system

Abstract

We provide the system. [Solution] A means for receiving input data, A means of saving the received data, Methods for training machine learning models based on stored data, A means for generating a user-specific training plan using a pre-trained model, A means of displaying the generated learning plan to the user. A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is difficult for engineers to make an effective learning plan and schedule for qualification exams in order to improve their careers. Also, there are few means to grasp the progress of learning in real time, making it difficult to proceed with learning efficiently. There is a need for a system that proposes an optimal learning path for engineers to acquire the necessary skill sets and knowledge and provides a specific plan.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, and means for displaying the generated learning plan to the user. Furthermore, by also including means for pre-processing the received data and means for generating a qualification exam schedule based on the user's skill set and goals, the system enables the user to proceed with learning efficiently.

[0006] "Means for receiving input data" refers to the interface and process by which users input their own information, skill sets, goals, and other necessary data into the system.

[0007] "Means for storing received data" refers to methods and systems for securely and efficiently storing data received from users in a database or other storage medium.

[0008] "Methods for training machine learning models based on stored data" refers to the process of using stored data to apply machine learning algorithms and build and train successful machine learning models.

[0009] "Means for generating user-specific learning plans using pre-trained models" refers to a process that uses pre-trained machine learning models to automatically create learning plans tailored to each user's individual goals and skill sets.

[0010] "Means for displaying the generated learning plan to the user" refers to an interface and display method for visually presenting the generated learning plan in a way that the user can easily understand and implement.

[0011] "Means for pre-processing received data" refers to the process of pre-processing data collected from users, such as converting it into an appropriate format and supplementing any deficiencies.

[0012] "A means of generating a certification exam schedule based on the user's skill set and goals" refers to a process that proposes the optimal date for a certification exam based on the user's skill set and set goals, and provides functions such as alerts. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0017] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a system that enables engineers to learn efficiently and achieve their goals. Specific embodiments thereof are described below.

[0035] System-wide configuration

[0036] The system consists of means for user data input, server-side data storage and model training, and terminal-side provision of a user interface.

[0037] Data collection

[0038] The user first logs into the system. After logging in, the user enters their technical experience, skill set, learning history, and goals they wish to achieve. This data is entered through an input form on the terminal.

[0039] The server validates the input data in real time and saves it to the database in the appropriate format. This includes checking for blank fields and verifying the format. If validation is successful, the data is securely stored. The saved data is stored in a database such as MySQL® or MongoDB.

[0040] Model Learning

[0041] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[0042] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is also useful for the user, helping them to understand the progress of the learning process.

[0043] Generating a learning plan

[0044] Users input their goals and current skill sets into the system. For example, they might input a goal such as "I want to pass the AWS® Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[0045] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[0046] Furthermore, the server also generates a schedule for certification exams. Based on the user's goals, it might schedule an exam six months in advance and present study content and a timeline for exam preparation. This schedule is designed to allow users to study efficiently and prepare for the exam.

[0047] Displaying the study plan

[0048] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0049] Specific example

[0050] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0051] In this way, the present invention makes it possible to provide a system that enables engineers to efficiently advance their learning and achieve their desired goals.

[0052] The following describes the processing flow.

[0053] Step 1:

[0054] The user logs into the system.

[0055] The user enters their ID and password and clicks the login button.

[0056] The server compares the received authentication information with the database and redirects the user to the dashboard if authentication is successful.

[0057] Step 2:

[0058] Users enter their own background, skill set, and goals.

[0059] Users enter detailed technical information into the input form. Specifically, they fill in information such as past project experience, technologies used, qualifications obtained, and learning history.

[0060] The terminal provides an interface to assist in inputting this information.

[0061] Step 3:

[0062] The server saves the entered data.

[0063] The server validates the entered data in real time, checking whether all required fields are filled in and whether the data format is correct.

[0064] Save the data that passed validation to the database.

[0065] Step 4:

[0066] The server trains a machine learning model based on the stored data.

[0067] The server retrieves engineer profile information from the database and performs preprocessing. Preprocessing includes data normalization and imputation of missing values.

[0068] The data is split into training data and test data, and a model is trained using algorithms such as support vector machines or neural networks.

[0069] Step 5:

[0070] The server monitors the progress of the learning model.

[0071] The server records the progress of the learning process (e.g., accuracy, changes in the loss function).

[0072] The device displays this information in real time in a dashboard format, allowing users to check their learning progress.

[0073] Step 6:

[0074] The server saves the model once training is complete.

[0075] The server either saves the trained model as a model file or stores it in a database for persistent storage.

[0076] Step 7:

[0077] The user enters their goals and skill set.

[0078] The user accesses the system again and enters their goal (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[0079] The terminal provides an interface for efficiently inputting and managing this information.

[0080] Step 8:

[0081] The server generates a learning plan based on the entered goals and skill set.

[0082] The server retrieves the information entered by the user and generates an appropriate training plan based on the trained model.

[0083] A study plan includes specific learning content, recommended resources, and a study schedule.

[0084] Step 9:

[0085] The server generates the schedule for the certification exam.

[0086] The server sets appropriate certification exam dates according to the user's goals.

[0087] The proposed exam schedule will include the exam date and time, preparation period, and important deadlines.

[0088] Step 10:

[0089] The device displays the generated study plan and qualification exam schedule.

[0090] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[0091] Users can begin learning based on this information.

[0092] (Example 1)

[0093] 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."

[0094] Conventional learning systems for engineers have suffered from insufficient automatic generation of learning plans and certification exam schedules tailored to individual user skill sets and goals, making it difficult for users to learn efficiently. Furthermore, the training of machine learning models based on stored data and the generation of learning plans using the results were rarely applied, and real-time tracking of user progress and the display of visual learning plans were incomplete, resulting in decreased user learning efficiency.

[0095] 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.

[0096] In this invention, the server includes means for receiving input information, means for storing the received information in a storage device, means for training a machine learning algorithm based on the stored information, means for generating a user-specific learning plan using the trained algorithm, and means for displaying the generated learning plan on a user interface. This makes it possible to automatically generate learning plans and qualification exam schedules tailored to the user's individual skill set and goals, and further enables users to efficiently progress in their studies by tracking progress in real time and visually displaying the learning plan.

[0097] "Input information" refers to various data that users provide to the system, such as their career history, skill set, learning history, and goals.

[0098] A "memory device" is a database or storage system used to store received information.

[0099] A "machine learning algorithm" is a mathematical model or computational method that learns from stored information and performs predictions and classifications.

[0100] A "user interface" is a visual interface through which a user interacts with a system, inputting data and viewing plans.

[0101] A "learning plan" is a set of specific learning content and schedule generated by the system to help the user achieve their goals.

[0102] The "certification exam schedule" refers to the date and time of the certification exam and the preparation timeline, which are set based on the user's goals.

[0103] "Real-time tracking" is a function that allows the system to monitor and record the user's learning progress in real time.

[0104] This invention is a system that enables engineers to learn efficiently and achieve their goals, and it functions through user data input, server-based data storage and model learning, and terminal-based provision of a user interface. Specific embodiments of the system are described below.

[0105] Hardware and software to use

[0106] The device provides an input form for the user to log in and enter data. Specifically, a web browser or mobile application is used.

[0107] The server stores data and trains machine learning models. Relational databases such as MySQL and MongoDB, as well as NoSQL databases, are used as databases. Machine learning algorithms include support vector machines, random forests, and neural networks.

[0108] The device provides a user interface for displaying study plans and qualification exam schedules, and also includes progress tracking and reminder functions.

[0109] Data collection and storage

[0110] Users log into the system and enter their work history, skill set, learning history, and goals they wish to achieve. This data is entered through input forms on the device and transmitted to the server in real time.

[0111] The server validates the submitted data in real time, checking for blank fields and verifying the format. Data that passes validation is securely stored in a MySQL or MongoDB database.

[0112] Training machine learning models

[0113] The server periodically retrieves stored data and performs data preprocessing (such as normalizing numerical data and imputing missing values). Then, it trains machine learning models using algorithms such as support vector machines, random forests, and neural networks. The trained models learn the characteristics and patterns of successful engineers and use that information to make predictions.

[0114] Generation and display of learning plans

[0115] Similarly, users input their goals and current skill sets into the system. For example, they might input a goal such as "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience.

[0116] The server generates a personalized learning plan for each user based on pre-trained models. Specifically, this plan includes weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also generates a certification exam schedule, for example, setting the exam six months in advance and providing study content and a timeline for exam preparation.

[0117] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0118] Specific example

[0119] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0120] Example of a prompt

[0121] "Please create a study plan to obtain the AWS Certified Solutions Architect certification. My current skill set includes Python and basic networking knowledge. The exam is scheduled for six months from now."

[0122] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve their desired goals.

[0123] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0124] Step 1: User Login

[0125] Operation: The user enters their username and password on the system's login screen and submits the authentication information.

[0126] Input: Username, Password

[0127] Data processing or calculation: The server receives authentication information and performs authentication by comparing it with user information in the database.

[0128] Output: The authentication result is returned, and if successful, a user session is started.

[0129] Step 2: Data Entry

[0130] Operation: The user uses the terminal's input form to enter their background, skill set, learning history, and goals.

[0131] Input: User background, skill set, learning history, goals

[0132] Data processing or calculation: The terminal collects the input data and sends it to the server.

[0133] Output: Data is sent to the server.

[0134] Step 3: Data Validation

[0135] Operation: The server checks for blank fields and verifies the format of the received data.

[0136] Input: Data entered by the user

[0137] Data processing or calculation: The server performs data blank detection and format validation.

[0138] Output: Validation results are output, and successful data proceeds to the next step.

[0139] Step 4: Save Data

[0140] Operation: The server saves data that has successfully been validated to a database such as MySQL or MongoDB.

[0141] Input: Data that successfully passed validation

[0142] Data processing or calculation: The server executes an insert query (INSERT) against the database.

[0143] Output: The data is saved to the database.

[0144] Step 5: Data Retrieval

[0145] Operation: The server periodically queries and retrieves stored data.

[0146] Input: Query against stored data

[0147] Data processing or calculation: The server retrieves the necessary data from the database using SQL or NoSQL queries.

[0148] Output: The acquired data proceeds to the next step.

[0149] Step 6: Data Preprocessing

[0150] Operation: The server performs preprocessing on the retrieved data, such as normalizing numerical data and imputing missing values.

[0151] Input: Acquired data

[0152] Data processing or calculations: The server performs data normalization (e.g., Min-Max Scaling or Standard Scaler) and imputation of missing values ​​(e.g., mean imputation).

[0153] Output: Pre-processed data is obtained.

[0154] Step 7: Training the machine learning model

[0155] Operation: The server applies machine learning algorithms (e.g., support vector machines, random forests, neural networks) to preprocessed data and trains the model.

[0156] Input: Preprocessed data

[0157] Data processing or computation: The server uses the specified algorithm to train the training data and optimize the model parameters.

[0158] Output: Trained machine learning model.

[0159] Step 8: Display the dashboard

[0160] Operation: The terminal displays the training progress received from the server as graphs and charts.

[0161] Input: Training progress (e.g., model accuracy, change in loss function)

[0162] Data processing or calculation: The terminal generates graphs and charts to visualize the received data.

[0163] Output: A progress dashboard is displayed to the user.

[0164] Step 9: Enter a new goal

[0165] Operation: The user enters a new goal (e.g., obtaining AWS Certified Solutions Architect certification) and their current skill set into the system.

[0166] Input: Goals and current skill set

[0167] Data processing or calculation: The terminal sends the input to the server.

[0168] Output: New goal and skill set data is sent to the server.

[0169] Step 10: Generating a study plan

[0170] Operation: The server generates individual learning plans using pre-trained models based on new goals and skill sets.

[0171] Input: New goals and skill sets

[0172] Data processing or computation: The server uses the trained model to generate an optimal learning plan (weekly learning content, recommended materials, and progress tracking methods).

[0173] Output: The generated training plan.

[0174] Step 11: Generate a schedule for the certification exam.

[0175] Operation: The server generates a qualification exam schedule based on the user's goals, for example, setting an exam date six months in advance.

[0176] Input: User's goal

[0177] Data processing or calculation: The server uses a schedule generation algorithm to set the test schedule.

[0178] Output: Qualification exam schedule.

[0179] Step 12: Display your study plan and schedule

[0180] Operation: The device displays the generated study plan and qualification exam schedule in a calendar format.

[0181] Input: Study plan, qualification exam schedule

[0182] Data processing or calculation: The terminal generates a calendar that visualizes the learning plan and schedule.

[0183] Output: Study plan and exam schedule in calendar format.

[0184] Step 13: Track progress

[0185] Operation: The device tracks the user's learning progress in real time and displays the completion status of planned learning content.

[0186] Input: Progress data

[0187] Data processing or calculation: The terminal analyzes progress data and generates completion status and reminders.

[0188] Output: Display of progress and reminders.

[0189] (Application Example 1)

[0190] 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."

[0191] Conventional technologies have made it difficult to create concrete learning plans for engineers and operators working in factories, based on their individual skill levels and goals. Furthermore, the lack of real-time means to monitor work procedures and learning progress hindered effective skill development. This invention aims to solve these problems and provide a system that supports efficient skill development for engineers within factories.

[0192] 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.

[0193] In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan on a display device, means for displaying work procedures and learning progress in real time using the display device, and means for notifying the user of reminders regarding work procedures and learning progress. This enables engineers and operators to obtain an optimal learning plan based on their own skill set and goals, and to efficiently improve their skills while checking their progress in real time.

[0194] "Means for receiving input data" refers to a device or function that provides an interface for a user to input their career history, skill set, learning history, and goals into the system.

[0195] "Means for storing received data" refers to a device or function for securely storing data entered by a user in a storage device such as a database, after properly validating it.

[0196] "Means for training machine learning models based on stored data" refers to a device or function for appropriately preprocessing stored user data and training machine learning models using algorithms such as support vector machines or neural networks.

[0197] "Means for generating a user-specific learning plan using a pre-trained model" refers to a device or function that automatically generates an optimal, customized learning plan for each user using a pre-trained machine learning model.

[0198] "Means for displaying the generated learning plan on a display device" refers to a device or function for visually displaying the generated user-specific learning plan.

[0199] "Means for displaying work procedures and learning progress in real time using a display device" refers to a device or function for displaying work procedures and learning progress on a display device so that they can be visually confirmed in real time.

[0200] "Means for notifying users of work procedures and learning progress" refers to a device or function for sending notifications regarding work procedures and learning progress as reminders to users.

[0201] This invention provides a system that enables engineers to learn efficiently and achieve their goals. The following describes specific embodiments of the invention.

[0202] The system consists of user terminals, servers, and display devices.

[0203] First, the user logs into the terminal and enters their work history, skill set, learning history, and goals. The terminal receives the input data and sends it to the server. The server validates the received data in real time and securely stores it in a database such as MySQL or MongoDB.

[0204] The stored data is periodically retrieved by the server and used to train machine learning models. Data preprocessing includes imputation of missing values ​​and normalization of numerical data. Subsequently, the models are trained using algorithms such as support vector machines and neural networks.

[0205] The device uses a pre-trained model to generate a personalized learning plan for each user. For example, for a user whose goal is to "pass the AWS Certified Solutions Architect exam," the system automatically generates specific weekly study content, recommended reference materials, and progress tracking methods. This plan is customized according to the user's skill set and goals.

[0206] Furthermore, the server displays the generated learning plan in real time on a display device. This display device is expected to be a smart glasses or head-mounted display. This allows the user to check work procedures and learning progress in real time. The display device also has a function to notify users of reminders regarding work procedures and learning progress.

[0207] To illustrate the process using a concrete example, consider a scenario where a user wears smart glasses and performs machine maintenance work in a factory. The user inputs their skill set (e.g., basic knowledge of Python and networking) into the system and sets a goal (e.g., acquiring a specific machine maintenance skill). The system receives this information, stores it in a database, and generates an appropriate learning plan using a trained model. The smart glasses display the work procedures and learning progress in real time within the user's field of view.

[0208] Examples of prompt statements to input into a generative AI model are as follows:

[0209] User skill set: X, Y, Z

[0210] Objective: To acquire basic maintenance skills.

[0211] Desired time: 1 month

[0212] Based on this prompt, the system provides a learning plan and real-time display to help engineers efficiently improve their skills.

[0213] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0214] Step 1:

[0215] The user logs into the device and enters their background, skill set, learning history, and goals. The entered data is received by the device and sent to the server.

[0216] Input: User background, skill set, learning history, goals

[0217] Output: Received data

[0218] Specific operation: The user enters the required information into the input form on the terminal and clicks the submit button. The terminal receives the input data and sends it to the server.

[0219] Step 2:

[0220] The server validates the received data and saves it to a database such as MySQL or MongoDB. Validation includes checking for blank fields and verifying data format.

[0221] Input: Received data

[0222] Output: Saving validated data

[0223] Specific operation: The server checks for blank fields and formatting of the received data, and then saves it to the database after formatting it appropriately.

[0224] Step 3:

[0225] The server periodically retrieves and preprocesses the stored data. Data preprocessing includes imputing missing values ​​and normalizing numerical data.

[0226] Input: Saved data

[0227] Output: Preprocessed data

[0228] Specific operation: The server reads the stored data and automatically performs preprocessing such as imputing missing values ​​and normalizing numerical data.

[0229] Step 4:

[0230] The server uses the preprocessed data to train machine learning models using algorithms such as support vector machines and neural networks.

[0231] Input: Preprocessed data

[0232] Output: Trained model

[0233] Specific operation: The server inputs pre-processed data into the algorithm and trains the model for a specified number of epochs.

[0234] Step 5:

[0235] The server uses a pre-trained model to generate a personalized learning plan for the user. The generated plan includes specific weekly learning content, recommended reference materials, and progress tracking methods.

[0236] Input: Trained model and user data

[0237] Output: User-specific learning plan

[0238] Specific operation: The server inputs the user's skill set and goals into a pre-trained model and automatically generates an optimal learning plan.

[0239] Step 6:

[0240] The server sends the generated learning plan to a display device for real-time display. Smart glasses or head-mounted displays are used as the display device.

[0241] Input: User-specific learning plan

[0242] Output: Display of the learning plan on the display device.

[0243] Specific operation: The server sends the generated learning plan to smart glasses or a head-mounted display, allowing the user to view it in real time.

[0244] Step 7:

[0245] The display device shows work procedures and learning progress in real time and notifies users of reminders as needed.

[0246] Input: User-specific learning plan and progress data

[0247] Output: Notification and display to the user

[0248] Specific operation: Smart glasses or head-mounted displays monitor the user's learning progress and display reminders and work procedures in their field of vision.

[0249] 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.

[0250] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan in response to those emotions. Specific embodiments thereof are described below.

[0251] System-wide configuration

[0252] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, and emotion engine-side emotion recognition and analysis.

[0253] Data collection

[0254] After logging into the system, users enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is entered through input forms on the device.

[0255] The server validates the input data in real time and saves it to the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[0256] Model Learning

[0257] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[0258] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked.

[0259] Emotion recognition by an emotion engine

[0260] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[0261] The server receives and stores emotional data from the emotion engine. Emotional data is also stored in a database for analyzing long-term emotional trends.

[0262] Creating and adjusting study plans

[0263] Users enter their goals and current skill sets. For example, they might enter a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[0264] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[0265] Furthermore, the server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan can be modified to reduce the learning burden.

[0266] Qualification exam schedule

[0267] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[0268] Displaying the study plan

[0269] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0270] Specific example

[0271] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0272] Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to include measures to reduce the intensity of the learning content and promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[0273] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve individual goals while taking into account the emotional state of the user.

[0274] The following describes the processing flow.

[0275] Step 1:

[0276] The user logs into the system.

[0277] The user enters their ID and password and clicks the login button.

[0278] The server verifies the entered authentication information against the database and redirects the user to the dashboard if authentication is successful.

[0279] Step 2:

[0280] Users enter their own background, skill set, and goals.

[0281] The user enters detailed engineer information into the input form. Specifically, enter past project experience, technologies used, qualifications obtained, educational background, etc.

[0282] The terminal provides an interface to assist with these information inputs.

[0283] Step 3:

[0284] The server saves the input data.

[0285] The server validates the input data in real time to check if all required fields are filled and if the data format is correct.

[0286] Save the data that has passed validation to the database.

[0287] Step 4:

[0288] The server trains a machine learning model based on the saved data.

[0289] The server retrieves the engineer's profile information from the database and performs preprocessing. Preprocessing includes data normalization and filling in missing values.

[0290] Split the data into training data and test data, and use algorithms such as support vector machines and neural networks to train the model.

[0291] Step 5:

[0292] The terminal monitors the progress of the learning model.

[0293] The terminal displays the progress of the learning process (e.g., accuracy, changes in the loss function) on the dashboard in real time so that the user can check the progress of the learning.

[0294] Step 6:

[0295] The server saves the model for which learning has been completed.

[0296] The server saves it as a model file or stores it in a database in order to permanently save the model for which learning has been completed.

[0297] Step 7:

[0298] The user inputs their goals and skill set.

[0299] The user accesses the system again and inputs their goals (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[0300] The terminal provides an interface for efficiently inputting and managing these.

[0301] Step 8:

[0302] The server generates a learning plan based on the input goals and skill set.

[0303] The server obtains the information input by the user and generates an appropriate learning plan based on the learned model.

[0304] The learning plan includes specific learning content, recommended resources, and a learning schedule.

[0305] Step 9:

[0306] The server generates a schedule for the qualification exam.

[0307] The server sets an appropriate schedule for the qualification exam according to the user's goals.

[0308] The proposed exam schedule includes the date and time of the exam, a preparation period, and important deadlines.

[0309] Step 10:

[0310] The device displays the generated study plan and qualification exam schedule.

[0311] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[0312] Step 11:

[0313] The device collects user emotion data.

[0314] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[0315] The emotion engine analyzes this data to recognize the user's current emotional state.

[0316] Step 12:

[0317] The server stores emotional data.

[0318] The system receives emotional data from the emotion engine and stores it in a database.

[0319] Emotional data will also be recorded for long-term sentiment analysis.

[0320] Step 13:

[0321] The server adjusts the learning plan based on sentiment data.

[0322] The learning plan is adjusted in real time according to the user's emotional state. For example, if the user is feeling stressed, the content is changed to reduce the learning burden.

[0323] The tailored plan is designed to allow users to learn at their own pace without feeling overwhelmed.

[0324] Step 14:

[0325] The device will display the adjusted learning plan.

[0326] The adjusted study plan is displayed again in calendar format, and the user is notified.

[0327] Users can review the new plan and continue their learning.

[0328] (Example 2)

[0329] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0330] Conventional learning plan generation systems have difficulty considering the individual emotional state of users, which can lead to decreased learning efficiency. Furthermore, scheduling certification exams could not reflect the user's learning progress or emotional state in real time. This resulted in users experiencing stress and being unable to progress with their studies according to plan.

[0331] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan to the user, means for collecting and analyzing user sentiment data, and means for adjusting the learning plan based on the sentiment data. This makes it possible to efficiently provide a learning plan while taking into account the individual emotional state of the user, making it easier for engineers to achieve their goals.

[0332] "Input data" refers to information that users provide to the system, including data such as work history, skill set, and goals.

[0333] "Means of acceptance" refers to the interface or process that a system uses to obtain input data from a user.

[0334] "Means of storage" refers to mechanisms or processes for storing input data temporarily or permanently in a memory device.

[0335] A "machine learning model" is an algorithm or program that learns from data and performs tasks such as prediction and classification.

[0336] A "trained model" is a machine learning model that has been optimized based on training data, and it is a model that makes predictions and recommendations using user input data.

[0337] A "user-specific learning plan" is a learning plan and schedule that is automatically customized based on the user's individual goals and skill set.

[0338] "Means of display" refers to interfaces or devices that visually show the generated learning plan to the user.

[0339] "Emotional data" refers to data that represents a user's emotional state, obtained from their facial expressions, voice, and actions.

[0340] "Means of collection and analysis" refers to systems and processes for acquiring emotional data, analyzing it, and determining the user's emotional state.

[0341] "Means of adjustment" refer to mechanisms or processes for dynamically changing the learning plan based on the user's emotional data.

[0342] "Means of preprocessing" refers to mechanisms or processes that perform operations such as normalization, imputation of missing values, and conversion of data formats in order to improve the quality of the data.

[0343] "Skills" refer to information that indicates the level of a user's specific knowledge or technical abilities.

[0344] A "qualification exam schedule" is a schedule that helps users plan the timing of their studies and exams in preparation for the qualification exam they are aiming for.

[0345] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan tailored to those emotions. The system consists of means for user data input, data storage and model training by a server, provision of a user interface by a terminal, and recognition and analysis of the user's emotions by an emotion engine.

[0346] Data collection

[0347] Users log in to the system using a terminal and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered through input forms on the terminal. The server validates the entered data in real time and stores it in the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[0348] Model Learning

[0349] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and makes predictions based on them. The terminal displays the progress of the learning process in real time on a dashboard. Here, for example, the accuracy of the model, changes in the loss function, and the progress of the learning epoch can be visually checked.

[0350] Emotion recognition by an emotion engine

[0351] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust). The server receives the emotional data from the emotion engine and stores it. The emotional data is also stored in a database to analyze long-term emotional trends.

[0352] Creating and adjusting study plans

[0353] Users input their goals and current skill sets. For example, they might input a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server. Based on a trained model, the server generates a personalized learning plan for the user. This plan might include specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also adjusts the learning plan in real time based on sentiment data from the sentiment engine. For example, if the user is experiencing stress, the plan can be modified to reduce the learning burden.

[0354] Qualification exam schedule

[0355] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[0356] Displaying the study plan

[0357] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0358] Specific example

[0359] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance. Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to slightly reduce the learning content and include measures to promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[0360] Example of a prompt

[0361] "My goal is to pass the AWS Certified Solutions Architect exam. My current skill set includes Python and basic networking knowledge. Please generate a study plan for each AWS service."

[0362] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0363] Step 1:

[0364] Users log in to their terminal and enter their work history, skill set, and goals. Specifically, they enter information such as past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals into an input form. The input data includes goals such as "obtaining AWS Certified Solutions Architect certification" and skill sets such as "Python" and "fundamental networking knowledge." The input data is sent from the terminal to the server.

[0365] Input: Data from the user regarding their career history, skill set, and goals.

[0366] Output: User data sent to the server

[0367] Step 2:

[0368] The server validates the received input data in real time. The validation process includes checking required fields (e.g., whether goals and skill sets are present) and checking data format (e.g., date format and integer values). Once validation is complete, the data is stored in a database such as MySQL or MongoDB.

[0369] Input: User data sent from the terminal

[0370] Output: Validated user data, saved to the database.

[0371] Step 3:

[0372] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Subsequently, models are trained using algorithms such as support vector machines, random forests, and neural networks.

[0373] Input: Validated user data

[0374] Output: Trained machine learning model

[0375] Step 4:

[0376] The device displays the progress of the learning process in real time on a dashboard. Here, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is retrieved from the server and displayed on the device's screen.

[0377] Input: Training process data from the server

[0378] Output: Learning process visualization data on the dashboard

[0379] Step 5:

[0380] The device periodically sends user facial expressions, voice, and behavioral data to the emotion engine. For example, it collects data using the camera and microphone when the user is watching a lesson video. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[0381] Input: User's facial expressions, voice, and behavioral data

[0382] Output: Recognized user emotional state data

[0383] Step 6:

[0384] The server receives emotional data from the emotion engine and stores it in a database. Simultaneously, it analyzes the emotional data and uses it to understand long-term emotional trends.

[0385] Input: Emotional state data from the emotion engine

[0386] Output: Emotional state data stored in the database, analysis results

[0387] Step 7:

[0388] The server generates a personalized learning plan based on pre-trained models. This plan may include, for example, what AWS services to learn each week, recommended reference materials, and methods for tracking progress. This plan is automatically customized according to the user's goals and current skill level.

[0389] Input: Stored user data, trained model

[0390] Output: User-specific learning plan

[0391] Step 8:

[0392] The server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan is modified to include measures that reduce the learning content and promote relaxation.

[0393] Input: Emotional state data

[0394] Output: Adjusted learning plan

[0395] Step 9:

[0396] The device visually displays the generated study plan and qualification exam schedule. It uses a calendar format to allow users to visually check their progress and next tasks. A reminder function is also implemented to help users stay on track with their studies.

[0397] Input: Generated and adjusted study plans, qualification exam schedules

[0398] Output: Visually displayed study plan and exam schedule

[0399] (Application Example 2)

[0400] 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".

[0401] While improving the productivity of factory workers, it is also necessary to appropriately adjust work content according to the emotional state of the workers and effectively manage their mental health. This invention aims to improve the working environment and reduce worker stress by providing a system that recognizes and analyzes workers' emotions and adjusts work content and learning plans based on the results.

[0402] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model and sentiment analysis results, means for displaying the generated learning plan to the user, and means for adjusting work content and providing mental care guidance based on sentiment analysis results. This enables real-time monitoring of workers' emotions and allows for appropriate work adjustments and mental care.

[0403] "Means for receiving input data" refers to functions that collect data such as user history, skill sets, and goals through input forms or similar means.

[0404] "Means for saving received data" refers to a function that validates user-entered data in real time and saves it to the database in an appropriate format.

[0405] "Methods for training machine learning models based on stored data" refers to functions that retrieve stored data, preprocess the data, and then train models using various machine learning algorithms.

[0406] "Means for recognizing and analyzing user emotions" refers to a system that analyzes a user's facial expressions, voice, and behavioral data to recognize their emotional state.

[0407] "Means for generating a user-specific learning plan using a trained model and sentiment analysis results" refers to a function that automatically generates a learning plan optimized for the user based on a trained machine learning model and the results of sentiment analysis.

[0408] "Means for displaying the generated learning plan to the user" refers to an interface that visually displays the customized learning plan, making it easy for the user to follow along.

[0409] "A means of adjusting work content and providing mental care guidance based on emotion analysis results" refers to a function that takes the user's emotional state into consideration, adjusts work content in real time, and provides mental care as needed.

[0410] This invention relates to a system that recognizes the emotions of workers in a factory and customizes work content and learning plans according to those emotions. Specific embodiments are described below.

[0411] System-wide configuration

[0412] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, emotion recognition and analysis by an emotion engine, and means for adjusting workers' work conditions and providing mental care support.

[0413] Data collection

[0414] After logging into the system, users enter their career history, current skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered into the terminal and sent to the server.

[0415] The server validates the input data in real time and stores it in the database in the appropriate format. The data validation process includes checking required fields and verifying the data format. Databases such as MySQL and MongoDB are used.

[0416] Model Learning

[0417] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses them to make predictions.

[0418] The device displays the progress of the learning process in real time on a dashboard. Here, you can visually check the model's accuracy, changes in the loss function, and the progress of the learning epochs.

[0419] Emotion recognition by an emotion engine

[0420] The terminal transmits facial expressions, voice, and behavioral data collected from the worker via the camera and microphone to the emotion engine. The emotion engine analyzes this data to recognize the worker's current emotional state (joy, anger, sadness, surprise, fear, disgust). For emotion recognition, for example, OpenCV (face recognition) and Keras (emotion recognition model) are used.

[0421] The server generates personalized learning plans for workers based on emotional data received from the emotion engine. These plans include specific weekly learning content, recommended reference materials, and progress tracking methods.

[0422] Adjusting the study plan

[0423] The server adjusts learning plans and work content in real time based on emotional data obtained from the emotion engine. For example, if a worker is experiencing stress, it can reduce the learning burden and change work content to a more relaxing one. It also provides mental health support.

[0424] Qualification exam schedule

[0425] The server sets appropriate qualification exam dates based on the worker's goals. It adjusts the exam preparation period and exam date, taking into account the worker's learning progress and emotional state.

[0426] Displaying the study plan

[0427] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for workers to follow along. Progress tracking and reminder functions are also provided to help workers stay on track with their studies.

[0428] Specific example:

[0429] For example, suppose a worker sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information and uses a pre-trained model to generate an appropriate learning plan. This plan includes what to learn about each AWS service each week, along with related exercises and practice tests. The exam dates are also set.

[0430] The device uses an emotion engine to analyze the worker's facial expressions and voice to understand their emotional state during learning. For example, if the worker is feeling fatigued, the server adjusts the learning plan to include some lighter learning content and measures to promote relaxation.

[0431] Examples of prompt statements:

[0432] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[0433] In this way, the present invention makes it possible to provide a system that allows workers to efficiently carry out their work and learning, and to achieve their individual goals, while taking into account the emotional state of the workers.

[0434] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0435] Step 1:

[0436] Users log into the system and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is collected through input forms on the terminal. The entered data is sent to the server in a standard format (e.g., JSON or XML).

[0437] Step 2:

[0438] The server validates the received data. Specifically, it checks required fields and data format. For example, it verifies whether skill sets and experience are entered correctly. The validated data is stored in a database (MySQL or MongoDB) in an organized format (e.g., normalized numbers or formatted text).

[0439] Step 3:

[0440] The server retrieves the stored data and trains a machine learning model. Data preprocessing includes normalization of numerical data and imputation of missing values. The preprocessed data is then used to train a model using machine learning algorithms such as support vector machines (SVMs), random forests, and neural networks. Model training involves iterative computation with multiple epochs using the training dataset, and is repeated until the model's accuracy improves.

[0441] Step 4:

[0442] The device displays the progress and accuracy of the trained model on a dashboard. The displayed information includes model accuracy, changes in the loss function, and progress through training epochs. The dashboard consists of visually easy-to-understand graphs and charts, allowing users to understand the model's performance in real time.

[0443] Step 5:

[0444] The terminal transmits facial expressions, voice, and behavioral data of workers collected through the camera and microphone to the emotion engine. Specifically, it analyzes emotions using facial image data captured by the camera and voice data collected by the microphone. The emotion engine uses OpenCV and Keras to analyze this data and recognize the worker's emotional state (joy, anger, sadness, surprise, fear, disgust). This analysis uses an emotion recognition model (e.g., a pre-trained CNN model).

[0445] Step 6:

[0446] The server generates a personalized learning plan for each worker based on the emotional data received from the emotion engine. This plan includes specific weekly learning content, recommended reference materials, and progress tracking methods. The emotional data is received in JSON format and integrated with other user data stored in the database.

[0447] Step 7:

[0448] The server adjusts learning plans and work content in real time based on the results of emotion analysis. For example, if a worker is feeling stressed, it will reduce the learning burden and change the content to promote relaxation. This adjustment is optimized based on past emotion data and success stories obtained from the database.

[0449] Step 8:

[0450] The device displays the generated learning plan and work adjustments to the worker. It also provides a calendar-style display, tracking functions, and reminder functions to help workers progress with their learning according to the plan. Mental health advice is also displayed as needed.

[0451] Examples of specific prompt messages:

[0452] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[0453] In this way, each step works in coordination, and a system is realized that provides optimal work adjustments and learning plans while taking into account the emotional state of the workers.

[0454] 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.

[0455] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0456] 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.

[0457] [Second Embodiment]

[0458] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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".

[0470] This invention provides a system that enables engineers to learn efficiently and achieve their goals. Specific embodiments thereof are described below.

[0471] System-wide configuration

[0472] The system consists of means for user data input, server-side data storage and model training, and terminal-side provision of a user interface.

[0473] Data collection

[0474] The user first logs into the system. After logging in, the user enters their technical experience, skill set, learning history, and goals they wish to achieve. This data is entered through an input form on the terminal.

[0475] The server validates the input data in real time and saves it to the database in the appropriate format. This includes checking for blank fields and verifying the format. If validation is successful, the data is stored securely. The saved data is stored in a database such as MySQL or MongoDB.

[0476] Model Learning

[0477] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[0478] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is also useful for the user, helping them to understand the progress of the learning process.

[0479] Generating a learning plan

[0480] Users input their goals and current skill sets into the system. For example, they might input a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[0481] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[0482] Furthermore, the server also generates a schedule for certification exams. Based on the user's goals, it might schedule an exam six months in advance and present study content and a timeline for exam preparation. This schedule is designed to allow users to study efficiently and prepare for the exam.

[0483] Displaying the study plan

[0484] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0485] Specific example

[0486] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0487] In this way, the present invention makes it possible to provide a system that enables engineers to efficiently advance their learning and achieve their desired goals.

[0488] The following describes the processing flow.

[0489] Step 1:

[0490] The user logs into the system.

[0491] The user enters their ID and password and clicks the login button.

[0492] The server compares the received authentication information with the database and redirects the user to the dashboard if authentication is successful.

[0493] Step 2:

[0494] Users enter their own background, skill set, and goals.

[0495] Users enter detailed technical information into the input form. Specifically, they fill in information such as past project experience, technologies used, qualifications obtained, and learning history.

[0496] The terminal provides an interface to assist in inputting this information.

[0497] Step 3:

[0498] The server saves the entered data.

[0499] The server validates the entered data in real time, checking whether all required fields are filled in and whether the data format is correct.

[0500] Save the data that passed validation to the database.

[0501] Step 4:

[0502] The server trains a machine learning model based on the stored data.

[0503] The server retrieves engineer profile information from the database and performs preprocessing. Preprocessing includes data normalization and imputation of missing values.

[0504] The data is split into training data and test data, and a model is trained using algorithms such as support vector machines or neural networks.

[0505] Step 5:

[0506] The server monitors the progress of the learning model.

[0507] The server records the progress of the learning process (e.g., accuracy, changes in the loss function).

[0508] The device displays this information in real time in a dashboard format, allowing users to check their learning progress.

[0509] Step 6:

[0510] The server saves the model once training is complete.

[0511] The server either saves the trained model as a model file or stores it in a database for persistent storage.

[0512] Step 7:

[0513] The user enters their goals and skill set.

[0514] The user accesses the system again and enters their goal (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[0515] The terminal provides an interface for efficiently inputting and managing this information.

[0516] Step 8:

[0517] The server generates a learning plan based on the entered goals and skill set.

[0518] The server retrieves the information entered by the user and generates an appropriate training plan based on the trained model.

[0519] A study plan includes specific learning content, recommended resources, and a study schedule.

[0520] Step 9:

[0521] The server generates the schedule for the certification exam.

[0522] The server sets appropriate certification exam dates according to the user's goals.

[0523] The proposed exam schedule will include the exam date and time, preparation period, and important deadlines.

[0524] Step 10:

[0525] The device displays the generated study plan and qualification exam schedule.

[0526] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[0527] Users can begin learning based on this information.

[0528] (Example 1)

[0529] 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."

[0530] Conventional learning systems for engineers have suffered from insufficient automatic generation of learning plans and certification exam schedules tailored to individual user skill sets and goals, making it difficult for users to learn efficiently. Furthermore, the training of machine learning models based on stored data and the generation of learning plans using the results were rarely applied, and real-time tracking of user progress and the display of visual learning plans were incomplete, resulting in decreased user learning efficiency.

[0531] 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.

[0532] In this invention, the server includes means for receiving input information, means for storing the received information in a storage device, means for training a machine learning algorithm based on the stored information, means for generating a user-specific learning plan using the trained algorithm, and means for displaying the generated learning plan on a user interface. This makes it possible to automatically generate learning plans and qualification exam schedules tailored to the user's individual skill set and goals, and further enables users to efficiently progress in their studies by tracking progress in real time and visually displaying the learning plan.

[0533] "Input information" refers to various data that users provide to the system, such as their career history, skill set, learning history, and goals.

[0534] A "memory device" is a database or storage system used to store received information.

[0535] A "machine learning algorithm" is a mathematical model or computational method that learns from stored information and performs predictions and classifications.

[0536] A "user interface" is a visual interface through which a user interacts with a system, inputting data and viewing plans.

[0537] A "learning plan" is a set of specific learning content and schedule generated by the system to help the user achieve their goals.

[0538] The "certification exam schedule" refers to the date and time of the certification exam and the preparation timeline, which are set based on the user's goals.

[0539] "Real-time tracking" is a function that allows the system to monitor and record the user's learning progress in real time.

[0540] This invention is a system that enables engineers to learn efficiently and achieve their goals, and it functions through user data input, server-based data storage and model learning, and terminal-based provision of a user interface. Specific embodiments of the system are described below.

[0541] Hardware and software to use

[0542] The device provides an input form for the user to log in and enter data. Specifically, a web browser or mobile application is used.

[0543] The server stores data and trains machine learning models. Relational databases such as MySQL and MongoDB, as well as NoSQL databases, are used as databases. Machine learning algorithms include support vector machines, random forests, and neural networks.

[0544] The device provides a user interface for displaying study plans and qualification exam schedules, and also includes progress tracking and reminder functions.

[0545] Data collection and storage

[0546] Users log into the system and enter their work history, skill set, learning history, and goals they wish to achieve. This data is entered through input forms on the device and transmitted to the server in real time.

[0547] The server validates the submitted data in real time, checking for blank fields and verifying the format. Data that passes validation is securely stored in a MySQL or MongoDB database.

[0548] Training machine learning models

[0549] The server periodically retrieves stored data and performs data preprocessing (such as normalizing numerical data and imputing missing values). Then, it trains machine learning models using algorithms such as support vector machines, random forests, and neural networks. The trained models learn the characteristics and patterns of successful engineers and use that information to make predictions.

[0550] Generation and display of learning plans

[0551] Similarly, users input their goals and current skill sets into the system. For example, they might input a goal such as "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience.

[0552] The server generates a personalized learning plan for each user based on pre-trained models. Specifically, this plan includes weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also generates a certification exam schedule, for example, setting the exam six months in advance and providing study content and a timeline for exam preparation.

[0553] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0554] Specific example

[0555] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0556] Example of a prompt

[0557] "Please create a study plan to obtain the AWS Certified Solutions Architect certification. My current skill set includes Python and basic networking knowledge. The exam is scheduled for six months from now."

[0558] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve their desired goals.

[0559] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0560] Step 1: User Login

[0561] Operation: The user enters their username and password on the system's login screen and submits the authentication information.

[0562] Input: Username, Password

[0563] Data processing or calculation: The server receives authentication information and performs authentication by comparing it with user information in the database.

[0564] Output: The authentication result is returned, and if successful, a user session is started.

[0565] Step 2: Data Entry

[0566] Operation: The user uses the terminal's input form to enter their background, skill set, learning history, and goals.

[0567] Input: User background, skill set, learning history, goals

[0568] Data processing or calculation: The terminal collects the input data and sends it to the server.

[0569] Output: Data is sent to the server.

[0570] Step 3: Data Validation

[0571] Operation: The server checks for blank fields and verifies the format of the received data.

[0572] Input: Data entered by the user

[0573] Data processing or calculation: The server performs data blank detection and format validation.

[0574] Output: Validation results are output, and successful data proceeds to the next step.

[0575] Step 4: Save Data

[0576] Operation: The server saves data that has successfully been validated to a database such as MySQL or MongoDB.

[0577] Input: Data that successfully passed validation

[0578] Data processing or calculation: The server executes an insert query (INSERT) against the database.

[0579] Output: The data is saved to the database.

[0580] Step 5: Data Retrieval

[0581] Operation: The server periodically queries and retrieves stored data.

[0582] Input: Query against stored data

[0583] Data processing or calculation: The server retrieves the necessary data from the database using SQL or NoSQL queries.

[0584] Output: The acquired data proceeds to the next step.

[0585] Step 6: Data Preprocessing

[0586] Operation: The server performs preprocessing on the retrieved data, such as normalizing numerical data and imputing missing values.

[0587] Input: Acquired data

[0588] Data processing or calculations: The server performs data normalization (e.g., Min-Max Scaling or Standard Scaler) and imputation of missing values ​​(e.g., mean imputation).

[0589] Output: Pre-processed data is obtained.

[0590] Step 7: Training the machine learning model

[0591] Operation: The server applies machine learning algorithms (e.g., support vector machines, random forests, neural networks) to preprocessed data and trains the model.

[0592] Input: Preprocessed data

[0593] Data processing or computation: The server uses the specified algorithm to train the training data and optimize the model parameters.

[0594] Output: Trained machine learning model.

[0595] Step 8: Display the dashboard

[0596] Operation: The terminal displays the training progress received from the server as graphs and charts.

[0597] Input: Training progress (e.g., model accuracy, change in loss function)

[0598] Data processing or calculation: The terminal generates graphs and charts to visualize the received data.

[0599] Output: A progress dashboard is displayed to the user.

[0600] Step 9: Enter a new goal

[0601] Operation: The user enters a new goal (e.g., obtaining AWS Certified Solutions Architect certification) and their current skill set into the system.

[0602] Input: Goals and current skill set

[0603] Data processing or calculation: The terminal sends the input to the server.

[0604] Output: New goal and skill set data is sent to the server.

[0605] Step 10: Generating a study plan

[0606] Operation: The server generates individual learning plans using pre-trained models based on new goals and skill sets.

[0607] Input: New goals and skill sets

[0608] Data processing or computation: The server uses the trained model to generate an optimal learning plan (weekly learning content, recommended materials, and progress tracking methods).

[0609] Output: The generated training plan.

[0610] Step 11: Generate a schedule for the certification exam.

[0611] Operation: The server generates a qualification exam schedule based on the user's goals, for example, setting an exam date six months in advance.

[0612] Input: User's goal

[0613] Data processing or calculation: The server uses a schedule generation algorithm to set the test schedule.

[0614] Output: Qualification exam schedule.

[0615] Step 12: Display your study plan and schedule

[0616] Operation: The device displays the generated study plan and qualification exam schedule in a calendar format.

[0617] Input: Study plan, qualification exam schedule

[0618] Data processing or calculation: The terminal generates a calendar that visualizes the learning plan and schedule.

[0619] Output: Study plan and exam schedule in calendar format.

[0620] Step 13: Track progress

[0621] Operation: The device tracks the user's learning progress in real time and displays the completion status of planned learning content.

[0622] Input: Progress data

[0623] Data processing or calculation: The terminal analyzes progress data and generates completion status and reminders.

[0624] Output: Display of progress and reminders.

[0625] (Application Example 1)

[0626] 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."

[0627] Conventional technologies have made it difficult to create concrete learning plans for engineers and operators working in factories, based on their individual skill levels and goals. Furthermore, the lack of real-time means to monitor work procedures and learning progress hindered effective skill development. This invention aims to solve these problems and provide a system that supports efficient skill development for engineers within factories.

[0628] 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.

[0629] In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan on a display device, means for displaying work procedures and learning progress in real time using the display device, and means for notifying the user of reminders regarding work procedures and learning progress. This enables engineers and operators to obtain an optimal learning plan based on their own skill set and goals, and to efficiently improve their skills while checking their progress in real time.

[0630] "Means for receiving input data" refers to a device or function that provides an interface for a user to input their career history, skill set, learning history, and goals into the system.

[0631] "Means for storing received data" refers to a device or function for securely storing data entered by a user in a storage device such as a database, after properly validating it.

[0632] "Means for training machine learning models based on stored data" refers to a device or function for appropriately preprocessing stored user data and training machine learning models using algorithms such as support vector machines or neural networks.

[0633] "Means for generating a user-specific learning plan using a pre-trained model" refers to a device or function that automatically generates an optimal, customized learning plan for each user using a pre-trained machine learning model.

[0634] "Means for displaying the generated learning plan on a display device" refers to a device or function for visually displaying the generated user-specific learning plan.

[0635] "Means for displaying work procedures and learning progress in real time using a display device" refers to a device or function for displaying work procedures and learning progress on a display device so that they can be visually confirmed in real time.

[0636] "Means for notifying users of work procedures and learning progress" refers to a device or function for sending notifications regarding work procedures and learning progress as reminders to users.

[0637] This invention provides a system that enables engineers to learn efficiently and achieve their goals. The following describes specific embodiments of the invention.

[0638] The system consists of user terminals, servers, and display devices.

[0639] First, the user logs into the terminal and enters their work history, skill set, learning history, and goals. The terminal receives the input data and sends it to the server. The server validates the received data in real time and securely stores it in a database such as MySQL or MongoDB.

[0640] The stored data is periodically retrieved by the server and used to train machine learning models. Data preprocessing includes imputation of missing values ​​and normalization of numerical data. Subsequently, the models are trained using algorithms such as support vector machines and neural networks.

[0641] The device uses a pre-trained model to generate a personalized learning plan for each user. For example, for a user whose goal is to "pass the AWS Certified Solutions Architect exam," the system automatically generates specific weekly study content, recommended reference materials, and progress tracking methods. This plan is customized according to the user's skill set and goals.

[0642] Furthermore, the server displays the generated learning plan in real time on a display device. This display device is expected to be a smart glasses or head-mounted display. This allows the user to check work procedures and learning progress in real time. The display device also has a function to notify users of reminders regarding work procedures and learning progress.

[0643] To illustrate the process using a concrete example, consider a scenario where a user wears smart glasses and performs machine maintenance work in a factory. The user inputs their skill set (e.g., basic knowledge of Python and networking) into the system and sets a goal (e.g., acquiring a specific machine maintenance skill). The system receives this information, stores it in a database, and generates an appropriate learning plan using a trained model. The smart glasses display the work procedures and learning progress in real time within the user's field of view.

[0644] Examples of prompt statements to input into a generative AI model are as follows:

[0645] User skill set: X, Y, Z

[0646] Objective: To acquire basic maintenance skills.

[0647] Desired time: 1 month

[0648] Based on this prompt, the system provides a learning plan and real-time display to help engineers efficiently improve their skills.

[0649] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0650] Step 1:

[0651] The user logs into the device and enters their background, skill set, learning history, and goals. The entered data is received by the device and sent to the server.

[0652] Input: User background, skill set, learning history, goals

[0653] Output: Received data

[0654] Specific operation: The user enters the required information into the input form on the terminal and clicks the submit button. The terminal receives the input data and sends it to the server.

[0655] Step 2:

[0656] The server validates the received data and saves it to a database such as MySQL or MongoDB. Validation includes checking for blank fields and verifying data format.

[0657] Input: Received data

[0658] Output: Saving validated data

[0659] Specific operation: The server checks for blank fields and formatting of the received data, and then saves it to the database after formatting it appropriately.

[0660] Step 3:

[0661] The server periodically retrieves and preprocesses the stored data. Data preprocessing includes imputing missing values ​​and normalizing numerical data.

[0662] Input: Saved data

[0663] Output: Preprocessed data

[0664] Specific operation: The server reads the stored data and automatically performs preprocessing such as imputing missing values ​​and normalizing numerical data.

[0665] Step 4:

[0666] The server uses the preprocessed data to train machine learning models using algorithms such as support vector machines and neural networks.

[0667] Input: Preprocessed data

[0668] Output: Trained model

[0669] Specific operation: The server inputs pre-processed data into the algorithm and trains the model for a specified number of epochs.

[0670] Step 5:

[0671] The server uses a pre-trained model to generate a personalized learning plan for the user. The generated plan includes specific weekly learning content, recommended reference materials, and progress tracking methods.

[0672] Input: Trained model and user data

[0673] Output: User-specific learning plan

[0674] Specific operation: The server inputs the user's skill set and goals into a pre-trained model and automatically generates an optimal learning plan.

[0675] Step 6:

[0676] The server sends the generated learning plan to a display device for real-time display. Smart glasses or head-mounted displays are used as the display device.

[0677] Input: User-specific learning plan

[0678] Output: Display of the learning plan on the display device.

[0679] Specific operation: The server sends the generated learning plan to smart glasses or a head-mounted display, allowing the user to view it in real time.

[0680] Step 7:

[0681] The display device shows work procedures and learning progress in real time and notifies users of reminders as needed.

[0682] Input: User-specific learning plan and progress data

[0683] Output: Notification and display to the user

[0684] Specific operation: Smart glasses or head-mounted displays monitor the user's learning progress and display reminders and work procedures in their field of vision.

[0685] 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.

[0686] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan in response to those emotions. Specific embodiments thereof are described below.

[0687] System-wide configuration

[0688] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, and emotion engine-side emotion recognition and analysis.

[0689] Data collection

[0690] After logging into the system, users enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is entered through input forms on the device.

[0691] The server validates the input data in real time and saves it to the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[0692] Model Learning

[0693] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[0694] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked.

[0695] Emotion recognition by an emotion engine

[0696] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[0697] The server receives and stores emotional data from the emotion engine. Emotional data is also stored in a database for analyzing long-term emotional trends.

[0698] Creating and adjusting study plans

[0699] Users enter their goals and current skill sets. For example, they might enter a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[0700] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[0701] Furthermore, the server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan can be modified to reduce the learning burden.

[0702] Qualification exam schedule

[0703] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[0704] Displaying the study plan

[0705] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0706] Specific example

[0707] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0708] Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to include measures to reduce the intensity of the learning content and promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[0709] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve individual goals while taking into account the emotional state of the user.

[0710] The following describes the processing flow.

[0711] Step 1:

[0712] The user logs into the system.

[0713] The user enters their ID and password and clicks the login button.

[0714] The server verifies the entered authentication information against the database and redirects the user to the dashboard if authentication is successful.

[0715] Step 2:

[0716] Users enter their own background, skill set, and goals.

[0717] Users enter detailed technical information into the input form. Specifically, they fill in information such as past project experience, technologies used, qualifications obtained, and educational history.

[0718] The terminal provides an interface to assist in inputting this information.

[0719] Step 3:

[0720] The server saves the entered data.

[0721] The server validates the entered data in real time, checking whether all required fields are filled in and whether the data format is correct.

[0722] Save the data that passed validation to the database.

[0723] Step 4:

[0724] The server trains a machine learning model based on the stored data.

[0725] The server retrieves engineer profile information from the database and performs preprocessing. Preprocessing includes data normalization and imputation of missing values.

[0726] The data is split into training data and test data, and a model is trained using algorithms such as support vector machines or neural networks.

[0727] Step 5:

[0728] The device monitors the progress of the learning model.

[0729] The device displays the progress of the learning process (e.g., accuracy, changes in the loss function) in real time on a dashboard, allowing the user to monitor the learning progress.

[0730] Step 6:

[0731] The server saves the model once training is complete.

[0732] The server either saves the trained model as a model file or stores it in a database for persistent storage.

[0733] Step 7:

[0734] The user enters their goals and skill set.

[0735] The user accesses the system again and enters their goal (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[0736] The terminal provides an interface for efficiently inputting and managing this information.

[0737] Step 8:

[0738] The server generates a learning plan based on the entered goals and skill set.

[0739] The server retrieves the information entered by the user and generates an appropriate training plan based on the trained model.

[0740] A study plan includes specific learning content, recommended resources, and a study schedule.

[0741] Step 9:

[0742] The server generates the schedule for the certification exam.

[0743] The server sets appropriate certification exam dates according to the user's goals.

[0744] The proposed exam schedule will include the exam date and time, preparation period, and important deadlines.

[0745] Step 10:

[0746] The device displays the generated study plan and qualification exam schedule.

[0747] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[0748] Step 11:

[0749] The device collects user emotion data.

[0750] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[0751] The emotion engine analyzes this data to recognize the user's current emotional state.

[0752] Step 12:

[0753] The server stores emotional data.

[0754] The system receives emotional data from the emotion engine and stores it in a database.

[0755] Emotional data will also be recorded for long-term sentiment analysis.

[0756] Step 13:

[0757] The server adjusts the learning plan based on sentiment data.

[0758] The learning plan is adjusted in real time according to the user's emotional state. For example, if the user is feeling stressed, the content is changed to reduce the learning burden.

[0759] The tailored plan is designed to allow users to learn at their own pace without feeling overwhelmed.

[0760] Step 14:

[0761] The device will display the adjusted learning plan.

[0762] The adjusted study plan is displayed again in calendar format, and the user is notified.

[0763] Users can review the new plan and continue their learning.

[0764] (Example 2)

[0765] 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".

[0766] Conventional learning plan generation systems have difficulty considering the individual emotional state of users, which can lead to decreased learning efficiency. Furthermore, scheduling certification exams could not reflect the user's learning progress or emotional state in real time. This resulted in users experiencing stress and being unable to progress with their studies according to plan.

[0767] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan to the user, means for collecting and analyzing user sentiment data, and means for adjusting the learning plan based on the sentiment data. This makes it possible to efficiently provide a learning plan while taking into account the individual emotional state of the user, making it easier for engineers to achieve their goals.

[0768] "Input data" refers to information that users provide to the system, including data such as work history, skill set, and goals.

[0769] "Means of acceptance" refers to the interface or process that a system uses to obtain input data from a user.

[0770] "Means of storage" refers to mechanisms or processes for storing input data temporarily or permanently in a memory device.

[0771] A "machine learning model" is an algorithm or program that learns from data and performs tasks such as prediction and classification.

[0772] A "trained model" is a machine learning model that has been optimized based on training data, and it is a model that makes predictions and recommendations using user input data.

[0773] A "user-specific learning plan" is a learning plan and schedule that is automatically customized based on the user's individual goals and skill set.

[0774] "Means of display" refers to interfaces or devices that visually show the generated learning plan to the user.

[0775] "Emotional data" refers to data that represents a user's emotional state, obtained from their facial expressions, voice, and actions.

[0776] "Means of collection and analysis" refers to systems and processes for acquiring emotional data, analyzing it, and determining the user's emotional state.

[0777] "Means of adjustment" refer to mechanisms or processes for dynamically changing the learning plan based on the user's emotional data.

[0778] "Means of preprocessing" refers to mechanisms or processes that perform operations such as normalization, imputation of missing values, and conversion of data formats in order to improve the quality of the data.

[0779] "Skills" refer to information that indicates the level of a user's specific knowledge or technical abilities.

[0780] A "qualification exam schedule" is a schedule that helps users plan the timing of their studies and exams in preparation for the qualification exam they are aiming for.

[0781] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan tailored to those emotions. The system consists of means for user data input, data storage and model training by a server, provision of a user interface by a terminal, and recognition and analysis of the user's emotions by an emotion engine.

[0782] Data collection

[0783] Users log in to the system using a terminal and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered through input forms on the terminal. The server validates the entered data in real time and stores it in the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[0784] Model Learning

[0785] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and makes predictions based on them. The terminal displays the progress of the learning process in real time on a dashboard. Here, for example, the accuracy of the model, changes in the loss function, and the progress of the learning epoch can be visually checked.

[0786] Emotion recognition by an emotion engine

[0787] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust). The server receives the emotional data from the emotion engine and stores it. The emotional data is also stored in a database to analyze long-term emotional trends.

[0788] Creating and adjusting study plans

[0789] Users input their goals and current skill sets. For example, they might input a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server. Based on a trained model, the server generates a personalized learning plan for the user. This plan might include specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also adjusts the learning plan in real time based on sentiment data from the sentiment engine. For example, if the user is experiencing stress, the plan can be modified to reduce the learning burden.

[0790] Qualification exam schedule

[0791] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[0792] Displaying the study plan

[0793] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0794] Specific example

[0795] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance. Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to slightly reduce the learning content and include measures to promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[0796] Example of a prompt

[0797] "My goal is to pass the AWS Certified Solutions Architect exam. My current skill set includes Python and basic networking knowledge. Please generate a study plan for each AWS service."

[0798] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0799] Step 1:

[0800] Users log in to their terminal and enter their work history, skill set, and goals. Specifically, they enter information such as past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals into an input form. The input data includes goals such as "obtaining AWS Certified Solutions Architect certification" and skill sets such as "Python" and "fundamental networking knowledge." The input data is sent from the terminal to the server.

[0801] Input: Data from the user regarding their career history, skill set, and goals.

[0802] Output: User data sent to the server

[0803] Step 2:

[0804] The server validates the received input data in real time. The validation process includes checking required fields (e.g., whether goals and skill sets are present) and checking data format (e.g., date format and integer values). Once validation is complete, the data is stored in a database such as MySQL or MongoDB.

[0805] Input: User data sent from the terminal

[0806] Output: Validated user data, saved to the database.

[0807] Step 3:

[0808] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Subsequently, models are trained using algorithms such as support vector machines, random forests, and neural networks.

[0809] Input: Validated user data

[0810] Output: Trained machine learning model

[0811] Step 4:

[0812] The device displays the progress of the learning process in real time on a dashboard. Here, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is retrieved from the server and displayed on the device's screen.

[0813] Input: Training process data from the server

[0814] Output: Learning process visualization data on the dashboard

[0815] Step 5:

[0816] The device periodically sends user facial expressions, voice, and behavioral data to the emotion engine. For example, it collects data using the camera and microphone when the user is watching a lesson video. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[0817] Input: User's facial expressions, voice, and behavioral data

[0818] Output: Recognized user emotional state data

[0819] Step 6:

[0820] The server receives emotional data from the emotion engine and stores it in a database. Simultaneously, it analyzes the emotional data and uses it to understand long-term emotional trends.

[0821] Input: Emotional state data from the emotion engine

[0822] Output: Emotional state data stored in the database, analysis results

[0823] Step 7:

[0824] The server generates a personalized learning plan based on pre-trained models. This plan may include, for example, what AWS services to learn each week, recommended reference materials, and methods for tracking progress. This plan is automatically customized according to the user's goals and current skill level.

[0825] Input: Stored user data, trained model

[0826] Output: User-specific learning plan

[0827] Step 8:

[0828] The server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan is modified to include measures that reduce the learning content and promote relaxation.

[0829] Input: Emotional state data

[0830] Output: Adjusted learning plan

[0831] Step 9:

[0832] The device visually displays the generated study plan and qualification exam schedule. It uses a calendar format to allow users to visually check their progress and next tasks. A reminder function is also implemented to help users stay on track with their studies.

[0833] Input: Generated and adjusted study plans, qualification exam schedules

[0834] Output: Visually displayed study plan and exam schedule

[0835] (Application Example 2)

[0836] 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."

[0837] While improving the productivity of factory workers, it is also necessary to appropriately adjust work content according to the emotional state of the workers and effectively manage their mental health. This invention aims to improve the working environment and reduce worker stress by providing a system that recognizes and analyzes workers' emotions and adjusts work content and learning plans based on the results.

[0838] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model and sentiment analysis results, means for displaying the generated learning plan to the user, and means for adjusting work content and providing mental care guidance based on sentiment analysis results. This enables real-time monitoring of workers' emotions and allows for appropriate work adjustments and mental care.

[0839] "Means for receiving input data" refers to functions that collect data such as user history, skill sets, and goals through input forms or similar means.

[0840] "Means for saving received data" refers to a function that validates user-entered data in real time and saves it to the database in an appropriate format.

[0841] "Methods for training machine learning models based on stored data" refers to functions that retrieve stored data, preprocess the data, and then train models using various machine learning algorithms.

[0842] "Means for recognizing and analyzing user emotions" refers to a system that analyzes a user's facial expressions, voice, and behavioral data to recognize their emotional state.

[0843] "Means for generating a user-specific learning plan using a trained model and sentiment analysis results" refers to a function that automatically generates a learning plan optimized for the user based on a trained machine learning model and the results of sentiment analysis.

[0844] "Means for displaying the generated learning plan to the user" refers to an interface that visually displays the customized learning plan, making it easy for the user to follow along.

[0845] "A means of adjusting work content and providing mental care guidance based on emotion analysis results" refers to a function that takes the user's emotional state into consideration, adjusts work content in real time, and provides mental care as needed.

[0846] This invention relates to a system that recognizes the emotions of workers in a factory and customizes work content and learning plans according to those emotions. Specific embodiments are described below.

[0847] System-wide configuration

[0848] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, emotion recognition and analysis by an emotion engine, and means for adjusting workers' work conditions and providing mental care support.

[0849] Data collection

[0850] After logging into the system, users enter their career history, current skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered into the terminal and sent to the server.

[0851] The server validates the input data in real time and stores it in the database in the appropriate format. The data validation process includes checking required fields and verifying the data format. Databases such as MySQL and MongoDB are used.

[0852] Model Learning

[0853] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses them to make predictions.

[0854] The device displays the progress of the learning process in real time on a dashboard. Here, you can visually check the model's accuracy, changes in the loss function, and the progress of the learning epochs.

[0855] Emotion recognition by an emotion engine

[0856] The terminal transmits facial expressions, voice, and behavioral data collected from the worker via the camera and microphone to the emotion engine. The emotion engine analyzes this data to recognize the worker's current emotional state (joy, anger, sadness, surprise, fear, disgust). For emotion recognition, for example, OpenCV (face recognition) and Keras (emotion recognition model) are used.

[0857] The server generates personalized learning plans for workers based on emotional data received from the emotion engine. These plans include specific weekly learning content, recommended reference materials, and progress tracking methods.

[0858] Adjusting the study plan

[0859] The server adjusts learning plans and work content in real time based on emotional data obtained from the emotion engine. For example, if a worker is experiencing stress, it can reduce the learning burden and change work content to a more relaxing one. It also provides mental health support.

[0860] Qualification exam schedule

[0861] The server sets appropriate qualification exam dates based on the worker's goals. It adjusts the exam preparation period and exam date, taking into account the worker's learning progress and emotional state.

[0862] Displaying the study plan

[0863] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for workers to follow along. Progress tracking and reminder functions are also provided to help workers stay on track with their studies.

[0864] Specific example:

[0865] For example, suppose a worker sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information and uses a pre-trained model to generate an appropriate learning plan. This plan includes what to learn about each AWS service each week, along with related exercises and practice tests. The exam dates are also set.

[0866] The device uses an emotion engine to analyze the worker's facial expressions and voice to understand their emotional state during learning. For example, if the worker is feeling fatigued, the server adjusts the learning plan to include some lighter learning content and measures to promote relaxation.

[0867] Examples of prompt statements:

[0868] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[0869] In this way, the present invention makes it possible to provide a system that allows workers to efficiently carry out their work and learning, and to achieve their individual goals, while taking into account the emotional state of the workers.

[0870] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0871] Step 1:

[0872] Users log into the system and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is collected through input forms on the terminal. The entered data is sent to the server in a standard format (e.g., JSON or XML).

[0873] Step 2:

[0874] The server validates the received data. Specifically, it checks required fields and data format. For example, it verifies whether skill sets and experience are entered correctly. The validated data is stored in a database (MySQL or MongoDB) in an organized format (e.g., normalized numbers or formatted text).

[0875] Step 3:

[0876] The server retrieves the stored data and trains a machine learning model. Data preprocessing includes normalization of numerical data and imputation of missing values. The preprocessed data is then used to train a model using machine learning algorithms such as support vector machines (SVMs), random forests, and neural networks. Model training involves iterative computation with multiple epochs using the training dataset, and is repeated until the model's accuracy improves.

[0877] Step 4:

[0878] The device displays the progress and accuracy of the trained model on a dashboard. The displayed information includes model accuracy, changes in the loss function, and progress through training epochs. The dashboard consists of visually easy-to-understand graphs and charts, allowing users to understand the model's performance in real time.

[0879] Step 5:

[0880] The terminal transmits facial expressions, voice, and behavioral data of workers collected through the camera and microphone to the emotion engine. Specifically, it analyzes emotions using facial image data captured by the camera and voice data collected by the microphone. The emotion engine uses OpenCV and Keras to analyze this data and recognize the worker's emotional state (joy, anger, sadness, surprise, fear, disgust). This analysis uses an emotion recognition model (e.g., a pre-trained CNN model).

[0881] Step 6:

[0882] The server generates a personalized learning plan for each worker based on the emotional data received from the emotion engine. This plan includes specific weekly learning content, recommended reference materials, and progress tracking methods. The emotional data is received in JSON format and integrated with other user data stored in the database.

[0883] Step 7:

[0884] The server adjusts learning plans and work content in real time based on the results of emotion analysis. For example, if a worker is feeling stressed, it will reduce the learning burden and change the content to promote relaxation. This adjustment is optimized based on past emotion data and success stories obtained from the database.

[0885] Step 8:

[0886] The device displays the generated learning plan and work adjustments to the worker. It also provides a calendar-style display, tracking functions, and reminder functions to help workers progress with their learning according to the plan. Mental health advice is also displayed as needed.

[0887] Examples of specific prompt messages:

[0888] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[0889] In this way, each step works in coordination, and a system is realized that provides optimal work adjustments and learning plans while taking into account the emotional state of the workers.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] [Third Embodiment]

[0894] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0895] 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.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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".

[0906] This invention provides a system that enables engineers to learn efficiently and achieve their goals. Specific embodiments thereof are described below.

[0907] System-wide configuration

[0908] The system consists of means for user data input, server-side data storage and model training, and terminal-side provision of a user interface.

[0909] Data collection

[0910] The user first logs into the system. After logging in, the user enters their technical experience, skill set, learning history, and goals they wish to achieve. This data is entered through an input form on the terminal.

[0911] The server validates the input data in real time and saves it to the database in the appropriate format. This includes checking for blank fields and verifying the format. If validation is successful, the data is stored securely. The saved data is stored in a database such as MySQL or MongoDB.

[0912] Model Learning

[0913] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[0914] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is also useful for the user, helping them to understand the progress of the learning process.

[0915] Generating a learning plan

[0916] Users input their goals and current skill sets into the system. For example, they might input a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[0917] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[0918] Furthermore, the server also generates a schedule for certification exams. Based on the user's goals, it might schedule an exam six months in advance and present study content and a timeline for exam preparation. This schedule is designed to allow users to study efficiently and prepare for the exam.

[0919] Displaying the study plan

[0920] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0921] Specific example

[0922] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0923] In this way, the present invention makes it possible to provide a system that enables engineers to efficiently advance their learning and achieve their desired goals.

[0924] The following describes the processing flow.

[0925] Step 1:

[0926] The user logs into the system.

[0927] The user enters their ID and password and clicks the login button.

[0928] The server compares the received authentication information with the database and redirects the user to the dashboard if authentication is successful.

[0929] Step 2:

[0930] Users enter their own background, skill set, and goals.

[0931] Users enter detailed technical information into the input form. Specifically, they fill in information such as past project experience, technologies used, qualifications obtained, and learning history.

[0932] The terminal provides an interface to assist in inputting this information.

[0933] Step 3:

[0934] The server saves the entered data.

[0935] The server validates the entered data in real time, checking whether all required fields are filled in and whether the data format is correct.

[0936] Save the data that passed validation to the database.

[0937] Step 4:

[0938] The server trains a machine learning model based on the stored data.

[0939] The server retrieves engineer profile information from the database and performs preprocessing. Preprocessing includes data normalization and imputation of missing values.

[0940] The data is split into training data and test data, and a model is trained using algorithms such as support vector machines or neural networks.

[0941] Step 5:

[0942] The server monitors the progress of the learning model.

[0943] The server records the progress of the learning process (e.g., accuracy, changes in the loss function).

[0944] The device displays this information in real time in a dashboard format, allowing users to check their learning progress.

[0945] Step 6:

[0946] The server saves the model once training is complete.

[0947] The server either saves the trained model as a model file or stores it in a database for persistent storage.

[0948] Step 7:

[0949] The user enters their goals and skill set.

[0950] The user accesses the system again and enters their goal (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[0951] The terminal provides an interface for efficiently inputting and managing this information.

[0952] Step 8:

[0953] The server generates a learning plan based on the entered goals and skill set.

[0954] The server retrieves the information entered by the user and generates an appropriate training plan based on the trained model.

[0955] A study plan includes specific learning content, recommended resources, and a study schedule.

[0956] Step 9:

[0957] The server generates the schedule for the certification exam.

[0958] The server sets appropriate certification exam dates according to the user's goals.

[0959] The proposed exam schedule will include the exam date and time, preparation period, and important deadlines.

[0960] Step 10:

[0961] The device displays the generated study plan and qualification exam schedule.

[0962] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[0963] Users can begin learning based on this information.

[0964] (Example 1)

[0965] 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."

[0966] Conventional learning systems for engineers have suffered from insufficient automatic generation of learning plans and certification exam schedules tailored to individual user skill sets and goals, making it difficult for users to learn efficiently. Furthermore, the training of machine learning models based on stored data and the generation of learning plans using the results were rarely applied, and real-time tracking of user progress and the display of visual learning plans were incomplete, resulting in decreased user learning efficiency.

[0967] 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.

[0968] In this invention, the server includes means for receiving input information, means for storing the received information in a storage device, means for training a machine learning algorithm based on the stored information, means for generating a user-specific learning plan using the trained algorithm, and means for displaying the generated learning plan on a user interface. This makes it possible to automatically generate learning plans and qualification exam schedules tailored to the user's individual skill set and goals, and further enables users to efficiently progress in their studies by tracking progress in real time and visually displaying the learning plan.

[0969] "Input information" refers to various data that users provide to the system, such as their career history, skill set, learning history, and goals.

[0970] A "memory device" is a database or storage system used to store received information.

[0971] A "machine learning algorithm" is a mathematical model or computational method that learns from stored information and performs predictions and classifications.

[0972] A "user interface" is a visual interface through which a user interacts with a system, inputting data and viewing plans.

[0973] A "learning plan" is a set of specific learning content and schedule generated by the system to help the user achieve their goals.

[0974] The "certification exam schedule" refers to the date and time of the certification exam and the preparation timeline, which are set based on the user's goals.

[0975] "Real-time tracking" is a function that allows the system to monitor and record the user's learning progress in real time.

[0976] This invention is a system that enables engineers to learn efficiently and achieve their goals, and it functions through user data input, server-based data storage and model learning, and terminal-based provision of a user interface. Specific embodiments of the system are described below.

[0977] Hardware and software to use

[0978] The device provides an input form for the user to log in and enter data. Specifically, a web browser or mobile application is used.

[0979] The server stores data and trains machine learning models. Relational databases such as MySQL and MongoDB, as well as NoSQL databases, are used as databases. Machine learning algorithms include support vector machines, random forests, and neural networks.

[0980] The device provides a user interface for displaying study plans and qualification exam schedules, and also includes progress tracking and reminder functions.

[0981] Data collection and storage

[0982] Users log into the system and enter their work history, skill set, learning history, and goals they wish to achieve. This data is entered through input forms on the device and transmitted to the server in real time.

[0983] The server validates the submitted data in real time, checking for blank fields and verifying the format. Data that passes validation is securely stored in a MySQL or MongoDB database.

[0984] Training machine learning models

[0985] The server periodically retrieves stored data and performs data preprocessing (such as normalizing numerical data and imputing missing values). Then, it trains machine learning models using algorithms such as support vector machines, random forests, and neural networks. The trained models learn the characteristics and patterns of successful engineers and use that information to make predictions.

[0986] Generation and display of learning plans

[0987] Similarly, users input their goals and current skill sets into the system. For example, they might input a goal such as "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience.

[0988] The server generates a personalized learning plan for each user based on pre-trained models. Specifically, this plan includes weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also generates a certification exam schedule, for example, setting the exam six months in advance and providing study content and a timeline for exam preparation.

[0989] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[0990] Specific example

[0991] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[0992] Example of a prompt

[0993] "Please create a study plan to obtain the AWS Certified Solutions Architect certification. My current skill set includes Python and basic networking knowledge. The exam is scheduled for six months from now."

[0994] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve their desired goals.

[0995] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0996] Step 1: User Login

[0997] Operation: The user enters their username and password on the system's login screen and submits the authentication information.

[0998] Input: Username, Password

[0999] Data processing or calculation: The server receives authentication information and performs authentication by comparing it with user information in the database.

[1000] Output: The authentication result is returned, and if successful, a user session is started.

[1001] Step 2: Data Entry

[1002] Operation: The user uses the terminal's input form to enter their background, skill set, learning history, and goals.

[1003] Input: User background, skill set, learning history, goals

[1004] Data processing or calculation: The terminal collects the input data and sends it to the server.

[1005] Output: Data is sent to the server.

[1006] Step 3: Data Validation

[1007] Operation: The server checks for blank fields and verifies the format of the received data.

[1008] Input: Data entered by the user

[1009] Data processing or calculation: The server performs data blank detection and format validation.

[1010] Output: Validation results are output, and successful data proceeds to the next step.

[1011] Step 4: Save Data

[1012] Operation: The server saves data that has successfully been validated to a database such as MySQL or MongoDB.

[1013] Input: Data that successfully passed validation

[1014] Data processing or calculation: The server executes an insert query (INSERT) against the database.

[1015] Output: The data is saved to the database.

[1016] Step 5: Data Retrieval

[1017] Operation: The server periodically queries and retrieves stored data.

[1018] Input: Query against stored data

[1019] Data processing or calculation: The server retrieves the necessary data from the database using SQL or NoSQL queries.

[1020] Output: The acquired data proceeds to the next step.

[1021] Step 6: Data Preprocessing

[1022] Operation: The server performs preprocessing on the retrieved data, such as normalizing numerical data and imputing missing values.

[1023] Input: Acquired data

[1024] Data processing or calculations: The server performs data normalization (e.g., Min-Max Scaling or Standard Scaler) and imputation of missing values ​​(e.g., mean imputation).

[1025] Output: Pre-processed data is obtained.

[1026] Step 7: Training the machine learning model

[1027] Operation: The server applies machine learning algorithms (e.g., support vector machines, random forests, neural networks) to preprocessed data and trains the model.

[1028] Input: Preprocessed data

[1029] Data processing or computation: The server uses the specified algorithm to train the training data and optimize the model parameters.

[1030] Output: Trained machine learning model.

[1031] Step 8: Display the dashboard

[1032] Operation: The terminal displays the training progress received from the server as graphs and charts.

[1033] Input: Training progress (e.g., model accuracy, change in loss function)

[1034] Data processing or calculation: The terminal generates graphs and charts to visualize the received data.

[1035] Output: A progress dashboard is displayed to the user.

[1036] Step 9: Enter a new goal

[1037] Operation: The user enters a new goal (e.g., obtaining AWS Certified Solutions Architect certification) and their current skill set into the system.

[1038] Input: Goals and current skill set

[1039] Data processing or calculation: The terminal sends the input to the server.

[1040] Output: New goal and skill set data is sent to the server.

[1041] Step 10: Generating a study plan

[1042] Operation: The server generates individual learning plans using pre-trained models based on new goals and skill sets.

[1043] Input: New goals and skill sets

[1044] Data processing or computation: The server uses the trained model to generate an optimal learning plan (weekly learning content, recommended materials, and progress tracking methods).

[1045] Output: The generated training plan.

[1046] Step 11: Generate a schedule for the certification exam.

[1047] Operation: The server generates a qualification exam schedule based on the user's goals, for example, setting an exam date six months in advance.

[1048] Input: User's goal

[1049] Data processing or calculation: The server uses a schedule generation algorithm to set the test schedule.

[1050] Output: Qualification exam schedule.

[1051] Step 12: Display your study plan and schedule

[1052] Operation: The device displays the generated study plan and qualification exam schedule in a calendar format.

[1053] Input: Study plan, qualification exam schedule

[1054] Data processing or calculation: The terminal generates a calendar that visualizes the learning plan and schedule.

[1055] Output: Study plan and exam schedule in calendar format.

[1056] Step 13: Track progress

[1057] Operation: The device tracks the user's learning progress in real time and displays the completion status of planned learning content.

[1058] Input: Progress data

[1059] Data processing or calculation: The terminal analyzes progress data and generates completion status and reminders.

[1060] Output: Display of progress and reminders.

[1061] (Application Example 1)

[1062] 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."

[1063] Conventional technologies have made it difficult to create concrete learning plans for engineers and operators working in factories, based on their individual skill levels and goals. Furthermore, the lack of real-time means to monitor work procedures and learning progress hindered effective skill development. This invention aims to solve these problems and provide a system that supports efficient skill development for engineers within factories.

[1064] 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.

[1065] In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan on a display device, means for displaying work procedures and learning progress in real time using the display device, and means for notifying the user of reminders regarding work procedures and learning progress. This enables engineers and operators to obtain an optimal learning plan based on their own skill set and goals, and to efficiently improve their skills while checking their progress in real time.

[1066] "Means for receiving input data" refers to a device or function that provides an interface for a user to input their career history, skill set, learning history, and goals into the system.

[1067] "Means for storing received data" refers to a device or function for securely storing data entered by a user in a storage device such as a database, after properly validating it.

[1068] "Means for training machine learning models based on stored data" refers to a device or function for appropriately preprocessing stored user data and training machine learning models using algorithms such as support vector machines or neural networks.

[1069] "Means for generating a user-specific learning plan using a pre-trained model" refers to a device or function that automatically generates an optimal, customized learning plan for each user using a pre-trained machine learning model.

[1070] "Means for displaying the generated learning plan on a display device" refers to a device or function for visually displaying the generated user-specific learning plan.

[1071] "Means for displaying work procedures and learning progress in real time using a display device" refers to a device or function for displaying work procedures and learning progress on a display device so that they can be visually confirmed in real time.

[1072] "Means for notifying users of work procedures and learning progress" refers to a device or function for sending notifications regarding work procedures and learning progress as reminders to users.

[1073] This invention provides a system that enables engineers to learn efficiently and achieve their goals. The following describes specific embodiments of the invention.

[1074] The system consists of user terminals, servers, and display devices.

[1075] First, the user logs into the terminal and enters their work history, skill set, learning history, and goals. The terminal receives the input data and sends it to the server. The server validates the received data in real time and securely stores it in a database such as MySQL or MongoDB.

[1076] The stored data is periodically retrieved by the server and used to train machine learning models. Data preprocessing includes imputation of missing values ​​and normalization of numerical data. Subsequently, the models are trained using algorithms such as support vector machines and neural networks.

[1077] The device uses a pre-trained model to generate a personalized learning plan for each user. For example, for a user whose goal is to "pass the AWS Certified Solutions Architect exam," the system automatically generates specific weekly study content, recommended reference materials, and progress tracking methods. This plan is customized according to the user's skill set and goals.

[1078] Furthermore, the server displays the generated learning plan in real time on a display device. This display device is expected to be a smart glasses or head-mounted display. This allows the user to check work procedures and learning progress in real time. The display device also has a function to notify users of reminders regarding work procedures and learning progress.

[1079] To illustrate the process using a concrete example, consider a scenario where a user wears smart glasses and performs machine maintenance work in a factory. The user inputs their skill set (e.g., basic knowledge of Python and networking) into the system and sets a goal (e.g., acquiring a specific machine maintenance skill). The system receives this information, stores it in a database, and generates an appropriate learning plan using a trained model. The smart glasses display the work procedures and learning progress in real time within the user's field of view.

[1080] Examples of prompt statements to input into a generative AI model are as follows:

[1081] User skill set: X, Y, Z

[1082] Objective: To acquire basic maintenance skills.

[1083] Desired time: 1 month

[1084] Based on this prompt, the system provides a learning plan and real-time display to help engineers efficiently improve their skills.

[1085] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1086] Step 1:

[1087] The user logs into the device and enters their background, skill set, learning history, and goals. The entered data is received by the device and sent to the server.

[1088] Input: User background, skill set, learning history, goals

[1089] Output: Received data

[1090] Specific operation: The user enters the required information into the input form on the terminal and clicks the submit button. The terminal receives the input data and sends it to the server.

[1091] Step 2:

[1092] The server validates the received data and saves it to a database such as MySQL or MongoDB. Validation includes checking for blank fields and verifying data format.

[1093] Input: Received data

[1094] Output: Saving validated data

[1095] Specific operation: The server checks for blank fields and formatting of the received data, and then saves it to the database after formatting it appropriately.

[1096] Step 3:

[1097] The server periodically retrieves and preprocesses the stored data. Data preprocessing includes imputing missing values ​​and normalizing numerical data.

[1098] Input: Saved data

[1099] Output: Preprocessed data

[1100] Specific operation: The server reads the stored data and automatically performs preprocessing such as imputing missing values ​​and normalizing numerical data.

[1101] Step 4:

[1102] The server uses the preprocessed data to train machine learning models using algorithms such as support vector machines and neural networks.

[1103] Input: Preprocessed data

[1104] Output: Trained model

[1105] Specific operation: The server inputs pre-processed data into the algorithm and trains the model for a specified number of epochs.

[1106] Step 5:

[1107] The server uses a pre-trained model to generate a personalized learning plan for the user. The generated plan includes specific weekly learning content, recommended reference materials, and progress tracking methods.

[1108] Input: Trained model and user data

[1109] Output: User-specific learning plan

[1110] Specific operation: The server inputs the user's skill set and goals into a pre-trained model and automatically generates an optimal learning plan.

[1111] Step 6:

[1112] The server sends the generated learning plan to a display device for real-time display. Smart glasses or head-mounted displays are used as the display device.

[1113] Input: User-specific learning plan

[1114] Output: Display of the learning plan on the display device.

[1115] Specific operation: The server sends the generated learning plan to smart glasses or a head-mounted display, allowing the user to view it in real time.

[1116] Step 7:

[1117] The display device shows work procedures and learning progress in real time and notifies users of reminders as needed.

[1118] Input: User-specific learning plan and progress data

[1119] Output: Notification and display to the user

[1120] Specific operation: Smart glasses or head-mounted displays monitor the user's learning progress and display reminders and work procedures in their field of vision.

[1121] 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.

[1122] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan in response to those emotions. Specific embodiments thereof are described below.

[1123] System-wide configuration

[1124] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, and emotion engine-side emotion recognition and analysis.

[1125] Data collection

[1126] After logging into the system, users enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is entered through input forms on the device.

[1127] The server validates the input data in real time and saves it to the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[1128] Model Learning

[1129] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[1130] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked.

[1131] Emotion recognition by an emotion engine

[1132] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[1133] The server receives and stores emotional data from the emotion engine. Emotional data is also stored in a database for analyzing long-term emotional trends.

[1134] Creating and adjusting study plans

[1135] Users enter their goals and current skill sets. For example, they might enter a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[1136] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[1137] Furthermore, the server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan can be modified to reduce the learning burden.

[1138] Qualification exam schedule

[1139] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[1140] Displaying the study plan

[1141] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[1142] Specific example

[1143] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[1144] Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to include measures to reduce the intensity of the learning content and promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[1145] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve individual goals while taking into account the emotional state of the user.

[1146] The following describes the processing flow.

[1147] Step 1:

[1148] The user logs into the system.

[1149] The user enters their ID and password and clicks the login button.

[1150] The server verifies the entered authentication information against the database and redirects the user to the dashboard if authentication is successful.

[1151] Step 2:

[1152] Users enter their own background, skill set, and goals.

[1153] Users enter detailed technical information into the input form. Specifically, they fill in information such as past project experience, technologies used, qualifications obtained, and educational history.

[1154] The terminal provides an interface to assist in inputting this information.

[1155] Step 3:

[1156] The server saves the entered data.

[1157] The server validates the entered data in real time, checking whether all required fields are filled in and whether the data format is correct.

[1158] Save the data that passed validation to the database.

[1159] Step 4:

[1160] The server trains a machine learning model based on the stored data.

[1161] The server retrieves engineer profile information from the database and performs preprocessing. Preprocessing includes data normalization and imputation of missing values.

[1162] The data is split into training data and test data, and a model is trained using algorithms such as support vector machines or neural networks.

[1163] Step 5:

[1164] The device monitors the progress of the learning model.

[1165] The device displays the progress of the learning process (e.g., accuracy, changes in the loss function) in real time on a dashboard, allowing the user to monitor the learning progress.

[1166] Step 6:

[1167] The server saves the model once training is complete.

[1168] The server either saves the trained model as a model file or stores it in a database for persistent storage.

[1169] Step 7:

[1170] The user enters their goals and skill set.

[1171] The user accesses the system again and enters their goal (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[1172] The terminal provides an interface for efficiently inputting and managing this information.

[1173] Step 8:

[1174] The server generates a learning plan based on the entered goals and skill set.

[1175] The server retrieves the information entered by the user and generates an appropriate training plan based on the trained model.

[1176] A study plan includes specific learning content, recommended resources, and a study schedule.

[1177] Step 9:

[1178] The server generates the schedule for the certification exam.

[1179] The server sets appropriate certification exam dates according to the user's goals.

[1180] The proposed exam schedule will include the exam date and time, preparation period, and important deadlines.

[1181] Step 10:

[1182] The device displays the generated study plan and qualification exam schedule.

[1183] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[1184] Step 11:

[1185] The device collects user emotion data.

[1186] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[1187] The emotion engine analyzes this data to recognize the user's current emotional state.

[1188] Step 12:

[1189] The server stores emotional data.

[1190] The system receives emotional data from the emotion engine and stores it in a database.

[1191] Emotional data will also be recorded for long-term sentiment analysis.

[1192] Step 13:

[1193] The server adjusts the learning plan based on sentiment data.

[1194] The learning plan is adjusted in real time according to the user's emotional state. For example, if the user is feeling stressed, the content is changed to reduce the learning burden.

[1195] The tailored plan is designed to allow users to learn at their own pace without feeling overwhelmed.

[1196] Step 14:

[1197] The device will display the adjusted learning plan.

[1198] The adjusted study plan is displayed again in calendar format, and the user is notified.

[1199] Users can review the new plan and continue their learning.

[1200] (Example 2)

[1201] 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."

[1202] Conventional learning plan generation systems have difficulty considering the individual emotional state of users, which can lead to decreased learning efficiency. Furthermore, scheduling certification exams could not reflect the user's learning progress or emotional state in real time. This resulted in users experiencing stress and being unable to progress with their studies according to plan.

[1203] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan to the user, means for collecting and analyzing user sentiment data, and means for adjusting the learning plan based on the sentiment data. This makes it possible to efficiently provide a learning plan while taking into account the individual emotional state of the user, making it easier for engineers to achieve their goals.

[1204] "Input data" refers to information that users provide to the system, including data such as work history, skill set, and goals.

[1205] "Means of acceptance" refers to the interface or process that a system uses to obtain input data from a user.

[1206] "Means of storage" refers to mechanisms or processes for storing input data temporarily or permanently in a memory device.

[1207] A "machine learning model" is an algorithm or program that learns from data and performs tasks such as prediction and classification.

[1208] A "trained model" is a machine learning model that has been optimized based on training data, and it is a model that makes predictions and recommendations using user input data.

[1209] A "user-specific learning plan" is a learning plan and schedule that is automatically customized based on the user's individual goals and skill set.

[1210] "Means of display" refers to interfaces or devices that visually show the generated learning plan to the user.

[1211] "Emotional data" refers to data that represents a user's emotional state, obtained from their facial expressions, voice, and actions.

[1212] "Means of collection and analysis" refers to systems and processes for acquiring emotional data, analyzing it, and determining the user's emotional state.

[1213] "Means of adjustment" refer to mechanisms or processes for dynamically changing the learning plan based on the user's emotional data.

[1214] "Means of preprocessing" refers to mechanisms or processes that perform operations such as normalization, imputation of missing values, and conversion of data formats in order to improve the quality of the data.

[1215] "Skills" refer to information that indicates the level of a user's specific knowledge or technical abilities.

[1216] A "qualification exam schedule" is a schedule that helps users plan the timing of their studies and exams in preparation for the qualification exam they are aiming for.

[1217] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan tailored to those emotions. The system consists of means for user data input, data storage and model training by a server, provision of a user interface by a terminal, and recognition and analysis of the user's emotions by an emotion engine.

[1218] Data collection

[1219] Users log in to the system using a terminal and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered through input forms on the terminal. The server validates the entered data in real time and stores it in the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[1220] Model Learning

[1221] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and makes predictions based on them. The terminal displays the progress of the learning process in real time on a dashboard. Here, for example, the accuracy of the model, changes in the loss function, and the progress of the learning epoch can be visually checked.

[1222] Emotion recognition by an emotion engine

[1223] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust). The server receives the emotional data from the emotion engine and stores it. The emotional data is also stored in a database to analyze long-term emotional trends.

[1224] Creating and adjusting study plans

[1225] Users input their goals and current skill sets. For example, they might input a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server. Based on a trained model, the server generates a personalized learning plan for the user. This plan might include specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also adjusts the learning plan in real time based on sentiment data from the sentiment engine. For example, if the user is experiencing stress, the plan can be modified to reduce the learning burden.

[1226] Qualification exam schedule

[1227] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[1228] Displaying the study plan

[1229] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[1230] Specific example

[1231] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance. Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to slightly reduce the learning content and include measures to promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[1232] Example of a prompt

[1233] "My goal is to pass the AWS Certified Solutions Architect exam. My current skill set includes Python and basic networking knowledge. Please generate a study plan for each AWS service."

[1234] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1235] Step 1:

[1236] Users log in to their terminal and enter their work history, skill set, and goals. Specifically, they enter information such as past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals into an input form. The input data includes goals such as "obtaining AWS Certified Solutions Architect certification" and skill sets such as "Python" and "fundamental networking knowledge." The input data is sent from the terminal to the server.

[1237] Input: Data from the user regarding their career history, skill set, and goals.

[1238] Output: User data sent to the server

[1239] Step 2:

[1240] The server validates the received input data in real time. The validation process includes checking required fields (e.g., whether goals and skill sets are present) and checking data format (e.g., date format and integer values). Once validation is complete, the data is stored in a database such as MySQL or MongoDB.

[1241] Input: User data sent from the terminal

[1242] Output: Validated user data, saved to the database.

[1243] Step 3:

[1244] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Subsequently, models are trained using algorithms such as support vector machines, random forests, and neural networks.

[1245] Input: Validated user data

[1246] Output: Trained machine learning model

[1247] Step 4:

[1248] The device displays the progress of the learning process in real time on a dashboard. Here, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is retrieved from the server and displayed on the device's screen.

[1249] Input: Training process data from the server

[1250] Output: Learning process visualization data on the dashboard

[1251] Step 5:

[1252] The device periodically sends user facial expressions, voice, and behavioral data to the emotion engine. For example, it collects data using the camera and microphone when the user is watching a lesson video. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[1253] Input: User's facial expressions, voice, and behavioral data

[1254] Output: Recognized user emotional state data

[1255] Step 6:

[1256] The server receives emotional data from the emotion engine and stores it in a database. Simultaneously, it analyzes the emotional data and uses it to understand long-term emotional trends.

[1257] Input: Emotional state data from the emotion engine

[1258] Output: Emotional state data stored in the database, analysis results

[1259] Step 7:

[1260] The server generates a personalized learning plan based on pre-trained models. This plan may include, for example, what AWS services to learn each week, recommended reference materials, and methods for tracking progress. This plan is automatically customized according to the user's goals and current skill level.

[1261] Input: Stored user data, trained model

[1262] Output: User-specific learning plan

[1263] Step 8:

[1264] The server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan is modified to include measures that reduce the learning content and promote relaxation.

[1265] Input: Emotional state data

[1266] Output: Adjusted learning plan

[1267] Step 9:

[1268] The device visually displays the generated study plan and qualification exam schedule. It uses a calendar format to allow users to visually check their progress and next tasks. A reminder function is also implemented to help users stay on track with their studies.

[1269] Input: Generated and adjusted study plans, qualification exam schedules

[1270] Output: Visually displayed study plan and exam schedule

[1271] (Application Example 2)

[1272] 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."

[1273] While improving the productivity of factory workers, it is also necessary to appropriately adjust work content according to the emotional state of the workers and effectively manage their mental health. This invention aims to improve the working environment and reduce worker stress by providing a system that recognizes and analyzes workers' emotions and adjusts work content and learning plans based on the results.

[1274] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model and sentiment analysis results, means for displaying the generated learning plan to the user, and means for adjusting work content and providing mental care guidance based on sentiment analysis results. This enables real-time monitoring of workers' emotions and allows for appropriate work adjustments and mental care.

[1275] "Means for receiving input data" refers to functions that collect data such as user history, skill sets, and goals through input forms or similar means.

[1276] "Means for saving received data" refers to a function that validates user-entered data in real time and saves it to the database in an appropriate format.

[1277] "Methods for training machine learning models based on stored data" refers to functions that retrieve stored data, preprocess the data, and then train models using various machine learning algorithms.

[1278] "Means for recognizing and analyzing user emotions" refers to a system that analyzes a user's facial expressions, voice, and behavioral data to recognize their emotional state.

[1279] "Means for generating a user-specific learning plan using a trained model and sentiment analysis results" refers to a function that automatically generates a learning plan optimized for the user based on a trained machine learning model and the results of sentiment analysis.

[1280] "Means for displaying the generated learning plan to the user" refers to an interface that visually displays the customized learning plan, making it easy for the user to follow along.

[1281] "A means of adjusting work content and providing mental care guidance based on emotion analysis results" refers to a function that takes the user's emotional state into consideration, adjusts work content in real time, and provides mental care as needed.

[1282] This invention relates to a system that recognizes the emotions of workers in a factory and customizes work content and learning plans according to those emotions. Specific embodiments are described below.

[1283] System-wide configuration

[1284] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, emotion recognition and analysis by an emotion engine, and means for adjusting workers' work conditions and providing mental care support.

[1285] Data collection

[1286] After logging into the system, users enter their career history, current skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered into the terminal and sent to the server.

[1287] The server validates the input data in real time and stores it in the database in the appropriate format. The data validation process includes checking required fields and verifying the data format. Databases such as MySQL and MongoDB are used.

[1288] Model Learning

[1289] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses them to make predictions.

[1290] The device displays the progress of the learning process in real time on a dashboard. Here, you can visually check the model's accuracy, changes in the loss function, and the progress of the learning epochs.

[1291] Emotion recognition by an emotion engine

[1292] The terminal transmits facial expressions, voice, and behavioral data collected from the worker via the camera and microphone to the emotion engine. The emotion engine analyzes this data to recognize the worker's current emotional state (joy, anger, sadness, surprise, fear, disgust). For emotion recognition, for example, OpenCV (face recognition) and Keras (emotion recognition model) are used.

[1293] The server generates personalized learning plans for workers based on emotional data received from the emotion engine. These plans include specific weekly learning content, recommended reference materials, and progress tracking methods.

[1294] Adjusting the study plan

[1295] The server adjusts learning plans and work content in real time based on emotional data obtained from the emotion engine. For example, if a worker is experiencing stress, it can reduce the learning burden and change work content to a more relaxing one. It also provides mental health support.

[1296] Qualification exam schedule

[1297] The server sets appropriate qualification exam dates based on the worker's goals. It adjusts the exam preparation period and exam date, taking into account the worker's learning progress and emotional state.

[1298] Displaying the study plan

[1299] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for workers to follow along. Progress tracking and reminder functions are also provided to help workers stay on track with their studies.

[1300] Specific example:

[1301] For example, suppose a worker sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information and uses a pre-trained model to generate an appropriate learning plan. This plan includes what to learn about each AWS service each week, along with related exercises and practice tests. The exam dates are also set.

[1302] The device uses an emotion engine to analyze the worker's facial expressions and voice to understand their emotional state during learning. For example, if the worker is feeling fatigued, the server adjusts the learning plan to include some lighter learning content and measures to promote relaxation.

[1303] Examples of prompt statements:

[1304] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[1305] In this way, the present invention makes it possible to provide a system that allows workers to efficiently carry out their work and learning, and to achieve their individual goals, while taking into account the emotional state of the workers.

[1306] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1307] Step 1:

[1308] Users log into the system and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is collected through input forms on the terminal. The entered data is sent to the server in a standard format (e.g., JSON or XML).

[1309] Step 2:

[1310] The server validates the received data. Specifically, it checks required fields and data format. For example, it verifies whether skill sets and experience are entered correctly. The validated data is stored in a database (MySQL or MongoDB) in an organized format (e.g., normalized numbers or formatted text).

[1311] Step 3:

[1312] The server retrieves the stored data and trains a machine learning model. Data preprocessing includes normalization of numerical data and imputation of missing values. The preprocessed data is then used to train a model using machine learning algorithms such as support vector machines (SVMs), random forests, and neural networks. Model training involves iterative computation with multiple epochs using the training dataset, and is repeated until the model's accuracy improves.

[1313] Step 4:

[1314] The device displays the progress and accuracy of the trained model on a dashboard. The displayed information includes model accuracy, changes in the loss function, and progress through training epochs. The dashboard consists of visually easy-to-understand graphs and charts, allowing users to understand the model's performance in real time.

[1315] Step 5:

[1316] The terminal transmits facial expressions, voice, and behavioral data of workers collected through the camera and microphone to the emotion engine. Specifically, it analyzes emotions using facial image data captured by the camera and voice data collected by the microphone. The emotion engine uses OpenCV and Keras to analyze this data and recognize the worker's emotional state (joy, anger, sadness, surprise, fear, disgust). This analysis uses an emotion recognition model (e.g., a pre-trained CNN model).

[1317] Step 6:

[1318] The server generates a personalized learning plan for each worker based on the emotional data received from the emotion engine. This plan includes specific weekly learning content, recommended reference materials, and progress tracking methods. The emotional data is received in JSON format and integrated with other user data stored in the database.

[1319] Step 7:

[1320] The server adjusts learning plans and work content in real time based on the results of emotion analysis. For example, if a worker is feeling stressed, it will reduce the learning burden and change the content to promote relaxation. This adjustment is optimized based on past emotion data and success stories obtained from the database.

[1321] Step 8:

[1322] The device displays the generated learning plan and work adjustments to the worker. It also provides a calendar-style display, tracking functions, and reminder functions to help workers progress with their learning according to the plan. Mental health advice is also displayed as needed.

[1323] Examples of specific prompt messages:

[1324] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[1325] In this way, each step works in coordination, and a system is realized that provides optimal work adjustments and learning plans while taking into account the emotional state of the workers.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] [Fourth Embodiment]

[1330] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1331] 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.

[1332] 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).

[1333] 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.

[1334] 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.

[1335] 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).

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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".

[1343] This invention provides a system that enables engineers to learn efficiently and achieve their goals. Specific embodiments thereof are described below.

[1344] System-wide configuration

[1345] The system consists of means for user data input, server-side data storage and model training, and terminal-side provision of a user interface.

[1346] Data collection

[1347] The user first logs into the system. After logging in, the user enters their technical experience, skill set, learning history, and goals they wish to achieve. This data is entered through an input form on the terminal.

[1348] The server validates the input data in real time and saves it to the database in the appropriate format. This includes checking for blank fields and verifying the format. If validation is successful, the data is stored securely. The saved data is stored in a database such as MySQL or MongoDB.

[1349] Model Learning

[1350] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[1351] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is also useful for the user, helping them to understand the progress of the learning process.

[1352] Generating a learning plan

[1353] Users input their goals and current skill sets into the system. For example, they might input a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[1354] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[1355] Furthermore, the server also generates a schedule for certification exams. Based on the user's goals, it might schedule an exam six months in advance and present study content and a timeline for exam preparation. This schedule is designed to allow users to study efficiently and prepare for the exam.

[1356] Displaying the study plan

[1357] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[1358] Specific example

[1359] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[1360] In this way, the present invention makes it possible to provide a system that enables engineers to efficiently advance their learning and achieve their desired goals.

[1361] The following describes the processing flow.

[1362] Step 1:

[1363] The user logs into the system.

[1364] The user enters their ID and password and clicks the login button.

[1365] The server compares the received authentication information with the database and redirects the user to the dashboard if authentication is successful.

[1366] Step 2:

[1367] Users enter their own background, skill set, and goals.

[1368] Users enter detailed technical information into the input form. Specifically, they fill in information such as past project experience, technologies used, qualifications obtained, and learning history.

[1369] The terminal provides an interface to assist in inputting this information.

[1370] Step 3:

[1371] The server saves the entered data.

[1372] The server validates the entered data in real time, checking whether all required fields are filled in and whether the data format is correct.

[1373] Save the data that passed validation to the database.

[1374] Step 4:

[1375] The server trains a machine learning model based on the stored data.

[1376] The server retrieves engineer profile information from the database and performs preprocessing. Preprocessing includes data normalization and imputation of missing values.

[1377] The data is split into training data and test data, and a model is trained using algorithms such as support vector machines or neural networks.

[1378] Step 5:

[1379] The server monitors the progress of the learning model.

[1380] The server records the progress of the learning process (e.g., accuracy, changes in the loss function).

[1381] The device displays this information in real time in a dashboard format, allowing users to check their learning progress.

[1382] Step 6:

[1383] The server saves the model once training is complete.

[1384] The server either saves the trained model as a model file or stores it in a database for persistent storage.

[1385] Step 7:

[1386] The user enters their goals and skill set.

[1387] The user accesses the system again and enters their goal (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[1388] The terminal provides an interface for efficiently inputting and managing this information.

[1389] Step 8:

[1390] The server generates a learning plan based on the entered goals and skill set.

[1391] The server retrieves the information entered by the user and generates an appropriate training plan based on the trained model.

[1392] A study plan includes specific learning content, recommended resources, and a study schedule.

[1393] Step 9:

[1394] The server generates the schedule for the certification exam.

[1395] The server sets appropriate certification exam dates according to the user's goals.

[1396] The proposed exam schedule will include the exam date and time, preparation period, and important deadlines.

[1397] Step 10:

[1398] The device displays the generated study plan and qualification exam schedule.

[1399] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[1400] Users can begin learning based on this information.

[1401] (Example 1)

[1402] 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".

[1403] Conventional learning systems for engineers have suffered from insufficient automatic generation of learning plans and certification exam schedules tailored to individual user skill sets and goals, making it difficult for users to learn efficiently. Furthermore, the training of machine learning models based on stored data and the generation of learning plans using the results were rarely applied, and real-time tracking of user progress and the display of visual learning plans were incomplete, resulting in decreased user learning efficiency.

[1404] 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.

[1405] In this invention, the server includes means for receiving input information, means for storing the received information in a storage device, means for training a machine learning algorithm based on the stored information, means for generating a user-specific learning plan using the trained algorithm, and means for displaying the generated learning plan on a user interface. This makes it possible to automatically generate learning plans and qualification exam schedules tailored to the user's individual skill set and goals, and further enables users to efficiently progress in their studies by tracking progress in real time and visually displaying the learning plan.

[1406] "Input information" refers to various data that users provide to the system, such as their career history, skill set, learning history, and goals.

[1407] A "memory device" is a database or storage system used to store received information.

[1408] A "machine learning algorithm" is a mathematical model or computational method that learns from stored information and performs predictions and classifications.

[1409] A "user interface" is a visual interface through which a user interacts with a system, inputting data and viewing plans.

[1410] A "learning plan" is a set of specific learning content and schedule generated by the system to help the user achieve their goals.

[1411] The "certification exam schedule" refers to the date and time of the certification exam and the preparation timeline, which are set based on the user's goals.

[1412] "Real-time tracking" is a function that allows the system to monitor and record the user's learning progress in real time.

[1413] This invention is a system that enables engineers to learn efficiently and achieve their goals, and it functions through user data input, server-based data storage and model learning, and terminal-based provision of a user interface. Specific embodiments of the system are described below.

[1414] Hardware and software to use

[1415] The device provides an input form for the user to log in and enter data. Specifically, a web browser or mobile application is used.

[1416] The server stores data and trains machine learning models. Relational databases such as MySQL and MongoDB, as well as NoSQL databases, are used as databases. Machine learning algorithms include support vector machines, random forests, and neural networks.

[1417] The device provides a user interface for displaying study plans and qualification exam schedules, and also includes progress tracking and reminder functions.

[1418] Data collection and storage

[1419] Users log into the system and enter their work history, skill set, learning history, and goals they wish to achieve. This data is entered through input forms on the device and transmitted to the server in real time.

[1420] The server validates the submitted data in real time, checking for blank fields and verifying the format. Data that passes validation is securely stored in a MySQL or MongoDB database.

[1421] Training machine learning models

[1422] The server periodically retrieves stored data and performs data preprocessing (such as normalizing numerical data and imputing missing values). Then, it trains machine learning models using algorithms such as support vector machines, random forests, and neural networks. The trained models learn the characteristics and patterns of successful engineers and use that information to make predictions.

[1423] Generation and display of learning plans

[1424] Similarly, users input their goals and current skill sets into the system. For example, they might input a goal such as "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience.

[1425] The server generates a personalized learning plan for each user based on pre-trained models. Specifically, this plan includes weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also generates a certification exam schedule, for example, setting the exam six months in advance and providing study content and a timeline for exam preparation.

[1426] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for users to understand and implement. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[1427] Specific example

[1428] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[1429] Example of a prompt

[1430] "Please create a study plan to obtain the AWS Certified Solutions Architect certification. My current skill set includes Python and basic networking knowledge. The exam is scheduled for six months from now."

[1431] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve their desired goals.

[1432] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1433] Step 1: User Login

[1434] Operation: The user enters their username and password on the system's login screen and submits the authentication information.

[1435] Input: Username, Password

[1436] Data processing or calculation: The server receives authentication information and performs authentication by comparing it with user information in the database.

[1437] Output: The authentication result is returned, and if successful, a user session is started.

[1438] Step 2: Data Entry

[1439] Operation: The user uses the terminal's input form to enter their background, skill set, learning history, and goals.

[1440] Input: User background, skill set, learning history, goals

[1441] Data processing or calculation: The terminal collects the input data and sends it to the server.

[1442] Output: Data is sent to the server.

[1443] Step 3: Data Validation

[1444] Operation: The server checks for blank fields and verifies the format of the received data.

[1445] Input: Data entered by the user

[1446] Data processing or calculation: The server performs data blank detection and format validation.

[1447] Output: Validation results are output, and successful data proceeds to the next step.

[1448] Step 4: Save Data

[1449] Operation: The server saves data that has successfully been validated to a database such as MySQL or MongoDB.

[1450] Input: Data that successfully passed validation

[1451] Data processing or calculation: The server executes an insert query (INSERT) against the database.

[1452] Output: The data is saved to the database.

[1453] Step 5: Data Retrieval

[1454] Operation: The server periodically queries and retrieves stored data.

[1455] Input: Query against stored data

[1456] Data processing or calculation: The server retrieves the necessary data from the database using SQL or NoSQL queries.

[1457] Output: The acquired data proceeds to the next step.

[1458] Step 6: Data Preprocessing

[1459] Operation: The server performs preprocessing on the retrieved data, such as normalizing numerical data and imputing missing values.

[1460] Input: Acquired data

[1461] Data processing or calculations: The server performs data normalization (e.g., Min-Max Scaling or Standard Scaler) and imputation of missing values ​​(e.g., mean imputation).

[1462] Output: Pre-processed data is obtained.

[1463] Step 7: Training the machine learning model

[1464] Operation: The server applies machine learning algorithms (e.g., support vector machines, random forests, neural networks) to preprocessed data and trains the model.

[1465] Input: Preprocessed data

[1466] Data processing or computation: The server uses the specified algorithm to train the training data and optimize the model parameters.

[1467] Output: Trained machine learning model.

[1468] Step 8: Display the dashboard

[1469] Operation: The terminal displays the training progress received from the server as graphs and charts.

[1470] Input: Training progress (e.g., model accuracy, change in loss function)

[1471] Data processing or calculation: The terminal generates graphs and charts to visualize the received data.

[1472] Output: A progress dashboard is displayed to the user.

[1473] Step 9: Enter a new goal

[1474] Operation: The user enters a new goal (e.g., obtaining AWS Certified Solutions Architect certification) and their current skill set into the system.

[1475] Input: Goals and current skill set

[1476] Data processing or calculation: The terminal sends the input to the server.

[1477] Output: New goal and skill set data is sent to the server.

[1478] Step 10: Generating a study plan

[1479] Operation: The server generates individual learning plans using pre-trained models based on new goals and skill sets.

[1480] Input: New goals and skill sets

[1481] Data processing or computation: The server uses the trained model to generate an optimal learning plan (weekly learning content, recommended materials, and progress tracking methods).

[1482] Output: The generated training plan.

[1483] Step 11: Generate a schedule for the certification exam.

[1484] Operation: The server generates a qualification exam schedule based on the user's goals, for example, setting an exam date six months in advance.

[1485] Input: User's goal

[1486] Data processing or calculation: The server uses a schedule generation algorithm to set the test schedule.

[1487] Output: Qualification exam schedule.

[1488] Step 12: Display your study plan and schedule

[1489] Operation: The device displays the generated study plan and qualification exam schedule in a calendar format.

[1490] Input: Study plan, qualification exam schedule

[1491] Data processing or calculation: The terminal generates a calendar that visualizes the learning plan and schedule.

[1492] Output: Study plan and exam schedule in calendar format.

[1493] Step 13: Track progress

[1494] Operation: The device tracks the user's learning progress in real time and displays the completion status of planned learning content.

[1495] Input: Progress data

[1496] Data processing or calculation: The terminal analyzes progress data and generates completion status and reminders.

[1497] Output: Display of progress and reminders.

[1498] (Application Example 1)

[1499] 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".

[1500] Conventional technologies have made it difficult to create concrete learning plans for engineers and operators working in factories, based on their individual skill levels and goals. Furthermore, the lack of real-time means to monitor work procedures and learning progress hindered effective skill development. This invention aims to solve these problems and provide a system that supports efficient skill development for engineers within factories.

[1501] 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.

[1502] In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan on a display device, means for displaying work procedures and learning progress in real time using the display device, and means for notifying the user of reminders regarding work procedures and learning progress. This enables engineers and operators to obtain an optimal learning plan based on their own skill set and goals, and to efficiently improve their skills while checking their progress in real time.

[1503] "Means for receiving input data" refers to a device or function that provides an interface for a user to input their career history, skill set, learning history, and goals into the system.

[1504] "Means for storing received data" refers to a device or function for securely storing data entered by a user in a storage device such as a database, after properly validating it.

[1505] "Means for training machine learning models based on stored data" refers to a device or function for appropriately preprocessing stored user data and training machine learning models using algorithms such as support vector machines or neural networks.

[1506] "Means for generating a user-specific learning plan using a pre-trained model" refers to a device or function that automatically generates an optimal, customized learning plan for each user using a pre-trained machine learning model.

[1507] "Means for displaying the generated learning plan on a display device" refers to a device or function for visually displaying the generated user-specific learning plan.

[1508] "Means for displaying work procedures and learning progress in real time using a display device" refers to a device or function for displaying work procedures and learning progress on a display device so that they can be visually confirmed in real time.

[1509] "Means for notifying users of work procedures and learning progress" refers to a device or function for sending notifications regarding work procedures and learning progress as reminders to users.

[1510] This invention provides a system that enables engineers to learn efficiently and achieve their goals. The following describes specific embodiments of the invention.

[1511] The system consists of user terminals, servers, and display devices.

[1512] First, the user logs into the terminal and enters their work history, skill set, learning history, and goals. The terminal receives the input data and sends it to the server. The server validates the received data in real time and securely stores it in a database such as MySQL or MongoDB.

[1513] The stored data is periodically retrieved by the server and used to train machine learning models. Data preprocessing includes imputation of missing values ​​and normalization of numerical data. Subsequently, the models are trained using algorithms such as support vector machines and neural networks.

[1514] The device uses a pre-trained model to generate a personalized learning plan for each user. For example, for a user whose goal is to "pass the AWS Certified Solutions Architect exam," the system automatically generates specific weekly study content, recommended reference materials, and progress tracking methods. This plan is customized according to the user's skill set and goals.

[1515] Furthermore, the server displays the generated learning plan in real time on a display device. This display device is expected to be a smart glasses or head-mounted display. This allows the user to check work procedures and learning progress in real time. The display device also has a function to notify users of reminders regarding work procedures and learning progress.

[1516] To illustrate the process using a concrete example, consider a scenario where a user wears smart glasses and performs machine maintenance work in a factory. The user inputs their skill set (e.g., basic knowledge of Python and networking) into the system and sets a goal (e.g., acquiring a specific machine maintenance skill). The system receives this information, stores it in a database, and generates an appropriate learning plan using a trained model. The smart glasses display the work procedures and learning progress in real time within the user's field of view.

[1517] Examples of prompt statements to input into a generative AI model are as follows:

[1518] User skill set: X, Y, Z

[1519] Objective: To acquire basic maintenance skills.

[1520] Desired time: 1 month

[1521] Based on this prompt, the system provides a learning plan and real-time display to help engineers efficiently improve their skills.

[1522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1523] Step 1:

[1524] The user logs into the device and enters their background, skill set, learning history, and goals. The entered data is received by the device and sent to the server.

[1525] Input: User background, skill set, learning history, goals

[1526] Output: Received data

[1527] Specific operation: The user enters the required information into the input form on the terminal and clicks the submit button. The terminal receives the input data and sends it to the server.

[1528] Step 2:

[1529] The server validates the received data and saves it to a database such as MySQL or MongoDB. Validation includes checking for blank fields and verifying data format.

[1530] Input: Received data

[1531] Output: Saving validated data

[1532] Specific operation: The server checks for blank fields and formatting of the received data, and then saves it to the database after formatting it appropriately.

[1533] Step 3:

[1534] The server periodically retrieves and preprocesses the stored data. Data preprocessing includes imputing missing values ​​and normalizing numerical data.

[1535] Input: Saved data

[1536] Output: Preprocessed data

[1537] Specific operation: The server reads the stored data and automatically performs preprocessing such as imputing missing values ​​and normalizing numerical data.

[1538] Step 4:

[1539] The server uses the preprocessed data to train machine learning models using algorithms such as support vector machines and neural networks.

[1540] Input: Preprocessed data

[1541] Output: Trained model

[1542] Specific operation: The server inputs pre-processed data into the algorithm and trains the model for a specified number of epochs.

[1543] Step 5:

[1544] The server uses a pre-trained model to generate a personalized learning plan for the user. The generated plan includes specific weekly learning content, recommended reference materials, and progress tracking methods.

[1545] Input: Trained model and user data

[1546] Output: User-specific learning plan

[1547] Specific operation: The server inputs the user's skill set and goals into a pre-trained model and automatically generates an optimal learning plan.

[1548] Step 6:

[1549] The server sends the generated learning plan to a display device for real-time display. Smart glasses or head-mounted displays are used as the display device.

[1550] Input: User-specific learning plan

[1551] Output: Display of the learning plan on the display device.

[1552] Specific operation: The server sends the generated learning plan to smart glasses or a head-mounted display, allowing the user to view it in real time.

[1553] Step 7:

[1554] The display device shows work procedures and learning progress in real time and notifies users of reminders as needed.

[1555] Input: User-specific learning plan and progress data

[1556] Output: Notification and display to the user

[1557] Specific operation: Smart glasses or head-mounted displays monitor the user's learning progress and display reminders and work procedures in their field of vision.

[1558] 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.

[1559] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan in response to those emotions. Specific embodiments thereof are described below.

[1560] System-wide configuration

[1561] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, and emotion engine-side emotion recognition and analysis.

[1562] Data collection

[1563] After logging into the system, users enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is entered through input forms on the device.

[1564] The server validates the input data in real time and saves it to the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[1565] Model Learning

[1566] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses that information to make predictions.

[1567] The device displays the progress of the learning process in real time on a dashboard. Here, for example, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked.

[1568] Emotion recognition by an emotion engine

[1569] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[1570] The server receives and stores emotional data from the emotion engine. Emotional data is also stored in a database for analyzing long-term emotional trends.

[1571] Creating and adjusting study plans

[1572] Users enter their goals and current skill sets. For example, they might enter a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server.

[1573] The server generates a personalized learning plan for each user based on a pre-trained model. This plan includes, for example, specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level.

[1574] Furthermore, the server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan can be modified to reduce the learning burden.

[1575] Qualification exam schedule

[1576] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[1577] Displaying the study plan

[1578] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[1579] Specific example

[1580] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a pre-trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance.

[1581] Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to include measures to reduce the intensity of the learning content and promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[1582] In this way, the present invention makes it possible to provide a system that allows engineers to efficiently advance their learning and achieve individual goals while taking into account the emotional state of the user.

[1583] The following describes the processing flow.

[1584] Step 1:

[1585] The user logs into the system.

[1586] The user enters their ID and password and clicks the login button.

[1587] The server verifies the entered authentication information against the database and redirects the user to the dashboard if authentication is successful.

[1588] Step 2:

[1589] Users enter their own background, skill set, and goals.

[1590] Users enter detailed technical information into the input form. Specifically, they fill in information such as past project experience, technologies used, qualifications obtained, and educational history.

[1591] The terminal provides an interface to assist in inputting this information.

[1592] Step 3:

[1593] The server saves the entered data.

[1594] The server validates the entered data in real time, checking whether all required fields are filled in and whether the data format is correct.

[1595] Save the data that passed validation to the database.

[1596] Step 4:

[1597] The server trains a machine learning model based on the stored data.

[1598] The server retrieves engineer profile information from the database and performs preprocessing. Preprocessing includes data normalization and imputation of missing values.

[1599] The data is split into training data and test data, and a model is trained using algorithms such as support vector machines or neural networks.

[1600] Step 5:

[1601] The device monitors the progress of the learning model.

[1602] The device displays the progress of the learning process (e.g., accuracy, changes in the loss function) in real time on a dashboard, allowing the user to monitor the learning progress.

[1603] Step 6:

[1604] The server saves the model once training is complete.

[1605] The server either saves the trained model as a model file or stores it in a database for persistent storage.

[1606] Step 7:

[1607] The user enters their goals and skill set.

[1608] The user accesses the system again and enters their goal (e.g., "Pass the AWS Certified Solutions Architect exam") and current skill set.

[1609] The terminal provides an interface for efficiently inputting and managing this information.

[1610] Step 8:

[1611] The server generates a learning plan based on the entered goals and skill set.

[1612] The server retrieves the information entered by the user and generates an appropriate training plan based on the trained model.

[1613] A study plan includes specific learning content, recommended resources, and a study schedule.

[1614] Step 9:

[1615] The server generates the schedule for the certification exam.

[1616] The server sets appropriate certification exam dates according to the user's goals.

[1617] The proposed exam schedule will include the exam date and time, preparation period, and important deadlines.

[1618] Step 10:

[1619] The device displays the generated study plan and qualification exam schedule.

[1620] The device will visually display study plans and qualification exam schedules in a calendar format, making it easy for users to follow along.

[1621] Step 11:

[1622] The device collects user emotion data.

[1623] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[1624] The emotion engine analyzes this data to recognize the user's current emotional state.

[1625] Step 12:

[1626] The server stores emotional data.

[1627] The system receives emotional data from the emotion engine and stores it in a database.

[1628] Emotional data will also be recorded for long-term sentiment analysis.

[1629] Step 13:

[1630] The server adjusts the learning plan based on sentiment data.

[1631] The learning plan is adjusted in real time according to the user's emotional state. For example, if the user is feeling stressed, the content is changed to reduce the learning burden.

[1632] The tailored plan is designed to allow users to learn at their own pace without feeling overwhelmed.

[1633] Step 14:

[1634] The device will display the adjusted learning plan.

[1635] The adjusted study plan is displayed again in calendar format, and the user is notified.

[1636] Users can review the new plan and continue their learning.

[1637] (Example 2)

[1638] 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".

[1639] Conventional learning plan generation systems have difficulty considering the individual emotional state of users, which can lead to decreased learning efficiency. Furthermore, scheduling certification exams could not reflect the user's learning progress or emotional state in real time. This resulted in users experiencing stress and being unable to progress with their studies according to plan.

[1640] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model, means for displaying the generated learning plan to the user, means for collecting and analyzing user sentiment data, and means for adjusting the learning plan based on the sentiment data. This makes it possible to efficiently provide a learning plan while taking into account the individual emotional state of the user, making it easier for engineers to achieve their goals.

[1641] "Input data" refers to information that users provide to the system, including data such as work history, skill set, and goals.

[1642] "Means of acceptance" refers to the interface or process that a system uses to obtain input data from a user.

[1643] "Means of storage" refers to mechanisms or processes for storing input data temporarily or permanently in a memory device.

[1644] A "machine learning model" is an algorithm or program that learns from data and performs tasks such as prediction and classification.

[1645] A "trained model" is a machine learning model that has been optimized based on training data, and it is a model that makes predictions and recommendations using user input data.

[1646] A "user-specific learning plan" is a learning plan and schedule that is automatically customized based on the user's individual goals and skill set.

[1647] "Means of display" refers to interfaces or devices that visually show the generated learning plan to the user.

[1648] "Emotional data" refers to data that represents a user's emotional state, obtained from their facial expressions, voice, and actions.

[1649] "Means of collection and analysis" refers to systems and processes for acquiring emotional data, analyzing it, and determining the user's emotional state.

[1650] "Means of adjustment" refer to mechanisms or processes for dynamically changing the learning plan based on the user's emotional data.

[1651] "Means of preprocessing" refers to mechanisms or processes that perform operations such as normalization, imputation of missing values, and conversion of data formats in order to improve the quality of the data.

[1652] "Skills" refer to information that indicates the level of a user's specific knowledge or technical abilities.

[1653] A "qualification exam schedule" is a schedule that helps users plan the timing of their studies and exams in preparation for the qualification exam they are aiming for.

[1654] This invention relates to a system that recognizes a user's emotions and provides a customized learning plan tailored to those emotions. The system consists of means for user data input, data storage and model training by a server, provision of a user interface by a terminal, and recognition and analysis of the user's emotions by an emotion engine.

[1655] Data collection

[1656] Users log in to the system using a terminal and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered through input forms on the terminal. The server validates the entered data in real time and stores it in the database in the appropriate format. The validation process includes checking required fields and verifying the data format. The saved data is stored in a database such as MySQL or MongoDB.

[1657] Model Learning

[1658] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing is performed, such as normalizing numerical data and imputing missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and makes predictions based on them. The terminal displays the progress of the learning process in real time on a dashboard. Here, for example, the accuracy of the model, changes in the loss function, and the progress of the learning epoch can be visually checked.

[1659] Emotion recognition by an emotion engine

[1660] The device transmits the user's facial expressions, voice, and behavioral data to the emotion engine. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust). The server receives the emotional data from the emotion engine and stores it. The emotional data is also stored in a database to analyze long-term emotional trends.

[1661] Creating and adjusting study plans

[1662] Users input their goals and current skill sets. For example, they might input a goal like "I want to pass the AWS Certified Solutions Architect exam," along with their current programming skills and project experience. This data is then received and stored by the server. Based on a trained model, the server generates a personalized learning plan for the user. This plan might include specific weekly learning content, recommended reference materials, and progress tracking methods. This plan is automatically customized according to the user's goals and current skill level. The server also adjusts the learning plan in real time based on sentiment data from the sentiment engine. For example, if the user is experiencing stress, the plan can be modified to reduce the learning burden.

[1663] Qualification exam schedule

[1664] The server sets appropriate certification exam dates based on the user's goals. It adjusts the exam preparation period and exam date based on the user's learning progress and emotional state. It is important to propose a realistic schedule that allows sufficient preparation time.

[1665] Displaying the study plan

[1666] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for the user to follow along. Progress tracking and reminder functions are also provided to help users stay on track with their studies.

[1667] Specific example

[1668] For example, suppose a user sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information, stores it in a database, and uses a trained model to generate an appropriate learning plan. This plan includes weekly learning content for each AWS service, along with related exercises and practice tests. The exam date is also set six months in advance. Next, the device uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state during learning. For example, if the user is feeling fatigued, the server adjusts the learning plan to slightly reduce the learning content and include measures to promote relaxation. In this way, it supports the user in learning as efficiently as possible.

[1669] Example of a prompt

[1670] "My goal is to pass the AWS Certified Solutions Architect exam. My current skill set includes Python and basic networking knowledge. Please generate a study plan for each AWS service."

[1671] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1672] Step 1:

[1673] Users log in to their terminal and enter their work history, skill set, and goals. Specifically, they enter information such as past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals into an input form. The input data includes goals such as "obtaining AWS Certified Solutions Architect certification" and skill sets such as "Python" and "fundamental networking knowledge." The input data is sent from the terminal to the server.

[1674] Input: Data from the user regarding their career history, skill set, and goals.

[1675] Output: User data sent to the server

[1676] Step 2:

[1677] The server validates the received input data in real time. The validation process includes checking required fields (e.g., whether goals and skill sets are present) and checking data format (e.g., date format and integer values). Once validation is complete, the data is stored in a database such as MySQL or MongoDB.

[1678] Input: User data sent from the terminal

[1679] Output: Validated user data, saved to the database.

[1680] Step 3:

[1681] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Subsequently, models are trained using algorithms such as support vector machines, random forests, and neural networks.

[1682] Input: Validated user data

[1683] Output: Trained machine learning model

[1684] Step 4:

[1685] The device displays the progress of the learning process in real time on a dashboard. Here, the model's accuracy, changes in the loss function, and the progress of the learning epoch can be visually checked. This information is retrieved from the server and displayed on the device's screen.

[1686] Input: Training process data from the server

[1687] Output: Learning process visualization data on the dashboard

[1688] Step 5:

[1689] The device periodically sends user facial expressions, voice, and behavioral data to the emotion engine. For example, it collects data using the camera and microphone when the user is watching a lesson video. The emotion engine analyzes this data to recognize the user's current emotional state (e.g., joy, anger, sadness, surprise, fear, disgust).

[1690] Input: User's facial expressions, voice, and behavioral data

[1691] Output: Recognized user emotional state data

[1692] Step 6:

[1693] The server receives emotional data from the emotion engine and stores it in a database. Simultaneously, it analyzes the emotional data and uses it to understand long-term emotional trends.

[1694] Input: Emotional state data from the emotion engine

[1695] Output: Emotional state data stored in the database, analysis results

[1696] Step 7:

[1697] The server generates a personalized learning plan based on pre-trained models. This plan may include, for example, what AWS services to learn each week, recommended reference materials, and methods for tracking progress. This plan is automatically customized according to the user's goals and current skill level.

[1698] Input: Stored user data, trained model

[1699] Output: User-specific learning plan

[1700] Step 8:

[1701] The server adjusts the learning plan in real time based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the plan is modified to include measures that reduce the learning content and promote relaxation.

[1702] Input: Emotional state data

[1703] Output: Adjusted learning plan

[1704] Step 9:

[1705] The device visually displays the generated study plan and qualification exam schedule. It uses a calendar format to allow users to visually check their progress and next tasks. A reminder function is also implemented to help users stay on track with their studies.

[1706] Input: Generated and adjusted study plans, qualification exam schedules

[1707] Output: Visually displayed study plan and exam schedule

[1708] (Application Example 2)

[1709] 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".

[1710] While improving the productivity of factory workers, it is also necessary to appropriately adjust work content according to the emotional state of the workers and effectively manage their mental health. This invention aims to improve the working environment and reduce worker stress by providing a system that recognizes and analyzes workers' emotions and adjusts work content and learning plans based on the results.

[1711] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data, means for storing the received data, means for training a machine learning model based on the stored data, means for generating a user-specific learning plan using the trained model and sentiment analysis results, means for displaying the generated learning plan to the user, and means for adjusting work content and providing mental care guidance based on sentiment analysis results. This enables real-time monitoring of workers' emotions and allows for appropriate work adjustments and mental care.

[1712] "Means for receiving input data" refers to functions that collect data such as user history, skill sets, and goals through input forms or similar means.

[1713] "Means for saving received data" refers to a function that validates user-entered data in real time and saves it to the database in an appropriate format.

[1714] "Methods for training machine learning models based on stored data" refers to functions that retrieve stored data, preprocess the data, and then train models using various machine learning algorithms.

[1715] "Means for recognizing and analyzing user emotions" refers to a system that analyzes a user's facial expressions, voice, and behavioral data to recognize their emotional state.

[1716] "Means for generating a user-specific learning plan using a trained model and sentiment analysis results" refers to a function that automatically generates a learning plan optimized for the user based on a trained machine learning model and the results of sentiment analysis.

[1717] "Means for displaying the generated learning plan to the user" refers to an interface that visually displays the customized learning plan, making it easy for the user to follow along.

[1718] "A means of adjusting work content and providing mental care guidance based on emotion analysis results" refers to a function that takes the user's emotional state into consideration, adjusts work content in real time, and provides mental care as needed.

[1719] This invention relates to a system that recognizes the emotions of workers in a factory and customizes work content and learning plans according to those emotions. Specific embodiments are described below.

[1720] System-wide configuration

[1721] The system consists of user data input, server-side data storage and model training, terminal-side user interface provision, emotion recognition and analysis by an emotion engine, and means for adjusting workers' work conditions and providing mental care support.

[1722] Data collection

[1723] After logging into the system, users enter their career history, current skill set, and goals. This includes past project experience, technologies used, certifications obtained, learning history, current challenges, and future goals. This data is entered into the terminal and sent to the server.

[1724] The server validates the input data in real time and stores it in the database in the appropriate format. The data validation process includes checking required fields and verifying the data format. Databases such as MySQL and MongoDB are used.

[1725] Model Learning

[1726] The server periodically retrieves stored data and uses it to train machine learning models. Data preprocessing includes normalization of numerical data and imputation of missing values. Then, the model is trained using algorithms such as support vector machines, random forests, and neural networks. This model learns the characteristics and patterns of successful engineers and uses them to make predictions.

[1727] The device displays the progress of the learning process in real time on a dashboard. Here, you can visually check the model's accuracy, changes in the loss function, and the progress of the learning epochs.

[1728] Emotion recognition by an emotion engine

[1729] The terminal transmits facial expressions, voice, and behavioral data collected from the worker via the camera and microphone to the emotion engine. The emotion engine analyzes this data to recognize the worker's current emotional state (joy, anger, sadness, surprise, fear, disgust). For emotion recognition, for example, OpenCV (face recognition) and Keras (emotion recognition model) are used.

[1730] The server generates personalized learning plans for workers based on emotional data received from the emotion engine. These plans include specific weekly learning content, recommended reference materials, and progress tracking methods.

[1731] Adjusting the study plan

[1732] The server adjusts learning plans and work content in real time based on emotional data obtained from the emotion engine. For example, if a worker is experiencing stress, it can reduce the learning burden and change work content to a more relaxing one. It also provides mental health support.

[1733] Qualification exam schedule

[1734] The server sets appropriate qualification exam dates based on the worker's goals. It adjusts the exam preparation period and exam date, taking into account the worker's learning progress and emotional state.

[1735] Displaying the study plan

[1736] The device visually displays the generated study plan and qualification exam schedule. It is presented in a calendar format, making it easy for workers to follow along. Progress tracking and reminder functions are also provided to help workers stay on track with their studies.

[1737] Specific example:

[1738] For example, suppose a worker sets "AWS Certified Solutions Architect" as their goal and inputs Python and basic networking knowledge as their current skill set. The server receives this information and uses a pre-trained model to generate an appropriate learning plan. This plan includes what to learn about each AWS service each week, along with related exercises and practice tests. The exam dates are also set.

[1739] The device uses an emotion engine to analyze the worker's facial expressions and voice to understand their emotional state during learning. For example, if the worker is feeling fatigued, the server adjusts the learning plan to include some lighter learning content and measures to promote relaxation.

[1740] Examples of prompt statements:

[1741] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[1742] In this way, the present invention makes it possible to provide a system that allows workers to efficiently carry out their work and learning, and to achieve their individual goals, while taking into account the emotional state of the workers.

[1743] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1744] Step 1:

[1745] Users log into the system and enter their career history, skill set, and goals. This includes past project experience, technologies used, certifications, learning history, current challenges, and future goals. This data is collected through input forms on the terminal. The entered data is sent to the server in a standard format (e.g., JSON or XML).

[1746] Step 2:

[1747] The server validates the received data. Specifically, it checks required fields and data format. For example, it verifies whether skill sets and experience are entered correctly. The validated data is stored in a database (MySQL or MongoDB) in an organized format (e.g., normalized numbers or formatted text).

[1748] Step 3:

[1749] The server retrieves the stored data and trains a machine learning model. Data preprocessing includes normalization of numerical data and imputation of missing values. The preprocessed data is then used to train a model using machine learning algorithms such as support vector machines (SVMs), random forests, and neural networks. Model training involves iterative computation with multiple epochs using the training dataset, and is repeated until the model's accuracy improves.

[1750] Step 4:

[1751] The device displays the progress and accuracy of the trained model on a dashboard. The displayed information includes model accuracy, changes in the loss function, and progress through training epochs. The dashboard consists of visually easy-to-understand graphs and charts, allowing users to understand the model's performance in real time.

[1752] Step 5:

[1753] The terminal transmits facial expressions, voice, and behavioral data of workers collected through the camera and microphone to the emotion engine. Specifically, it analyzes emotions using facial image data captured by the camera and voice data collected by the microphone. The emotion engine uses OpenCV and Keras to analyze this data and recognize the worker's emotional state (joy, anger, sadness, surprise, fear, disgust). This analysis uses an emotion recognition model (e.g., a pre-trained CNN model).

[1754] Step 6:

[1755] The server generates a personalized learning plan for each worker based on the emotional data received from the emotion engine. This plan includes specific weekly learning content, recommended reference materials, and progress tracking methods. The emotional data is received in JSON format and integrated with other user data stored in the database.

[1756] Step 7:

[1757] The server adjusts learning plans and work content in real time based on the results of emotion analysis. For example, if a worker is feeling stressed, it will reduce the learning burden and change the content to promote relaxation. This adjustment is optimized based on past emotion data and success stories obtained from the database.

[1758] Step 8:

[1759] The device displays the generated learning plan and work adjustments to the worker. It also provides a calendar-style display, tracking functions, and reminder functions to help workers progress with their learning according to the plan. Mental health advice is also displayed as needed.

[1760] Examples of specific prompt messages:

[1761] "Please suggest ways to alleviate the workload of factory workers who are experiencing stress. Also, please provide evidence that these are effective solutions."

[1762] In this way, each step works in coordination, and a system is realized that provides optimal work adjustments and learning plans while taking into account the emotional state of the workers.

[1763] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1764] 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.

[1765] 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 robot 414.

[1766] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1767] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1768] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1769] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1770] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1771] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1772] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1773] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1774] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1775] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1776] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1777] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1778] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1779] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1780] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1781] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1782] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1783] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1784] The following is further disclosed regarding the embodiments described above.

[1785] (Claim 1)

[1786] [Means for receiving input data,

[1787] [Means for saving the received data,

[1788] [Methods for training machine learning models based on stored data,

[1789] [Means for generating a user-specific training plan using a trained model,

[1790] [Means for displaying the generated learning plan to the user]

[1791] A system that includes this.

[1792] (Claim 2)

[1793] [Further comprising means for preprocessing the received data]

[1794] The system according to claim 1.

[1795] (Claim 3)

[1796] [Furthermore, it provides a means to generate a qualification exam schedule based on the user's skill set and goals.]

[1797] The system according to claim 1.

[1798] "Example 1"

[1799] (Claim 1)

[1800] [Means for receiving input information,

[1801] [Means for storing the received information in a storage device,

[1802] [Methods for training machine learning algorithms based on stored information,

[1803] [Means for generating a user-specific learning plan using a trained algorithm,

[1804] [Means for displaying the generated learning plan in the user interface]

[1805] A system that includes this.

[1806] (Claim 2)

[1807] [The system according to claim 1, which performs preprocessing of received information.

[1808] (Claim 3)

[1809] The system according to claim 1, which generates a schedule for certification exams based on the user's skill set and goals.

[1810] "Application Example 1"

[1811] (Claim 1)

[1812] [Means for receiving input data,

[1813] [Means for saving the received data,

[1814] [Methods for training machine learning models based on stored data,

[1815] [Means for generating a user-specific training plan using a trained model,

[1816] [Means for displaying the generated learning plan on a display device,

[1817] [Means of displaying work procedures and learning progress in real time using a display device,

[1818] [A means of notifying users of work procedures and learning progress reminders]

[1819] A system that includes this.

[1820] (Claim 2)

[1821] [Further comprising means for preprocessing the received data]

[1822] The system according to claim 1.

[1823] (Claim 3)

[1824] [Furthermore, it provides a means to generate a qualification exam schedule based on the user's skill set and goals.]

[1825] The system according to claim 1.

[1826] "Example 2 of combining an emotion engine"

[1827] (Claim 1)

[1828] [Means for receiving input data,

[1829] [Means for saving the received data,

[1830] [Methods for training machine learning models based on stored data,

[1831] [Means for generating a user-specific training plan using a trained model,

[1832] [Means for displaying the generated learning plan to the user,

[1833] [Means for collecting and analyzing user sentiment data,

[1834] [Methods for adjusting learning plans based on emotional data,

[1835] A system that includes this.

[1836] (Claim 2)

[1837] [Further comprising means for preprocessing the received data]

[1838] The system according to claim 1.

[1839] (Claim 3)

[1840] [Furthermore, it provides a means to generate a qualification exam schedule based on the user's skills and goals.]

[1841] The system according to claim 1.

[1842] "Application example 2 when combining with an emotional engine"

[1843] (Claim 1)

[1844] [Means for receiving input data,

[1845] [Means for saving the received data,

[1846] [Methods for training machine learning models based on stored data,

[1847] [Means for recognizing and analyzing user emotions,

[1848] [Means for generating a user-specific learning plan using a trained model and sentiment analysis results,

[1849] [Means for displaying the generated learning plan to the user,

[1850] [Methods for adjusting work content and providing mental health care guidance based on the results of emotional analysis]

[1851] A system that includes this.

[1852] (Claim 2)

[1853] The system according to claim 1, further comprising means for preprocessing received data.

[1854] (Claim 3)

[1855] The system according to claim 1, further comprising means for generating a schedule of qualification exams based on the user's skill set and goals. [Explanation of symbols]

[1856] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving input data, A means of saving the received data, Methods for training machine learning models based on stored data, A means for generating a user-specific training plan using a pre-trained model, A means of displaying the generated learning plan to the user. A system that includes this.

2. The system further includes means for pre-processing the received data. The system according to claim 1.

3. It also includes a means to generate a qualification exam schedule based on the user's skill set and goals. The system according to claim 1.

Images