system

Abstract

We provide the system. [Solution] Means for collecting user activity data, A means for evaluating the user's skills based on the aforementioned activity data, A means of proposing the most suitable job to the user based on the aforementioned skill evaluation, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In order to appropriately allocate human resources within a company, it is essential to accurately grasp the skills of individual members. However, in conventional self-evaluation and personnel evaluation methods, evaluations often deviate from actual skills due to subjectivity and judgments from limited perspectives. Also, in the modern business environment that demands rapid organizational changes and new career opportunities, real-time skill evaluation and appropriate placement of personnel are required. Against this background, there is a need to develop a new system that objectively and automatically evaluates skills and proposes optimal job positions. 【Means for Solving the Problems】 【0005】 This invention provides a system that automatically collects user activity data and objectively evaluates skills based on the collected data. Specifically, it extracts text information from the user's communication and task history in their work and generates a skill score using natural language processing technology. Furthermore, based on the generated skill score, a matching engine proposes the most suitable job for the user. This makes it possible to quickly and effectively allocate personnel through objective data analysis, thereby improving job efficiency and satisfaction. 【0006】 "User activity data" refers to information about user behavior, including communication and task history during work. 【0007】 "Means of collection" refers to methods and technologies for automatically acquiring data from various platforms. 【0008】 "Means of evaluating skills" refer to algorithms and processes that analyze collected data and objectively measure a user's abilities. 【0009】 "A means of proposing the most suitable job" refers to a process of identifying and presenting suitable jobs and positions for users based on their skill assessment results. 【0010】 "Means for extracting text information" refers to methods and techniques for extracting necessary character information from collected data. 【0011】 "Means for generating skill scores" refer to methods and technologies for quantifying a user's skill level using analyzed data. 【0012】 A "skill mapping database" is a collection of information that stores user skill information in relation to the competency requirements sought by an organization. 【0013】 A "matching engine" is a system that compares skill assessment results with the organization's job requirements, and is a core element for optimal talent placement. [Brief explanation of the drawing] 【0014】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [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】 【0015】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0016】 First, the terms used in the following description will be explained. 【0017】 In the following embodiments, a labeled 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), and the like. 【0018】 In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0019】 In the following embodiments, a labeled 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. 【0020】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0021】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0022】 [First Embodiment] 【0023】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0024】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0025】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0026】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0027】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0028】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0029】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0030】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0031】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0032】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0033】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0034】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0035】 This invention is a system that evaluates a user's skills and suggests appropriate job roles based on data obtained through the user's work activities. This system consists of three main elements: a server, a terminal, and the user. The role of each element is described below. 【0036】 The server is the main component that performs centralized data processing and analysis. First, the server automatically collects user activity data from various business tools and communication platforms. This data includes email exchanges, actions on project management tools, and chat logs. The collected data is formatted through a cleaning process to remove unnecessary information. Then, text analysis is performed using natural language processing techniques, and the user's skill level is calculated by a skill evaluation algorithm. This calculated skill score is recorded in a skill mapping database and integrated into the user's profile. The server also uses this data to perform calculations that enable the matching engine to determine the most suitable job for the user. 【0037】 The terminal acts as an interface with the user and is used to present evaluation results. The terminal displays skill evaluation results and job suggestions obtained from the server in a user-friendly format. Specifically, users see a detailed skill evaluation visualized on their dashboard, and new career suggestions appear as notifications. This allows users to objectively understand their own skill level and decide on their next career step. 【0038】 Through this system, users can receive regular skill assessments, review proposed job roles, and reassess their career direction. They can consider new job offers and make choices that align with their personal growth. In this way, users can objectively analyze their skills and aim for further career advancement. 【0039】 By using this system, users' skills are regularly evaluated through their daily work, and optimal job positions are suggested, enabling efficient talent allocation within the organization. As a result, overall company productivity can be improved, and individual users' career paths can be optimized. 【0040】 The following describes the processing flow. 【0041】 Step 1: 【0042】 The server automatically collects data related to users' work activities from various communication platforms and business tools. This includes emails, chat logs, and project management system update histories, and the data is collected in real time using APIs and web crawlers. 【0043】 Step 2: 【0044】 The server preprocesses the collected data. Unnecessary information is removed, and the text data is cleaned to prepare it for analysis. This process also includes correcting spelling errors and standardizing the formatting. 【0045】 Step 3: 【0046】 The server analyzes pre-processed text data. Using natural language processing techniques, it extracts keywords from the text and identifies the user's skills based on their activities. This analysis result is quantified by a skill evaluation algorithm, and a skill score is generated. 【0047】 Step 4: 【0048】 The server generates skill scores which are then stored in a skill mapping database. This database continuously updates and compares each user's skills with the skill requirements sought by the company. 【0049】 Step 5: 【0050】 The server uses information from the skills mapping database to perform a matching process that identifies suitable jobs and career opportunities for the user. It matches the user's skills with the organization's requirements in real time to determine the optimal job position. 【0051】 Step 6: 【0052】 The terminal displays evaluation results and job suggestions sent from the server to the user. Through the user interface, skill evaluations and specific career opportunities are displayed on a dashboard. 【0053】 Step 7: 【0054】 Users review the information presented and consider the suggested job roles and career opportunities. By providing feedback, data is accumulated to improve the system's accuracy and the appropriateness of its suggestions. 【0055】 (Example 1) 【0056】 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." 【0057】 In today's work environment, efficiently evaluating users' skills and proposing the most suitable job based on those evaluations is challenging. While companies need to provide appropriate jobs that match individual abilities and motivations, manual evaluation is time-consuming, labor-intensive, and often lacks objectivity. Therefore, there is a need for a system that uses users' work data to objectively and efficiently assess skills and propose the most suitable job. 【0058】 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. 【0059】 In this invention, the server includes means for collecting user behavior information from various sources and organizing the behavior information while eliminating duplication; means for analyzing the behavior information and performing a skills assessment based on natural language; and means for deriving and presenting suitable jobs using a generative AI model. This makes it possible to quickly and accurately suggest the most suitable job for each individual by continuously evaluating the user's skills. 【0060】 "User behavior information" refers to all data generated by users through their work activities, such as emails, project management logs, and chat logs. 【0061】 "Information sources" refer to various business tools and communication platforms used to obtain user activity information. 【0062】 "Organizing" refers to the process of removing duplicate or unnecessary parts from collected behavioral information and converting it into a format suitable for analysis. 【0063】 "Natural language-based skill assessment" refers to a method that uses natural language processing technology to analyze behavioral information and quantify and evaluate a user's skills. 【0064】 A "generative AI model" refers to an algorithm or tool that utilizes machine learning technology to recommend the most suitable job based on the user's skill information. 【0065】 "Suitable job" refers to the job title or position that best matches the user's skills and evaluation, as suggested based on the user's abilities and performance. 【0066】 "Job requirements" refer to the skills, experience, and knowledge required for a specific job, and serve as the basis for matching the user's skills. 【0067】 The embodiments for carrying out the present invention are shown below. 【0068】 This system is realized with servers, terminals, and users as its main components, each playing a specific role. 【0069】 The server plays a central role in aggregating, organizing, and analyzing user behavior information. The server collects digital data such as emails, project management tools, and chat logs obtained from users' daily work. This could potentially utilize automated data collection scripts written in programming languages ​​such as Python or Java. The collected data is then processed through a data cleansing process to remove redundancy and convert it into a format suitable for analysis. Next, natural language processing libraries such as NLTK and SpaCy are used to analyze the behavioral information and evaluate user skills. 【0070】 Based on the acquired skill assessment data, the server executes a generative AI model. For example, it uses Tensorflow® or PyTorch to perform calculations to suggest the job best suited to the user's skills. This suggestion uses prompt statements. A concrete example of a prompt statement would be, "Assess the user's project management skills and suggest an appropriate job." 【0071】 The terminal serves to present the user with skill assessments and job suggestions obtained from the server. The user interface can be built using libraries such as React or Angular, and it displays skill assessment results and notifications of suitable jobs in an easy-to-understand visual format. 【0072】 Users review the content presented through their devices, reassessing their skills and career plans. They can consider newly proposed job opportunities and choose roles that align with their personal growth. Through this process, users receive continuous skill evaluations and appropriate job suggestions, gaining valuable opportunities for career advancement. 【0073】 Thus, the present invention supports intelligent personnel allocation and enables the maximization of individual users' capabilities. 【0074】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0075】 Step 1: 【0076】 The server automatically collects user behavior information from various tools and platforms. Input data includes emails, project management tools, and chat logs. APIs and scraping techniques may be used to collect this data. The data is stored in raw form. 【0077】 Step 2: 【0078】 The server performs data cleansing on the collected raw data. This process involves filtering to remove duplicates and noise. The input is the raw data collected in step 1, and the output is the formatted, clean data. This clean data is processed to include only the information necessary for analysis. 【0079】 Step 3: 【0080】 The server analyzes the formatted data using natural language processing techniques. Specifically, it analyzes the specialized terminology and context contained in the text. The input is clean data, and the output is a score that quantifies the user's skill level. This process uses natural language processing libraries such as NLTK and SpaCy. 【0081】 Step 4: 【0082】 The server runs a generative AI model and uses the calculated skill score to suggest the most suitable job. The input consists of the skill score and the generative AI model prompt. The prompt used is "Evaluate the user's XX skills and suggest an appropriate job." The output is a list of suggested jobs, sorted in descending order of matching degree. 【0083】 Step 5: 【0084】 The terminal presents the user with skill assessment results and job suggestions sent from the server. Inputs are a list of suggested jobs and skill scores. The terminal uses a user interface based on React or Angular to visually display this information on a dashboard. Outputs are visualized assessment results and job suggestions for the user. 【0085】 Step 6: 【0086】 The user reviews the provided information and re-evaluates their career plan. Input consists of job suggestions and skill assessment results presented from the terminal. The user selects jobs of interest from the presented options and obtains further information. Output is the user's chosen next job or learning plan. The user's selection is fed back into the system and used to improve future suggestions. 【0087】 (Application Example 1) 【0088】 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." 【0089】 In smart cities, residents and staff are expected to maximize their abilities and participate in appropriate activities to improve the overall efficiency of the city. However, until now, there has been no system in place to effectively collect information on each individual's activities and propose appropriate activities based on that data. If appropriate activities are not proposed, individuals' abilities may not be fully utilized, potentially hindering the city's development and efficiency improvements. 【0090】 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. 【0091】 In this invention, the server includes means for collecting user activity information, means for evaluating the user's technical capabilities based on the activity information, means for proposing the most suitable activity to the user based on the technical capability evaluation, and means for providing notifications regarding the proposed activity to the user's portable electronic device. This enables residents and staff to quickly participate in activities best suited to their abilities, thereby improving the overall operational efficiency of the smart city. 【0092】 "Means for collecting user activity information" refers to technologies or methods for systematically collecting data on the actions and operations that individual users perform in their daily lives and work. 【0093】 "Means of evaluating technical capabilities" refers to technologies or methods that measure and judge the level of a user's skills and knowledge using numerical values ​​or indicators based on collected activity information. 【0094】 "Means of proposing optimal activities" refers to techniques or methods that, taking into account the evaluated technical abilities, indicate to users the most appropriate actions to take, such as jobs or volunteer activities. 【0095】 "Means of providing notifications" means a technology or method that sends visual or auditory alerts or messages to a user's mobile electronic device regarding a proposed activity. 【0096】 The system that realizes this invention mainly consists of a server, a terminal, and a user. 【0097】 The server plays a central role in receiving and processing user activity information. The hardware used is a data server equipped with a powerful processor and sufficient storage. Frameworks such as Python and Django are used for data processing. Specifically, the NLTK library is used for natural language processing to analyze user activity information and quantify technical skills. Based on this skill assessment, an activity matching engine using a generative AI model works to generate optimal activity suggestions. 【0098】 The terminal is the user's portable electronic device and functions as an interface to provide the user with notifications of suggested activities. An application is installed, providing visual notifications and reminders, allowing the user to easily choose their next action. Activity information is also transmitted from this terminal to the server. 【0099】 Users engage with the system on a daily basis and receive skill assessments and suggestions through system feedback. For example, a city hall might host a digital literacy improvement event, and citizens deemed to have high IT skills might receive invitations to participate. Users can check these notifications on their smartphones and decide whether or not to attend the event. 【0100】 To ensure the generative AI model functions correctly, enter the following as an example prompt: "Based on citizen activity data, perform a skills assessment and propose suitable volunteer activities. The assessment will use past activity history and event participation data, and will also take into account communication skills and IT skills." This prompt will cause the generative AI model to generate output that provides appropriate suggestions to the user. 【0101】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0102】 Step 1: 【0103】 Users input daily activity information into the system via their smartphones. This activity information is automatically collected by communication apps and scheduling tools. The input data is sent to the server in its original format. The output is then saved to the server in a unified format. 【0104】 Step 2: 【0105】 The server processes the received activity information through a data cleaning process. This process involves formatting the data and removing unnecessary information. The input is raw data, and the output is clean data that can be analyzed. Specifically, this involves imputing missing values ​​and removing duplicate data. 【0106】 Step 3: 【0107】 The server analyzes clean data using natural language processing techniques. It receives processed clean data as input, extracts text information, and quantifies the user's skill level. A skill score is generated as output and recorded in the database. During this process, the NLTK library is utilized for vocabulary analysis and syntax understanding. 【0108】 Step 4: 【0109】 The server uses the generated skill score to send a prompt to the AI ​​model, which then creates the optimal activity suggestion. The prompt is "Based on citizen activity data, please assess skills and suggest suitable volunteer activities," and the output is the suggested activity. 【0110】 Step 5: 【0111】 The server sends the generated proposal to the terminal and notifies the user. The notification is played back on the user's smartphone through the app. The output is a visual notification displaying detailed information about the proposed activity. The user reviews this notification and decides whether to participate in the activity. 【0112】 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. 【0113】 This invention is a system that evaluates skills based on user work activity data and combines them with an emotion engine to propose the most suitable job to the user. This system takes the user's emotional state into consideration to achieve more personalized job recommendations. The specific configuration and operation of the system are described below. 【0114】 The server collects data on the user's work activities from various platforms, including email, chat tools, and project management tools. The server extracts text information from this data and performs a standard skills assessment process. In parallel, the server activates an emotion engine to detect emotions from the user's text information. The emotion engine utilizes natural language processing to identify positive, negative, and neutral emotions, quantifying them and storing them as data. 【0115】 The terminal presents the user with skill assessments and emotion analysis results transmitted from the server. The terminal visualizes job suggestions based not only on skill scores but also on emotional states. This allows users to objectively understand their own skill level and emotional state, which can assist them in job selection. For example, if the emotion engine detects that a user is experiencing stress in a project, the terminal will display suggestions for less stressful jobs to that user. 【0116】 Users review the presented job offers and make career decisions. They contribute to system improvement by considering job offers based on their skills and emotions and providing feedback. This feedback is stored on the server and used to improve the accuracy of subsequent skill assessments and emotion recognition. 【0117】 Through this system, companies can make appropriate job assignments that take into account employees' emotional states, which is expected to improve efficiency and satisfaction in the workplace. Furthermore, users will be able to choose career paths that take their own emotions into consideration. 【0118】 The following describes the processing flow. 【0119】 Step 1: 【0120】 The server collects user work activity data from various platforms, including email, chat, and project management tools. The collected data is used for both skill assessment and sentiment recognition. 【0121】 Step 2: 【0122】 The server preprocesses the collected data. This involves cleaning the data and formatting the text to make it suitable for analysis. This processing is necessary for skill assessment and sentiment analysis. 【0123】 Step 3: 【0124】 The server analyzes text data and evaluates the user's skills. Using natural language processing techniques, it extracts important keywords from the text and quantifies the skills based on them. This skill score is stored in a skill mapping database. 【0125】 Step 4: 【0126】 In parallel, the server runs an emotion engine to recognize the user's emotions from text data. It identifies emotional states such as positive, negative, and neutral, and records them as a numerical emotion score. 【0127】 Step 5: 【0128】 The server integrates the acquired skill and sentiment scores and executes a matching process to suggest the most suitable job. Based on the user's skills and sentiment, it matches them with the organization's job requirements. 【0129】 Step 6: 【0130】 The terminal presents job suggestions from the server to the user. These suggestions, which consider not only skill assessments but also emotional states, are visualized and displayed on the user's dashboard. 【0131】 Step 7: 【0132】 Users review the presented suggestions and make choices regarding their careers. By providing feedback, data is accumulated that improves the accuracy of the system's analysis results and suggestions. 【0133】 (Example 2) 【0134】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0135】 Conventional systems only perform skill assessments based on data obtained from users' work activities, and lack job suggestions that take into account the user's emotional state. As a result, it is difficult to suggest appropriate jobs to individual users, and there is a challenge in improving user stress and satisfaction. 【0136】 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. 【0137】 In this invention, the server includes means for collecting information related to the user's work activities, means for extracting text information from the information and analyzing the user's emotional state using natural language processing, and means for analyzing the text information and evaluating the user's skills. This enables personalized job recommendations that take into account both the user's skill assessment and emotional state. 【0138】 "Information related to the user's work activities" refers to data about the user's daily work, including text and metadata obtained from emails, messages, task management, etc. 【0139】 "A method for extracting text information and analyzing a user's emotional state using natural language processing" refers to the process of extracting necessary text portions from collected data and classifying and quantifying the emotions within the text as positive, negative, or neutral using machine learning techniques. 【0140】 "Methods for evaluating user skills" refer to the process of applying generative AI models or machine learning algorithms based on extracted text information to quantify and express the level of a user's abilities and knowledge. 【0141】 "Personalized job recommendations" refer to suggestions that recommend the most suitable roles and tasks for each user, taking into account their individual skills and emotional state. 【0142】 "Means of collecting feedback" refers to an interface for users to input their opinions and impressions of the presented suggestions into the system, as well as a database for storing that information. 【0143】 "Methods for improving system accuracy" refers to the process of analyzing collected feedback, incorporating the results into algorithms for future skill evaluations and sentiment analysis, and thereby improving the quality of suggestions. 【0144】 This invention relates to a system that collects information related to a user's work activities and provides personalized job recommendations through skill evaluation and emotional state analysis. 【0145】 The server first collects information related to the user's work activities from various sources. Specifically, it retrieves text and metadata from email systems, messaging applications, and task management tools via APIs. Next, it formats the collected data using Python libraries and extracts the necessary text information. This utilizes data processing libraries such as pandas. After this, it analyzes the user's emotional state using natural language processing techniques on the extracted text information. A machine learning model using TensorFlow quantifies emotions such as positive, negative, and neutral. 【0146】 Subsequently, the server uses a generative AI model to evaluate the user's skills. In this process, machine learning libraries such as scikit-learn are utilized to extract keywords from the text and quantify the user's skills. 【0147】 The terminal retrieves skill evaluation scores and emotional scores generated by the server and displays the information to the user in a visually easy-to-understand format. Through an interactive dashboard using JavaScript (registered trademark), users can understand their own skills and emotional state and view job suggestions based on them. Specifically, if the terminal determines that an emotional state is due to stress, it will display less stressful jobs as suggestions. 【0148】 Users make career decisions based on job suggestions displayed on their devices and provide feedback. This feedback is collected by a server and used to improve the system's accuracy. User feedback allows the system to continuously learn, enabling it to provide more accurate suggestions in future skill assessments and sentiment analyses. 【0149】 For example, if a user frequently sends emails reporting on project progress, the server can detect emotions indicating stress from those emails, and the terminal will then suggest a support role rather than project management based on this. This system can gain more advanced insights by inputting prompts using a generative AI model. For instance, a prompt such as "Suggest a role that takes emotions into account, based on the user's work activity data" can be used to specify the scope of tasks the system should perform. 【0150】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0151】 Step 1: 【0152】 The server collects information related to the user's work activities. Specifically, it retrieves data from various sources, such as email systems, messaging applications, and task management tool APIs. The input at this stage is configuration data, including user account information and access permissions, and the output is raw work activity data. The server temporarily stores the retrieved data in preparation for subsequent processing. 【0153】 Step 2: 【0154】 The server extracts necessary text information from the collected data and performs preprocessing. Specifically, it uses a Python library (e.g., pandas) to format the data and remove unnecessary strings and HTML tags that would cause noise. The input to this process is raw business activity data, and the output is formatted text data. This formatted data is then used for subsequent sentiment analysis and skill assessment. 【0155】 Step 3: 【0156】 The server analyzes emotional states using formatted text data. Specifically, it uses natural language processing techniques and applies a TensorFlow sentiment analysis model to calculate positive, negative, and neutral sentiment scores. The input for this step is formatted text data, and the output is a numerical sentiment score. The server stores this sentiment score in a database. 【0157】 Step 4: 【0158】 The server uses a generative AI model to evaluate the user's skills. This model extracts keywords from text data and uses their frequency and relevance to quantify a skill score. At this stage, the input is formatted text data, and the output is a quantified skill score. The server records the skill score, along with the sentiment score, in a database. 【0159】 Step 5: 【0160】 The terminal retrieves skill and sentiment scores sent from the server and presents them visually to the user. Using JavaScript, the scores and suggestions are displayed in the interface as graphs and tables. The input for this step is the skill and sentiment scores, and the output is a visualized display on the user interface. This allows the terminal to present the user with less stressful job suggestions. 【0161】 Step 6: 【0162】 Users select career options based on job suggestions displayed on their terminals and provide feedback. Specifically, users evaluate the usefulness and suitability of the suggestions. Input is the job suggestions displayed on the terminal, and output is the user's feedback data sent to the server. This feedback is reflected in subsequent skill evaluations and sentiment analysis, contributing to system improvement. 【0163】 (Application Example 2) 【0164】 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". 【0165】 In today's workplace environment, there is a growing need to properly manage employees' emotions and stress levels. However, traditional job suggestion systems based on work data have the challenge of not considering the user's emotional state and therefore being unable to suggest the most suitable job. Furthermore, there has been no clear means of providing employees with specific information to understand their own emotional state and improve their behavior based on that understanding. 【0166】 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. 【0167】 In this invention, the server includes means for collecting user work activity data, means for analyzing the user's work activity data to generate an emotion score, and means for providing the user with job suggestions and self-care advice based on skill evaluation and emotion analysis. This enables the user to understand their own emotional state and select the most appropriate job and self-care actions accordingly. 【0168】 "User work activity data" refers to information related to all activities that a user performs in the course of their work, including communication records such as emails, chat messages, and project management tools. 【0169】 "Skill assessment" is a process of quantifying or qualitatively analyzing a user's abilities and expertise based on their work activity data. 【0170】 "Emotional state" refers to a psychological state identified from a user's text information and other relevant data, and includes emotional categories such as positive, negative, and neutral. 【0171】 "Self-care advice" refers to specific suggestions and action plans provided to promote psychological and physical health, based on the user's current emotional state and work environment. 【0172】 An "emotion score" is a numerical value calculated by analyzing a user's text information using a specific algorithm or model, and it is an indicator that quantitatively shows the user's emotional state. 【0173】 A "job suggestion" refers to a proposal for assigning the most suitable role or task to a user, based on their skill assessment and emotional state. 【0174】 This system provides users with optimal job recommendations and self-care advice based on skill assessments and sentiment analysis derived from their work activity data. The system's hardware and software configuration, along with its specific operation methods, are described below. 【0175】 The server collects user work activity data from the business platform. Specifically, the server uses communication APIs to extract necessary data from email, chat messages, and project management tools. At this stage, programming languages ​​such as Python and Java are used to standardize the data. 【0176】 Next, the server analyzes the text information of the collected activity data using natural language processing tools (e.g., NLTK or spaCy). For sentiment analysis, it utilizes deep learning models (e.g., BERT or Hugging Face Transformers) to calculate sentiment scores. Finally, to perform skill assessment from the text information, it uses data analysis libraries (e.g., pandas, scikit-learn). 【0177】 Based on the analyzed skill assessment and emotion score, the server uses a generative AI model to generate job suggestions and specific advice for self-care. These generated suggestions are then sent to the user's device. 【0178】 The device presents suggestions to the user through an interactive user interface (e.g., React Native or Swift). The user can review the presented job suggestions and self-care advice and select actionable steps. 【0179】 As a concrete example, if the emotion engine determines that user A is experiencing excessive stress in a chat, the system will suggest a 15-minute relaxation yoga session to A. In this case, the generative AI model will use a prompt message like the following: 【0180】 "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0181】 In this way, the system can respond to the user's emotional state, enabling the user to take appropriate stress management measures. 【0182】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0183】 Step 1: 【0184】 The server collects user work activity data from the business platform via APIs. Input data includes emails, chat messages, and message logs from project management tools. The server converts this data into a standard format and stores it in a database. 【0185】 Step 2: 【0186】 The server uses natural language processing tools (such as NLTK and spaCy) to analyze collected text data and generate sentiment scores. The input is text information, and the output is a sentiment score indicating positive, negative, or neutral. The server extracts statistical features from the text and calculates the sentiment score using a sentiment analysis algorithm. 【0187】 Step 3: 【0188】 The server performs skill assessments using data analysis libraries (such as pandas and scikit-learn). The input data consists of standardized work activity data from the previous step, and the output is an evaluation score indicating the user's skills. The server calculates specific patterns and keywords in the data to generate skill evaluation metrics. 【0189】 Step 4: 【0190】 The server uses a generative AI model to generate job suggestions and self-care advice based on emotion scores and skill assessments. The input data consists of emotion scores and skill assessment scores, and the output is corresponding job suggestions and advice. The generative AI model generates responses using the prompt "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0191】 Step 5: 【0192】 The terminal presents the user with job suggestions and self-care advice received from the server. The input data is the suggestion information provided by the server, and the output is a display on the user interface. The terminal visualizes the suggestions, allowing the user to review and select from them. 【0193】 Step 6: 【0194】 Users review the suggestions displayed on their device and select jobs and self-care options that suit them. The input is the provided job suggestions and advice, while the output is the user's chosen actions. Users provide feedback on their selections via their device and send it to the server. This feedback is used to improve the system in the future. 【0195】 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. 【0196】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0197】 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. 【0198】 [Second Embodiment] 【0199】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0200】 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. 【0201】 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). 【0202】 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. 【0203】 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. 【0204】 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). 【0205】 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. 【0206】 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. 【0207】 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. 【0208】 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. 【0209】 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. 【0210】 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". 【0211】 This invention is a system that evaluates a user's skills and suggests appropriate job roles based on data obtained through the user's work activities. This system consists of three main elements: a server, a terminal, and the user. The role of each element is described below. 【0212】 The server is the main component that performs centralized data processing and analysis. First, the server automatically collects user activity data from various business tools and communication platforms. This data includes email exchanges, actions on project management tools, and chat logs. The collected data is formatted through a cleaning process to remove unnecessary information. Then, text analysis is performed using natural language processing techniques, and the user's skill level is calculated by a skill evaluation algorithm. This calculated skill score is recorded in a skill mapping database and integrated into the user's profile. The server also uses this data to perform calculations that enable the matching engine to determine the most suitable job for the user. 【0213】 The terminal acts as an interface with the user and is used to present evaluation results. The terminal displays skill evaluation results and job suggestions obtained from the server in a user-friendly format. Specifically, users see a detailed skill evaluation visualized on their dashboard, and new career suggestions appear as notifications. This allows users to objectively understand their own skill level and decide on their next career step. 【0214】 Through this system, users can receive regular skill assessments, review proposed job roles, and reassess their career direction. They can consider new job offers and make choices that align with their personal growth. In this way, users can objectively analyze their skills and aim for further career advancement. 【0215】 By using this system, users' skills are regularly evaluated through their daily work, and optimal job positions are suggested, enabling efficient talent allocation within the organization. As a result, overall company productivity can be improved, and individual users' career paths can be optimized. 【0216】 The following describes the processing flow. 【0217】 Step 1: 【0218】 The server automatically collects data related to users' work activities from various communication platforms and business tools. This includes emails, chat logs, and project management system update histories, and the data is collected in real time using APIs and web crawlers. 【0219】 Step 2: 【0220】 The server preprocesses the collected data. Unnecessary information is removed, and the text data is cleaned to prepare it for analysis. This process also includes correcting spelling errors and standardizing the formatting. 【0221】 Step 3: 【0222】 The server analyzes pre-processed text data. Using natural language processing techniques, it extracts keywords from the text and identifies the user's skills based on their activities. This analysis result is quantified by a skill evaluation algorithm, and a skill score is generated. 【0223】 Step 4: 【0224】 The server generates skill scores which are then stored in a skill mapping database. This database continuously updates and compares each user's skills with the skill requirements sought by the company. 【0225】 Step 5: 【0226】 The server uses information from the skills mapping database to perform a matching process that identifies suitable jobs and career opportunities for the user. It matches the user's skills with the organization's requirements in real time to determine the optimal job position. 【0227】 Step 6: 【0228】 The terminal displays evaluation results and job suggestions sent from the server to the user. Through the user interface, skill evaluations and specific career opportunities are displayed on a dashboard. 【0229】 Step 7: 【0230】 Users review the information presented and consider the suggested job roles and career opportunities. By providing feedback, data is accumulated to improve the system's accuracy and the appropriateness of its suggestions. 【0231】 (Example 1) 【0232】 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." 【0233】 In today's work environment, efficiently evaluating users' skills and proposing the most suitable job based on those evaluations is challenging. While companies need to provide appropriate jobs that match individual abilities and motivations, manual evaluation is time-consuming, labor-intensive, and often lacks objectivity. Therefore, there is a need for a system that uses users' work data to objectively and efficiently assess skills and propose the most suitable job. 【0234】 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. 【0235】 In this invention, the server includes means for collecting user behavior information from various sources and organizing the behavior information while eliminating duplication; means for analyzing the behavior information and performing a skills assessment based on natural language; and means for deriving and presenting suitable jobs using a generative AI model. This makes it possible to quickly and accurately suggest the most suitable job for each individual by continuously evaluating the user's skills. 【0236】 "User behavior information" refers to all data generated by users through their work activities, such as emails, project management logs, and chat logs. 【0237】 "Information sources" refer to various business tools and communication platforms used to obtain user activity information. 【0238】 "Organizing" refers to the process of removing duplicate or unnecessary parts from collected behavioral information and converting it into a format suitable for analysis. 【0239】 "Natural language-based skill assessment" refers to a method that uses natural language processing technology to analyze behavioral information and quantify and evaluate a user's skills. 【0240】 A "generative AI model" refers to an algorithm or tool that utilizes machine learning technology to recommend the most suitable job based on the user's skill information. 【0241】 "Suitable job" refers to the job title or position that best matches the user's skills and evaluation, as suggested based on the user's abilities and performance. 【0242】 "Job requirements" refer to the skills, experience, and knowledge required for a specific job, and serve as the basis for matching the user's skills. 【0243】 The embodiments for carrying out the present invention are shown below. 【0244】 This system is realized with servers, terminals, and users as its main components, each playing a specific role. 【0245】 The server plays a central role in aggregating, organizing, and analyzing user behavior information. The server collects digital data such as emails, project management tools, and chat logs from users' daily work. This could potentially utilize automated data collection scripts written in programming languages ​​like Python or Java. The collected data is then processed through a data cleansing process to remove redundancy and convert it into a format suitable for analysis. Next, natural language processing libraries such as NLTK and SpaCy are used to analyze the behavioral information and evaluate user skills. 【0246】 Based on the acquired skill assessment data, the server executes a generative AI model. For example, it uses TensorFlow or PyTorch to perform calculations to suggest the job best suited to the user's skills. This suggestion uses prompt statements. A concrete example of a prompt statement would be, "Assess the user's project management skills and suggest a suitable job." 【0247】 The terminal serves to present the user with skill assessments and job suggestions obtained from the server. The user interface can be built using libraries such as React or Angular, and it displays skill assessment results and notifications of suitable jobs in an easy-to-understand visual format. 【0248】 Users review the content presented through their devices, reassessing their skills and career plans. They can consider newly proposed job opportunities and choose roles that align with their personal growth. Through this process, users receive continuous skill evaluations and appropriate job suggestions, gaining valuable opportunities for career advancement. 【0249】 Thus, the present invention supports intelligent personnel allocation and enables the maximization of individual users' capabilities. 【0250】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0251】 Step 1: 【0252】 The server automatically collects user behavior information from various tools and platforms. Input data includes emails, project management tools, and chat logs. APIs and scraping techniques may be used to collect this data. The data is stored in raw form. 【0253】 Step 2: 【0254】 The server performs data cleansing on the collected raw data. This process involves filtering to remove duplicates and noise. The input is the raw data collected in step 1, and the output is the formatted, clean data. This clean data is processed to include only the information necessary for analysis. 【0255】 Step 3: 【0256】 The server analyzes the formatted data using natural language processing techniques. Specifically, it analyzes the specialized terminology and context contained in the text. The input is clean data, and the output is a score that quantifies the user's skill level. This process uses natural language processing libraries such as NLTK and SpaCy. 【0257】 Step 4: 【0258】 The server runs a generative AI model and uses the calculated skill score to suggest the most suitable job. The input consists of the skill score and the generative AI model prompt. The prompt used is "Evaluate the user's XX skills and suggest an appropriate job." The output is a list of suggested jobs, sorted in descending order of matching degree. 【0259】 Step 5: 【0260】 The terminal presents the user with skill assessment results and job suggestions sent from the server. Inputs are a list of suggested jobs and skill scores. The terminal uses a user interface based on React or Angular to visually display this information on a dashboard. Outputs are visualized assessment results and job suggestions for the user. 【0261】 Step 6: 【0262】 The user reviews the provided information and re-evaluates their career plan. Input consists of job suggestions and skill assessment results presented from the terminal. The user selects jobs of interest from the presented options and obtains further information. Output is the user's chosen next job or learning plan. The user's selection is fed back into the system and used to improve future suggestions. 【0263】 (Application Example 1) 【0264】 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." 【0265】 In smart cities, residents and staff are expected to maximize their abilities and participate in appropriate activities to improve the overall efficiency of the city. However, until now, there has been no system in place to effectively collect information on each individual's activities and propose appropriate activities based on that data. If appropriate activities are not proposed, individuals' abilities may not be fully utilized, potentially hindering the city's development and efficiency improvements. 【0266】 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. 【0267】 In this invention, the server includes means for collecting user activity information, means for evaluating the user's technical capabilities based on the activity information, means for proposing the most suitable activity to the user based on the technical capability evaluation, and means for providing notifications regarding the proposed activity to the user's portable electronic device. This enables residents and staff to quickly participate in activities best suited to their abilities, thereby improving the overall operational efficiency of the smart city. 【0268】 "Means for collecting user activity information" refers to technologies or methods for systematically collecting data on the actions and operations that individual users perform in their daily lives and work. 【0269】 "Means of evaluating technical capabilities" refers to technologies or methods that measure and judge the level of a user's skills and knowledge using numerical values ​​or indicators based on collected activity information. 【0270】 "Means of proposing optimal activities" refers to techniques or methods that, taking into account the evaluated technical abilities, indicate to users the most appropriate actions to take, such as jobs or volunteer activities. 【0271】 "Means of providing notifications" means a technology or method that sends visual or auditory alerts or messages to a user's mobile electronic device regarding a proposed activity. 【0272】 The system that realizes this invention mainly consists of a server, a terminal, and a user. 【0273】 The server plays a central role in receiving and processing user activity information. The hardware used is a data server equipped with a powerful processor and sufficient storage. Frameworks such as Python and Django are used for data processing. Specifically, the NLTK library is used for natural language processing to analyze user activity information and quantify technical skills. Based on this skill assessment, an activity matching engine using a generative AI model works to generate optimal activity suggestions. 【0274】 The terminal is the user's portable electronic device and functions as an interface to provide the user with notifications of suggested activities. An application is installed, providing visual notifications and reminders, allowing the user to easily choose their next action. Activity information is also transmitted from this terminal to the server. 【0275】 Users engage with the system on a daily basis and receive skill assessments and suggestions through system feedback. For example, a city hall might host a digital literacy improvement event, and citizens deemed to have high IT skills might receive invitations to participate. Users can check these notifications on their smartphones and decide whether or not to attend the event. 【0276】 To ensure the generative AI model functions correctly, enter the following as an example prompt: "Based on citizen activity data, perform a skills assessment and propose suitable volunteer activities. The assessment will use past activity history and event participation data, and will also take into account communication skills and IT skills." This prompt will cause the generative AI model to generate output that provides appropriate suggestions to the user. 【0277】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0278】 Step 1: 【0279】 Users input daily activity information into the system via their smartphones. This activity information is automatically collected by communication apps and scheduling tools. The input data is sent to the server in its original format. The output is then saved to the server in a unified format. 【0280】 Step 2: 【0281】 The server applies the received activity information to a data cleaning process. In this process, data formatting and removal of unnecessary information are performed. The input is raw data, and the output is clean data that can be analyzed. Specifically, it performs tasks such as filling in missing values and deleting duplicate data. 【0282】 Step 3: 【0283】 The server analyzes the clean data using natural language processing techniques. It receives the processed clean data as input, extracts text information, and quantifies the user's skill level. As output, a skill score is generated and recorded in the database. At this time, the NLTK library is utilized to perform vocabulary analysis and syntactic understanding. 【0284】 Step 4: 【0285】 The server sends a prompt sentence to the generated AI model using the generated skill score to create an optimal activity proposal. As the prompt sentence, "Based on the citizen's activity data, perform a skill evaluation and propose suitable volunteer activities." is input, and the proposed content is obtained as output. 【0286】 Step 5: 【0287】 The server sends the generated proposal to the terminal and notifies the user. The notification is reproduced through the app on the user's smartphone. As output, it is a visual notification, and the detailed information of the proposed activity is displayed. The user checks this notification and makes a decision on whether to participate in the activity. 【0288】 Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion. 【0289】 This invention is a system that evaluates skills based on user work activity data and combines them with an emotion engine to propose the most suitable job to the user. This system takes the user's emotional state into consideration to achieve more personalized job recommendations. The specific configuration and operation of the system are described below. 【0290】 The server collects data on the user's work activities from various platforms, including email, chat tools, and project management tools. The server extracts text information from this data and performs a standard skills assessment process. In parallel, the server activates an emotion engine to detect emotions from the user's text information. The emotion engine utilizes natural language processing to identify positive, negative, and neutral emotions, quantifying them and storing them as data. 【0291】 The terminal presents the user with skill assessments and emotion analysis results transmitted from the server. The terminal visualizes job suggestions based not only on skill scores but also on emotional states. This allows users to objectively understand their own skill level and emotional state, which can assist them in job selection. For example, if the emotion engine detects that a user is experiencing stress in a project, the terminal will display suggestions for less stressful jobs to that user. 【0292】 Users review the presented job offers and make career decisions. They contribute to system improvement by considering job offers based on their skills and emotions and providing feedback. This feedback is stored on the server and used to improve the accuracy of subsequent skill assessments and emotion recognition. 【0293】 Through this system, companies can make appropriate job assignments that take into account employees' emotional states, which is expected to improve efficiency and satisfaction in the workplace. Furthermore, users will be able to choose career paths that take their own emotions into consideration. 【0294】 The following describes the processing flow. 【0295】 Step 1: 【0296】 The server collects user work activity data from various platforms, including email, chat, and project management tools. The collected data is used for both skill assessment and sentiment recognition. 【0297】 Step 2: 【0298】 The server preprocesses the collected data. This involves cleaning the data and formatting the text to make it suitable for analysis. This processing is necessary for skill assessment and sentiment analysis. 【0299】 Step 3: 【0300】 The server analyzes text data and evaluates the user's skills. Using natural language processing techniques, it extracts important keywords from the text and quantifies the skills based on them. This skill score is stored in a skill mapping database. 【0301】 Step 4: 【0302】 In parallel, the server runs an emotion engine to recognize the user's emotions from text data. It identifies emotional states such as positive, negative, and neutral, and records them as a numerical emotion score. 【0303】 Step 5: 【0304】 The server integrates the acquired skill and sentiment scores and executes a matching process to suggest the most suitable job. Based on the user's skills and sentiment, it matches them with the organization's job requirements. 【0305】 Step 6: 【0306】 The terminal presents the job proposals from the server to the user. Proposals that take into account not only skill evaluations but also emotional states are visualized and displayed on the user's dashboard. 【0307】 Step 7: 【0308】 The user checks the presented proposals and makes selections regarding their career. By providing feedback, data is accumulated to improve the analysis results and proposal accuracy of the system. 【0309】 (Example 2) 【0310】 Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0311】 In the conventional system, only skill evaluations based on data obtained from the user's business activities are performed, and there is a lack of job proposals considering the user's emotional state. Therefore, there is a problem that it is difficult to propose appropriate jobs for individual users, and it is impossible to improve the user's stress and satisfaction. 【0312】 The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0313】 In this invention, the server includes means for collecting information related to the user's business activities, means for extracting text information from the information and analyzing the user's emotional state using natural language processing, and means for analyzing the text information to evaluate the user's skills. As a result, personalized job proposals considering both the user's skill evaluation and emotional state become possible. 【0314】 "Information related to the user's business activities" refers to data related to the user's daily business, and refers to text and metadata obtained from e-mails, messages, task management, etc. 【0315】 "A method for extracting text information and analyzing a user's emotional state using natural language processing" refers to the process of extracting necessary text portions from collected data and classifying and quantifying the emotions within the text as positive, negative, or neutral using machine learning techniques. 【0316】 "Methods for evaluating user skills" refer to the process of applying generative AI models or machine learning algorithms based on extracted text information to quantify and express the level of a user's abilities and knowledge. 【0317】 "Personalized job recommendations" refer to suggestions that recommend the most suitable roles and tasks for each user, taking into account their individual skills and emotional state. 【0318】 "Means of collecting feedback" refers to an interface for users to input their opinions and impressions of the presented suggestions into the system, as well as a database for storing that information. 【0319】 "Methods for improving system accuracy" refers to the process of analyzing collected feedback, incorporating the results into algorithms for future skill evaluations and sentiment analysis, and thereby improving the quality of suggestions. 【0320】 This invention relates to a system that collects information related to a user's work activities and provides personalized job recommendations through skill evaluation and emotional state analysis. 【0321】 The server first collects information related to the user's work activities from various sources. Specifically, it retrieves text and metadata from email systems, messaging applications, and task management tools via APIs. Next, it formats the collected data using Python libraries and extracts the necessary text information. This utilizes data processing libraries such as pandas. After this, it analyzes the user's emotional state using natural language processing techniques on the extracted text information. A machine learning model using TensorFlow quantifies emotions such as positive, negative, and neutral. 【0322】 Subsequently, the server uses a generative AI model to evaluate the user's skills. In this process, machine learning libraries such as scikit-learn are utilized to extract keywords from the text and quantify the user's skills. 【0323】 The terminal retrieves skill evaluation scores and emotional scores generated by the server and displays the information to the user in a visually easy-to-understand format. Through an interactive dashboard using JavaScript, users can understand their own skills and emotional state and view job suggestions based on that. Specifically, if the terminal determines that an emotional state is due to stress, it will display less stressful jobs as suggestions. 【0324】 Users make career decisions based on job suggestions displayed on their devices and provide feedback. This feedback is collected by a server and used to improve the system's accuracy. User feedback allows the system to continuously learn, enabling it to provide more accurate suggestions in future skill assessments and sentiment analyses. 【0325】 For example, if a user frequently sends emails reporting on project progress, the server can detect emotions indicating stress from those emails, and the terminal will then suggest a support role rather than project management based on this. This system can gain more advanced insights by inputting prompts using a generative AI model. For instance, a prompt such as "Suggest a role that takes emotions into account, based on the user's work activity data" can be used to specify the scope of tasks the system should perform. 【0326】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0327】 Step 1: 【0328】 The server collects information related to the user's work activities. Specifically, it retrieves data from various sources, such as email systems, messaging applications, and task management tool APIs. The input at this stage is configuration data, including user account information and access permissions, and the output is raw work activity data. The server temporarily stores the retrieved data in preparation for subsequent processing. 【0329】 Step 2: 【0330】 The server extracts necessary text information from the collected data and performs preprocessing. Specifically, it uses a Python library (e.g., pandas) to format the data and remove unnecessary strings and HTML tags that would cause noise. The input to this process is raw business activity data, and the output is formatted text data. This formatted data is then used for subsequent sentiment analysis and skill assessment. 【0331】 Step 3: 【0332】 The server analyzes emotional states using formatted text data. Specifically, it uses natural language processing techniques and applies a TensorFlow sentiment analysis model to calculate positive, negative, and neutral sentiment scores. The input for this step is formatted text data, and the output is a numerical sentiment score. The server stores this sentiment score in a database. 【0333】 Step 4: 【0334】 The server uses a generative AI model to evaluate the user's skills. This model extracts keywords from text data and uses their frequency and relevance to quantify a skill score. At this stage, the input is formatted text data, and the output is a quantified skill score. The server records the skill score, along with the sentiment score, in a database. 【0335】 Step 5: 【0336】 The terminal retrieves skill and sentiment scores sent from the server and presents them visually to the user. Using JavaScript, the scores and suggestions are displayed in the interface as graphs and tables. The input for this step is the skill and sentiment scores, and the output is a visualized display on the user interface. This allows the terminal to present the user with less stressful job suggestions. 【0337】 Step 6: 【0338】 Users select career options based on job suggestions displayed on their terminals and provide feedback. Specifically, users evaluate the usefulness and suitability of the suggestions. Input is the job suggestions displayed on the terminal, and output is the user's feedback data sent to the server. This feedback is reflected in subsequent skill evaluations and sentiment analysis, contributing to system improvement. 【0339】 (Application Example 2) 【0340】 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." 【0341】 In today's workplace environment, there is a growing need to properly manage employees' emotions and stress levels. However, traditional job suggestion systems based on work data have the challenge of not considering the user's emotional state and therefore being unable to suggest the most suitable job. Furthermore, there has been no clear means of providing employees with specific information to understand their own emotional state and improve their behavior based on that understanding. 【0342】 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. 【0343】 In this invention, the server includes means for collecting user work activity data, means for analyzing the user's work activity data to generate an emotion score, and means for providing the user with job suggestions and self-care advice based on skill evaluation and emotion analysis. This enables the user to understand their own emotional state and select the most appropriate job and self-care actions accordingly. 【0344】 "User work activity data" refers to information related to all activities that a user performs in the course of their work, including communication records such as emails, chat messages, and project management tools. 【0345】 "Skill assessment" is a process of quantifying or qualitatively analyzing a user's abilities and expertise based on their work activity data. 【0346】 "Emotional state" refers to a psychological state identified from a user's text information and other relevant data, and includes emotional categories such as positive, negative, and neutral. 【0347】 "Self-care advice" refers to specific suggestions and action plans provided to promote psychological and physical health, based on the user's current emotional state and work environment. 【0348】 An "emotion score" is a numerical value calculated by analyzing a user's text information using a specific algorithm or model, and it is an indicator that quantitatively shows the user's emotional state. 【0349】 A "job suggestion" refers to a proposal for assigning the most suitable role or task to a user, based on their skill assessment and emotional state. 【0350】 This system provides users with optimal job recommendations and self-care advice based on skill assessments and sentiment analysis derived from their work activity data. The system's hardware and software configuration, along with its specific operation methods, are described below. 【0351】 The server collects user work activity data from the business platform. Specifically, the server uses communication APIs to extract necessary data from email, chat messages, and project management tools. At this stage, programming languages ​​such as Python and Java are used to standardize the data. 【0352】 Next, the server analyzes the text information of the collected activity data using natural language processing tools (e.g., NLTK or spaCy). For sentiment analysis, it utilizes deep learning models (e.g., BERT or Hugging Face Transformers) to calculate sentiment scores. Finally, to perform skill assessment from the text information, it uses data analysis libraries (e.g., pandas, scikit-learn). 【0353】 Based on the analyzed skill assessment and emotion score, the server uses a generative AI model to generate job suggestions and specific advice for self-care. These generated suggestions are then sent to the user's device. 【0354】 The device presents suggestions to the user through an interactive user interface (e.g., React Native or Swift). The user can review the presented job suggestions and self-care advice and select actionable steps. 【0355】 As a concrete example, if the emotion engine determines that user A is experiencing excessive stress in a chat, the system will suggest a 15-minute relaxation yoga session to A. In this case, the generative AI model will use a prompt message like the following: 【0356】 "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0357】 In this way, the system can respond to the user's emotional state, enabling the user to take appropriate stress management measures. 【0358】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0359】 Step 1: 【0360】 The server collects user work activity data from the business platform via APIs. Input data includes emails, chat messages, and message logs from project management tools. The server converts this data into a standard format and stores it in a database. 【0361】 Step 2: 【0362】 The server uses natural language processing tools (such as NLTK and spaCy) to analyze collected text data and generate sentiment scores. The input is text information, and the output is a sentiment score indicating positive, negative, or neutral. The server extracts statistical features from the text and calculates the sentiment score using a sentiment analysis algorithm. 【0363】 Step 3: 【0364】 The server performs skill assessments using data analysis libraries (such as pandas and scikit-learn). The input data consists of standardized work activity data from the previous step, and the output is an evaluation score indicating the user's skills. The server calculates specific patterns and keywords in the data to generate skill evaluation metrics. 【0365】 Step 4: 【0366】 The server uses a generative AI model to generate job suggestions and self-care advice based on emotion scores and skill assessments. The input data consists of emotion scores and skill assessment scores, and the output is corresponding job suggestions and advice. The generative AI model generates responses using the prompt "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0367】 Step 5: 【0368】 The terminal presents the user with job suggestions and self-care advice received from the server. The input data is the suggestion information provided by the server, and the output is a display on the user interface. The terminal visualizes the suggestions, allowing the user to review and select from them. 【0369】 Step 6: 【0370】 Users review the suggestions displayed on their device and select jobs and self-care options that suit them. The input is the provided job suggestions and advice, while the output is the user's chosen actions. Users provide feedback on their selections via their device and send it to the server. This feedback is used to improve the system in the future. 【0371】 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. 【0372】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0373】 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. 【0374】 [Third Embodiment] 【0375】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0376】 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. 【0377】 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). 【0378】 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. 【0379】 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. 【0380】 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). 【0381】 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. 【0382】 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. 【0383】 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. 【0384】 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. 【0385】 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. 【0386】 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". 【0387】 This invention is a system that evaluates a user's skills and suggests appropriate job roles based on data obtained through the user's work activities. This system consists of three main elements: a server, a terminal, and the user. The role of each element is described below. 【0388】 The server is the main component that performs centralized data processing and analysis. First, the server automatically collects user activity data from various business tools and communication platforms. This data includes email exchanges, actions on project management tools, and chat logs. The collected data is formatted through a cleaning process to remove unnecessary information. Then, text analysis is performed using natural language processing techniques, and the user's skill level is calculated by a skill evaluation algorithm. This calculated skill score is recorded in a skill mapping database and integrated into the user's profile. The server also uses this data to perform calculations that enable the matching engine to determine the most suitable job for the user. 【0389】 The terminal acts as an interface with the user and is used to present evaluation results. The terminal displays skill evaluation results and job suggestions obtained from the server in a user-friendly format. Specifically, users see a detailed skill evaluation visualized on their dashboard, and new career suggestions appear as notifications. This allows users to objectively understand their own skill level and decide on their next career step. 【0390】 Through this system, users can receive regular skill assessments, review proposed job roles, and reassess their career direction. They can consider new job offers and make choices that align with their personal growth. In this way, users can objectively analyze their skills and aim for further career advancement. 【0391】 By using this system, users' skills are regularly evaluated through their daily work, and optimal job positions are suggested, enabling efficient talent allocation within the organization. As a result, overall company productivity can be improved, and individual users' career paths can be optimized. 【0392】 The following describes the processing flow. 【0393】 Step 1: 【0394】 The server automatically collects data related to users' work activities from various communication platforms and business tools. This includes emails, chat logs, and project management system update histories, and the data is collected in real time using APIs and web crawlers. 【0395】 Step 2: 【0396】 The server preprocesses the collected data. Unnecessary information is removed, and the text data is cleaned to prepare it for analysis. This process also includes correcting spelling errors and standardizing the formatting. 【0397】 Step 3: 【0398】 The server analyzes pre-processed text data. Using natural language processing techniques, it extracts keywords from the text and identifies the user's skills based on their activities. This analysis result is quantified by a skill evaluation algorithm, and a skill score is generated. 【0399】 Step 4: 【0400】 The server generates skill scores which are then stored in a skill mapping database. This database continuously updates and compares each user's skills with the skill requirements sought by the company. 【0401】 Step 5: 【0402】 The server uses information from the skills mapping database to perform a matching process that identifies suitable jobs and career opportunities for the user. It matches the user's skills with the organization's requirements in real time to determine the optimal job position. 【0403】 Step 6: 【0404】 The terminal displays evaluation results and job suggestions sent from the server to the user. Through the user interface, skill evaluations and specific career opportunities are displayed on a dashboard. 【0405】 Step 7: 【0406】 Users review the information presented and consider the suggested job roles and career opportunities. By providing feedback, data is accumulated to improve the system's accuracy and the appropriateness of its suggestions. 【0407】 (Example 1) 【0408】 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." 【0409】 In today's work environment, efficiently evaluating users' skills and proposing the most suitable job based on those evaluations is challenging. While companies need to provide appropriate jobs that match individual abilities and motivations, manual evaluation is time-consuming, labor-intensive, and often lacks objectivity. Therefore, there is a need for a system that uses users' work data to objectively and efficiently assess skills and propose the most suitable job. 【0410】 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. 【0411】 In this invention, the server includes means for collecting user behavior information from various sources and organizing the behavior information while eliminating duplication; means for analyzing the behavior information and performing a skills assessment based on natural language; and means for deriving and presenting suitable jobs using a generative AI model. This makes it possible to quickly and accurately suggest the most suitable job for each individual by continuously evaluating the user's skills. 【0412】 "User behavior information" refers to all data generated by users through their work activities, such as emails, project management logs, and chat logs. 【0413】 "Information sources" refer to various business tools and communication platforms used to obtain user activity information. 【0414】 "Organizing" refers to the process of removing duplicate or unnecessary parts from collected behavioral information and converting it into a format suitable for analysis. 【0415】 "Natural language-based skill assessment" refers to a method that uses natural language processing technology to analyze behavioral information and quantify and evaluate a user's skills. 【0416】 A "generative AI model" refers to an algorithm or tool that utilizes machine learning technology to recommend the most suitable job based on the user's skill information. 【0417】 "Suitable job" refers to the job title or position that best matches the user's skills and evaluation, as suggested based on the user's abilities and performance. 【0418】 "Job requirements" refer to the skills, experience, and knowledge required for a specific job, and serve as the basis for matching the user's skills. 【0419】 The embodiments for carrying out the present invention are shown below. 【0420】 This system is realized with servers, terminals, and users as its main components, each playing a specific role. 【0421】 The server plays a central role in aggregating, organizing, and analyzing user behavior information. The server collects digital data such as emails, project management tools, and chat logs from users' daily work. This could potentially utilize automated data collection scripts written in programming languages ​​like Python or Java. The collected data is then processed through a data cleansing process to remove redundancy and convert it into a format suitable for analysis. Next, natural language processing libraries such as NLTK and SpaCy are used to analyze the behavioral information and evaluate user skills. 【0422】 Based on the acquired skill assessment data, the server executes a generative AI model. For example, it uses TensorFlow or PyTorch to perform calculations to suggest the job best suited to the user's skills. This suggestion uses prompt statements. A concrete example of a prompt statement would be, "Assess the user's project management skills and suggest a suitable job." 【0423】 The terminal serves to present the user with skill assessments and job suggestions obtained from the server. The user interface can be built using libraries such as React or Angular, and it displays skill assessment results and notifications of suitable jobs in an easy-to-understand visual format. 【0424】 Users review the content presented through their devices, reassessing their skills and career plans. They can consider newly proposed job opportunities and choose roles that align with their personal growth. Through this process, users receive continuous skill evaluations and appropriate job suggestions, gaining valuable opportunities for career advancement. 【0425】 Thus, the present invention supports intelligent personnel allocation and enables the maximization of individual users' capabilities. 【0426】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0427】 Step 1: 【0428】 The server automatically collects user behavior information from various tools and platforms. Input data includes emails, project management tools, and chat logs. APIs and scraping techniques may be used to collect this data. The data is stored in raw form. 【0429】 Step 2: 【0430】 The server performs data cleansing on the collected raw data. This process involves filtering to remove duplicates and noise. The input is the raw data collected in step 1, and the output is the formatted, clean data. This clean data is processed to include only the information necessary for analysis. 【0431】 Step 3: 【0432】 The server analyzes the formatted data using natural language processing techniques. Specifically, it analyzes the specialized terminology and context contained in the text. The input is clean data, and the output is a score that quantifies the user's skill level. This process uses natural language processing libraries such as NLTK and SpaCy. 【0433】 Step 4: 【0434】 The server runs a generative AI model and uses the calculated skill score to suggest the most suitable job. The input consists of the skill score and the generative AI model prompt. The prompt used is "Evaluate the user's XX skills and suggest an appropriate job." The output is a list of suggested jobs, sorted in descending order of matching degree. 【0435】 Step 5: 【0436】 The terminal presents the user with skill assessment results and job suggestions sent from the server. Inputs are a list of suggested jobs and skill scores. The terminal uses a user interface based on React or Angular to visually display this information on a dashboard. Outputs are visualized assessment results and job suggestions for the user. 【0437】 Step 6: 【0438】 The user reviews the provided information and re-evaluates their career plan. Input consists of job suggestions and skill assessment results presented from the terminal. The user selects jobs of interest from the presented options and obtains further information. Output is the user's chosen next job or learning plan. The user's selection is fed back into the system and used to improve future suggestions. 【0439】 (Application Example 1) 【0440】 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." 【0441】 In smart cities, residents and staff are expected to maximize their abilities and participate in appropriate activities to improve the overall efficiency of the city. However, until now, there has been no system in place to effectively collect information on each individual's activities and propose appropriate activities based on that data. If appropriate activities are not proposed, individuals' abilities may not be fully utilized, potentially hindering the city's development and efficiency improvements. 【0442】 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. 【0443】 In this invention, the server includes means for collecting user activity information, means for evaluating the user's technical capabilities based on the activity information, means for proposing the most suitable activity to the user based on the technical capability evaluation, and means for providing notifications regarding the proposed activity to the user's portable electronic device. This enables residents and staff to quickly participate in activities best suited to their abilities, thereby improving the overall operational efficiency of the smart city. 【0444】 "Means for collecting user activity information" refers to technologies or methods for systematically collecting data on the actions and operations that individual users perform in their daily lives and work. 【0445】 "Means of evaluating technical capabilities" refers to technologies or methods that measure and judge the level of a user's skills and knowledge using numerical values ​​or indicators based on collected activity information. 【0446】 "Means of proposing optimal activities" refers to techniques or methods that, taking into account the evaluated technical abilities, indicate to users the most appropriate actions to take, such as jobs or volunteer activities. 【0447】 "Means of providing notifications" means a technology or method that sends visual or auditory alerts or messages to a user's mobile electronic device regarding a proposed activity. 【0448】 The system that realizes this invention mainly consists of a server, a terminal, and a user. 【0449】 The server plays a central role in receiving and processing user activity information. The hardware used is a data server equipped with a powerful processor and sufficient storage. Frameworks such as Python and Django are used for data processing. Specifically, the NLTK library is used for natural language processing to analyze user activity information and quantify technical skills. Based on this skill assessment, an activity matching engine using a generative AI model works to generate optimal activity suggestions. 【0450】 The terminal is the user's portable electronic device and functions as an interface to provide the user with notifications of suggested activities. An application is installed, providing visual notifications and reminders, allowing the user to easily choose their next action. Activity information is also transmitted from this terminal to the server. 【0451】 Users engage with the system on a daily basis and receive skill assessments and suggestions through system feedback. For example, a city hall might host a digital literacy improvement event, and citizens deemed to have high IT skills might receive invitations to participate. Users can check these notifications on their smartphones and decide whether or not to attend the event. 【0452】 To ensure the generative AI model functions correctly, enter the following as an example prompt: "Based on citizen activity data, perform a skills assessment and propose suitable volunteer activities. The assessment will use past activity history and event participation data, and will also take into account communication skills and IT skills." This prompt will cause the generative AI model to generate output that provides appropriate suggestions to the user. 【0453】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0454】 Step 1: 【0455】 Users input daily activity information into the system via their smartphones. This activity information is automatically collected by communication apps and scheduling tools. The input data is sent to the server in its original format. The output is then saved to the server in a unified format. 【0456】 Step 2: 【0457】 The server processes the received activity information through a data cleaning process. This process involves formatting the data and removing unnecessary information. The input is raw data, and the output is clean data that can be analyzed. Specifically, this involves imputing missing values ​​and removing duplicate data. 【0458】 Step 3: 【0459】 The server analyzes clean data using natural language processing techniques. It receives processed clean data as input, extracts text information, and quantifies the user's skill level. A skill score is generated as output and recorded in the database. During this process, the NLTK library is utilized for vocabulary analysis and syntax understanding. 【0460】 Step 4: 【0461】 The server uses the generated skill score to send a prompt to the AI ​​model, which then creates the optimal activity suggestion. The prompt is "Based on citizen activity data, please assess skills and suggest suitable volunteer activities," and the output is the suggested activity. 【0462】 Step 5: 【0463】 The server sends the generated proposal to the terminal and notifies the user. The notification is played back on the user's smartphone through the app. The output is a visual notification displaying detailed information about the proposed activity. The user reviews this notification and decides whether to participate in the activity. 【0464】 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. 【0465】 This invention is a system that evaluates skills based on user work activity data and combines them with an emotion engine to propose the most suitable job to the user. This system takes the user's emotional state into consideration to achieve more personalized job recommendations. The specific configuration and operation of the system are described below. 【0466】 The server collects data on the user's work activities from various platforms, including email, chat tools, and project management tools. The server extracts text information from this data and performs a standard skills assessment process. In parallel, the server activates an emotion engine to detect emotions from the user's text information. The emotion engine utilizes natural language processing to identify positive, negative, and neutral emotions, quantifying them and storing them as data. 【0467】 The terminal presents the user with skill assessments and emotion analysis results transmitted from the server. The terminal visualizes job suggestions based not only on skill scores but also on emotional states. This allows users to objectively understand their own skill level and emotional state, which can assist them in job selection. For example, if the emotion engine detects that a user is experiencing stress in a project, the terminal will display suggestions for less stressful jobs to that user. 【0468】 Users review the presented job offers and make career decisions. They contribute to system improvement by considering job offers based on their skills and emotions and providing feedback. This feedback is stored on the server and used to improve the accuracy of subsequent skill assessments and emotion recognition. 【0469】 Through this system, companies can make appropriate job assignments that take into account employees' emotional states, which is expected to improve efficiency and satisfaction in the workplace. Furthermore, users will be able to choose career paths that take their own emotions into consideration. 【0470】 The following describes the processing flow. 【0471】 Step 1: 【0472】 The server collects user work activity data from various platforms, including email, chat, and project management tools. The collected data is used for both skill assessment and sentiment recognition. 【0473】 Step 2: 【0474】 The server preprocesses the collected data. This involves cleaning the data and formatting the text to make it suitable for analysis. This processing is necessary for skill assessment and sentiment analysis. 【0475】 Step 3: 【0476】 The server analyzes text data and evaluates the user's skills. Using natural language processing techniques, it extracts important keywords from the text and quantifies the skills based on them. This skill score is stored in a skill mapping database. 【0477】 Step 4: 【0478】 In parallel, the server runs an emotion engine to recognize the user's emotions from text data. It identifies emotional states such as positive, negative, and neutral, and records them as a numerical emotion score. 【0479】 Step 5: 【0480】 The server integrates the acquired skill and sentiment scores and executes a matching process to suggest the most suitable job. Based on the user's skills and sentiment, it matches them with the organization's job requirements. 【0481】 Step 6: 【0482】 The terminal presents job suggestions from the server to the user. These suggestions, which consider not only skill assessments but also emotional states, are visualized and displayed on the user's dashboard. 【0483】 Step 7: 【0484】 Users review the presented suggestions and make choices regarding their careers. By providing feedback, data is accumulated that improves the accuracy of the system's analysis results and suggestions. 【0485】 (Example 2) 【0486】 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." 【0487】 Conventional systems only perform skill assessments based on data obtained from users' work activities, and lack job suggestions that take into account the user's emotional state. As a result, it is difficult to suggest appropriate jobs to individual users, and there is a challenge in improving user stress and satisfaction. 【0488】 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. 【0489】 In this invention, the server includes means for collecting information related to the user's work activities, means for extracting text information from the information and analyzing the user's emotional state using natural language processing, and means for analyzing the text information and evaluating the user's skills. This enables personalized job recommendations that take into account both the user's skill assessment and emotional state. 【0490】 "Information related to the user's work activities" refers to data about the user's daily work, including text and metadata obtained from emails, messages, task management, etc. 【0491】 "A method for extracting text information and analyzing a user's emotional state using natural language processing" refers to the process of extracting necessary text portions from collected data and classifying and quantifying the emotions within the text as positive, negative, or neutral using machine learning techniques. 【0492】 "Methods for evaluating user skills" refer to the process of applying generative AI models or machine learning algorithms based on extracted text information to quantify and express the level of a user's abilities and knowledge. 【0493】 "Personalized job recommendations" refer to suggestions that recommend the most suitable roles and tasks for each user, taking into account their individual skills and emotional state. 【0494】 "Means of collecting feedback" refers to an interface for users to input their opinions and impressions of the presented suggestions into the system, as well as a database for storing that information. 【0495】 "Methods for improving system accuracy" refers to the process of analyzing collected feedback, incorporating the results into algorithms for future skill evaluations and sentiment analysis, and thereby improving the quality of suggestions. 【0496】 This invention relates to a system that collects information related to a user's work activities and provides personalized job recommendations through skill evaluation and emotional state analysis. 【0497】 The server first collects information related to the user's work activities from various sources. Specifically, it retrieves text and metadata from email systems, messaging applications, and task management tools via APIs. Next, it formats the collected data using Python libraries and extracts the necessary text information. This utilizes data processing libraries such as pandas. After this, it analyzes the user's emotional state using natural language processing techniques on the extracted text information. A machine learning model using TensorFlow quantifies emotions such as positive, negative, and neutral. 【0498】 Subsequently, the server uses a generative AI model to evaluate the user's skills. In this process, machine learning libraries such as scikit-learn are utilized to extract keywords from the text and quantify the user's skills. 【0499】 The terminal retrieves skill evaluation scores and emotional scores generated by the server and displays the information to the user in a visually easy-to-understand format. Through an interactive dashboard using JavaScript, users can understand their own skills and emotional state and view job suggestions based on that. Specifically, if the terminal determines that an emotional state is due to stress, it will display less stressful jobs as suggestions. 【0500】 Users make career decisions based on job suggestions displayed on their devices and provide feedback. This feedback is collected by a server and used to improve the system's accuracy. User feedback allows the system to continuously learn, enabling it to provide more accurate suggestions in future skill assessments and sentiment analyses. 【0501】 For example, if a user frequently sends emails reporting on project progress, the server can detect emotions indicating stress from those emails, and the terminal will then suggest a support role rather than project management based on this. This system can gain more advanced insights by inputting prompts using a generative AI model. For instance, a prompt such as "Suggest a role that takes emotions into account, based on the user's work activity data" can be used to specify the scope of tasks the system should perform. 【0502】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0503】 Step 1: 【0504】 The server collects information related to the user's work activities. Specifically, it retrieves data from various sources, such as email systems, messaging applications, and task management tool APIs. The input at this stage is configuration data, including user account information and access permissions, and the output is raw work activity data. The server temporarily stores the retrieved data in preparation for subsequent processing. 【0505】 Step 2: 【0506】 The server extracts necessary text information from the collected data and performs preprocessing. Specifically, it uses a Python library (e.g., pandas) to format the data and remove unnecessary strings and HTML tags that would cause noise. The input to this process is raw business activity data, and the output is formatted text data. This formatted data is then used for subsequent sentiment analysis and skill assessment. 【0507】 Step 3: 【0508】 The server analyzes emotional states using formatted text data. Specifically, it uses natural language processing techniques and applies a TensorFlow sentiment analysis model to calculate positive, negative, and neutral sentiment scores. The input for this step is formatted text data, and the output is a numerical sentiment score. The server stores this sentiment score in a database. 【0509】 Step 4: 【0510】 The server uses a generative AI model to evaluate the user's skills. This model extracts keywords from text data and uses their frequency and relevance to quantify a skill score. At this stage, the input is formatted text data, and the output is a quantified skill score. The server records the skill score, along with the sentiment score, in a database. 【0511】 Step 5: 【0512】 The terminal retrieves skill and sentiment scores sent from the server and presents them visually to the user. Using JavaScript, the scores and suggestions are displayed in the interface as graphs and tables. The input for this step is the skill and sentiment scores, and the output is a visualized display on the user interface. This allows the terminal to present the user with less stressful job suggestions. 【0513】 Step 6: 【0514】 Users select career options based on job suggestions displayed on their terminals and provide feedback. Specifically, users evaluate the usefulness and suitability of the suggestions. Input is the job suggestions displayed on the terminal, and output is the user's feedback data sent to the server. This feedback is reflected in subsequent skill evaluations and sentiment analysis, contributing to system improvement. 【0515】 (Application Example 2) 【0516】 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." 【0517】 In today's workplace environment, there is a growing need to properly manage employees' emotions and stress levels. However, traditional job suggestion systems based on work data have the challenge of not considering the user's emotional state and therefore being unable to suggest the most suitable job. Furthermore, there has been no clear means of providing employees with specific information to understand their own emotional state and improve their behavior based on that understanding. 【0518】 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. 【0519】 In this invention, the server includes means for collecting user work activity data, means for analyzing the user's work activity data to generate an emotion score, and means for providing the user with job suggestions and self-care advice based on skill evaluation and emotion analysis. This enables the user to understand their own emotional state and select the most appropriate job and self-care actions accordingly. 【0520】 "User work activity data" refers to information related to all activities that a user performs in the course of their work, including communication records such as emails, chat messages, and project management tools. 【0521】 "Skill assessment" is a process of quantifying or qualitatively analyzing a user's abilities and expertise based on their work activity data. 【0522】 "Emotional state" refers to a psychological state identified from a user's text information and other relevant data, and includes emotional categories such as positive, negative, and neutral. 【0523】 "Self-care advice" refers to specific suggestions and action plans provided to promote psychological and physical health, based on the user's current emotional state and work environment. 【0524】 An "emotion score" is a numerical value calculated by analyzing a user's text information using a specific algorithm or model, and it is an indicator that quantitatively shows the user's emotional state. 【0525】 A "job suggestion" refers to a proposal for assigning the most suitable role or task to a user, based on their skill assessment and emotional state. 【0526】 This system provides users with optimal job recommendations and self-care advice based on skill assessments and sentiment analysis derived from their work activity data. The system's hardware and software configuration, along with its specific operation methods, are described below. 【0527】 The server collects user work activity data from the business platform. Specifically, the server uses communication APIs to extract necessary data from email, chat messages, and project management tools. At this stage, programming languages ​​such as Python and Java are used to standardize the data. 【0528】 Next, the server analyzes the text information of the collected activity data using natural language processing tools (e.g., NLTK or spaCy). For sentiment analysis, it utilizes deep learning models (e.g., BERT or Hugging Face Transformers) to calculate sentiment scores. Finally, to perform skill assessment from the text information, it uses data analysis libraries (e.g., pandas, scikit-learn). 【0529】 Based on the analyzed skill assessment and emotion score, the server uses a generative AI model to generate job suggestions and specific advice for self-care. These generated suggestions are then sent to the user's device. 【0530】 The device presents suggestions to the user through an interactive user interface (e.g., React Native or Swift). The user can review the presented job suggestions and self-care advice and select actionable steps. 【0531】 As a concrete example, if the emotion engine determines that user A is experiencing excessive stress in a chat, the system will suggest a 15-minute relaxation yoga session to A. In this case, the generative AI model will use a prompt message like the following: 【0532】 "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0533】 In this way, the system can respond to the user's emotional state, enabling the user to take appropriate stress management measures. 【0534】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0535】 Step 1: 【0536】 The server collects user work activity data from the business platform via APIs. Input data includes emails, chat messages, and message logs from project management tools. The server converts this data into a standard format and stores it in a database. 【0537】 Step 2: 【0538】 The server uses natural language processing tools (such as NLTK and spaCy) to analyze collected text data and generate sentiment scores. The input is text information, and the output is a sentiment score indicating positive, negative, or neutral. The server extracts statistical features from the text and calculates the sentiment score using a sentiment analysis algorithm. 【0539】 Step 3: 【0540】 The server performs skill assessments using data analysis libraries (such as pandas and scikit-learn). The input data consists of standardized work activity data from the previous step, and the output is an evaluation score indicating the user's skills. The server calculates specific patterns and keywords in the data to generate skill evaluation metrics. 【0541】 Step 4: 【0542】 The server uses a generative AI model to generate job suggestions and self-care advice based on emotion scores and skill assessments. The input data consists of emotion scores and skill assessment scores, and the output is corresponding job suggestions and advice. The generative AI model generates responses using the prompt "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0543】 Step 5: 【0544】 The terminal presents the user with job suggestions and self-care advice received from the server. The input data is the suggestion information provided by the server, and the output is a display on the user interface. The terminal visualizes the suggestions, allowing the user to review and select from them. 【0545】 Step 6: 【0546】 Users review the suggestions displayed on their device and select jobs and self-care options that suit them. The input is the provided job suggestions and advice, while the output is the user's chosen actions. Users provide feedback on their selections via their device and send it to the server. This feedback is used to improve the system in the future. 【0547】 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. 【0548】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0549】 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. 【0550】 [Fourth Embodiment] 【0551】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0552】 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. 【0553】 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). 【0554】 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. 【0555】 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. 【0556】 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). 【0557】 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. 【0558】 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. 【0559】 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. 【0560】 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. 【0561】 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. 【0562】 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. 【0563】 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". 【0564】 This invention is a system that evaluates a user's skills and suggests appropriate job roles based on data obtained through the user's work activities. This system consists of three main elements: a server, a terminal, and the user. The role of each element is described below. 【0565】 The server is the main component that performs centralized data processing and analysis. First, the server automatically collects user activity data from various business tools and communication platforms. This data includes email exchanges, actions on project management tools, and chat logs. The collected data is formatted through a cleaning process to remove unnecessary information. Then, text analysis is performed using natural language processing techniques, and the user's skill level is calculated by a skill evaluation algorithm. This calculated skill score is recorded in a skill mapping database and integrated into the user's profile. The server also uses this data to perform calculations that enable the matching engine to determine the most suitable job for the user. 【0566】 The terminal acts as an interface with the user and is used to present evaluation results. The terminal displays skill evaluation results and job suggestions obtained from the server in a user-friendly format. Specifically, users see a detailed skill evaluation visualized on their dashboard, and new career suggestions appear as notifications. This allows users to objectively understand their own skill level and decide on their next career step. 【0567】 Through this system, users can receive regular skill assessments, review proposed job roles, and reassess their career direction. They can consider new job offers and make choices that align with their personal growth. In this way, users can objectively analyze their skills and aim for further career advancement. 【0568】 By using this system, users' skills are regularly evaluated through their daily work, and optimal job positions are suggested, enabling efficient talent allocation within the organization. As a result, overall company productivity can be improved, and individual users' career paths can be optimized. 【0569】 The following describes the processing flow. 【0570】 Step 1: 【0571】 The server automatically collects data related to users' work activities from various communication platforms and business tools. This includes emails, chat logs, and project management system update histories, and the data is collected in real time using APIs and web crawlers. 【0572】 Step 2: 【0573】 The server preprocesses the collected data. Unnecessary information is removed, and the text data is cleaned to prepare it for analysis. This process also includes correcting spelling errors and standardizing the formatting. 【0574】 Step 3: 【0575】 The server analyzes pre-processed text data. Using natural language processing techniques, it extracts keywords from the text and identifies the user's skills based on their activities. This analysis result is quantified by a skill evaluation algorithm, and a skill score is generated. 【0576】 Step 4: 【0577】 The server generates skill scores which are then stored in a skill mapping database. This database continuously updates and compares each user's skills with the skill requirements sought by the company. 【0578】 Step 5: 【0579】 The server uses information from the skills mapping database to perform a matching process that identifies suitable jobs and career opportunities for the user. It matches the user's skills with the organization's requirements in real time to determine the optimal job position. 【0580】 Step 6: 【0581】 The terminal displays evaluation results and job suggestions sent from the server to the user. Through the user interface, skill evaluations and specific career opportunities are displayed on a dashboard. 【0582】 Step 7: 【0583】 Users review the information presented and consider the suggested job roles and career opportunities. By providing feedback, data is accumulated to improve the system's accuracy and the appropriateness of its suggestions. 【0584】 (Example 1) 【0585】 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". 【0586】 In today's work environment, efficiently evaluating users' skills and proposing the most suitable job based on those evaluations is challenging. While companies need to provide appropriate jobs that match individual abilities and motivations, manual evaluation is time-consuming, labor-intensive, and often lacks objectivity. Therefore, there is a need for a system that uses users' work data to objectively and efficiently assess skills and propose the most suitable job. 【0587】 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. 【0588】 In this invention, the server includes means for collecting user behavior information from various sources and organizing the behavior information while eliminating duplication; means for analyzing the behavior information and performing a skills assessment based on natural language; and means for deriving and presenting suitable jobs using a generative AI model. This makes it possible to quickly and accurately suggest the most suitable job for each individual by continuously evaluating the user's skills. 【0589】 "User behavior information" refers to all data generated by users through their work activities, such as emails, project management logs, and chat logs. 【0590】 "Information sources" refer to various business tools and communication platforms used to obtain user activity information. 【0591】 "Organizing" refers to the process of removing duplicate or unnecessary parts from collected behavioral information and converting it into a format suitable for analysis. 【0592】 "Natural language-based skill assessment" refers to a method that uses natural language processing technology to analyze behavioral information and quantify and evaluate a user's skills. 【0593】 A "generative AI model" refers to an algorithm or tool that utilizes machine learning technology to recommend the most suitable job based on the user's skill information. 【0594】 "Suitable job" refers to the job title or position that best matches the user's skills and evaluation, as suggested based on the user's abilities and performance. 【0595】 "Job requirements" refer to the skills, experience, and knowledge required for a specific job, and serve as the basis for matching the user's skills. 【0596】 The embodiments for carrying out the present invention are shown below. 【0597】 This system is realized with servers, terminals, and users as its main components, each playing a specific role. 【0598】 The server plays a central role in aggregating, organizing, and analyzing user behavior information. The server collects digital data such as emails, project management tools, and chat logs from users' daily work. This could potentially utilize automated data collection scripts written in programming languages ​​like Python or Java. The collected data is then processed through a data cleansing process to remove redundancy and convert it into a format suitable for analysis. Next, natural language processing libraries such as NLTK and SpaCy are used to analyze the behavioral information and evaluate user skills. 【0599】 Based on the acquired skill assessment data, the server executes a generative AI model. For example, it uses TensorFlow or PyTorch to perform calculations to suggest the job best suited to the user's skills. This suggestion uses prompt statements. A concrete example of a prompt statement would be, "Assess the user's project management skills and suggest a suitable job." 【0600】 The terminal serves to present the user with skill assessments and job suggestions obtained from the server. The user interface can be built using libraries such as React or Angular, and it displays skill assessment results and notifications of suitable jobs in an easy-to-understand visual format. 【0601】 Users review the content presented through their devices, reassessing their skills and career plans. They can consider newly proposed job opportunities and choose roles that align with their personal growth. Through this process, users receive continuous skill evaluations and appropriate job suggestions, gaining valuable opportunities for career advancement. 【0602】 Thus, the present invention supports intelligent personnel allocation and enables the maximization of individual users' capabilities. 【0603】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0604】 Step 1: 【0605】 The server automatically collects user behavior information from various tools and platforms. Input data includes emails, project management tools, and chat logs. APIs and scraping techniques may be used to collect this data. The data is stored in raw form. 【0606】 Step 2: 【0607】 The server performs data cleansing on the collected raw data. This process involves filtering to remove duplicates and noise. The input is the raw data collected in step 1, and the output is the formatted, clean data. This clean data is processed to include only the information necessary for analysis. 【0608】 Step 3: 【0609】 The server analyzes the formatted data using natural language processing techniques. Specifically, it analyzes the specialized terminology and context contained in the text. The input is clean data, and the output is a score that quantifies the user's skill level. This process uses natural language processing libraries such as NLTK and SpaCy. 【0610】 Step 4: 【0611】 The server runs a generative AI model and uses the calculated skill score to suggest the most suitable job. The input consists of the skill score and the generative AI model prompt. The prompt used is "Evaluate the user's XX skills and suggest an appropriate job." The output is a list of suggested jobs, sorted in descending order of matching degree. 【0612】 Step 5: 【0613】 The terminal presents the user with skill assessment results and job suggestions sent from the server. Inputs are a list of suggested jobs and skill scores. The terminal uses a user interface based on React or Angular to visually display this information on a dashboard. Outputs are visualized assessment results and job suggestions for the user. 【0614】 Step 6: 【0615】 The user reviews the provided information and re-evaluates their career plan. Input consists of job suggestions and skill assessment results presented from the terminal. The user selects jobs of interest from the presented options and obtains further information. Output is the user's chosen next job or learning plan. The user's selection is fed back into the system and used to improve future suggestions. 【0616】 (Application Example 1) 【0617】 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". 【0618】 In smart cities, residents and staff are expected to maximize their abilities and participate in appropriate activities to improve the overall efficiency of the city. However, until now, there has been no system in place to effectively collect information on each individual's activities and propose appropriate activities based on that data. If appropriate activities are not proposed, individuals' abilities may not be fully utilized, potentially hindering the city's development and efficiency improvements. 【0619】 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. 【0620】 In this invention, the server includes means for collecting user activity information, means for evaluating the user's technical capabilities based on the activity information, means for proposing the most suitable activity to the user based on the technical capability evaluation, and means for providing notifications regarding the proposed activity to the user's portable electronic device. This enables residents and staff to quickly participate in activities best suited to their abilities, thereby improving the overall operational efficiency of the smart city. 【0621】 "Means for collecting user activity information" refers to technologies or methods for systematically collecting data on the actions and operations that individual users perform in their daily lives and work. 【0622】 "Means of evaluating technical capabilities" refers to technologies or methods that measure and judge the level of a user's skills and knowledge using numerical values ​​or indicators based on collected activity information. 【0623】 "Means of proposing optimal activities" refers to techniques or methods that, taking into account the evaluated technical abilities, indicate to users the most appropriate actions to take, such as jobs or volunteer activities. 【0624】 "Means of providing notifications" means a technology or method that sends visual or auditory alerts or messages to a user's mobile electronic device regarding a proposed activity. 【0625】 The system that realizes this invention mainly consists of a server, a terminal, and a user. 【0626】 The server plays a central role in receiving and processing user activity information. The hardware used is a data server equipped with a powerful processor and sufficient storage. Frameworks such as Python and Django are used for data processing. Specifically, the NLTK library is used for natural language processing to analyze user activity information and quantify technical skills. Based on this skill assessment, an activity matching engine using a generative AI model works to generate optimal activity suggestions. 【0627】 The terminal is the user's portable electronic device and functions as an interface to provide the user with notifications of suggested activities. An application is installed, providing visual notifications and reminders, allowing the user to easily choose their next action. Activity information is also transmitted from this terminal to the server. 【0628】 Users engage with the system on a daily basis and receive skill assessments and suggestions through system feedback. For example, a city hall might host a digital literacy improvement event, and citizens deemed to have high IT skills might receive invitations to participate. Users can check these notifications on their smartphones and decide whether or not to attend the event. 【0629】 To ensure the generative AI model functions correctly, enter the following as an example prompt: "Based on citizen activity data, perform a skills assessment and propose suitable volunteer activities. The assessment will use past activity history and event participation data, and will also take into account communication skills and IT skills." This prompt will cause the generative AI model to generate output that provides appropriate suggestions to the user. 【0630】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0631】 Step 1: 【0632】 Users input daily activity information into the system via their smartphones. This activity information is automatically collected by communication apps and scheduling tools. The input data is sent to the server in its original format. The output is then saved to the server in a unified format. 【0633】 Step 2: 【0634】 The server processes the received activity information through a data cleaning process. This process involves formatting the data and removing unnecessary information. The input is raw data, and the output is clean data that can be analyzed. Specifically, this involves imputing missing values ​​and removing duplicate data. 【0635】 Step 3: 【0636】 The server analyzes clean data using natural language processing techniques. It receives processed clean data as input, extracts text information, and quantifies the user's skill level. A skill score is generated as output and recorded in the database. During this process, the NLTK library is utilized for vocabulary analysis and syntax understanding. 【0637】 Step 4: 【0638】 The server uses the generated skill score to send a prompt to the AI ​​model, which then creates the optimal activity suggestion. The prompt is "Based on citizen activity data, please assess skills and suggest suitable volunteer activities," and the output is the suggested activity. 【0639】 Step 5: 【0640】 The server sends the generated proposal to the terminal and notifies the user. The notification is played back on the user's smartphone through the app. The output is a visual notification displaying detailed information about the proposed activity. The user reviews this notification and decides whether to participate in the activity. 【0641】 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. 【0642】 This invention is a system that evaluates skills based on user work activity data and combines them with an emotion engine to propose the most suitable job to the user. This system takes the user's emotional state into consideration to achieve more personalized job recommendations. The specific configuration and operation of the system are described below. 【0643】 The server collects data on the user's work activities from various platforms, including email, chat tools, and project management tools. The server extracts text information from this data and performs a standard skills assessment process. In parallel, the server activates an emotion engine to detect emotions from the user's text information. The emotion engine utilizes natural language processing to identify positive, negative, and neutral emotions, quantifying them and storing them as data. 【0644】 The terminal presents the user with skill assessments and emotion analysis results transmitted from the server. The terminal visualizes job suggestions based not only on skill scores but also on emotional states. This allows users to objectively understand their own skill level and emotional state, which can assist them in job selection. For example, if the emotion engine detects that a user is experiencing stress in a project, the terminal will display suggestions for less stressful jobs to that user. 【0645】 Users review the presented job offers and make career decisions. They contribute to system improvement by considering job offers based on their skills and emotions and providing feedback. This feedback is stored on the server and used to improve the accuracy of subsequent skill assessments and emotion recognition. 【0646】 Through this system, companies can make appropriate job assignments that take into account employees' emotional states, which is expected to improve efficiency and satisfaction in the workplace. Furthermore, users will be able to choose career paths that take their own emotions into consideration. 【0647】 The following describes the processing flow. 【0648】 Step 1: 【0649】 The server collects user work activity data from various platforms, including email, chat, and project management tools. The collected data is used for both skill assessment and sentiment recognition. 【0650】 Step 2: 【0651】 The server preprocesses the collected data. This involves cleaning the data and formatting the text to make it suitable for analysis. This processing is necessary for skill assessment and sentiment analysis. 【0652】 Step 3: 【0653】 The server analyzes text data and evaluates the user's skills. Using natural language processing techniques, it extracts important keywords from the text and quantifies the skills based on them. This skill score is stored in a skill mapping database. 【0654】 Step 4: 【0655】 In parallel, the server runs an emotion engine to recognize the user's emotions from text data. It identifies emotional states such as positive, negative, and neutral, and records them as a numerical emotion score. 【0656】 Step 5: 【0657】 The server integrates the acquired skill and sentiment scores and executes a matching process to suggest the most suitable job. Based on the user's skills and sentiment, it matches them with the organization's job requirements. 【0658】 Step 6: 【0659】 The terminal presents job suggestions from the server to the user. These suggestions, which consider not only skill assessments but also emotional states, are visualized and displayed on the user's dashboard. 【0660】 Step 7: 【0661】 Users review the presented suggestions and make choices regarding their careers. By providing feedback, data is accumulated that improves the accuracy of the system's analysis results and suggestions. 【0662】 (Example 2) 【0663】 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". 【0664】 Conventional systems only perform skill assessments based on data obtained from users' work activities, and lack job suggestions that take into account the user's emotional state. As a result, it is difficult to suggest appropriate jobs to individual users, and there is a challenge in improving user stress and satisfaction. 【0665】 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. 【0666】 In this invention, the server includes means for collecting information related to the user's work activities, means for extracting text information from the information and analyzing the user's emotional state using natural language processing, and means for analyzing the text information and evaluating the user's skills. This enables personalized job recommendations that take into account both the user's skill assessment and emotional state. 【0667】 "Information related to the user's work activities" refers to data about the user's daily work, including text and metadata obtained from emails, messages, task management, etc. 【0668】 "A method for extracting text information and analyzing a user's emotional state using natural language processing" refers to the process of extracting necessary text portions from collected data and classifying and quantifying the emotions within the text as positive, negative, or neutral using machine learning techniques. 【0669】 "Methods for evaluating user skills" refer to the process of applying generative AI models or machine learning algorithms based on extracted text information to quantify and express the level of a user's abilities and knowledge. 【0670】 "Personalized job recommendations" refer to suggestions that recommend the most suitable roles and tasks for each user, taking into account their individual skills and emotional state. 【0671】 "Means of collecting feedback" refers to an interface for users to input their opinions and impressions of the presented suggestions into the system, as well as a database for storing that information. 【0672】 "Methods for improving system accuracy" refers to the process of analyzing collected feedback, incorporating the results into algorithms for future skill evaluations and sentiment analysis, and thereby improving the quality of suggestions. 【0673】 This invention relates to a system that collects information related to a user's work activities and provides personalized job recommendations through skill evaluation and emotional state analysis. 【0674】 The server first collects information related to the user's work activities from various sources. Specifically, it retrieves text and metadata from email systems, messaging applications, and task management tools via APIs. Next, it formats the collected data using Python libraries and extracts the necessary text information. This utilizes data processing libraries such as pandas. After this, it analyzes the user's emotional state using natural language processing techniques on the extracted text information. A machine learning model using TensorFlow quantifies emotions such as positive, negative, and neutral. 【0675】 Subsequently, the server uses a generative AI model to evaluate the user's skills. In this process, machine learning libraries such as scikit-learn are utilized to extract keywords from the text and quantify the user's skills. 【0676】 The terminal retrieves skill evaluation scores and emotional scores generated by the server and displays the information to the user in a visually easy-to-understand format. Through an interactive dashboard using JavaScript, users can understand their own skills and emotional state and view job suggestions based on that. Specifically, if the terminal determines that an emotional state is due to stress, it will display less stressful jobs as suggestions. 【0677】 Users make career decisions based on job suggestions displayed on their devices and provide feedback. This feedback is collected by a server and used to improve the system's accuracy. User feedback allows the system to continuously learn, enabling it to provide more accurate suggestions in future skill assessments and sentiment analyses. 【0678】 For example, if a user frequently sends emails reporting on project progress, the server can detect emotions indicating stress from those emails, and the terminal will then suggest a support role rather than project management based on this. This system can gain more advanced insights by inputting prompts using a generative AI model. For instance, a prompt such as "Suggest a role that takes emotions into account, based on the user's work activity data" can be used to specify the scope of tasks the system should perform. 【0679】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0680】 Step 1: 【0681】 The server collects information related to the user's work activities. Specifically, it retrieves data from various sources, such as email systems, messaging applications, and task management tool APIs. The input at this stage is configuration data, including user account information and access permissions, and the output is raw work activity data. The server temporarily stores the retrieved data in preparation for subsequent processing. 【0682】 Step 2: 【0683】 The server extracts necessary text information from the collected data and performs preprocessing. Specifically, it uses a Python library (e.g., pandas) to format the data and remove unnecessary strings and HTML tags that would cause noise. The input to this process is raw business activity data, and the output is formatted text data. This formatted data is then used for subsequent sentiment analysis and skill assessment. 【0684】 Step 3: 【0685】 The server analyzes emotional states using formatted text data. Specifically, it uses natural language processing techniques and applies a TensorFlow sentiment analysis model to calculate positive, negative, and neutral sentiment scores. The input for this step is formatted text data, and the output is a numerical sentiment score. The server stores this sentiment score in a database. 【0686】 Step 4: 【0687】 The server uses a generative AI model to evaluate the user's skills. This model extracts keywords from text data and uses their frequency and relevance to quantify a skill score. At this stage, the input is formatted text data, and the output is a quantified skill score. The server records the skill score, along with the sentiment score, in a database. 【0688】 Step 5: 【0689】 The terminal retrieves skill and sentiment scores sent from the server and presents them visually to the user. Using JavaScript, the scores and suggestions are displayed in the interface as graphs and tables. The input for this step is the skill and sentiment scores, and the output is a visualized display on the user interface. This allows the terminal to present the user with less stressful job suggestions. 【0690】 Step 6: 【0691】 Users select career options based on job suggestions displayed on their terminals and provide feedback. Specifically, users evaluate the usefulness and suitability of the suggestions. Input is the job suggestions displayed on the terminal, and output is the user's feedback data sent to the server. This feedback is reflected in subsequent skill evaluations and sentiment analysis, contributing to system improvement. 【0692】 (Application Example 2) 【0693】 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". 【0694】 In today's workplace environment, there is a growing need to properly manage employees' emotions and stress levels. However, traditional job suggestion systems based on work data have the challenge of not considering the user's emotional state and therefore being unable to suggest the most suitable job. Furthermore, there has been no clear means of providing employees with specific information to understand their own emotional state and improve their behavior based on that understanding. 【0695】 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. 【0696】 In this invention, the server includes means for collecting user work activity data, means for analyzing the user's work activity data to generate an emotion score, and means for providing the user with job suggestions and self-care advice based on skill evaluation and emotion analysis. This enables the user to understand their own emotional state and select the most appropriate job and self-care actions accordingly. 【0697】 "User work activity data" refers to information related to all activities that a user performs in the course of their work, including communication records such as emails, chat messages, and project management tools. 【0698】 "Skill assessment" is a process of quantifying or qualitatively analyzing a user's abilities and expertise based on their work activity data. 【0699】 "Emotional state" refers to a psychological state identified from a user's text information and other relevant data, and includes emotional categories such as positive, negative, and neutral. 【0700】 "Self-care advice" refers to specific suggestions and action plans provided to promote psychological and physical health, based on the user's current emotional state and work environment. 【0701】 An "emotion score" is a numerical value calculated by analyzing a user's text information using a specific algorithm or model, and it is an indicator that quantitatively shows the user's emotional state. 【0702】 A "job suggestion" refers to a proposal for assigning the most suitable role or task to a user, based on their skill assessment and emotional state. 【0703】 This system provides users with optimal job recommendations and self-care advice based on skill assessments and sentiment analysis derived from their work activity data. The system's hardware and software configuration, along with its specific operation methods, are described below. 【0704】 The server collects user work activity data from the business platform. Specifically, the server uses communication APIs to extract necessary data from email, chat messages, and project management tools. At this stage, programming languages ​​such as Python and Java are used to standardize the data. 【0705】 Next, the server analyzes the text information of the collected activity data using natural language processing tools (e.g., NLTK or spaCy). For sentiment analysis, it utilizes deep learning models (e.g., BERT or Hugging Face Transformers) to calculate sentiment scores. Finally, to perform skill assessment from the text information, it uses data analysis libraries (e.g., pandas, scikit-learn). 【0706】 Based on the analyzed skill assessment and emotion score, the server uses a generative AI model to generate job suggestions and specific advice for self-care. These generated suggestions are then sent to the user's device. 【0707】 The device presents suggestions to the user through an interactive user interface (e.g., React Native or Swift). The user can review the presented job suggestions and self-care advice and select actionable steps. 【0708】 As a concrete example, if the emotion engine determines that user A is experiencing excessive stress in a chat, the system will suggest a 15-minute relaxation yoga session to A. In this case, the generative AI model will use a prompt message like the following: 【0709】 "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0710】 In this way, the system can respond to the user's emotional state, enabling the user to take appropriate stress management measures. 【0711】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0712】 Step 1: 【0713】 The server collects user work activity data from the business platform via APIs. Input data includes emails, chat messages, and message logs from project management tools. The server converts this data into a standard format and stores it in a database. 【0714】 Step 2: 【0715】 The server uses natural language processing tools (such as NLTK and spaCy) to analyze collected text data and generate sentiment scores. The input is text information, and the output is a sentiment score indicating positive, negative, or neutral. The server extracts statistical features from the text and calculates the sentiment score using a sentiment analysis algorithm. 【0716】 Step 3: 【0717】 The server performs skill assessments using data analysis libraries (such as pandas and scikit-learn). The input data consists of standardized work activity data from the previous step, and the output is an evaluation score indicating the user's skills. The server calculates specific patterns and keywords in the data to generate skill evaluation metrics. 【0718】 Step 4: 【0719】 The server uses a generative AI model to generate job suggestions and self-care advice based on emotion scores and skill assessments. The input data consists of emotion scores and skill assessment scores, and the output is corresponding job suggestions and advice. The generative AI model generates responses using the prompt "The user's recent messages indicate stress and anxiety. Please suggest relaxing activities and services that can help manage stress." 【0720】 Step 5: 【0721】 The terminal presents the user with job suggestions and self-care advice received from the server. The input data is the suggestion information provided by the server, and the output is a display on the user interface. The terminal visualizes the suggestions, allowing the user to review and select from them. 【0722】 Step 6: 【0723】 Users review the suggestions displayed on their device and select jobs and self-care options that suit them. The input is the provided job suggestions and advice, while the output is the user's chosen actions. Users provide feedback on their selections via their device and send it to the server. This feedback is used to improve the system in the future. 【0724】 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. 【0725】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0726】 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. 【0727】 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. 【0728】 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. 【0729】 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. 【0730】 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. 【0731】 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. 【0732】 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." 【0733】 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. 【0734】 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. 【0735】 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. 【0736】 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. 【0737】 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. 【0738】 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. 【0739】 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. 【0740】 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. 【0741】 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. 【0742】 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. 【0743】 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. 【0744】 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 as being incorporated by reference. 【0745】 The following is further disclosed regarding the embodiments described above. 【0746】 (Claim 1) 【0747】 Means for collecting user activity data, 【0748】 A means for evaluating the user's skills based on the aforementioned activity data, 【0749】 A means of proposing the most suitable job to the user based on the aforementioned skill evaluation, 【0750】 A system that includes this. 【0751】 (Claim 2) 【0752】 The system according to claim 1, further comprising means for extracting text information from user activity data and analyzing the text information to generate a skill score. 【0753】 (Claim 3) 【0754】 The system according to claim 1, further comprising means for matching the user's skills with the organization's job requirements and selecting a job to propose based on the degree of suitability. 【0755】 "Example 1" 【0756】 (Claim 1) 【0757】 A means for collecting user behavior information from diverse sources and organizing the said behavior information while eliminating duplication, 【0758】 A means for analyzing the aforementioned behavioral information and performing a skills assessment based on natural language, 【0759】 A means of deriving and presenting suitable job roles using a generative AI model, 【0760】 A system that includes this. 【0761】 (Claim 2) 【0762】 The system according to claim 1, further comprising means for providing information to the user visually using the results of the aforementioned natural language-based skills assessment. 【0763】 (Claim 3) 【0764】 The system according to claim 1, further comprising means for matching the user's skills with the organization's job requirements using a generating AI model, selecting the most suitable job, and notifying the user. 【0765】 "Application Example 1" 【0766】 (Claim 1) 【0767】 Means for collecting user activity information, 【0768】 A means for evaluating the user's technical capabilities based on the aforementioned activity information, 【0769】 A means of proposing the optimal activity to the user based on the aforementioned technical capability evaluation, 【0770】 A means of providing the user with a notification regarding the proposed activity on their mobile electronic device, 【0771】 A system that includes this. 【0772】 (Claim 2) 【0773】 The system according to claim 1, further comprising means for extracting language data from user activity information and analyzing the language data to generate a capability score. 【0774】 (Claim 3) 【0775】 The system according to claim 1, further comprising means for matching the user's capabilities with the organization's activity requirements and selecting activities to propose based on their suitability. 【0776】 "Example 2 of combining an emotion engine" 【0777】 (Claim 1) 【0778】 Means for collecting information related to the user's business activities, 【0779】 A means for extracting text information from the aforementioned information and analyzing the user's emotional state using natural language processing, 【0780】 A means for analyzing the aforementioned text information to evaluate the user's skills, 【0781】 A means of suggesting the most suitable job to the user based on the aforementioned skill evaluation and emotional state, 【0782】 A means of displaying the proposed content and collecting feedback from users, 【0783】 A means to improve the accuracy of the system based on the aforementioned feedback, 【0784】 A system that includes this. 【0785】 (Claim 2) 【0786】 The system according to claim 1, further comprising means for extracting text information from user business activity data and quantifying the text information as sentiment data using natural language processing technology. 【0787】 (Claim 3) 【0788】 The system according to claim 1, further comprising means for making stress-aware job suggestions based on the user's emotional state and skill assessment. 【0789】 "Application example 2 when combining with an emotional engine" 【0790】 (Claim 1) 【0791】 Means for collecting user business activity data, 【0792】 A means for evaluating user skills based on the aforementioned business activity data, 【0793】 A means of proposing the most suitable role to the user based on the aforementioned skill assessment, 【0794】 A means for analyzing the emotional state of the user, 【0795】 A means for generating self-care advice for the user based on the aforementioned emotional state and skill evaluation, 【0796】 A system that includes this. 【0797】 (Claim 2) 【0798】 The system according to claim 1, further comprising means for extracting text information from user business activity data and analyzing the text information to generate a sentiment score. 【0799】 (Claim 3) 【0800】 The system according to claim 1, further comprising means for matching the user's emotional state with organizational requirements and selecting self-care actions to propose based on their suitability. [Explanation of Symbols] 【0801】 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

[Claim 1] Means for collecting user activity data, A means for evaluating the user's skills based on the aforementioned activity data, A means of proposing the most suitable job to the user based on the aforementioned skill evaluation, A system that includes this. [Claim 2] The system according to claim 1, further comprising means for extracting text information from user activity data and analyzing the text information to generate a skill score. [Claim 3] The system according to claim 1, further comprising means for matching the user's skills with the organization's job requirements and selecting a job to propose based on the degree of suitability.

Images