System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting email data of employees; means for collecting chat data of employees; means for collecting documents created by employees; means for analyzing the collected email data, chat data, and documents to extract keywords and phrases; means for classifying the extracted keywords and phrases to identify skill sets and work contents of employees; means for registering the identified skill sets and work contents in a database for each employee; and means for reflecting the registered skill sets and work contents in a visualization tool.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional human resource visualization tools required employees to manually input detailed information, which was often time-consuming. As a result, there was a tendency for accurate and up-to-date information to be lacking, leading to issues with potential skills being buried. In addition, information updates were often delayed, which could lead to inadequacies in current personnel allocation and development plans. Another issue was that it was difficult to properly grasp the contributions and workload imbalances of individual employees. [Means for solving the problem]

[0005] This invention solves these problems by utilizing generative AI, which collects employee email data, chat data, and documents created by employees, analyzes the collected data, and extracts keywords and phrases. Specifically, it automatically extracts employee job descriptions and skills from the collected data and registers the classified information in a database for each employee. Furthermore, the registered information is reflected in a visualization tool and displayed via a graphical interface, making it easy for employees and managers to view and use. It also has a function to receive feedback from employees and modify or add skill sets and job descriptions. This enables efficient management of accurate and up-to-date information on human resources, supporting optimal personnel allocation and development planning.

[0006] "Email data" refers to the content of emails sent and received by employees, and is information that is saved in text format.

[0007] "Chat data" refers to the logs of messages and conversations exchanged on chat tools used by employees, and is information that is saved in text format.

[0008] "Documents" refers to document files created or shared by employees, and are information that is extracted and saved in text format.

[0009] "Generative AI" refers to artificial intelligence technology that analyzes collected data and extracts keywords and phrases.

[0010] "Keywords and phrases" refer to important words and expressions extracted from collected data that indicate an employee's job duties and skills.

[0011] "Skill set" refers to the skills, knowledge, and experience possessed by an employee, and refers to the ability to perform specific tasks.

[0012] "Job content" refers to the specific tasks or types of projects that an employee is responsible for.

[0013] A "database" refers to a collection of information that systematically manages and stores each employee's skills and job duties.

[0014] A "visualization tool" is a system that visually displays employee skills and job duties, making them easy for managers and other employees to view and use.

[0015] "Feedback" refers to the opinions and correction requests employees provide to the system, and is information used to update skill sets and job descriptions.

[0016] "Graphical interface" refers to the design elements of the screens and dashboards that visualization tools use to visually display information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention relates to a system that collects data from email, chat tools, and document management systems that employees use daily, analyzes this data using generative AI, extracts the work content and skills of employees, and reflects this in a visualization tool.

[0039] 1. Data Collection

[0040] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[0041] 2. Data Analysis

[0042] Generative AI: The collected data is analyzed by generative AI. This analysis involves extracting keywords and key phrases using natural language processing techniques. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[0043] Server: The analysis results provided by the generative AI are categorized and organized by employee, allowing each employee's skill set and job duties to be identified and registered in a database.

[0044] 3. Information Registration

[0045] Server: The analyzed information is registered in a database for each employee. The database centrally manages employee skill sets and work history. For example, the database entry for "Yamada Taro" would register his skills such as "project management," "Python," and "data analysis."

[0046] 4. Visualization of information

[0047] Server: The information registered in the database is reflected in the visualization tool. The visualization tool uses a graphical interface and is designed to be easily viewable by other employees and managers. For example, information about Yamada Taro's skill set and the projects he is involved in is displayed in dashboard format.

[0048] 5. Feedback and Updates

[0049] Users (employees): Through the visualization tool, they can check their own skill sets and work history and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[0050] Server: The server receives feedback from employees and updates their skill sets and work history in the database. Based on this feedback, the information in the visualization tool is also updated in real time.

[0051] The specific processing flow of this system will be described later, but by combining these elements, it is possible to accurately grasp employee skills and job content, and support optimal personnel allocation and effective human resource development. For example, when selecting members for a new project, the visualization tool can be used to quickly identify the appropriate members. In addition, it is easy to understand workload imbalances and contribution levels, resulting in efficient team management.

[0052] The processing flow will be explained below.

[0053] Step 1: Collect data

[0054] Server: Regularly access and collect data from each employee's email server, chat tool, and document management system. This collection process is automated and includes a scheduling function to ensure the most up-to-date data is always available.

[0055] Specific behavior:

[0056] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[0057] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[0058] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[0059] Step 2: Analyze the data

[0060] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[0061] Specific behavior:

[0062] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[0063] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[0064] Calculate keyword relevance and identify important phrases.

[0065] Step 3: Categorize and organize information

[0066] Server: Organizes the keywords and phrases extracted by generative AI and classifies each employee's skill set and job duties, thereby clarifying each employee's profile.

[0067] Specific behavior:

[0068] The extracted keywords are then mapped to templates for updating employee skill sets.

[0069] Create categories to categorize information based on specific job duties and skills.

[0070] The classified information is registered in a database as a profile for each employee.

[0071] Step 4: Register your information

[0072] Server: Classified skill sets and work content are registered in a database for each employee. This database centrally manages employee skills and project history.

[0073] Specific behavior:

[0074] Create a profile for each employee and enter the necessary skills and work history.

[0075] The registered information is stored in a database so that updated information is reflected immediately.

[0076] Step 5: Reflecting on visualization tools

[0077] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to make it easy for employees and managers to view the information.

[0078] Specific behavior:

[0079] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[0080] Visually display each employee's skill set and job duties in the form of graphs and charts.

[0081] Step 6: Feedback and Updates

[0082] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[0083] Specific behavior:

[0084] Employees use visualization tools to check their skill sets and job duties.

[0085] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[0086] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[0087] Through this series of processing steps, the system can automatically grasp and visualize employee skills and job duties, enabling efficient human resource management and optimal allocation.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] Modern companies are required to accurately understand and appropriately manage their employees' skills and work content. Traditional methods require manual collection and classification of employee work content and skills, which requires significant time and effort, and can lead to inaccurate information or oversights. As a result, optimal personnel allocation and effective human resource development become difficult, reducing the efficiency of the entire company. To solve this problem, a system is needed that can automatically collect and analyze data, visualize it, and incorporate feedback in an integrated manner.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes: means for collecting email data from email servers used by employees; means for collecting chat data from chat tools used by employees; means for collecting documents from document management systems used by employees; means for analyzing the collected email data, chat data, and documents using a generative AI model based on natural language processing technology to extract keywords and important phrases; means for classifying the extracted keywords and important phrases by employee and identifying the employee's skill set and job content; means for registering the identified skill set and job content in a database for each employee; means for reflecting the registered skill set and job content in a visualization tool and displaying it in dashboard format using a graphical interface; and means for receiving feedback from employees and updating the skill set and job content in the database. This allows for an accurate understanding of employee skills and job content, enabling appropriate personnel placement and effective human resource development.

[0093] An "email server" is a server system that stores and manages data on e-mails sent and received by employees.

[0094] A "chat tool" is a communication tool that allows employees to exchange messages in real time.

[0095] A "document management system" is a system for storing, managing, and sharing document files created by employees.

[0096] "Natural language processing technology" is a technology that enables computers to understand, analyze, and respond to human language.

[0097] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to extract keywords and phrases from text data.

[0098] "Keywords" are specific words extracted as a result of data analysis that describe employees' skills and job duties.

[0099] "Key phrases" are specific phrases extracted as a result of data analysis that provide detailed information about an employee's skills and job duties.

[0100] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[0101] "Job Description" is a detailed description of the work or tasks performed by a particular employee.

[0102] A "database" is a system for centrally storing, managing, and searching information.

[0103] A "visualization tool" is software that visually displays information in a database, making it easier to view.

[0104] A "graphical interface" is a user interface that displays information in a visually easy-to-understand format.

[0105] "Dashboard format" is a format in which information is aggregated and displayed on a single screen using multiple widgets, graphs, and charts.

[0106] "Feedback" is any correction or additional information that an employee provides to the system.

[0107] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model, extracts employees' work content and skills, and reflects this information in a visualization tool.

[0108] System Overview

[0109] The entire system consists of the following hardware and software:

[0110] Server: Handles data collection, analysis, classification, registration, visualization, and feedback processing.

[0111] Email server: Provides employee email data.

[0112] Chat tool: Provides employee chat data.

[0113] Document Management System: Provides employee-generated documents.

[0114] Generative AI model: Analyzes collected data and extracts keywords and important phrases.

[0115] Visualization tool: Displays employee skills and job duties in a graphical interface.

[0116] Specific processing of the program

[0117] Data collection

[0118] Server: First, periodically collect email data sent and received by employees from the email server (for example, Gmail's IMAP server). To do this, Python's IMAP library is used to connect to the email server and retrieve unread emails. The email body is then converted to text format and saved in data storage.

[0119] Examples:

[0120] Example text: sales_report_email.txt

[0121] In addition, the server collects message logs from chat tools (e.g., Slack), obtains chat messages using the Slack API, converts them into text format, and stores them in the data storage.

[0122] Examples:

[0123] Example text: client_meeting_chat.txt

[0124] The server also periodically collects document files from a document management system (e.g., Google Drive), retrieves new documents using the Google Drive API, converts their contents into text format, and saves them in the data storage.

[0125] Examples:

[0126] Example text: project_plan_document.txt

[0127] Data analysis

[0128] Generative AI model: The collected data is analyzed by a generative AI model, which uses natural language processing techniques to extract keywords and key phrases to identify employee skills and job roles.

[0129] Example prompt sentence:

[0130] Please report on the progress of your new project.

[0131] Specific operation: Using a generative AI model such as BERT, keywords such as "project management," "data analysis," and "Python" are extracted from text data by executing the above prompt.

[0132] Classifying and organizing information

[0133] Server: Next, the server categorizes and organizes the analysis results provided by the generative AI model by employee, identifying each employee's skill set and job duties, and registering them in a database.

[0134] Example: Using a Python script, the analysis results are categorized by employee and the data is inserted into a database such as MySQL or PostgreSQL.

[0135] Information visualization

[0136] Server: The registered information is reflected in the visualization tool, which allows employees and managers to easily view the information. For example, skill sets and work history can be displayed in dashboard format.

[0137] Example: Using Power BI or Tableau dashboards to retrieve and visualize information from databases.

[0138] Feedback and Updates

[0139] Users (employees): They can review the visualized information and provide corrections or additional feedback as needed, for example, adding new skills.

[0140] Example: Use a feedback form in Power BI or Tableau to ask employees to add "JavaScript" skills.

[0141] Server: The server receives feedback from employees and updates the database, which in turn updates the information in the visualization tool in real time.

[0142] This system is a powerful tool for accurately understanding employee skills and job duties, ensuring appropriate personnel placement and effective personnel development.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1: Collect data

[0145] Servers: Collect data from email servers, chat tools, and document management systems.

[0146] Input: Email server (e.g. Gmail), chat tool (e.g. Slack), document management system (e.g. Google Drive)

[0147] Data processing: Convert data from each system into text format

[0148] Output: Collected email data, chat data, and document data (text format)

[0149] Specific operations: Uses Python's IMAP library to retrieve unread emails from an email server and save them as text files. Uses Slack API to retrieve messages from a specific channel and save them in text format. Uses Google Drive API to convert the contents of a new file to text and save it.

[0150] Step 2: Temporarily save data

[0151] Server: Stores collected data in temporary storage.

[0152] Input: Textual data collected in Step 1

[0153] Data processing: unifying data formats (text conversion, organization)

[0154] Output: Text data in a unified format

[0155] Specific operation: Execute a script that converts text data collected from various sources into a unified format and saves it in a specified directory.

[0156] Step 3: Data analysis

[0157] Generative AI: Analyzes collected text data and extracts keywords and important phrases.

[0158] Input: Text data in a unified format

[0159] Data processing: Keyword extraction and phrase analysis using natural language processing technology

[0160] Output: Extracted keywords and key phrases

[0161] How it works: Using a generative AI model such as BERT, it extracts keywords and phrases related to skills and job duties from collected text data. It then performs the analysis using prompt sentences.

[0162] Step 4: Organize and categorize information

[0163] Server: Classifies and organizes the analysis results by employee.

[0164] Input: Extracted keywords and key phrases

[0165] Data processing: Classify the analysis results by employee

[0166] Output: Skill sets and job duties categorized for each employee

[0167] Specific operation: The analysis results are processed using a Python script, the data is classified by employee, and inserted into the corresponding records in the database.

[0168] Step 5: Registering information in the database

[0169] Server: Registers information classified by employee in a database.

[0170] Input: Skill sets and job duties of each employee

[0171] Data processing: Registration process to database

[0172] Output: A database entry for each employee with their skill set and job description

[0173] Specific behavior: Generates an SQL query to insert each employee's skill set and job description into the database.

[0174] Step 6: Visualize the information

[0175] Server: Reflects the registered data in the visualization tool.

[0176] Input: Database entries that register the skill sets and job duties of each employee

[0177] Data processing: Retrieving information through database queries and preparing it for display in a graphical interface

[0178] Output: Visual information display in the form of a dashboard

[0179] What you will do: Use dashboard tools like Power BI and Tableau to query information from the database and update the dashboard.

[0180] Step 7: Gather feedback

[0181] Users (employees): Through visualization tools, they can check their own skill sets and work history, and provide corrections and additional feedback.

[0182] Input: Information that is modified or added on the dashboard

[0183] Data processing: Entering corrected and added information

[0184] Output: Corrections and additional information

[0185] What it does: Employees add new skills, such as "JavaScript," using feedback forms in Power BI and Tableau.

[0186] Step 8: Update the Database

[0187] Server: Receives feedback from employees and updates the database.

[0188] Input: Corrections and additional feedback information

[0189] Data processing: Database update processing

[0190] Output: Updated database entry

[0191] What it does: A Python script processes feedback collected from employees and updates database records using SQL queries.

[0192] Through these steps, the system can automatically collect, analyze, classify, register, visualize, and reflect feedback on employee skills and work content, enabling companies to achieve appropriate personnel allocation and effective human resource development, thereby improving business efficiency.

[0193] (Application example 1)

[0194] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0195] With conventional systems, it was difficult to grasp and effectively manage the skills and work content of each employee. Similarly, with robot work, there was a lack of means to visualize the tasks and skill sets that each robot excels at, and to make efficient work allocations and improvements. This resulted in insufficient resource management of both humans and robots, leading to issues with reduced overall work efficiency.

[0196] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0197] In this invention, the server includes means for collecting employee email data, means for collecting employee chat data, means for collecting documents created by employees, means for analyzing the collected email data, chat data, and documents and extracting keywords and phrases, means for classifying the extracted keywords and phrases and identifying employee skill sets and work content, means for registering the identified skill sets and work content in a database for each employee, means for reflecting the registered skill sets and work content in a visualization tool, means for collecting robot work logs and analyzing work content to extract skill sets, and means for visualizing the extracted robot skill sets. This enables accurate understanding of the work content and skill sets of employees and robots, enabling efficient resource management.

[0198] "Email data" refers to the content and metadata of emails sent and received by employees.

[0199] "Chat data" refers to the content and metadata of messages sent by employees using chat tools.

[0200] "Documents" refers to electronic documents such as text files, presentation materials, and spreadsheets created by employees.

[0201] "Keywords" refer to important words extracted from the email data, chat data, and documents being analyzed.

[0202] "Phrases" refer to important clauses or grammatical units extracted from the email data, chat data, and documents being analyzed.

[0203] A "skill set" refers to the collection of specific knowledge, skills, and abilities possessed by an employee or robot.

[0204] "Work content" refers to the specific tasks and scope of duties that an employee or robot performs on a daily basis.

[0205] A "database" is a collection of data organized according to a specific structure, where the skill sets and job descriptions of employees or robots are registered.

[0206] "Visualization tools" refer to software and applications that visually represent data.

[0207] "Server" refers to a back-end computer system that collects, analyzes, stores, and manages data.

[0208] "Work log" refers to the history and detailed records of the work performed by a robot.

[0209] A "robot" is a mechanical device that performs specific tasks automatically in a factory or other environment.

[0210] "Analysis" refers to the process of examining collected data in detail using statistical, machine learning, or other methods to extract meaningful information.

[0211] This invention relates to a system that collects data from employees' emails, chat tools, and document management systems, analyzes the data using a generative AI model, extracts the skills and work details of employees and robots, and reflects them in a visualization tool. This system makes it possible to optimally allocate personnel and robots, effectively develop personnel, and improve business efficiency.

[0212] Hardware and Software Configuration

[0213] The system includes the following hardware and software:

[0214] Server: Collects, analyzes, stores, and manages data. Examples include Amazon Web Services (AWS) and Microsoft Azure.

[0215] Cloud database: A database for centrally managing the skill sets and work details of employees and robots. Examples include Amazon RDS and Google Cloud SQL.

[0216] Visualization tools: Software for visually displaying data. Examples include Tableau and Power BI.

[0217] Generative AI models: AI models that analyze data and identify skill sets and job roles. Examples include OpenAI GPT-3 and Google BERT.

[0218] Data collection

[0219] The server collects data from email servers, chat tools, and document management systems used by employees on a daily basis, including obtaining email data using the SMTP protocol and obtaining chat messages and document files through APIs, such as the Gmail API and Slack API.

[0220] Data analysis

[0221] The server analyzes the collected data using a generative AI model, specifically using natural language processing (NLP) techniques to extract keywords and key phrases. During this analysis, skill sets and job descriptions are identified.

[0222] Data classification and registration

[0223] The analysis results are categorized by employee by the server and registered in a cloud database. This allows for centralized management of each employee's skill set and work history. Robot work logs are also collected in the same way, and the analysis results are registered in the database.

[0224] Visualization

[0225] The registered information is displayed in a graphical interface through a visualization tool. For example, employee skill sets and work history, as well as the work content and efficiency of robots, are displayed in dashboard format, allowing managers to understand the status of resources at a glance.

[0226] Feedback and Updates

[0227] Users (employees) can check their own skill sets and work history and provide corrections or additional feedback as needed. The server receives this feedback and updates the information in the database, which in turn updates the information in the visualization tool in real time.

[0228] Specific examples

[0229] For example, if Employee A's skill set includes the skills of "Project Management," "Python," and "Data Analysis," feedback can be provided to encourage the addition of the new skill of "JavaScript." Furthermore, it can be visualized that Robot A performs a lot of "Precision Machining" and "Inspection," and that it is achieving better results than other robots in "Precision Machining" in particular.

[0230] Prompt Sentence Examples

[0231] Specific examples of prompts to be input into a generative AI model include, "Please tell me the main skills of Employee A based on the chat messages he has sent over the past month," and "Please analyze the work logs of Robot A over the past month and tell me what tasks he is good at and how well he performed."

[0232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0233] Step 1:

[0234] The server collects employee email data, chat data, and documents. This includes periodically retrieving email data from an email server using the SMTP protocol and collecting data from chat tools (e.g., Slack) and document management systems (e.g., Google Drive) via APIs. The input data is email, chat messages, and document files, and the output is saved in data storage after being converted to text format.

[0235] Step 2:

[0236] The server processes the collected data and analyzes it using a generative AI model. This analysis includes extracting keywords and phrases using natural language processing (NLP) techniques. For example, a Python script is used to invoke a generative model (e.g., GPT-3) to extract important words and phrases within the text. The input data is the text data collected and saved in step 1, and the output is the analyzed keywords and phrases.

[0237] Step 3:

[0238] The server categorizes the analysis results provided by the generative AI model for each employee and registers their skill sets and job descriptions in a database. During this process, the data is organized into categories based on each employee's email address and chat ID and saved in a cloud database. The input data is the analysis results obtained in step 2, and the output is each employee's skill set and job description.

[0239] Step 4:

[0240] The server then reflects the registered skill sets and work details in a visualization tool. This involves using a graphical interface to display each employee's skill set and work history in dashboard format. For example, data visualization is performed using Tableau or Power BI. The input data are the skill sets and work details registered in the database, and the output is a visually displayed dashboard.

[0241] Step 5:

[0242] Users (employees) can check their own skill sets and work history through the visualization tool and provide corrections or additional feedback as needed. The input data is the feedback from the users, and the output is the updated skill sets and work content.

[0243] Step 6:

[0244] The server receives feedback from employees and updates their skill sets and work history in the database. This involves modifying the database in real time and keeping the information in the visualization tool up to date. The input data is the feedback provided in step 5, and the output is the updated database and visualization tool.

[0245] Step 7:

[0246] The server collects and analyzes the robot's work logs to extract the robot's skill set and work content. This involves acquiring data from IoT sensors and logging systems used in the factory. The input data is the robot's work logs, and the output is the analyzed robot's skill set.

[0247] Step 8:

[0248] The server classifies the analysis results by robot and registers the robot's skill set and work content in a database. The input data are the analysis results obtained in step 7, and the output is the skill set and work content for each robot.

[0249] Step 9:

[0250] The server reflects the registered robot's skill set in the visualization tool and displays it graphically. This allows managers to understand at a glance the robot's specialties and performance. The input data is the robot's skill set registered in the database, and the output is a visual dashboard.

[0251] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0252] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this information in a visualization tool.

[0253] 1. Data Collection

[0254] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[0255] 2. Data Analysis

[0256] Generative AI: Collected data is analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases, such as skills and job descriptions like "project management," "data analysis," and "Python."

[0257] Emotion engine: Furthermore, the emotion engine recognizes the user's emotions from the analyzed data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[0258] Server: The analysis results provided by the generative AI and emotion engine are categorized and organized by employee, allowing each employee's skill set, job duties, and emotional state to be identified and registered in a database.

[0259] 3. Information Registration

[0260] Server: The analyzed information is registered in a database for each employee. The database centrally manages employees' skill sets, work history, and emotional states. For example, the database entry for "Yamada Taro" will record his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[0261] 4. Visualization of information

[0262] Server: The information in the database is reflected in the visualization tool. The visualization tool uses a graphical interface to make it easy for other employees and managers to view the information. For example, Yamada Taro's skill set, job duties, and current emotional state (stress level, etc.) are displayed in dashboard format.

[0263] 5. Feedback and Updates

[0264] Users (employees): Through visualization tools, they can check their own skill sets, work history, and emotional state, and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[0265] Server: The server receives feedback from employees and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[0266] 6. Utilizing Emotional Data

[0267] Server: Evaluates workload and stress levels based on emotional data obtained from users. Based on this evaluation, the health and work status of employees is understood, and appropriate feedback and suggestions for improvement are provided.

[0268] Specific working example:

[0269] For example, if emotional data indicates that Yamada Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[0270] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[0271] Through this series of processes, the system automatically grasps and visualizes employee skills, work content, and emotional state, making it possible to improve the efficiency of human resource management, optimize staff allocation, and support employee health management, which is expected to improve productivity and employee satisfaction across the company.

[0272] The processing flow will be explained below.

[0273] Step 1: Collect data

[0274] Server: Regularly accesses each employee's email server, chat tool, and document management system to collect data. This includes the ability to automatically retrieve required data using APIs.

[0275] Specific behavior:

[0276] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[0277] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[0278] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[0279] Step 2: Analyze the data

[0280] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[0281] Specific behavior:

[0282] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[0283] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[0284] Calculate keyword relevance and identify important phrases.

[0285] Emotion Engine: Analyzes the collected data to recognize the user's emotions. This process involves analyzing, for example, the tone and style of writing.

[0286] Specific behavior:

[0287] Classify emotions such as positive, negative, and neutral from the content of emails and chats.

[0288] For example, phrases such as "tired" and "troubled" are recognized as negative emotions.

[0289] The recognized emotional data is organized and stored as the employee's emotional state.

[0290] Step 3: Categorize and organize information

[0291] Server: Based on the analysis results provided by the generative AI and emotion engine, classifies each employee's skill set, job content, and emotional state.

[0292] Specific behavior:

[0293] Extracted keywords and phrases are mapped to templates based on skills and job duties.

[0294] Classifying sentiment data into categories such as positive, negative, and neutral.

[0295] The classified information is registered in a database as a profile for each employee.

[0296] Step 4: Register your information

[0297] Server: Registers classified skill sets, job duties, and emotional states in a database for each employee.

[0298] Specific behavior:

[0299] Create a profile for each employee and enter the necessary skills, work history, and emotional state.

[0300] The registered information is stored in a database so that updated information is reflected immediately.

[0301] Step 5: Reflecting on visualization tools

[0302] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to make it easy for employees and managers to view the information.

[0303] Specific behavior:

[0304] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[0305] Visually display each employee's skill set, job duties, and emotional state in graphs and charts.

[0306] Step 6: Feedback and Updates

[0307] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[0308] Specific behavior:

[0309] Employees use visualization tools to identify their skill sets, job duties, and emotional state.

[0310] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[0311] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[0312] Step 7: Use emotion data

[0313] Server: Evaluates workload and stress levels based on emotional data obtained from users. The results of this evaluation are used to improve employee health and work efficiency.

[0314] Specific behavior:

[0315] Emotional data is used to assess employee stress levels and create reports to help balance work.

[0316] If high stress levels are detected, the system will automatically send notifications suggesting appropriate rest or task reallocation.

[0317] Visualize the emotional state of the entire team and help managers adjust workload imbalances appropriately.

[0318] This series of processing steps automatically grasps and visualizes employee skills, work content, and emotional state, enabling efficient human resource management, optimal allocation, and employee health management. As a result, improvements in productivity and employee satisfaction across the entire company can be expected.

[0319] Example 2

[0320] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0321] Conventional employee management systems struggled to efficiently collect and analyze a wide range of data, including email, chat, and documents, and to centrally understand employees' skill sets, work content, and emotional state. This made it difficult to properly evaluate employees' workloads and stress levels and provide optimal feedback and suggestions for improvement. Furthermore, there was a lack of visualization methods for displaying collected data in an easy-to-understand manner, making it difficult for employees and managers to easily check the information. Furthermore, few systems allowed for dynamic updating of data based on employee feedback.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0323] In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for preprocessing the collected email data, chat data, and documents; means including a generation AI for analyzing the preprocessed data and extracting keywords and phrases; means including an emotion engine for recognizing employee emotions from the analyzed data; means for classifying the extracted keywords, phrases, and emotional states and identifying employee skill sets, job content, and emotional states; means for registering the identified skill sets, job content, and emotional states in a database for each employee; and means for reflecting the registered skill sets, job content, and emotional states in a visualization tool. This enables a unified understanding of employee skills, job content, and emotional states and a visually easy-to-understand display. Furthermore, the database can be dynamically updated based on feedback from employees, enabling business management and improvement proposals based on the latest information.

[0324] "Email data" refers to digital information including the content, metadata, and attachments of emails sent and received by employees.

[0325] "Chat data" refers to digital information including messages exchanged on chat tools used by employees and their metadata (such as time of sending, sender, recipient, and chat room information).

[0326] "Documents" are digital files such as text files, spreadsheets, presentations, and PDF documents that employees create or manage.

[0327] "Preprocessing" refers to processes such as data cleansing, format conversion, and normalization to convert collected raw data into a format that is easy to analyze.

[0328] "Generative AI" is an artificial intelligence system that uses natural language processing technology to automatically extract keywords and important phrases from text data.

[0329] The "Emotion Engine" is a machine learning-based system for analyzing and classifying employees' emotional states (e.g., stress levels, satisfaction, etc.) from text data.

[0330] A "skill set" is information that lists the work-related skills, knowledge, and techniques possessed by a particular employee.

[0331] "Job content" refers to information about the tasks and projects that employees perform on a daily basis, as well as the general duties they are responsible for.

[0332] "Emotional state" is information that indicates an employee's psychological state and emotional movements (for example, stress, satisfaction, fatigue, etc.).

[0333] The "database" is a digital data storage system that collects, analyzes, and organizes each employee's skill set, job content, and emotional state for centralized management.

[0334] A "visualization tool" is a graphical interface that visually displays information in a database, allowing employees and managers to easily view and analyze it.

[0335] "Feedback" is information that employees provide to the system to request modifications or additions to their skill sets or job duties.

[0336] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this in a visualization tool.

[0337] Data collection and preprocessing

[0338] Server: First, the server collects data from email servers (e.g., Gmail), chat tools (e.g., Slack), and document management systems (e.g., Google Drive) used by employees. This data is periodically obtained using APIs or protocols. It collects sent and received email data from email servers, message logs from chat tools, and created document files from document management systems. The collected data is then converted into text format and stored in data storage.

[0339] Data analysis

[0340] Preprocessing: The server performs preprocessing to convert the collected data into a format suitable for analysis, such as removing boilerplate text, removing HTML tags, and standardizing dates and timestamps.

[0341] Generative AI: The pre-processed data is then analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases from the text data. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[0342] Emotion engine: The emotion engine recognizes emotional states from analyzed text data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[0343] Organizing and registering information

[0344] Server: The server categorizes and organizes the analysis results provided by the generative AI and emotion engine for each employee. This identifies each employee's skill set, job description, and emotional state, and registers them in the database. For example, the database entry for "Employee Taro" includes his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[0345] Information visualization

[0346] Server: The server uses the information in the database to display the visualization tool. The visualization tool uses a graphical interface and is designed to make it easy for other employees and managers to view information. For example, Taro's skill set, job description, and current emotional state are displayed in dashboard format.

[0347] Feedback and Updates

[0348] User (employee): Through the visualization tool, users can check their own skill sets, work history, and emotional state, and provide feedback as needed. For example, they can provide feedback to Taro to add the new skill "JavaScript."

[0349] Server: The server receives feedback from users and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[0350] Utilizing Emotional Data

[0351] Server: The server evaluates the workload and stress level based on the emotional data obtained from the user. Based on this evaluation, the server grasps the employee's health and work situation and provides appropriate feedback and suggestions for improvement.

[0352] Specific working example:

[0353] If emotional data indicates that Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[0354] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[0355] Example of an input prompt for a generative AI model:

[0356] "Extract employee skill sets and job descriptions from the following text data, and analyze their emotional state. The text data is as follows: 'Today we had a project management meeting. We also performed data analysis using Python. It seems like they're a little stressed.'"

[0357] As described above, the present invention makes it possible to grasp employee skills, work content, and emotional state in a unified manner and display them in a visually easy-to-understand manner. Furthermore, by receiving feedback from employees and dynamically updating the database, work management and improvement proposals can be made based on the latest information.

[0358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0359] Step 1: Data collection

[0360] Servers: Periodically collect data from email servers, chat tools, and document management systems used by employees. Specific actions include:

[0361] Email Data Collection: Uses the Gmail API to retrieve inbound and outbound email data from employee mailboxes.

[0362] Input: Email data obtained from the Gmail API

[0363] Output: Acquired email data (sending / receiving history, email body, attachments, etc.)

[0364] Chat data collection: Use the Slack API to obtain message logs between employees.

[0365] Input: Chat messages retrieved through the Slack API

[0366] Output: Acquired chat data (message content, chat room information, timestamp, etc.)

[0367] Document data collection: Use the Google Drive API to obtain document files created by employees.

[0368] Input: Document data retrieved from the Google Drive API

[0369] Output: Retrieved document data (file name, file contents, metadata, etc.)

[0370] Step 2: Data Preprocessing

[0371] Server: Converts collected data into a format suitable for analysis. Specific operations include:

[0372] Text normalization: Removes HTML tags and special characters from collected text data to make the text clean.

[0373] Input: Collected raw data (email data, chat data, document data)

[0374] Output: Clean text data

[0375] Cleaning: Removes boilerplate and unnecessary header information, producing pure text information for analysis.

[0376] Input: clean text data

[0377] Output: Text data with unnecessary information removed

[0378] Format conversion: Convert dates and timestamps into a unified format.

[0379] Input: Text data with unnecessary information removed

[0380] Output: Text data converted into an easy-to-parse format

[0381] Step 3: Data analysis

[0382] Generative AI and Emotion Engine: Analyzes pre-processed data to extract employee skills and emotional states. Specific actions include:

[0383] Keyword extraction: Generative AI uses natural language processing techniques to extract keywords and key phrases from text data.

[0384] Input: Text data converted into an easy-to-parse format

[0385] Output: Extracted keywords and significant phrases

[0386] Sentiment analysis: The emotion engine analyzes employee emotions from text data and identifies emotional states such as "high stress" or "satisfied."

[0387] Input: Text data converted into an easy-to-parse format

[0388] Output: Parsed emotional state information

[0389] Step 4: Organize and register information

[0390] Server: Classifies and organizes the analysis results provided by the generative AI and emotion engine for each employee. Specific operations include:

[0391] Data classification: Based on each employee's information (e.g., "Employee Taro"), associate their skill set, job duties, and emotional state.

[0392] Input: extracted keywords and key phrases, parsed emotional state information

[0393] Output: Organized information for each employee

[0394] Database registration: Classified information is registered in a database for each employee.

[0395] Input: Organized information for each employee

[0396] Output: Skill sets, job descriptions, and emotional states registered in the database

[0397] Step 5: Visualize the information

[0398] Server: Reflects the information in the database to the visualization tool. This includes the following specific operations:

[0399] Extraction and display of information: The registered information is reflected in visualization tools such as dashboards and displayed visually.

[0400] Input: Information registered in the database

[0401] Output: Visualized data (e.g., dashboard display)

[0402] Step 6: Feedback and Updates

[0403] User (employee) and server: User provides feedback and server updates the database. Specific actions include:

[0404] User feedback: Users use the visualization tool to input corrections and additions to their information.

[0405] Input: User feedback information (e.g. "Add JavaScript skills")

[0406] Output: Feedback data

[0407] Database Update: The server receives the feedback data and updates the database in real time.

[0408] Input: Feedback data

[0409] Output: Updated database information

[0410] Step 7: Leverage sentiment data

[0411] Server: Based on the analyzed emotional data, it evaluates workload and stress levels and suggests appropriate actions. Specific actions include:

[0412] Emotional assessment: Analyze collected emotional data to assess workload and stress levels.

[0413] Input: Parsed emotion data

[0414] Output: Evaluation results (stress level and workload status)

[0415] Action proposal: Based on the evaluation results, we propose appropriate feedback and task redistribution to employees.

[0416] Input: Evaluation result

[0417] Output: Suggested feedback and / or actions

[0418] Through these steps, the system will be able to grasp and visualize employee skills, work content, and emotional state in a unified manner, and dynamically update them based on feedback. This process is expected to improve productivity and employee satisfaction across the company.

[0419] (Application example 2)

[0420] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0421] There is a need for a system that can grasp the work content and skill sets of robots working in factories in real time, and manage the appropriate work allocation and health status. Conventional methods require humans to check the robot's work status and abnormal conditions one by one, which reduces work efficiency and makes it difficult to respond to abnormalities in real time. In addition, there is an issue that accurate management is not possible due to insufficient detailed analysis and visualization of the robot's work content.

[0422] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for analyzing the collected email data, chat data, and documents to extract important keywords and phrases; means for classifying the extracted keywords and phrases and identifying the employee's ability set and job content; means for registering the identified ability set and job content in a database for each employee; and means for reflecting the registered ability set, job content, and emotional state in a visualization tool and displaying it via a head-mounted display. This makes it possible to monitor and manage the work content and abnormal conditions of robots in a factory in real time, thereby improving work efficiency and enabling appropriate abnormality responses.

[0423] A head-mounted display is a device used to display images in front of the wearer's eyes, allowing the user to obtain visual information in real time.

[0424] Emotional state refers to the mental state of employees and robots, such as stress levels and satisfaction, analyzed from collected data.

[0425] A visualization tool is a tool that displays data using a graphical interface to make information intuitively easy to understand.

[0426] A capability set refers to the skills and expertise possessed by employees or robots, as well as the specific work tasks that are extracted through analysis.

[0427] A database is a data storage system that stores collected data in an organized manner and manages it so that it can be used for later retrieval and analysis.

[0428] Keywords and phrases are important words and sentences that indicate specific skills or job content and are extracted by generative AI from collected data.

[0429] An employee is someone who is part of a company or organization that uses this system and who uses email, chat tools, and document management systems for daily work and communication.

[0430] This invention is a system that can grasp the work content, skill sets, and emotional states of robots working in factories in real time, and then allocate tasks appropriately and manage their health. This system collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model and emotion engine, and then reflects it in a visualization tool. Managers can also access information in real time using a head-mounted display.

[0431] Hardware configuration

[0432] The server includes a means for periodically collecting data from the email server, chat tool, and document management system, and also includes data storage for saving the collected data.

[0433] The head-mounted display is a device that displays images in front of the manager's eyes, allowing the manager to visually check the robot's work content and emotional state in real time.

[0434] Software configuration

[0435] Generative AI models and sentiment engines are used to analyze collected data and extract key keywords, phrases, and emotional states. Specifically, they leverage natural language processing techniques to identify skill sets and job roles, and perform sentiment analysis.

[0436] A visualization tool is software that displays analyzed data in a graphical interface, making it easier for managers to intuitively understand the information.

[0437] Data collection and analysis

[0438] The server first collects data from email servers, chat tools, and document management systems. This data is converted into text format and stored in data storage. The generative AI model then uses natural language processing technology to extract important keywords and phrases, and the emotion engine recognizes emotional states from the analyzed data. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," as well as emotional states such as "high stress." The results of this analysis are classified for each employee and robot and registered in a database.

[0439] Data visualization and feedback

[0440] The registered data is displayed in a graphical interface using a visualization tool, and managers can check the information in real time via a head-mounted display. This allows managers to immediately understand the robot's work content and emotional state and give instructions on work allocation or rest as necessary. For example, if the robot is in a state of high stress, the system will send a notification and suggest appropriate rest or task reallocation.

[0441] Specific examples

[0442] By using this system, it is possible to improve the work efficiency of robots in factories. For example, by inputting prompt statements such as "Leader, how is today's work progress? Please analyze the skill set and emotional state based on chat history, email content, and document content, visualize them, and report them to us. For example, we would like to obtain information such as, 'Robot operation skills have improved, but stress levels are rising,'" into the generative AI model, detailed analysis results can be obtained. This enables appropriate work management and efficiency in real time.

[0443] In summary, the present invention realizes improved work efficiency and health management by understanding the work content and emotional state of robots in a factory in real time and taking appropriate measures.

[0444] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0445] Step 1:

[0446] The data collection server periodically collects data from email servers, chat tools, and document management systems. It handles raw data collected from each system's API as input. This data is converted to text format and stored in data storage. For example, it collects emails, chat logs, and document files from the past 24 hours at 9:00 a.m. every day.

[0447] Step 2:

[0448] The data analysis server analyzes the collected email data, chat data, and documents using a generative AI model and emotion engine. The text data collected in step 1 is used as input. The generative AI model uses natural language processing techniques to extract keywords and important phrases, and the emotion engine analyzes emotional states. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," and emotional states such as "high stress."

[0449] Step 3:

[0450] Data Classification and Registration The server classifies the data based on the analysis results obtained from the generative AI model and emotion engine, and registers it in a database for each employee and robot. The analysis results are used as input. The skill set, job content, and emotional state of each employee and robot are stored in the database as output. For example, information such as "Employee A" having high "robot operation skills" and low "stress level" is registered in the database.

[0451] Step 4:

[0452] Data visualization: The server generates a graphical interface using a visualization tool based on the information in the database. As input, it uses the skill sets and emotional states registered in the database. As output, it generates visual information that is displayed in real time through a head-mounted display. For example, a manager can wear the head-mounted display and check employee A's "robot operation skills" and "stress level."

[0453] Step 5:

[0454] Real-time feedback The user (manager) checks the visualized information and provides feedback as necessary. As input, the user checks the information displayed on the head-mounted display. As output, the feedback content is sent to the server and the database is updated. For example, if employee A is feeling stressed, the manager can reallocate tasks or instruct him or her to take a break.

[0455] Step 6:

[0456] Reflecting Feedback The server receives feedback from the user and modifies or adds information to the database. As input, it uses the feedback information from the administrator. As output, the updated skill set and emotional state are reflected in the database. For example, "JavaScript" is added as a new skill set, and the stress level is adjusted appropriately.

[0457] This series of processes makes it possible to grasp the work content and emotional state of robots in the factory in real time, allowing for appropriate work allocation and health management.

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

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

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

[0461] [Second embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0474] This invention relates to a system that collects data from email, chat tools, and document management systems that employees use daily, analyzes this data using generative AI, extracts the work content and skills of employees, and reflects this in a visualization tool.

[0475] 1. Data Collection

[0476] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[0477] 2. Data Analysis

[0478] Generative AI: The collected data is analyzed by generative AI. This analysis involves extracting keywords and key phrases using natural language processing techniques. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[0479] Server: The analysis results provided by the generative AI are categorized and organized by employee, allowing each employee's skill set and job duties to be identified and registered in a database.

[0480] 3. Information Registration

[0481] Server: The analyzed information is registered in a database for each employee. The database centrally manages employee skill sets and work history. For example, the database entry for "Yamada Taro" would register his skills such as "project management," "Python," and "data analysis."

[0482] 4. Visualization of information

[0483] Server: The information registered in the database is reflected in the visualization tool. The visualization tool uses a graphical interface and is designed to be easily viewable by other employees and managers. For example, information about Yamada Taro's skill set and the projects he is involved in is displayed in dashboard format.

[0484] 5. Feedback and Updates

[0485] Users (employees): Through the visualization tool, they can check their own skill sets and work history and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[0486] Server: The server receives feedback from employees and updates their skill sets and work history in the database. Based on this feedback, the information in the visualization tool is also updated in real time.

[0487] The specific processing flow of this system will be described later, but by combining these elements, it is possible to accurately grasp employee skills and job content, and support optimal personnel allocation and effective human resource development. For example, when selecting members for a new project, the visualization tool can be used to quickly identify the appropriate members. In addition, it is easy to understand workload imbalances and contribution levels, resulting in efficient team management.

[0488] The processing flow will be explained below.

[0489] Step 1: Collect data

[0490] Server: Regularly access and collect data from each employee's email server, chat tool, and document management system. This collection process is automated and includes a scheduling function to ensure the most up-to-date data is always available.

[0491] Specific behavior:

[0492] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[0493] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[0494] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[0495] Step 2: Analyze the data

[0496] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[0497] Specific behavior:

[0498] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[0499] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[0500] Calculate keyword relevance and identify important phrases.

[0501] Step 3: Categorize and organize information

[0502] Server: Organizes the keywords and phrases extracted by generative AI and classifies each employee's skill set and job duties, thereby clarifying each employee's profile.

[0503] Specific behavior:

[0504] The extracted keywords are then mapped to templates for updating employee skill sets.

[0505] Create categories and categorize information based on specific job duties and skills.

[0506] The classified information is registered in a database as a profile for each employee.

[0507] Step 4: Register your information

[0508] Server: Classified skill sets and work content are registered in a database for each employee. This database centrally manages employee skills and project history.

[0509] Specific behavior:

[0510] Create a profile for each employee and enter the necessary skills and work history.

[0511] The registered information is stored in a database so that updated information is reflected immediately.

[0512] Step 5: Reflecting on visualization tools

[0513] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to allow employees and managers to easily view the information.

[0514] Specific behavior:

[0515] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[0516] Visually display each employee's skill set and job duties in the form of graphs and charts.

[0517] Step 6: Feedback and Updates

[0518] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[0519] Specific behavior:

[0520] Employees use visualization tools to check their skill sets and job duties.

[0521] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[0522] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[0523] Through this series of processing steps, the system can automatically grasp and visualize employee skills and job duties, enabling efficient human resource management and optimal allocation.

[0524] Example 1

[0525] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0526] Modern companies are required to accurately understand and appropriately manage their employees' skills and work content. Traditional methods require manual collection and classification of employee work content and skills, which requires significant time and effort, and can lead to inaccurate information or oversights. As a result, optimal personnel allocation and effective human resource development become difficult, reducing the efficiency of the entire company. To solve this problem, a system is needed that can automatically collect and analyze data, visualize it, and incorporate feedback in an integrated manner.

[0527] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0528] In this invention, the server includes: means for collecting email data from email servers used by employees; means for collecting chat data from chat tools used by employees; means for collecting documents from document management systems used by employees; means for analyzing the collected email data, chat data, and documents using a generative AI model based on natural language processing technology to extract keywords and important phrases; means for classifying the extracted keywords and important phrases by employee and identifying the employee's skill set and job content; means for registering the identified skill set and job content in a database for each employee; means for reflecting the registered skill set and job content in a visualization tool and displaying it in dashboard format using a graphical interface; and means for receiving feedback from employees and updating the skill set and job content in the database. This allows for an accurate understanding of employee skills and job content, enabling appropriate personnel placement and effective human resource development.

[0529] An "email server" is a server system that stores and manages data on e-mails sent and received by employees.

[0530] A "chat tool" is a communication tool that allows employees to exchange messages in real time.

[0531] A "document management system" is a system for storing, managing, and sharing document files created by employees.

[0532] "Natural language processing technology" is a technology that enables computers to understand, analyze, and respond to human language.

[0533] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to extract keywords and phrases from text data.

[0534] "Keywords" are specific words extracted as a result of data analysis that describe employees' skills and job duties.

[0535] "Key phrases" are specific phrases extracted as a result of data analysis that provide detailed information about an employee's skills and job duties.

[0536] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[0537] "Job Description" is a detailed description of the work or tasks performed by a particular employee.

[0538] A "database" is a system for centrally storing, managing, and searching information.

[0539] A "visualization tool" is software that visually displays information in a database, making it easier to view.

[0540] A "graphical interface" is a user interface that displays information in a visually easy-to-understand format.

[0541] "Dashboard format" is a format in which information is aggregated and displayed on a single screen using multiple widgets, graphs, and charts.

[0542] "Feedback" is any correction or additional information that an employee provides to the system.

[0543] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model, extracts employees' work content and skills, and reflects this information in a visualization tool.

[0544] System Overview

[0545] The entire system consists of the following hardware and software:

[0546] Server: Handles data collection, analysis, classification, registration, visualization, and feedback processing.

[0547] Email server: Provides employee email data.

[0548] Chat tool: Provides employee chat data.

[0549] Document Management System: Provides employee-generated documents.

[0550] Generative AI model: Analyzes collected data and extracts keywords and important phrases.

[0551] Visualization tool: Displays employee skills and job duties in a graphical interface.

[0552] Specific processing of the program

[0553] Data collection

[0554] Server: First, periodically collect email data sent and received by employees from the email server (for example, Gmail's IMAP server). To do this, Python's IMAP library is used to connect to the email server and retrieve unread emails. The email body is then converted to text format and saved in data storage.

[0555] Examples:

[0556] Example text: sales_report_email.txt

[0557] In addition, the server collects message logs from chat tools (e.g., Slack), obtains chat messages using the Slack API, converts them into text format, and stores them in the data storage as well.

[0558] Examples:

[0559] Example text: client_meeting_chat.txt

[0560] The server also periodically collects document files from a document management system (e.g., Google Drive), retrieves new documents using the Google Drive API, converts their contents into text format, and saves them in the data storage.

[0561] Examples:

[0562] Example text: project_plan_document.txt

[0563] Data analysis

[0564] Generative AI model: The collected data is analyzed by a generative AI model, which uses natural language processing techniques to extract keywords and key phrases to identify employee skills and job roles.

[0565] Example prompt sentence:

[0566] Please report on the progress of your new project.

[0567] Specific operation: Using a generative AI model such as BERT, keywords such as "project management," "data analysis," and "Python" are extracted from text data by executing the above prompt.

[0568] Classifying and organizing information

[0569] Server: Next, the server categorizes and organizes the analysis results provided by the generative AI model by employee, identifying each employee's skill set and job duties, and registering them in a database.

[0570] Example: Using a Python script, the analysis results are categorized by employee and the data is inserted into a database such as MySQL or PostgreSQL.

[0571] Information visualization

[0572] Server: The registered information is reflected in the visualization tool, which allows employees and managers to easily view the information. For example, skill sets and work history can be displayed in dashboard format.

[0573] Example: Using Power BI or Tableau dashboards to retrieve and visualize information from databases.

[0574] Feedback and Updates

[0575] Users (employees): They can review the visualized information and provide corrections or additional feedback as needed, for example, adding new skills.

[0576] Example: Use a feedback form in Power BI or Tableau to ask employees to add "JavaScript" skills.

[0577] Server: The server receives feedback from employees and updates the database, which in turn updates the information in the visualization tool in real time.

[0578] This system is a powerful tool for accurately understanding employee skills and job duties, ensuring appropriate personnel placement and effective personnel development.

[0579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0580] Step 1: Collect data

[0581] Servers: Collect data from email servers, chat tools, and document management systems.

[0582] Input: Email server (e.g. Gmail), chat tool (e.g. Slack), document management system (e.g. Google Drive)

[0583] Data processing: Convert data from each system into text format

[0584] Output: Collected email data, chat data, and document data (text format)

[0585] Specific operations: Uses Python's IMAP library to retrieve unread emails from an email server and save them as text files. Uses Slack API to retrieve messages from a specific channel and save them in text format. Uses Google Drive API to convert the contents of a new file to text and save it.

[0586] Step 2: Temporarily save data

[0587] Server: Stores collected data in temporary storage.

[0588] Input: Textual data collected in Step 1

[0589] Data processing: unifying data formats (text conversion, organization)

[0590] Output: Text data in a unified format

[0591] Specific operation: Execute a script that converts text data collected from various sources into a unified format and saves it in a specified directory.

[0592] Step 3: Data analysis

[0593] Generative AI: Analyzes collected text data and extracts keywords and important phrases.

[0594] Input: Text data in a unified format

[0595] Data processing: Keyword extraction and phrase analysis using natural language processing technology

[0596] Output: Extracted keywords and key phrases

[0597] How it works: Using a generative AI model such as BERT, it extracts keywords and phrases related to skills and job duties from collected text data. It then performs the analysis using prompt sentences.

[0598] Step 4: Organize and categorize information

[0599] Server: Classifies and organizes the analysis results by employee.

[0600] Input: Extracted keywords and key phrases

[0601] Data processing: Classify the analysis results by employee

[0602] Output: Skill sets and job duties categorized for each employee

[0603] Specific operation: The analysis results are processed using a Python script, the data is classified by employee, and inserted into the corresponding records in the database.

[0604] Step 5: Registering information in the database

[0605] Server: Registers information classified by employee in a database.

[0606] Input: Skill sets and job duties of each employee

[0607] Data processing: Registration process to database

[0608] Output: A database entry for each employee with their skill set and job description

[0609] Specific behavior: Generates an SQL query to insert each employee's skill set and job description into the database.

[0610] Step 6: Visualize the information

[0611] Server: Reflects the registered data in the visualization tool.

[0612] Input: Database entries that register the skill sets and job duties of each employee

[0613] Data processing: Retrieving information through database queries and preparing it for display in a graphical interface

[0614] Output: Visual information display in the form of a dashboard

[0615] What you will do: Use dashboard tools like Power BI and Tableau to query information from the database and update the dashboard.

[0616] Step 7: Gather feedback

[0617] Users (employees): Through visualization tools, they can check their own skill sets and work history, and provide corrections and additional feedback.

[0618] Input: Information that is modified or added on the dashboard

[0619] Data processing: Entering corrected and added information

[0620] Output: Corrections and additional information

[0621] What it does: Employees add new skills, such as "JavaScript," using feedback forms in Power BI and Tableau.

[0622] Step 8: Update the Database

[0623] Server: Receives feedback from employees and updates the database.

[0624] Input: Corrections and additional feedback information

[0625] Data processing: Database update processing

[0626] Output: Updated database entry

[0627] What it does: A Python script processes feedback collected from employees and updates database records using SQL queries.

[0628] Through these steps, the system can automatically collect, analyze, classify, register, visualize, and reflect feedback on employee skills and work content, enabling companies to achieve appropriate personnel allocation and effective human resource development, thereby improving business efficiency.

[0629] (Application example 1)

[0630] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0631] With conventional systems, it was difficult to grasp and effectively manage the skills and work content of each employee. Similarly, with robot work, there was a lack of means to visualize the tasks and skill sets that each robot excels at, and to make efficient work allocations and improvements. This resulted in insufficient resource management of both humans and robots, leading to issues with reduced overall work efficiency.

[0632] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0633] In this invention, the server includes means for collecting employee email data, means for collecting employee chat data, means for collecting documents created by employees, means for analyzing the collected email data, chat data, and documents and extracting keywords and phrases, means for classifying the extracted keywords and phrases and identifying employee skill sets and work content, means for registering the identified skill sets and work content in a database for each employee, means for reflecting the registered skill sets and work content in a visualization tool, means for collecting robot work logs and analyzing work content to extract skill sets, and means for visualizing the extracted robot skill sets. This enables accurate understanding of the work content and skill sets of employees and robots, enabling efficient resource management.

[0634] "Email data" refers to the content and metadata of emails sent and received by employees.

[0635] "Chat data" refers to the content and metadata of messages sent by employees using chat tools.

[0636] "Documents" refers to electronic documents such as text files, presentation materials, and spreadsheets created by employees.

[0637] "Keywords" refer to important words extracted from the email data, chat data, and documents being analyzed.

[0638] "Phrases" refer to important clauses or grammatical units extracted from the email data, chat data, and documents being analyzed.

[0639] A "skill set" refers to the collection of specific knowledge, techniques, and abilities possessed by an employee or robot.

[0640] "Work content" refers to the specific tasks and scope of duties that an employee or robot performs on a daily basis.

[0641] A "database" is a collection of data organized according to a specific structure, where the skill sets and job descriptions of employees or robots are registered.

[0642] "Visualization tools" refer to software and applications that visually represent data.

[0643] "Server" refers to a back-end computer system that collects, analyzes, stores, and manages data.

[0644] "Work log" refers to the history and detailed records of the work performed by a robot.

[0645] A "robot" is a mechanical device that performs specific tasks automatically in a factory or other environment.

[0646] "Analysis" refers to the process of examining collected data in detail using statistical, machine learning, or other methods to extract meaningful information.

[0647] This invention relates to a system that collects data from employees' emails, chat tools, and document management systems, analyzes the data using a generative AI model, extracts the skills and work details of employees and robots, and reflects them in a visualization tool. This system makes it possible to optimally allocate personnel and robots, effectively develop personnel, and improve business efficiency.

[0648] Hardware and Software Configuration

[0649] The system includes the following hardware and software:

[0650] Server: Collects, analyzes, stores, and manages data. Examples include Amazon Web Services (AWS) and Microsoft Azure.

[0651] Cloud database: A database for centrally managing the skill sets and work details of employees and robots. Examples include Amazon RDS and Google Cloud SQL.

[0652] Visualization tools: Software for visually displaying data. Examples include Tableau and Power BI.

[0653] Generative AI models: AI models that analyze data and identify skill sets and job roles. Examples include OpenAI GPT-3 and Google BERT.

[0654] Data collection

[0655] The server collects data from email servers, chat tools, and document management systems used by employees on a daily basis, including obtaining email data using the SMTP protocol and obtaining chat messages and document files through APIs, such as the Gmail API and Slack API.

[0656] Data analysis

[0657] The server analyzes the collected data using a generative AI model, specifically using natural language processing (NLP) techniques to extract keywords and key phrases. During this analysis, skill sets and job descriptions are identified.

[0658] Data classification and registration

[0659] The analysis results are categorized by employee by the server and registered in a cloud database. This allows for centralized management of each employee's skill set and work history. Robot work logs are also collected in the same way, and the analysis results are registered in the database.

[0660] Visualization

[0661] The registered information is displayed in a graphical interface through a visualization tool. For example, employee skill sets and work history, as well as robot work content and efficiency, are displayed in dashboard format, allowing managers to understand the status of resources at a glance.

[0662] Feedback and Updates

[0663] Users (employees) can check their own skill sets and work history and provide corrections or additional feedback as needed. The server receives this feedback and updates the information in the database, which in turn updates the information in the visualization tool in real time.

[0664] Specific examples

[0665] For example, if Employee A's skill set includes the skills of "Project Management," "Python," and "Data Analysis," feedback can be provided to encourage the addition of the new skill of "JavaScript." Furthermore, it can be visualized that Robot A performs a lot of "Precision Machining" and "Inspection," and that it is achieving better results than other robots in "Precision Machining" in particular.

[0666] Prompt Sentence Examples

[0667] Specific examples of prompts to be input into a generative AI model include, "Please tell me the main skills of Employee A based on the chat messages he has sent over the past month," and "Please analyze the work logs of Robot A over the past month and tell me what tasks he is good at and how well he performed."

[0668] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0669] Step 1:

[0670] The server collects employee email data, chat data, and documents. This includes periodically retrieving email data from an email server using the SMTP protocol and collecting data from chat tools (e.g., Slack) and document management systems (e.g., Google Drive) via APIs. The input data is email, chat messages, and document files, and the output is saved in data storage after being converted to text format.

[0671] Step 2:

[0672] The server processes the collected data and analyzes it using a generative AI model. This analysis includes extracting keywords and phrases using natural language processing (NLP) techniques. For example, a Python script is used to invoke a generative model (e.g., GPT-3) to extract important words and phrases within the text. The input data is the text data collected and saved in step 1, and the output is the analyzed keywords and phrases.

[0673] Step 3:

[0674] The server categorizes the analysis results provided by the generative AI model for each employee and registers their skill sets and job descriptions in a database. During this process, the data is organized into categories based on each employee's email address and chat ID and saved in a cloud database. The input data is the analysis results obtained in step 2, and the output is each employee's skill set and job description.

[0675] Step 4:

[0676] The server then reflects the registered skill sets and work details in a visualization tool. This involves using a graphical interface to display each employee's skill set and work history in dashboard format. For example, data visualization is performed using Tableau or Power BI. The input data are the skill sets and work details registered in the database, and the output is a visually displayed dashboard.

[0677] Step 5:

[0678] Users (employees) can check their own skill sets and work history through the visualization tool and provide corrections or additional feedback as needed. The input data is the feedback from the user, and the output is the updated skill sets and work content.

[0679] Step 6:

[0680] The server receives feedback from employees and updates their skill sets and work history in the database. This involves modifying the database in real time and keeping the information in the visualization tool up to date. The input data is the feedback provided in step 5, and the output is the updated database and visualization tool.

[0681] Step 7:

[0682] The server collects and analyzes the robot's work logs to extract the robot's skill set and work content. This involves acquiring data from IoT sensors and logging systems used in the factory. The input data is the robot's work logs, and the output is the analyzed robot's skill set.

[0683] Step 8:

[0684] The server classifies the analysis results by robot and registers the robot's skill set and work content in a database. The input data are the analysis results obtained in step 7, and the output is the skill set and work content for each robot.

[0685] Step 9:

[0686] The server reflects the registered robot's skill set in the visualization tool and displays it graphically. This allows managers to understand at a glance the robot's specialties and performance. The input data is the robot's skill set registered in the database, and the output is a visual dashboard.

[0687] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0688] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this information in a visualization tool.

[0689] 1. Data Collection

[0690] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[0691] 2. Data Analysis

[0692] Generative AI: Collected data is analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases, such as skills and job descriptions like "project management," "data analysis," and "Python."

[0693] Emotion engine: Furthermore, the emotion engine recognizes the user's emotions from the analyzed data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[0694] Server: The analysis results provided by the generative AI and emotion engine are categorized and organized by employee, allowing each employee's skill set, job duties, and emotional state to be identified and registered in a database.

[0695] 3. Information Registration

[0696] Server: The analyzed information is registered in a database for each employee. The database centrally manages employees' skill sets, work history, and emotional states. For example, the database entry for "Yamada Taro" will record his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[0697] 4. Visualization of information

[0698] Server: The information in the database is reflected in the visualization tool. The visualization tool uses a graphical interface to make it easy for other employees and managers to view the information. For example, Yamada Taro's skill set, job duties, and current emotional state (stress level, etc.) are displayed in dashboard format.

[0699] 5. Feedback and Updates

[0700] Users (employees): Through visualization tools, they can check their own skill sets, work history, and emotional state, and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[0701] Server: The server receives feedback from employees and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[0702] 6. Utilizing Emotional Data

[0703] Server: Evaluates workload and stress levels based on emotional data obtained from users. Based on this evaluation, the health and work status of employees is understood, and appropriate feedback and suggestions for improvement are provided.

[0704] Specific working example:

[0705] For example, if emotional data indicates that Yamada Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[0706] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[0707] Through this series of processes, the system automatically grasps and visualizes employee skills, work content, and emotional state, making it possible to improve the efficiency of human resource management, optimize staff allocation, and support employee health management, which is expected to improve productivity and employee satisfaction across the company.

[0708] The processing flow will be explained below.

[0709] Step 1: Collect data

[0710] Server: Regularly accesses each employee's email server, chat tool, and document management system to collect data. This includes the ability to automatically retrieve required data using APIs.

[0711] Specific behavior:

[0712] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[0713] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[0714] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[0715] Step 2: Analyze the data

[0716] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[0717] Specific behavior:

[0718] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[0719] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[0720] Calculate keyword relevance and identify important phrases.

[0721] Emotion Engine: Analyzes the collected data to recognize the user's emotions. This process involves analyzing, for example, the tone and style of writing.

[0722] Specific behavior:

[0723] Classify emotions such as positive, negative, and neutral from the content of emails and chats.

[0724] For example, phrases such as "tired" and "troubled" are recognized as negative emotions.

[0725] The recognized emotional data is organized and stored as the employee's emotional state.

[0726] Step 3: Categorize and organize information

[0727] Server: Based on the analysis results provided by the generative AI and emotion engine, classifies each employee's skill set, job content, and emotional state.

[0728] Specific behavior:

[0729] Extracted keywords and phrases are mapped to templates based on skills and job duties.

[0730] Classifying sentiment data into categories such as positive, negative, and neutral.

[0731] The classified information is registered in a database as a profile for each employee.

[0732] Step 4: Register your information

[0733] Server: Registers classified skill sets, job duties, and emotional states in a database for each employee.

[0734] Specific behavior:

[0735] Create a profile for each employee and enter the necessary skills, work history, and emotional state.

[0736] The registered information is stored in a database so that updated information is reflected immediately.

[0737] Step 5: Reflecting on visualization tools

[0738] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to allow employees and managers to easily view the information.

[0739] Specific behavior:

[0740] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[0741] Visually display each employee's skill set, job duties, and emotional state in graphs and charts.

[0742] Step 6: Feedback and Updates

[0743] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[0744] Specific behavior:

[0745] Employees use visualization tools to identify their skill sets, job duties, and emotional state.

[0746] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[0747] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[0748] Step 7: Use emotion data

[0749] Server: Evaluates workload and stress levels based on emotional data obtained from users. The results of this evaluation are used to improve employee health and work efficiency.

[0750] Specific behavior:

[0751] Emotional data is used to assess employee stress levels and create reports to help balance work.

[0752] If high stress levels are detected, the system will automatically send notifications suggesting appropriate rest or task reallocation.

[0753] Visualize the emotional state of the entire team and help managers adjust workload imbalances appropriately.

[0754] This series of processing steps automatically grasps and visualizes employee skills, work content, and emotional state, enabling efficient human resource management, optimal allocation, and employee health management. As a result, improvements in productivity and employee satisfaction across the entire company can be expected.

[0755] Example 2

[0756] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0757] Conventional employee management systems struggled to efficiently collect and analyze a wide range of data, including email, chat, and documents, and to centrally understand employees' skill sets, work content, and emotional state. This made it difficult to properly evaluate employees' workloads and stress levels and provide optimal feedback and suggestions for improvement. Furthermore, there was a lack of visualization methods for displaying collected data in an easy-to-understand manner, making it difficult for employees and managers to easily check the information. Furthermore, few systems allowed for dynamic updating of data based on employee feedback.

[0758] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0759] In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for preprocessing the collected email data, chat data, and documents; means including a generation AI for analyzing the preprocessed data and extracting keywords and phrases; means including an emotion engine for recognizing employee emotions from the analyzed data; means for classifying the extracted keywords, phrases, and emotional states and identifying employee skill sets, job content, and emotional states; means for registering the identified skill sets, job content, and emotional states in a database for each employee; and means for reflecting the registered skill sets, job content, and emotional states in a visualization tool. This enables a unified understanding of employee skills, job content, and emotional states and a visually easy-to-understand display. Furthermore, the database can be dynamically updated based on feedback from employees, enabling business management and improvement proposals based on the latest information.

[0760] "Email data" refers to digital information including the content, metadata, and attachments of emails sent and received by employees.

[0761] "Chat data" refers to digital information including messages exchanged on chat tools used by employees and their metadata (such as time of sending, sender, recipient, and chat room information).

[0762] "Documents" are digital files such as text files, spreadsheets, presentations, and PDF documents that employees create or manage.

[0763] "Preprocessing" refers to processes such as data cleansing, format conversion, and normalization to convert collected raw data into a format that is easy to analyze.

[0764] "Generative AI" is an artificial intelligence system that uses natural language processing technology to automatically extract keywords and important phrases from text data.

[0765] The "Emotion Engine" is a machine learning-based system for analyzing and classifying employees' emotional states (e.g., stress levels, satisfaction, etc.) from text data.

[0766] A "skill set" is information that lists the work-related skills, knowledge, and techniques possessed by a particular employee.

[0767] "Job content" refers to information about the tasks and projects that employees perform on a daily basis, as well as the general duties they are responsible for.

[0768] "Emotional state" is information that indicates an employee's psychological state and emotional movements (for example, stress, satisfaction, fatigue, etc.).

[0769] The "database" is a digital data storage system that collects, analyzes, and organizes each employee's skill set, job content, and emotional state for centralized management.

[0770] A "visualization tool" is a graphical interface that visually displays information in a database, allowing employees and managers to easily view and analyze it.

[0771] "Feedback" is information that employees provide to the system regarding corrections or additions to their skill sets or job duties.

[0772] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this in a visualization tool.

[0773] Data collection and preprocessing

[0774] Server: First, the server collects data from email servers (e.g., Gmail), chat tools (e.g., Slack), and document management systems (e.g., Google Drive) used by employees. This data is periodically obtained using APIs or protocols. It collects sent and received email data from email servers, message logs from chat tools, and created document files from document management systems. The collected data is then converted into text format and stored in data storage.

[0775] Data analysis

[0776] Preprocessing: The server performs preprocessing to convert the collected data into a format suitable for analysis, such as removing boilerplate text, removing HTML tags, and standardizing dates and timestamps.

[0777] Generative AI: The pre-processed data is then analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases from the text data. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[0778] Emotion engine: The emotion engine recognizes emotional states from analyzed text data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[0779] Organizing and registering information

[0780] Server: The server categorizes and organizes the analysis results provided by the generative AI and emotion engine for each employee. This identifies each employee's skill set, job description, and emotional state, and registers them in the database. For example, the database entry for "Employee Taro" includes his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[0781] Information visualization

[0782] Server: The server uses the information in the database to display the visualization tool. The visualization tool uses a graphical interface and is designed to make it easy for other employees and managers to view information. For example, Taro's skill set, job description, and current emotional state are displayed in dashboard format.

[0783] Feedback and Updates

[0784] User (employee): Through the visualization tool, users can check their own skill sets, work history, and emotional state, and provide feedback as needed. For example, they can provide feedback to Taro to add the new skill "JavaScript."

[0785] Server: The server receives feedback from users and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[0786] Utilizing Emotional Data

[0787] Server: The server evaluates the workload and stress level based on the emotional data obtained from the user. Based on this evaluation, the server grasps the employee's health and work situation and provides appropriate feedback and suggestions for improvement.

[0788] Specific working example:

[0789] If emotional data indicates that Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[0790] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[0791] Example of an input prompt for a generative AI model:

[0792] "Extract employee skill sets and job descriptions from the following text data, and analyze their emotional state. The text data is as follows: 'Today we had a project management meeting. We also performed data analysis using Python. It seems like they're a little stressed.'"

[0793] As described above, the present invention makes it possible to grasp employee skills, work content, and emotional state in a unified manner and display them in a visually easy-to-understand manner. Furthermore, by receiving feedback from employees and dynamically updating the database, work management and improvement proposals can be made based on the latest information.

[0794] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0795] Step 1: Data collection

[0796] Servers: Periodically collect data from email servers, chat tools, and document management systems used by employees. Specific actions include:

[0797] Email Data Collection: Uses the Gmail API to retrieve inbound and outbound email data from employee mailboxes.

[0798] Input: Email data obtained from the Gmail API

[0799] Output: Acquired email data (sending / receiving history, email body, attachments, etc.)

[0800] Chat data collection: Use the Slack API to obtain message logs between employees.

[0801] Input: Chat messages retrieved through the Slack API

[0802] Output: Acquired chat data (message content, chat room information, timestamp, etc.)

[0803] Document data collection: Use the Google Drive API to obtain document files created by employees.

[0804] Input: Document data retrieved from the Google Drive API

[0805] Output: Retrieved document data (file name, file contents, metadata, etc.)

[0806] Step 2: Data Preprocessing

[0807] Server: Converts collected data into a format suitable for analysis. Specific operations include:

[0808] Text normalization: Removes HTML tags and special characters from collected text data to make the text clean.

[0809] Input: Collected raw data (email data, chat data, document data)

[0810] Output: Clean text data

[0811] Cleaning: Removes boilerplate and unnecessary header information, producing pure text information for analysis.

[0812] Input: clean text data

[0813] Output: Text data with unnecessary information removed

[0814] Format conversion: Convert dates and timestamps into a unified format.

[0815] Input: Text data with unnecessary information removed

[0816] Output: Text data converted into an easy-to-parse format

[0817] Step 3: Data analysis

[0818] Generative AI and Emotion Engine: Analyzes pre-processed data to extract employee skills and emotional states. Specific actions include:

[0819] Keyword extraction: Generative AI uses natural language processing techniques to extract keywords and key phrases from text data.

[0820] Input: Text data converted into an easy-to-parse format

[0821] Output: Extracted keywords and significant phrases

[0822] Sentiment analysis: The emotion engine analyzes employee emotions from text data and identifies emotional states such as "high stress" or "satisfied."

[0823] Input: Text data converted into an easy-to-parse format

[0824] Output: Parsed emotional state information

[0825] Step 4: Organize and register information

[0826] Server: Classifies and organizes the analysis results provided by the generative AI and emotion engine for each employee. Specific operations include:

[0827] Data classification: Based on each employee's information (e.g., "Employee Taro"), associate their skill set, job duties, and emotional state.

[0828] Input: extracted keywords and key phrases, parsed emotional state information

[0829] Output: Organized information for each employee

[0830] Database registration: Classified information is registered in a database for each employee.

[0831] Input: Organized information for each employee

[0832] Output: Skill sets, job descriptions, and emotional states registered in the database

[0833] Step 5: Visualize the information

[0834] Server: Reflects the information in the database to the visualization tool. This includes the following specific operations:

[0835] Extraction and display of information: The registered information is reflected in visualization tools such as dashboards and displayed visually.

[0836] Input: Information registered in the database

[0837] Output: Visualized data (e.g., dashboard display)

[0838] Step 6: Feedback and Updates

[0839] User (employee) and server: User provides feedback and server updates the database. Specific actions include:

[0840] User feedback: Users use the visualization tool to input corrections and additions to their information.

[0841] Input: User feedback information (e.g. "Add JavaScript skills")

[0842] Output: Feedback data

[0843] Database Update: The server receives the feedback data and updates the database in real time.

[0844] Input: Feedback data

[0845] Output: Updated database information

[0846] Step 7: Leverage sentiment data

[0847] Server: Based on the analyzed emotional data, it evaluates workload and stress levels and suggests appropriate actions. Specific actions include:

[0848] Emotional assessment: Analyze collected emotional data to assess workload and stress levels.

[0849] Input: Parsed emotion data

[0850] Output: Evaluation results (stress level and workload status)

[0851] Action proposal: Based on the evaluation results, we propose appropriate feedback and task redistribution to employees.

[0852] Input: Evaluation result

[0853] Output: Suggested feedback and / or actions

[0854] Through these steps, the system will be able to grasp and visualize employee skills, work content, and emotional state in a unified manner, and dynamically update them based on feedback. This process is expected to improve productivity and employee satisfaction across the company.

[0855] (Application example 2)

[0856] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0857] There is a need for a system that can grasp the work content and skill sets of robots working in factories in real time, and manage the appropriate work allocation and health status. Conventional methods require humans to check the robot's work status and abnormal conditions one by one, which reduces work efficiency and makes it difficult to respond to abnormalities in real time. In addition, there is an issue that accurate management is not possible due to insufficient detailed analysis and visualization of the robot's work content.

[0858] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for analyzing the collected email data, chat data, and documents to extract important keywords and phrases; means for classifying the extracted keywords and phrases and identifying the employee's ability set and job content; means for registering the identified ability set and job content in a database for each employee; and means for reflecting the registered ability set, job content, and emotional state in a visualization tool and displaying it via a head-mounted display. This makes it possible to monitor and manage the work content and abnormal conditions of robots in a factory in real time, thereby improving work efficiency and enabling appropriate abnormality responses.

[0859] A head-mounted display is a device used to display images in front of the wearer's eyes, allowing the user to obtain visual information in real time.

[0860] Emotional state refers to the mental state of employees and robots, such as stress levels and satisfaction, analyzed from collected data.

[0861] A visualization tool is a tool that displays data using a graphical interface to make information intuitively easy to understand.

[0862] A capability set refers to the skills and expertise possessed by employees or robots, as well as the specific work tasks that are extracted through analysis.

[0863] A database is a data storage system that stores collected data in an organized manner and manages it so that it can be used for later retrieval and analysis.

[0864] Keywords and phrases are important words and sentences that indicate specific skills or job content and are extracted by generative AI from collected data.

[0865] An employee is someone who is part of a company or organization that uses this system and who uses email, chat tools, and document management systems for daily work and communication.

[0866] This invention is a system that can grasp the work content, skill sets, and emotional states of robots working in factories in real time, and then allocate tasks appropriately and manage their health. This system collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model and emotion engine, and then reflects it in a visualization tool. Managers can also access information in real time using a head-mounted display.

[0867] Hardware configuration

[0868] The server includes a means for periodically collecting data from the email server, chat tool, and document management system, and also includes data storage for saving the collected data.

[0869] The head-mounted display is a device that displays images in front of the manager's eyes, allowing the manager to visually check the robot's work content and emotional state in real time.

[0870] Software configuration

[0871] Generative AI models and sentiment engines are used to analyze collected data and extract key keywords, phrases, and emotional states. Specifically, they leverage natural language processing techniques to identify skill sets and job roles, and perform sentiment analysis.

[0872] A visualization tool is software that displays analyzed data in a graphical interface, making it easier for managers to intuitively understand the information.

[0873] Data collection and analysis

[0874] The server first collects data from email servers, chat tools, and document management systems. This data is converted into text format and stored in data storage. The generative AI model then uses natural language processing technology to extract important keywords and phrases, and the emotion engine recognizes emotional states from the analyzed data. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," as well as emotional states such as "high stress." The results of this analysis are classified for each employee and robot and registered in a database.

[0875] Data visualization and feedback

[0876] The registered data is displayed in a graphical interface using a visualization tool, and managers can check the information in real time via a head-mounted display. This allows managers to immediately understand the robot's work content and emotional state and give instructions on work allocation or rest as necessary. For example, if the robot is in a state of high stress, the system will send a notification and suggest appropriate rest or task reallocation.

[0877] Specific examples

[0878] By using this system, it is possible to improve the work efficiency of robots in factories. For example, by inputting prompt statements such as "Leader, how is today's work progress? Please analyze the skill set and emotional state based on chat history, email content, and document content, visualize them, and report them to us. For example, we would like to obtain information such as, 'Robot operation skills have improved, but stress levels are rising,'" into the generative AI model, detailed analysis results can be obtained. This enables appropriate work management and efficiency in real time.

[0879] In summary, the present invention realizes improved work efficiency and health management by understanding the work content and emotional state of robots in a factory in real time and taking appropriate measures.

[0880] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0881] Step 1:

[0882] The data collection server periodically collects data from email servers, chat tools, and document management systems. It handles raw data collected from each system's API as input. This data is converted to text format and stored in data storage. For example, it collects emails, chat logs, and document files from the past 24 hours at 9:00 a.m. every day.

[0883] Step 2:

[0884] The data analysis server analyzes the collected email data, chat data, and documents using a generative AI model and emotion engine. The text data collected in step 1 is used as input. The generative AI model uses natural language processing techniques to extract keywords and important phrases, and the emotion engine analyzes emotional states. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," and emotional states such as "high stress."

[0885] Step 3:

[0886] Data Classification and Registration The server classifies the data based on the analysis results obtained from the generative AI model and emotion engine, and registers it in a database for each employee and robot. The analysis results are used as input. The skill set, job content, and emotional state of each employee and robot are stored in the database as output. For example, information such as "Employee A" having high "robot operation skills" and low "stress level" is registered in the database.

[0887] Step 4:

[0888] Data visualization: The server generates a graphical interface using a visualization tool based on the information in the database. As input, it uses the skill sets and emotional states registered in the database. As output, it generates visual information that is displayed in real time through a head-mounted display. For example, a manager can wear the head-mounted display and check employee A's "robot operation skills" and "stress level."

[0889] Step 5:

[0890] Real-time feedback The user (manager) checks the visualized information and provides feedback as necessary. As input, the user checks the information displayed on the head-mounted display. As output, the feedback content is sent to the server and the database is updated. For example, if employee A is feeling stressed, the manager can reallocate tasks or instruct him or her to take a break.

[0891] Step 6:

[0892] Reflecting Feedback The server receives feedback from the user and modifies or adds information to the database. As input, it uses the feedback information from the administrator. As output, the updated skill set and emotional state are reflected in the database. For example, "JavaScript" is added as a new skill set, and the stress level is adjusted appropriately.

[0893] This series of processes makes it possible to grasp the work content and emotional state of robots in the factory in real time, allowing for appropriate work allocation and health management.

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

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

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

[0897] [Third embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0910] This invention relates to a system that collects data from email, chat tools, and document management systems that employees use daily, analyzes this data using generative AI, extracts the work content and skills of employees, and reflects this in a visualization tool.

[0911] 1. Data Collection

[0912] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[0913] 2. Data Analysis

[0914] Generative AI: The collected data is analyzed by generative AI. This analysis involves extracting keywords and key phrases using natural language processing techniques. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[0915] Server: The analysis results provided by the generative AI are categorized and organized by employee, allowing each employee's skill set and job duties to be identified and registered in a database.

[0916] 3. Information Registration

[0917] Server: The analyzed information is registered in a database for each employee. The database centrally manages employee skill sets and work history. For example, the database entry for "Yamada Taro" would register his skills such as "project management," "Python," and "data analysis."

[0918] 4. Visualization of information

[0919] Server: The information registered in the database is reflected in the visualization tool. The visualization tool uses a graphical interface and is designed to be easily viewable by other employees and managers. For example, information about Yamada Taro's skill set and the projects he is involved in is displayed in dashboard format.

[0920] 5. Feedback and Updates

[0921] Users (employees): Through the visualization tool, they can check their own skill sets and work history and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[0922] Server: The server receives feedback from employees and updates their skill sets and work history in the database. Based on this feedback, the information in the visualization tool is also updated in real time.

[0923] The specific processing flow of this system will be described later, but by combining these elements, it is possible to accurately grasp employee skills and job content, and support optimal personnel allocation and effective human resource development. For example, when selecting members for a new project, the visualization tool can be used to quickly identify the appropriate members. In addition, it is easy to understand workload imbalances and contribution levels, resulting in efficient team management.

[0924] The processing flow will be explained below.

[0925] Step 1: Collect data

[0926] Server: Regularly access and collect data from each employee's email server, chat tool, and document management system. This collection process is automated and includes a scheduling function to ensure the most up-to-date data is always available.

[0927] Specific behavior:

[0928] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[0929] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[0930] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[0931] Step 2: Analyze the data

[0932] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[0933] Specific behavior:

[0934] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[0935] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[0936] Calculate keyword relevance and identify important phrases.

[0937] Step 3: Categorize and organize information

[0938] Server: Organizes the keywords and phrases extracted by generative AI and classifies each employee's skill set and job duties, thereby clarifying each employee's profile.

[0939] Specific behavior:

[0940] The extracted keywords are then mapped to templates for updating employee skill sets.

[0941] Create categories and categorize information based on specific job duties and skills.

[0942] The classified information is registered in a database as a profile for each employee.

[0943] Step 4: Register your information

[0944] Server: Classified skill sets and work content are registered in a database for each employee. This database centrally manages employee skills and project history.

[0945] Specific behavior:

[0946] Create a profile for each employee and enter the necessary skills and work history.

[0947] The registered information is stored in a database so that updated information is reflected immediately.

[0948] Step 5: Reflecting on visualization tools

[0949] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to allow employees and managers to easily view the information.

[0950] Specific behavior:

[0951] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[0952] Visually display each employee's skill set and job duties in the form of graphs and charts.

[0953] Step 6: Feedback and Updates

[0954] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[0955] Specific behavior:

[0956] Employees use visualization tools to check their skill sets and job duties.

[0957] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[0958] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[0959] Through this series of processing steps, the system can automatically grasp and visualize employee skills and job duties, enabling efficient human resource management and optimal allocation.

[0960] Example 1

[0961] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0962] Modern companies are required to accurately understand and appropriately manage their employees' skills and work content. Traditional methods require manual collection and classification of employee work content and skills, which requires significant time and effort, and can lead to inaccurate information or oversights. As a result, optimal personnel allocation and effective human resource development become difficult, reducing the efficiency of the entire company. To solve this problem, a system is needed that can automatically collect and analyze data, visualize it, and incorporate feedback in an integrated manner.

[0963] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0964] In this invention, the server includes: means for collecting email data from email servers used by employees; means for collecting chat data from chat tools used by employees; means for collecting documents from document management systems used by employees; means for analyzing the collected email data, chat data, and documents using a generative AI model based on natural language processing technology to extract keywords and important phrases; means for classifying the extracted keywords and important phrases by employee and identifying the employee's skill set and job content; means for registering the identified skill set and job content in a database for each employee; means for reflecting the registered skill set and job content in a visualization tool and displaying it in dashboard format using a graphical interface; and means for receiving feedback from employees and updating the skill set and job content in the database. This allows for an accurate understanding of employee skills and job content, enabling appropriate personnel placement and effective human resource development.

[0965] An "email server" is a server system that stores and manages data on e-mails sent and received by employees.

[0966] A "chat tool" is a communication tool that allows employees to exchange messages in real time.

[0967] A "document management system" is a system for storing, managing, and sharing document files created by employees.

[0968] "Natural language processing technology" is a technology that enables computers to understand, analyze, and respond to human language.

[0969] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to extract keywords and phrases from text data.

[0970] "Keywords" are specific words extracted as a result of data analysis that describe employees' skills and job duties.

[0971] "Key phrases" are specific phrases extracted as a result of data analysis that provide detailed information about an employee's skills and job duties.

[0972] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[0973] "Job Description" is a detailed description of the work or tasks performed by a particular employee.

[0974] A "database" is a system for centrally storing, managing, and searching information.

[0975] A "visualization tool" is software that visually displays information in a database, making it easier to view.

[0976] A "graphical interface" is a user interface that displays information in a visually easy-to-understand format.

[0977] "Dashboard format" is a format in which information is aggregated and displayed on a single screen using multiple widgets, graphs, and charts.

[0978] "Feedback" is any correction or additional information that an employee provides to the system.

[0979] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model, extracts employees' work content and skills, and reflects this information in a visualization tool.

[0980] System Overview

[0981] The entire system consists of the following hardware and software:

[0982] Server: Handles data collection, analysis, classification, registration, visualization, and feedback processing.

[0983] Email server: Provides employee email data.

[0984] Chat tool: Provides employee chat data.

[0985] Document Management System: Provides employee-generated documents.

[0986] Generative AI model: Analyzes collected data and extracts keywords and important phrases.

[0987] Visualization tool: Displays employee skills and job duties in a graphical interface.

[0988] Specific processing of the program

[0989] Data collection

[0990] Server: First, periodically collect email data sent and received by employees from the email server (for example, Gmail's IMAP server). To do this, Python's IMAP library is used to connect to the email server and retrieve unread emails. The email body is then converted to text format and saved in data storage.

[0991] Examples:

[0992] Example text: sales_report_email.txt

[0993] In addition, the server collects message logs from chat tools (e.g., Slack), obtains chat messages using the Slack API, converts them into text format, and stores them in the data storage as well.

[0994] Examples:

[0995] Example text: client_meeting_chat.txt

[0996] The server also periodically collects document files from a document management system (e.g., Google Drive), retrieves new documents using the Google Drive API, converts their contents into text format, and saves them in the data storage.

[0997] Examples:

[0998] Example text: project_plan_document.txt

[0999] Data analysis

[1000] Generative AI model: The collected data is analyzed by a generative AI model, which uses natural language processing techniques to extract keywords and key phrases to identify employee skills and job roles.

[1001] Example prompt sentence:

[1002] Please report on the progress of your new project.

[1003] Specific operation: Using a generative AI model such as BERT, keywords such as "project management," "data analysis," and "Python" are extracted from text data by executing the above prompt.

[1004] Classifying and organizing information

[1005] Server: Next, the server categorizes and organizes the analysis results provided by the generative AI model by employee, identifying each employee's skill set and job duties, and registering them in a database.

[1006] Example: Using a Python script, the analysis results are categorized by employee and the data is inserted into a database such as MySQL or PostgreSQL.

[1007] Information visualization

[1008] Server: The registered information is reflected in the visualization tool, which allows employees and managers to easily view the information. For example, skill sets and work history can be displayed in dashboard format.

[1009] Example: Using Power BI or Tableau dashboards to retrieve and visualize information from databases.

[1010] Feedback and Updates

[1011] Users (employees): They can review the visualized information and provide corrections or additional feedback as needed, for example, adding new skills.

[1012] Example: Use a feedback form in Power BI or Tableau to ask employees to add "JavaScript" skills.

[1013] Server: The server receives feedback from employees and updates the database, which in turn updates the information in the visualization tool in real time.

[1014] This system is a powerful tool for accurately understanding employee skills and job duties, ensuring appropriate personnel placement and effective personnel development.

[1015] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1016] Step 1: Collect data

[1017] Servers: Collect data from email servers, chat tools, and document management systems.

[1018] Input: Email server (e.g. Gmail), chat tool (e.g. Slack), document management system (e.g. Google Drive)

[1019] Data processing: Convert data from each system into text format

[1020] Output: Collected email data, chat data, and document data (text format)

[1021] Specific operations: Uses Python's IMAP library to retrieve unread emails from an email server and save them as text files. Uses Slack API to retrieve messages from a specific channel and save them in text format. Uses Google Drive API to convert the contents of a new file to text and save it.

[1022] Step 2: Temporarily save data

[1023] Server: Stores collected data in temporary storage.

[1024] Input: Textual data collected in Step 1

[1025] Data processing: unifying data formats (text conversion, organization)

[1026] Output: Text data in a unified format

[1027] Specific operation: Execute a script that converts text data collected from various sources into a unified format and saves it in a specified directory.

[1028] Step 3: Data analysis

[1029] Generative AI: Analyzes collected text data and extracts keywords and important phrases.

[1030] Input: Text data in a unified format

[1031] Data processing: Keyword extraction and phrase analysis using natural language processing technology

[1032] Output: Extracted keywords and key phrases

[1033] How it works: Using a generative AI model such as BERT, it extracts keywords and phrases related to skills and job duties from collected text data. It then performs the analysis using prompt sentences.

[1034] Step 4: Organize and categorize information

[1035] Server: Classifies and organizes the analysis results by employee.

[1036] Input: Extracted keywords and key phrases

[1037] Data processing: Classify the analysis results by employee

[1038] Output: Skill sets and job duties categorized for each employee

[1039] Specific operation: The analysis results are processed using a Python script, the data is classified by employee, and inserted into the corresponding records in the database.

[1040] Step 5: Registering information in the database

[1041] Server: Registers information classified by employee in a database.

[1042] Input: Skill sets and job duties of each employee

[1043] Data processing: Registration process to database

[1044] Output: A database entry for each employee with their skill set and job description

[1045] Specific behavior: Generates an SQL query to insert each employee's skill set and job description into the database.

[1046] Step 6: Visualize the information

[1047] Server: Reflects the registered data in the visualization tool.

[1048] Input: Database entries that register the skill sets and job duties of each employee

[1049] Data processing: Retrieving information through database queries and preparing it for display in a graphical interface

[1050] Output: Visual information display in the form of a dashboard

[1051] What you will do: Use dashboard tools like Power BI and Tableau to query information from the database and update the dashboard.

[1052] Step 7: Gather feedback

[1053] Users (employees): Through visualization tools, they can check their own skill sets and work history, and provide corrections and additional feedback.

[1054] Input: Information that is modified or added on the dashboard

[1055] Data processing: Entering corrected and added information

[1056] Output: Corrections and additional information

[1057] What it does: Employees add new skills, such as "JavaScript," using feedback forms in Power BI and Tableau.

[1058] Step 8: Update the Database

[1059] Server: Receives feedback from employees and updates the database.

[1060] Input: Corrections and additional feedback information

[1061] Data processing: Database update processing

[1062] Output: Updated database entry

[1063] What it does: A Python script processes feedback collected from employees and updates database records using SQL queries.

[1064] Through these steps, the system can automatically collect, analyze, classify, register, visualize, and reflect feedback on employee skills and work content, enabling companies to achieve appropriate personnel allocation and effective human resource development, thereby improving business efficiency.

[1065] (Application example 1)

[1066] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1067] With conventional systems, it was difficult to grasp and effectively manage the skills and work content of each employee. Similarly, with robot work, there was a lack of means to visualize the tasks and skill sets that each robot excels at, and to make efficient work allocations and improvements. This resulted in insufficient resource management of both humans and robots, leading to issues with reduced overall work efficiency.

[1068] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1069] In this invention, the server includes means for collecting employee email data, means for collecting employee chat data, means for collecting documents created by employees, means for analyzing the collected email data, chat data, and documents and extracting keywords and phrases, means for classifying the extracted keywords and phrases and identifying employee skill sets and work content, means for registering the identified skill sets and work content in a database for each employee, means for reflecting the registered skill sets and work content in a visualization tool, means for collecting robot work logs and analyzing work content to extract skill sets, and means for visualizing the extracted robot skill sets. This enables accurate understanding of the work content and skill sets of employees and robots, enabling efficient resource management.

[1070] "Email data" refers to the content and metadata of emails sent and received by employees.

[1071] "Chat data" refers to the content and metadata of messages sent by employees using chat tools.

[1072] "Documents" refers to electronic documents such as text files, presentation materials, and spreadsheets created by employees.

[1073] "Keywords" refer to important words extracted from the email data, chat data, and documents being analyzed.

[1074] "Phrases" refer to important clauses or grammatical units extracted from the email data, chat data, and documents being analyzed.

[1075] A "skill set" refers to the collection of specific knowledge, techniques, and abilities possessed by an employee or robot.

[1076] "Work content" refers to the specific tasks and scope of duties that an employee or robot performs on a daily basis.

[1077] A "database" is a collection of data organized according to a specific structure, where the skill sets and job descriptions of employees or robots are registered.

[1078] "Visualization tools" refer to software and applications that visually represent data.

[1079] "Server" refers to a back-end computer system that collects, analyzes, stores, and manages data.

[1080] "Work log" refers to the history and detailed records of the work performed by a robot.

[1081] A "robot" is a mechanical device that performs specific tasks automatically in a factory or other environment.

[1082] "Analysis" refers to the process of examining collected data in detail using statistical, machine learning, or other methods to extract meaningful information.

[1083] This invention relates to a system that collects data from employees' emails, chat tools, and document management systems, analyzes the data using a generative AI model, extracts the skills and work details of employees and robots, and reflects them in a visualization tool. This system makes it possible to optimally allocate personnel and robots, effectively develop personnel, and improve business efficiency.

[1084] Hardware and Software Configuration

[1085] The system includes the following hardware and software:

[1086] Server: Collects, analyzes, stores, and manages data. Examples include Amazon Web Services (AWS) and Microsoft Azure.

[1087] Cloud database: A database for centrally managing the skill sets and work details of employees and robots. Examples include Amazon RDS and Google Cloud SQL.

[1088] Visualization tools: Software for visually displaying data. Examples include Tableau and Power BI.

[1089] Generative AI models: AI models that analyze data and identify skill sets and job roles. Examples include OpenAI GPT-3 and Google BERT.

[1090] Data collection

[1091] The server collects data from email servers, chat tools, and document management systems used by employees on a daily basis, including obtaining email data using the SMTP protocol and obtaining chat messages and document files through APIs, such as the Gmail API and Slack API.

[1092] Data analysis

[1093] The server analyzes the collected data using a generative AI model, specifically using natural language processing (NLP) techniques to extract keywords and key phrases. During this analysis, skill sets and job descriptions are identified.

[1094] Data classification and registration

[1095] The analysis results are categorized by employee by the server and registered in a cloud database. This allows for centralized management of each employee's skill set and work history. Robot work logs are also collected in the same way, and the analysis results are registered in the database.

[1096] Visualization

[1097] The registered information is displayed in a graphical interface through a visualization tool. For example, employee skill sets and work history, as well as robot work content and efficiency, are displayed in dashboard format, allowing managers to understand the status of resources at a glance.

[1098] Feedback and Updates

[1099] Users (employees) can check their own skill sets and work history and provide corrections or additional feedback as needed. The server receives this feedback and updates the information in the database, which in turn updates the information in the visualization tool in real time.

[1100] Specific examples

[1101] For example, if Employee A's skill set includes the skills of "Project Management," "Python," and "Data Analysis," feedback can be provided to encourage the addition of the new skill of "JavaScript." Furthermore, it can be visualized that Robot A performs a lot of "Precision Machining" and "Inspection," and that it is achieving better results than other robots in "Precision Machining" in particular.

[1102] Prompt Sentence Examples

[1103] Specific examples of prompts to be input into a generative AI model include, "Please tell me the main skills of Employee A based on the chat messages he has sent over the past month," and "Please analyze the work logs of Robot A over the past month and tell me what tasks he is good at and how well he performed."

[1104] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1105] Step 1:

[1106] The server collects employee email data, chat data, and documents. This includes periodically retrieving email data from an email server using the SMTP protocol and collecting data from chat tools (e.g., Slack) and document management systems (e.g., Google Drive) via APIs. The input data is email, chat messages, and document files, and the output is saved in data storage after being converted to text format.

[1107] Step 2:

[1108] The server processes the collected data and analyzes it using a generative AI model. This analysis includes extracting keywords and phrases using natural language processing (NLP) techniques. For example, a Python script is used to invoke a generative model (e.g., GPT-3) to extract important words and phrases within the text. The input data is the text data collected and saved in step 1, and the output is the analyzed keywords and phrases.

[1109] Step 3:

[1110] The server categorizes the analysis results provided by the generative AI model for each employee and registers their skill sets and job descriptions in a database. During this process, the data is organized into categories based on each employee's email address and chat ID and saved in a cloud database. The input data is the analysis results obtained in step 2, and the output is each employee's skill set and job description.

[1111] Step 4:

[1112] The server then reflects the registered skill sets and work details in a visualization tool. This involves using a graphical interface to display each employee's skill set and work history in dashboard format. For example, data visualization is performed using Tableau or Power BI. The input data are the skill sets and work details registered in the database, and the output is a visually displayed dashboard.

[1113] Step 5:

[1114] Users (employees) can check their own skill sets and work history through the visualization tool and provide corrections or additional feedback as needed. The input data is the feedback from the user, and the output is the updated skill sets and work content.

[1115] Step 6:

[1116] The server receives feedback from employees and updates their skill sets and work history in the database. This involves modifying the database in real time and keeping the information in the visualization tool up to date. The input data is the feedback provided in step 5, and the output is the updated database and visualization tool.

[1117] Step 7:

[1118] The server collects and analyzes the robot's work logs to extract the robot's skill set and work content. This involves acquiring data from IoT sensors and logging systems used in the factory. The input data is the robot's work logs, and the output is the analyzed robot's skill set.

[1119] Step 8:

[1120] The server classifies the analysis results by robot and registers the robot's skill set and work content in a database. The input data are the analysis results obtained in step 7, and the output is the skill set and work content for each robot.

[1121] Step 9:

[1122] The server reflects the registered robot's skill set in the visualization tool and displays it graphically. This allows managers to understand at a glance the robot's specialties and performance. The input data is the robot's skill set registered in the database, and the output is a visual dashboard.

[1123] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1124] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this information in a visualization tool.

[1125] 1. Data Collection

[1126] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[1127] 2. Data Analysis

[1128] Generative AI: Collected data is analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases, such as skills and job descriptions like "project management," "data analysis," and "Python."

[1129] Emotion engine: Furthermore, the emotion engine recognizes the user's emotions from the analyzed data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[1130] Server: The analysis results provided by the generative AI and emotion engine are categorized and organized by employee, allowing each employee's skill set, job duties, and emotional state to be identified and registered in a database.

[1131] 3. Information Registration

[1132] Server: The analyzed information is registered in a database for each employee. The database centrally manages employees' skill sets, work history, and emotional states. For example, the database entry for "Yamada Taro" will record his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[1133] 4. Visualization of information

[1134] Server: The information in the database is reflected in the visualization tool. The visualization tool uses a graphical interface to make it easy for other employees and managers to view the information. For example, Yamada Taro's skill set, job duties, and current emotional state (stress level, etc.) are displayed in dashboard format.

[1135] 5. Feedback and Updates

[1136] Users (employees): Through visualization tools, they can check their own skill sets, work history, and emotional state, and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[1137] Server: The server receives feedback from employees and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[1138] 6. Utilizing Emotional Data

[1139] Server: Evaluates workload and stress levels based on emotional data obtained from users. Based on this evaluation, the health and work status of employees is understood, and appropriate feedback and suggestions for improvement are provided.

[1140] Specific working example:

[1141] For example, if emotional data indicates that Yamada Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[1142] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[1143] Through this series of processes, the system automatically grasps and visualizes employee skills, work content, and emotional state, making it possible to improve the efficiency of human resource management, optimize staff allocation, and support employee health management, which is expected to improve productivity and employee satisfaction across the company.

[1144] The processing flow will be explained below.

[1145] Step 1: Collect data

[1146] Server: Regularly accesses each employee's email server, chat tool, and document management system to collect data. This includes the ability to automatically retrieve required data using APIs.

[1147] Specific behavior:

[1148] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[1149] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[1150] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[1151] Step 2: Analyze the data

[1152] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[1153] Specific behavior:

[1154] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[1155] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[1156] Calculate keyword relevance and identify important phrases.

[1157] Emotion Engine: Analyzes the collected data to recognize the user's emotions. This process involves analyzing, for example, the tone and style of writing.

[1158] Specific behavior:

[1159] Classify emotions such as positive, negative, and neutral from the content of emails and chats.

[1160] For example, phrases such as "tired" and "troubled" are recognized as negative emotions.

[1161] The recognized emotional data is organized and stored as the employee's emotional state.

[1162] Step 3: Categorize and organize information

[1163] Server: Based on the analysis results provided by the generative AI and emotion engine, classifies each employee's skill set, job content, and emotional state.

[1164] Specific behavior:

[1165] Extracted keywords and phrases are mapped to templates based on skills and job duties.

[1166] Classifying sentiment data into categories such as positive, negative, and neutral.

[1167] The classified information is registered in a database as a profile for each employee.

[1168] Step 4: Register your information

[1169] Server: Registers classified skill sets, job duties, and emotional states in a database for each employee.

[1170] Specific behavior:

[1171] Create a profile for each employee and enter the necessary skills, work history, and emotional state.

[1172] The registered information is stored in a database so that updated information is reflected immediately.

[1173] Step 5: Reflecting on visualization tools

[1174] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to allow employees and managers to easily view the information.

[1175] Specific behavior:

[1176] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[1177] Visually display each employee's skill set, job duties, and emotional state in graphs and charts.

[1178] Step 6: Feedback and Updates

[1179] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[1180] Specific behavior:

[1181] Employees use visualization tools to identify their skill sets, job duties, and emotional state.

[1182] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[1183] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[1184] Step 7: Use emotion data

[1185] Server: Evaluates workload and stress levels based on emotional data obtained from users. The results of this evaluation are used to improve employee health and work efficiency.

[1186] Specific behavior:

[1187] Emotional data is used to assess employee stress levels and create reports to help balance work.

[1188] If high stress levels are detected, the system will automatically send notifications suggesting appropriate rest or task reallocation.

[1189] Visualize the emotional state of the entire team and help managers adjust workload imbalances appropriately.

[1190] This series of processing steps automatically grasps and visualizes employee skills, work content, and emotional state, enabling efficient human resource management, optimal allocation, and employee health management. As a result, improvements in productivity and employee satisfaction across the entire company can be expected.

[1191] Example 2

[1192] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1193] Conventional employee management systems struggled to efficiently collect and analyze a wide range of data, including email, chat, and documents, and to centrally understand employees' skill sets, work content, and emotional state. This made it difficult to properly evaluate employees' workloads and stress levels and provide optimal feedback and suggestions for improvement. Furthermore, there was a lack of visualization methods for displaying collected data in an easy-to-understand manner, making it difficult for employees and managers to easily check the information. Furthermore, few systems allowed for dynamic updating of data based on employee feedback.

[1194] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1195] In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for preprocessing the collected email data, chat data, and documents; means including a generation AI for analyzing the preprocessed data and extracting keywords and phrases; means including an emotion engine for recognizing employee emotions from the analyzed data; means for classifying the extracted keywords, phrases, and emotional states and identifying employee skill sets, job content, and emotional states; means for registering the identified skill sets, job content, and emotional states in a database for each employee; and means for reflecting the registered skill sets, job content, and emotional states in a visualization tool. This enables a unified understanding of employee skills, job content, and emotional states and a visually easy-to-understand display. Furthermore, the database can be dynamically updated based on feedback from employees, enabling business management and improvement proposals based on the latest information.

[1196] "Email data" refers to digital information including the content, metadata, and attachments of emails sent and received by employees.

[1197] "Chat data" refers to digital information including messages exchanged on chat tools used by employees and their metadata (such as time of sending, sender, recipient, and chat room information).

[1198] "Documents" are digital files such as text files, spreadsheets, presentations, and PDF documents that employees create or manage.

[1199] "Preprocessing" refers to processes such as data cleansing, format conversion, and normalization to convert collected raw data into a format that is easy to analyze.

[1200] "Generative AI" is an artificial intelligence system that uses natural language processing technology to automatically extract keywords and important phrases from text data.

[1201] The "Emotion Engine" is a machine learning-based system for analyzing and classifying employees' emotional states (e.g., stress levels, satisfaction, etc.) from text data.

[1202] A "skill set" is information that lists the work-related skills, knowledge, and techniques possessed by a particular employee.

[1203] "Job content" refers to information about the tasks and projects that employees perform on a daily basis, as well as the general duties they are responsible for.

[1204] "Emotional state" is information that indicates an employee's psychological state and emotional movements (for example, stress, satisfaction, fatigue, etc.).

[1205] The "database" is a digital data storage system that collects, analyzes, and organizes each employee's skill set, job content, and emotional state for centralized management.

[1206] A "visualization tool" is a graphical interface that visually displays information in a database, allowing employees and managers to easily view and analyze it.

[1207] "Feedback" is information that employees provide to the system regarding corrections or additions to their skill sets or job duties.

[1208] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this in a visualization tool.

[1209] Data collection and preprocessing

[1210] Server: First, the server collects data from email servers (e.g., Gmail), chat tools (e.g., Slack), and document management systems (e.g., Google Drive) used by employees. This data is periodically obtained using APIs or protocols. It collects sent and received email data from email servers, message logs from chat tools, and created document files from document management systems. The collected data is then converted into text format and stored in data storage.

[1211] Data analysis

[1212] Preprocessing: The server performs preprocessing to convert the collected data into a format suitable for analysis, such as removing boilerplate text, removing HTML tags, and standardizing dates and timestamps.

[1213] Generative AI: The pre-processed data is then analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases from the text data. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[1214] Emotion engine: The emotion engine recognizes emotional states from analyzed text data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[1215] Organizing and registering information

[1216] Server: The server categorizes and organizes the analysis results provided by the generative AI and emotion engine for each employee. This identifies each employee's skill set, job description, and emotional state, and registers them in the database. For example, the database entry for "Employee Taro" includes his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[1217] Information visualization

[1218] Server: The server uses the information in the database to display the visualization tool. The visualization tool uses a graphical interface and is designed to make it easy for other employees and managers to view information. For example, Taro's skill set, job description, and current emotional state are displayed in dashboard format.

[1219] Feedback and Updates

[1220] User (employee): Through the visualization tool, users can check their own skill sets, work history, and emotional state, and provide feedback as needed. For example, they can provide feedback to Taro to add the new skill "JavaScript."

[1221] Server: The server receives feedback from users and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[1222] Utilizing Emotional Data

[1223] Server: The server evaluates the workload and stress level based on the emotional data obtained from the user. Based on this evaluation, the server grasps the employee's health and work situation and provides appropriate feedback and suggestions for improvement.

[1224] Specific working example:

[1225] If emotional data indicates that Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[1226] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[1227] Example of an input prompt for a generative AI model:

[1228] "Extract employee skill sets and job descriptions from the following text data, and analyze their emotional state. The text data is as follows: 'Today, we had a project management meeting. We also performed data analysis using Python. It seems that the employee is a little stressed.'"

[1229] As described above, the present invention makes it possible to grasp employee skills, work content, and emotional state in a unified manner and display them in a visually easy-to-understand manner. Furthermore, by receiving feedback from employees and dynamically updating the database, work management and improvement proposals can be made based on the latest information.

[1230] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1231] Step 1: Data collection

[1232] Servers: Periodically collect data from email servers, chat tools, and document management systems used by employees. Specific actions include:

[1233] Email Data Collection: Uses the Gmail API to retrieve inbound and outbound email data from employee mailboxes.

[1234] Input: Email data obtained from the Gmail API

[1235] Output: Acquired email data (sending / receiving history, email body, attachments, etc.)

[1236] Chat data collection: Use the Slack API to obtain message logs between employees.

[1237] Input: Chat messages retrieved through the Slack API

[1238] Output: Acquired chat data (message content, chat room information, timestamp, etc.)

[1239] Document data collection: Use the Google Drive API to obtain document files created by employees.

[1240] Input: Document data retrieved from the Google Drive API

[1241] Output: Retrieved document data (file name, file contents, metadata, etc.)

[1242] Step 2: Data Preprocessing

[1243] Server: Converts collected data into a format suitable for analysis. Specific operations include:

[1244] Text normalization: Removes HTML tags and special characters from collected text data to make the text clean.

[1245] Input: Collected raw data (email data, chat data, document data)

[1246] Output: Clean text data

[1247] Cleaning: Removes boilerplate and unnecessary header information, producing pure text information for analysis.

[1248] Input: clean text data

[1249] Output: Text data with unnecessary information removed

[1250] Format conversion: Convert dates and timestamps into a unified format.

[1251] Input: Text data with unnecessary information removed

[1252] Output: Text data converted into an easy-to-parse format

[1253] Step 3: Data analysis

[1254] Generative AI and Emotion Engine: Analyzes pre-processed data to extract employee skills and emotional states. Specific actions include:

[1255] Keyword extraction: Generative AI uses natural language processing techniques to extract keywords and key phrases from text data.

[1256] Input: Text data converted into an easy-to-parse format

[1257] Output: Extracted keywords and significant phrases

[1258] Sentiment analysis: The emotion engine analyzes employee emotions from text data and identifies emotional states such as "high stress" or "satisfied."

[1259] Input: Text data converted into an easy-to-parse format

[1260] Output: Parsed emotional state information

[1261] Step 4: Organize and register information

[1262] Server: Classifies and organizes the analysis results provided by the generative AI and emotion engine for each employee. Specific operations include:

[1263] Data classification: Based on each employee's information (e.g., "Employee Taro"), associate their skill set, job duties, and emotional state.

[1264] Input: extracted keywords and key phrases, parsed emotional state information

[1265] Output: Organized information for each employee

[1266] Database registration: Classified information is registered in a database for each employee.

[1267] Input: Organized information for each employee

[1268] Output: Skill sets, job descriptions, and emotional states registered in the database

[1269] Step 5: Visualize the information

[1270] Server: Reflects the information in the database to the visualization tool. This includes the following specific operations:

[1271] Extraction and display of information: The registered information is reflected in visualization tools such as dashboards and displayed visually.

[1272] Input: Information registered in the database

[1273] Output: Visualized data (e.g., dashboard display)

[1274] Step 6: Feedback and Updates

[1275] User (employee) and server: User provides feedback and server updates the database. Specific actions include:

[1276] User feedback: Users use the visualization tool to input corrections and additions to their information.

[1277] Input: User feedback information (e.g. "Add JavaScript skills")

[1278] Output: Feedback data

[1279] Database Update: The server receives the feedback data and updates the database in real time.

[1280] Input: Feedback data

[1281] Output: Updated database information

[1282] Step 7: Leverage sentiment data

[1283] Server: Based on the analyzed emotional data, it evaluates workload and stress levels and suggests appropriate actions. Specific actions include:

[1284] Emotional assessment: Analyze collected emotional data to assess workload and stress levels.

[1285] Input: Parsed emotion data

[1286] Output: Evaluation results (stress level and workload status)

[1287] Action proposal: Based on the evaluation results, we propose appropriate feedback and task redistribution to employees.

[1288] Input: Evaluation result

[1289] Output: Suggested feedback and / or actions

[1290] Through these steps, the system will be able to grasp and visualize employee skills, work content, and emotional state in a unified manner, and dynamically update them based on feedback. This process is expected to improve productivity and employee satisfaction across the company.

[1291] (Application example 2)

[1292] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1293] There is a need for a system that can grasp the work content and skill sets of robots working in factories in real time, and manage the appropriate work allocation and health status. Conventional methods require humans to check the robot's work status and abnormal conditions one by one, which reduces work efficiency and makes it difficult to respond to abnormalities in real time. In addition, there is an issue that accurate management is not possible due to insufficient detailed analysis and visualization of the robot's work content.

[1294] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for analyzing the collected email data, chat data, and documents to extract important keywords and phrases; means for classifying the extracted keywords and phrases and identifying the employee's ability set and job content; means for registering the identified ability set and job content in a database for each employee; and means for reflecting the registered ability set, job content, and emotional state in a visualization tool and displaying it via a head-mounted display. This makes it possible to monitor and manage the work content and abnormal conditions of robots in a factory in real time, thereby improving work efficiency and enabling appropriate abnormality responses.

[1295] A head-mounted display is a device used to display images in front of the wearer's eyes, allowing the user to obtain visual information in real time.

[1296] Emotional state refers to the mental state of employees and robots, such as stress levels and satisfaction, analyzed from collected data.

[1297] A visualization tool is a tool that displays data using a graphical interface to make information intuitively easy to understand.

[1298] A capability set refers to the skills and expertise possessed by employees or robots, as well as the specific work tasks that are extracted through analysis.

[1299] A database is a data storage system that stores collected data in an organized manner and manages it so that it can be used for later retrieval and analysis.

[1300] Keywords and phrases are important words and sentences that indicate specific skills or job content and are extracted by generative AI from collected data.

[1301] An employee is someone who is part of a company or organization that uses this system and who uses email, chat tools, and document management systems for daily work and communication.

[1302] This invention is a system that can grasp the work content, skill sets, and emotional states of robots working in factories in real time, and then allocate tasks appropriately and manage their health. This system collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model and emotion engine, and then reflects it in a visualization tool. Managers can also access information in real time using a head-mounted display.

[1303] Hardware configuration

[1304] The server includes a means for periodically collecting data from the email server, chat tool, and document management system, and also includes data storage for saving the collected data.

[1305] The head-mounted display is a device that displays images in front of the manager's eyes, allowing the manager to visually check the robot's work content and emotional state in real time.

[1306] Software configuration

[1307] Generative AI models and sentiment engines are used to analyze collected data and extract key keywords, phrases, and emotional states. Specifically, they leverage natural language processing techniques to identify skill sets and job roles, and perform sentiment analysis.

[1308] A visualization tool is software that displays analyzed data in a graphical interface, making it easier for managers to intuitively understand the information.

[1309] Data collection and analysis

[1310] The server first collects data from email servers, chat tools, and document management systems. This data is converted into text format and stored in data storage. The generative AI model then uses natural language processing technology to extract important keywords and phrases, and the emotion engine recognizes emotional states from the analyzed data. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," as well as emotional states such as "high stress." The results of this analysis are classified for each employee and robot and registered in a database.

[1311] Data visualization and feedback

[1312] The registered data is displayed in a graphical interface using a visualization tool, and managers can check the information in real time via a head-mounted display. This allows managers to immediately understand the robot's work content and emotional state and give instructions on work allocation or rest as necessary. For example, if the robot is in a state of high stress, the system will send a notification and suggest appropriate rest or task reallocation.

[1313] Specific examples

[1314] By using this system, it is possible to improve the work efficiency of robots in factories. For example, by inputting prompt statements such as "Leader, how is today's work progress? Please analyze the skill set and emotional state based on chat history, email content, and document content, visualize them, and report them to us. For example, we would like to obtain information such as, 'Robot operation skills have improved, but stress levels are rising,'" into the generative AI model, detailed analysis results can be obtained. This enables appropriate work management and efficiency in real time.

[1315] In summary, the present invention realizes improved work efficiency and health management by understanding the work content and emotional state of robots in a factory in real time and taking appropriate measures.

[1316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1317] Step 1:

[1318] The data collection server periodically collects data from email servers, chat tools, and document management systems. It handles raw data collected from each system's API as input. This data is converted to text format and stored in data storage. For example, it collects emails, chat logs, and document files from the past 24 hours at 9:00 a.m. every day.

[1319] Step 2:

[1320] The data analysis server analyzes the collected email data, chat data, and documents using a generative AI model and emotion engine. The text data collected in step 1 is used as input. The generative AI model uses natural language processing techniques to extract keywords and important phrases, and the emotion engine analyzes emotional states. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," and emotional states such as "high stress."

[1321] Step 3:

[1322] Data Classification and Registration The server classifies the data based on the analysis results obtained from the generative AI model and emotion engine, and registers it in a database for each employee and robot. The analysis results are used as input. The skill set, job content, and emotional state of each employee and robot are stored in the database as output. For example, information such as "Employee A" having high "robot operation skills" and low "stress level" is registered in the database.

[1323] Step 4:

[1324] Data visualization: The server generates a graphical interface using a visualization tool based on the information in the database. As input, it uses the skill sets and emotional states registered in the database. As output, it generates visual information that is displayed in real time through a head-mounted display. For example, a manager can wear the head-mounted display and check employee A's "robot operation skills" and "stress level."

[1325] Step 5:

[1326] Real-time feedback The user (manager) checks the visualized information and provides feedback as necessary. As input, the user checks the information displayed on the head-mounted display. As output, the feedback content is sent to the server and the database is updated. For example, if employee A is feeling stressed, the manager can reallocate tasks or instruct him or her to take a break.

[1327] Step 6:

[1328] Reflecting Feedback The server receives feedback from the user and modifies or adds information to the database. As input, it uses the feedback information from the administrator. As output, the updated skill set and emotional state are reflected in the database. For example, "JavaScript" is added as a new skill set, and the stress level is adjusted appropriately.

[1329] This series of processes makes it possible to grasp the work content and emotional state of robots in the factory in real time, allowing for appropriate work allocation and health management.

[1330] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1331] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1332] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1333] [Fourth embodiment]

[1334] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1335] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1336] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1337] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1338] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1339] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1340] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1341] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1342] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1343] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1344] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1345] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1346] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1347] This invention relates to a system that collects data from email, chat tools, and document management systems that employees use daily, analyzes this data using generative AI, extracts the work content and skills of employees, and reflects this in a visualization tool.

[1348] 1. Data Collection

[1349] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[1350] 2. Data Analysis

[1351] Generative AI: The collected data is analyzed by generative AI. This analysis involves extracting keywords and key phrases using natural language processing techniques. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[1352] Server: The analysis results provided by the generative AI are categorized and organized by employee, allowing each employee's skill set and job duties to be identified and registered in a database.

[1353] 3. Information Registration

[1354] Server: The analyzed information is registered in a database for each employee. The database centrally manages employee skill sets and work history. For example, the database entry for "Yamada Taro" would register his skills such as "project management," "Python," and "data analysis."

[1355] 4. Visualization of information

[1356] Server: The information registered in the database is reflected in the visualization tool. The visualization tool uses a graphical interface and is designed to be easily viewable by other employees and managers. For example, information about Yamada Taro's skill set and the projects he is involved in is displayed in dashboard format.

[1357] 5. Feedback and Updates

[1358] Users (employees): Through the visualization tool, they can check their own skill sets and work history and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[1359] Server: The server receives feedback from employees and updates their skill sets and work history in the database. Based on this feedback, the information in the visualization tool is also updated in real time.

[1360] The specific processing flow of this system will be described later, but by combining these elements, it is possible to accurately grasp employee skills and job content, and support optimal personnel allocation and effective human resource development. For example, when selecting members for a new project, the visualization tool can be used to quickly identify the appropriate members. In addition, it is easy to understand workload imbalances and contribution levels, resulting in efficient team management.

[1361] The processing flow will be explained below.

[1362] Step 1: Collect data

[1363] Server: Regularly access and collect data from each employee's email server, chat tool, and document management system. This collection process is automated and includes a scheduling function to ensure the most up-to-date data is always available.

[1364] Specific behavior:

[1365] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[1366] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[1367] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[1368] Step 2: Analyze the data

[1369] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[1370] Specific behavior:

[1371] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[1372] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[1373] Calculate keyword relevance and identify important phrases.

[1374] Step 3: Categorize and organize information

[1375] Server: Organizes the keywords and phrases extracted by generative AI and classifies each employee's skill set and job duties, thereby clarifying each employee's profile.

[1376] Specific behavior:

[1377] The extracted keywords are then mapped to templates for updating employee skill sets.

[1378] Create categories and categorize information based on specific job duties and skills.

[1379] The classified information is registered in a database as a profile for each employee.

[1380] Step 4: Register your information

[1381] Server: Classified skill sets and work content are registered in a database for each employee. This database centrally manages employee skills and project history.

[1382] Specific behavior:

[1383] Create a profile for each employee and enter the necessary skills and work history.

[1384] The registered information is stored in a database so that updated information is reflected immediately.

[1385] Step 5: Reflecting on visualization tools

[1386] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to allow employees and managers to easily view the information.

[1387] Specific behavior:

[1388] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[1389] Visually display each employee's skill set and job duties in the form of graphs and charts.

[1390] Step 6: Feedback and Updates

[1391] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[1392] Specific behavior:

[1393] Employees use visualization tools to check their skill sets and job duties.

[1394] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[1395] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[1396] Through this series of processing steps, the system can automatically grasp and visualize employee skills and job duties, enabling efficient human resource management and optimal allocation.

[1397] Example 1

[1398] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1399] Modern companies are required to accurately understand and appropriately manage their employees' skills and work content. Traditional methods require manual collection and classification of employee work content and skills, which requires significant time and effort, and can lead to inaccurate information or oversights. As a result, optimal personnel allocation and effective human resource development become difficult, reducing the efficiency of the entire company. To solve this problem, a system is needed that can automatically collect and analyze data, visualize it, and incorporate feedback in an integrated manner.

[1400] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1401] In this invention, the server includes: means for collecting email data from email servers used by employees; means for collecting chat data from chat tools used by employees; means for collecting documents from document management systems used by employees; means for analyzing the collected email data, chat data, and documents using a generative AI model based on natural language processing technology to extract keywords and important phrases; means for classifying the extracted keywords and important phrases by employee and identifying the employee's skill set and job content; means for registering the identified skill set and job content in a database for each employee; means for reflecting the registered skill set and job content in a visualization tool and displaying it in dashboard format using a graphical interface; and means for receiving feedback from employees and updating the skill set and job content in the database. This allows for an accurate understanding of employee skills and job content, enabling appropriate personnel placement and effective human resource development.

[1402] An "email server" is a server system that stores and manages data on e-mails sent and received by employees.

[1403] A "chat tool" is a communication tool that allows employees to exchange messages in real time.

[1404] A "document management system" is a system for storing, managing, and sharing document files created by employees.

[1405] "Natural language processing technology" is a technology that enables computers to understand, analyze, and respond to human language.

[1406] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to extract keywords and phrases from text data.

[1407] "Keywords" are specific words extracted as a result of data analysis that describe employees' skills and job duties.

[1408] "Key phrases" are specific phrases extracted as a result of data analysis that provide detailed information about an employee's skills and job duties.

[1409] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[1410] "Job Description" is a detailed description of the work or tasks performed by a particular employee.

[1411] A "database" is a system for centrally storing, managing, and searching information.

[1412] A "visualization tool" is software that visually displays information in a database, making it easier to view.

[1413] A "graphical interface" is a user interface that displays information in a visually easy-to-understand format.

[1414] "Dashboard format" is a format in which information is aggregated and displayed on a single screen using multiple widgets, graphs, and charts.

[1415] "Feedback" is any correction or additional information that an employee provides to the system.

[1416] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model, extracts employees' work content and skills, and reflects this information in a visualization tool.

[1417] System Overview

[1418] The entire system consists of the following hardware and software:

[1419] Server: Handles data collection, analysis, classification, registration, visualization, and feedback processing.

[1420] Email server: Provides employee email data.

[1421] Chat tool: Provides employee chat data.

[1422] Document Management System: Provides employee-generated documents.

[1423] Generative AI model: Analyzes collected data and extracts keywords and important phrases.

[1424] Visualization tool: Displays employee skills and job duties in a graphical interface.

[1425] Specific processing of the program

[1426] Data collection

[1427] Server: First, periodically collect email data sent and received by employees from the email server (for example, Gmail's IMAP server). To do this, Python's IMAP library is used to connect to the email server and retrieve unread emails. The email body is then converted to text format and saved in data storage.

[1428] Examples:

[1429] Example text: sales_report_email.txt

[1430] In addition, the server collects message logs from chat tools (e.g., Slack), obtains chat messages using the Slack API, converts them into text format, and stores them in the data storage as well.

[1431] Examples:

[1432] Example text: client_meeting_chat.txt

[1433] The server also periodically collects document files from a document management system (e.g., Google Drive), retrieves new documents using the Google Drive API, converts their contents into text format, and saves them in the data storage.

[1434] Examples:

[1435] Example text: project_plan_document.txt

[1436] Data analysis

[1437] Generative AI model: The collected data is analyzed by a generative AI model, which uses natural language processing techniques to extract keywords and key phrases to identify employee skills and job roles.

[1438] Example prompt sentence:

[1439] Please report on the progress of your new project.

[1440] Specific operation: Using a generative AI model such as BERT, keywords such as "project management," "data analysis," and "Python" are extracted from text data by executing the above prompt.

[1441] Classifying and organizing information

[1442] Server: Next, the server categorizes and organizes the analysis results provided by the generative AI model by employee, identifying each employee's skill set and job duties, and registering them in a database.

[1443] Example: Using a Python script, the analysis results are categorized by employee and the data is inserted into a database such as MySQL or PostgreSQL.

[1444] Information visualization

[1445] Server: The registered information is reflected in the visualization tool, which allows employees and managers to easily view the information. For example, skill sets and work history can be displayed in dashboard format.

[1446] Example: Using Power BI or Tableau dashboards to retrieve and visualize information from databases.

[1447] Feedback and Updates

[1448] Users (employees): They can review the visualized information and provide corrections or additional feedback as needed, for example, adding new skills.

[1449] Example: Use a feedback form in Power BI or Tableau to ask employees to add "JavaScript" skills.

[1450] Server: The server receives feedback from employees and updates the database, which in turn updates the information in the visualization tool in real time.

[1451] This system is a powerful tool for accurately understanding employee skills and job duties, ensuring appropriate personnel placement and effective personnel development.

[1452] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1453] Step 1: Collect data

[1454] Servers: Collect data from email servers, chat tools, and document management systems.

[1455] Input: Email server (e.g. Gmail), chat tool (e.g. Slack), document management system (e.g. Google Drive)

[1456] Data processing: Convert data from each system into text format

[1457] Output: Collected email data, chat data, and document data (text format)

[1458] Specific operations: Uses Python's IMAP library to retrieve unread emails from an email server and save them as text files. Uses Slack API to retrieve messages from a specific channel and save them in text format. Uses Google Drive API to convert the contents of a new file to text and save it.

[1459] Step 2: Temporarily save data

[1460] Server: Stores collected data in temporary storage.

[1461] Input: Textual data collected in Step 1

[1462] Data processing: unifying data formats (text conversion, organization)

[1463] Output: Text data in a unified format

[1464] Specific operation: Execute a script that converts text data collected from various sources into a unified format and saves it in a specified directory.

[1465] Step 3: Data analysis

[1466] Generative AI: Analyzes collected text data and extracts keywords and important phrases.

[1467] Input: Text data in a unified format

[1468] Data processing: Keyword extraction and phrase analysis using natural language processing technology

[1469] Output: Extracted keywords and key phrases

[1470] How it works: Using a generative AI model such as BERT, it extracts keywords and phrases related to skills and job duties from collected text data. It then performs the analysis using prompt sentences.

[1471] Step 4: Organize and categorize information

[1472] Server: Classifies and organizes the analysis results by employee.

[1473] Input: Extracted keywords and key phrases

[1474] Data processing: Classify the analysis results by employee

[1475] Output: Skill sets and job duties categorized for each employee

[1476] Specific operation: The analysis results are processed using a Python script, the data is classified by employee, and inserted into the corresponding records in the database.

[1477] Step 5: Registering information in the database

[1478] Server: Registers information classified by employee in a database.

[1479] Input: Skill sets and job duties of each employee

[1480] Data processing: Registration process to database

[1481] Output: A database entry for each employee with their skill set and job description

[1482] Specific behavior: Generates an SQL query to insert each employee's skill set and job description into the database.

[1483] Step 6: Visualize the information

[1484] Server: Reflects the registered data in the visualization tool.

[1485] Input: Database entries that register the skill sets and job duties of each employee

[1486] Data processing: Retrieving information through database queries and preparing it for display in a graphical interface

[1487] Output: Visual information display in the form of a dashboard

[1488] What you will do: Use dashboard tools like Power BI and Tableau to query information from the database and update the dashboard.

[1489] Step 7: Gather feedback

[1490] Users (employees): Through visualization tools, they can check their own skill sets and work history, and provide corrections and additional feedback.

[1491] Input: Information that is modified or added on the dashboard

[1492] Data processing: Entering corrected and added information

[1493] Output: Corrections and additional information

[1494] What it does: Employees add new skills, such as "JavaScript," using feedback forms in Power BI and Tableau.

[1495] Step 8: Update the Database

[1496] Server: Receives feedback from employees and updates the database.

[1497] Input: Corrections and additional feedback information

[1498] Data processing: Database update processing

[1499] Output: Updated database entry

[1500] What it does: A Python script processes feedback collected from employees and updates database records using SQL queries.

[1501] Through these steps, the system can automatically collect, analyze, classify, register, visualize, and reflect feedback on employee skills and work content, enabling companies to achieve appropriate personnel allocation and effective human resource development, thereby improving business efficiency.

[1502] (Application example 1)

[1503] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1504] With conventional systems, it was difficult to grasp and effectively manage the skills and work content of each employee. Similarly, with robot work, there was a lack of means to visualize the tasks and skill sets that each robot excels at, and to make efficient work allocations and improvements. This resulted in insufficient resource management of both humans and robots, leading to issues with reduced overall work efficiency.

[1505] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1506] In this invention, the server includes means for collecting employee email data, means for collecting employee chat data, means for collecting documents created by employees, means for analyzing the collected email data, chat data, and documents and extracting keywords and phrases, means for classifying the extracted keywords and phrases and identifying employee skill sets and work content, means for registering the identified skill sets and work content in a database for each employee, means for reflecting the registered skill sets and work content in a visualization tool, means for collecting robot work logs and analyzing work content to extract skill sets, and means for visualizing the extracted robot skill sets. This enables accurate understanding of the work content and skill sets of employees and robots, enabling efficient resource management.

[1507] "Email data" refers to the content and metadata of emails sent and received by employees.

[1508] "Chat data" refers to the content and metadata of messages sent by employees using chat tools.

[1509] "Documents" refers to electronic documents such as text files, presentation materials, and spreadsheets created by employees.

[1510] "Keywords" refer to important words extracted from the email data, chat data, and documents being analyzed.

[1511] "Phrases" refer to important clauses or grammatical units extracted from the email data, chat data, and documents being analyzed.

[1512] A "skill set" refers to the collection of specific knowledge, techniques, and abilities possessed by an employee or robot.

[1513] "Work content" refers to the specific tasks and scope of duties that an employee or robot performs on a daily basis.

[1514] A "database" is a collection of data organized according to a specific structure, where the skill sets and job descriptions of employees or robots are registered.

[1515] "Visualization tools" refer to software and applications that visually represent data.

[1516] "Server" refers to a back-end computer system that collects, analyzes, stores, and manages data.

[1517] "Work log" refers to the history and detailed records of the work performed by a robot.

[1518] A "robot" is a mechanical device that performs specific tasks automatically in a factory or other environment.

[1519] "Analysis" refers to the process of examining collected data in detail using statistical, machine learning, or other methods to extract meaningful information.

[1520] This invention relates to a system that collects data from employees' emails, chat tools, and document management systems, analyzes the data using a generative AI model, extracts the skills and work details of employees and robots, and reflects them in a visualization tool. This system makes it possible to optimally allocate personnel and robots, effectively develop personnel, and improve business efficiency.

[1521] Hardware and Software Configuration

[1522] The system includes the following hardware and software:

[1523] Server: Collects, analyzes, stores, and manages data. Examples include Amazon Web Services (AWS) and Microsoft Azure.

[1524] Cloud database: A database for centrally managing the skill sets and work details of employees and robots. Examples include Amazon RDS and Google Cloud SQL.

[1525] Visualization tools: Software for visually displaying data. Examples include Tableau and Power BI.

[1526] Generative AI models: AI models that analyze data and identify skill sets and job roles. Examples include OpenAI GPT-3 and Google BERT.

[1527] Data collection

[1528] The server collects data from email servers, chat tools, and document management systems used by employees on a daily basis, including obtaining email data using the SMTP protocol and obtaining chat messages and document files through APIs, such as the Gmail API and Slack API.

[1529] Data analysis

[1530] The server analyzes the collected data using a generative AI model, specifically using natural language processing (NLP) techniques to extract keywords and key phrases. During this analysis, skill sets and job descriptions are identified.

[1531] Data classification and registration

[1532] The analysis results are categorized by employee by the server and registered in a cloud database. This allows for centralized management of each employee's skill set and work history. Robot work logs are also collected in the same way, and the analysis results are registered in the database.

[1533] Visualization

[1534] The registered information is displayed in a graphical interface through a visualization tool. For example, employee skill sets and work history, as well as robot work content and efficiency, are displayed in dashboard format, allowing managers to understand the status of resources at a glance.

[1535] Feedback and Updates

[1536] Users (employees) can check their own skill sets and work history and provide corrections or additional feedback as needed. The server receives this feedback and updates the information in the database, which in turn updates the information in the visualization tool in real time.

[1537] Specific examples

[1538] For example, if Employee A's skill set includes the skills of "Project Management," "Python," and "Data Analysis," feedback can be provided to encourage the addition of the new skill of "JavaScript." Furthermore, it can be visualized that Robot A performs a lot of "Precision Machining" and "Inspection," and that it is achieving better results than other robots in "Precision Machining" in particular.

[1539] Prompt Sentence Examples

[1540] Specific examples of prompts to be input into a generative AI model include, "Please tell me the main skills of Employee A based on the chat messages he has sent over the past month," and "Please analyze the work logs of Robot A over the past month and tell me what tasks he is good at and how well he performed."

[1541] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1542] Step 1:

[1543] The server collects employee email data, chat data, and documents. This includes periodically retrieving email data from an email server using the SMTP protocol and collecting data from chat tools (e.g., Slack) and document management systems (e.g., Google Drive) via APIs. The input data is email, chat messages, and document files, and the output is saved in data storage after being converted to text format.

[1544] Step 2:

[1545] The server processes the collected data and analyzes it using a generative AI model. This analysis includes extracting keywords and phrases using natural language processing (NLP) techniques. For example, a Python script is used to invoke a generative model (e.g., GPT-3) to extract important words and phrases within the text. The input data is the text data collected and saved in step 1, and the output is the analyzed keywords and phrases.

[1546] Step 3:

[1547] The server categorizes the analysis results provided by the generative AI model for each employee and registers their skill sets and job descriptions in a database. During this process, the data is organized into categories based on each employee's email address and chat ID and saved in a cloud database. The input data is the analysis results obtained in step 2, and the output is each employee's skill set and job description.

[1548] Step 4:

[1549] The server then reflects the registered skill sets and work details in a visualization tool. This involves using a graphical interface to display each employee's skill set and work history in dashboard format. For example, data visualization is performed using Tableau or Power BI. The input data are the skill sets and work details registered in the database, and the output is a visually displayed dashboard.

[1550] Step 5:

[1551] Users (employees) can check their own skill sets and work history through the visualization tool and provide corrections or additional feedback as needed. The input data is the feedback from the user, and the output is the updated skill sets and work content.

[1552] Step 6:

[1553] The server receives feedback from employees and updates their skill sets and work history in the database. This involves modifying the database in real time and keeping the information in the visualization tool up to date. The input data is the feedback provided in step 5, and the output is the updated database and visualization tool.

[1554] Step 7:

[1555] The server collects and analyzes the robot's work logs to extract the robot's skill set and work content. This involves acquiring data from IoT sensors and logging systems used in the factory. The input data is the robot's work logs, and the output is the analyzed robot's skill set.

[1556] Step 8:

[1557] The server classifies the analysis results by robot and registers the robot's skill set and work content in a database. The input data are the analysis results obtained in step 7, and the output is the skill set and work content for each robot.

[1558] Step 9:

[1559] The server reflects the registered robot's skill set in the visualization tool and displays it graphically. This allows managers to understand at a glance the robot's specialties and performance. The input data is the robot's skill set registered in the database, and the output is a visual dashboard.

[1560] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1561] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this information in a visualization tool.

[1562] 1. Data Collection

[1563] Server: The first step the system takes is to periodically collect data from the email server, chat tool, and document management system used by employees. For example, it collects sent and received email data from the email server, message logs from the chat tool, and created document files from the document management system. This data is converted into text format and saved in data storage.

[1564] 2. Data Analysis

[1565] Generative AI: Collected data is analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases, such as skills and job descriptions like "project management," "data analysis," and "Python."

[1566] Emotion engine: Furthermore, the emotion engine recognizes the user's emotions from the analyzed data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[1567] Server: The analysis results provided by the generative AI and emotion engine are categorized and organized by employee, allowing each employee's skill set, job duties, and emotional state to be identified and registered in a database.

[1568] 3. Information Registration

[1569] Server: The analyzed information is registered in a database for each employee. The database centrally manages employees' skill sets, work history, and emotional states. For example, the database entry for "Yamada Taro" will record his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[1570] 4. Visualization of information

[1571] Server: The information in the database is reflected in the visualization tool. The visualization tool uses a graphical interface to make it easy for other employees and managers to view the information. For example, Yamada Taro's skill set, job duties, and current emotional state (stress level, etc.) are displayed in dashboard format.

[1572] 5. Feedback and Updates

[1573] Users (employees): Through visualization tools, they can check their own skill sets, work history, and emotional state, and provide corrections or additional feedback as needed. For example, they can provide feedback to Taro Yamada to add the new skill "JavaScript."

[1574] Server: The server receives feedback from employees and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[1575] 6. Utilizing Emotional Data

[1576] Server: Evaluates workload and stress levels based on emotional data obtained from users. Based on this evaluation, the health and work status of employees is understood, and appropriate feedback and suggestions for improvement are provided.

[1577] Specific working example:

[1578] For example, if emotional data indicates that Yamada Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[1579] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[1580] Through this series of processes, the system automatically grasps and visualizes employee skills, work content, and emotional state, making it possible to improve the efficiency of human resource management, optimize staff allocation, and support employee health management, which is expected to improve productivity and employee satisfaction across the company.

[1581] The processing flow will be explained below.

[1582] Step 1: Collect data

[1583] Server: Regularly accesses each employee's email server, chat tool, and document management system to collect data. This includes the ability to automatically retrieve required data using APIs.

[1584] Specific behavior:

[1585] The server logs in to the email server and retrieves emails sent or received within the past 24 hours, converts the retrieved emails into text format, and stores them in the specified data storage.

[1586] The server uses the chat tool's API to obtain message logs for channels that employees are participating in. The obtained logs are converted into text format and saved.

[1587] The server accesses the document management system to retrieve documents created or shared by employees, extracts text from the documents, and stores it.

[1588] Step 2: Analyze the data

[1589] Generative AI: Analyzes collected email, chat, and document data and uses natural language processing techniques to extract keywords and important phrases.

[1590] Specific behavior:

[1591] The acquired data is segmented and morphologically analyzed, and a language model is applied to understand the context.

[1592] Keywords related to the job content and skills (e.g., "project management," "Python," "data analysis") are extracted from each sentence.

[1593] Calculate keyword relevance and identify important phrases.

[1594] Emotion Engine: Analyzes the collected data to recognize the user's emotions. This process involves analyzing, for example, the tone and style of writing.

[1595] Specific behavior:

[1596] Classify emotions such as positive, negative, and neutral from the content of emails and chats.

[1597] For example, phrases such as "tired" and "troubled" are recognized as negative emotions.

[1598] The recognized emotional data is organized and stored as the employee's emotional state.

[1599] Step 3: Categorize and organize information

[1600] Server: Based on the analysis results provided by the generative AI and emotion engine, classifies each employee's skill set, job content, and emotional state.

[1601] Specific behavior:

[1602] Extracted keywords and phrases are mapped to templates based on skills and job duties.

[1603] Classifying sentiment data into categories such as positive, negative, and neutral.

[1604] The classified information is registered in a database as a profile for each employee.

[1605] Step 4: Register your information

[1606] Server: Registers classified skill sets, job duties, and emotional states in a database for each employee.

[1607] Specific behavior:

[1608] Create a profile for each employee and enter the necessary skills, work history, and emotional state.

[1609] The registered information is stored in a database so that updated information is reflected immediately.

[1610] Step 5: Reflecting on visualization tools

[1611] Server: Based on the information in the database, the visualization tool is updated. The visualization tool uses a graphical interface to allow employees and managers to easily view the information.

[1612] Specific behavior:

[1613] The latest information is retrieved from the database and the visualization tool dashboard is updated.

[1614] Visually display each employee's skill set, job duties, and emotional state in graphs and charts.

[1615] Step 6: Feedback and Updates

[1616] Users (employees): Through the visualization tool, they can check their own profile and provide feedback as needed. The feedback is sent to the system and the information in the database is updated.

[1617] Specific behavior:

[1618] Employees use visualization tools to identify their skill sets, job duties, and emotional state.

[1619] Suggest adding new skills or modifying job descriptions and send feedback to the system.

[1620] Based on the feedback received by the server, the information in the database is updated and reflected in the visualization tool.

[1621] Step 7: Use emotion data

[1622] Server: Evaluates workload and stress levels based on emotional data obtained from users. The results of this evaluation are used to improve employee health and work efficiency.

[1623] Specific behavior:

[1624] Emotional data is used to assess employee stress levels and create reports to help balance work.

[1625] If high stress levels are detected, the system will automatically send notifications suggesting appropriate rest or task reallocation.

[1626] Visualize the emotional state of the entire team and help managers adjust workload imbalances appropriately.

[1627] This series of processing steps automatically grasps and visualizes employee skills, work content, and emotional state, enabling efficient human resource management, optimal allocation, and employee health management. As a result, improvements in productivity and employee satisfaction across the entire company can be expected.

[1628] Example 2

[1629] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1630] Conventional employee management systems struggled to efficiently collect and analyze a wide range of data, including email, chat, and documents, and to centrally understand employees' skill sets, work content, and emotional state. This made it difficult to properly evaluate employees' workloads and stress levels and provide optimal feedback and suggestions for improvement. Furthermore, there was a lack of visualization methods for displaying collected data in an easy-to-understand manner, making it difficult for employees and managers to easily check the information. Furthermore, few systems allowed for dynamic updating of data based on employee feedback.

[1631] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1632] In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for preprocessing the collected email data, chat data, and documents; means including a generation AI for analyzing the preprocessed data and extracting keywords and phrases; means including an emotion engine for recognizing employee emotions from the analyzed data; means for classifying the extracted keywords, phrases, and emotional states and identifying employee skill sets, job content, and emotional states; means for registering the identified skill sets, job content, and emotional states in a database for each employee; and means for reflecting the registered skill sets, job content, and emotional states in a visualization tool. This enables a unified understanding of employee skills, job content, and emotional states and a visually easy-to-understand display. Furthermore, the database can be dynamically updated based on feedback from employees, enabling business management and improvement proposals based on the latest information.

[1633] "Email data" refers to digital information including the content, metadata, and attachments of emails sent and received by employees.

[1634] "Chat data" refers to digital information including messages exchanged on chat tools used by employees and their metadata (such as time of sending, sender, recipient, and chat room information).

[1635] "Documents" are digital files such as text files, spreadsheets, presentations, and PDF documents that employees create or manage.

[1636] "Preprocessing" refers to processes such as data cleansing, format conversion, and normalization to convert collected raw data into a format that is easy to analyze.

[1637] "Generative AI" is an artificial intelligence system that uses natural language processing technology to automatically extract keywords and important phrases from text data.

[1638] The "Emotion Engine" is a machine learning-based system for analyzing and classifying employees' emotional states (e.g., stress levels, satisfaction, etc.) from text data.

[1639] A "skill set" is information that lists the work-related skills, knowledge, and techniques possessed by a particular employee.

[1640] "Job content" refers to information about the tasks and projects that employees perform on a daily basis, as well as the general duties they are responsible for.

[1641] "Emotional state" is information that indicates an employee's psychological state and emotional movements (for example, stress, satisfaction, fatigue, etc.).

[1642] The "database" is a digital data storage system that collects, analyzes, and organizes each employee's skill set, job content, and emotional state for centralized management.

[1643] A "visualization tool" is a graphical interface that visually displays information in a database, allowing employees and managers to easily view and analyze it.

[1644] "Feedback" is information that employees provide to the system regarding corrections or additions to their skill sets or job duties.

[1645] This invention relates to a system that collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using generative AI and an emotion engine, extracts employees' work content, skills, and emotional state, and reflects this in a visualization tool.

[1646] Data collection and preprocessing

[1647] Server: First, the server collects data from email servers (e.g., Gmail), chat tools (e.g., Slack), and document management systems (e.g., Google Drive) used by employees. This data is periodically obtained using APIs or protocols. It collects sent and received email data from email servers, message logs from chat tools, and created document files from document management systems. The collected data is then converted into text format and stored in data storage.

[1648] Data analysis

[1649] Preprocessing: The server performs preprocessing to convert the collected data into a format suitable for analysis, such as removing boilerplate text, removing HTML tags, and standardizing dates and timestamps.

[1650] Generative AI: The pre-processed data is then analyzed by generative AI, which uses natural language processing techniques to extract keywords and key phrases from the text data. For example, it identifies skills and job descriptions such as "project management," "data analysis," and "Python."

[1651] Emotion engine: The emotion engine recognizes emotional states from analyzed text data. For example, it identifies emotional states such as "high stress" or "satisfied" from the context of emails or chats.

[1652] Organizing and registering information

[1653] Server: The server categorizes and organizes the analysis results provided by the generative AI and emotion engine for each employee. This identifies each employee's skill set, job description, and emotional state, and registers them in the database. For example, the database entry for "Employee Taro" includes his skills such as "project management," "Python," and "data analysis," as well as information such as his recent emotional state of "high stress."

[1654] Information visualization

[1655] Server: The server uses the information in the database to display the visualization tool. The visualization tool uses a graphical interface and is designed to make it easy for other employees and managers to view information. For example, Taro's skill set, job description, and current emotional state are displayed in dashboard format.

[1656] Feedback and Updates

[1657] User (employee): Through the visualization tool, users can check their own skill sets, work history, and emotional state, and provide feedback as needed. For example, they can provide feedback to Taro to add the new skill "JavaScript."

[1658] Server: The server receives feedback from users and updates the database with information on skills, work history, and emotions. Based on this feedback, the information in the visualization tool is also updated in real time.

[1659] Utilizing Emotional Data

[1660] Server: The server evaluates the workload and stress level based on the emotional data obtained from the user. Based on this evaluation, the server grasps the employee's health and work situation and provides appropriate feedback and suggestions for improvement.

[1661] Specific working example:

[1662] If emotional data indicates that Taro's stress level is high, the system will automatically send feedback and suggest appropriate rest or task reallocation.

[1663] The visualization tool also visualizes the emotional state of the entire team, allowing managers to appropriately adjust workload imbalances.

[1664] Example of an input prompt for a generative AI model:

[1665] "Extract employee skill sets and job descriptions from the following text data, and analyze their emotional state. The text data is as follows: 'Today, we had a project management meeting. We also performed data analysis using Python. It seems that the employee is a little stressed.'"

[1666] As described above, the present invention makes it possible to grasp employee skills, work content, and emotional state in a unified manner and display them in a visually easy-to-understand manner. Furthermore, by receiving feedback from employees and dynamically updating the database, work management and improvement proposals can be made based on the latest information.

[1667] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1668] Step 1: Data collection

[1669] Servers: Periodically collect data from email servers, chat tools, and document management systems used by employees. Specific actions include:

[1670] Email Data Collection: Uses the Gmail API to retrieve inbound and outbound email data from employee mailboxes.

[1671] Input: Email data obtained from the Gmail API

[1672] Output: Acquired email data (sending / receiving history, email body, attachments, etc.)

[1673] Chat data collection: Use the Slack API to obtain message logs between employees.

[1674] Input: Chat messages retrieved through the Slack API

[1675] Output: Acquired chat data (message content, chat room information, timestamp, etc.)

[1676] Document data collection: Use the Google Drive API to obtain document files created by employees.

[1677] Input: Document data retrieved from the Google Drive API

[1678] Output: Retrieved document data (file name, file contents, metadata, etc.)

[1679] Step 2: Data Preprocessing

[1680] Server: Converts collected data into a format suitable for analysis. Specific operations include:

[1681] Text normalization: Removes HTML tags and special characters from collected text data to make the text clean.

[1682] Input: Collected raw data (email data, chat data, document data)

[1683] Output: Clean text data

[1684] Cleaning: Removes boilerplate and unnecessary header information, producing pure text information for analysis.

[1685] Input: clean text data

[1686] Output: Text data with unnecessary information removed

[1687] Format conversion: Convert dates and timestamps into a unified format.

[1688] Input: Text data with unnecessary information removed

[1689] Output: Text data converted into an easy-to-parse format

[1690] Step 3: Data analysis

[1691] Generative AI and Emotion Engine: Analyzes pre-processed data to extract employee skills and emotional states. Specific actions include:

[1692] Keyword extraction: Generative AI uses natural language processing techniques to extract keywords and key phrases from text data.

[1693] Input: Text data converted into an easy-to-parse format

[1694] Output: Extracted keywords and significant phrases

[1695] Sentiment analysis: The emotion engine analyzes employee emotions from text data and identifies emotional states such as "high stress" or "satisfied."

[1696] Input: Text data converted into an easy-to-parse format

[1697] Output: Parsed emotional state information

[1698] Step 4: Organize and register information

[1699] Server: Classifies and organizes the analysis results provided by the generative AI and emotion engine for each employee. Specific operations include:

[1700] Data classification: Based on each employee's information (e.g., "Employee Taro"), associate their skill set, job duties, and emotional state.

[1701] Input: extracted keywords and key phrases, parsed emotional state information

[1702] Output: Organized information for each employee

[1703] Database registration: Classified information is registered in a database for each employee.

[1704] Input: Organized information for each employee

[1705] Output: Skill sets, job descriptions, and emotional states registered in the database

[1706] Step 5: Visualize the information

[1707] Server: Reflects the information in the database to the visualization tool. This includes the following specific operations:

[1708] Extraction and display of information: The registered information is reflected in visualization tools such as dashboards and displayed visually.

[1709] Input: Information registered in the database

[1710] Output: Visualized data (e.g., dashboard display)

[1711] Step 6: Feedback and Updates

[1712] User (employee) and server: User provides feedback and server updates the database. Specific actions include:

[1713] User feedback: Users use the visualization tool to input corrections and additions to their information.

[1714] Input: User feedback information (e.g. "Add JavaScript skills")

[1715] Output: Feedback data

[1716] Database Update: The server receives the feedback data and updates the database in real time.

[1717] Input: Feedback data

[1718] Output: Updated database information

[1719] Step 7: Leverage sentiment data

[1720] Server: Based on the analyzed emotional data, it evaluates workload and stress levels and suggests appropriate actions. Specific actions include:

[1721] Emotional assessment: Analyze collected emotional data to assess workload and stress levels.

[1722] Input: Parsed emotion data

[1723] Output: Evaluation results (stress level and workload status)

[1724] Action proposal: Based on the evaluation results, we propose appropriate feedback and task redistribution to employees.

[1725] Input: Evaluation result

[1726] Output: Suggested feedback and / or actions

[1727] Through these steps, the system will be able to grasp and visualize employee skills, work content, and emotional state in a unified manner, and dynamically update them based on feedback. This process is expected to improve productivity and employee satisfaction across the company.

[1728] (Application example 2)

[1729] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1730] There is a need for a system that can grasp the work content and skill sets of robots working in factories in real time, and manage the appropriate work allocation and health status. Conventional methods require humans to check the robot's work status and abnormal conditions one by one, which reduces work efficiency and makes it difficult to respond to abnormalities in real time. In addition, there is an issue that accurate management is not possible due to insufficient detailed analysis and visualization of the robot's work content.

[1731] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting employee email data; means for collecting employee chat data; means for collecting documents created by employees; means for analyzing the collected email data, chat data, and documents to extract important keywords and phrases; means for classifying the extracted keywords and phrases and identifying the employee's ability set and job content; means for registering the identified ability set and job content in a database for each employee; and means for reflecting the registered ability set, job content, and emotional state in a visualization tool and displaying it via a head-mounted display. This makes it possible to monitor and manage the work content and abnormal conditions of robots in a factory in real time, thereby improving work efficiency and enabling appropriate abnormality responses.

[1732] A head-mounted display is a device used to display images in front of the wearer's eyes, allowing the user to obtain visual information in real time.

[1733] Emotional state refers to the mental state of employees and robots, such as stress levels and satisfaction, analyzed from collected data.

[1734] A visualization tool is a tool that displays data using a graphical interface to make information intuitively easy to understand.

[1735] A capability set refers to the skills and expertise possessed by employees or robots, as well as the specific work tasks that are extracted through analysis.

[1736] A database is a data storage system that stores collected data in an organized manner and manages it so that it can be used for later retrieval and analysis.

[1737] Keywords and phrases are important words and sentences that indicate specific skills or job content and are extracted by generative AI from collected data.

[1738] An employee is someone who is part of a company or organization that uses this system and who uses email, chat tools, and document management systems for daily work and communication.

[1739] This invention is a system that can grasp the work content, skill sets, and emotional states of robots working in factories in real time, and then allocate tasks appropriately and manage their health. This system collects data from email, chat tools, and document management systems used daily by employees, analyzes this data using a generative AI model and emotion engine, and then reflects it in a visualization tool. Managers can also access information in real time using a head-mounted display.

[1740] Hardware configuration

[1741] The server includes a means for periodically collecting data from the email server, chat tool, and document management system, and also includes data storage for saving the collected data.

[1742] The head-mounted display is a device that displays images in front of the manager's eyes, allowing the manager to visually check the robot's work content and emotional state in real time.

[1743] Software configuration

[1744] Generative AI models and sentiment engines are used to analyze collected data and extract key keywords, phrases, and emotional states. Specifically, they leverage natural language processing techniques to identify skill sets and job roles, and perform sentiment analysis.

[1745] A visualization tool is software that displays analyzed data in a graphical interface, making it easier for managers to intuitively understand the information.

[1746] Data collection and analysis

[1747] The server first collects data from email servers, chat tools, and document management systems. This data is converted into text format and stored in data storage. The generative AI model then uses natural language processing technology to extract important keywords and phrases, and the emotion engine recognizes emotional states from the analyzed data. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," as well as emotional states such as "high stress." The results of this analysis are classified for each employee and robot and registered in a database.

[1748] Data visualization and feedback

[1749] The registered data is displayed in a graphical interface using a visualization tool, and managers can check the information in real time via a head-mounted display. This allows managers to immediately understand the robot's work content and emotional state and give instructions on work allocation or rest as necessary. For example, if the robot is in a state of high stress, the system will send a notification and suggest appropriate rest or task reallocation.

[1750] Specific examples

[1751] By using this system, it is possible to improve the work efficiency of robots in factories. For example, by inputting prompt statements such as "Leader, how is today's work progress? Please analyze the skill set and emotional state based on chat history, email content, and document content, visualize them, and report them to us. For example, we would like to obtain information such as, 'Robot operation skills have improved, but stress levels are rising,'" into the generative AI model, detailed analysis results can be obtained. This enables appropriate work management and efficiency in real time.

[1752] In summary, the present invention realizes improved work efficiency and health management by understanding the work content and emotional state of robots in a factory in real time and taking appropriate measures.

[1753] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1754] Step 1:

[1755] The data collection server periodically collects data from email servers, chat tools, and document management systems. It handles raw data collected from each system's API as input. This data is converted to text format and stored in data storage. For example, it collects emails, chat logs, and document files from the past 24 hours at 9:00 a.m. every day.

[1756] Step 2:

[1757] The data analysis server analyzes the collected email data, chat data, and documents using a generative AI model and emotion engine. The text data collected in step 1 is used as input. The generative AI model uses natural language processing techniques to extract keywords and important phrases, and the emotion engine analyzes emotional states. For example, it identifies skill sets such as "robot operation skills" and "fault response skills," and emotional states such as "high stress."

[1758] Step 3:

[1759] Data Classification and Registration The server classifies the data based on the analysis results obtained from the generative AI model and emotion engine, and registers it in a database for each employee and robot. The analysis results are used as input. The skill set, job content, and emotional state of each employee and robot are stored in the database as output. For example, information such as "Employee A" having high "robot operation skills" and low "stress level" is registered in the database.

[1760] Step 4:

[1761] Data visualization: The server generates a graphical interface using a visualization tool based on the information in the database. As input, it uses the skill sets and emotional states registered in the database. As output, it generates visual information that is displayed in real time through a head-mounted display. For example, a manager can wear the head-mounted display and check employee A's "robot operation skills" and "stress level."

[1762] Step 5:

[1763] Real-time feedback The user (manager) checks the visualized information and provides feedback as necessary. As input, the user checks the information displayed on the head-mounted display. As output, the feedback content is sent to the server and the database is updated. For example, if employee A is feeling stressed, the manager can reallocate tasks or instruct him or her to take a break.

[1764] Step 6:

[1765] Reflecting Feedback The server receives feedback from the user and modifies or adds information to the database. As input, it uses the feedback information from the administrator. As output, the updated skill set and emotional state are reflected in the database. For example, "JavaScript" is added as a new skill set, and the stress level is adjusted appropriately.

[1766] This series of processes makes it possible to grasp the work content and emotional state of robots in the factory in real time, allowing for appropriate work allocation and health management.

[1767] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1768] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1769] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1770] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1771] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1772] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1773] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1774] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1775] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1776] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1777] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1778] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1779] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1780] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1781] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1782] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1783] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1784] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1785] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1786] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1787] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1788] The following is further disclosed regarding the above embodiment.

[1789] (Claim 1)

[1790] a means of collecting employee email data;

[1791] A means of collecting employee chat data;

[1792] A means of collecting documents created by employees;

[1793] means for analyzing the collected email data, chat data, and documents to extract keywords and phrases;

[1794] A mean...

Claims

1. a means of collecting employee email data; A means of collecting employee chat data; A means of collecting documents created by employees; means for analyzing the collected email data, chat data, and documents to extract keywords and phrases; A means of classifying extracted keywords and phrases to identify employee skill sets and job duties; A means of registering the identified skill sets and job duties in a database for each employee; A means to reflect the registered skill sets and work contents in the visualization tool, A system including:

2. 2. The system according to claim 1, further comprising means for displaying the skill sets and work contents registered in the database for each employee using a graphical interface when the skill sets and work contents are reflected in the visualization tool.

3. 10. The system of claim 1, further comprising means for receiving feedback from employees and modifying or adding skill sets and job descriptions registered in the database.

Images