system

Abstract

We provide the system. [Solution] A means of collecting information on the user's job title, department, area of ​​expertise, and years of experience, A means of analyzing training needs based on collected information, A means of generating training content based on analysis results, A means of delivering the generated training content to the user's device, A means of collecting user-generated feedback, A means of analyzing the collected feedback and using it to improve future training menus, A system that includes this.

Description

Technical Field

[0004] , , ,

[0005] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current training system, there is a problem that the training menu for administrative staff is insufficient. Specifically, while the training menu for private companies is rich, there is little content specialized for administrative staff. As a result, it is difficult for administrative staff to receive appropriate and efficient training. In such a situation, since the opportunity to receive training that meets the needs of administrative staff is limited, there is a problem that it is difficult to improve knowledge and skills.

Means for Solving the Problems

[0005] The system will include a means for collecting information on users' job titles, departments, areas of expertise, and years of experience. Based on this collected information, it will analyze training needs and provide a means for generating appropriate training content. The system will also include a means for delivering the generated training content to users' devices and for collecting user feedback. Furthermore, by introducing a means for analyzing the collected feedback and using it to improve future training menus, the system will ensure that effective training menus specifically tailored for government officials are provided.

[0006] "User data" refers to information such as the user's job title, department, area of ​​expertise, and years of experience.

[0007] "Means of collection" refers to the systems and processes for acquiring user data, transmitting it to a server, and storing it.

[0008] "Training needs" refer to the need for knowledge and skills that users should acquire, as identified based on user data.

[0009] "Means of analysis" refers to the process or system used to evaluate user needs and skill levels based on collected user data, and to select appropriate training content.

[0010] "Means of generation" refers to the system and process for creating optimal training content for users based on the analysis results.

[0011] "Training content" refers to educational materials such as documents, videos, texts, and quizzes that users use for learning.

[0012] "Means of distribution" refers to the system and process for sending the generated training content to the user's device.

[0013] "Terminal" refers to the device that a user uses to view training content.

[0014] "Feedback" refers to information for users to provide opinions and evaluations regarding training content.

[0015] "Means for collection (for feedback)" refers to a system and process for obtaining the feedback provided by users and transmitting it to the server.

[0016] "Means for analysis (for feedback)" refers to a process and system for evaluating the collected feedback and utilizing it for improving future training menus.

[0017] "Progress status" refers to information on the progress of users' learning and which training content has been completed and to what extent.

[0018] "Means for monitoring" refers to a system and process for continuously monitoring the progress status of users and recording the data.

[0019] "Log" refers to data that records users' activities and progress status in chronological order.

Brief Description of Drawings

[0020] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7]It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the language used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] This invention relates to a system that provides specialized training menus for government officials. This system, by incorporating the following key functions, enables a complete process from user data collection to training content generation, distribution, and feedback collection and analysis.

[0042] System-wide flow

[0043] 1. Collection of user data

[0044] The user logs into the device.

[0045] Users log in to the system using a terminal. Login information includes a user ID and password.

[0046] The device sends login information to the server.

[0047] The terminal sends the entered login information to the server. The server validates the login information and authenticates the user if successful.

[0048] Users enter their profile information.

[0049] Users enter profile information such as their job title, department, area of ​​expertise, and years of experience on their device.

[0050] The device sends profile information to the server.

[0051] The device sends the entered profile information to the server. The server receives the profile information and stores it in its database.

[0052] 2. Generating training content

[0053] The server analyzes user data.

[0054] The server analyzes the collected user profile information. The analysis identifies training needs based on the user's skill level and area of ​​expertise.

[0055] The server uses generative AI to generate training content.

[0056] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0057] The server organizes the training content that has been generated.

[0058] The generated training content is customized and organized based on user profiles. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[0059] 3. Content distribution

[0060] The server delivers training content to the terminals.

[0061] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[0062] Users view training content using their devices.

[0063] Users access training content using their devices. For example, a user might watch a video about "the latest trends in environmental policy."

[0064] The device collects user progress data.

[0065] The device monitors the user's learning progress and records it as a log. Progress data includes viewed training content and completed assignments.

[0066] 4. Gathering feedback

[0067] Users enter feedback on their devices.

[0068] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0069] The device sends feedback to the server.

[0070] The terminal sends the input feedback to the server. The server receives the feedback data and stores it in a database.

[0071] The server analyzes the feedback data.

[0072] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0073] Specific examples

[0074] The following are specific examples of how to use this system.

[0075] 1. Collection of user data

[0076] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[0077] 2. Generating training content

[0078] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[0079] 3. Content distribution

[0080] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[0081] 4. Gathering feedback

[0082] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[0083] In this way, this system can provide customized training menus for administrative staff through a series of processes.

[0084] The following describes the processing flow.

[0085] Step 1:

[0086] The user logs into the device.

[0087] Users access the system using a terminal and log in by entering their user ID and password.

[0088] Step 2:

[0089] The device sends login information to the server.

[0090] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[0091] Step 3:

[0092] The user enters their profile information.

[0093] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[0094] Step 4:

[0095] The device sends profile information to the server.

[0096] The device sends the entered profile information to the server, and the server stores this data in a database.

[0097] Step 5:

[0098] The server analyzes the user data.

[0099] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[0100] Step 6:

[0101] The server uses generative AI to generate training content.

[0102] The AI ​​on the server generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0103] Step 7:

[0104] The server organizes the training content that has been generated.

[0105] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[0106] Step 8:

[0107] The server delivers the training content to the terminals.

[0108] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[0109] Step 9:

[0110] Users view training content using their devices.

[0111] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[0112] Step 10:

[0113] The device collects user progress data.

[0114] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[0115] Step 11:

[0116] The user enters feedback on their device.

[0117] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0118] Step 12:

[0119] The device sends feedback to the server.

[0120] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[0121] Step 13:

[0122] The server analyzes the feedback data.

[0123] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0124] (Example 1)

[0125] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0126] Modern training programs for government officials often contain general content that doesn't align with individual job experience or specialization, making efficient and effective skill development difficult. Furthermore, insufficient feedback and progress tracking make it challenging to improve training programs and provide individualized support. To address these challenges, customized training content tailored to individual employees, along with continuous monitoring and improvement of training effectiveness, are necessary.

[0127] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0128] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; and means for generating training content based on the analysis results using a generative artificial intelligence model. This enables the automatic generation and distribution of training content optimized for each user's characteristics. Furthermore, the user's terminal includes means for distributing and displaying the generated training content to the user; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for recording the user's learning progress. This enables real-time monitoring of the user's progress and effective collection and analysis of feedback.

[0129] "Means for collecting information on the user's job title, department, area of ​​expertise, and years of experience" refers to an interface for users to input and transmit information related to their job duties, and communication means for transmitting this information to the server.

[0130] "Means for analyzing training needs based on collected information" refers to algorithms and analysis systems for analyzing collected user information and identifying the training required for each user.

[0131] "Means for generating training content based on analysis results using a generative artificial intelligence model" refers to an artificial intelligence system and related software tools for automatically generating training content according to the analysis results.

[0132] "Means for delivering and displaying generated training content on a user's device" refers to communication means and user interface for transmitting generated training content to a user's device and displaying and playing it back.

[0133] "Means of collecting user-generated feedback" refers to a form for users to input and submit feedback after training, and the means of communication for sending that feedback to the server.

[0134] "Means for analyzing collected feedback and using it to improve future training menus" refers to analytical systems and algorithms for analyzing collected feedback data and using the results to improve and optimize training programs.

[0135] "Means for recording user learning progress" refers to systems and related software tools for monitoring users' training progress and recording and retaining that data.

[0136] This invention relates to a system that provides specialized training menus for government officials. This system provides specific means for realizing a series of processes including user data collection, training content generation, content distribution, and feedback collection and analysis.

[0137] User data collection

[0138] The user logs into the device.

[0139] Users log in to the system by entering their user ID and password on their terminal. This login information is encrypted and sent from the terminal to the server. The server receives the login information, compares it with the database, and performs authentication.

[0140] Enter your profile information

[0141] Upon successful authentication, the user enters detailed profile information on their device, including their job title, department, area of ​​expertise, and years of experience. This information is also encrypted before being sent to the server and stored in the database.

[0142] Training content generation

[0143] User Data Analysis

[0144] The server analyzes the collected user profile information. Machine learning algorithms (e.g., k-means clustering) are used for the analysis to identify training needs based on the user's skill level and area of ​​expertise.

[0145] Use of generative AI

[0146] Based on the analysis results, training content is generated using a generative AI (for example, OpenAI's GPT-3). In this process, prompts are used to instruct the AI ​​on the content to be generated. For example, the prompt "Create a lecture on the latest trends in environmental policy" is input to the generative AI.

[0147] Organizing content

[0148] The generated training content is categorized and organized according to the user's skill level and area of ​​expertise. The content is tagged and customized using natural language processing tools (e.g., spaCy).

[0149] Content distribution

[0150] Distribution of training content

[0151] The server sends the generated customized training content to the terminal. The terminal prepares the received content for the user to view and access easily.

[0152] Viewing training content

[0153] Users view the generated training content through their devices. For example, they can watch a video on "Methods for Formulating Advanced Environmental Policies."

[0154] Gathering feedback and monitoring progress

[0155] Feedback Input

[0156] After completing the training, users enter feedback on their understanding and the usefulness of the content into their terminals. This feedback information is also encrypted before being sent to the server and stored in the database.

[0157] Record of progress

[0158] The device monitors the user's learning progress (e.g., viewed, not viewed, completed assignments) in real time and records it as a log. This information is also sent to the server periodically.

[0159] Feedback analysis

[0160] The server analyzes the collected feedback and extracts statistics and trends. The analysis results can be used to improve future training content and develop new training programs.

[0161] Specific example

[0162] For example, if a user enters profile information such as "Environmental Conservation Department, Section Chief, over 10 years of experience," this information is sent to the server and stored in the database. The server then sends prompts to the generative AI to generate training content such as "Methods for Formulating Advanced Environmental Policies" or "Building Regional Partnerships." An example of a prompt might be, "Please create a lecture on methods for formulating advanced environmental policies."

[0163] Thus, the present invention makes it possible to provide training menus optimized for individual administrative staff, enabling efficient and effective skill improvement.

[0164] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0165] Step 1:

[0166] The user enters their login information.

[0167] Input: User ID and password

[0168] Specific action: The user enters their user ID and password into the login form displayed on the device and clicks the login button.

[0169] Output: Encrypted login information is sent from the terminal to the server.

[0170] Step 2:

[0171] The device sends login information to the server.

[0172] Input: Encrypted login information

[0173] Specific operation: The terminal encrypts the login information using an encryption library (e.g., OpenSSL) and sends it to the server via the HTTPS protocol.

[0174] Output: The server receives the login information.

[0175] Step 3:

[0176] The server authenticates the login information.

[0177] Input: Received login information

[0178] Specific operation: The server checks the login information against the database, and if they match, generates a JWT token and sends it to the terminal. If authentication is successful, the server generates an authentication token and returns a login success response.

[0179] Output: Authentication token and login success response

[0180] Step 4:

[0181] Users enter their profile information.

[0182] Input: Profile information such as job title, department, area of ​​expertise, and years of experience.

[0183] Specific operation: The authenticated user enters profile information such as job title, department, area of ​​expertise, and years of experience into a form displayed on the device, and clicks the save button.

[0184] Output: Encrypted profile information is sent from the device to the server.

[0185] Step 5:

[0186] The device sends profile information to the server.

[0187] Input: Encrypted profile information

[0188] Specific operation: The device serializes the profile information in JSON format and sends it to the server via the HTTPS protocol.

[0189] Output: The server receives the profile information and saves it to the database.

[0190] Step 6:

[0191] The server analyzes user data.

[0192] Input: User profile information stored in the database

[0193] Specific operation: The server uses machine learning algorithms (e.g., k-means clustering) to analyze user profile information and identify the user's skill level and training needs.

[0194] Output: Analysis results identifying user skill levels and training needs

[0195] Step 7:

[0196] The server uses generative AI to generate training content.

[0197] Input: Analysis results and prompts

[0198] Specific operation: The server inputs a prompt message into a generative AI (e.g., OpenAI's GPT-3) and generates appropriate training content. For example, the prompt message might be "Please create a lecture on the latest trends in environmental policy."

[0199] Output: Generated training content

[0200] Step 8:

[0201] The server organizes the training content.

[0202] Input: Generated training content and analysis results

[0203] Specific operation: The server uses a natural language processing tool (e.g., spaCy) to customize and organize the generated training content based on the user's skill level.

[0204] Output: Customized training content

[0205] Step 9:

[0206] The server delivers the training content.

[0207] Input: Customized training content

[0208] Specific operation: The server uses a REST API to send customized training content to the device, and the device displays it to the user.

[0209] Output: Training content delivered to the device

[0210] Step 10:

[0211] Users view training content.

[0212] Input: Distributed training content

[0213] Specific actions: The user opens training content (e.g., videos, documents) in their device's browser and watches or learns from it.

[0214] Output: User training progress data

[0215] Step 11:

[0216] The device records the user's progress data.

[0217] Input: User's learning progress

[0218] Specific operation: The device logs the tasks it has viewed or completed and periodically sends this data to the server.

[0219] Output: Log of progress data sent to the server

[0220] Step 12:

[0221] Users enter feedback

[0222] Input: Feedback on understanding and usefulness of the training content.

[0223] Specific action: After the training is completed, the user enters their evaluation and comments into the feedback form on their device and clicks the submit button.

[0224] Output: Feedback information is sent from the terminal to the server.

[0225] Step 13:

[0226] The device sends feedback to the server.

[0227] Input: Feedback information

[0228] Specific operation: The terminal serializes the feedback information in JSON format and sends it to the server via the HTTPS protocol.

[0229] Output: The server receives the feedback information and saves it to the database.

[0230] Step 14:

[0231] The server analyzes the feedback data.

[0232] Input: Feedback information stored in the database

[0233] Specific operation: The server uses data analysis tools (e.g., pandas, scikit-learn) to analyze feedback data and extract trends and statistical information.

[0234] Output: Analyzed feedback information and improvement suggestion data

[0235] (Application Example 1)

[0236] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0237] It is crucial for field workers and engineers to receive training tailored to their position, area of ​​expertise, and years of experience. However, traditional training systems struggle to provide training optimized for individual users. Furthermore, the lack of real-time training content display and audio guidance makes consistent skill development difficult.

[0238] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0239] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for displaying the training content in real time and providing voice guidance through a robot interface. This enables the provision of an optimal training program based on the user's individual needs and real-time content delivery.

[0240] "Users" refer to field workers and engineers who use the system.

[0241] "Position" refers to the job title or position a user holds within an organization.

[0242] "Department" refers to the department within the specific organization to which the user belongs.

[0243] "Specialized field" refers to the area of ​​technology or knowledge that a user is particularly familiar with.

[0244] "Years of experience" refers to the length of time a user has been engaged in a specific job or role.

[0245] "Means of collection" refers to methods and devices for obtaining necessary information from users.

[0246] "Means for analyzing training needs" refers to methods and devices for identifying the training content that users require based on collected information.

[0247] "Means for generating training content" refers to methods and devices for creating appropriate training materials and teaching aids based on analysis results.

[0248] "Terminal" refers to a device used by a user, and includes personal computers, smartphones, and other similar devices.

[0249] "Means of distribution" refers to the methods and devices used to send the generated training content to the user's device.

[0250] "Feedback" refers to evaluations and opinions from users who have received training.

[0251] A "robot interface" refers to the user interface of a robot that displays training content and provides voice guidance.

[0252] "Real-time" refers to a situation where processing or display occurs immediately.

[0253] "Guidance" refers to providing users with instructions and information through audio or text.

[0254] The system of this invention provides specialized training programs for factory workers and engineers. The system's configuration and processing are described in detail below.

[0255] System Configuration

[0256] 1. Methods for collecting user data

[0257] The server collects information such as job title, department, area of ​​expertise, and years of experience entered by users (field workers and engineers) via their terminals. The collected information is stored in a database.

[0258] 2. Methods for analyzing training needs

[0259] The server analyzes the collected user data to identify training needs based on the user's skill level and area of ​​expertise. Data analysis algorithms are used for this analysis.

[0260] 3. Means of generating training content

[0261] The server uses a generation AI model based on the analysis results to generate appropriate training content. This generation process uses prompts to meet the user's specific needs.

[0262] 4. Means of delivering content

[0263] Through a robotic interface, the generated training content is displayed in real time on the user's device. Audio guidance is also used to provide users with specific procedures and information.

[0264] 5. Methods for collecting feedback

[0265] The robot interface collects user feedback after training and sends it to a server. The collected feedback is stored in a database and used to improve future training programs.

[0266] Hardware and software to use

[0267] Hardware:

[0268] Robot interface: Displays training content and provides audio guidance.

[0269] Device: A computer or smartphone used by the user.

[0270] Server: Runs AI models for data analysis and generation.

[0271] software:

[0272] Python: Implementation of a program and analysis algorithm for generating training content.

[0273] Request Library: Uses HTTP requests to send and receive data.

[0274] JSON: Used as a format for storing and sending / receiving data.

[0275] Generative AI model: Used to generate training content.

[0276] Specific example

[0277] The user inputs information such as "engineer," "production line," and "5 years of experience" into the terminal. The server receives and analyzes this information and sends prompt messages like the following to the generation model.

[0278] Example of a prompt

[0279] Please generate detailed training content for engineers on how to operate production line equipment.

[0280] Based on this prompt text, the generative AI model generates specific training content and delivers it to the user through the robot interface. For example, it provides a video explanation of "how to operate the new device" or real-time voice guidance. After that, the user inputs feedback after the training ends, which is utilized to improve the next training program.

[0281] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0282] Step 1:

[0283] The user logs in to the system from the terminal. At this time, the user ID and password are input and sent to the server. The server validates the input data and checks the authentication information. If the authentication is successful, the user can access the system.

[0284] Step 2:

[0285] The user inputs profile information on the terminal. This includes job title, department, field of expertise, number of years of experience, etc. The terminal sends this information to the server, and the server saves it in the database. The input information is saved in a structured format for later analysis.

[0286] Step 3:

[0287] The server analyzes the collected user profile information. In this analysis process, the training needs based on the user's skill level and field of expertise are identified. Algorithms are used to perform data processing and data calculations to identify the optimal training content for the user.

[0288] Step 4:

[0289] The server uses an AI model to generate training content based on the analysis results. The generation process involves inputting prompts tailored to the user's needs into the model to generate specific training content. For example, a prompt such as "Generate detailed training content on how to operate production line equipment for engineers" might be used.

[0290] Step 5:

[0291] The server delivers the generated training content to the terminal. The content is displayed in real time through a robotic interface, and audio guidance is provided. Users review and complete the training content on their terminal.

[0292] Step 6:

[0293] After the user completes the training, they enter feedback into the device. This feedback includes an evaluation of the training content and suggestions for improvement. The device then sends the feedback information to the server.

[0294] Step 7:

[0295] The server analyzes the collected feedback and stores it in a database. The analysis results are extracted as statistics and trends and used to improve future training menus and generate new training content.

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

[0297] The present invention is a system that provides a specialized training menu for administrative staff, and by combining an emotion engine that recognizes the emotions of users, it provides a more personalized training experience. This system has the following main functions: collecting user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing the emotional data of users.

[0298] Overall system flow

[0299] 1. Collection of user data

[0300] The user logs in to the terminal.

[0301] The user accesses the system using the terminal, enters the user ID and password, and logs in.

[0302] The terminal sends the login information to the server.

[0303] The terminal sends the login information entered by the user to the server, and the server validates the login information and authenticates the user if the authentication is successful.

[0304] The user enters profile information.

[0305] The user enters profile information such as their job position, department, field of expertise, and years of experience on the terminal.

[0306] The terminal sends the profile information to the server.

[0307] The terminal sends the entered profile information to the server, and the server saves it in the database.

[0308] 2. Generation of training content

[0309] The server analyzes the user data.

[0310] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[0311] The server uses generative AI to generate training content.

[0312] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0313] The server organizes the training content that has been generated.

[0314] The generated training content is customized and organized based on the user's profile. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[0315] 3. Content distribution

[0316] The server delivers training content to the terminals.

[0317] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[0318] Users view training content using their devices.

[0319] Users access training content using their devices. For example, they might watch a video about "the latest trends in environmental policy."

[0320] The device collects user progress data.

[0321] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[0322] 4. Gathering feedback

[0323] Users enter feedback on their devices.

[0324] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0325] The device sends feedback to the server.

[0326] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[0327] The server analyzes the feedback data.

[0328] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0329] 5. Introduction of an emotional engine

[0330] The device collects user sentiment data.

[0331] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[0332] The device sends emotional data to the server.

[0333] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[0334] The server analyzes the emotional data.

[0335] The server analyzes collected emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[0336] Adjusting training content based on emotional data

[0337] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[0338] Specific examples

[0339] The following are specific examples of how to use this system.

[0340] 1. Collection of user data

[0341] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[0342] 2. Generating training content

[0343] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[0344] 3. Content distribution

[0345] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[0346] 4. Gathering feedback

[0347] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[0348] 5. Introduction of an emotional engine

[0349] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[0350] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[0351] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The user logs into the device.

[0355] Users access the system using a terminal and log in by entering their user ID and password.

[0356] Step 2:

[0357] The device sends login information to the server.

[0358] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[0359] Step 3:

[0360] The user enters their profile information.

[0361] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[0362] Step 4:

[0363] The device sends profile information to the server.

[0364] The device sends the entered profile information to the server, which then stores it in a database.

[0365] Step 5:

[0366] The server analyzes the user data.

[0367] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[0368] Step 6:

[0369] The server uses generative AI to generate training content.

[0370] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0371] Step 7:

[0372] The server organizes the training content that has been generated.

[0373] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[0374] Step 8:

[0375] The server delivers the training content to the terminals.

[0376] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[0377] Step 9:

[0378] Users view training content using their devices.

[0379] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[0380] Step 10:

[0381] The device collects user progress data.

[0382] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[0383] Step 11:

[0384] The user enters feedback on their device.

[0385] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0386] Step 12:

[0387] The device sends feedback to the server.

[0388] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[0389] Step 13:

[0390] The server analyzes the feedback data.

[0391] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0392] Step 14:

[0393] The device collects user emotion data.

[0394] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[0395] Step 15:

[0396] The device sends emotional data to the server.

[0397] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[0398] Step 16:

[0399] The server analyzes the emotional data.

[0400] The server analyzes collected emotional data to evaluate the user's comfort level and learning effectiveness. This makes it possible to further improve the user's learning experience.

[0401] Step 17:

[0402] The server adjusts training content based on emotional data.

[0403] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[0404] Specific examples

[0405] 1. Collection of user data

[0406] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[0407] 2. Generating training content

[0408] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[0409] 3. Content distribution

[0410] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[0411] 4. Gathering feedback

[0412] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[0413] 5. Introduction of an emotional engine

[0414] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[0415] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[0416] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[0417] (Example 2)

[0418] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0419] Traditional training systems have struggled to provide training content that caters to the diverse needs and skill levels of individual users. Furthermore, the lack of a means to deliver personalized training experiences that consider user emotions hindered the improvement of training effectiveness. Additionally, insufficient post-training feedback and progress tracking made continuous improvement of training programs difficult.

[0420] In Example 2, the identification processing performed by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for collecting user emotion data; and means for analyzing the collected emotion data and using it to adjust the training content. This makes it possible to provide a personalized training experience based on the user's individual needs and emotions, thereby improving training effectiveness. Furthermore, it is possible to continuously improve the training menu based on the collected feedback and progress data.

[0421] "Users" refer to government officials who use the system to receive training, or those who perform corresponding duties.

[0422] A "terminal" refers to a computer or mobile device that a user uses to access a system.

[0423] A "server" refers to a central processing unit that performs tasks such as collecting and analyzing user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing sentiment data.

[0424] "Training content" refers to learning resources such as educational materials, videos, and documents generated based on the user's training needs.

[0425] "Feedback" refers to the opinions and evaluations that users provide after using training content.

[0426] "Emotional data" refers to information about a user's emotional state, collected from their facial expressions, voice, and other sources.

[0427] "Generative AI models" refer to artificial intelligence technologies (e.g., OpenAI GPT-3) that generate appropriate training content based on user data.

[0428] A "prompt" refers to the text of instructions or questions that are input to a generative AI model.

[0429] "Methods for analyzing training needs" refers to the process of identifying the most suitable training content for a given user based on collected user data.

[0430] "Methods for generating training content based on analysis results" refers to the process of creating training content based on analysis results using a generative AI model.

[0431] "Means of collecting user emotion data" refers to a function that recognizes emotions from the user's facial expressions and voice and collects that data.

[0432] "Means of analyzing collected emotional data and using it to adjust training content" refers to the process of analyzing collected emotional data to improve the suitability of training content according to the user's state.

[0433] This invention is a system that provides specialized training menus for government officials. This system collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user emotional data. By combining this with an emotional engine, it can provide a more personalized training experience.

[0434] The hardware required to implement the system includes terminals for user access (e.g., personal computers and smartphones), servers (cloud servers are also applicable), and input devices such as cameras and microphones for recognizing user emotions. The software includes generative AI models (e.g., OpenAI GPT-3), data analysis tools, database management systems, and emotion recognition software (e.g., Affectiva).

[0435] User data collection

[0436] Users access the system using a terminal and log in by entering their user ID and password. The login information is sent from the terminal to the server, which validates the login information and authenticates the user if authentication is successful. Subsequently, the user enters profile information such as their job title, department, area of ​​expertise, and years of experience into a form on the terminal, which sends this information to the server, and the server stores it in a database.

[0437] Training content generation

[0438] The server analyzes stored user profile information and uses a generative AI model (OpenAI GPT-3) to identify training needs based on the user's skill level and area of ​​expertise. For example, if the user is an employee of the environmental conservation department, training content will be generated that includes topics such as "the latest trends in environmental policy" and "how to cooperate with local residents." The generated content is customized based on the user's profile, including detailed explanations for beginners and high-level challenges for experienced users.

[0439] Example of a prompt:

[0440] "Please generate training content for a user who is a manager in the environmental conservation department, based on their more than 10 years of experience in developing advanced environmental policies."

[0441] Content distribution

[0442] The server delivers the generated customized training content to the terminal, which receives the content and prepares to display it to the user. The user uses the terminal to view the training content, for example, by watching a video on "Latest Trends in Environmental Policy." The terminal monitors the user's learning progress and records the viewed training content and completed assignments as logs. Based on this, the user's progress can be tracked.

[0443] Feedback collection and analysis

[0444] After completing a training session, users input feedback on their understanding and the usefulness of the content into a terminal. The terminal sends the input feedback to a server, which receives the feedback data and stores it in a database. The server analyzes the feedback data and extracts statistics and trends. The analysis results are used to improve future training menus and generate new training content.

[0445] Introducing an emotional engine

[0446] Emotion engines (such as Affectiva) collect emotional data from users' facial expressions and voice. For example, they capture a user's facial expressions with a camera while they are watching a video and analyze their emotions. The collected emotional data is sent to a server via the device, where it is analyzed to evaluate the user's comfort level and learning effectiveness. Based on the analysis results, the difficulty level and content of the training can be adjusted to make it more relaxing for the user.

[0447] In this way, the system provides customized training menus for government officials, realizing an optimal learning experience based on the individual needs and emotions of the users.

[0448] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0449] Step 1:

[0450] The user logs into the device.

[0451] The user accesses the system's login page and enters their user ID and password. The terminal then sends this login information to the server. The server receives this information and executes an authentication query against the database. If authentication is successful, the server initiates a session and issues an authentication token.

[0452] Input: User ID, Password

[0453] Output: Authentication token

[0454] Step 2:

[0455] The device sends login information to the server.

[0456] The entered user ID and password are sent from the device to the server. The server validates the received information and, if correct, returns an authentication token to the device.

[0457] Input: User ID, Password

[0458] Output: Authentication result, authentication token

[0459] Step 3:

[0460] The user enters their profile information.

[0461] After successful authentication, the user enters profile information such as job title, department, area of ​​expertise, and years of experience into the device.

[0462] Input: Position, Department, Specialty, Years of Experience

[0463] Output: Profile Information

[0464] Step 4:

[0465] The device sends profile information to the server.

[0466] Once the user's profile information is entered, the device sends it to the server. The server then stores the received information in its database.

[0467] Input: Profile Information

[0468] Output: Profile information stored in the database

[0469] Step 5:

[0470] The server analyzes the user data.

[0471] The server retrieves and analyzes user profile information stored in the database. This identifies training needs based on the user's skill level and area of ​​expertise.

[0472] Input: Profile information stored in the database

[0473] Output: Training needs analysis results

[0474] Step 6:

[0475] The server uses generative AI to generate training content.

[0476] The server inputs prompt text into a generative AI model (e.g., OpenAI GPT-3) based on the analysis results. The generative AI generates appropriate training content and returns the result to the server.

[0477] Input: Training needs analysis results

[0478] Output: Generated training content

[0479] Step 7:

[0480] The server organizes the training content that has been generated.

[0481] The server analyzes the generated training content and customizes it based on the user's profile. For example, it includes detailed content for beginners and high-level challenges for experienced users.

[0482] Input: Generated training content

[0483] Output: Customized training content

[0484] Step 8:

[0485] The server delivers the training content to the terminals.

[0486] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[0487] Input: Customized training content

[0488] Output: Training content delivered to the terminal

[0489] Step 9:

[0490] Users view training content using their devices.

[0491] Users view training content displayed on their devices and check videos and materials.

[0492] Input: Training content delivered to the device

[0493] Output: Viewed training content

[0494] Step 10:

[0495] The device collects user progress data.

[0496] While the user is viewing the training content, the device monitors the user's learning progress and records the content viewed and completed assignments as logs.

[0497] Input: User's learning progress information

[0498] Output: Progress data recorded as a log.

[0499] Step 11:

[0500] The user enters feedback on their device.

[0501] After the training is completed, users will enter feedback on their understanding of the content and its usefulness into a feedback form on their device.

[0502] Input: Feedback Information

[0503] Output: Input feedback

[0504] Step 12:

[0505] The device sends feedback to the server.

[0506] The feedback entered by the user is sent from the device to the server, and the server stores the feedback data in a database.

[0507] Input: Input feedback

[0508] Output: Feedback stored in the database

[0509] Step 13:

[0510] The server analyzes the feedback data.

[0511] The server retrieves and analyzes the stored feedback data. The analysis results will be used to improve future training menus and generate new content.

[0512] Input: Feedback stored in the database

[0513] Output: Feedback analysis results

[0514] Step 14:

[0515] The device collects user emotion data.

[0516] Emotion recognition software collects emotional data from the user's facial expressions and voice. For example, it captures the user's facial expressions with a camera while they are watching a video and analyzes their emotions.

[0517] Input: User's facial expressions, voice data

[0518] Output: Collected sentiment data

[0519] Step 15:

[0520] The device sends emotional data to the server.

[0521] The collected emotional data is sent from the device to the server, which then stores the data in a database.

[0522] Input: Collected emotional data

[0523] Output: Sentiment data stored in the database

[0524] Step 16:

[0525] The server analyzes the emotional data.

[0526] The server analyzes stored emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[0527] Input: Saved emotion data

[0528] Output: Sentiment data analysis results

[0529] Step 17:

[0530] We will adjust training content based on emotional data.

[0531] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[0532] Input: Sentiment data analysis results

[0533] Output: Adjusted training content

[0534] (Application Example 2)

[0535] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0536] While conventional training systems could provide personalized content based on users' job titles and areas of expertise, they had limitations in personalizing content that took into account users' psychological states and emotions. Furthermore, the lack of technology to collect and analyze emotional data and adjust training content in real time based on that data made it difficult to maximize user learning effectiveness.

[0537] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for recognizing the user's emotions; means for collecting and analyzing user emotion data; and means for adjusting the training content based on the user's emotion data. This makes it possible to adjust the training content in real time according to the user's psychological state and maximize the learning effect.

[0538] "Position" refers to a role or authority within an organization.

[0539] "Department" refers to a division within an organization that has specific duties or functions.

[0540] A "specialized field" refers to an area that focuses on a specific technology or knowledge.

[0541] "Years of experience" refers to the number of years a user has accumulated practical experience in their field of expertise or position.

[0542] "Training needs" refer to the training content and skill improvement requirements that users desire.

[0543] "Analysis" refers to the process of thoroughly examining collected information and deriving its meaning.

[0544] "Generation" means creating new training content based on the analysis results.

[0545] "Distribution" refers to sending the created training content to the user's device.

[0546] "Feedback" refers to the opinions, impressions, and evaluations provided by users.

[0547] "Means of recognizing emotions" refers to methods of detecting a user's psychological state and emotions from their facial expressions, voice, etc.

[0548] "Emotional data" refers to information about a user's emotional state, and includes data obtained through methods such as facial expression and voice analysis.

[0549] "Means of adjustment" refers to the process of changing the content and difficulty level of training materials based on collected and analyzed information.

[0550] "Real-time" means that processing and reactions occur almost simultaneously with real-world time.

[0551] The system of this invention collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user sentiment data in order to personalize training content.

[0552] The system uses the following main hardware and software components.

[0553] 1. User terminals: Devices used by users include smartphones, smart glasses, and head-mounted displays. These devices are used for data entry, content display, and sentiment data collection.

[0554] 2. Server: A central management system is required for analyzing user data, generating and distributing training content, analyzing feedback, and analyzing sentiment data. This server consists of various software modules that receive and analyze data from the user interface.

[0555] 3. Generative AI: Used to generate training content based on user data. The generative AI model is implemented in Python and creates customized training materials and assignments based on the user's profile data.

[0556] 4. Emotion Recognition Engine: Used to identify emotions from the user's facial expressions and voice. For example, it utilizes OpenCV (an open-source computer vision library) and machine learning models for emotion recognition (e.g., models trained using TENSORFLOW® or Keras).

[0557] Users access the system using a terminal and log in by entering their user ID and password. The terminal collects profile information such as the user's job title, department, area of ​​expertise, and years of experience, and sends it to the server. The server analyzes this data to identify the user's skill level and training needs, and generates training content using generative AI. The generated content is delivered to the terminal, and the user views it. The user's progress is monitored by the terminal and recorded as a log.

[0558] While users are using training content, cameras and microphones built into smart glasses or head-mounted displays analyze the user's facial expressions and voice in real time, collecting emotional data. The collected emotional data is sent to a server for analysis. This allows the training content to be adjusted to be more relaxing if the user is tense, or more challenging if they are focused.

[0559] As a concrete example, suppose a technician is wearing a head-mounted display and watching a training video on "advanced troubleshooting methods." At this time, an emotion recognition engine recognizes emotions such as "concentrating" or "being confused" in real time from the technician's facial expressions and voice while watching, and adjusts the training content accordingly.

[0560] For example, the following instructions can be given to a generative AI as a prompt:

[0561] "The user's area of ​​expertise is machine operation, with 5 years of experience, and their position is department leader. Please create training content that includes advanced troubleshooting methods within the basic operation manual."

[0562] This system allows engineers to have a more effective and personalized learning experience.

[0563] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0564] Step 1:

[0565] The terminal collects user data. The user logs into the terminal and enters information about their job title, department, area of ​​expertise, and years of experience. The terminal sends the entered user data to the server. The server then stores the user's profile information in a database.

[0566] Input: User ID and password, job title, department, area of ​​expertise, years of experience

[0567] Output: User profile information stored in the database

[0568] Step 2:

[0569] The server analyzes user data to identify training needs. The server analyzes user profile information stored in the database to identify the corresponding skill level and training needs. It then generates training content by inputting prompts into a generative AI model.

[0570] Input: User profile information stored in the database, prompt text

[0571] Data processing: Analysis of profile information and identification of training needs through the operation of AI models.

[0572] Output: User-optimized training content

[0573] Step 3:

[0574] The server generates training content and delivers it to the user's device. The server converts the generated content into a data format and sends it to the user's device. The device displays the received training content to the user, supporting their learning.

[0575] Input: Generated training content

[0576] Output: Training content delivered to the user's terminal.

[0577] Step 4:

[0578] The device monitors the user's progress and records it as a log. When the user views training content, the device collects progress data (viewed content and completed tasks) in real time and sends it to the server. The server stores this data in a database.

[0579] Input: User viewing and operation data

[0580] Data processing: Collection and organization of progress data

[0581] Output: Progress log saved in the database

[0582] Step 5:

[0583] The device collects user feedback and sends it to the server. After completing the training content, the user enters feedback on the device. The device sends this feedback data to the server, which stores it in a database.

[0584] Input: User-entered feedback data

[0585] Output: Feedback data stored in the database

[0586] Step 6:

[0587] The server analyzes the feedback data and uses it to improve future training programs. The server analyzes the collected feedback as statistics and trends, and uses the analysis results to obtain guidelines for improving future training content.

[0588] Input: Feedback data stored in the database

[0589] Data processing: Analysis of feedback data

[0590] Output: Guidelines for improving training menus based on analysis results

[0591] Step 7:

[0592] The emotion engine recognizes the user's emotions in real time. While viewing training content, the camera and microphone built into the device monitor the user's facial expressions and voice, collecting emotional data. The collected data is sent to a server, where the emotion recognition engine performs analysis.

[0593] Input: User's facial expressions and voice data

[0594] Data processing: Real-time emotional data analysis

[0595] Output: Analyzed sentiment data

[0596] Step 8:

[0597] The server adjusts training content based on emotional data. Based on collected and analyzed emotional data, the training content is adjusted in real time to ensure users learn most effectively. Specifically, if a user is feeling stressed, the content is changed to something more relaxing; if they are concentrating, it becomes more challenging.

[0598] Input: Analyzed sentiment data

[0599] Data processing: Adjusting training content based on emotional data

[0600] Output: Adjusted training content

[0601] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0602] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0603] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0604] [Second Embodiment]

[0605] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0606] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0607] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0608] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0609] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0610] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0611] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0612] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0613] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0614] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0615] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0616] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0617] This invention relates to a system that provides specialized training menus for government officials. This system, by incorporating the following key functions, enables a complete process from user data collection to training content generation, distribution, and feedback collection and analysis.

[0618] System-wide flow

[0619] 1. Collection of user data

[0620] The user logs into the device.

[0621] Users log in to the system using a terminal. Login information includes a user ID and password.

[0622] The device sends login information to the server.

[0623] The terminal sends the entered login information to the server. The server validates the login information and authenticates the user if successful.

[0624] Users enter their profile information.

[0625] Users enter profile information such as their job title, department, area of ​​expertise, and years of experience on their device.

[0626] The device sends profile information to the server.

[0627] The device sends the entered profile information to the server. The server receives the profile information and stores it in its database.

[0628] 2. Generating training content

[0629] The server analyzes user data.

[0630] The server analyzes the collected user profile information. The analysis identifies training needs based on the user's skill level and area of ​​expertise.

[0631] The server uses generative AI to generate training content.

[0632] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0633] The server organizes the training content that has been generated.

[0634] The generated training content is customized and organized based on user profiles. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[0635] 3. Content distribution

[0636] The server delivers training content to the terminals.

[0637] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[0638] Users view training content using their devices.

[0639] Users access training content using their devices. For example, a user might watch a video about "the latest trends in environmental policy."

[0640] The device collects user progress data.

[0641] The device monitors the user's learning progress and records it as a log. Progress data includes viewed training content and completed assignments.

[0642] 4. Gathering feedback

[0643] Users enter feedback on their devices.

[0644] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0645] The device sends feedback to the server.

[0646] The terminal sends the input feedback to the server. The server receives the feedback data and stores it in a database.

[0647] The server analyzes the feedback data.

[0648] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0649] Specific examples

[0650] The following are specific examples of how to use this system.

[0651] 1. Collection of user data

[0652] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[0653] 2. Generating training content

[0654] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[0655] 3. Content distribution

[0656] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[0657] 4. Gathering feedback

[0658] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[0659] In this way, this system can provide customized training menus for administrative staff through a series of processes.

[0660] The following describes the processing flow.

[0661] Step 1:

[0662] The user logs into the device.

[0663] Users access the system using a terminal and log in by entering their user ID and password.

[0664] Step 2:

[0665] The device sends login information to the server.

[0666] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[0667] Step 3:

[0668] The user enters their profile information.

[0669] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[0670] Step 4:

[0671] The device sends profile information to the server.

[0672] The device sends the entered profile information to the server, and the server stores this data in a database.

[0673] Step 5:

[0674] The server analyzes the user data.

[0675] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[0676] Step 6:

[0677] The server uses generative AI to generate training content.

[0678] The AI ​​on the server generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0679] Step 7:

[0680] The server organizes the training content that has been generated.

[0681] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[0682] Step 8:

[0683] The server delivers the training content to the terminals.

[0684] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[0685] Step 9:

[0686] Users view training content using their devices.

[0687] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[0688] Step 10:

[0689] The device collects user progress data.

[0690] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[0691] Step 11:

[0692] The user enters feedback on their device.

[0693] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0694] Step 12:

[0695] The device sends feedback to the server.

[0696] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[0697] Step 13:

[0698] The server analyzes the feedback data.

[0699] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0700] (Example 1)

[0701] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0702] Modern training programs for government officials often contain general content that doesn't align with individual job experience or specialization, making efficient and effective skill development difficult. Furthermore, insufficient feedback and progress tracking make it challenging to improve training programs and provide individualized support. To address these challenges, customized training content tailored to individual employees, along with continuous monitoring and improvement of training effectiveness, are necessary.

[0703] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0704] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; and means for generating training content based on the analysis results using a generative artificial intelligence model. This enables the automatic generation and distribution of training content optimized for each user's characteristics. Furthermore, the user's terminal includes means for distributing and displaying the generated training content to the user; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for recording the user's learning progress. This enables real-time monitoring of the user's progress and effective collection and analysis of feedback.

[0705] "Means for collecting information on the user's job title, department, area of ​​expertise, and years of experience" refers to an interface for users to input and transmit information related to their job duties, and communication means for transmitting this information to the server.

[0706] "Means for analyzing training needs based on collected information" refers to algorithms and analysis systems for analyzing collected user information and identifying the training required for each user.

[0707] "Means for generating training content based on analysis results using a generative artificial intelligence model" refers to an artificial intelligence system and related software tools for automatically generating training content according to the analysis results.

[0708] "Means for delivering and displaying generated training content on a user's device" refers to communication means and user interface for transmitting generated training content to a user's device and displaying and playing it back.

[0709] "Means of collecting user-generated feedback" refers to a form for users to input and submit feedback after training, and the means of communication for sending that feedback to the server.

[0710] "Means for analyzing collected feedback and using it to improve future training menus" refers to analytical systems and algorithms for analyzing collected feedback data and using the results to improve and optimize training programs.

[0711] "Means for recording user learning progress" refers to systems and related software tools for monitoring users' training progress and recording and retaining that data.

[0712] This invention relates to a system that provides specialized training menus for government officials. This system provides specific means for realizing a series of processes including user data collection, training content generation, content distribution, and feedback collection and analysis.

[0713] User data collection

[0714] The user logs into the device.

[0715] Users log in to the system by entering their user ID and password on their terminal. This login information is encrypted and sent from the terminal to the server. The server receives the login information, compares it with the database, and performs authentication.

[0716] Enter your profile information

[0717] Upon successful authentication, the user enters detailed profile information on their device, including their job title, department, area of ​​expertise, and years of experience. This information is also encrypted before being sent to the server and stored in the database.

[0718] Training content generation

[0719] User Data Analysis

[0720] The server analyzes the collected user profile information. Machine learning algorithms (e.g., k-means clustering) are used for the analysis to identify training needs based on the user's skill level and area of ​​expertise.

[0721] Use of generative AI

[0722] Based on the analysis results, training content is generated using a generative AI (e.g., OpenAI's GPT-3). In this process, prompts are used to instruct the AI ​​on the content to be generated. For example, the prompt "Create a lecture on the latest trends in environmental policy" is input to the generative AI.

[0723] Organizing content

[0724] The generated training content is categorized and organized according to the user's skill level and area of ​​expertise. The content is tagged and customized using natural language processing tools (e.g., spaCy).

[0725] Content distribution

[0726] Distribution of training content

[0727] The server sends the generated customized training content to the terminal. The terminal prepares the received content for the user to view and access easily.

[0728] Viewing training content

[0729] Users view the generated training content through their devices. For example, they can watch a video on "Methods for Formulating Advanced Environmental Policies."

[0730] Gathering feedback and monitoring progress

[0731] Feedback Input

[0732] After completing the training, users enter feedback on their understanding and the usefulness of the content into their terminals. This feedback information is also encrypted before being sent to the server and stored in the database.

[0733] Record of progress

[0734] The device monitors the user's learning progress (e.g., viewed, not viewed, completed assignments) in real time and records it as a log. This information is also sent to the server periodically.

[0735] Feedback analysis

[0736] The server analyzes the collected feedback and extracts statistics and trends. The analysis results can be used to improve future training content and develop new training programs.

[0737] Specific example

[0738] For example, if a user enters profile information such as "Environmental Conservation Department, Section Chief, over 10 years of experience," this information is sent to the server and stored in the database. The server then sends prompts to the generative AI to generate training content such as "Methods for Formulating Advanced Environmental Policies" or "Building Regional Partnerships." An example of a prompt might be, "Please create a lecture on methods for formulating advanced environmental policies."

[0739] Thus, the present invention makes it possible to provide training menus optimized for individual administrative staff, enabling efficient and effective skill improvement.

[0740] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0741] Step 1:

[0742] The user enters their login information.

[0743] Input: User ID and password

[0744] Specific action: The user enters their user ID and password into the login form displayed on the device and clicks the login button.

[0745] Output: Encrypted login information is sent from the terminal to the server.

[0746] Step 2:

[0747] The device sends login information to the server.

[0748] Input: Encrypted login information

[0749] Specific operation: The terminal encrypts the login information using an encryption library (e.g., OpenSSL) and sends it to the server via the HTTPS protocol.

[0750] Output: The server receives the login information.

[0751] Step 3:

[0752] The server authenticates the login information.

[0753] Input: Received login information

[0754] Specific operation: The server checks the login information against the database, and if they match, generates a JWT token and sends it to the terminal. If authentication is successful, the server generates an authentication token and returns a login success response.

[0755] Output: Authentication token and login success response

[0756] Step 4:

[0757] Users enter their profile information.

[0758] Input: Profile information such as job title, department, area of ​​expertise, and years of experience.

[0759] Specific operation: The authenticated user enters profile information such as job title, department, area of ​​expertise, and years of experience into a form displayed on the device, and clicks the save button.

[0760] Output: Encrypted profile information is sent from the device to the server.

[0761] Step 5:

[0762] The device sends profile information to the server.

[0763] Input: Encrypted profile information

[0764] Specific operation: The device serializes the profile information in JSON format and sends it to the server via the HTTPS protocol.

[0765] Output: The server receives the profile information and saves it to the database.

[0766] Step 6:

[0767] The server analyzes user data.

[0768] Input: User profile information stored in the database

[0769] Specific operation: The server uses machine learning algorithms (e.g., k-means clustering) to analyze user profile information and identify the user's skill level and training needs.

[0770] Output: Analysis results identifying user skill levels and training needs

[0771] Step 7:

[0772] The server uses generative AI to generate training content.

[0773] Input: Analysis results and prompts

[0774] Specific operation: The server inputs a prompt message into a generative AI (e.g., OpenAI's GPT-3) and generates appropriate training content. For example, the prompt message might be "Please create a lecture on the latest trends in environmental policy."

[0775] Output: Generated training content

[0776] Step 8:

[0777] The server organizes the training content.

[0778] Input: Generated training content and analysis results

[0779] Specific operation: The server uses a natural language processing tool (e.g., spaCy) to customize and organize the generated training content based on the user's skill level.

[0780] Output: Customized training content

[0781] Step 9:

[0782] The server delivers the training content.

[0783] Input: Customized training content

[0784] Specific operation: The server uses a REST API to send customized training content to the device, and the device displays it to the user.

[0785] Output: Training content delivered to the device

[0786] Step 10:

[0787] Users view training content.

[0788] Input: Distributed training content

[0789] Specific actions: The user opens training content (e.g., videos, documents) in their device's browser and watches or learns from it.

[0790] Output: User training progress data

[0791] Step 11:

[0792] The device records the user's progress data.

[0793] Input: User's learning progress

[0794] Specific operation: The device logs the tasks it has viewed or completed and periodically sends this data to the server.

[0795] Output: Log of progress data sent to the server

[0796] Step 12:

[0797] Users enter feedback

[0798] Input: Feedback on understanding and usefulness of the training content.

[0799] Specific action: After the training is completed, the user enters their evaluation and comments into the feedback form on their device and clicks the submit button.

[0800] Output: Feedback information is sent from the terminal to the server.

[0801] Step 13:

[0802] The device sends feedback to the server.

[0803] Input: Feedback information

[0804] Specific operation: The terminal serializes the feedback information in JSON format and sends it to the server via the HTTPS protocol.

[0805] Output: The server receives the feedback information and saves it to the database.

[0806] Step 14:

[0807] The server analyzes the feedback data.

[0808] Input: Feedback information stored in the database

[0809] Specific operation: The server uses data analysis tools (e.g., pandas, scikit-learn) to analyze feedback data and extract trends and statistical information.

[0810] Output: Analyzed feedback information and improvement suggestion data

[0811] (Application Example 1)

[0812] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0813] It is crucial for field workers and engineers to receive training tailored to their position, area of ​​expertise, and years of experience. However, traditional training systems struggle to provide training optimized for individual users. Furthermore, the lack of real-time training content display and audio guidance makes consistent skill development difficult.

[0814] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0815] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for displaying the training content in real time and providing voice guidance through a robot interface. This enables the provision of an optimal training program based on the user's individual needs and real-time content delivery.

[0816] "Users" refer to field workers and engineers who use the system.

[0817] "Position" refers to the job title or position a user holds within an organization.

[0818] "Department" refers to the department within the specific organization to which the user belongs.

[0819] "Specialized field" refers to the area of ​​technology or knowledge that a user is particularly familiar with.

[0820] "Years of experience" refers to the length of time a user has been engaged in a specific job or role.

[0821] "Means of collection" refers to methods and devices for obtaining necessary information from users.

[0822] "Means for analyzing training needs" refers to methods and devices for identifying the training content that users require based on collected information.

[0823] "Means for generating training content" refers to methods and devices for creating appropriate training materials and teaching aids based on analysis results.

[0824] "Terminal" refers to a device used by a user, and includes personal computers, smartphones, and other similar devices.

[0825] "Means of distribution" refers to the methods and devices used to send the generated training content to the user's device.

[0826] "Feedback" refers to evaluations and opinions from users who have received training.

[0827] A "robot interface" refers to the user interface of a robot that displays training content and provides voice guidance.

[0828] "Real-time" refers to a situation where processing or display occurs immediately.

[0829] "Guidance" refers to providing users with instructions and information through audio or text.

[0830] The system of this invention provides specialized training programs for factory workers and engineers. The system's configuration and processing are described in detail below.

[0831] System Configuration

[0832] 1. Methods for collecting user data

[0833] The server collects information such as job title, department, area of ​​expertise, and years of experience entered by users (field workers and engineers) via their terminals. The collected information is stored in a database.

[0834] 2. Methods for analyzing training needs

[0835] The server analyzes the collected user data to identify training needs based on the user's skill level and area of ​​expertise. Data analysis algorithms are used for this analysis.

[0836] 3. Means of generating training content

[0837] The server uses a generation AI model based on the analysis results to generate appropriate training content. This generation process uses prompts to meet the user's specific needs.

[0838] 4. Means of delivering content

[0839] Through a robotic interface, the generated training content is displayed in real time on the user's device. Audio guidance is also used to provide users with specific procedures and information.

[0840] 5. Methods for collecting feedback

[0841] The robot interface collects user feedback after training and sends it to a server. The collected feedback is stored in a database and used to improve future training programs.

[0842] Hardware and software to use

[0843] Hardware:

[0844] Robot interface: Displays training content and provides audio guidance.

[0845] Device: A computer or smartphone used by the user.

[0846] Server: Runs AI models for data analysis and generation.

[0847] software:

[0848] Python: Implementation of a program and analysis algorithm for generating training content.

[0849] Request Library: Uses HTTP requests to send and receive data.

[0850] JSON: Used as a format for storing and sending / receiving data.

[0851] Generative AI model: Used to generate training content.

[0852] Specific example

[0853] The user inputs information such as "engineer," "production line," and "5 years of experience" into the terminal. The server receives and analyzes this information and sends prompt messages like the following to the generation model.

[0854] Example of a prompt

[0855] Please generate detailed training content for engineers on how to operate production line equipment.

[0856] The AI ​​model generates specific training content based on this prompt and delivers it to the user through the robot interface. For example, it provides video explanations and audio guides in real time regarding "how to operate the new equipment." After the training is completed, the user provides feedback, which is used to improve the next training program.

[0857] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0858] Step 1:

[0859] The user logs into the system from their terminal. During this process, they enter their user ID and password, which are then sent to the server. The server validates the entered data and checks the authentication information. If authentication is successful, the user gains access to the system.

[0860] Step 2:

[0861] The user enters profile information on their device. This includes job title, department, area of ​​expertise, and years of experience. The device sends this information to the server, which stores it in a database. The entered information is stored in a structured format for later analysis.

[0862] Step 3:

[0863] The server analyzes the collected user profile information. This analysis process identifies training needs based on the user's skill level and area of ​​expertise. Algorithms are used to process and calculate data and identify the most suitable training content for each user.

[0864] Step 4:

[0865] The server uses an AI model to generate training content based on the analysis results. The generation process involves inputting prompts tailored to the user's needs into the model to generate specific training content. For example, a prompt such as "Generate detailed training content on how to operate production line equipment for engineers" might be used.

[0866] Step 5:

[0867] The server delivers the generated training content to the terminal. The content is displayed in real time through a robotic interface, and audio guidance is provided. Users review and complete the training content on their terminal.

[0868] Step 6:

[0869] After the user completes the training, they enter feedback into the device. This feedback includes an evaluation of the training content and suggestions for improvement. The device then sends the feedback information to the server.

[0870] Step 7:

[0871] The server analyzes the collected feedback and stores it in a database. The analysis results are extracted as statistics and trends and used to improve future training menus and generate new training content.

[0872] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0873] This invention provides a system that offers specialized training menus for government officials, and by combining this with an emotion engine that recognizes user emotions, it provides a more personalized training experience. This system has the following main functions: collecting user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing user emotion data.

[0874] System-wide flow

[0875] 1. Collection of user data

[0876] The user logs into the device.

[0877] Users access the system using a terminal and log in by entering their user ID and password.

[0878] The device sends login information to the server.

[0879] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[0880] Users enter their profile information.

[0881] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[0882] The device sends profile information to the server.

[0883] The device sends the entered profile information to the server, which then stores it in a database.

[0884] 2. Generating training content

[0885] The server analyzes user data.

[0886] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[0887] The server uses generative AI to generate training content.

[0888] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0889] The server organizes the training content that has been generated.

[0890] The generated training content is customized and organized based on the user's profile. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[0891] 3. Content distribution

[0892] The server delivers training content to the terminals.

[0893] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[0894] Users view training content using their devices.

[0895] Users access training content using their devices. For example, they might watch a video about "the latest trends in environmental policy."

[0896] The device collects user progress data.

[0897] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[0898] 4. Gathering feedback

[0899] Users enter feedback on their devices.

[0900] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0901] The device sends feedback to the server.

[0902] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[0903] The server analyzes the feedback data.

[0904] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0905] 5. Introduction of an emotional engine

[0906] The device collects user sentiment data.

[0907] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[0908] The device sends emotional data to the server.

[0909] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[0910] The server analyzes the emotional data.

[0911] The server analyzes collected emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[0912] Adjusting training content based on emotional data

[0913] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[0914] Specific examples

[0915] The following are specific examples of how to use this system.

[0916] 1. Collection of user data

[0917] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[0918] 2. Generating training content

[0919] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[0920] 3. Content distribution

[0921] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[0922] 4. Gathering feedback

[0923] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[0924] 5. Introduction of an emotional engine

[0925] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[0926] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[0927] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[0928] The following describes the processing flow.

[0929] Step 1:

[0930] The user logs into the device.

[0931] Users access the system using a terminal and log in by entering their user ID and password.

[0932] Step 2:

[0933] The device sends login information to the server.

[0934] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[0935] Step 3:

[0936] The user enters their profile information.

[0937] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[0938] Step 4:

[0939] The device sends profile information to the server.

[0940] The device sends the entered profile information to the server, which then stores it in a database.

[0941] Step 5:

[0942] The server analyzes the user data.

[0943] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[0944] Step 6:

[0945] The server uses generative AI to generate training content.

[0946] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[0947] Step 7:

[0948] The server organizes the training content that has been generated.

[0949] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[0950] Step 8:

[0951] The server delivers the training content to the terminals.

[0952] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[0953] Step 9:

[0954] Users view training content using their devices.

[0955] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[0956] Step 10:

[0957] The device collects user progress data.

[0958] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[0959] Step 11:

[0960] The user enters feedback on their device.

[0961] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[0962] Step 12:

[0963] The device sends feedback to the server.

[0964] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[0965] Step 13:

[0966] The server analyzes the feedback data.

[0967] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[0968] Step 14:

[0969] The device collects user emotion data.

[0970] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[0971] Step 15:

[0972] The device sends emotional data to the server.

[0973] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[0974] Step 16:

[0975] The server analyzes the emotional data.

[0976] The server analyzes collected emotional data to evaluate the user's comfort level and learning effectiveness. This makes it possible to further improve the user's learning experience.

[0977] Step 17:

[0978] The server adjusts training content based on emotional data.

[0979] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[0980] Specific examples

[0981] 1. Collection of user data

[0982] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[0983] 2. Generating training content

[0984] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[0985] 3. Content distribution

[0986] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[0987] 4. Gathering feedback

[0988] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[0989] 5. Introduction of an emotional engine

[0990] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[0991] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[0992] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[0993] (Example 2)

[0994] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0995] Traditional training systems have struggled to provide training content that caters to the diverse needs and skill levels of individual users. Furthermore, the lack of a means to deliver personalized training experiences that consider user emotions hindered the improvement of training effectiveness. Additionally, insufficient post-training feedback and progress tracking made continuous improvement of training programs difficult.

[0996] In Example 2, the identification processing performed by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for collecting user emotion data; and means for analyzing the collected emotion data and using it to adjust the training content. This makes it possible to provide a personalized training experience based on the user's individual needs and emotions, thereby improving training effectiveness. Furthermore, it is possible to continuously improve the training menu based on the collected feedback and progress data.

[0997] "Users" refer to government officials who use the system to receive training, or those who perform corresponding duties.

[0998] A "terminal" refers to a computer or mobile device that a user uses to access a system.

[0999] A "server" refers to a central processing unit that performs tasks such as collecting and analyzing user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing sentiment data.

[1000] "Training content" refers to learning resources such as educational materials, videos, and documents generated based on the user's training needs.

[1001] "Feedback" refers to the opinions and evaluations that users provide after using training content.

[1002] "Emotional data" refers to information about a user's emotional state, collected from their facial expressions, voice, and other sources.

[1003] "Generative AI models" refer to artificial intelligence technologies (e.g., OpenAI GPT-3) that generate appropriate training content based on user data.

[1004] A "prompt" refers to the text of instructions or questions that are input to a generative AI model.

[1005] "Methods for analyzing training needs" refers to the process of identifying the most suitable training content for a given user based on collected user data.

[1006] "Methods for generating training content based on analysis results" refers to the process of creating training content based on analysis results using a generative AI model.

[1007] "Means of collecting user emotion data" refers to a function that recognizes emotions from the user's facial expressions and voice and collects that data.

[1008] "Means of analyzing collected emotional data and using it to adjust training content" refers to the process of analyzing collected emotional data to improve the suitability of training content according to the user's state.

[1009] This invention is a system that provides specialized training menus for government officials. This system collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user emotional data. By combining this with an emotional engine, it can provide a more personalized training experience.

[1010] The hardware required to implement the system includes terminals for user access (e.g., personal computers and smartphones), servers (cloud servers are also applicable), and input devices such as cameras and microphones for recognizing user emotions. The software includes generative AI models (e.g., OpenAI GPT-3), data analysis tools, database management systems, and emotion recognition software (e.g., Affectiva).

[1011] User data collection

[1012] Users access the system using a terminal and log in by entering their user ID and password. The login information is sent from the terminal to the server, which validates the login information and authenticates the user if authentication is successful. Subsequently, the user enters profile information such as their job title, department, area of ​​expertise, and years of experience into a form on the terminal, which sends this information to the server, and the server stores it in a database.

[1013] Training content generation

[1014] The server analyzes stored user profile information and uses a generative AI model (OpenAI GPT-3) to identify training needs based on the user's skill level and area of ​​expertise. For example, if the user is an employee of the environmental conservation department, training content will be generated that includes topics such as "the latest trends in environmental policy" and "how to cooperate with local residents." The generated content is customized based on the user's profile, including detailed explanations for beginners and high-level challenges for experienced users.

[1015] Example of a prompt:

[1016] "Please generate training content for a user who is a manager in the environmental conservation department, based on their more than 10 years of experience in developing advanced environmental policies."

[1017] Content distribution

[1018] The server delivers the generated customized training content to the terminal, which receives the content and prepares to display it to the user. The user uses the terminal to view the training content, for example, by watching a video on "Latest Trends in Environmental Policy." The terminal monitors the user's learning progress and records the viewed training content and completed assignments as logs. Based on this, the user's progress can be tracked.

[1019] Feedback collection and analysis

[1020] After completing a training session, users input feedback on their understanding and the usefulness of the content into a terminal. The terminal sends the input feedback to a server, which receives the feedback data and stores it in a database. The server analyzes the feedback data and extracts statistics and trends. The analysis results are used to improve future training menus and generate new training content.

[1021] Introducing an emotional engine

[1022] Emotion engines (such as Affectiva) collect emotional data from users' facial expressions and voice. For example, they capture a user's facial expressions with a camera while they are watching a video and analyze their emotions. The collected emotional data is sent to a server via the device, where it is analyzed to evaluate the user's comfort level and learning effectiveness. Based on the analysis results, the difficulty level and content of the training can be adjusted to make it more relaxing for the user.

[1023] In this way, the system provides customized training menus for government officials, realizing an optimal learning experience based on the individual needs and emotions of the users.

[1024] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1025] Step 1:

[1026] The user logs into the device.

[1027] The user accesses the system's login page and enters their user ID and password. The terminal then sends this login information to the server. The server receives this information and executes an authentication query against the database. If authentication is successful, the server initiates a session and issues an authentication token.

[1028] Input: User ID, Password

[1029] Output: Authentication token

[1030] Step 2:

[1031] The device sends login information to the server.

[1032] The entered user ID and password are sent from the device to the server. The server validates the received information and, if correct, returns an authentication token to the device.

[1033] Input: User ID, Password

[1034] Output: Authentication result, authentication token

[1035] Step 3:

[1036] The user enters their profile information.

[1037] After successful authentication, the user enters profile information such as job title, department, area of ​​expertise, and years of experience into the device.

[1038] Input: Position, Department, Specialty, Years of Experience

[1039] Output: Profile Information

[1040] Step 4:

[1041] The device sends profile information to the server.

[1042] Once the user's profile information is entered, the device sends it to the server. The server then stores the received information in its database.

[1043] Input: Profile Information

[1044] Output: Profile information stored in the database

[1045] Step 5:

[1046] The server analyzes the user data.

[1047] The server retrieves and analyzes user profile information stored in the database. This identifies training needs based on the user's skill level and area of ​​expertise.

[1048] Input: Profile information stored in the database

[1049] Output: Training needs analysis results

[1050] Step 6:

[1051] The server uses generative AI to generate training content.

[1052] The server inputs prompt text into a generative AI model (e.g., OpenAI GPT-3) based on the analysis results. The generative AI generates appropriate training content and returns the result to the server.

[1053] Input: Training needs analysis results

[1054] Output: Generated training content

[1055] Step 7:

[1056] The server organizes the training content that has been generated.

[1057] The server analyzes the generated training content and customizes it based on the user's profile. For example, it includes detailed content for beginners and high-level challenges for experienced users.

[1058] Input: Generated training content

[1059] Output: Customized training content

[1060] Step 8:

[1061] The server delivers the training content to the terminals.

[1062] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[1063] Input: Customized training content

[1064] Output: Training content delivered to the terminal

[1065] Step 9:

[1066] Users view training content using their devices.

[1067] Users view training content displayed on their devices and check videos and materials.

[1068] Input: Training content delivered to the device

[1069] Output: Viewed training content

[1070] Step 10:

[1071] The device collects user progress data.

[1072] While the user is viewing the training content, the device monitors the user's learning progress and records the content viewed and completed assignments as logs.

[1073] Input: User's learning progress information

[1074] Output: Progress data recorded as a log.

[1075] Step 11:

[1076] The user enters feedback on their device.

[1077] After the training is completed, users will enter feedback on their understanding of the content and its usefulness into a feedback form on their device.

[1078] Input: Feedback Information

[1079] Output: Input feedback

[1080] Step 12:

[1081] The device sends feedback to the server.

[1082] The feedback entered by the user is sent from the device to the server, and the server stores the feedback data in a database.

[1083] Input: Input feedback

[1084] Output: Feedback stored in the database

[1085] Step 13:

[1086] The server analyzes the feedback data.

[1087] The server retrieves and analyzes the stored feedback data. The analysis results will be used to improve future training menus and generate new content.

[1088] Input: Feedback stored in the database

[1089] Output: Feedback analysis results

[1090] Step 14:

[1091] The device collects user emotion data.

[1092] Emotion recognition software collects emotional data from the user's facial expressions and voice. For example, it captures the user's facial expressions with a camera while they are watching a video and analyzes their emotions.

[1093] Input: User's facial expressions, voice data

[1094] Output: Collected sentiment data

[1095] Step 15:

[1096] The device sends emotional data to the server.

[1097] The collected emotional data is sent from the device to the server, which then stores the data in a database.

[1098] Input: Collected emotional data

[1099] Output: Sentiment data stored in the database

[1100] Step 16:

[1101] The server analyzes the emotional data.

[1102] The server analyzes stored emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[1103] Input: Saved emotion data

[1104] Output: Sentiment data analysis results

[1105] Step 17:

[1106] We will adjust training content based on emotional data.

[1107] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[1108] Input: Sentiment data analysis results

[1109] Output: Adjusted training content

[1110] (Application Example 2)

[1111] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1112] While conventional training systems could provide personalized content based on users' job titles and areas of expertise, they had limitations in personalizing content that took into account users' psychological states and emotions. Furthermore, the lack of technology to collect and analyze emotional data and adjust training content in real time based on that data made it difficult to maximize user learning effectiveness.

[1113] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for recognizing the user's emotions; means for collecting and analyzing user emotion data; and means for adjusting the training content based on the user's emotion data. This makes it possible to adjust the training content in real time according to the user's psychological state and maximize the learning effect.

[1114] "Position" refers to a role or authority within an organization.

[1115] "Department" refers to a division within an organization that has specific duties or functions.

[1116] A "specialized field" refers to an area that focuses on a specific technology or knowledge.

[1117] "Years of experience" refers to the number of years a user has accumulated practical experience in their field of expertise or position.

[1118] "Training needs" refer to the training content and skill improvement requirements that users desire.

[1119] "Analysis" refers to the process of thoroughly examining collected information and deriving its meaning.

[1120] "Generation" means creating new training content based on the analysis results.

[1121] "Distribution" refers to sending the created training content to the user's device.

[1122] "Feedback" refers to the opinions, impressions, and evaluations provided by users.

[1123] "Means of recognizing emotions" refers to methods of detecting a user's psychological state and emotions from their facial expressions, voice, etc.

[1124] "Emotional data" refers to information about a user's emotional state, and includes data obtained through methods such as facial expression and voice analysis.

[1125] "Means of adjustment" refers to the process of changing the content and difficulty level of training materials based on collected and analyzed information.

[1126] "Real-time" means that processing and reactions occur almost simultaneously with real-world time.

[1127] The system of this invention collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user sentiment data in order to personalize training content.

[1128] The system uses the following main hardware and software components.

[1129] 1. User terminals: Devices used by users include smartphones, smart glasses, and head-mounted displays. These devices are used for data entry, content display, and sentiment data collection.

[1130] 2. Server: A central management system is required for analyzing user data, generating and distributing training content, analyzing feedback, and analyzing sentiment data. This server consists of various software modules that receive and analyze data from the user interface.

[1131] 3. Generative AI: Used to generate training content based on user data. The generative AI model is implemented in Python and creates customized training materials and assignments based on the user's profile data.

[1132] 4. Emotion Recognition Engine: Used to identify emotions from the user's facial expressions and voice. For example, it utilizes OpenCV (an open-source computer vision library) and a machine learning model for emotion recognition (e.g., a model trained using TensorFlow or Keras).

[1133] Users access the system using a terminal and log in by entering their user ID and password. The terminal collects profile information such as the user's job title, department, area of ​​expertise, and years of experience, and sends it to the server. The server analyzes this data to identify the user's skill level and training needs, and generates training content using generative AI. The generated content is delivered to the terminal, and the user views it. The user's progress is monitored by the terminal and recorded as a log.

[1134] While users are using training content, cameras and microphones built into smart glasses or head-mounted displays analyze the user's facial expressions and voice in real time, collecting emotional data. The collected emotional data is sent to a server for analysis. This allows the training content to be adjusted to be more relaxing if the user is tense, or more challenging if they are focused.

[1135] As a concrete example, suppose a technician is wearing a head-mounted display and watching a training video on "advanced troubleshooting methods." At this time, an emotion recognition engine recognizes emotions such as "concentrating" or "being confused" in real time from the technician's facial expressions and voice while watching, and adjusts the training content accordingly.

[1136] For example, the following instructions can be given to a generative AI as a prompt:

[1137] "The user's area of ​​expertise is machine operation, with 5 years of experience, and their position is department leader. Please create training content that includes advanced troubleshooting methods within the basic operation manual."

[1138] This system allows engineers to have a more effective and personalized learning experience.

[1139] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1140] Step 1:

[1141] The terminal collects user data. The user logs into the terminal and enters information about their job title, department, area of ​​expertise, and years of experience. The terminal sends the entered user data to the server. The server then stores the user's profile information in a database.

[1142] Input: User ID and password, job title, department, area of ​​expertise, years of experience

[1143] Output: User profile information stored in the database

[1144] Step 2:

[1145] The server analyzes user data to identify training needs. The server analyzes user profile information stored in the database to identify the corresponding skill level and training needs. It then generates training content by inputting prompts into a generative AI model.

[1146] Input: User profile information stored in the database, prompt text

[1147] Data processing: Analysis of profile information and identification of training needs through the operation of AI models.

[1148] Output: User-optimized training content

[1149] Step 3:

[1150] The server generates training content and delivers it to the user's device. The server converts the generated content into a data format and sends it to the user's device. The device displays the received training content to the user, supporting their learning.

[1151] Input: Generated training content

[1152] Output: Training content delivered to the user's terminal.

[1153] Step 4:

[1154] The device monitors the user's progress and records it as a log. When the user views training content, the device collects progress data (viewed content and completed tasks) in real time and sends it to the server. The server stores this data in a database.

[1155] Input: User viewing and operation data

[1156] Data processing: Collection and organization of progress data

[1157] Output: Progress log saved in the database

[1158] Step 5:

[1159] The device collects user feedback and sends it to the server. After completing the training content, the user enters feedback on the device. The device sends this feedback data to the server, which stores it in a database.

[1160] Input: User-entered feedback data

[1161] Output: Feedback data stored in the database

[1162] Step 6:

[1163] The server analyzes the feedback data and uses it to improve future training programs. The server analyzes the collected feedback as statistics and trends, and uses the analysis results to obtain guidelines for improving future training content.

[1164] Input: Feedback data stored in the database

[1165] Data processing: Analysis of feedback data

[1166] Output: Guidelines for improving training menus based on analysis results

[1167] Step 7:

[1168] The emotion engine recognizes the user's emotions in real time. While viewing training content, the camera and microphone built into the device monitor the user's facial expressions and voice, collecting emotional data. The collected data is sent to a server, where the emotion recognition engine performs analysis.

[1169] Input: User's facial expressions and voice data

[1170] Data processing: Real-time emotional data analysis

[1171] Output: Analyzed sentiment data

[1172] Step 8:

[1173] The server adjusts training content based on emotional data. Based on collected and analyzed emotional data, the training content is adjusted in real time to ensure users learn most effectively. Specifically, if a user is feeling stressed, the content is changed to something more relaxing; if they are concentrating, it becomes more challenging.

[1174] Input: Analyzed sentiment data

[1175] Data processing: Adjusting training content based on emotional data

[1176] Output: Adjusted training content

[1177] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1178] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1179] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1180] [Third Embodiment]

[1181] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1182] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1183] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1184] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1185] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1186] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1187] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1188] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1189] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1190] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1191] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1192] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1193] This invention relates to a system that provides specialized training menus for government officials. This system, by incorporating the following key functions, enables a complete process from user data collection to training content generation, distribution, and feedback collection and analysis.

[1194] System-wide flow

[1195] 1. Collection of user data

[1196] The user logs into the device.

[1197] Users log in to the system using a terminal. Login information includes a user ID and password.

[1198] The device sends login information to the server.

[1199] The terminal sends the entered login information to the server. The server validates the login information and authenticates the user if successful.

[1200] Users enter their profile information.

[1201] Users enter profile information such as their job title, department, area of ​​expertise, and years of experience on their device.

[1202] The device sends profile information to the server.

[1203] The device sends the entered profile information to the server. The server receives the profile information and stores it in its database.

[1204] 2. Generating training content

[1205] The server analyzes user data.

[1206] The server analyzes the collected user profile information. The analysis identifies training needs based on the user's skill level and area of ​​expertise.

[1207] The server uses generative AI to generate training content.

[1208] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[1209] The server organizes the training content that has been generated.

[1210] The generated training content is customized and organized based on user profiles. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[1211] 3. Content distribution

[1212] The server delivers training content to the terminals.

[1213] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[1214] Users view training content using their devices.

[1215] Users access training content using their devices. For example, a user might watch a video about "the latest trends in environmental policy."

[1216] The device collects user progress data.

[1217] The device monitors the user's learning progress and records it as a log. Progress data includes viewed training content and completed assignments.

[1218] 4. Gathering feedback

[1219] Users enter feedback on their devices.

[1220] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[1221] The device sends feedback to the server.

[1222] The terminal sends the input feedback to the server. The server receives the feedback data and stores it in a database.

[1223] The server analyzes the feedback data.

[1224] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[1225] Specific examples

[1226] The following are specific examples of how to use this system.

[1227] 1. Collection of user data

[1228] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[1229] 2. Generating training content

[1230] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[1231] 3. Content distribution

[1232] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[1233] 4. Gathering feedback

[1234] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[1235] In this way, this system can provide customized training menus for administrative staff through a series of processes.

[1236] The following describes the processing flow.

[1237] Step 1:

[1238] The user logs into the device.

[1239] Users access the system using a terminal and log in by entering their user ID and password.

[1240] Step 2:

[1241] The device sends login information to the server.

[1242] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[1243] Step 3:

[1244] The user enters their profile information.

[1245] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[1246] Step 4:

[1247] The device sends profile information to the server.

[1248] The device sends the entered profile information to the server, and the server stores this data in a database.

[1249] Step 5:

[1250] The server analyzes the user data.

[1251] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[1252] Step 6:

[1253] The server uses generative AI to generate training content.

[1254] The AI ​​on the server generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[1255] Step 7:

[1256] The server organizes the training content that has been generated.

[1257] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[1258] Step 8:

[1259] The server delivers the training content to the terminals.

[1260] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[1261] Step 9:

[1262] Users view training content using their devices.

[1263] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[1264] Step 10:

[1265] The device collects user progress data.

[1266] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[1267] Step 11:

[1268] The user enters feedback on their device.

[1269] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[1270] Step 12:

[1271] The device sends feedback to the server.

[1272] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[1273] Step 13:

[1274] The server analyzes the feedback data.

[1275] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[1276] (Example 1)

[1277] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1278] Modern training programs for government officials often contain general content that doesn't align with individual job experience or specialization, making efficient and effective skill development difficult. Furthermore, insufficient feedback and progress tracking make it challenging to improve training programs and provide individualized support. To address these challenges, customized training content tailored to individual employees, along with continuous monitoring and improvement of training effectiveness, are necessary.

[1279] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1280] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; and means for generating training content based on the analysis results using a generative artificial intelligence model. This enables the automatic generation and distribution of training content optimized for each user's characteristics. Furthermore, the user's terminal includes means for distributing and displaying the generated training content to the user; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for recording the user's learning progress. This enables real-time monitoring of the user's progress and effective collection and analysis of feedback.

[1281] "Means for collecting information on the user's job title, department, area of ​​expertise, and years of experience" refers to an interface for users to input and transmit information related to their job duties, and communication means for transmitting this information to the server.

[1282] "Means for analyzing training needs based on collected information" refers to algorithms and analysis systems for analyzing collected user information and identifying the training required for each user.

[1283] "Means for generating training content based on analysis results using a generative artificial intelligence model" refers to an artificial intelligence system and related software tools for automatically generating training content according to the analysis results.

[1284] "Means for delivering and displaying generated training content on a user's device" refers to communication means and user interface for transmitting generated training content to a user's device and displaying and playing it back.

[1285] "Means of collecting user-generated feedback" refers to a form for users to input and submit feedback after training, and the means of communication for sending that feedback to the server.

[1286] "Means for analyzing collected feedback and using it to improve future training menus" refers to analytical systems and algorithms for analyzing collected feedback data and using the results to improve and optimize training programs.

[1287] "Means for recording user learning progress" refers to systems and related software tools for monitoring users' training progress and recording and retaining that data.

[1288] This invention relates to a system that provides specialized training menus for government officials. This system provides specific means for realizing a series of processes including user data collection, training content generation, content distribution, and feedback collection and analysis.

[1289] User data collection

[1290] The user logs into the device.

[1291] Users log in to the system by entering their user ID and password on their terminal. This login information is encrypted and sent from the terminal to the server. The server receives the login information, compares it with the database, and performs authentication.

[1292] Enter your profile information

[1293] Upon successful authentication, the user enters detailed profile information on their device, including their job title, department, area of ​​expertise, and years of experience. This information is also encrypted before being sent to the server and stored in the database.

[1294] Training content generation

[1295] User Data Analysis

[1296] The server analyzes the collected user profile information. Machine learning algorithms (e.g., k-means clustering) are used for the analysis to identify training needs based on the user's skill level and area of ​​expertise.

[1297] Use of generative AI

[1298] Based on the analysis results, training content is generated using a generative AI (e.g., OpenAI's GPT-3). In this process, prompts are used to instruct the AI ​​on the content to be generated. For example, the prompt "Create a lecture on the latest trends in environmental policy" is input to the generative AI.

[1299] Organizing content

[1300] The generated training content is categorized and organized according to the user's skill level and area of ​​expertise. The content is tagged and customized using natural language processing tools (e.g., spaCy).

[1301] Content distribution

[1302] Distribution of training content

[1303] The server sends the generated customized training content to the terminal. The terminal prepares the received content for the user to view and access easily.

[1304] Viewing training content

[1305] Users view the generated training content through their devices. For example, they can watch a video on "Methods for Formulating Advanced Environmental Policies."

[1306] Gathering feedback and monitoring progress

[1307] Feedback Input

[1308] After completing the training, users enter feedback on their understanding and the usefulness of the content into their terminals. This feedback information is also encrypted before being sent to the server and stored in the database.

[1309] Record of progress

[1310] The device monitors the user's learning progress (e.g., viewed, not viewed, completed assignments) in real time and records it as a log. This information is also sent to the server periodically.

[1311] Feedback analysis

[1312] The server analyzes the collected feedback and extracts statistics and trends. The analysis results can be used to improve future training content and develop new training programs.

[1313] Specific example

[1314] For example, if a user enters profile information such as "Environmental Conservation Department, Section Chief, over 10 years of experience," this information is sent to the server and stored in the database. The server then sends prompts to the generative AI to generate training content such as "Methods for Formulating Advanced Environmental Policies" or "Building Regional Partnerships." An example of a prompt might be, "Please create a lecture on methods for formulating advanced environmental policies."

[1315] Thus, the present invention makes it possible to provide training menus optimized for individual administrative staff, enabling efficient and effective skill improvement.

[1316] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1317] Step 1:

[1318] The user enters their login information.

[1319] Input: User ID and password

[1320] Specific action: The user enters their user ID and password into the login form displayed on the device and clicks the login button.

[1321] Output: Encrypted login information is sent from the terminal to the server.

[1322] Step 2:

[1323] The device sends login information to the server.

[1324] Input: Encrypted login information

[1325] Specific operation: The terminal encrypts the login information using an encryption library (e.g., OpenSSL) and sends it to the server via the HTTPS protocol.

[1326] Output: The server receives the login information.

[1327] Step 3:

[1328] The server authenticates the login information.

[1329] Input: Received login information

[1330] Specific operation: The server checks the login information against the database, and if they match, generates a JWT token and sends it to the terminal. If authentication is successful, the server generates an authentication token and returns a login success response.

[1331] Output: Authentication token and login success response

[1332] Step 4:

[1333] Users enter their profile information.

[1334] Input: Profile information such as job title, department, area of ​​expertise, and years of experience.

[1335] Specific operation: The authenticated user enters profile information such as job title, department, area of ​​expertise, and years of experience into a form displayed on the device, and clicks the save button.

[1336] Output: Encrypted profile information is sent from the device to the server.

[1337] Step 5:

[1338] The device sends profile information to the server.

[1339] Input: Encrypted profile information

[1340] Specific operation: The device serializes the profile information in JSON format and sends it to the server via the HTTPS protocol.

[1341] Output: The server receives the profile information and saves it to the database.

[1342] Step 6:

[1343] The server analyzes user data.

[1344] Input: User profile information stored in the database

[1345] Specific operation: The server uses machine learning algorithms (e.g., k-means clustering) to analyze user profile information and identify the user's skill level and training needs.

[1346] Output: Analysis results identifying user skill levels and training needs

[1347] Step 7:

[1348] The server uses generative AI to generate training content.

[1349] Input: Analysis results and prompts

[1350] Specific operation: The server inputs a prompt message into a generative AI (e.g., OpenAI's GPT-3) and generates appropriate training content. For example, the prompt message might be "Please create a lecture on the latest trends in environmental policy."

[1351] Output: Generated training content

[1352] Step 8:

[1353] The server organizes the training content.

[1354] Input: Generated training content and analysis results

[1355] Specific operation: The server uses a natural language processing tool (e.g., spaCy) to customize and organize the generated training content based on the user's skill level.

[1356] Output: Customized training content

[1357] Step 9:

[1358] The server delivers the training content.

[1359] Input: Customized training content

[1360] Specific operation: The server uses a REST API to send customized training content to the device, and the device displays it to the user.

[1361] Output: Training content delivered to the device

[1362] Step 10:

[1363] Users view training content.

[1364] Input: Distributed training content

[1365] Specific actions: The user opens training content (e.g., videos, documents) in their device's browser and watches or learns from it.

[1366] Output: User training progress data

[1367] Step 11:

[1368] The device records the user's progress data.

[1369] Input: User's learning progress

[1370] Specific operation: The device logs the tasks it has viewed or completed and periodically sends this data to the server.

[1371] Output: Log of progress data sent to the server

[1372] Step 12:

[1373] Users enter feedback

[1374] Input: Feedback on understanding and usefulness of the training content.

[1375] Specific action: After the training is completed, the user enters their evaluation and comments into the feedback form on their device and clicks the submit button.

[1376] Output: Feedback information is sent from the terminal to the server.

[1377] Step 13:

[1378] The device sends feedback to the server.

[1379] Input: Feedback information

[1380] Specific operation: The terminal serializes the feedback information in JSON format and sends it to the server via the HTTPS protocol.

[1381] Output: The server receives the feedback information and saves it to the database.

[1382] Step 14:

[1383] The server analyzes the feedback data.

[1384] Input: Feedback information stored in the database

[1385] Specific operation: The server uses data analysis tools (e.g., pandas, scikit-learn) to analyze feedback data and extract trends and statistical information.

[1386] Output: Analyzed feedback information and improvement suggestion data

[1387] (Application Example 1)

[1388] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1389] It is crucial for field workers and engineers to receive training tailored to their position, area of ​​expertise, and years of experience. However, traditional training systems struggle to provide training optimized for individual users. Furthermore, the lack of real-time training content display and audio guidance makes consistent skill development difficult.

[1390] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1391] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for displaying the training content in real time and providing voice guidance through a robot interface. This enables the provision of an optimal training program based on the user's individual needs and real-time content delivery.

[1392] "Users" refer to field workers and engineers who use the system.

[1393] "Position" refers to the job title or position a user holds within an organization.

[1394] "Department" refers to the department within the specific organization to which the user belongs.

[1395] "Specialized field" refers to the area of ​​technology or knowledge that a user is particularly familiar with.

[1396] "Years of experience" refers to the length of time a user has been engaged in a specific job or role.

[1397] "Means of collection" refers to methods and devices for obtaining necessary information from users.

[1398] "Means for analyzing training needs" refers to methods and devices for identifying the training content that users require based on collected information.

[1399] "Means for generating training content" refers to methods and devices for creating appropriate training materials and teaching aids based on analysis results.

[1400] "Terminal" refers to a device used by a user, and includes personal computers, smartphones, and other similar devices.

[1401] "Means of distribution" refers to the methods and devices used to send the generated training content to the user's device.

[1402] "Feedback" refers to evaluations and opinions from users who have received training.

[1403] A "robot interface" refers to the user interface of a robot that displays training content and provides voice guidance.

[1404] "Real-time" refers to a situation where processing or display occurs immediately.

[1405] "Guidance" refers to providing users with instructions and information through audio or text.

[1406] The system of this invention provides specialized training programs for factory workers and engineers. The system's configuration and processing are described in detail below.

[1407] System Configuration

[1408] 1. Methods for collecting user data

[1409] The server collects information such as job title, department, area of ​​expertise, and years of experience entered by users (field workers and engineers) via their terminals. The collected information is stored in a database.

[1410] 2. Methods for analyzing training needs

[1411] The server analyzes the collected user data to identify training needs based on the user's skill level and area of ​​expertise. Data analysis algorithms are used for this analysis.

[1412] 3. Means of generating training content

[1413] The server uses a generation AI model based on the analysis results to generate appropriate training content. This generation process uses prompts to meet the user's specific needs.

[1414] 4. Means of delivering content

[1415] Through a robotic interface, the generated training content is displayed in real time on the user's device. Audio guidance is also used to provide users with specific procedures and information.

[1416] 5. Methods for collecting feedback

[1417] The robot interface collects user feedback after training and sends it to a server. The collected feedback is stored in a database and used to improve future training programs.

[1418] Hardware and software to use

[1419] Hardware:

[1420] Robot interface: Displays training content and provides audio guidance.

[1421] Device: A computer or smartphone used by the user.

[1422] Server: Runs AI models for data analysis and generation.

[1423] software:

[1424] Python: Implementation of a program and analysis algorithm for generating training content.

[1425] Request Library: Uses HTTP requests to send and receive data.

[1426] JSON: Used as a format for storing and sending / receiving data.

[1427] Generative AI model: Used to generate training content.

[1428] Specific example

[1429] The user inputs information such as "engineer," "production line," and "5 years of experience" into the terminal. The server receives and analyzes this information and sends prompt messages like the following to the generation model.

[1430] Example of a prompt

[1431] Please generate detailed training content for engineers on how to operate production line equipment.

[1432] The AI ​​model generates specific training content based on this prompt and delivers it to the user through the robot interface. For example, it provides video explanations and audio guides in real time regarding "how to operate the new equipment." After the training is completed, the user provides feedback, which is used to improve the next training program.

[1433] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1434] Step 1:

[1435] The user logs into the system from their terminal. During this process, they enter their user ID and password, which are then sent to the server. The server validates the entered data and checks the authentication information. If authentication is successful, the user gains access to the system.

[1436] Step 2:

[1437] The user enters profile information on their device. This includes job title, department, area of ​​expertise, and years of experience. The device sends this information to the server, which stores it in a database. The entered information is stored in a structured format for later analysis.

[1438] Step 3:

[1439] The server analyzes the collected user profile information. This analysis process identifies training needs based on the user's skill level and area of ​​expertise. Algorithms are used to process and calculate data and identify the most suitable training content for each user.

[1440] Step 4:

[1441] The server uses an AI model to generate training content based on the analysis results. The generation process involves inputting prompts tailored to the user's needs into the model to generate specific training content. For example, a prompt such as "Generate detailed training content on how to operate production line equipment for engineers" might be used.

[1442] Step 5:

[1443] The server delivers the generated training content to the terminal. The content is displayed in real time through a robotic interface, and audio guidance is provided. Users review and complete the training content on their terminal.

[1444] Step 6:

[1445] After the user completes the training, they enter feedback into the device. This feedback includes an evaluation of the training content and suggestions for improvement. The device then sends the feedback information to the server.

[1446] Step 7:

[1447] The server analyzes the collected feedback and stores it in a database. The analysis results are extracted as statistics and trends and used to improve future training menus and generate new training content.

[1448] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1449] This invention provides a system that offers specialized training menus for government officials, and by combining this with an emotion engine that recognizes user emotions, it provides a more personalized training experience. This system has the following main functions: collecting user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing user emotion data.

[1450] System-wide flow

[1451] 1. Collection of user data

[1452] The user logs into the device.

[1453] Users access the system using a terminal and log in by entering their user ID and password.

[1454] The device sends login information to the server.

[1455] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[1456] Users enter their profile information.

[1457] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[1458] The device sends profile information to the server.

[1459] The device sends the entered profile information to the server, which then stores it in a database.

[1460] 2. Generating training content

[1461] The server analyzes user data.

[1462] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[1463] The server uses generative AI to generate training content.

[1464] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[1465] The server organizes the training content that has been generated.

[1466] The generated training content is customized and organized based on the user's profile. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[1467] 3. Content distribution

[1468] The server delivers training content to the terminals.

[1469] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[1470] Users view training content using their devices.

[1471] Users access training content using their devices. For example, they might watch a video about "the latest trends in environmental policy."

[1472] The device collects user progress data.

[1473] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[1474] 4. Gathering feedback

[1475] Users enter feedback on their devices.

[1476] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[1477] The device sends feedback to the server.

[1478] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[1479] The server analyzes the feedback data.

[1480] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[1481] 5. Introduction of an emotional engine

[1482] The device collects user sentiment data.

[1483] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[1484] The device sends emotional data to the server.

[1485] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[1486] The server analyzes the emotional data.

[1487] The server analyzes collected emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[1488] Adjusting training content based on emotional data

[1489] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[1490] Specific examples

[1491] The following are specific examples of how to use this system.

[1492] 1. Collection of user data

[1493] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[1494] 2. Generating training content

[1495] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[1496] 3. Content distribution

[1497] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[1498] 4. Gathering feedback

[1499] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[1500] 5. Introduction of an emotional engine

[1501] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[1502] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[1503] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[1504] The following describes the processing flow.

[1505] Step 1:

[1506] The user logs into the device.

[1507] Users access the system using a terminal and log in by entering their user ID and password.

[1508] Step 2:

[1509] The device sends login information to the server.

[1510] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[1511] Step 3:

[1512] The user enters their profile information.

[1513] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[1514] Step 4:

[1515] The device sends profile information to the server.

[1516] The device sends the entered profile information to the server, which then stores it in a database.

[1517] Step 5:

[1518] The server analyzes the user data.

[1519] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[1520] Step 6:

[1521] The server uses generative AI to generate training content.

[1522] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[1523] Step 7:

[1524] The server organizes the training content that has been generated.

[1525] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[1526] Step 8:

[1527] The server delivers the training content to the terminals.

[1528] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[1529] Step 9:

[1530] Users view training content using their devices.

[1531] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[1532] Step 10:

[1533] The device collects user progress data.

[1534] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[1535] Step 11:

[1536] The user enters feedback on their device.

[1537] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[1538] Step 12:

[1539] The device sends feedback to the server.

[1540] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[1541] Step 13:

[1542] The server analyzes the feedback data.

[1543] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[1544] Step 14:

[1545] The device collects user emotion data.

[1546] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[1547] Step 15:

[1548] The device sends emotional data to the server.

[1549] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[1550] Step 16:

[1551] The server analyzes the emotional data.

[1552] The server analyzes collected emotional data to evaluate the user's comfort level and learning effectiveness. This makes it possible to further improve the user's learning experience.

[1553] Step 17:

[1554] The server adjusts training content based on emotional data.

[1555] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[1556] Specific examples

[1557] 1. Collection of user data

[1558] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[1559] 2. Generating training content

[1560] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[1561] 3. Content distribution

[1562] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[1563] 4. Gathering feedback

[1564] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[1565] 5. Introduction of an emotional engine

[1566] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[1567] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[1568] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[1569] (Example 2)

[1570] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1571] Traditional training systems have struggled to provide training content that caters to the diverse needs and skill levels of individual users. Furthermore, the lack of a means to deliver personalized training experiences that consider user emotions hindered the improvement of training effectiveness. Additionally, insufficient post-training feedback and progress tracking made continuous improvement of training programs difficult.

[1572] In Example 2, the identification processing performed by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for collecting user emotion data; and means for analyzing the collected emotion data and using it to adjust the training content. This makes it possible to provide a personalized training experience based on the user's individual needs and emotions, thereby improving training effectiveness. Furthermore, it is possible to continuously improve the training menu based on the collected feedback and progress data.

[1573] "Users" refer to government officials who use the system to receive training, or those who perform corresponding duties.

[1574] A "terminal" refers to a computer or mobile device that a user uses to access a system.

[1575] A "server" refers to a central processing unit that performs tasks such as collecting and analyzing user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing sentiment data.

[1576] "Training content" refers to learning resources such as educational materials, videos, and documents generated based on the user's training needs.

[1577] "Feedback" refers to the opinions and evaluations that users provide after using training content.

[1578] "Emotional data" refers to information about a user's emotional state, collected from their facial expressions, voice, and other sources.

[1579] "Generative AI models" refer to artificial intelligence technologies (e.g., OpenAI GPT-3) that generate appropriate training content based on user data.

[1580] A "prompt" refers to the text of instructions or questions that are input to a generative AI model.

[1581] "Methods for analyzing training needs" refers to the process of identifying the most suitable training content for a given user based on collected user data.

[1582] "Methods for generating training content based on analysis results" refers to the process of creating training content based on analysis results using a generative AI model.

[1583] "Means of collecting user emotion data" refers to a function that recognizes emotions from the user's facial expressions and voice and collects that data.

[1584] "Means of analyzing collected emotional data and using it to adjust training content" refers to the process of analyzing collected emotional data to improve the suitability of training content according to the user's state.

[1585] This invention is a system that provides specialized training menus for government officials. This system collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user emotional data. By combining this with an emotional engine, it can provide a more personalized training experience.

[1586] The hardware required to implement the system includes terminals for user access (e.g., personal computers and smartphones), servers (cloud servers are also applicable), and input devices such as cameras and microphones for recognizing user emotions. The software includes generative AI models (e.g., OpenAI GPT-3), data analysis tools, database management systems, and emotion recognition software (e.g., Affectiva).

[1587] User data collection

[1588] Users access the system using a terminal and log in by entering their user ID and password. The login information is sent from the terminal to the server, which validates the login information and authenticates the user if authentication is successful. Subsequently, the user enters profile information such as their job title, department, area of ​​expertise, and years of experience into a form on the terminal, which sends this information to the server, and the server stores it in a database.

[1589] Training content generation

[1590] The server analyzes stored user profile information and uses a generative AI model (OpenAI GPT-3) to identify training needs based on the user's skill level and area of ​​expertise. For example, if the user is an employee of the environmental conservation department, training content will be generated that includes topics such as "the latest trends in environmental policy" and "how to cooperate with local residents." The generated content is customized based on the user's profile, including detailed explanations for beginners and high-level challenges for experienced users.

[1591] Example of a prompt:

[1592] "Please generate training content for a user who is a manager in the environmental conservation department, based on their more than 10 years of experience in developing advanced environmental policies."

[1593] Content distribution

[1594] The server delivers the generated customized training content to the terminal, which receives the content and prepares to display it to the user. The user uses the terminal to view the training content, for example, by watching a video on "Latest Trends in Environmental Policy." The terminal monitors the user's learning progress and records the viewed training content and completed assignments as logs. Based on this, the user's progress can be tracked.

[1595] Feedback collection and analysis

[1596] After completing a training session, users input feedback on their understanding and the usefulness of the content into a terminal. The terminal sends the input feedback to a server, which receives the feedback data and stores it in a database. The server analyzes the feedback data and extracts statistics and trends. The analysis results are used to improve future training menus and generate new training content.

[1597] Introducing an emotional engine

[1598] Emotion engines (such as Affectiva) collect emotional data from users' facial expressions and voice. For example, they capture a user's facial expressions with a camera while they are watching a video and analyze their emotions. The collected emotional data is sent to a server via the device, where it is analyzed to evaluate the user's comfort level and learning effectiveness. Based on the analysis results, the difficulty level and content of the training can be adjusted to make it more relaxing for the user.

[1599] In this way, the system provides customized training menus for government officials, realizing an optimal learning experience based on the individual needs and emotions of the users.

[1600] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1601] Step 1:

[1602] The user logs into the device.

[1603] The user accesses the system's login page and enters their user ID and password. The terminal then sends this login information to the server. The server receives this information and executes an authentication query against the database. If authentication is successful, the server initiates a session and issues an authentication token.

[1604] Input: User ID, Password

[1605] Output: Authentication token

[1606] Step 2:

[1607] The device sends login information to the server.

[1608] The entered user ID and password are sent from the device to the server. The server validates the received information and, if correct, returns an authentication token to the device.

[1609] Input: User ID, Password

[1610] Output: Authentication result, authentication token

[1611] Step 3:

[1612] The user enters their profile information.

[1613] After successful authentication, the user enters profile information such as job title, department, area of ​​expertise, and years of experience into the device.

[1614] Input: Position, Department, Specialty, Years of Experience

[1615] Output: Profile Information

[1616] Step 4:

[1617] The device sends profile information to the server.

[1618] Once the user's profile information is entered, the device sends it to the server. The server then stores the received information in its database.

[1619] Input: Profile Information

[1620] Output: Profile information stored in the database

[1621] Step 5:

[1622] The server analyzes the user data.

[1623] The server retrieves and analyzes user profile information stored in the database. This identifies training needs based on the user's skill level and area of ​​expertise.

[1624] Input: Profile information stored in the database

[1625] Output: Training needs analysis results

[1626] Step 6:

[1627] The server uses generative AI to generate training content.

[1628] The server inputs prompt text into a generative AI model (e.g., OpenAI GPT-3) based on the analysis results. The generative AI generates appropriate training content and returns the result to the server.

[1629] Input: Training needs analysis results

[1630] Output: Generated training content

[1631] Step 7:

[1632] The server organizes the training content that has been generated.

[1633] The server analyzes the generated training content and customizes it based on the user's profile. For example, it includes detailed content for beginners and high-level challenges for experienced users.

[1634] Input: Generated training content

[1635] Output: Customized training content

[1636] Step 8:

[1637] The server delivers the training content to the terminals.

[1638] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[1639] Input: Customized training content

[1640] Output: Training content delivered to the terminal

[1641] Step 9:

[1642] Users view training content using their devices.

[1643] Users view training content displayed on their devices and check videos and materials.

[1644] Input: Training content delivered to the device

[1645] Output: Viewed training content

[1646] Step 10:

[1647] The device collects user progress data.

[1648] While the user is viewing the training content, the device monitors the user's learning progress and records the content viewed and completed assignments as logs.

[1649] Input: User's learning progress information

[1650] Output: Progress data recorded as a log.

[1651] Step 11:

[1652] The user enters feedback on their device.

[1653] After the training is completed, users will enter feedback on their understanding of the content and its usefulness into a feedback form on their device.

[1654] Input: Feedback Information

[1655] Output: Input feedback

[1656] Step 12:

[1657] The device sends feedback to the server.

[1658] The feedback entered by the user is sent from the device to the server, and the server stores the feedback data in a database.

[1659] Input: Input feedback

[1660] Output: Feedback stored in the database

[1661] Step 13:

[1662] The server analyzes the feedback data.

[1663] The server retrieves and analyzes the stored feedback data. The analysis results will be used to improve future training menus and generate new content.

[1664] Input: Feedback stored in the database

[1665] Output: Feedback analysis results

[1666] Step 14:

[1667] The device collects user emotion data.

[1668] Emotion recognition software collects emotional data from the user's facial expressions and voice. For example, it captures the user's facial expressions with a camera while they are watching a video and analyzes their emotions.

[1669] Input: User's facial expressions, voice data

[1670] Output: Collected sentiment data

[1671] Step 15:

[1672] The device sends emotional data to the server.

[1673] The collected emotional data is sent from the device to the server, which then stores the data in a database.

[1674] Input: Collected emotional data

[1675] Output: Sentiment data stored in the database

[1676] Step 16:

[1677] The server analyzes the emotional data.

[1678] The server analyzes stored emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[1679] Input: Saved emotion data

[1680] Output: Sentiment data analysis results

[1681] Step 17:

[1682] We will adjust training content based on emotional data.

[1683] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[1684] Input: Sentiment data analysis results

[1685] Output: Adjusted training content

[1686] (Application Example 2)

[1687] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1688] While conventional training systems could provide personalized content based on users' job titles and areas of expertise, they had limitations in personalizing content that took into account users' psychological states and emotions. Furthermore, the lack of technology to collect and analyze emotional data and adjust training content in real time based on that data made it difficult to maximize user learning effectiveness.

[1689] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for recognizing the user's emotions; means for collecting and analyzing user emotion data; and means for adjusting the training content based on the user's emotion data. This makes it possible to adjust the training content in real time according to the user's psychological state and maximize the learning effect.

[1690] "Position" refers to a role or authority within an organization.

[1691] "Department" refers to a division within an organization that has specific duties or functions.

[1692] A "specialized field" refers to an area that focuses on a specific technology or knowledge.

[1693] "Years of experience" refers to the number of years a user has accumulated practical experience in their field of expertise or position.

[1694] "Training needs" refer to the training content and skill improvement requirements that users desire.

[1695] "Analysis" refers to the process of thoroughly examining collected information and deriving its meaning.

[1696] "Generation" means creating new training content based on the analysis results.

[1697] "Distribution" refers to sending the created training content to the user's device.

[1698] "Feedback" refers to the opinions, impressions, and evaluations provided by users.

[1699] "Means of recognizing emotions" refers to methods of detecting a user's psychological state and emotions from their facial expressions, voice, etc.

[1700] "Emotional data" refers to information about a user's emotional state, and includes data obtained through methods such as facial expression and voice analysis.

[1701] "Means of adjustment" refers to the process of changing the content and difficulty level of training materials based on collected and analyzed information.

[1702] "Real-time" means that processing and reactions occur almost simultaneously with real-world time.

[1703] The system of this invention collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user sentiment data in order to personalize training content.

[1704] The system uses the following main hardware and software components.

[1705] 1. User terminals: Devices used by users include smartphones, smart glasses, and head-mounted displays. These devices are used for data entry, content display, and sentiment data collection.

[1706] 2. Server: A central management system is required for analyzing user data, generating and distributing training content, analyzing feedback, and analyzing sentiment data. This server consists of various software modules that receive and analyze data from the user interface.

[1707] 3. Generative AI: Used to generate training content based on user data. The generative AI model is implemented in Python and creates customized training materials and assignments based on the user's profile data.

[1708] 4. Emotion Recognition Engine: Used to identify emotions from the user's facial expressions and voice. For example, it utilizes OpenCV (an open-source computer vision library) and a machine learning model for emotion recognition (e.g., a model trained using TensorFlow or Keras).

[1709] Users access the system using a terminal and log in by entering their user ID and password. The terminal collects profile information such as the user's job title, department, area of ​​expertise, and years of experience, and sends it to the server. The server analyzes this data to identify the user's skill level and training needs, and generates training content using generative AI. The generated content is delivered to the terminal, and the user views it. The user's progress is monitored by the terminal and recorded as a log.

[1710] While users are using training content, cameras and microphones built into smart glasses or head-mounted displays analyze the user's facial expressions and voice in real time, collecting emotional data. The collected emotional data is sent to a server for analysis. This allows the training content to be adjusted to be more relaxing if the user is tense, or more challenging if they are focused.

[1711] As a concrete example, suppose a technician is wearing a head-mounted display and watching a training video on "advanced troubleshooting methods." At this time, an emotion recognition engine recognizes emotions such as "concentrating" or "being confused" in real time from the technician's facial expressions and voice while watching, and adjusts the training content accordingly.

[1712] For example, the following instructions can be given to a generative AI as a prompt:

[1713] "The user's area of ​​expertise is machine operation, with 5 years of experience, and their position is department leader. Please create training content that includes advanced troubleshooting methods within the basic operation manual."

[1714] This system allows engineers to have a more effective and personalized learning experience.

[1715] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1716] Step 1:

[1717] The terminal collects user data. The user logs into the terminal and enters information about their job title, department, area of ​​expertise, and years of experience. The terminal sends the entered user data to the server. The server then stores the user's profile information in a database.

[1718] Input: User ID and password, job title, department, area of ​​expertise, years of experience

[1719] Output: User profile information stored in the database

[1720] Step 2:

[1721] The server analyzes user data to identify training needs. The server analyzes user profile information stored in the database to identify the corresponding skill level and training needs. It then generates training content by inputting prompts into a generative AI model.

[1722] Input: User profile information stored in the database, prompt text

[1723] Data processing: Analysis of profile information and identification of training needs through the operation of AI models.

[1724] Output: User-optimized training content

[1725] Step 3:

[1726] The server generates training content and delivers it to the user's device. The server converts the generated content into a data format and sends it to the user's device. The device displays the received training content to the user, supporting their learning.

[1727] Input: Generated training content

[1728] Output: Training content delivered to the user's terminal.

[1729] Step 4:

[1730] The device monitors the user's progress and records it as a log. When the user views training content, the device collects progress data (viewed content and completed tasks) in real time and sends it to the server. The server stores this data in a database.

[1731] Input: User viewing and operation data

[1732] Data processing: Collection and organization of progress data

[1733] Output: Progress log saved in the database

[1734] Step 5:

[1735] The device collects user feedback and sends it to the server. After completing the training content, the user enters feedback on the device. The device sends this feedback data to the server, which stores it in a database.

[1736] Input: User-entered feedback data

[1737] Output: Feedback data stored in the database

[1738] Step 6:

[1739] The server analyzes the feedback data and uses it to improve future training programs. The server analyzes the collected feedback as statistics and trends, and uses the analysis results to obtain guidelines for improving future training content.

[1740] Input: Feedback data stored in the database

[1741] Data processing: Analysis of feedback data

[1742] Output: Guidelines for improving training menus based on analysis results

[1743] Step 7:

[1744] The emotion engine recognizes the user's emotions in real time. While viewing training content, the camera and microphone built into the device monitor the user's facial expressions and voice, collecting emotional data. The collected data is sent to a server, where the emotion recognition engine performs analysis.

[1745] Input: User's facial expressions and voice data

[1746] Data processing: Real-time emotional data analysis

[1747] Output: Analyzed sentiment data

[1748] Step 8:

[1749] The server adjusts training content based on emotional data. Based on collected and analyzed emotional data, the training content is adjusted in real time to ensure users learn most effectively. Specifically, if a user is feeling stressed, the content is changed to something more relaxing; if they are concentrating, it becomes more challenging.

[1750] Input: Analyzed sentiment data

[1751] Data processing: Adjusting training content based on emotional data

[1752] Output: Adjusted training content

[1753] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1754] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1755] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1756] [Fourth Embodiment]

[1757] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1758] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1759] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1760] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1761] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1762] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1763] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1764] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1765] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1766] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1767] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1768] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1769] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1770] This invention relates to a system that provides specialized training menus for government officials. This system, by incorporating the following key functions, enables a complete process from user data collection to training content generation, distribution, and feedback collection and analysis.

[1771] System-wide flow

[1772] 1. Collection of user data

[1773] The user logs into the device.

[1774] Users log in to the system using a terminal. Login information includes a user ID and password.

[1775] The device sends login information to the server.

[1776] The terminal sends the entered login information to the server. The server validates the login information and authenticates the user if successful.

[1777] Users enter their profile information.

[1778] Users enter profile information such as their job title, department, area of ​​expertise, and years of experience on their device.

[1779] The device sends profile information to the server.

[1780] The device sends the entered profile information to the server. The server receives the profile information and stores it in its database.

[1781] 2. Generating training content

[1782] The server analyzes user data.

[1783] The server analyzes the collected user profile information. The analysis identifies training needs based on the user's skill level and area of ​​expertise.

[1784] The server uses generative AI to generate training content.

[1785] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[1786] The server organizes the training content that has been generated.

[1787] The generated training content is customized and organized based on user profiles. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[1788] 3. Content distribution

[1789] The server delivers training content to the terminals.

[1790] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[1791] Users view training content using their devices.

[1792] Users access training content using their devices. For example, a user might watch a video about "the latest trends in environmental policy."

[1793] The device collects user progress data.

[1794] The device monitors the user's learning progress and records it as a log. Progress data includes viewed training content and completed assignments.

[1795] 4. Gathering feedback

[1796] Users enter feedback on their devices.

[1797] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[1798] The device sends feedback to the server.

[1799] The terminal sends the input feedback to the server. The server receives the feedback data and stores it in a database.

[1800] The server analyzes the feedback data.

[1801] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[1802] Specific examples

[1803] The following are specific examples of how to use this system.

[1804] 1. Collection of user data

[1805] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[1806] 2. Generating training content

[1807] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[1808] 3. Content distribution

[1809] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[1810] 4. Gathering feedback

[1811] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[1812] In this way, this system can provide customized training menus for administrative staff through a series of processes.

[1813] The following describes the processing flow.

[1814] Step 1:

[1815] The user logs into the device.

[1816] Users access the system using a terminal and log in by entering their user ID and password.

[1817] Step 2:

[1818] The device sends login information to the server.

[1819] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[1820] Step 3:

[1821] The user enters their profile information.

[1822] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[1823] Step 4:

[1824] The device sends profile information to the server.

[1825] The device sends the entered profile information to the server, and the server stores this data in a database.

[1826] Step 5:

[1827] The server analyzes the user data.

[1828] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[1829] Step 6:

[1830] The server uses generative AI to generate training content.

[1831] The AI ​​on the server generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[1832] Step 7:

[1833] The server organizes the training content that has been generated.

[1834] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[1835] Step 8:

[1836] The server delivers the training content to the terminals.

[1837] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[1838] Step 9:

[1839] Users view training content using their devices.

[1840] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[1841] Step 10:

[1842] The device collects user progress data.

[1843] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[1844] Step 11:

[1845] The user enters feedback on their device.

[1846] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[1847] Step 12:

[1848] The device sends feedback to the server.

[1849] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[1850] Step 13:

[1851] The server analyzes the feedback data.

[1852] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[1853] (Example 1)

[1854] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1855] Modern training programs for government officials often contain general content that doesn't align with individual job experience or specialization, making efficient and effective skill development difficult. Furthermore, insufficient feedback and progress tracking make it challenging to improve training programs and provide individualized support. To address these challenges, customized training content tailored to individual employees, along with continuous monitoring and improvement of training effectiveness, are necessary.

[1856] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1857] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; and means for generating training content based on the analysis results using a generative artificial intelligence model. This enables the automatic generation and distribution of training content optimized for each user's characteristics. Furthermore, the user's terminal includes means for distributing and displaying the generated training content to the user; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for recording the user's learning progress. This enables real-time monitoring of the user's progress and effective collection and analysis of feedback.

[1858] "Means for collecting information on the user's job title, department, area of ​​expertise, and years of experience" refers to an interface for users to input and transmit information related to their job duties, and communication means for transmitting this information to the server.

[1859] "Means for analyzing training needs based on collected information" refers to algorithms and analysis systems for analyzing collected user information and identifying the training required for each user.

[1860] "Means for generating training content based on analysis results using a generative artificial intelligence model" refers to an artificial intelligence system and related software tools for automatically generating training content according to the analysis results.

[1861] "Means for delivering and displaying generated training content on a user's device" refers to communication means and user interface for transmitting generated training content to a user's device and displaying and playing it back.

[1862] "Means of collecting user-generated feedback" refers to a form for users to input and submit feedback after training, and the means of communication for sending that feedback to the server.

[1863] "Means for analyzing collected feedback and using it to improve future training menus" refers to analytical systems and algorithms for analyzing collected feedback data and using the results to improve and optimize training programs.

[1864] "Means for recording user learning progress" refers to systems and related software tools for monitoring users' training progress and recording and retaining that data.

[1865] This invention relates to a system that provides specialized training menus for government officials. This system provides specific means for realizing a series of processes including user data collection, training content generation, content distribution, and feedback collection and analysis.

[1866] User data collection

[1867] The user logs into the device.

[1868] Users log in to the system by entering their user ID and password on their terminal. This login information is encrypted and sent from the terminal to the server. The server receives the login information, compares it with the database, and performs authentication.

[1869] Enter your profile information

[1870] Upon successful authentication, the user enters detailed profile information on their device, including their job title, department, area of ​​expertise, and years of experience. This information is also encrypted before being sent to the server and stored in the database.

[1871] Training content generation

[1872] User Data Analysis

[1873] The server analyzes the collected user profile information. Machine learning algorithms (e.g., k-means clustering) are used for the analysis to identify training needs based on the user's skill level and area of ​​expertise.

[1874] Use of generative AI

[1875] Based on the analysis results, training content is generated using a generative AI (e.g., OpenAI's GPT-3). In this process, prompts are used to instruct the AI ​​on the content to be generated. For example, the prompt "Create a lecture on the latest trends in environmental policy" is input to the generative AI.

[1876] Organizing content

[1877] The generated training content is categorized and organized according to the user's skill level and area of ​​expertise. The content is tagged and customized using natural language processing tools (e.g., spaCy).

[1878] Content distribution

[1879] Distribution of training content

[1880] The server sends the generated customized training content to the terminal. The terminal prepares the received content for the user to view and access easily.

[1881] Viewing training content

[1882] Users view the generated training content through their devices. For example, they can watch a video on "Methods for Formulating Advanced Environmental Policies."

[1883] Gathering feedback and monitoring progress

[1884] Feedback Input

[1885] After completing the training, users enter feedback on their understanding and the usefulness of the content into their terminals. This feedback information is also encrypted before being sent to the server and stored in the database.

[1886] Record of progress

[1887] The device monitors the user's learning progress (e.g., viewed, not viewed, completed assignments) in real time and records it as a log. This information is also sent to the server periodically.

[1888] Feedback analysis

[1889] The server analyzes the collected feedback and extracts statistics and trends. The analysis results can be used to improve future training content and develop new training programs.

[1890] Specific example

[1891] For example, if a user enters profile information such as "Environmental Conservation Department, Section Chief, over 10 years of experience," this information is sent to the server and stored in the database. The server then sends prompts to the generative AI to generate training content such as "Methods for Formulating Advanced Environmental Policies" or "Building Regional Partnerships." An example of a prompt might be, "Please create a lecture on methods for formulating advanced environmental policies."

[1892] Thus, the present invention makes it possible to provide training menus optimized for individual administrative staff, enabling efficient and effective skill improvement.

[1893] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1894] Step 1:

[1895] The user enters their login information.

[1896] Input: User ID and password

[1897] Specific action: The user enters their user ID and password into the login form displayed on the device and clicks the login button.

[1898] Output: Encrypted login information is sent from the terminal to the server.

[1899] Step 2:

[1900] The device sends login information to the server.

[1901] Input: Encrypted login information

[1902] Specific operation: The terminal encrypts the login information using an encryption library (e.g., OpenSSL) and sends it to the server via the HTTPS protocol.

[1903] Output: The server receives the login information.

[1904] Step 3:

[1905] The server authenticates the login information.

[1906] Input: Received login information

[1907] Specific operation: The server checks the login information against the database, and if they match, generates a JWT token and sends it to the terminal. If authentication is successful, the server generates an authentication token and returns a login success response.

[1908] Output: Authentication token and login success response

[1909] Step 4:

[1910] Users enter their profile information.

[1911] Input: Profile information such as job title, department, area of ​​expertise, and years of experience.

[1912] Specific operation: The authenticated user enters profile information such as job title, department, area of ​​expertise, and years of experience into a form displayed on the device, and clicks the save button.

[1913] Output: Encrypted profile information is sent from the device to the server.

[1914] Step 5:

[1915] The device sends profile information to the server.

[1916] Input: Encrypted profile information

[1917] Specific operation: The device serializes the profile information in JSON format and sends it to the server via the HTTPS protocol.

[1918] Output: The server receives the profile information and saves it to the database.

[1919] Step 6:

[1920] The server analyzes user data.

[1921] Input: User profile information stored in the database

[1922] Specific operation: The server uses machine learning algorithms (e.g., k-means clustering) to analyze user profile information and identify the user's skill level and training needs.

[1923] Output: Analysis results identifying user skill levels and training needs

[1924] Step 7:

[1925] The server uses generative AI to generate training content.

[1926] Input: Analysis results and prompts

[1927] Specific operation: The server inputs a prompt message into a generative AI (e.g., OpenAI's GPT-3) and generates appropriate training content. For example, the prompt message might be "Please create a lecture on the latest trends in environmental policy."

[1928] Output: Generated training content

[1929] Step 8:

[1930] The server organizes the training content.

[1931] Input: Generated training content and analysis results

[1932] Specific operation: The server uses a natural language processing tool (e.g., spaCy) to customize and organize the generated training content based on the user's skill level.

[1933] Output: Customized training content

[1934] Step 9:

[1935] The server delivers the training content.

[1936] Input: Customized training content

[1937] Specific operation: The server uses a REST API to send customized training content to the device, and the device displays it to the user.

[1938] Output: Training content delivered to the device

[1939] Step 10:

[1940] Users view training content.

[1941] Input: Distributed training content

[1942] Specific actions: The user opens training content (e.g., videos, documents) in their device's browser and watches or learns from it.

[1943] Output: User training progress data

[1944] Step 11:

[1945] The device records the user's progress data.

[1946] Input: User's learning progress

[1947] Specific operation: The device logs the tasks it has viewed or completed and periodically sends this data to the server.

[1948] Output: Log of progress data sent to the server

[1949] Step 12:

[1950] Users enter feedback

[1951] Input: Feedback on understanding and usefulness of the training content.

[1952] Specific action: After the training is completed, the user enters their evaluation and comments into the feedback form on their device and clicks the submit button.

[1953] Output: Feedback information is sent from the terminal to the server.

[1954] Step 13:

[1955] The device sends feedback to the server.

[1956] Input: Feedback information

[1957] Specific operation: The terminal serializes the feedback information in JSON format and sends it to the server via the HTTPS protocol.

[1958] Output: The server receives the feedback information and saves it to the database.

[1959] Step 14:

[1960] The server analyzes the feedback data.

[1961] Input: Feedback information stored in the database

[1962] Specific operation: The server uses data analysis tools (e.g., pandas, scikit-learn) to analyze feedback data and extract trends and statistical information.

[1963] Output: Analyzed feedback information and improvement suggestion data

[1964] (Application Example 1)

[1965] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1966] It is crucial for field workers and engineers to receive training tailored to their position, area of ​​expertise, and years of experience. However, traditional training systems struggle to provide training optimized for individual users. Furthermore, the lack of real-time training content display and audio guidance makes consistent skill development difficult.

[1967] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1968] In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting user-inputted feedback; means for analyzing the collected feedback and using it to improve future training menus; and means for displaying the training content in real time and providing voice guidance through a robot interface. This enables the provision of an optimal training program based on the user's individual needs and real-time content delivery.

[1969] "Users" refer to field workers and engineers who use the system.

[1970] "Position" refers to the job title or position a user holds within an organization.

[1971] "Department" refers to the department within the specific organization to which the user belongs.

[1972] "Specialized field" refers to the area of ​​technology or knowledge that a user is particularly familiar with.

[1973] "Years of experience" refers to the length of time a user has been engaged in a specific job or role.

[1974] "Means of collection" refers to methods and devices for obtaining necessary information from users.

[1975] "Means for analyzing training needs" refers to methods and devices for identifying the training content that users require based on collected information.

[1976] "Means for generating training content" refers to methods and devices for creating appropriate training materials and teaching aids based on analysis results.

[1977] "Terminal" refers to a device used by a user, and includes personal computers, smartphones, and other similar devices.

[1978] "Means of distribution" refers to the methods and devices used to send the generated training content to the user's device.

[1979] "Feedback" refers to evaluations and opinions from users who have received training.

[1980] A "robot interface" refers to the user interface of a robot that displays training content and provides voice guidance.

[1981] "Real-time" refers to a situation where processing or display occurs immediately.

[1982] "Guidance" refers to providing users with instructions and information through audio or text.

[1983] The system of this invention provides specialized training programs for factory workers and engineers. The system's configuration and processing are described in detail below.

[1984] System Configuration

[1985] 1. Methods for collecting user data

[1986] The server collects information such as job title, department, area of ​​expertise, and years of experience entered by users (field workers and engineers) via their terminals. The collected information is stored in a database.

[1987] 2. Methods for analyzing training needs

[1988] The server analyzes the collected user data to identify training needs based on the user's skill level and area of ​​expertise. Data analysis algorithms are used for this analysis.

[1989] 3. Means of generating training content

[1990] The server uses a generation AI model based on the analysis results to generate appropriate training content. This generation process uses prompts to meet the user's specific needs.

[1991] 4. Means of delivering content

[1992] Through a robotic interface, the generated training content is displayed in real time on the user's device. Audio guidance is also used to provide users with specific procedures and information.

[1993] 5. Methods for collecting feedback

[1994] The robot interface collects user feedback after training and sends it to a server. The collected feedback is stored in a database and used to improve future training programs.

[1995] Hardware and software to use

[1996] Hardware:

[1997] Robot interface: Displays training content and provides audio guidance.

[1998] Device: A computer or smartphone used by the user.

[1999] Server: Runs AI models for data analysis and generation.

[2000] software:

[2001] Python: Implementation of a program and analysis algorithm for generating training content.

[2002] Request Library: Uses HTTP requests to send and receive data.

[2003] JSON: Used as a format for storing and sending / receiving data.

[2004] Generative AI model: Used to generate training content.

[2005] Specific example

[2006] The user inputs information such as "engineer," "production line," and "5 years of experience" into the terminal. The server receives and analyzes this information and sends prompt messages like the following to the generation model.

[2007] Example of a prompt

[2008] Please generate detailed training content for engineers on how to operate production line equipment.

[2009] The AI ​​model generates specific training content based on this prompt and delivers it to the user through the robot interface. For example, it provides video explanations and audio guides in real time regarding "how to operate the new equipment." After the training is completed, the user provides feedback, which is used to improve the next training program.

[2010] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[2011] Step 1:

[2012] The user logs into the system from their terminal. During this process, they enter their user ID and password, which are then sent to the server. The server validates the entered data and checks the authentication information. If authentication is successful, the user gains access to the system.

[2013] Step 2:

[2014] The user enters profile information on their device. This includes job title, department, area of ​​expertise, and years of experience. The device sends this information to the server, which stores it in a database. The entered information is stored in a structured format for later analysis.

[2015] Step 3:

[2016] The server analyzes the collected user profile information. This analysis process identifies training needs based on the user's skill level and area of ​​expertise. Algorithms are used to process and calculate data and identify the most suitable training content for each user.

[2017] Step 4:

[2018] The server uses an AI model to generate training content based on the analysis results. The generation process involves inputting prompts tailored to the user's needs into the model to generate specific training content. For example, a prompt such as "Generate detailed training content on how to operate production line equipment for engineers" might be used.

[2019] Step 5:

[2020] The server delivers the generated training content to the terminal. The content is displayed in real time through a robotic interface, and audio guidance is provided. Users review and complete the training content on their terminal.

[2021] Step 6:

[2022] After the user completes the training, they enter feedback into the device. This feedback includes an evaluation of the training content and suggestions for improvement. The device then sends the feedback information to the server.

[2023] Step 7:

[2024] The server analyzes the collected feedback and stores it in a database. The analysis results are extracted as statistics and trends and used to improve future training menus and generate new training content.

[2025] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[2026] This invention provides a system that offers specialized training menus for government officials, and by combining this with an emotion engine that recognizes user emotions, it provides a more personalized training experience. This system has the following main functions: collecting user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing user emotion data.

[2027] System-wide flow

[2028] 1. Collection of user data

[2029] The user logs into the device.

[2030] Users access the system using a terminal and log in by entering their user ID and password.

[2031] The device sends login information to the server.

[2032] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[2033] Users enter their profile information.

[2034] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[2035] The device sends profile information to the server.

[2036] The device sends the entered profile information to the server, which then stores it in a database.

[2037] 2. Generating training content

[2038] The server analyzes user data.

[2039] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[2040] The server uses generative AI to generate training content.

[2041] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[2042] The server organizes the training content that has been generated.

[2043] The generated training content is customized and organized based on the user's profile. For example, beginner-level content is made more detailed, while advanced challenges are included for experienced users.

[2044] 3. Content distribution

[2045] The server delivers training content to the terminals.

[2046] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[2047] Users view training content using their devices.

[2048] Users access training content using their devices. For example, they might watch a video about "the latest trends in environmental policy."

[2049] The device collects user progress data.

[2050] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[2051] 4. Gathering feedback

[2052] Users enter feedback on their devices.

[2053] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[2054] The device sends feedback to the server.

[2055] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[2056] The server analyzes the feedback data.

[2057] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[2058] 5. Introduction of an emotional engine

[2059] The device collects user sentiment data.

[2060] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[2061] The device sends emotional data to the server.

[2062] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[2063] The server analyzes the emotional data.

[2064] The server analyzes collected emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[2065] Adjusting training content based on emotional data

[2066] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[2067] Specific examples

[2068] The following are specific examples of how to use this system.

[2069] 1. Collection of user data

[2070] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[2071] 2. Generating training content

[2072] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[2073] 3. Content distribution

[2074] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[2075] 4. Gathering feedback

[2076] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[2077] 5. Introduction of an emotional engine

[2078] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[2079] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[2080] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[2081] The following describes the processing flow.

[2082] Step 1:

[2083] The user logs into the device.

[2084] Users access the system using a terminal and log in by entering their user ID and password.

[2085] Step 2:

[2086] The device sends login information to the server.

[2087] The terminal sends the login information entered by the user to the server, and the server validates the login information. If authentication is successful, the user is authenticated.

[2088] Step 3:

[2089] The user enters their profile information.

[2090] Users enter their profile information on their device, including their job title, department, area of ​​expertise, and years of experience.

[2091] Step 4:

[2092] The device sends profile information to the server.

[2093] The device sends the entered profile information to the server, which then stores it in a database.

[2094] Step 5:

[2095] The server analyzes the user data.

[2096] The server analyzes the stored user profile information to identify training needs based on the user's skill level and area of ​​expertise.

[2097] Step 6:

[2098] The server uses generative AI to generate training content.

[2099] The generative AI generates appropriate training content based on the analysis results. For example, if the user is an employee of the environmental conservation department, it will generate content such as "the latest trends in environmental policy" or "how to cooperate with local residents."

[2100] Step 7:

[2101] The server organizes the training content that has been generated.

[2102] The server customizes and organizes the generated training content based on the user's profile. For example, it provides detailed content for beginners and includes high-level challenges for experienced users.

[2103] Step 8:

[2104] The server delivers the training content to the terminals.

[2105] The server sends the generated customized training content to the terminal. The terminal receives the delivered content and prepares to display it to the user.

[2106] Step 9:

[2107] Users view training content using their devices.

[2108] Users access training content using their devices, for example, by watching a video on "the latest trends in environmental policy."

[2109] Step 10:

[2110] The device collects user progress data.

[2111] The device monitors the user's learning progress and records the training content viewed and completed assignments as logs.

[2112] Step 11:

[2113] The user enters feedback on their device.

[2114] After completing the training, users input feedback on their understanding and the usefulness of the content into their device.

[2115] Step 12:

[2116] The device sends feedback to the server.

[2117] The terminal sends the input feedback to the server, which receives the feedback data and stores it in a database.

[2118] Step 13:

[2119] The server analyzes the feedback data.

[2120] The server analyzes feedback data and extracts statistics and trends. The analysis results are then used to improve future training programs and generate new training content.

[2121] Step 14:

[2122] The device collects user emotion data.

[2123] The emotion engine recognizes the user's emotions and collects emotional data, for example, from the user's facial expressions and voice.

[2124] Step 15:

[2125] The device sends emotional data to the server.

[2126] The device sends the collected emotional data to the server. The server receives the emotional data and stores it in a database.

[2127] Step 16:

[2128] The server analyzes the emotional data.

[2129] The server analyzes collected emotional data to evaluate the user's comfort level and learning effectiveness. This makes it possible to further improve the user's learning experience.

[2130] Step 17:

[2131] The server adjusts training content based on emotional data.

[2132] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[2133] Specific examples

[2134] 1. Collection of user data

[2135] The user enters information such as "Environmental Conservation Department, Section Chief, over 10 years of experience" into the terminal. The terminal sends this information to the server, which then stores it in a database.

[2136] 2. Generating training content

[2137] Based on data such as "environmental conservation department" and "more than 10 years of experience," the server uses a generative AI to generate training content such as "methods for formulating advanced environmental policies" and "building regional partnerships."

[2138] 3. Content distribution

[2139] The server delivers the generated training content to the terminal, and the terminal displays it to the user. The user watches a video about "How to formulate advanced environmental policies."

[2140] 4. Gathering feedback

[2141] After watching a video, users input feedback into their device, such as "The content was detailed and helpful" or "I would like to see more examples," and the device sends this feedback to the server.

[2142] 5. Introduction of an emotional engine

[2143] The emotion engine collects emotional data from the user's facial expressions while they are watching a video, identifying emotions such as "concentrated" or "excited."

[2144] The device sends emotional data to the server, which analyzes the data and uses it to assess the appropriateness of the training content and to adjust future content.

[2145] Thus, this system can provide customized training menus for government officials through a series of processes and an emotion engine. By collecting and analyzing emotion data, it is possible to further improve the user's learning experience.

[2146] (Example 2)

[2147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2148] Traditional training systems have struggled to provide training content that caters to the diverse needs and skill levels of individual users. Furthermore, the lack of a means to deliver personalized training experiences that consider user emotions hindered the improvement of training effectiveness. Additionally, insufficient post-training feedback and progress tracking made continuous improvement of training programs difficult.

[2149] In Example 2, the identification processing performed by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for collecting user emotion data; and means for analyzing the collected emotion data and using it to adjust the training content. This makes it possible to provide a personalized training experience based on the user's individual needs and emotions, thereby improving training effectiveness. Furthermore, it is possible to continuously improve the training menu based on the collected feedback and progress data.

[2150] "Users" refer to government officials who use the system to receive training, or those who perform corresponding duties.

[2151] A "terminal" refers to a computer or mobile device that a user uses to access a system.

[2152] A "server" refers to a central processing unit that performs tasks such as collecting and analyzing user data, generating and distributing training content, collecting and analyzing feedback, and collecting and analyzing sentiment data.

[2153] "Training content" refers to learning resources such as educational materials, videos, and documents generated based on the user's training needs.

[2154] "Feedback" refers to the opinions and evaluations that users provide after using training content.

[2155] "Emotional data" refers to information about a user's emotional state, collected from their facial expressions, voice, and other sources.

[2156] "Generative AI models" refer to artificial intelligence technologies (e.g., OpenAI GPT-3) that generate appropriate training content based on user data.

[2157] A "prompt" refers to the text of instructions or questions that are input to a generative AI model.

[2158] "Methods for analyzing training needs" refers to the process of identifying the most suitable training content for a given user based on collected user data.

[2159] "Methods for generating training content based on analysis results" refers to the process of creating training content based on analysis results using a generative AI model.

[2160] "Means of collecting user emotion data" refers to a function that recognizes emotions from the user's facial expressions and voice and collects that data.

[2161] "Means of analyzing collected emotional data and using it to adjust training content" refers to the process of analyzing collected emotional data to improve the suitability of training content according to the user's state.

[2162] This invention is a system that provides specialized training menus for government officials. This system collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user emotional data. By combining this with an emotional engine, it can provide a more personalized training experience.

[2163] The hardware required to implement the system includes terminals for user access (e.g., personal computers and smartphones), servers (cloud servers are also applicable), and input devices such as cameras and microphones for recognizing user emotions. The software includes generative AI models (e.g., OpenAI GPT-3), data analysis tools, database management systems, and emotion recognition software (e.g., Affectiva).

[2164] User data collection

[2165] Users access the system using a terminal and log in by entering their user ID and password. The login information is sent from the terminal to the server, which validates the login information and authenticates the user if authentication is successful. Subsequently, the user enters profile information such as their job title, department, area of ​​expertise, and years of experience into a form on the terminal, which sends this information to the server, and the server stores it in a database.

[2166] Training content generation

[2167] The server analyzes stored user profile information and uses a generative AI model (OpenAI GPT-3) to identify training needs based on the user's skill level and area of ​​expertise. For example, if the user is an employee of the environmental conservation department, training content will be generated that includes topics such as "the latest trends in environmental policy" and "how to cooperate with local residents." The generated content is customized based on the user's profile, including detailed explanations for beginners and high-level challenges for experienced users.

[2168] Example of a prompt:

[2169] "Please generate training content for a user who is a manager in the environmental conservation department, based on their more than 10 years of experience in developing advanced environmental policies."

[2170] Content distribution

[2171] The server delivers the generated customized training content to the terminal, which receives the content and prepares to display it to the user. The user uses the terminal to view the training content, for example, by watching a video on "Latest Trends in Environmental Policy." The terminal monitors the user's learning progress and records the viewed training content and completed assignments as logs. Based on this, the user's progress can be tracked.

[2172] Feedback collection and analysis

[2173] After completing a training session, users input feedback on their understanding and the usefulness of the content into a terminal. The terminal sends the input feedback to a server, which receives the feedback data and stores it in a database. The server analyzes the feedback data and extracts statistics and trends. The analysis results are used to improve future training menus and generate new training content.

[2174] Introducing an emotional engine

[2175] Emotion engines (such as Affectiva) collect emotional data from users' facial expressions and voice. For example, they capture a user's facial expressions with a camera while they are watching a video and analyze their emotions. The collected emotional data is sent to a server via the device, where it is analyzed to evaluate the user's comfort level and learning effectiveness. Based on the analysis results, the difficulty level and content of the training can be adjusted to make it more relaxing for the user.

[2176] In this way, the system provides customized training menus for government officials, realizing an optimal learning experience based on the individual needs and emotions of the users.

[2177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2178] Step 1:

[2179] The user logs into the device.

[2180] The user accesses the system's login page and enters their user ID and password. The terminal then sends this login information to the server. The server receives this information and executes an authentication query against the database. If authentication is successful, the server initiates a session and issues an authentication token.

[2181] Input: User ID, Password

[2182] Output: Authentication token

[2183] Step 2:

[2184] The device sends login information to the server.

[2185] The entered user ID and password are sent from the device to the server. The server validates the received information and, if correct, returns an authentication token to the device.

[2186] Input: User ID, Password

[2187] Output: Authentication result, authentication token

[2188] Step 3:

[2189] The user enters their profile information.

[2190] After successful authentication, the user enters profile information such as job title, department, area of ​​expertise, and years of experience into the device.

[2191] Input: Position, Department, Specialty, Years of Experience

[2192] Output: Profile Information

[2193] Step 4:

[2194] The device sends profile information to the server.

[2195] Once the user's profile information is entered, the device sends it to the server. The server then stores the received information in its database.

[2196] Input: Profile Information

[2197] Output: Profile information stored in the database

[2198] Step 5:

[2199] The server analyzes the user data.

[2200] The server retrieves and analyzes user profile information stored in the database. This identifies training needs based on the user's skill level and area of ​​expertise.

[2201] Input: Profile information stored in the database

[2202] Output: Training needs analysis results

[2203] Step 6:

[2204] The server uses generative AI to generate training content.

[2205] The server inputs prompt text into a generative AI model (e.g., OpenAI GPT-3) based on the analysis results. The generative AI generates appropriate training content and returns the result to the server.

[2206] Input: Training needs analysis results

[2207] Output: Generated training content

[2208] Step 7:

[2209] The server organizes the training content that has been generated.

[2210] The server analyzes the generated training content and customizes it based on the user's profile. For example, it includes detailed content for beginners and high-level challenges for experienced users.

[2211] Input: Generated training content

[2212] Output: Customized training content

[2213] Step 8:

[2214] The server delivers the training content to the terminals.

[2215] The server sends the generated customized training content to the terminal. The terminal receives the content and prepares to display it to the user.

[2216] Input: Customized training content

[2217] Output: Training content delivered to the terminal

[2218] Step 9:

[2219] Users view training content using their devices.

[2220] Users view training content displayed on their devices and check videos and materials.

[2221] Input: Training content delivered to the device

[2222] Output: Viewed training content

[2223] Step 10:

[2224] The device collects user progress data.

[2225] While the user is viewing the training content, the device monitors the user's learning progress and records the content viewed and completed assignments as logs.

[2226] Input: User's learning progress information

[2227] Output: Progress data recorded as a log.

[2228] Step 11:

[2229] The user enters feedback on their device.

[2230] After the training is completed, users will enter feedback on their understanding of the content and its usefulness into a feedback form on their device.

[2231] Input: Feedback Information

[2232] Output: Input feedback

[2233] Step 12:

[2234] The device sends feedback to the server.

[2235] The feedback entered by the user is sent from the device to the server, and the server stores the feedback data in a database.

[2236] Input: Input feedback

[2237] Output: Feedback stored in the database

[2238] Step 13:

[2239] The server analyzes the feedback data.

[2240] The server retrieves and analyzes the stored feedback data. The analysis results will be used to improve future training menus and generate new content.

[2241] Input: Feedback stored in the database

[2242] Output: Feedback analysis results

[2243] Step 14:

[2244] The device collects user emotion data.

[2245] Emotion recognition software collects emotional data from the user's facial expressions and voice. For example, it captures the user's facial expressions with a camera while they are watching a video and analyzes their emotions.

[2246] Input: User's facial expressions, voice data

[2247] Output: Collected sentiment data

[2248] Step 15:

[2249] The device sends emotional data to the server.

[2250] The collected emotional data is sent from the device to the server, which then stores the data in a database.

[2251] Input: Collected emotional data

[2252] Output: Sentiment data stored in the database

[2253] Step 16:

[2254] The server analyzes the emotional data.

[2255] The server analyzes stored emotional data to evaluate user comfort and learning effectiveness. The analysis results are used to adjust and personalize training content.

[2256] Input: Saved emotion data

[2257] Output: Sentiment data analysis results

[2258] Step 17:

[2259] We will adjust training content based on emotional data.

[2260] The server adjusts the difficulty level and content of the training materials based on the analysis results. For example, if a user is feeling nervous, the content will be changed to something more relaxing.

[2261] Input: Sentiment data analysis results

[2262] Output: Adjusted training content

[2263] (Application Example 2)

[2264] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2265] While conventional training systems could provide personalized content based on users' job titles and areas of expertise, they had limitations in personalizing content that took into account users' psychological states and emotions. Furthermore, the lack of technology to collect and analyze emotional data and adjust training content in real time based on that data made it difficult to maximize user learning effectiveness.

[2266] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information on the user's job title, department, field of expertise, and years of experience; means for analyzing training needs based on the collected information; means for generating training content based on the analysis results; means for distributing the generated training content to the user's terminal; means for collecting feedback entered by the user; means for analyzing the collected feedback and using it to improve future training menus; means for recognizing the user's emotions; means for collecting and analyzing user emotion data; and means for adjusting the training content based on the user's emotion data. This makes it possible to adjust the training content in real time according to the user's psychological state and maximize the learning effect.

[2267] "Position" refers to a role or authority within an organization.

[2268] "Department" refers to a division within an organization that has specific duties or functions.

[2269] A "specialized field" refers to an area that focuses on a specific technology or knowledge.

[2270] "Years of experience" refers to the number of years a user has accumulated practical experience in their field of expertise or position.

[2271] "Training needs" refer to the training content and skill improvement requirements that users desire.

[2272] "Analysis" refers to the process of thoroughly examining collected information and deriving its meaning.

[2273] "Generation" means creating new training content based on the analysis results.

[2274] "Distribution" refers to sending the created training content to the user's device.

[2275] "Feedback" refers to the opinions, impressions, and evaluations provided by users.

[2276] "Means of recognizing emotions" refers to methods of detecting a user's psychological state and emotions from their facial expressions, voice, etc.

[2277] "Emotional data" refers to information about a user's emotional state, and includes data obtained through methods such as facial expression and voice analysis.

[2278] "Means of adjustment" refers to the process of changing the content and difficulty level of training materials based on collected and analyzed information.

[2279] "Real-time" means that processing and reactions occur almost simultaneously with real-world time.

[2280] The system of this invention collects user data, generates and distributes training content, collects and analyzes feedback, and collects and analyzes user sentiment data in order to personalize training content.

[2281] The system uses the following main hardware and software components.

[2282] 1. User terminals: Devices used by users include smartphones, smart glasses, and head-mounted displays. These devices are used for data entry, content display, and sentiment data collection.

[2283] 2. Server: A central management system is required for analyzing user data, generating and distributing training content, analyzing feedback, and analyzing sentiment data. This server consists of various software modules that receive and analyze data from the user interface.

[2284] 3. Generative AI: Used to generate training content based on user data. The generative AI model is implemented in Python and creates customized training materials and assignments based on the user's profile data.

[2285] 4. Emotion Recognition Engine: Used to identify emotions from the user's facial expressions and voice. For example, it utilizes OpenCV (an open-source computer vision library) and a machine learning model for emotion recognition (e.g., a model trained using TensorFlow or Keras).

[2286] Users access the system using a terminal and log in by entering their user ID and password. The terminal collects profile information such as the user's job title, department, area of ​​expertise, and years of experience, and sends it to the server. The server analyzes this data to identify the user's skill level and training needs, and generates training content using generative AI. The generated content is delivered to the terminal, and the user views it. The user's progress is monitored by the terminal and recorded as a log.

[2287] While users are using training content, cameras and microphones built into smart glasses or head-mounted displays analyze the user's facial expressions and voice in real time, collecting emotional data. The collected emotional data is sent to a server for analysis. This allows the training content to be adjusted to be more relaxing if the user is tense, or more challenging if they are focused.

[2288] As a concrete example, suppose a technician is wearing a head-mounted display and watching a training video on "advanced troubleshooting methods." At this time, an emotion recognition engine recognizes emotions such as "concentrating" or "being confused" in real time from the technician's facial expressions and voice while watching, and adjusts the training content accordingly.

[2289] For example, the following instructions can be given to a generative AI as a prompt:

[2290] "The user's area of ​​expertise is machine operation, with 5 years of experience, and their position is department leader. Please create training content that includes advanced troubleshooting methods within the basic operation manual."

[2291] This system allows engineers to have a more effective and personalized learning experience.

[2292] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2293] Step 1:

[2294] The terminal collects user data. The user logs into the terminal and enters information about their job title, department, area of ​​expertise, and years of experience. The terminal sends the entered user data to the server. The server then stores the user's profile information in a database.

[2295] Input: User ID and password, job title, department, area of ​​expertise, years of experience

[2296] Output: User profile information stored in the database

[2297] Step 2:

[2298] The server analyzes user data to identify training needs. The server analyzes user profile information stored in the database to identify the corresponding skill level and training needs. It then generates training content by inputting prompts into a generative AI model.

[2299] Input: User profile information stored in the database, prompt text

[2300] Data processing: Analysis of profile information and identification of training needs through the operation of AI models.

[2301] Output: User-optimized training content

[2302] Step 3:

[2303] The server generates training content and delivers it to the user's device. The server converts the generated content into a data format and sends it to the user's device. The device displays the received training content to the user, supporting their learning.

[2304] Input: Generated training content

[2305] Output: Training content delivered to the user's terminal.

[2306] Step 4:

[2307] The device monitors the user's progress and records it as a log. When the user views training content, the device collects progress data (viewed content and completed tasks) in real time and sends it to the server. The server stores this data in a database.

[2308] Input: User viewing and operation data

[2309] Data processing: Collection and organization of progress data

[2310] Output: Progress log saved in the database

[2311] Step 5:

[2312] The device collects user feedback and sends it to the server. After completing the training content, the user enters feedback on the device. The device sends this feedback data to the server, which stores it in a database.

[2313] Input: User-entered feedback data

[2314] Output: Feedback data stored in the database

[2315] Step 6:

[2316] The server analyzes the feedback data and uses it to improve future training programs. The server analyzes the collected feedback as statistics and trends, and uses the analysis results to obtain guidelines for improving future training content.

[2317] Input: Feedback data stored in the database

[2318] Data processing: Analysis of feedback data

[2319] Output: Guidelines for improving training menus based on analysis results

[2320] Step 7:

[2321] The emotion engine recognizes the user's emotions in real time. While viewing training content, the camera and microphone built into the device monitor the user's facial expressions and voice, collecting emotional data. The collected data is sent to a server, where the emotion recognition engine ...

Claims

1. A means of collecting information on the user's job title, department, area of ​​expertise, and years of experience, A means of analyzing training needs based on collected information, A means of generating training content based on analysis results, A means of delivering the generated training content to the user's device, A means of collecting user-generated feedback, A means of analyzing the collected feedback and using it to improve future training menus, A system that includes this.

2. The system according to claim 1, which identifies the user's skill level based on collected information and generates training content suitable for that level.

3. The system according to claim 1, further comprising means for monitoring the user's progress and recording it as a log.

Images