information about the work results and achievements that an employee has made to date.

[0274] An "interface" is a means or environment for humans and systems to exchange information and interact with each other.

[0275] "Requirements" refer to the conditions or abilities necessary to achieve a specific goal.

[0276] "List view" is a method of displaying information in a bulleted list format, making it quick and easy to review visually.

[0277] "Analysis" is the process of breaking down and studying complex data and information in order to understand it and find meaning and patterns.

[0278] The system for realizing this invention consists of a server that performs cloud-based data processing, a user terminal for inputting and receiving user request data, and a program that utilizes natural language processing technology.

[0279] The server uses AWS's relational database service (RDS) to receive labor-related request data from companies. Subsequently, the server retrieves workers' work history and performance data from the database. On the user's terminal, requests are entered through a dedicated application and sent to the server via the cloud.

[0280] Google Cloud Natural Language API is used for data processing, and the requirement data and the obtained worker data are analyzed. Based on this information, the server identifies workers who meet the requirements and numerically calculates the degree of compliance with the company's requirements. The optimized results are listed on the interface of the terminal and are designed to enable the company's personnel staff to quickly check and select.

[0281] As a specific example, assume that an online retail company is planning to expand its digital marketing strategy and is seeking a marketer with expertise in consumer behavior data analysis. When the requirement specifications are input into the application from the user terminal, the server lists and provides highly accurate candidates with past similar project experience. This significantly improves the efficiency of the personnel procedure.

[0282] Example of a prompt sentence to input into the generative AI model:

[0283] "We are seeking workers with the following characteristics. Experience in consumer behavior data analysis, advertising campaign management, and SEO measures is required. Identify candidates with these skills and over 5 years of experience."

[0284] The flow of the specific process in Application Example 1 will be described using Figure 12.

[0285] Step 1:

[0286] The user uses the terminal to input the requirements of the desired worker into the dedicated application. The input requirements include specific skills, years of experience, working conditions, etc. This information is directly sent to the server.

[0287] Step 2:

[0288] The server retrieves worker history and performance data from AWS's relational database service (RDS). Based on the requirements data received from the user, it searches relevant historical data and extracts candidates who may match the requirements. The input is the requirements data from the user, and the output is a list of candidates.

[0289] Step 3:

[0290] The server uses the Google Cloud Natural Language API to analyze the retrieved work history and experience data. This analysis step quantifies the candidate's skills and experience and calculates their suitability for the user's requirements. The input is work history data, and the output is a quantified suitability score. This process includes converting natural language sentences into structured data.

[0291] Step 4:

[0292] The server lists and presents the workers who best match the requirements based on the calculated suitability score. This list is sorted in descending order of suitability and displayed in a visually easy-to-view format on the user's terminal. Suitability data is taken as input, and the output is a list display.

[0293] Step 5:

[0294] Users can review a list of candidates presented through their device and select the most suitable worker. The selected information is immediately utilized in the company's recruitment process. Here, the user's selection information is output, forming the basis for HR personnel to make informed decisions.

[0295] The above processing steps enable a system that allows companies to quickly identify and select the most suitable workers.

[0296] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0297] This invention provides a more accurate talent recommendation system for companies and employees by combining it with an emotion engine that recognizes user emotions. This system utilizes emotion recognition technology in addition to existing functions that identify suitable employees based on company requirements.

[0298] First, the terminal receives the company's request data. At this time, the user's facial expressions and voice data are analyzed in real time by an emotion engine, and the user's emotional state is evaluated. The server considers both the received request data and the emotional data and performs analysis. For example, if the user feels it is urgent, it is possible to prioritize listing employees who can respond quickly.

[0299] Next, the server uses natural language processing technology to analyze the request data and match it with employee history and performance data. The importance of the requests and the way the matching results are presented are dynamically adjusted in response to changes in emotions.

[0300] As a concrete example, consider a situation where a corporate user is experiencing high levels of anxiety regarding the deadline when starting a new project. In this case, the emotion engine determines the user's emotion to be "anxious" and decides that a swift response is required. The server then proposes employees with high suitability who can immediately contribute, thus meeting the user's needs. Furthermore, information is presented in a concise and easy-to-understand manner to minimize user stress.

[0301] Thus, the present invention, through a system that combines emotion recognition, can improve the user experience and support flexible personnel allocation tailored to the needs of companies.

[0302] The following describes the processing flow.

[0303] Step 1:

[0304] The terminal receives the requirement data of the enterprise input by the user, and simultaneously captures the user's expression and voice. Thereby, preparations are made to obtain emotion data simultaneously with the input.

[0305] Step 2:

[0306] The emotion engine analyzes the captured user's expression and voice data, and evaluates the user's emotional state in real time. For example, tension, anxiety, joy, etc. are detected.

[0307] Step 3:

[0308] The server receives the requirement data and emotion data sent from the terminal, and formats the requirement data into a form that can be analyzed. This formatting includes data cleaning and standardization.

[0309] Step 4:

[0310] The server obtains the employee's history data and performance data from the database. Here, the employee's job history, skill set, and performance data are extracted.

[0311] Step 5:

[0312] The server analyzes the formatted requirement data and the employee's data using natural language processing technology. Extract important keywords and features from each data, and convert them into structured data.

[0313] Step 6:

[0314] The server adjusts the analysis results based on the emotion data. For example, when the user is tense, by introducing evaluation criteria that emphasize speed, employees with immediate combat effectiveness are preferentially matched.

[0315] Step 7:

[0316] The server calculates the degree of suitability for the request data and lists the most suitable employees. The degree of suitability is quantified, and the employee with the highest degree of suitability is selected.

[0317] Step 8:

[0318] The server outputs information about the identified employee to the user's terminal. Here, the information is displayed in a way that takes the user's emotional state into consideration, making it easy to understand.

[0319] Step 9:

[0320] Users review the personnel information presented through their terminals and make final decisions regarding employee selection and assignment requests as needed.

[0321] (Example 2)

[0322] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0323] While conventional talent matching systems select appropriate workers based on company requirements, they lack the ability to dynamically prioritize candidates based on the user's emotional state, limiting their potential for improving the user experience. Furthermore, the methods for providing worker information are fixed and not adjusted to the user's psychological state. This results in a challenge in responding quickly to stressful situations or situations requiring immediate action.

[0324] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0325] In this invention, the server includes means for acquiring corporate request information, means for acquiring worker history and performance information, and means for analyzing and evaluating the user's emotional state. This makes it possible to provide information that takes the user's emotions into consideration, and to dynamically adjust the priority of the requested information.

[0326] "Company requirements information" refers to data about the characteristics, skill sets, and job duties of workers that companies seek.

[0327] "Worker history and performance information" refers to data on a worker's past work experience, skills, achievements, and qualifications.

[0328] "Extracting characteristics" is the process of identifying and extracting the features and elements necessary for matching from the acquired information.

[0329] "User emotional state" refers to the psychological state of system users and is an emotional indicator obtained by analyzing facial expressions, voice, etc.

[0330] "Dynamic adjustment" refers to the process of changing settings and displays in real time according to data and circumstances.

[0331] This invention is a talent matching system for businesses that utilizes technology to recognize user emotions to provide more accurate worker recommendations. The system begins by receiving the company's request information and then analyzes it in combination with the worker's history and performance information. In addition, it has a function to identify the user's emotions and dynamically adjust the priority of the request information.

[0332] The server receives corporate request information via the internet. This includes job details, required skill sets, and urgency. The terminal functions to input this data through user input and send it to the server. Furthermore, an emotion engine analyzes the user's facial expressions and voice in real time to generate emotion data. Dedicated software, such as EmotionAPI, is used for this emotion analysis.

[0333] The server integrates this data, uses natural language processing techniques to analyze request information and historical data, and selects the most suitable worker. Google's Natural Language API may be used in this process. By incorporating sentiment data into the analysis, dynamic adjustments based on the user's state become possible, allowing for the recommendation of workers who can respond quickly to high-priority requests.

[0334] As a concrete example, consider a case where a company user is showing high levels of tension because they are in a hurry to implement a new project. In this case, the system will determine the tension as an "emotional state" and prioritize selecting workers who can immediately contribute. Furthermore, the list of proposed workers will be displayed simply and intuitively so as not to cause stress to the user.

[0335] An example of a prompt would be: "As a company prepares to launch a new project, we want to understand the needs of users who are feeling anxious and provide emotionally responsive personnel matching. Please explain in detail how to implement a system that analyzes users' emotions from their facial expressions and voices and quickly selects the most suitable employee." By inputting such prompts into the generating AI model, it becomes possible to explore more effective ways to use the system.

[0336] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0337] Step 1:

[0338] The terminal receives request information from corporate users. Users enter project start dates, required skill sets, and urgency into the terminal's form. The terminal organizes this data, converts it to a digital format, and sends it to the server. The process of transferring the request information to the server begins.

[0339] Step 2:

[0340] The device collects user emotional data. While the user inputs information, it uses the camera and microphone to collect facial expressions and voice in real time. Using emotion analysis software such as EmotionAPI, the device determines the user's emotional state based on the collected data. The analysis results are output as emotion labels such as "tense" or "relaxed."

[0341] Step 3:

[0342] The server integrates request information and sentiment data sent from the terminal. The server receives this data and compares it with past matching data stored in the database. If necessary, it analyzes the company's requests using natural language processing techniques based on the request information and extracts its characteristics. Google's Natural Language API and similar tools are used to output the characteristics of the request information.

[0343] Step 4:

[0344] The server compares the characteristics of the request information with the worker's history and performance information to generate a list of the most suitable workers. Emotional data is also used as a factor in the analysis. For example, if the emotional state is "stressed," workers who can respond immediately are prioritized. The server generates and outputs a list of suitable workers along with a numerical suitability score.

[0345] Step 5:

[0346] The server sends the worker matching results to the terminal. The terminal uses the received data to display the results in a user-friendly format. The information is presented concisely and clearly to minimize user stress. The user is then guided through the process of selecting their desired worker from the displayed results and making a final decision.

[0347] (Application Example 2)

[0348] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0349] In recent years, a challenge has arisen in that it is difficult for photographers on board autonomous vehicles to capture the optimal moment. In particular, the quality of a photograph is often influenced by the photographer's emotions, requiring real-time judgment on the appropriate timing for shooting. Conventional photography support systems lack dynamic advice that utilizes emotion recognition, and this could potentially help improve the quality of photography.

[0350] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0351] In this invention, the server includes means for receiving corporate request data, means for acquiring employee history and performance data, and means for evaluating the user's emotional state. This makes it possible to suggest the optimal shooting timing in real time based on the emotions of the photographer during shooting.

[0352] "Corporate requirements data" refers to information about employers' requirements or conditions regarding specific tasks or employee assignments.

[0353] "Employee history and performance data" refers to records of an employee's past work experience and achievements.

[0354] "Means of feature extraction" refers to processing steps or techniques for identifying and extracting meaningful patterns or attributes from data.

[0355] "Means for evaluating a user's emotional state" refers to technologies that use facial expression analysis, voice analysis, and other methods to determine an individual's current emotions.

[0356] "Means for dynamically adjusting the priority of identified employees" refers to a process for changing the importance of employees in the selection process in accordance with real-time changing conditions and requirements.

[0357] This invention is a matching system incorporating an emotion engine that flexibly selects employees suitable for a company's needs while evaluating the user's emotional state. The server has the function of receiving company request data and employee history and performance data, and further implements an emotion engine for analyzing the user's facial expressions and voice data. This emotion engine has the ability to determine the emotional state in real time using emotion recognition technology.

[0358] The hardware involves smart glasses worn by the user. Specifically, devices like Microsoft HoloLens are used to collect the user's visual and auditory data. This data is sent to emotion recognition software such as Affdex SDK to determine the user's emotions. The determined emotional state influences the talent matching process on the server, dynamically adjusting factors such as urgency and importance.

[0359] The program uses natural language processing technology to perform integrated analysis of corporate needs data and sentiment data. Using tools such as Google Cloud Natural Language, it accurately grasps the intent behind the requests and provides feedback to the employee selection process. This system proposes the most suitable employees in a concise and easy-to-understand format for the user.

[0360] For example, when a company starts a new project, if the emotion engine detects that the company is feeling pressured by the deadline, this information is taken into consideration, and employees who can respond quickly are selected. Furthermore, the information presented is also provided in a way that reduces stress.

[0361] An example of a prompt for a generative AI model might be: "I want to capture the moment the sun sets from the top of this hill! Please create a system where smart glasses tell me the optimal shooting timing in real time based on the photographer's emotions." This example concretely demonstrates a function that improves the user experience by adapting to realistic situations.

[0362] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0363] Step 1:

[0364] The terminal receives the company's requirements data. The input is the requirements data provided by the company, which includes project conditions and required skill sets. As output, the requirements data is sent to the server. The terminal converts this information into the required format and sends it to the server.

[0365] Step 2:

[0366] The server queries the employee history and performance database. The input is the history and performance database maintained by the server, and the output is a data list of employees that meet the specified criteria. The server uses queries such as SQL to extract the relevant data from the database.

[0367] Step 3:

[0368] The device analyzes the user's facial expressions and voice using an emotion engine. The input is the user's video and audio data collected by the device, and the output is the result of the emotion evaluation. The device uses the Affdex SDK to classify and quantify emotions in real time.

[0369] Step 4:

[0370] The server performs natural language processing based on request data, historical data, and sentiment ratings. The input is all the datasets obtained in the previous step, and the output is the feature extraction from the analysis results. The server uses Google Cloud Natural Language to pick out the meaning and importance of the requests.

[0371] Step 5:

[0372] The server adjusts employee priorities based on the evaluated emotional states. The input is extracted features and emotional state evaluations, and the output is a list of prioritized employees. The server dynamically adjusts each employee's goodness-of-fit score and reconstructs the rankings.

[0373] Step 6:

[0374] The server sends information about the most suitable employee to the terminal and displays it to the user. The input is a refined list of employees, and the output is screen information to be displayed to the user. The server packets the data and sends it, and the terminal integrates the received data into the UI and prepares it for display.

[0375] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0376] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0377] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0378] [Third Embodiment]

[0379] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0380] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0381] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0382] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0383] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0384] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0385] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0386] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0387] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0388] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0389] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0390] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0391] This invention relates to a system for efficiently matching companies with the personnel they need. Specifically, it involves a server receiving data on a company's requirements, collecting and analyzing employee career and performance data based on that data, and implementing a process to identify the most suitable personnel.

[0392] First, the user inputs the company's requirements data via a terminal. This requirements data includes the desired skills, job duties, location, and duration. The server receives this requirements data and retrieves employee history and performance data from its stored database.

[0393] Next, the server uses natural language processing technology to analyze the requirements data and career data. It quantifies the skills and experience of each employee and calculates how well they match the company's needs. This identifies the skill sets of employees that match the requirements data and calculates the degree of fit.

[0394] Once the optimal match is achieved, the server outputs the results to the user's terminal. Based on this output, the company user can make decisions to hire employees that meet their requirements.

[0395] As a concrete example, consider a small or medium-sized IT company seeking an employee with extensive programming experience for an AI project. When the user inputs the requirements data, the server searches the resumes of programmers who have previously participated in AI projects and selects the most suitable candidate. As a result, it becomes possible to quickly provide personnel that meet the company's needs. In this way, the present invention provides a system that solves the personnel shortage in companies and simultaneously promotes the effective utilization of employees.

[0396] The following describes the processing flow.

[0397] Step 1:

[0398] The terminal receives the company's request data entered by the user. This request data includes required skills, experience, job description, work location, and planned start date.

[0399] Step 2:

[0400] The server formats the request data received from the terminal into a parseable format. This formatting involves data cleaning and standardization.

[0401] Step 3:

[0402] The server retrieves employee history and performance data from the database. This includes information about the employee's work history, skill set, and achievements.

[0403] Step 4:

[0404] The server analyzes request data and history data using natural language processing techniques. It extracts important keywords and features from each data set and converts them into structured data.

[0405] Step 5:

[0406] The server matches the conditions in the request data with the features in the history data and quantifies the degree of fit. This process uses cosine similarity and machine learning algorithms to evaluate how well they match.

[0407] Step 6:

[0408] The server lists the calculated suitability scores for all employees and identifies the most suitable candidate. It then selects the employee with the highest suitability score as the optimal candidate.

[0409] Step 7:

[0410] The server outputs information about the identified individual to the user's terminal. Here, a detailed profile and reasons for recommendation are presented.

[0411] Step 8:

[0412] Users review the information presented through their devices and make hiring decisions based on the matching results. At this stage, the user makes the final decision on whether or not to request secondment.

[0413] (Example 1)

[0414] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0415] When conducting efficient talent matching, a challenge exists in quickly and accurately identifying workers with the specific skills and experience required by companies. In particular, there is a need for flexible analytical methods that can appropriately address diverse requirements.

[0416] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0417] In this invention, the server includes means for receiving organizational request information, means for acquiring worker history and performance information, and means for analyzing the request information and history information using natural language processing technology. This makes it possible to quickly identify and provide the most suitable worker to meet the diverse needs of a company.

[0418] "Organizational requirements information" refers to data that includes conditions such as the skills, experience, job duties, work location, and length of employment that companies and organizations require from personnel who fulfill specific roles.

[0419] "Worker history and performance information" refers to data that shows the job duties, achievements, and skill sets that a particular individual has experienced to date.

[0420] "Methods for extracting features" refer to the process of identifying and extracting important elements from given request information and career information to address specific conditions and requirements.

[0421] "Natural language processing technology" refers to a set of technologies that enable computers to understand and analyze information written in human language.

[0422] "Means for calculating quantified fit" refers to the process of generating a quantitative score to measure the degree of agreement between the requirements information and the worker's experience information.

[0423] "Utilizing generative AI models" refers to the process of analyzing and predicting data using models based on artificial intelligence technology.

[0424] This invention relates to an information system for efficiently matching personnel to the needs of an organization. Its aim is to quickly identify and provide workers who meet the company's requirements.

[0425] Users input organizational requirements via a terminal. This requirements include detailed conditions such as required skills, job responsibilities, work location, and employment period. For example, if an organization is looking for someone with "experience in AI projects and over 5 years of development experience using Python," this information is entered into the terminal and sent to the server.

[0426] The server retrieves worker history and performance information from the database based on the received request information. The server further analyzes the request information and worker history information using natural language processing (NLP) techniques. During this process, the server uses NLP techniques to extract important features from unstructured data and performs calculations to quantify that information. A generative AI model is then applied to refine the interpretation of the data.

[0427] Based on the analysis results, the server identifies the worker who best matches the requirements. The degree of suitability is quantified and displayed as a score indicating which worker most closely fits the organization's requirements. Based on these results, the user can make a hiring decision.

[0428] This system allows organizations to quickly identify candidates with the required skill sets, enabling them to address talent shortages and utilize resources efficiently. An example prompt would be: "We are looking for a worker with experience in AI projects and over 5 years of experience using Python. Please provide candidates who meet these criteria."

[0429] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0430] Step 1:

[0431] Users input organizational requirements into a terminal. Specifically, they fill in detailed information such as required skills, job description, work location, and employment period in a form. This information is sent from the terminal to the server as initial input for the entire system. Based on the input, the requirements information is sent to the server and processing begins.

[0432] Step 2:

[0433] The server receives request information sent from the terminal. This request information is temporarily stored in a database in a structured format. Specifically, the server verifies the integrity of the data using a communication protocol and then performs the saving process. This process prepares the dataset for analysis.

[0434] Step 3:

[0435] The server retrieves and searches for worker history and performance information from its stored database. Database technologies such as SQL queries are used to narrow down the list of suitable candidates for the requested information. The retrieved information is then prepared for subsequent analysis processing within the server.

[0436] Step 4:

[0437] The server uses natural language processing technology to analyze the request information and acquired history information. This analysis employs a generative AI model to extract and quantify important features from unstructured data. Specifically, the natural language processing engine tokenizes the input text and converts it into features for skill matching. This process yields the analyzed dataset.

[0438] Step 5:

[0439] The server calculates the degree of fit based on the analysis results. Here, the degree of match with the requested information is numerically evaluated using a scoring model or machine learning model. Based on the resulting score, the server lists candidates with high fit.

[0440] Step 6:

[0441] The server outputs information on the most suitable worker to the user's terminal based on the calculated suitability score. The user receives these results and reviews the detailed profile to make a hiring decision. The output information is displayed visually in a UI format to support the decision-making process.

[0442] (Application Example 1)

[0443] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0444] In today's digital market, companies are required to quickly and accurately identify workers with specific skills and experience. However, traditional systems lack mechanisms to efficiently match companies with personnel specialized in their specific requirements and market operations, making it difficult to select the right workers.

[0445] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0446] In this invention, the server includes a device for receiving corporate request data, a device for acquiring worker work history and performance data, and a device for providing an interface on which requirements for digital market operations can be entered. This makes it possible to quickly list and display workers best suited to the corporate digital market operations.

[0447] An "device" is a machine or mechanism designed to serve a specific purpose.

[0448] A "worker" is a person who engages in a specific job and possesses the skills and experience required for it.

[0449] "Work history" refers to historical information about the jobs and roles an employee has held in the past.

[0450] "Performance data" refers to information about the work results and achievements that an employee has made to date.

[0451] An "interface" is a means or environment for humans and systems to exchange information and interact with each other.

[0452] "Requirements" refer to the conditions or abilities necessary to achieve a specific goal.

[0453] "List view" is a method of displaying information in a bulleted list format, making it quick and easy to review visually.

[0454] "Analysis" is the process of breaking down and studying complex data and information in order to understand it and find meaning and patterns.

[0455] The system for realizing this invention consists of a server that performs cloud-based data processing, a user terminal for inputting and receiving user request data, and a program that utilizes natural language processing technology.

[0456] The server uses AWS's relational database service (RDS) to receive labor-related request data from companies. Subsequently, the server retrieves workers' work history and performance data from the database. On the user's terminal, requests are entered through a dedicated application and sent to the server via the cloud.

[0457] The Google Cloud Natural Language API is used for data processing, analyzing the request data and the retrieved worker data. Based on this information, the server identifies workers who meet the requirements and quantifies their degree of suitability to the company's needs. The optimized results are displayed in a list on the terminal interface, designed to allow the company's HR personnel to quickly review and select candidates.

[0458] As a concrete example, consider a scenario where an online retail company is planning to expand its digital marketing strategy and needs marketers skilled in consumer behavior data analysis. When the user inputs their requirements into the application from their terminal, the server provides a highly accurate list of candidates with similar project experience. This significantly improves the efficiency of the HR process.

[0459] Examples of prompts to input into a generative AI model:

[0460] "We are seeking candidates with the following characteristics: experience in consumer behavior data analysis, advertising campaign management, and SEO. Please identify individuals with these skills and at least 5 years of experience."

[0461] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0462] Step 1:

[0463] Users use a terminal to input the requirements for the desired workers into a dedicated application. These requirements include specific skills, years of experience, and working conditions. This information is then sent directly to the server.

[0464] Step 2:

[0465] The server retrieves worker history and performance data from AWS's relational database service (RDS). Based on the requirements data received from the user, it searches relevant historical data and extracts candidates who may match the requirements. The input is the requirements data from the user, and the output is a list of candidates.

[0466] Step 3:

[0467] The server uses the Google Cloud Natural Language API to analyze the retrieved work history and experience data. This analysis step quantifies the candidate's skills and experience and calculates their suitability for the user's requirements. The input is work history data, and the output is a quantified suitability score. This process includes converting natural language sentences into structured data.

[0468] Step 4:

[0469] The server lists and presents the workers who best match the requirements based on the calculated suitability score. This list is sorted in descending order of suitability and displayed in a visually easy-to-view format on the user's terminal. Suitability data is taken as input, and the output is a list display.

[0470] Step 5:

[0471] Users can review a list of candidates presented through their device and select the most suitable worker. The selected information is immediately utilized in the company's recruitment process. Here, the user's selection information is output, forming the basis for HR personnel to make informed decisions.

[0472] The above processing steps enable a system that allows companies to quickly identify and select the most suitable workers.

[0473] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0474] This invention provides a more accurate talent recommendation system for companies and employees by combining it with an emotion engine that recognizes user emotions. This system utilizes emotion recognition technology in addition to existing functions that identify suitable employees based on company requirements.

[0475] First, the terminal receives the company's request data. At this time, the user's facial expressions and voice data are analyzed in real time by an emotion engine, and the user's emotional state is evaluated. The server considers both the received request data and the emotional data and performs analysis. For example, if the user feels it is urgent, it is possible to prioritize listing employees who can respond quickly.

[0476] Next, the server uses natural language processing technology to analyze the request data and match it with employee history and performance data. The importance of the requests and the way the matching results are presented are dynamically adjusted in response to changes in emotions.

[0477] As a concrete example, consider a situation where a corporate user is experiencing high levels of anxiety regarding the deadline when starting a new project. In this case, the emotion engine determines the user's emotion to be "anxious" and decides that a swift response is required. The server then proposes employees with high suitability who can immediately contribute, thus meeting the user's needs. Furthermore, information is presented in a concise and easy-to-understand manner to minimize user stress.

[0478] Thus, the present invention, through a system that combines emotion recognition, can improve the user experience and support flexible personnel allocation tailored to the needs of companies.

[0479] The following describes the processing flow.

[0480] Step 1:

[0481] The terminal receives the company's request data entered by the user, and simultaneously captures the user's facial expressions and voice. This prepares the system for acquiring emotional data at the same time as the input.

[0482] Step 2:

[0483] The emotion engine analyzes captured user facial expressions and voice data to evaluate the user's emotional state in real time. For example, it can detect tension, anxiety, joy, and other emotions.

[0484] Step 3:

[0485] The server receives request data and sentiment data sent from the terminal and formats the request data into a parseable format. This formatting includes data cleaning and standardization.

[0486] Step 4:

[0487] The server retrieves employee career and performance data from the database. Here, it extracts employee work history, skill sets, and performance data.

[0488] Step 5:

[0489] The server uses natural language processing technology to analyze the formatted request data and employee data. It extracts important keywords and features from each data set and converts them into structured data.

[0490] Step 6:

[0491] The server adjusts the analysis results based on emotional data. For example, if a user is feeling stressed, it introduces evaluation criteria that prioritize speed, thereby prioritizing matching with employees who can immediately contribute.

[0492] Step 7:

[0493] The server calculates the degree of suitability for the request data and lists the most suitable employees. The degree of suitability is quantified, and the employee with the highest degree of suitability is selected.

[0494] Step 8:

[0495] The server outputs information about the identified employee to the user's terminal. Here, the information is displayed in a way that takes the user's emotional state into consideration, making it easy to understand.

[0496] Step 9:

[0497] Users review the personnel information presented through their terminals and make final decisions regarding employee selection and assignment requests as needed.

[0498] (Example 2)

[0499] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] While conventional talent matching systems select appropriate workers based on company requirements, they lack the ability to dynamically prioritize candidates based on the user's emotional state, limiting their potential for improving the user experience. Furthermore, the methods for providing worker information are fixed and not adjusted to the user's psychological state. This results in a challenge in responding quickly to stressful situations or situations requiring immediate action.

[0501] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0502] In this invention, the server includes means for acquiring corporate request information, means for acquiring worker history and performance information, and means for analyzing and evaluating the user's emotional state. This makes it possible to provide information that takes the user's emotions into consideration, and to dynamically adjust the priority of the requested information.

[0503] "Company requirements information" refers to data about the characteristics, skill sets, and job duties of workers that companies seek.

[0504] "Worker history and performance information" refers to data on a worker's past work experience, skills, achievements, and qualifications.

[0505] "Extracting characteristics" is the process of identifying and extracting the features and elements necessary for matching from the acquired information.

[0506] "User emotional state" refers to the psychological state of system users and is an emotional indicator obtained by analyzing facial expressions, voice, etc.

[0507] "Dynamic adjustment" refers to the process of changing settings and displays in real time according to data and circumstances.

[0508] This invention is a talent matching system for businesses that utilizes technology to recognize user emotions to provide more accurate worker recommendations. The system begins by receiving the company's request information and then analyzes it in combination with the worker's history and performance information. In addition, it has a function to identify the user's emotions and dynamically adjust the priority of the request information.

[0509] The server receives corporate request information via the internet. This includes job details, required skill sets, and urgency. The terminal functions to input this data through user input and send it to the server. Furthermore, an emotion engine analyzes the user's facial expressions and voice in real time to generate emotion data. Dedicated software, such as EmotionAPI, is used for this emotion analysis.

[0510] The server integrates this data, uses natural language processing techniques to analyze request information and historical data, and selects the most suitable worker. Google's Natural Language API may be used in this process. By incorporating sentiment data into the analysis, dynamic adjustments based on the user's state become possible, allowing for the recommendation of workers who can respond quickly to high-priority requests.

[0511] As a concrete example, consider a case where a company user is showing high levels of tension because they are in a hurry to implement a new project. In this case, the system will determine the tension as an "emotional state" and prioritize selecting workers who can immediately contribute. Furthermore, the list of proposed workers will be displayed simply and intuitively so as not to cause stress to the user.

[0512] An example of a prompt would be: "As a company prepares to launch a new project, we want to understand the needs of users who are feeling anxious and provide emotionally responsive personnel matching. Please explain in detail how to implement a system that analyzes users' emotions from their facial expressions and voices and quickly selects the most suitable employee." By inputting such prompts into the generating AI model, it becomes possible to explore more effective ways to use the system.

[0513] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0514] Step 1:

[0515] The terminal receives request information from corporate users. Users enter project start dates, required skill sets, and urgency into the terminal's form. The terminal organizes this data, converts it to a digital format, and sends it to the server. The process of transferring the request information to the server begins.

[0516] Step 2:

[0517] The device collects user emotional data. While the user inputs information, it uses the camera and microphone to collect facial expressions and voice in real time. Using emotion analysis software such as EmotionAPI, the device determines the user's emotional state based on the collected data. The analysis results are output as emotion labels such as "tense" or "relaxed."

[0518] Step 3:

[0519] The server integrates request information and sentiment data sent from the terminal. The server receives this data and compares it with past matching data stored in the database. If necessary, it analyzes the company's requests using natural language processing techniques based on the request information and extracts its characteristics. Google's Natural Language API and similar tools are used to output the characteristics of the request information.

[0520] Step 4:

[0521] The server compares the characteristics of the request information with the worker's history and performance information to generate a list of the most suitable workers. Emotional data is also used as a factor in the analysis. For example, if the emotional state is "stressed," workers who can respond immediately are prioritized. The server generates and outputs a list of suitable workers along with a numerical suitability score.

[0522] Step 5:

[0523] The server sends the worker matching results to the terminal. The terminal uses the received data to display the results in a user-friendly format. The information is presented concisely and clearly to minimize user stress. The user is then guided through the process of selecting their desired worker from the displayed results and making a final decision.

[0524] (Application Example 2)

[0525] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0526] In recent years, a challenge has arisen in that it is difficult for photographers on board autonomous vehicles to capture the optimal moment. In particular, the quality of a photograph is often influenced by the photographer's emotions, requiring real-time judgment on the appropriate timing for shooting. Conventional photography support systems lack dynamic advice that utilizes emotion recognition, and this could potentially help improve the quality of photography.

[0527] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0528] In this invention, the server includes means for receiving corporate request data, means for acquiring employee history and performance data, and means for evaluating the user's emotional state. This makes it possible to suggest the optimal shooting timing in real time based on the emotions of the photographer during shooting.

[0529] "Corporate requirements data" refers to information about employers' requirements or conditions regarding specific tasks or employee assignments.

[0530] "Employee history and performance data" refers to records of an employee's past work experience and achievements.

[0531] "Means of feature extraction" refers to processing steps or techniques for identifying and extracting meaningful patterns or attributes from data.

[0532] "Means for evaluating a user's emotional state" refers to technologies that use facial expression analysis, voice analysis, and other methods to determine an individual's current emotions.

[0533] "Means for dynamically adjusting the priority of identified employees" refers to a process for changing the importance of employees in the selection process in accordance with real-time changing conditions and requirements.

[0534] This invention is a matching system incorporating an emotion engine that flexibly selects employees suitable for a company's needs while evaluating the user's emotional state. The server has the function of receiving company request data and employee history and performance data, and further implements an emotion engine for analyzing the user's facial expressions and voice data. This emotion engine has the ability to determine the emotional state in real time using emotion recognition technology.

[0535] The hardware involves smart glasses worn by the user. Specifically, devices like Microsoft HoloLens are used to collect the user's visual and auditory data. This data is sent to emotion recognition software such as Affdex SDK to determine the user's emotions. The determined emotional state influences the talent matching process on the server, dynamically adjusting factors such as urgency and importance.

[0536] The program uses natural language processing technology to perform integrated analysis of corporate needs data and sentiment data. Using tools such as Google Cloud Natural Language, it accurately grasps the intent behind the requests and provides feedback to the employee selection process. This system proposes the most suitable employees in a concise and easy-to-understand format for the user.

[0537] For example, when a company starts a new project, if the emotion engine detects that the company is feeling pressured by the deadline, this information is taken into consideration, and employees who can respond quickly are selected. Furthermore, the information presented is also provided in a way that reduces stress.

[0538] An example of a prompt for a generative AI model might be: "I want to capture the moment the sun sets from the top of this hill! Please create a system where smart glasses tell me the optimal shooting timing in real time based on the photographer's emotions." This example concretely demonstrates a function that improves the user experience by adapting to realistic situations.

[0539] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0540] Step 1:

[0541] The terminal receives the company's requirements data. The input is the requirements data provided by the company, which includes project conditions and required skill sets. As output, the requirements data is sent to the server. The terminal converts this information into the required format and sends it to the server.

[0542] Step 2:

[0543] The server queries the employee history and performance database. The input is the history and performance database maintained by the server, and the output is a data list of employees that meet the specified criteria. The server uses queries such as SQL to extract the relevant data from the database.

[0544] Step 3:

[0545] The device analyzes the user's facial expressions and voice using an emotion engine. The input is the user's video and audio data collected by the device, and the output is the result of the emotion evaluation. The device uses the Affdex SDK to classify and quantify emotions in real time.

[0546] Step 4:

[0547] The server performs natural language processing based on request data, historical data, and sentiment ratings. The input is all the datasets obtained in the previous step, and the output is the feature extraction from the analysis results. The server uses Google Cloud Natural Language to pick out the meaning and importance of the requests.

[0548] Step 5:

[0549] The server adjusts employee priorities based on the evaluated emotional states. The input is extracted features and emotional state evaluations, and the output is a list of prioritized employees. The server dynamically adjusts each employee's goodness-of-fit score and reconstructs the rankings.

[0550] Step 6:

[0551] The server sends information about the most suitable employee to the terminal and displays it to the user. The input is a refined list of employees, and the output is screen information to be displayed to the user. The server packets the data and sends it, and the terminal integrates the received data into the UI and prepares it for display.

[0552] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0553] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0554] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0555] [Fourth Embodiment]

[0556] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0557] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0558] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0559] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0560] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0561] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0562] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0563] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0564] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0565] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0566] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0567] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0568] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0569] This invention relates to a system for efficiently matching companies with the personnel they need. Specifically, it involves a server receiving data on a company's requirements, collecting and analyzing employee career and performance data based on that data, and implementing a process to identify the most suitable personnel.

[0570] First, the user inputs the company's requirements data via a terminal. This requirements data includes the desired skills, job duties, location, and duration. The server receives this requirements data and retrieves employee history and performance data from its stored database.

[0571] Next, the server uses natural language processing technology to analyze the requirements data and career data. It quantifies the skills and experience of each employee and calculates how well they match the company's needs. This identifies the skill sets of employees that match the requirements data and calculates the degree of fit.

[0572] Once the optimal match is achieved, the server outputs the results to the user's terminal. Based on this output, the company user can make decisions to hire employees that meet their requirements.

[0573] As a concrete example, consider a small or medium-sized IT company seeking an employee with extensive programming experience for an AI project. When the user inputs the requirements data, the server searches the resumes of programmers who have previously participated in AI projects and selects the most suitable candidate. As a result, it becomes possible to quickly provide personnel that meet the company's needs. In this way, the present invention provides a system that solves the personnel shortage in companies and simultaneously promotes the effective utilization of employees.

[0574] The following describes the processing flow.

[0575] Step 1:

[0576] The terminal receives the company's request data entered by the user. This request data includes required skills, experience, job description, work location, and planned start date.

[0577] Step 2:

[0578] The server formats the request data received from the terminal into a parseable format. This formatting involves data cleaning and standardization.

[0579] Step 3:

[0580] The server retrieves employee history and performance data from the database. This includes information about the employee's work history, skill set, and achievements.

[0581] Step 4:

[0582] The server analyzes request data and history data using natural language processing techniques. It extracts important keywords and features from each data set and converts them into structured data.

[0583] Step 5:

[0584] The server matches the conditions in the request data with the features in the history data and quantifies the degree of fit. This process uses cosine similarity and machine learning algorithms to evaluate how well they match.

[0585] Step 6:

[0586] The server lists the calculated suitability scores for all employees and identifies the most suitable candidate. It then selects the employee with the highest suitability score as the optimal candidate.

[0587] Step 7:

[0588] The server outputs information about the identified individual to the user's terminal. Here, a detailed profile and reasons for recommendation are presented.

[0589] Step 8:

[0590] Users review the information presented through their devices and make hiring decisions based on the matching results. At this stage, the user makes the final decision on whether or not to request secondment.

[0591] (Example 1)

[0592] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0593] When conducting efficient talent matching, a challenge exists in quickly and accurately identifying workers with the specific skills and experience required by companies. In particular, there is a need for flexible analytical methods that can appropriately address diverse requirements.

[0594] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0595] In this invention, the server includes means for receiving organizational request information, means for acquiring worker history and performance information, and means for analyzing the request information and history information using natural language processing technology. This makes it possible to quickly identify and provide the most suitable worker to meet the diverse needs of a company.

[0596] "Organizational requirements information" refers to data that includes conditions such as the skills, experience, job duties, work location, and length of employment that companies and organizations require from personnel who fulfill specific roles.

[0597] "Worker history and performance information" refers to data that shows the job duties, achievements, and skill sets that a particular individual has experienced to date.

[0598] "Methods for extracting features" refer to the process of identifying and extracting important elements from given request information and career information to address specific conditions and requirements.

[0599] "Natural language processing technology" refers to a set of technologies that enable computers to understand and analyze information written in human language.

[0600] "Means for calculating quantified fit" refers to the process of generating a quantitative score to measure the degree of agreement between the requirements information and the worker's experience information.

[0601] "Utilizing generative AI models" refers to the process of analyzing and predicting data using models based on artificial intelligence technology.

[0602] This invention relates to an information system for efficiently matching personnel to the needs of an organization. Its aim is to quickly identify and provide workers who meet the company's requirements.

[0603] Users input organizational requirements via a terminal. This requirements include detailed conditions such as required skills, job responsibilities, work location, and employment period. For example, if an organization is looking for someone with "experience in AI projects and over 5 years of development experience using Python," this information is entered into the terminal and sent to the server.

[0604] The server retrieves worker history and performance information from the database based on the received request information. The server further analyzes the request information and worker history information using natural language processing (NLP) techniques. During this process, the server uses NLP techniques to extract important features from unstructured data and performs calculations to quantify that information. A generative AI model is then applied to refine the interpretation of the data.

[0605] Based on the analysis results, the server identifies the worker who best matches the requirements. The degree of suitability is quantified and displayed as a score indicating which worker most closely fits the organization's requirements. Based on these results, the user can make a hiring decision.

[0606] This system allows organizations to quickly identify candidates with the required skill sets, enabling them to address talent shortages and utilize resources efficiently. An example prompt would be: "We are looking for a worker with experience in AI projects and over 5 years of experience using Python. Please provide candidates who meet these criteria."

[0607] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0608] Step 1:

[0609] Users input organizational requirements into a terminal. Specifically, they fill in detailed information such as required skills, job description, work location, and employment period in a form. This information is sent from the terminal to the server as initial input for the entire system. Based on the input, the requirements information is sent to the server and processing begins.

[0610] Step 2:

[0611] The server receives request information sent from the terminal. This request information is temporarily stored in a database in a structured format. Specifically, the server verifies the integrity of the data using a communication protocol and then performs the saving process. This process prepares the dataset for analysis.

[0612] Step 3:

[0613] The server retrieves and searches for worker history and performance information from its stored database. Database technologies such as SQL queries are used to narrow down the list of suitable candidates for the requested information. The retrieved information is then prepared for subsequent analysis processing within the server.

[0614] Step 4:

[0615] The server uses natural language processing technology to analyze the request information and acquired history information. This analysis employs a generative AI model to extract and quantify important features from unstructured data. Specifically, the natural language processing engine tokenizes the input text and converts it into features for skill matching. This process yields the analyzed dataset.

[0616] Step 5:

[0617] The server calculates the degree of fit based on the analysis results. Here, the degree of match with the requested information is numerically evaluated using a scoring model or machine learning model. Based on the resulting score, the server lists candidates with high fit.

[0618] Step 6:

[0619] The server outputs information on the most suitable worker to the user's terminal based on the calculated suitability score. The user receives these results and reviews the detailed profile to make a hiring decision. The output information is displayed visually in a UI format to support the decision-making process.

[0620] (Application Example 1)

[0621] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0622] In today's digital market, companies are required to quickly and accurately identify workers with specific skills and experience. However, traditional systems lack mechanisms to efficiently match companies with personnel specialized in their specific requirements and market operations, making it difficult to select the right workers.

[0623] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0624] In this invention, the server includes a device for receiving corporate request data, a device for acquiring worker work history and performance data, and a device for providing an interface on which requirements for digital market operations can be entered. This makes it possible to quickly list and display workers best suited to the corporate digital market operations.

[0625] An "device" is a machine or mechanism designed to serve a specific purpose.

[0626] A "worker" is a person who engages in a specific job and possesses the skills and experience required for it.

[0627] "Work history" refers to historical information about the jobs and roles an employee has held in the past.

[0628] "Performance data" refers to information about the work results and achievements that an employee has made to date.

[0629] An "interface" is a means or environment for humans and systems to exchange information and interact with each other.

[0630] "Requirements" refer to the conditions or abilities necessary to achieve a specific goal.

[0631] "List view" is a method of displaying information in a bulleted list format, making it quick and easy to review visually.

[0632] "Analysis" is the process of breaking down and studying complex data and information in order to understand it and find meaning and patterns.

[0633] The system for realizing this invention consists of a server that performs cloud-based data processing, a user terminal for inputting and receiving user request data, and a program that utilizes natural language processing technology.

[0634] The server uses AWS's relational database service (RDS) to receive labor-related request data from companies. Subsequently, the server retrieves workers' work history and performance data from the database. On the user's terminal, requests are entered through a dedicated application and sent to the server via the cloud.

[0635] The Google Cloud Natural Language API is used for data processing, analyzing the request data and the retrieved worker data. Based on this information, the server identifies workers who meet the requirements and quantifies their degree of suitability to the company's needs. The optimized results are displayed in a list on the terminal interface, designed to allow the company's HR personnel to quickly review and select candidates.

[0636] As a concrete example, consider a scenario where an online retail company is planning to expand its digital marketing strategy and needs marketers skilled in consumer behavior data analysis. When the user inputs their requirements into the application from their terminal, the server provides a highly accurate list of candidates with similar project experience. This significantly improves the efficiency of the HR process.

[0637] Examples of prompts to input into a generative AI model:

[0638] "We are seeking candidates with the following characteristics: experience in consumer behavior data analysis, advertising campaign management, and SEO. Please identify individuals with these skills and at least 5 years of experience."

[0639] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0640] Step 1:

[0641] Users use a terminal to input the requirements for the desired workers into a dedicated application. These requirements include specific skills, years of experience, and working conditions. This information is then sent directly to the server.

[0642] Step 2:

[0643] The server retrieves worker history and performance data from AWS's relational database service (RDS). Based on the requirements data received from the user, it searches relevant historical data and extracts candidates who may match the requirements. The input is the requirements data from the user, and the output is a list of candidates.

[0644] Step 3:

[0645] The server uses the Google Cloud Natural Language API to analyze the retrieved work history and experience data. This analysis step quantifies the candidate's skills and experience and calculates their suitability for the user's requirements. The input is work history data, and the output is a quantified suitability score. This process includes converting natural language sentences into structured data.

[0646] Step 4:

[0647] The server lists and presents the workers who best match the requirements based on the calculated suitability score. This list is sorted in descending order of suitability and displayed in a visually easy-to-view format on the user's terminal. Suitability data is taken as input, and the output is a list display.

[0648] Step 5:

[0649] Users can review a list of candidates presented through their device and select the most suitable worker. The selected information is immediately utilized in the company's recruitment process. Here, the user's selection information is output, forming the basis for HR personnel to make informed decisions.

[0650] The above processing steps enable a system that allows companies to quickly identify and select the most suitable workers.

[0651] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0652] This invention provides a more accurate talent recommendation system for companies and employees by combining it with an emotion engine that recognizes user emotions. This system utilizes emotion recognition technology in addition to existing functions that identify suitable employees based on company requirements.

[0653] First, the terminal receives the company's request data. At this time, the user's facial expressions and voice data are analyzed in real time by an emotion engine, and the user's emotional state is evaluated. The server considers both the received request data and the emotional data and performs analysis. For example, if the user feels it is urgent, it is possible to prioritize listing employees who can respond quickly.

[0654] Next, the server uses natural language processing technology to analyze the request data and match it with employee history and performance data. The importance of the requests and the way the matching results are presented are dynamically adjusted in response to changes in emotions.

[0655] As a concrete example, consider a situation where a corporate user is experiencing high levels of anxiety regarding the deadline when starting a new project. In this case, the emotion engine determines the user's emotion to be "anxious" and decides that a swift response is required. The server then proposes employees with high suitability who can immediately contribute, thus meeting the user's needs. Furthermore, information is presented in a concise and easy-to-understand manner to minimize user stress.

[0656] Thus, the present invention, through a system that combines emotion recognition, can improve the user experience and support flexible personnel allocation tailored to the needs of companies.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The terminal receives the company's request data entered by the user, and simultaneously captures the user's facial expressions and voice. This prepares the system for acquiring emotional data at the same time as the input.

[0660] Step 2:

[0661] The emotion engine analyzes captured user facial expressions and voice data to evaluate the user's emotional state in real time. For example, it can detect tension, anxiety, joy, and other emotions.

[0662] Step 3:

[0663] The server receives request data and sentiment data sent from the terminal and formats the request data into a parseable format. This formatting includes data cleaning and standardization.

[0664] Step 4:

[0665] The server retrieves employee career and performance data from the database. Here, it extracts employee work history, skill sets, and performance data.

[0666] Step 5:

[0667] The server uses natural language processing technology to analyze the formatted request data and employee data. It extracts important keywords and features from each data set and converts them into structured data.

[0668] Step 6:

[0669] The server adjusts the analysis results based on emotional data. For example, if a user is feeling stressed, it introduces evaluation criteria that prioritize speed, thereby prioritizing matching with employees who can immediately contribute.

[0670] Step 7:

[0671] The server calculates the degree of suitability for the request data and lists the most suitable employees. The degree of suitability is quantified, and the employee with the highest degree of suitability is selected.

[0672] Step 8:

[0673] The server outputs information about the identified employee to the user's terminal. Here, the information is displayed in a way that takes the user's emotional state into consideration, making it easy to understand.

[0674] Step 9:

[0675] Users review the personnel information presented through their terminals and make final decisions regarding employee selection and assignment requests as needed.

[0676] (Example 2)

[0677] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0678] While conventional talent matching systems select appropriate workers based on company requirements, they lack the ability to dynamically prioritize candidates based on the user's emotional state, limiting their potential for improving the user experience. Furthermore, the methods for providing worker information are fixed and not adjusted to the user's psychological state. This results in a challenge in responding quickly to stressful situations or situations requiring immediate action.

[0679] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0680] In this invention, the server includes means for acquiring corporate request information, means for acquiring worker history and performance information, and means for analyzing and evaluating the user's emotional state. This makes it possible to provide information that takes the user's emotions into consideration, and to dynamically adjust the priority of the requested information.

[0681] "Company requirements information" refers to data about the characteristics, skill sets, and job duties of workers that companies seek.

[0682] "Worker history and performance information" refers to data on a worker's past work experience, skills, achievements, and qualifications.

[0683] "Extracting characteristics" is the process of identifying and extracting the features and elements necessary for matching from the acquired information.

[0684] "User emotional state" refers to the psychological state of system users and is an emotional indicator obtained by analyzing facial expressions, voice, etc.

[0685] "Dynamic adjustment" refers to the process of changing settings and displays in real time according to data and circumstances.

[0686] This invention is a talent matching system for businesses that utilizes technology to recognize user emotions to provide more accurate worker recommendations. The system begins by receiving the company's request information and then analyzes it in combination with the worker's history and performance information. In addition, it has a function to identify the user's emotions and dynamically adjust the priority of the request information.

[0687] The server receives corporate request information via the internet. This includes job details, required skill sets, and urgency. The terminal functions to input this data through user input and send it to the server. Furthermore, an emotion engine analyzes the user's facial expressions and voice in real time to generate emotion data. Dedicated software, such as EmotionAPI, is used for this emotion analysis.

[0688] The server integrates this data, uses natural language processing techniques to analyze request information and historical data, and selects the most suitable worker. Google's Natural Language API may be used in this process. By incorporating sentiment data into the analysis, dynamic adjustments based on the user's state become possible, allowing for the recommendation of workers who can respond quickly to high-priority requests.

[0689] As a concrete example, consider a case where a company user is showing high levels of tension because they are in a hurry to implement a new project. In this case, the system will determine the tension as an "emotional state" and prioritize selecting workers who can immediately contribute. Furthermore, the list of proposed workers will be displayed simply and intuitively so as not to cause stress to the user.

[0690] An example of a prompt would be: "As a company prepares to launch a new project, we want to understand the needs of users who are feeling anxious and provide emotionally responsive personnel matching. Please explain in detail how to implement a system that analyzes users' emotions from their facial expressions and voices and quickly selects the most suitable employee." By inputting such prompts into the generating AI model, it becomes possible to explore more effective ways to use the system.

[0691] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0692] Step 1:

[0693] The terminal receives request information from corporate users. Users enter project start dates, required skill sets, and urgency into the terminal's form. The terminal organizes this data, converts it to a digital format, and sends it to the server. The process of transferring the request information to the server begins.

[0694] Step 2:

[0695] The device collects user emotional data. While the user inputs information, it uses the camera and microphone to collect facial expressions and voice in real time. Using emotion analysis software such as EmotionAPI, the device determines the user's emotional state based on the collected data. The analysis results are output as emotion labels such as "tense" or "relaxed."

[0696] Step 3:

[0697] The server integrates request information and sentiment data sent from the terminal. The server receives this data and compares it with past matching data stored in the database. If necessary, it analyzes the company's requests using natural language processing techniques based on the request information and extracts its characteristics. Google's Natural Language API and similar tools are used to output the characteristics of the request information.

[0698] Step 4:

[0699] The server compares the characteristics of the request information with the worker's history and performance information to generate a list of the most suitable workers. Emotional data is also used as a factor in the analysis. For example, if the emotional state is "stressed," workers who can respond immediately are prioritized. The server generates and outputs a list of suitable workers along with a numerical suitability score.

[0700] Step 5:

[0701] The server sends the worker matching results to the terminal. The terminal uses the received data to display the results in a user-friendly format. The information is presented concisely and clearly to minimize user stress. The user is then guided through the process of selecting their desired worker from the displayed results and making a final decision.

[0702] (Application Example 2)

[0703] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0704] In recent years, a challenge has arisen in that it is difficult for photographers on board autonomous vehicles to capture the optimal moment. In particular, the quality of a photograph is often influenced by the photographer's emotions, requiring real-time judgment on the appropriate timing for shooting. Conventional photography support systems lack dynamic advice that utilizes emotion recognition, and this could potentially help improve the quality of photography.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0706] In this invention, the server includes means for receiving corporate request data, means for acquiring employee history and performance data, and means for evaluating the user's emotional state. This makes it possible to suggest the optimal shooting timing in real time based on the emotions of the photographer during shooting.

[0707] "Corporate requirements data" refers to information about employers' requirements or conditions regarding specific tasks or employee assignments.

[0708] "Employee history and performance data" refers to records of an employee's past work experience and achievements.

[0709] "Means of feature extraction" refers to processing steps or techniques for identifying and extracting meaningful patterns or attributes from data.

[0710] "Means for evaluating a user's emotional state" refers to technologies that use facial expression analysis, voice analysis, and other methods to determine an individual's current emotions.

[0711] "Means for dynamically adjusting the priority of identified employees" refers to a process for changing the importance of employees in the selection process in accordance with real-time changing conditions and requirements.

[0712] This invention is a matching system incorporating an emotion engine that flexibly selects employees suitable for a company's needs while evaluating the user's emotional state. The server has the function of receiving company request data and employee history and performance data, and further implements an emotion engine for analyzing the user's facial expressions and voice data. This emotion engine has the ability to determine the emotional state in real time using emotion recognition technology.

[0713] The hardware involves smart glasses worn by the user. Specifically, devices like Microsoft HoloLens are used to collect the user's visual and auditory data. This data is sent to emotion recognition software such as Affdex SDK to determine the user's emotions. The determined emotional state influences the talent matching process on the server, dynamically adjusting factors such as urgency and importance.

[0714] The program uses natural language processing technology to perform integrated analysis of corporate needs data and sentiment data. Using tools such as Google Cloud Natural Language, it accurately grasps the intent behind the requests and provides feedback to the employee selection process. This system proposes the most suitable employees in a concise and easy-to-understand format for the user.

[0715] For example, when a company starts a new project, if the emotion engine detects that the company is feeling pressured by the deadline, this information is taken into consideration, and employees who can respond quickly are selected. Furthermore, the information presented is also provided in a way that reduces stress.

[0716] An example of a prompt for a generative AI model might be: "I want to capture the moment the sun sets from the top of this hill! Please create a system where smart glasses tell me the optimal shooting timing in real time based on the photographer's emotions." This example concretely demonstrates a function that improves the user experience by adapting to realistic situations.

[0717] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0718] Step 1:

[0719] The terminal receives the company's requirements data. The input is the requirements data provided by the company, which includes project conditions and required skill sets. As output, the requirements data is sent to the server. The terminal converts this information into the required format and sends it to the server.

[0720] Step 2:

[0721] The server queries the employee history and performance database. The input is the history and performance database maintained by the server, and the output is a data list of employees that meet the specified criteria. The server uses queries such as SQL to extract the relevant data from the database.

[0722] Step 3:

[0723] The device analyzes the user's facial expressions and voice using an emotion engine. The input is the user's video and audio data collected by the device, and the output is the result of the emotion evaluation. The device uses the Affdex SDK to classify and quantify emotions in real time.

[0724] Step 4:

[0725] The server performs natural language processing based on request data, historical data, and sentiment ratings. The input is all the datasets obtained in the previous step, and the output is the feature extraction from the analysis results. The server uses Google Cloud Natural Language to pick out the meaning and importance of the requests.

[0726] Step 5:

[0727] The server adjusts employee priorities based on the evaluated emotional states. The input is extracted features and emotional state evaluations, and the output is a list of prioritized employees. The server dynamically adjusts each employee's goodness-of-fit score and reconstructs the rankings.

[0728] Step 6:

[0729] The server sends information about the most suitable employee to the terminal and displays it to the user. The input is a refined list of employees, and the output is screen information to be displayed to the user. The server packets the data and sends it, and the terminal integrates the received data into the UI and prepares it for display.

[0730] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0731] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0732] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0733] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0734] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0735] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0736] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0737] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0738] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0739] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0740] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0741] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0742] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0743] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0744] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0745] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0746] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0747] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0748] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0749] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0750] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0751] The following is further disclosed regarding the embodiments described above.

[0752] (Claim 1)

[0753] A means of receiving data on requests from companies,

[0754] Means for obtaining employee career and performance data,

[0755] A means for analyzing the aforementioned request data and career data to extract features,

[0756] Based on the extracted characteristics, a means for identifying employees who meet the requirements,

[0757] means for outputting the information of the identified employee,

[0758] A system that includes this.

[0759] (Claim 2)

[0760] The system according to claim 1, wherein natural language processing technology is used to analyze the aforementioned request data and career data.

[0761] (Claim 3)

[0762] The system according to claim 1, which, in identifying the suitable employee, calculates a numerical degree of suitability and uses the result to determine the suitability.

[0763] "Example 1"

[0764] (Claim 1)

[0765] Means of receiving information on the organization's requests,

[0766] Means for obtaining worker's career history and performance information,

[0767] A means for analyzing the aforementioned request information and career information to extract features,

[0768] Based on the extracted characteristics, a means for identifying a worker who meets the requirements,

[0769] A means for outputting the information of the identified worker,

[0770] A means of analyzing request information and career information using natural language processing technology,

[0771] In identifying suitable workers, a means for calculating a numerical degree of suitability,

[0772] A method for identifying suitable workers by analyzing request information and work history information using a generative AI model,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, which uses natural language processing technology.

[0776] (Claim 3)

[0777] The system according to claim 1, which identifies workers based on a quantified degree of fit.

[0778] "Application Example 1"

[0779] (Claim 1)

[0780] A device that receives data on requests from companies,

[0781] A device for acquiring workers' work history and performance data,

[0782] A device for analyzing the aforementioned request data and work history data to extract features,

[0783] Based on the extracted characteristics, a device for identifying workers who meet the requirements,

[0784] A device that outputs information on the identified worker,

[0785] A device that provides an interface into which requirements for operating a digital market can be input,

[0786] A device that lists workers who meet the requirements,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] The system according to claim 1, wherein natural language processing technology is used for analyzing the aforementioned request data, work history data, and digital market operation requirements.

[0790] (Claim 3)

[0791] The system according to claim 1, which, in identifying the aforementioned suitable workers, calculates a quantified degree of suitability and is based on experience and skills in digital market operations.

[0792] "Example 2 of combining an emotion engine"

[0793] (Claim 1)

[0794] A device for acquiring information requested by a company,

[0795] A device for acquiring worker history and performance information,

[0796] A device for analyzing the aforementioned request information and historical information to extract characteristics,

[0797] A device for identifying a worker who matches the requirements based on the extracted characteristics,

[0798] A device that provides information on the identified worker,

[0799] A device that analyzes and evaluates the emotional state of users,

[0800] A system including a device that dynamically adjusts the priority of requested information based on the aforementioned emotional state.

[0801] (Claim 2)

[0802] The system according to claim 1, wherein natural language processing technology is applied to the analysis of the aforementioned request information and historical information.

[0803] (Claim 3)

[0804] The system according to claim 1, which, in identifying matching workers, calculates a numerical degree of matching and uses the result to determine the degree of matching.

[0805] "Application example 2 when combining with an emotional engine"

[0806] (Claim 1)

[0807] A means of receiving data on requests from companies,

[0808] Means for obtaining employee history and performance data,

[0809] A means for analyzing the aforementioned request data and historical data to extract features,

[0810] Based on the extracted characteristics, a means for identifying employees who meet the requirements,

[0811] A means of evaluating the user's emotional state,

[0812] A means for dynamically adjusting the priority of an identified employee based on the aforementioned emotional state,

[0813] means for outputting the information of the identified employee,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, wherein natural language processing technology is used for analyzing the aforementioned request data, historical data, and emotional state.

[0817] (Claim 3)

[0818] The system according to claim 1, which, in identifying a suitable employee, calculates a numerical degree of suitability and adjusts priorities based on emotional state. [Explanation of Symbols]

[0819] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving data on requests from companies, Means for obtaining employee career and performance data, A means for analyzing the aforementioned request data and career data to extract features, Based on the extracted characteristics, a means for identifying employees who meet the requirements, means for outputting the information of the identified employee, A system that includes this.

2. The system according to claim 1, wherein natural language processing technology is used to analyze the aforementioned request data and career data.

3. The system according to claim 1, which, in identifying a suitable employee, calculates a numerically defined degree of suitability and uses the result to determine the suitability.

Images