System

Abstract

A system is provided.SOLUTION: A system, comprising: means for storing historical examination questions in a database; means for generating new questions from the historical examination question database using a generative AI model; means for recording a user's learning-progress; means for analyzing the user's learning-data to identify difficult areas; and means for generating and providing personalized questions to the user based on the difficult areas.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When preparing for qualification exams, many people face the problem of having to purchase expensive study guides and problem sets. Furthermore, these conventional learning resources lack the means to analyze and address individual weaknesses. This makes it difficult to study efficiently. The purpose of this invention is to solve these problems and provide a method that allows more people to easily pass qualification exams. [Means for solving the problem]

[0005] The present invention provides a system that stores past exam questions in a database and generates new questions using a generative AI model. It also includes a means for recording a user's learning progress data and analyzing that data to identify the user's weak areas. It generates personalized questions based on the analysis results and provides them to the user, enabling efficient learning. It also has a function for users to manage their individual learning progress by creating an account and logging in. This allows users to prepare for qualification exams effectively and at low cost.

[0006] "Past exam questions" refers to questions and answers previously asked in a qualification exam.

[0007] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0008] A "generative AI model" is a general term for algorithms that use artificial intelligence technology to generate new data or information based on specific data.

[0009] "New questions" refer to new test questions that are similar or related to existing questions and are created by a generative AI model based on a database of past test questions.

[0010] "Study progress data" refers to data such as progress, scores, and correct answer rate that are recorded as the user progresses with their studies.

[0011] "Analysis" is the process of breaking down and examining specific data to derive meaning.

[0012] The term "weak subject" refers to a subject in which the user scores particularly low or makes many incorrect answers when answering test questions.

[0013] "Personalized questions" refer to questions that are created to address specific weaknesses based on a user's individual learning progress data and analysis results.

[0014] An "account" is a record containing individual authentication information by a user that is used to access a particular service or system.

[0015] "Logging in" refers to the act of a user accessing a system using their account information. [Brief explanation of the drawings]

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

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

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

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

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0037] The present invention provides a learning support system for preparing for qualification exams. The system includes a means for storing past exam questions in a database, generating new questions using a generative AI model, recording and analyzing the user's learning progress data, and providing personalized questions.

[0038] Database of past exam questions

[0039] The server collects past exam questions and stores them in a database, along with metadata such as exam year, difficulty level, and category.

[0040] For example, past exam questions may be stored in the following format:

[0041] Question ID: 1

[0042] Question: Which of the following is the correct algorithm?

[0043] Correct answer: A

[0044] Exam year: 2020

[0045] Difficulty: Moderate

[0046] Category: Algorithms

[0047] User Registration and Login

[0048] The device helps users register and log in. When a user installs the app and creates a new account, information such as name, email address, and password is sent to the server and stored in a database. When users log in, the information they enter is checked against the records in the database.

[0049] Problem Generation

[0050] The server uses a generative AI model to generate new questions based on past exam questions in the database. This model learns the patterns and answer trends of past exam questions and creates new questions that are in line with the actual exam.

[0051] For example, a new question of the form:

[0052] Question: What protocols are used at the network layer?

[0053] Choices: TCP, UDP, IP, HTTP

[0054] Record your learning progress

[0055] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server stores this in a database and records and manages each user's learning progress.

[0056] Weakness analysis and personalization

[0057] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and provides them to the device.

[0058] For example, if a user scores low in the networking section, they will be offered questions like the following:

[0059] Question: Explain network layer protocols.

[0060] Choices: TCP, IP, HTTP, SMTP

[0061] User learning experience

[0062] The user operates the app on their device and works on the personalized questions provided. The answers are sent back to the server and reflected as new data in the user's learning progress. This allows the user to focus on their weak areas and effectively prepare for the qualification exam.

[0063] This system will provide efficient support for studying for qualification exams, allowing users to practice a wide range of questions at low cost and to carry out personalized learning to strengthen their weak areas.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The server collects past exam questions and stores them in a database. Questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[0067] Step 2:

[0068] The terminal prompts the user to enter their registration information. The user enters information such as their name, email address, and password, and sends it to the server. The server receives this information and stores it in a database.

[0069] Step 3:

[0070] A user logs in at a terminal. The entered email address and password are sent to the server and checked against the information in the database. If authentication is successful, the user is granted access to the system.

[0071] Step 4:

[0072] The server uses the generative AI model to generate new questions. Based on a database of past exam questions, the generative AI model analyzes question patterns and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[0073] Step 5:

[0074] The user works on the questions generated on the device. The user selects an answer from the options and sends the answer to the server. The server stores the answer in a database and records it as the user's learning progress data.

[0075] Step 6:

[0076] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect questions, etc., and identifies the user's weak areas. For example, it may be discovered that the user has a low correct answer rate for questions in the "Network" category.

[0077] Step 7:

[0078] The server generates personalized questions based on weak areas, and the generative AI model creates more practice questions related to the "Network" category and sends them to the device.

[0079] Step 8:

[0080] The user works on the personalized questions on their device. The answers are then sent back to the server and recorded as learning progress data. By repeating this process, the user can improve their weak areas while efficiently progressing through their studies.

[0081] Step 9:

[0082] The server periodically evaluates the user's learning progress and sends the results back to the device, allowing the user to create their next learning plan based on this information.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] Conventional learning support systems mainly provide static questions, making it difficult to provide questions tailored to each user's learning progress and weak areas. This makes it difficult to create an environment where users can study efficiently. In addition, a limited collection of questions is insufficient to handle a variety of exam questions.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes means for saving past test data, means for generating new test questions from a past test database using a generation processing model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating and providing the user with personalized test questions based on the weak areas, means for creating and authenticating an account, and means for transmitting answers to the generated test questions and personalized test questions to the server, thereby enabling users to study effectively and prepare for exams more efficiently.

[0088] "Past exam data" refers to data that includes information such as questions and answers from previously administered exams, exam years, difficulty levels, and categories.

[0089] "Means of storage" refers to a system that stores data and allows it to be retrieved as needed. Generally, this refers to a database or storage.

[0090] A "generative processing model" is an algorithm or AI model that generates new test questions based on past test data. Examples include machine learning and generative AI models.

[0091] "Study progress data" refers to information about the progress of a user's study, such as the results of questions answered during the study, the progress of the study, and the study time.

[0092] "Recording means" refers to the systems and mechanisms that capture, store, and keep data in a state where it can be reused later if necessary.

[0093] "Learning data" refers to a series of data generated by a user through learning activities. Specifically, it includes answer results, study time, and percentage of correct answers to questions.

[0094] "Means of analysis" refers to the technology and equipment used to analyze acquired data and extract useful information.

[0095] A "weak area" is an area in which a user has a low score and insufficient understanding in a particular field or topic during their studies.

[0096] "Means of identification" refers to methods or techniques for using data to reveal specific information or conditions.

[0097] "Individualized test questions" refer to test questions that are customized to take into account the individual user's learning progress and areas of weakness.

[0098] "Means of delivery" refers to the mechanism by which questions and data are delivered, displayed, or made accessible to users.

[0099] "Account creation and authentication method" refers to the process by which a user registers with a system and gains access, typically through authentication using information such as a username, password, and email address.

[0100] A "transmission medium" is a technique or method for transmitting data from one point to another, usually over a network.

[0101] The present invention is a study support system for preparing for qualification examinations, and can be implemented as follows.

[0102] Hardware and Software Use

[0103] server

[0104] Storage of past exam data: The server collects past exam data and stores it in a relational database (e.g., MySQL, PostgreSQL). The collected data includes the exam questions themselves as well as metadata such as exam year, difficulty level, and category.

[0105] Generative processing model: The server uses a generative AI model such as OpenAI's GPT-3.5 as a generative processing model, which generates new test questions based on past test data.

[0106] Recording and analyzing learning progress data: The server records the user's learning progress data and stores it in a database. Furthermore, this data is analyzed to identify the user's weak areas.

[0107] Terminal

[0108] User input assistance: The device (e.g., smartphone, tablet, PC) assists the user in registering a new account and logging in through the application, and also sends the results of the user's answers to the server.

[0109] Providing personalized questions: Displaying personalized test questions sent from the server and providing them to the user.

[0110] Examples of concrete examples and prompts

[0111] Collecting and storing past test data

[0112] The server collects past exam data from certification exam providers and public databases and stores it in a database in the following format:

[0113] Question ID: 1

[0114] Question: Which of the following is the correct algorithm?

[0115] Correct Answer: A

[0116] Exam year: 2020

[0117] Difficulty: Moderate

[0118] Category: Algorithms

[0119] Generate new exam questions

[0120] The server sends the following prompt to the generative AI model to generate a new test question:

[0121] Past exam questions:

[0122] 1. Question: Which of the following is the correct algorithm?

[0123] Choices: A, B, C, D

[0124] Correct Answer: A

[0125] Create a new question:

[0126] The generative AI model generates new test questions such as:

[0127] Question: What protocols are used at the network layer?

[0128] Choices: TCP, UDP, IP, HTTP

[0129] Recording and analyzing user answers

[0130] When the user enters the answer on the device, the result is sent to the server and recorded in the following format:

[0131] User ID: 12345

[0132] Question ID: 1

[0133] User Answer: B

[0134] Correct Answer: Incorrect

[0135] The server analyzes this data to identify the user's weak areas, and based on this analysis, it sends prompts back to the generative AI model to generate personalized questions.

[0136] Personalized Question Generation

[0137] For example, if the analysis shows that the user scores low in the networking area, the following prompt sentence will be sent to the generative AI model:

[0138] User weaknesses: Network layer

[0139] Past exam questions:

[0140] 1. Question: What protocols are used at the network layer?

[0141] Choices: TCP, IP, HTTP, SMTP

[0142] Correct Answer: IP

[0143] Generate a new personalized question:

[0144] The generative AI model generates problems like this:

[0145] Question: Explain network layer protocols.

[0146] Choices: TCP, IP, HTTP, SMTP

[0147] Update user learning progress

[0148] When the user answers the newly generated questions, the results are sent back to the server and recorded and analyzed as learning progress data, allowing users to efficiently prepare for qualification exams.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1: Collect and store historical test data

[0151] The server collects past exam data from certification exam providers and public databases, including test questions, exam years, difficulty levels, and categories.

[0152] Input: Qualification exam question data and its metadata.

[0153] Data processing: Organize the collected data by category and difficulty level, and convert it into a format that can be stored in the database.

[0154] Output: Organized historical test data is stored in a database.

[0155] Step 2: User Registration and Login

[0156] The device receives the user's input information (name, email address, password, etc.) and registers a new account.

[0157] Input: The registration information entered by the user.

[0158] Data calculation: The input information is sent to the server and saved in the database. The information entered at login is also verified against the database for authentication.

[0159] Output: Display a sign-up success or login success message to the user.

[0160] Step 3: Generate new exam questions

[0161] The server sends prompts to the generative AI model based on past test data in a database.

[0162] Input: Past test data and prompt for the question to be generated.

[0163] Data calculation: A generative AI model generates new test questions based on prompts.

[0164] Output: The generated new test questions are saved in the database so that they are available for the next test.

[0165] Step 4: Record your learning progress

[0166] The terminal receives the user's answer and sends the result to the server.

[0167] Input: User's answer, user ID, question ID, whether the answer was correct, etc.

[0168] Data calculation: The server records the received answer data in the database.

[0169] Output: The recorded answer data is saved in the database as learning progress data.

[0170] Step 5: Analyze weak areas and generate personalized test questions

[0171] The server analyzes the learning progress data in the database and identifies areas where the user is weak.

[0172] Input: Learning progress data (answer results, correct answer rate, etc.).

[0173] Data calculation: Using data analysis algorithms, we identify areas of weakness for each user.

[0174] Output: Generate prompts based on the identified weaknesses, which are then used by the generative AI model to generate new questions.

[0175] Step 6: Providing personalized questions

[0176] The server sends personalized questions generated by the generative AI model to the device.

[0177] Input: Personalized problem data.

[0178] Data calculation: The problem data is sent from the server to the terminal.

[0179] Output: Users can access personalized questions through their devices and advance their learning.

[0180] Step 7: Update your learning progress

[0181] The terminal transmits the results of the questions answered by the user to the server.

[0182] Input: New answer result (user ID, question ID, user's answer, whether the answer was correct or not).

[0183] Data calculation: The server saves the new answer results in the database and updates the learning progress data.

[0184] Output: Updated learning progress data is saved in the database for future analysis.

[0185] Through the above steps, this system effectively supports users' studies and enables them to prepare for qualification exams more efficiently.

[0186] (Application example 1)

[0187] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0188] Current certification exam preparation systems mainly require users to study individually at home or online, and lack real-time feedback and face-to-face learning support in brick-and-mortar stores. Furthermore, the lack of personalized study questions and immediate instruction from trainers makes effective learning difficult.

[0189] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0190] In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording a user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for the user to work on the personalized study questions using a terminal installed in a physical store, and means for a trainer to provide feedback in real time. This enables face-to-face learning in a physical store and realizes the provision of individual instruction and personalized study questions to users.

[0191] "Past exam questions" refer to questions that were asked in previous qualification exams, which are saved in a database and can be reused.

[0192] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate new problems from data.

[0193] A "database" is a structured collection of information for storing past exam questions and user learning progress data.

[0194] "User's learning progress data" is data that records the results of the problems the user has worked on and the progress of their learning.

[0195] The "weak area" refers to an area or category in which the user has particular difficulty in studying for a qualification exam.

[0196] "Personalized questions" refer to questions that are individually set based on the user's learning data and areas of weakness.

[0197] "Terminals installed in physical stores" refers to electronic devices for learning that are installed in physical stores to prepare for qualification exams.

[0198] A "trainer" is an expert who guides users in preparing for qualification exams and provides real-time feedback.

[0199] This invention is a system that supports users in preparing for qualification exams by utilizing terminals and servers installed in physical stores. This system stores past exam questions in a database and generates new questions using a generative AI model. This system also has the function of recording and analyzing the user's learning progress data to provide personalized questions.

[0200] Hardware and software used

[0201] This system uses the following hardware and software:

[0202] Hardware: Fixed kiosks, tablets, and smartphones installed in brick-and-mortar stores.

[0203] software:

[0204] Server side: Use Flask (a lightweight web application framework written in Python) to perform server-side processing.

[0205] Database: A relational database management system (RDBMS) such as SQLite or MySQL.

[0206] Front-end: Building the user interface using HTML / CSS / JavaScript.

[0207] Data processing and calculation

[0208] The server processes and calculates data in the following procedure.

[0209] 1. Database creation:

[0210] Past exam questions are collected and stored in a database along with metadata such as exam year, difficulty level, and category.

[0211] 2. Problem generation:

[0212] New questions are generated from a database of past exam questions using a generative AI model. The generative AI model learns the patterns of past exam questions and answer trends, and creates new questions that are in line with the actual exam.

[0213] For example, create a new question in the following format:

[0214] Question: "What protocols are used at the network layer?"

[0215] Choices: TCP, UDP, IP, HTTP

[0216] 3. Recording and analyzing your learning progress:

[0217] The server receives the answer results sent from the user's device and stores them in a database. The recorded data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. Based on this, the user's weak areas are analyzed.

[0218] 4. Providing personalized questions:

[0219] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if the user scored low in the network section, the following questions will be provided:

[0220] Question: "Explain network layer protocols."

[0221] Choices: TCP, IP, HTTP, SMTP

[0222] User learning experience

[0223] Users can operate devices installed in physical stores and work on personalized study questions. The devices are tablets or smartphones, and the user's answers are instantly sent to a server. Furthermore, trainers can provide real-time feedback, enabling effective study support.

[0224] For example, if a user requests that a problem be generated on demand, the following prompt sentence is input to the generative AI model:

[0225] "Generate a question asking, 'What protocol is used at the network layer?' The options are TCP, UDP, IP, and HTTP."

[0226] In this way, a system can be constructed that can provide individualized instruction and personalized problems to users.

[0227] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0228] Step 1: Collecting and creating a database of past exam questions

[0229] The server collects past exam questions and stores them in a database along with metadata such as exam year, difficulty level, category, etc. Specifically, the data for each question is formatted as shown below and registered in the database.

[0230] Input: Past exam questions (e.g., question text, answers, exam year)

[0231] Output: Structured data stored in a database

[0232] Step 2: User Registration and Login

[0233] A user creates an account using a device and sends information such as name, email address, and password to the server, which stores this information in a database and collates it with the information entered when logging in.

[0234] Input: User information (e.g. name, email address, password)

[0235] Output: User authentication status (registration complete, login success / failure)

[0236] Step 3: Generate a new problem

[0237] The server uses a generative AI model to generate new questions from a database of past exam questions. The model learns the patterns of past questions and creates new questions that are relevant to the actual exam.

[0238] Input: Generative AI model, past exam question data

[0239] Output: A newly generated question (e.g., "What protocol is used at the network layer?")

[0240] Step 4: Record your learning progress

[0241] When a user answers a study question on their device, the answer is sent to the server, which stores the answer in a database. The recorded data includes the user ID, question ID, the user's answer, and whether the answer was correct.

[0242] Input: User's answer result (e.g., user ID, question ID, user's answer)

[0243] Output: Learning progress data stored in a database

[0244] Step 5: Analyze your weaknesses

[0245] The server analyzes the user's learning progress data and identifies areas in which the user is weak. Based on the analysis results, if the user has a low score in a particular area, the server recognizes that area as a "weak area."

[0246] Input: User's learning progress data

[0247] Output: Identification of weak areas

[0248] Step 6: Deliver personalized questions

[0249] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the terminal. For example, if the user scores low in the networking area, the server creates related questions.

[0250] Input: Identification of weak areas, AI model for generating new problems

[0251] Output: A personalized question sent to the device (e.g., "What protocol is used at the network layer?")

[0252] Step 7: Provide real-time feedback

[0253] The trainer monitors the user's answers and provides real-time feedback. Each time the user submits an answer, the trainer provides advice based on the results.

[0254] Input: User's answer result

[0255] Output: Feedback from the trainer

[0256] The above processing steps enable face-to-face learning in a brick-and-mortar store, providing users with individualized instruction and personalized learning problems. For example, a new problem can be generated by inputting the prompt sentence, "Generate the question: What protocol is used in the network layer? The options are TCP, UDP, IP, and HTTP." into the generative AI model.

[0257] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0258] This invention combines an emotion engine with a learning support system for preparing for qualification exams. The system stores past exam questions in a database, generates new questions using a generative AI model, and includes a means for recording and analyzing the user's learning progress data and providing personalized questions. Furthermore, the system has the added function of recognizing the user's emotions and providing personalized feedback based on the emotion data.

[0259] Database of past exam questions

[0260] The server collects past exam questions and stores them in a database. These questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[0261] User Registration and Login

[0262] The terminal prompts the user to enter registration information. The user enters information such as name, email address, and password, and sends this to the server. The server stores the received information in a database. When logging in, the entered email address and password are sent to the server and compared with the information in the database. Users who are successfully authenticated can access the system.

[0263] Problem Generation

[0264] The server uses the generative AI model to generate new questions based on past questions in the database. The generative AI model analyzes the patterns of past questions and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[0265] Record your learning progress

[0266] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server saves the answer results in a database and records them as the user's learning progress data.

[0267] Weakness analysis and personalization

[0268] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if a user scores low in the "Network" category, questions related to that category will be provided.

[0269] Combining Emotion Engines

[0270] Furthermore, the server is equipped with an emotion engine. The device detects the user's facial expressions and voice during learning and sends this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[0271] Emotion-based personalization and feedback

[0272] The server uses emotional data to personalize learning content and feedback. For example, if a user is feeling stressed, it sends a message encouraging them to pause and relax. If a user shows high levels of concentration, it provides them with more challenging problems.

[0273] User learning experience

[0274] As users navigate the app on their devices and tackle the personalized questions provided, the emotion engine continuously collects emotional data. Based on this, the learning experience is adapted in real time. For example, if a user is feeling down, an encouraging message will be displayed. This feedback helps users maintain their motivation to study and efficiently prepare for exams.

[0275] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide more effective preparation for qualification exams.

[0276] The processing flow will be explained below.

[0277] Step 1:

[0278] The server collects past exam questions and stores them in a database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[0279] Step 2:

[0280] The terminal accepts the user's registration information. The user enters information such as their name, email address, and password into the terminal and sends it to the server. The server stores the received information in a database.

[0281] Step 3:

[0282] The user logs in at the terminal. The email address and password entered by the user are sent to the server and checked against the information in the database. If authentication is successful, the user is allowed to access the system.

[0283] Step 4:

[0284] The server uses the generative AI model to generate new questions based on past questions in the database. For example, a new question such as "What protocol is used in the network layer?" is generated from a past question. The newly generated question is then provided to the user.

[0285] Step 5:

[0286] The user works on the questions generated on the device. The user selects an answer and sends the answer to the server. The server stores the received answer in a database and records it as the user's learning progress data.

[0287] Step 6:

[0288] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect answers, etc. to identify the user's weak areas. For example, if the user has a low correct answer rate on questions in the "Network" category, that category will be identified as the user's weak area.

[0289] Step 7:

[0290] The server generates personalized questions based on the user's weak areas. The generative AI model creates new questions related to the user's weak areas and sends them to the device. For example, questions in the "Network" category are provided with a focus on the user.

[0291] Step 8:

[0292] The device detects the user's facial expressions and voice while studying and sends this emotional data to the server, where the emotion engine analyzes the user's emotions (stress, joy, concentration, etc.).

[0293] Step 9:

[0294] The server then uses the emotional data to personalize learning feedback. For example, if the user is feeling stressed, it will display a message on the device encouraging them to relax. If the user is highly focused, it will provide more challenging problems.

[0295] Step 10:

[0296] As users work through personalized exercises, learning progress and emotional data is continuously collected and analyzed, allowing the user's learning experience to adapt in real time, enabling more efficient learning.

[0297] Step 11:

[0298] The server periodically evaluates the user's learning progress and emotional data, and sends the results back to the device, allowing the user to plan their next learning plan based on this information.

[0299] Example 2

[0300] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0301] While conventional learning support systems analyze users' learning progress and areas of weakness, they do not provide individualized support that takes into account the user's emotional state, which creates challenges in maintaining learning efficiency and motivation. Furthermore, personalization based solely on the user's answers and learning data has its limitations, making it difficult to provide effective preparation for qualification exams.

[0302] The identification process by the identification 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 saving past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means having an emotion engine for collecting and analyzing the user's facial expression and voice data, and means for providing personalized feedback based on the emotion data. This makes it possible to improve learning efficiency and maintain motivation by understanding the user's emotional state in real time and individually adjusting the learning content and feedback based on that data.

[0303] "Past exam questions" means all questions previously asked in a particular qualification examination.

[0304] A "database" is a system for storing, managing, and retrieving data efficiently and systematically.

[0305] A "generative AI model" is an algorithmic model that uses artificial intelligence to generate new data, and often refers specifically to a natural language processing model.

[0306] "Study progress data" refers to data that records the results of answers given by a user while studying and the progress of that user.

[0307] "User learning data" refers to all data related to learning, such as the user's answer results, study time, correct answer rate, and answer tendencies.

[0308] "Weak areas" are specific areas or topics where a user has poor performance or understanding in their studies.

[0309] "Personalized questions" are questions that are customized to a user's specific learning needs or areas of weakness.

[0310] "Facial expression and voice data" refers to data such as facial expressions, voice tone, speed, and rhythm that represent the user's emotional state.

[0311] An "emotion engine" is software or algorithms that analyze facial and voice data to identify a user's emotional state.

[0312] "Personalized feedback" refers to feedback and advice that is individually tailored based on the user's learning status and emotions.

[0313] This invention is a learning support system for preparing for qualification exams, which provides users with a personalized learning experience by combining an emotion engine. This system consists of a server, a terminal, and a user.

[0314] Database of past exam questions

[0315] The server collects past exam questions from the internet and cooperating institutions and stores them in a PostgreSQL database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" is assigned metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network."

[0316] User Registration and Login

[0317] The terminal provides an interface for the user to enter information such as name, email address, and password. The user enters this information and sends it to the server. The server stores the received information in a PostgreSQL database, and the password is hashed using bcrypt. When logging in, the email address and password entered by the user are sent to the server and compared with the information stored in the database. If the comparison is successful, the user is allowed to access the system.

[0318] Problem Generation

[0319] The server uses the generative AI model to generate new questions based on past questions in the database. For example, the following prompt is input to the generative AI model: "Generate new questions based on questions in the network category from the past five years." Based on this prompt, the generative AI model (e.g., GPT-4) generates a new question: "What protocol is used in the network layer?"

[0320] Record your learning progress

[0321] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, and whether the answer was correct. The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data.

[0322] Weakness analysis and personalization

[0323] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. For example, if a user scores low in the "Network" category, questions related to that category will be provided. Using the generative AI model, a prompt sentence such as the following is input: "Please generate new questions based on past exam questions in the Network field."

[0324] Combining Emotion Engines

[0325] The server is equipped with an emotion engine, and the device uses a camera and microphone to collect the user's facial expressions and voice data in real time. This data is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The analysis results are reflected in learning content and feedback in real time.

[0326] Emotion-based personalization and feedback

[0327] The server uses emotional data to personalize learning content and feedback. For example, it inputs the following prompt into the generative AI model: "If the user is concentrating, provide problems with a moderate level of difficulty." If the user is feeling stressed, it sends a message encouraging them to pause their learning and relax.

[0328] User learning experience

[0329] As users interact with the app on their devices and complete the personalized tasks provided, the emotion engine continuously collects emotional data, allowing the server to adapt the learning experience in real time. For example, if a user is feeling down, it can display encouraging messages to keep the user motivated to learn.

[0330] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide efficient preparation for qualification exams.

[0331] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0332] Step 1: Collect past exam questions and save them in a database

[0333] Specific behavior:

[0334] The server collects past exam questions from the Internet and cooperating institutions. The input data are exam questions provided in various formats. The server converts these questions into a standardized format and stores them in a PostgreSQL database. The output data are the standardized exam questions and their metadata. For example, the metadata "Year: 2021," "Difficulty: Low," and "Category: Network" are added to the question "What is the role of the network layer?"

[0335] Step 2: User Registration and Login

[0336] Specific behavior:

[0337] The terminal provides an interface that lets the user enter information such as name, email address, and password. The input data is the user's registration information. This is sent to the server and stored in a PostgreSQL database. The password is hashed using bcrypt. The output data is the user information stored in the database. When logging in, the user enters their email address and password and sends it to the server. The server checks it against the information stored in the database, and if it matches, authentication is successful. The output is a success or failure status.

[0338] Step 3: Generate a new problem

[0339] Specific behavior:

[0340] The server creates and sends a prompt to the generative AI model. The input data is the metadata and text information of past questions. As an example, the prompt is "Please generate a new question based on questions in the network category from the past five years." The generative AI model (e.g., GPT-4) generates a new question based on this. The output data is the generated new question, such as "What protocol is used in the network layer?" The server stores this in a database and sends it to the terminal to provide to the user.

[0341] Step 4: Record your learning progress

[0342] Specific behavior:

[0343] The user answers a new question, and the device sends the results to the server. The input data is the user's answer (user ID, question ID, user answer, whether the answer was correct or not). The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data. The output data is an updated record of learning progress.

[0344] Step 5: Analyze weak areas and personalize

[0345] Specific behavior:

[0346] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. The input data is the user's learning data. Based on this, the server identifies areas where the user scored low, for example, in the "Network" category. Using a generative AI model, the server uses a prompt such as "Please generate new questions based on past exam questions in the Network category." The output data are the generated new personalized questions, which are sent to the terminal and provided to the user.

[0347] Step 6: Collect and analyze emotion data

[0348] Specific behavior:

[0349] The device uses a camera and microphone to collect the user's facial and voice data in real time. The input data is the user's facial and voice data. This is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The output data is the user's emotional state.

[0350] Step 7: Provide emotion-based feedback

[0351] Specific behavior:

[0352] The server personalizes learning content and feedback based on the emotional data. The input data is the analyzed emotional data. A prompt such as "If the user is concentrating, please provide questions with a moderate level of difficulty" is input to the generative AI model. The output data is personalized learning content and feedback, which is sent to the device and provided to the user.

[0353] Step 8: Adapting the learning experience on an ongoing basis

[0354] Specific behavior:

[0355] The device continuously collects emotional data while the user is learning, and the server analyzes it. The input data is real-time emotional data. Based on this, the server adaptively adjusts the learning experience and feedback and provides it to the user via the device. The output data is the learning experience and feedback updated in real time. For example, if the user is feeling down, an encouraging message is displayed, and if the user is concentrating well, challenging problems are provided.

[0356] (Application example 2)

[0357] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0358] While conventional learning support systems focus on analyzing users' progress and weak areas, they do not provide feedback based on the user's emotional state, making it difficult to maintain learning efficiency and motivation.In addition, appropriate feedback based on real-time emotional recognition is important for factory robot operators to efficiently improve their skills, but no system with such functionality existed.

[0359] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for recognizing and analyzing the user's emotional data, and means for providing feedback based on the emotional data. This not only analyzes the user's progress and weak areas, but also enables the provision of feedback tailored to the user's emotional state, which is expected to improve learning efficiency and maintain motivation. It also enables efficient training of factory robot operators.

[0360] The "means for storing past test questions in a database" refers to a device or function that collects test questions that have been given in the past and stores those questions in a database.

[0361] "Means for generating new questions from a database of past exam questions using a generative AI model" refers to a device or function that uses an artificial intelligence model to analyze a database of past exam questions and create new exam questions.

[0362] The "means for recording user's learning progress data" refers to a device or function for recording the results of the user's answers and the progress of the user.

[0363] The "means for analyzing the user's learning data and identifying weak areas" refers to a device or function that analyzes the user's learning data and identifies the areas or regions in which the user is weak.

[0364] The "means for generating personalized questions based on weak areas and providing them to the user" is a device or function that generates questions appropriate to the identified weak areas and provides them to the user individually.

[0365] The "means for recognizing and analyzing user emotional data" refers to a device or function that collects and analyzes emotional data such as the user's facial expressions and voice.

[0366] The "means for providing feedback based on emotion data" is a device or function that provides appropriate feedback or advice to the user based on the analyzed emotion data.

[0367] The present invention provides a training system for factory robot operators that uses past training data and a generative AI model to generate new training questions and provides personalized feedback based on the user's learning progress and emotional data.

[0368] Specifically, the following means are used:

[0369] 1. Database of past training data:

[0370] The server collects past training data and stores it in a database. This data is assigned metadata such as the training year, difficulty level, and category. For example, to a training task such as "What is the procedure for replacing parts on an industrial robot?", metadata such as "Year: 2021," "Difficulty: Medium," and "Category: Machine Operation" are added.

[0371] 2. Training problem generation:

[0372] The server uses a generative AI model to generate new questions based on past training data in the database. The generative AI model analyzes patterns in past training data and creates new questions. For example, a question might be generated: "What sensor technology is used in industrial robots?"

[0373] 3. Record your learning progress:

[0374] Users train through smart glasses or a head-mounted display. Their answers and progress data are sent from the device to a server, which records them. The recorded data includes the user ID, question ID, the user's answer, and whether or not the answer was correct.

[0375] 4. Weakness analysis and personalization:

[0376] The server analyzes the user's learning data and identifies their weak areas. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the smart glasses or head-mounted display. For example, if a user scores low in the "machine operation" category, questions related to that category will be provided.

[0377] 5. Emotion engine combination:

[0378] Furthermore, the server is equipped with an emotion engine. The smart glasses or head-mounted display detects the user's facial expressions and voice and transmits this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[0379] 6. Emotion-based personalization and feedback:

[0380] The server personalizes learning content and feedback based on emotional data. For example, if a user is feeling stressed, it will send a message encouraging them to pause and relax. If a user shows high levels of concentration, it will provide them with more challenging problems.

[0381] Specific examples

[0382] For example, if a user named "Tanaka" uses this system to learn a new machine operation technique, the system records his learning progress, analyzes his weak areas, and provides appropriate feedback in real time based on the analysis results and his emotional data.

[0383] Specific prompt examples

[0384] "Analyze the user's emotional data to determine the level of stress. Then provide feedback messages according to the results. For example, if the user is feeling stressed, generate a message saying, 'You are feeling stressed. Take a short break.' If the user is showing high concentration, generate a message saying, 'You are highly focused. Great! Keep it up!'"

[0385] In this way, the training system according to the present invention can improve the user's learning efficiency and provide appropriate feedback according to the user's emotional state.

[0386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0387] Step 1:

[0388] The server stores past training data in a database. Specifically, it collects and assigns metadata such as the year, difficulty level, and category to each training task. The input is past training data, and the output is a database containing training data with the metadata.

[0389] Step 2:

[0390] A user creates an account and logs in using smart glasses or a head-mounted display. The user enters their name, email address, and password, and this information is sent from the device to the server. The input is the user's registration information, and the output is the user information stored in the database.

[0391] Step 3:

[0392] The server uses a generative AI model to generate new problems based on the past training database. It analyzes past data patterns and creates new problems. The input is the past training data in the database, and the output is the generated new training problem.

[0393] Step 4:

[0394] The user works on the problems provided through smart glasses or a head-mounted display. The user's answers and progress are sent from the device to the server. The input is the user's answer data, and the output is progress data stored in a database.

[0395] Step 5:

[0396] The server analyzes the user's learning data and identifies areas of weakness. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. The input is the user's learning progress data, and the output is personalized questions.

[0397] Step 6:

[0398] The server is equipped with an emotion engine that analyzes the user's facial expressions and voice data sent from the device. The input is the user's emotional data, and the output is the analyzed emotional state.

[0399] Step 7:

[0400] The server personalizes learning content and feedback based on the emotional data. For example, it provides messages encouraging the user to relax if the user is feeling stressed, or provides challenging problems if the user is highly focused. The input is the analyzed emotional data, and the output is personalized feedback messages and problems.

[0401] Step 8:

[0402] It then retrains based on the feedback and new questions received by the user via the device. This process continues in real time. The input is personalized feedback and new questions, and the output is the user's ongoing learning progress data.

[0403] Through these steps, the factory robot training system can provide personalized feedback based on the user's progress and emotional state, improving learning efficiency.

[0404] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0405] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0410] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0411] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0412] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0414] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0415] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0416] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0417] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0418] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0419] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0420] The present invention provides a learning support system for preparing for qualification exams. The system includes a means for storing past exam questions in a database, generating new questions using a generative AI model, recording and analyzing the user's learning progress data, and providing personalized questions.

[0421] Database of past exam questions

[0422] The server collects past exam questions and stores them in a database, along with metadata such as exam year, difficulty level, and category.

[0423] For example, past exam questions may be stored in the following format:

[0424] Question ID: 1

[0425] Question: Which of the following is the correct algorithm?

[0426] Correct answer: A

[0427] Exam year: 2020

[0428] Difficulty: Moderate

[0429] Category: Algorithms

[0430] User Registration and Login

[0431] The device helps users register and log in. When a user installs the app and creates a new account, information such as name, email address, and password is sent to the server and stored in a database. When users log in, the information they enter is checked against the records in the database.

[0432] Problem Generation

[0433] The server uses a generative AI model to generate new questions based on past exam questions in the database. This model learns the patterns and answer trends of past exam questions and creates new questions that are in line with the actual exam.

[0434] For example, a new question of the form:

[0435] Question: What protocols are used at the network layer?

[0436] Choices: TCP, UDP, IP, HTTP

[0437] Record your learning progress

[0438] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server stores this in a database and records and manages each user's learning progress.

[0439] Weakness analysis and personalization

[0440] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and provides them to the device.

[0441] For example, if a user scores low in the networking section, they will be offered questions like the following:

[0442] Question: Explain network layer protocols.

[0443] Choices: TCP, IP, HTTP, SMTP

[0444] User learning experience

[0445] The user operates the app on their device and works on the personalized questions provided. The answers are sent back to the server and reflected as new data in the user's learning progress. This allows the user to focus on their weak areas and effectively prepare for the qualification exam.

[0446] This system will provide efficient support for studying for qualification exams, allowing users to practice a wide range of questions at low cost and to carry out personalized learning to strengthen their weak areas.

[0447] The processing flow will be explained below.

[0448] Step 1:

[0449] The server collects past exam questions and stores them in a database. Questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[0450] Step 2:

[0451] The terminal prompts the user to enter their registration information. The user enters information such as their name, email address, and password, and sends it to the server. The server receives this information and stores it in a database.

[0452] Step 3:

[0453] A user logs in at a terminal. The entered email address and password are sent to the server and checked against the information in the database. If authentication is successful, the user is granted access to the system.

[0454] Step 4:

[0455] The server uses the generative AI model to generate new questions. Based on a database of past exam questions, the generative AI model analyzes question patterns and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[0456] Step 5:

[0457] The user works on the questions generated on the device. The user selects an answer from the options and sends the answer to the server. The server stores the answer in a database and records it as the user's learning progress data.

[0458] Step 6:

[0459] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect questions, etc., and identifies the user's weak areas. For example, it may be discovered that the user has a low correct answer rate for questions in the "Network" category.

[0460] Step 7:

[0461] The server generates personalized questions based on weak areas, and the generative AI model creates more practice questions related to the "Network" category and sends them to the device.

[0462] Step 8:

[0463] The user works on the personalized questions on their device. The answers are then sent back to the server and recorded as learning progress data. By repeating this process, the user can improve their weak areas while efficiently progressing through their studies.

[0464] Step 9:

[0465] The server periodically evaluates the user's learning progress and sends the results back to the device, allowing the user to create their next learning plan based on this information.

[0466] Example 1

[0467] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0468] Conventional learning support systems mainly provide static questions, making it difficult to provide questions tailored to each user's learning progress and weak areas. This makes it difficult to create an environment where users can study efficiently. In addition, a limited collection of questions is insufficient to handle a variety of exam questions.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0470] In this invention, the server includes means for saving past test data, means for generating new test questions from a past test database using a generation processing model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating and providing the user with personalized test questions based on the weak areas, means for creating and authenticating an account, and means for transmitting answers to the generated test questions and personalized test questions to the server, thereby enabling users to study effectively and prepare for exams more efficiently.

[0471] "Past exam data" refers to data that includes information such as questions and answers from previously administered exams, exam years, difficulty levels, and categories.

[0472] "Means of storage" refers to a system that stores data and allows it to be retrieved as needed. Generally, this refers to a database or storage.

[0473] A "generative processing model" is an algorithm or AI model that generates new test questions based on past test data. Examples include machine learning and generative AI models.

[0474] "Study progress data" refers to information about the progress of a user's study, such as the results of questions answered during the study, the progress of the study, and the study time.

[0475] "Recording means" refers to the systems and mechanisms that capture, store, and keep data in a state where it can be reused later if necessary.

[0476] "Learning data" refers to a series of data generated by a user through learning activities. Specifically, it includes answer results, study time, and percentage of correct answers to questions.

[0477] "Means of analysis" refers to the technology and equipment used to analyze acquired data and extract useful information.

[0478] A "weak area" is an area in which a user has a low score and insufficient understanding in a particular field or topic during their studies.

[0479] "Means of identification" refers to methods or techniques for using data to reveal specific information or conditions.

[0480] "Individualized test questions" refer to test questions that are customized to take into account the individual user's learning progress and areas of weakness.

[0481] "Means of delivery" refers to the mechanism by which questions and data are delivered, displayed, or made accessible to users.

[0482] "Account creation and authentication method" refers to the process by which a user registers with a system and gains access, typically through authentication using information such as a username, password, and email address.

[0483] A "transmission medium" is a technique or method for transmitting data from one point to another, usually over a network.

[0484] The present invention is a study support system for preparing for qualification examinations, and can be implemented as follows.

[0485] Hardware and Software Use

[0486] server

[0487] Storage of past exam data: The server collects past exam data and stores it in a relational database (e.g., MySQL, PostgreSQL). The collected data includes the exam questions themselves as well as metadata such as exam year, difficulty level, and category.

[0488] Generative processing model: The server uses a generative AI model such as OpenAI's GPT-3.5 as a generative processing model, which generates new test questions based on past test data.

[0489] Recording and analyzing learning progress data: The server records the user's learning progress data and stores it in a database. Furthermore, this data is analyzed to identify the user's weak areas.

[0490] Terminal

[0491] User input assistance: The device (e.g., smartphone, tablet, PC) assists the user in registering a new account and logging in through the application, and also sends the results of the user's answers to the server.

[0492] Providing personalized questions: Displaying personalized test questions sent from the server and providing them to the user.

[0493] Examples of concrete examples and prompts

[0494] Collecting and storing past test data

[0495] The server collects past exam data from certification exam providers and public databases and stores it in a database in the following format:

[0496] Question ID: 1

[0497] Question: Which of the following is the correct algorithm?

[0498] Correct Answer: A

[0499] Exam year: 2020

[0500] Difficulty: Moderate

[0501] Category: Algorithms

[0502] Generate new exam questions

[0503] The server sends the following prompt to the generative AI model to generate a new test question:

[0504] Past exam questions:

[0505] 1. Question: Which of the following is the correct algorithm?

[0506] Choices: A, B, C, D

[0507] Correct Answer: A

[0508] Create a new question:

[0509] The generative AI model generates new test questions such as:

[0510] Question: What protocols are used at the network layer?

[0511] Choices: TCP, UDP, IP, HTTP

[0512] Recording and analyzing user answers

[0513] When the user enters the answer on the device, the result is sent to the server and recorded in the following format:

[0514] User ID: 12345

[0515] Question ID: 1

[0516] User Answer: B

[0517] Correct Answer: Incorrect

[0518] The server analyzes this data to identify the user's weak areas, and based on this analysis, it sends prompts back to the generative AI model to generate personalized questions.

[0519] Personalized Question Generation

[0520] For example, if the analysis shows that the user scores low in the networking area, the following prompt sentence will be sent to the generative AI model:

[0521] User weaknesses: Network layer

[0522] Past exam questions:

[0523] 1. Question: What protocols are used at the network layer?

[0524] Choices: TCP, IP, HTTP, SMTP

[0525] Correct Answer: IP

[0526] Generate a new personalized question:

[0527] The generative AI model generates problems like this:

[0528] Question: Explain network layer protocols.

[0529] Choices: TCP, IP, HTTP, SMTP

[0530] Update user learning progress

[0531] When the user answers the newly generated questions, the results are sent back to the server and recorded and analyzed as learning progress data, allowing users to efficiently prepare for qualification exams.

[0532] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0533] Step 1: Collect and store historical test data

[0534] The server collects past exam data from certification exam providers and public databases, including test questions, exam years, difficulty levels, and categories.

[0535] Input: Qualification exam question data and its metadata.

[0536] Data processing: Organize the collected data by category and difficulty level, and convert it into a format that can be stored in the database.

[0537] Output: Organized historical test data is stored in a database.

[0538] Step 2: User Registration and Login

[0539] The device receives the user's input information (name, email address, password, etc.) and registers a new account.

[0540] Input: The registration information entered by the user.

[0541] Data calculation: The input information is sent to the server and saved in the database. The information entered at login is also verified against the database for authentication.

[0542] Output: Display a sign-up success or login success message to the user.

[0543] Step 3: Generate new exam questions

[0544] The server sends prompts to the generative AI model based on past test data in a database.

[0545] Input: Past test data and prompt for the question to be generated.

[0546] Data calculation: A generative AI model generates new test questions based on prompts.

[0547] Output: The generated new test questions are saved in the database so that they are available for the next test.

[0548] Step 4: Record your learning progress

[0549] The terminal receives the user's answer and sends the result to the server.

[0550] Input: User's answer, user ID, question ID, whether the answer was correct, etc.

[0551] Data calculation: The server records the received answer data in the database.

[0552] Output: The recorded answer data is saved in the database as learning progress data.

[0553] Step 5: Analyze weak areas and generate personalized test questions

[0554] The server analyzes the learning progress data in the database and identifies areas where the user is weak.

[0555] Input: Learning progress data (answer results, correct answer rate, etc.).

[0556] Data calculation: Using data analysis algorithms, we identify areas of weakness for each user.

[0557] Output: Generate prompts based on the identified weaknesses, which are then used by the generative AI model to generate new questions.

[0558] Step 6: Providing personalized questions

[0559] The server sends personalized questions generated by the generative AI model to the device.

[0560] Input: Personalized problem data.

[0561] Data calculation: The problem data is sent from the server to the terminal.

[0562] Output: Users can access personalized questions through their devices and advance their learning.

[0563] Step 7: Update your learning progress

[0564] The terminal transmits the results of the questions answered by the user to the server.

[0565] Input: New answer result (user ID, question ID, user's answer, whether the answer was correct or not).

[0566] Data calculation: The server saves the new answer results in the database and updates the learning progress data.

[0567] Output: Updated learning progress data is saved in the database for future analysis.

[0568] Through the above steps, this system effectively supports users' studies and enables them to prepare for qualification exams more efficiently.

[0569] (Application example 1)

[0570] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0571] Current certification exam preparation systems mainly require users to study individually at home or online, and lack real-time feedback and face-to-face learning support in brick-and-mortar stores. Furthermore, the lack of personalized study questions and immediate instruction from trainers makes effective learning difficult.

[0572] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0573] In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording a user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for the user to work on the personalized study questions using a terminal installed in a physical store, and means for a trainer to provide feedback in real time. This enables face-to-face learning in a physical store and realizes the provision of individual instruction and personalized study questions to users.

[0574] "Past exam questions" refer to questions that were asked in previous qualification exams, which are saved in a database and can be reused.

[0575] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate new problems from data.

[0576] A "database" is a structured collection of information for storing past exam questions and user learning progress data.

[0577] "User's learning progress data" is data that records the results of the problems the user has worked on and the progress of their learning.

[0578] The "weak area" refers to an area or category in which the user has particular difficulty in studying for a qualification exam.

[0579] "Personalized questions" refer to questions that are individually set based on the user's learning data and areas of weakness.

[0580] "Terminals installed in physical stores" refers to electronic devices for learning that are installed in physical stores to prepare for qualification exams.

[0581] A "trainer" is an expert who guides users in preparing for qualification exams and provides real-time feedback.

[0582] This invention is a system that supports users in preparing for qualification exams by utilizing terminals and servers installed in physical stores. This system stores past exam questions in a database and generates new questions using a generative AI model. This system also has the function of recording and analyzing the user's learning progress data to provide personalized questions.

[0583] Hardware and software used

[0584] This system uses the following hardware and software:

[0585] Hardware: Fixed kiosks, tablets, and smartphones installed in brick-and-mortar stores.

[0586] software:

[0587] Server side: Use Flask (a lightweight web application framework written in Python) to perform server-side processing.

[0588] Database: A relational database management system (RDBMS) such as SQLite or MySQL.

[0589] Front-end: Building the user interface using HTML / CSS / JavaScript.

[0590] Data processing and calculation

[0591] The server processes and calculates data in the following procedure.

[0592] 1. Database creation:

[0593] Past exam questions are collected and stored in a database along with metadata such as exam year, difficulty level, and category.

[0594] 2. Problem generation:

[0595] New questions are generated from a database of past exam questions using a generative AI model. The generative AI model learns the patterns of past exam questions and answer trends, and creates new questions that are in line with the actual exam.

[0596] For example, create a new question in the following format:

[0597] Question: "What protocols are used at the network layer?"

[0598] Choices: TCP, UDP, IP, HTTP

[0599] 3. Recording and analyzing your learning progress:

[0600] The server receives the answer results sent from the user's device and stores them in a database. The recorded data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. Based on this, the user's weak areas are analyzed.

[0601] 4. Providing personalized questions:

[0602] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if the user scored low in the network section, the following questions will be provided:

[0603] Question: "Explain network layer protocols."

[0604] Choices: TCP, IP, HTTP, SMTP

[0605] User learning experience

[0606] Users can operate devices installed in physical stores and work on personalized study questions. The devices are tablets or smartphones, and the user's answers are instantly sent to a server. Furthermore, trainers can provide real-time feedback, enabling effective study support.

[0607] For example, if a user requests that a problem be generated on demand, the following prompt sentence is input to the generative AI model:

[0608] "Generate a question asking, 'What protocol is used at the network layer?' The options are TCP, UDP, IP, and HTTP."

[0609] In this way, a system can be constructed that can provide individualized instruction and personalized problems to users.

[0610] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0611] Step 1: Collecting and creating a database of past exam questions

[0612] The server collects past exam questions and stores them in a database along with metadata such as exam year, difficulty level, category, etc. Specifically, the data for each question is formatted as shown below and registered in the database.

[0613] Input: Past exam questions (e.g., question text, answers, exam year)

[0614] Output: Structured data stored in a database

[0615] Step 2: User Registration and Login

[0616] A user creates an account using a device and sends information such as name, email address, and password to the server, which stores this information in a database and collates it with the information entered when logging in.

[0617] Input: User information (e.g. name, email address, password)

[0618] Output: User authentication status (registration complete, login success / failure)

[0619] Step 3: Generate a new problem

[0620] The server uses a generative AI model to generate new questions from a database of past exam questions. The model learns the patterns of past questions and creates new questions that are relevant to the actual exam.

[0621] Input: Generative AI model, past exam question data

[0622] Output: A newly generated question (e.g., "What protocol is used at the network layer?")

[0623] Step 4: Record your learning progress

[0624] When a user answers a study question on their device, the answer is sent to the server, which stores the answer in a database. The recorded data includes the user ID, question ID, the user's answer, and whether the answer was correct.

[0625] Input: User's answer result (e.g., user ID, question ID, user's answer)

[0626] Output: Learning progress data stored in a database

[0627] Step 5: Analyze your weaknesses

[0628] The server analyzes the user's learning progress data and identifies areas in which the user is weak. Based on the analysis results, if the user has a low score in a particular area, the server recognizes that area as a "weak area."

[0629] Input: User's learning progress data

[0630] Output: Identification of weak areas

[0631] Step 6: Deliver personalized questions

[0632] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the terminal. For example, if the user scores low in the networking area, the server creates related questions.

[0633] Input: Identification of weak areas, AI model for generating new problems

[0634] Output: A personalized question sent to the device (e.g., "What protocol is used at the network layer?")

[0635] Step 7: Provide real-time feedback

[0636] The trainer monitors the user's answers and provides real-time feedback. Each time the user submits an answer, the trainer provides advice based on the results.

[0637] Input: User's answer result

[0638] Output: Feedback from the trainer

[0639] The above processing steps enable face-to-face learning in a brick-and-mortar store, providing users with individualized instruction and personalized learning problems. For example, a new problem can be generated by inputting the prompt sentence, "Generate the question: What protocol is used in the network layer? The options are TCP, UDP, IP, and HTTP." into the generative AI model.

[0640] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0641] This invention combines an emotion engine with a learning support system for preparing for qualification exams. The system stores past exam questions in a database, generates new questions using a generative AI model, and includes a means for recording and analyzing the user's learning progress data and providing personalized questions. Furthermore, the system has the added function of recognizing the user's emotions and providing personalized feedback based on the emotion data.

[0642] Database of past exam questions

[0643] The server collects past exam questions and stores them in a database. These questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[0644] User Registration and Login

[0645] The terminal prompts the user to enter registration information. The user enters information such as name, email address, and password, and sends this to the server. The server stores the received information in a database. When logging in, the entered email address and password are sent to the server and compared with the information in the database. Users who are successfully authenticated can access the system.

[0646] Problem Generation

[0647] The server uses the generative AI model to generate new questions based on past questions in the database. The generative AI model analyzes the patterns of past questions and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[0648] Record your learning progress

[0649] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server saves the answer results in a database and records them as the user's learning progress data.

[0650] Weakness analysis and personalization

[0651] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if a user scores low in the "Network" category, questions related to that category will be provided.

[0652] Combining Emotion Engines

[0653] Furthermore, the server is equipped with an emotion engine. The device detects the user's facial expressions and voice during learning and sends this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[0654] Emotion-based personalization and feedback

[0655] The server uses emotional data to personalize learning content and feedback. For example, if a user is feeling stressed, it sends a message encouraging them to pause and relax. If a user shows high levels of concentration, it provides them with more challenging problems.

[0656] User learning experience

[0657] As users navigate the app on their devices and tackle the personalized questions provided, the emotion engine continuously collects emotional data. Based on this, the learning experience is adapted in real time. For example, if a user is feeling down, an encouraging message will be displayed. This feedback helps users maintain their motivation to study and efficiently prepare for exams.

[0658] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide more effective preparation for qualification exams.

[0659] The processing flow will be explained below.

[0660] Step 1:

[0661] The server collects past exam questions and stores them in a database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[0662] Step 2:

[0663] The terminal accepts the user's registration information. The user enters information such as their name, email address, and password into the terminal and sends it to the server. The server stores the received information in a database.

[0664] Step 3:

[0665] The user logs in at the terminal. The email address and password entered by the user are sent to the server and checked against the information in the database. If authentication is successful, the user is allowed to access the system.

[0666] Step 4:

[0667] The server uses the generative AI model to generate new questions based on past questions in the database. For example, a new question such as "What protocol is used in the network layer?" is generated from a past question. The newly generated question is then provided to the user.

[0668] Step 5:

[0669] The user works on the questions generated on the device. The user selects an answer and sends the answer to the server. The server stores the received answer in a database and records it as the user's learning progress data.

[0670] Step 6:

[0671] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect answers, etc. to identify the user's weak areas. For example, if the user has a low correct answer rate on questions in the "Network" category, that category will be identified as the user's weak area.

[0672] Step 7:

[0673] The server generates personalized questions based on the user's weak areas. The generative AI model creates new questions related to the user's weak areas and sends them to the device. For example, questions in the "Network" category are provided with a focus on the user.

[0674] Step 8:

[0675] The device detects the user's facial expressions and voice while studying and sends this emotional data to the server, where the emotion engine analyzes the user's emotions (stress, joy, concentration, etc.).

[0676] Step 9:

[0677] The server then uses the emotional data to personalize learning feedback. For example, if the user is feeling stressed, it will display a message on the device encouraging them to relax. If the user is highly focused, it will provide more challenging problems.

[0678] Step 10:

[0679] As users work through personalized exercises, learning progress and emotional data is continuously collected and analyzed, allowing the user's learning experience to adapt in real time, enabling more efficient learning.

[0680] Step 11:

[0681] The server periodically evaluates the user's learning progress and emotional data, and sends the results back to the device, allowing the user to plan their next learning plan based on this information.

[0682] Example 2

[0683] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0684] While conventional learning support systems analyze users' learning progress and areas of weakness, they do not provide individualized support that takes into account the user's emotional state, which creates challenges in maintaining learning efficiency and motivation. Furthermore, personalization based solely on the user's answers and learning data has its limitations, making it difficult to provide effective preparation for qualification exams.

[0685] The identification process by the identification 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 saving past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means having an emotion engine for collecting and analyzing the user's facial expression and voice data, and means for providing personalized feedback based on the emotion data. This makes it possible to improve learning efficiency and maintain motivation by understanding the user's emotional state in real time and individually adjusting the learning content and feedback based on that data.

[0686] "Past exam questions" means all questions previously asked in a particular qualification examination.

[0687] A "database" is a system for storing, managing, and retrieving data efficiently and systematically.

[0688] A "generative AI model" is an algorithmic model that uses artificial intelligence to generate new data, and often refers specifically to a natural language processing model.

[0689] "Study progress data" refers to data that records the results of answers given by a user while studying and the progress of that user.

[0690] "User learning data" refers to all data related to learning, such as the user's answer results, study time, correct answer rate, and answer tendencies.

[0691] "Weak areas" are specific areas or topics where a user has poor performance or understanding in their studies.

[0692] "Personalized questions" are questions that are customized to a user's specific learning needs or areas of weakness.

[0693] "Facial expression and voice data" refers to data such as facial expressions, voice tone, speed, and rhythm that represent the user's emotional state.

[0694] An "emotion engine" is software or algorithms that analyze facial and voice data to identify a user's emotional state.

[0695] "Personalized feedback" refers to feedback and advice that is individually tailored based on the user's learning status and emotions.

[0696] This invention is a learning support system for preparing for qualification exams, which provides users with a personalized learning experience by combining an emotion engine. This system consists of a server, a terminal, and a user.

[0697] Database of past exam questions

[0698] The server collects past exam questions from the internet and cooperating institutions and stores them in a PostgreSQL database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" is assigned metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network."

[0699] User Registration and Login

[0700] The terminal provides an interface for the user to enter information such as name, email address, and password. The user enters this information and sends it to the server. The server stores the received information in a PostgreSQL database, and the password is hashed using bcrypt. When logging in, the email address and password entered by the user are sent to the server and compared with the information stored in the database. If the comparison is successful, the user is allowed to access the system.

[0701] Problem Generation

[0702] The server uses the generative AI model to generate new questions based on past questions in the database. For example, the following prompt is input to the generative AI model: "Generate new questions based on questions in the network category from the past five years." Based on this prompt, the generative AI model (e.g., GPT-4) generates a new question: "What protocol is used in the network layer?"

[0703] Record your learning progress

[0704] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, and whether the answer was correct. The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data.

[0705] Weakness analysis and personalization

[0706] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. For example, if a user scores low in the "Network" category, questions related to that category will be provided. Using the generative AI model, a prompt sentence such as the following is input: "Please generate new questions based on past exam questions in the Network field."

[0707] Combining Emotion Engines

[0708] The server is equipped with an emotion engine, and the device uses a camera and microphone to collect the user's facial expressions and voice data in real time. This data is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The analysis results are reflected in learning content and feedback in real time.

[0709] Emotion-based personalization and feedback

[0710] The server uses emotional data to personalize learning content and feedback. For example, it inputs the following prompt into the generative AI model: "If the user is concentrating, provide problems with a moderate level of difficulty." If the user is feeling stressed, it sends a message encouraging them to pause their learning and relax.

[0711] User learning experience

[0712] As users interact with the app on their devices and complete the personalized tasks provided, the emotion engine continuously collects emotional data, allowing the server to adapt the learning experience in real time. For example, if a user is feeling down, it can display encouraging messages to keep the user motivated to learn.

[0713] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide efficient preparation for qualification exams.

[0714] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0715] Step 1: Collect past exam questions and save them in a database

[0716] Specific behavior:

[0717] The server collects past exam questions from the Internet and cooperating institutions. The input data are exam questions provided in various formats. The server converts these questions into a standardized format and stores them in a PostgreSQL database. The output data are the standardized exam questions and their metadata. For example, the metadata "Year: 2021," "Difficulty: Low," and "Category: Network" are added to the question "What is the role of the network layer?"

[0718] Step 2: User Registration and Login

[0719] Specific behavior:

[0720] The terminal provides an interface that lets the user enter information such as name, email address, and password. The input data is the user's registration information. This is sent to the server and stored in a PostgreSQL database. The password is hashed using bcrypt. The output data is the user information stored in the database. When logging in, the user enters their email address and password and sends it to the server. The server checks it against the information stored in the database, and if it matches, authentication is successful. The output is a success or failure status.

[0721] Step 3: Generate a new problem

[0722] Specific behavior:

[0723] The server creates and sends a prompt to the generative AI model. The input data is the metadata and text information of past questions. As an example, the prompt is "Please generate a new question based on questions in the network category from the past five years." The generative AI model (e.g., GPT-4) generates a new question based on this. The output data is the generated new question, such as "What protocol is used in the network layer?" The server stores this in a database and sends it to the terminal to provide to the user.

[0724] Step 4: Record your learning progress

[0725] Specific behavior:

[0726] The user answers a new question, and the device sends the results to the server. The input data is the user's answer (user ID, question ID, user answer, whether the answer was correct or not). The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data. The output data is an updated record of learning progress.

[0727] Step 5: Analyze weak areas and personalize

[0728] Specific behavior:

[0729] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. The input data is the user's learning data. Based on this, the server identifies areas where the user scored low, for example, in the "Network" category. Using a generative AI model, the server uses a prompt such as "Please generate new questions based on past exam questions in the Network category." The output data are the generated new personalized questions, which are sent to the terminal and provided to the user.

[0730] Step 6: Collect and analyze emotion data

[0731] Specific behavior:

[0732] The device uses a camera and microphone to collect the user's facial and voice data in real time. The input data is the user's facial and voice data. This is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The output data is the user's emotional state.

[0733] Step 7: Provide emotion-based feedback

[0734] Specific behavior:

[0735] The server personalizes learning content and feedback based on the emotional data. The input data is the analyzed emotional data. A prompt such as "If the user is concentrating, please provide questions with a moderate level of difficulty" is input to the generative AI model. The output data is personalized learning content and feedback, which is sent to the device and provided to the user.

[0736] Step 8: Adapting the learning experience on an ongoing basis

[0737] Specific behavior:

[0738] The device continuously collects emotional data while the user is learning, and the server analyzes it. The input data is real-time emotional data. Based on this, the server adaptively adjusts the learning experience and feedback and provides it to the user via the device. The output data is the learning experience and feedback updated in real time. For example, if the user is feeling down, an encouraging message is displayed, and if the user is concentrating well, challenging problems are provided.

[0739] (Application example 2)

[0740] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0741] While conventional learning support systems focus on analyzing users' progress and weak areas, they do not provide feedback based on the user's emotional state, making it difficult to maintain learning efficiency and motivation.In addition, appropriate feedback based on real-time emotional recognition is important for factory robot operators to efficiently improve their skills, but no system with such functionality existed.

[0742] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for recognizing and analyzing the user's emotional data, and means for providing feedback based on the emotional data. This not only analyzes the user's progress and weak areas, but also enables the provision of feedback tailored to the user's emotional state, which is expected to improve learning efficiency and maintain motivation. It also enables efficient training of factory robot operators.

[0743] The "means for storing past test questions in a database" refers to a device or function that collects test questions that have been given in the past and stores those questions in a database.

[0744] "Means for generating new questions from a database of past exam questions using a generative AI model" refers to a device or function that uses an artificial intelligence model to analyze a database of past exam questions and create new exam questions.

[0745] The "means for recording user's learning progress data" refers to a device or function for recording the results of the user's answers and the progress of the user.

[0746] The "means for analyzing the user's learning data and identifying weak areas" refers to a device or function that analyzes the user's learning data and identifies the areas or regions in which the user is weak.

[0747] The "means for generating personalized questions based on weak areas and providing them to the user" is a device or function that generates questions appropriate to the identified weak areas and provides them to the user individually.

[0748] The "means for recognizing and analyzing user emotional data" refers to a device or function that collects and analyzes emotional data such as the user's facial expressions and voice.

[0749] The "means for providing feedback based on emotion data" is a device or function that provides appropriate feedback or advice to the user based on the analyzed emotion data.

[0750] The present invention provides a training system for factory robot operators that uses past training data and a generative AI model to generate new training questions and provides personalized feedback based on the user's learning progress and emotional data.

[0751] Specifically, the following means are used:

[0752] 1. Database of past training data:

[0753] The server collects past training data and stores it in a database. This data is assigned metadata such as the training year, difficulty level, and category. For example, to a training task such as "What is the procedure for replacing parts on an industrial robot?", metadata such as "Year: 2021," "Difficulty: Medium," and "Category: Machine Operation" are added.

[0754] 2. Training problem generation:

[0755] The server uses a generative AI model to generate new questions based on past training data in the database. The generative AI model analyzes patterns in past training data and creates new questions. For example, a question might be generated: "What sensor technology is used in industrial robots?"

[0756] 3. Record your learning progress:

[0757] Users train through smart glasses or a head-mounted display. Their answers and progress data are sent from the device to a server, which records them. The recorded data includes the user ID, question ID, the user's answer, and whether or not the answer was correct.

[0758] 4. Weakness analysis and personalization:

[0759] The server analyzes the user's learning data and identifies their weak areas. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the smart glasses or head-mounted display. For example, if a user scores low in the "machine operation" category, questions related to that category will be provided.

[0760] 5. Emotion engine combination:

[0761] Furthermore, the server is equipped with an emotion engine. The smart glasses or head-mounted display detects the user's facial expressions and voice and transmits this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[0762] 6. Emotion-based personalization and feedback:

[0763] The server personalizes learning content and feedback based on emotional data. For example, if a user is feeling stressed, it will send a message encouraging them to pause and relax. If a user shows high levels of concentration, it will provide them with more challenging problems.

[0764] Specific examples

[0765] For example, if a user named "Tanaka" uses this system to learn a new machine operation technique, the system records his learning progress, analyzes his weak areas, and provides appropriate feedback in real time based on the analysis results and his emotional data.

[0766] Specific prompt examples

[0767] "Analyze the user's emotional data to determine the level of stress. Then provide feedback messages according to the results. For example, if the user is feeling stressed, generate a message saying, 'You are feeling stressed. Take a short break.' If the user is showing high concentration, generate a message saying, 'You are highly focused. Great! Keep it up!'"

[0768] In this way, the training system according to the present invention can improve the user's learning efficiency and provide appropriate feedback according to the user's emotional state.

[0769] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0770] Step 1:

[0771] The server stores past training data in a database. Specifically, it collects and assigns metadata such as the year, difficulty level, and category to each training task. The input is past training data, and the output is a database containing training data with the metadata.

[0772] Step 2:

[0773] A user creates an account and logs in using smart glasses or a head-mounted display. The user enters their name, email address, and password, and this information is sent from the device to the server. The input is the user's registration information, and the output is the user information stored in the database.

[0774] Step 3:

[0775] The server uses a generative AI model to generate new problems based on the past training database. It analyzes past data patterns and creates new problems. The input is the past training data in the database, and the output is the generated new training problem.

[0776] Step 4:

[0777] The user works on the problems provided through smart glasses or a head-mounted display. The user's answers and progress are sent from the device to the server. The input is the user's answer data, and the output is progress data stored in a database.

[0778] Step 5:

[0779] The server analyzes the user's learning data and identifies areas of weakness. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. The input is the user's learning progress data, and the output is personalized questions.

[0780] Step 6:

[0781] The server is equipped with an emotion engine that analyzes the user's facial expressions and voice data sent from the device. The input is the user's emotional data, and the output is the analyzed emotional state.

[0782] Step 7:

[0783] The server personalizes learning content and feedback based on the emotional data. For example, it provides messages encouraging the user to relax if the user is feeling stressed, or provides challenging problems if the user is highly focused. The input is the analyzed emotional data, and the output is personalized feedback messages and problems.

[0784] Step 8:

[0785] It then retrains based on the feedback and new questions received by the user via the device. This process continues in real time. The input is personalized feedback and new questions, and the output is the user's ongoing learning progress data.

[0786] Through these steps, the factory robot training system can provide personalized feedback based on the user's progress and emotional state, improving learning efficiency.

[0787] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0788] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0789] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0790] [Third embodiment]

[0791] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0792] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0793] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0794] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0795] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0796] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0797] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0798] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0799] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0800] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0801] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0802] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0803] The present invention provides a learning support system for preparing for qualification exams. The system includes a means for storing past exam questions in a database, generating new questions using a generative AI model, recording and analyzing the user's learning progress data, and providing personalized questions.

[0804] Database of past exam questions

[0805] The server collects past exam questions and stores them in a database, along with metadata such as exam year, difficulty level, and category.

[0806] For example, past exam questions may be stored in the following format:

[0807] Question ID: 1

[0808] Question: Which of the following is the correct algorithm?

[0809] Correct answer: A

[0810] Exam year: 2020

[0811] Difficulty: Moderate

[0812] Category: Algorithms

[0813] User Registration and Login

[0814] The device helps users register and log in. When a user installs the app and creates a new account, information such as name, email address, and password is sent to the server and stored in a database. When users log in, the information they enter is checked against the records in the database.

[0815] Problem Generation

[0816] The server uses a generative AI model to generate new questions based on past exam questions in the database. This model learns the patterns and answer trends of past exam questions and creates new questions that are in line with the actual exam.

[0817] For example, a new question of the form:

[0818] Question: What protocols are used at the network layer?

[0819] Choices: TCP, UDP, IP, HTTP

[0820] Record your learning progress

[0821] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server stores this in a database and records and manages each user's learning progress.

[0822] Weakness analysis and personalization

[0823] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and provides them to the device.

[0824] For example, if a user scores low in the networking section, they will be offered questions like the following:

[0825] Question: Explain network layer protocols.

[0826] Choices: TCP, IP, HTTP, SMTP

[0827] User learning experience

[0828] The user operates the app on their device and works on the personalized questions provided. The answers are then sent back to the server and reflected as new data in their learning progress. This allows users to focus on their weak areas and effectively prepare for qualification exams.

[0829] This system will provide efficient support for studying for qualification exams, allowing users to practice a wide range of questions at low cost and to carry out personalized learning to strengthen their weak areas.

[0830] The processing flow will be explained below.

[0831] Step 1:

[0832] The server collects past exam questions and stores them in a database. Questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[0833] Step 2:

[0834] The terminal prompts the user to enter their registration information. The user enters information such as their name, email address, and password, and sends it to the server. The server receives this information and stores it in a database.

[0835] Step 3:

[0836] A user logs in at a terminal. The entered email address and password are sent to the server and checked against the information in the database. If authentication is successful, the user is granted access to the system.

[0837] Step 4:

[0838] The server uses the generative AI model to generate new questions. Based on a database of past exam questions, the generative AI model analyzes question patterns and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[0839] Step 5:

[0840] The user works on the questions generated on the device. The user selects an answer from the options and sends the answer to the server. The server stores the answer in a database and records it as the user's learning progress data.

[0841] Step 6:

[0842] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect questions, etc., and identifies the user's weak areas. For example, it may be discovered that the user has a low correct answer rate for questions in the "Network" category.

[0843] Step 7:

[0844] The server generates personalized questions based on weak areas, and the generative AI model creates more practice questions related to the "Network" category and sends them to the device.

[0845] Step 8:

[0846] The user works on the personalized questions on their device. The answers are then sent back to the server and recorded as learning progress data. By repeating this process, the user can improve their weak areas while efficiently progressing through their studies.

[0847] Step 9:

[0848] The server periodically evaluates the user's learning progress and sends the results back to the device, allowing the user to create their next learning plan based on this information.

[0849] Example 1

[0850] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0851] Conventional learning support systems mainly provide static questions, making it difficult to provide questions tailored to each user's learning progress and weak areas. This makes it difficult to create an environment where users can study efficiently. In addition, a limited collection of questions is not sufficient to handle a variety of exam questions.

[0852] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0853] In this invention, the server includes means for saving past test data, means for generating new test questions from a past test database using a generation processing model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating and providing the user with personalized test questions based on the weak areas, means for creating and authenticating an account, and means for transmitting answers to the generated test questions and personalized test questions to the server, thereby enabling users to study effectively and prepare for exams more efficiently.

[0854] "Past exam data" refers to data that includes information such as questions and answers from previously administered exams, exam years, difficulty levels, and categories.

[0855] "Means of storage" refers to a system that stores data and allows it to be retrieved as needed. Generally, this refers to a database or storage.

[0856] A "generative processing model" is an algorithm or AI model that generates new test questions based on past test data. Examples include machine learning and generative AI models.

[0857] "Study progress data" refers to information about the progress of a user's study, such as the results of questions answered during the study, the progress of the study, and the study time.

[0858] "Recording means" refers to the systems and mechanisms that capture, store, and keep data in a state where it can be reused later if necessary.

[0859] "Learning data" refers to a series of data generated by a user through learning activities. Specifically, it includes answer results, study time, and percentage of correct answers to questions.

[0860] "Means of analysis" refers to the technology and equipment used to analyze acquired data and extract useful information.

[0861] A "weak area" is an area in which a user has a low score and insufficient understanding in a particular field or topic during their studies.

[0862] "Means of identification" refers to methods or techniques for using data to reveal specific information or conditions.

[0863] "Individualized test questions" refer to test questions that are customized to take into account the individual user's learning progress and areas of weakness.

[0864] "Means of delivery" refers to the mechanism by which questions and data are delivered, displayed, or made accessible to users.

[0865] "Account creation and authentication method" refers to the process by which a user registers with a system and gains access, typically through authentication using information such as a username, password, and email address.

[0866] A "transmission medium" is a technique or method for transmitting data from one point to another, usually over a network.

[0867] The present invention is a study support system for preparing for qualification examinations, and can be implemented as follows.

[0868] Hardware and Software Use

[0869] server

[0870] Storage of past exam data: The server collects past exam data and stores it in a relational database (e.g., MySQL, PostgreSQL). The collected data includes the exam questions themselves as well as metadata such as exam year, difficulty level, and category.

[0871] Generative processing model: The server uses a generative AI model such as OpenAI's GPT-3.5 as a generative processing model, which generates new test questions based on past test data.

[0872] Recording and analyzing learning progress data: The server records the user's learning progress data and stores it in a database. Furthermore, this data is analyzed to identify the user's weak areas.

[0873] Terminal

[0874] User input assistance: The device (e.g., smartphone, tablet, PC) assists the user in registering a new account and logging in through the application, and also sends the results of the user's answers to the server.

[0875] Providing personalized questions: Displaying personalized test questions sent from the server and providing them to the user.

[0876] Examples of specific examples and prompts

[0877] Collecting and storing past test data

[0878] The server collects past exam data from certification exam providers and public databases and stores it in a database in the following format:

[0879] Question ID: 1

[0880] Question: Which of the following is the correct algorithm?

[0881] Correct Answer: A

[0882] Exam year: 2020

[0883] Difficulty: Moderate

[0884] Category: Algorithms

[0885] Generate new exam questions

[0886] The server sends the following prompt to the generative AI model to generate a new test question:

[0887] Past exam questions:

[0888] 1. Question: Which of the following is the correct algorithm?

[0889] Choices: A, B, C, D

[0890] Correct Answer: A

[0891] Create a new question:

[0892] The generative AI model generates new test questions such as:

[0893] Question: What protocols are used at the network layer?

[0894] Choices: TCP, UDP, IP, HTTP

[0895] Recording and analyzing user answers

[0896] When the user enters the answer on the device, the result is sent to the server and recorded in the following format:

[0897] User ID: 12345

[0898] Question ID: 1

[0899] User Answer: B

[0900] Correct Answer: Incorrect

[0901] The server analyzes this data to identify the user's areas of weakness, and based on this analysis, it sends prompts back to the generative AI model to generate personalized questions.

[0902] Personalized Question Generation

[0903] For example, if the analysis shows that the user scores low in the networking area, the following prompt sentence will be sent to the generative AI model:

[0904] User weaknesses: Network layer

[0905] Past exam questions:

[0906] 1. Question: What protocols are used at the network layer?

[0907] Choices: TCP, IP, HTTP, SMTP

[0908] Correct Answer: IP

[0909] Generate a new personalized question:

[0910] The generative AI model generates problems like this:

[0911] Question: Explain network layer protocols.

[0912] Choices: TCP, IP, HTTP, SMTP

[0913] Update user learning progress

[0914] When the user answers the newly generated questions, the results are sent back to the server and recorded and analyzed as learning progress data, allowing users to efficiently prepare for qualification exams.

[0915] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0916] Step 1: Collect and store historical test data

[0917] The server collects past exam data from certification exam providers and public databases, including test questions, exam years, difficulty levels, and categories.

[0918] Input: Qualification exam question data and its metadata.

[0919] Data processing: Organize the collected data by category and difficulty level, and convert it into a format that can be stored in the database.

[0920] Output: Organized historical test data is stored in a database.

[0921] Step 2: User Registration and Login

[0922] The device receives the user's input information (name, email address, password, etc.) and registers a new account.

[0923] Input: The registration information entered by the user.

[0924] Data calculation: The input information is sent to the server and saved in the database. The information entered at login is also verified against the database for authentication.

[0925] Output: Display a sign-up success or login success message to the user.

[0926] Step 3: Generate new exam questions

[0927] The server sends prompt sentences to the generative AI model based on past test data in a database.

[0928] Input: Past test data and prompt for the question to be generated.

[0929] Data calculation: A generative AI model generates new test questions based on prompts.

[0930] Output: The generated new test questions are saved in the database so that they are available for the next test.

[0931] Step 4: Record your learning progress

[0932] The terminal receives the user's answer and sends the result to the server.

[0933] Input: User's answer, user ID, question ID, whether the answer was correct, etc.

[0934] Data calculation: The server records the received answer data in the database.

[0935] Output: The recorded answer data is saved in the database as learning progress data.

[0936] Step 5: Analyze weak areas and generate personalized test questions

[0937] The server analyzes the learning progress data in the database and identifies areas where the user is weak.

[0938] Input: Learning progress data (answer results, correct answer rate, etc.).

[0939] Data calculation: Using data analysis algorithms, we identify areas of weakness for each user.

[0940] Output: Generate prompts based on the identified weaknesses, which are then used by the generative AI model to generate new questions.

[0941] Step 6: Providing personalized questions

[0942] The server sends personalized questions generated by the generative AI model to the device.

[0943] Input: Personalized problem data.

[0944] Data calculation: The problem data is sent from the server to the terminal.

[0945] Output: Users can access personalized questions through their devices and advance their learning.

[0946] Step 7: Update your learning progress

[0947] The terminal transmits the results of the questions answered by the user to the server.

[0948] Input: New answer result (user ID, question ID, user's answer, whether the answer was correct or not).

[0949] Data calculation: The server saves the new answer results in the database and updates the learning progress data.

[0950] Output: Updated learning progress data is saved in the database for future analysis.

[0951] Through the above steps, this system effectively supports users' studies and enables them to prepare for qualification exams more efficiently.

[0952] (Application example 1)

[0953] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0954] Current certification exam preparation systems mainly require users to study individually at home or online, and lack real-time feedback and face-to-face learning support in brick-and-mortar stores. Furthermore, the lack of personalized study questions and immediate instruction from trainers makes effective learning difficult.

[0955] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0956] In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording a user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for the user to work on the personalized study questions using a terminal installed in a physical store, and means for a trainer to provide feedback in real time. This enables face-to-face learning in a physical store and realizes the provision of individual instruction and personalized study questions to users.

[0957] "Past exam questions" refer to questions that were asked in previous qualification exams, which are saved in a database and can be reused.

[0958] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate new problems from data.

[0959] A "database" is a structured collection of information for storing past exam questions and user learning progress data.

[0960] "User's learning progress data" is data that records the results of the problems the user has worked on and the progress of their learning.

[0961] The "weak area" refers to an area or category in which the user has particular difficulty in studying for a qualification exam.

[0962] "Personalized questions" refer to questions that are individually set based on the user's learning data and areas of weakness.

[0963] "Terminals installed in physical stores" refers to electronic devices for learning that are installed in physical stores to prepare for qualification exams.

[0964] A "trainer" is an expert who guides users in preparing for qualification exams and provides real-time feedback.

[0965] This invention is a system that supports users in preparing for qualification exams by utilizing terminals and servers installed in physical stores. This system stores past exam questions in a database and generates new questions using a generative AI model. This system also has the function of recording and analyzing the user's learning progress data to provide personalized questions.

[0966] Hardware and software used

[0967] This system uses the following hardware and software:

[0968] Hardware: Fixed kiosks, tablets, and smartphones installed in brick-and-mortar stores.

[0969] software:

[0970] Server side: Use Flask (a lightweight web application framework written in Python) to perform server-side processing.

[0971] Database: A relational database management system (RDBMS) such as SQLite or MySQL.

[0972] Front-end: Building the user interface using HTML / CSS / JavaScript.

[0973] Data processing and calculation

[0974] The server processes and calculates data in the following procedure.

[0975] 1. Database creation:

[0976] Past exam questions are collected and stored in a database along with metadata such as exam year, difficulty level, and category.

[0977] 2. Problem generation:

[0978] New questions are generated from a database of past exam questions using a generative AI model. The generative AI model learns the patterns of past exam questions and answer trends, and creates new questions that are in line with the actual exam.

[0979] For example, create a new question in the following format:

[0980] Question: "What protocols are used at the network layer?"

[0981] Choices: TCP, UDP, IP, HTTP

[0982] 3. Recording and analyzing your learning progress:

[0983] The server receives the answer results sent from the user's device and stores them in a database. The recorded data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. Based on this, the user's weak areas are analyzed.

[0984] 4. Providing personalized questions:

[0985] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if the user scored low in the network section, the following questions will be provided:

[0986] Question: "Explain network layer protocols."

[0987] Choices: TCP, IP, HTTP, SMTP

[0988] User learning experience

[0989] Users can operate devices installed in physical stores and work on personalized study questions. The devices are tablets or smartphones, and the user's answers are instantly sent to a server. Furthermore, trainers can provide real-time feedback, enabling effective study support.

[0990] For example, if a user requests that a problem be generated on demand, the following prompt sentence is input to the generative AI model:

[0991] "Generate a question asking, 'What protocol is used at the network layer?' The options are TCP, UDP, IP, and HTTP."

[0992] In this way, a system can be constructed that can provide individualized instruction and personalized problems to users.

[0993] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0994] Step 1: Collecting and creating a database of past exam questions

[0995] The server collects past exam questions and stores them in a database along with metadata such as exam year, difficulty level, category, etc. Specifically, the data for each question is formatted as shown below and registered in the database.

[0996] Input: Past exam questions (e.g., question text, answers, exam year)

[0997] Output: Structured data stored in a database

[0998] Step 2: User Registration and Login

[0999] A user creates an account using a device and sends information such as name, email address, and password to the server, which stores this information in a database and collates it with the information entered when logging in.

[1000] Input: User information (e.g. name, email address, password)

[1001] Output: User authentication status (registration complete, login success / failure)

[1002] Step 3: Generate a new problem

[1003] The server uses a generative AI model to generate new questions from a database of past exam questions. The model learns the patterns of past questions and creates new questions that are relevant to the actual exam.

[1004] Input: Generative AI model, past exam question data

[1005] Output: A newly generated question (e.g., "What protocol is used at the network layer?")

[1006] Step 4: Record your learning progress

[1007] When a user answers a study question on their device, the answer is sent to the server, which stores the answer in a database. The recorded data includes the user ID, question ID, the user's answer, and whether the answer was correct.

[1008] Input: User's answer result (e.g., user ID, question ID, user's answer)

[1009] Output: Learning progress data stored in a database

[1010] Step 5: Analyze your weaknesses

[1011] The server analyzes the user's learning progress data and identifies areas in which the user is weak. Based on the analysis results, if the user has a low score in a particular area, the server recognizes that area as a "weak area."

[1012] Input: User's learning progress data

[1013] Output: Identification of weak areas

[1014] Step 6: Deliver personalized questions

[1015] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the terminal. For example, if the user scores low in the networking area, the server creates related questions.

[1016] Input: Identification of weak areas, AI model for generating new problems

[1017] Output: A personalized question sent to the device (e.g., "What protocol is used at the network layer?")

[1018] Step 7: Provide real-time feedback

[1019] The trainer monitors the user's answers and provides real-time feedback. Each time the user submits an answer, the trainer provides advice based on the results.

[1020] Input: User's answer result

[1021] Output: Feedback from the trainer

[1022] The above processing steps enable face-to-face learning in a brick-and-mortar store, providing users with individualized instruction and personalized learning problems. For example, a new problem can be generated by inputting the prompt sentence, "Generate the question: What protocol is used in the network layer? The options are TCP, UDP, IP, and HTTP." into the generative AI model.

[1023] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1024] This invention combines an emotion engine with a learning support system for preparing for qualification exams. The system stores past exam questions in a database, generates new questions using a generative AI model, and includes a means for recording and analyzing the user's learning progress data and providing personalized questions. Furthermore, the system has the added function of recognizing the user's emotions and providing personalized feedback based on the emotion data.

[1025] Database of past exam questions

[1026] The server collects past exam questions and stores them in a database. These questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[1027] User Registration and Login

[1028] The terminal prompts the user to enter registration information. The user enters information such as name, email address, and password, and sends this to the server. The server stores the received information in a database. When logging in, the entered email address and password are sent to the server and compared with the information in the database. Users who are successfully authenticated can access the system.

[1029] Problem Generation

[1030] The server uses the generative AI model to generate new questions based on past questions in the database. The generative AI model analyzes the patterns of past questions and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[1031] Record your learning progress

[1032] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server saves the answer results in a database and records them as the user's learning progress data.

[1033] Weakness analysis and personalization

[1034] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if a user scores low in the "Network" category, questions related to that category will be provided.

[1035] Combining Emotion Engines

[1036] Furthermore, the server is equipped with an emotion engine. The device detects the user's facial expressions and voice during learning and sends this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[1037] Emotion-based personalization and feedback

[1038] The server uses emotional data to personalize learning content and feedback. For example, if a user is feeling stressed, it sends a message encouraging them to pause and relax. If a user shows high levels of concentration, it provides them with more challenging problems.

[1039] User learning experience

[1040] As users navigate the app on their devices and tackle the personalized questions provided, the emotion engine continuously collects emotional data. Based on this, the learning experience is adapted in real time. For example, if a user is feeling down, an encouraging message will be displayed. This feedback helps users maintain their motivation to study and efficiently prepare for exams.

[1041] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide more effective preparation for qualification exams.

[1042] The processing flow will be explained below.

[1043] Step 1:

[1044] The server collects past exam questions and stores them in a database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[1045] Step 2:

[1046] The terminal accepts the user's registration information. The user enters information such as their name, email address, and password into the terminal and sends it to the server. The server stores the received information in a database.

[1047] Step 3:

[1048] The user logs in at the terminal. The email address and password entered by the user are sent to the server and checked against the information in the database. If authentication is successful, the user is allowed to access the system.

[1049] Step 4:

[1050] The server uses the generative AI model to generate new questions based on past questions in the database. For example, a new question such as "What protocol is used in the network layer?" is generated from a past question. The newly generated question is then provided to the user.

[1051] Step 5:

[1052] The user works on the questions generated on the device. The user selects an answer and sends the answer to the server. The server stores the received answer in a database and records it as the user's learning progress data.

[1053] Step 6:

[1054] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect answers, etc. to identify the user's weak areas. For example, if the user has a low correct answer rate on questions in the "Network" category, that category will be identified as the user's weak area.

[1055] Step 7:

[1056] The server generates personalized questions based on the user's weak areas. The generative AI model creates new questions related to the user's weak areas and sends them to the device. For example, questions in the "Network" category are provided with a focus on the user.

[1057] Step 8:

[1058] The device detects the user's facial expressions and voice while studying and sends this emotional data to the server, where the emotion engine analyzes the user's emotions (stress, joy, concentration, etc.).

[1059] Step 9:

[1060] The server then uses the emotional data to personalize learning feedback. For example, if the user is feeling stressed, it will display a message on the device encouraging them to relax. If the user is highly focused, it will provide more challenging problems.

[1061] Step 10:

[1062] As users work through personalized exercises, learning progress and emotional data is continuously collected and analyzed, allowing the user's learning experience to adapt in real time, enabling more efficient learning.

[1063] Step 11:

[1064] The server periodically evaluates the user's learning progress and emotional data, and sends the results back to the device, allowing the user to plan their next learning plan based on this information.

[1065] Example 2

[1066] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1067] While conventional learning support systems analyze users' learning progress and areas of weakness, they do not provide individualized support that takes into account the user's emotional state, which creates challenges in maintaining learning efficiency and motivation. Furthermore, personalization based solely on the user's answers and learning data has its limitations, making it difficult to provide effective preparation for qualification exams.

[1068] The identification process by the identification 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 saving past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means having an emotion engine for collecting and analyzing the user's facial expression and voice data, and means for providing personalized feedback based on the emotion data. This makes it possible to improve learning efficiency and maintain motivation by understanding the user's emotional state in real time and individually adjusting the learning content and feedback based on that data.

[1069] "Past exam questions" means all questions previously asked in a particular qualification examination.

[1070] A "database" is a system for storing, managing, and retrieving data efficiently and systematically.

[1071] A "generative AI model" is an algorithmic model that uses artificial intelligence to generate new data, and often refers specifically to a natural language processing model.

[1072] "Study progress data" refers to data that records the results of answers given by a user while studying and the progress of that user.

[1073] "User learning data" refers to all data related to learning, such as the user's answer results, study time, correct answer rate, and answer tendencies.

[1074] "Weak areas" are specific areas or topics where a user has poor performance or understanding in their studies.

[1075] "Personalized questions" are questions that are customized to a user's specific learning needs or areas of weakness.

[1076] "Facial expression and voice data" refers to data such as facial expressions, voice tone, speed, and rhythm that represent the user's emotional state.

[1077] An "emotion engine" is software or algorithms that analyze facial and voice data to identify a user's emotional state.

[1078] "Personalized feedback" refers to feedback and advice that is individually tailored based on the user's learning status and emotions.

[1079] This invention is a learning support system for preparing for qualification exams, which provides users with a personalized learning experience by combining an emotion engine. This system consists of a server, a terminal, and a user.

[1080] Database of past exam questions

[1081] The server collects past exam questions from the internet and cooperating institutions and stores them in a PostgreSQL database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" is assigned metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network."

[1082] User Registration and Login

[1083] The terminal provides an interface for the user to enter information such as name, email address, and password. The user enters this information and sends it to the server. The server stores the received information in a PostgreSQL database, and the password is hashed using bcrypt. When logging in, the email address and password entered by the user are sent to the server and compared with the information stored in the database. If the comparison is successful, the user is allowed to access the system.

[1084] Problem Generation

[1085] The server uses the generative AI model to generate new questions based on past questions in the database. For example, the following prompt is input to the generative AI model: "Generate new questions based on questions in the network category from the past five years." Based on this prompt, the generative AI model (e.g., GPT-4) generates a new question: "What protocol is used in the network layer?"

[1086] Record your learning progress

[1087] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, and whether the answer was correct. The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data.

[1088] Weakness analysis and personalization

[1089] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. For example, if a user scores low in the "Network" category, questions related to that category will be provided. Using the generative AI model, a prompt sentence such as the following is input: "Please generate new questions based on past exam questions in the Network field."

[1090] Combining Emotion Engines

[1091] The server is equipped with an emotion engine, and the device uses a camera and microphone to collect the user's facial expressions and voice data in real time. This data is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The analysis results are reflected in learning content and feedback in real time.

[1092] Emotion-based personalization and feedback

[1093] The server uses emotional data to personalize learning content and feedback. For example, it inputs the following prompt into the generative AI model: "If the user is concentrating, provide problems with a moderate level of difficulty." If the user is feeling stressed, it sends a message encouraging them to pause their learning and relax.

[1094] User learning experience

[1095] As users interact with the app on their devices and complete the personalized tasks provided, the emotion engine continuously collects emotional data, allowing the server to adapt the learning experience in real time. For example, if a user is feeling down, it can display encouraging messages to keep the user motivated to learn.

[1096] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide efficient preparation for qualification exams.

[1097] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1098] Step 1: Collect past exam questions and save them in a database

[1099] Specific behavior:

[1100] The server collects past exam questions from the Internet and cooperating institutions. The input data are exam questions provided in various formats. The server converts these questions into a standardized format and stores them in a PostgreSQL database. The output data are the standardized exam questions and their metadata. For example, the metadata "Year: 2021," "Difficulty: Low," and "Category: Network" are added to the question "What is the role of the network layer?"

[1101] Step 2: User Registration and Login

[1102] Specific behavior:

[1103] The terminal provides an interface that lets the user enter information such as name, email address, and password. The input data is the user's registration information. This is sent to the server and stored in a PostgreSQL database. The password is hashed using bcrypt. The output data is the user information stored in the database. When logging in, the user enters their email address and password and sends it to the server. The server checks it against the information stored in the database, and if it matches, authentication is successful. The output is a success or failure status.

[1104] Step 3: Generate a new problem

[1105] Specific behavior:

[1106] The server creates and sends a prompt to the generative AI model. The input data is the metadata and text information of past questions. As an example, the prompt is "Please generate a new question based on questions in the network category from the past five years." The generative AI model (e.g., GPT-4) generates a new question based on this. The output data is the generated new question, such as "What protocol is used in the network layer?" The server stores this in a database and sends it to the terminal to provide to the user.

[1107] Step 4: Record your learning progress

[1108] Specific behavior:

[1109] The user answers a new question, and the device sends the results to the server. The input data is the user's answer (user ID, question ID, user answer, whether the answer was correct or not). The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data. The output data is an updated record of learning progress.

[1110] Step 5: Analyze weak areas and personalize

[1111] Specific behavior:

[1112] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. The input data is the user's learning data. Based on this, the server identifies areas where the user scored low, for example, in the "Network" category. Using a generative AI model, the server uses a prompt such as "Please generate new questions based on past exam questions in the Network category." The output data are the generated new personalized questions, which are sent to the terminal and provided to the user.

[1113] Step 6: Collect and analyze emotion data

[1114] Specific behavior:

[1115] The device uses a camera and microphone to collect the user's facial and voice data in real time. The input data is the user's facial and voice data. This is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The output data is the user's emotional state.

[1116] Step 7: Provide emotion-based feedback

[1117] Specific behavior:

[1118] The server personalizes learning content and feedback based on the emotional data. The input data is the analyzed emotional data. A prompt such as "If the user is concentrating, please provide questions with a moderate level of difficulty" is input to the generative AI model. The output data is personalized learning content and feedback, which is sent to the device and provided to the user.

[1119] Step 8: Adapting the learning experience on an ongoing basis

[1120] Specific behavior:

[1121] The device continuously collects emotional data while the user is learning, and the server analyzes it. The input data is real-time emotional data. Based on this, the server adaptively adjusts the learning experience and feedback and provides it to the user via the device. The output data is the learning experience and feedback updated in real time. For example, if the user is feeling down, an encouraging message is displayed, and if the user is concentrating well, challenging problems are provided.

[1122] (Application example 2)

[1123] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1124] While conventional learning support systems focus on analyzing users' progress and weak areas, they do not provide feedback based on the user's emotional state, making it difficult to maintain learning efficiency and motivation.In addition, appropriate feedback based on real-time emotional recognition is important for factory robot operators to efficiently improve their skills, but no system with such functionality existed.

[1125] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for recognizing and analyzing the user's emotional data, and means for providing feedback based on the emotional data. This not only analyzes the user's progress and weak areas, but also enables the provision of feedback tailored to the user's emotional state, which is expected to improve learning efficiency and maintain motivation. It also enables efficient training of factory robot operators.

[1126] The "means for storing past test questions in a database" refers to a device or function that collects test questions that have been given in the past and stores those questions in a database.

[1127] "Means for generating new questions from a database of past exam questions using a generative AI model" refers to a device or function that uses an artificial intelligence model to analyze a database of past exam questions and create new exam questions.

[1128] The "means for recording user's learning progress data" refers to a device or function for recording the results of the user's answers and the progress of the user.

[1129] The "means for analyzing the user's learning data and identifying weak areas" refers to a device or function that analyzes the user's learning data and identifies the areas or regions in which the user is weak.

[1130] The "means for generating personalized questions based on weak areas and providing them to the user" is a device or function that generates questions appropriate to the identified weak areas and provides them to the user individually.

[1131] The "means for recognizing and analyzing user emotional data" refers to a device or function that collects and analyzes emotional data such as the user's facial expressions and voice.

[1132] The "means for providing feedback based on emotion data" is a device or function that provides appropriate feedback or advice to the user based on the analyzed emotion data.

[1133] The present invention provides a training system for factory robot operators that uses past training data and a generative AI model to generate new training questions and provides personalized feedback based on the user's learning progress and emotional data.

[1134] Specifically, the following means are used:

[1135] 1. Database of past training data:

[1136] The server collects past training data and stores it in a database. This data is assigned metadata such as the training year, difficulty level, and category. For example, to a training task such as "What is the procedure for replacing parts on an industrial robot?", metadata such as "Year: 2021," "Difficulty: Medium," and "Category: Machine Operation" are added.

[1137] 2. Training problem generation:

[1138] The server uses a generative AI model to generate new questions based on past training data in the database. The generative AI model analyzes patterns in past training data and creates new questions. For example, a question might be generated: "What sensor technology is used in industrial robots?"

[1139] 3. Record your learning progress:

[1140] Users train through smart glasses or a head-mounted display. Their answers and progress data are sent from the device to a server, which records them. The recorded data includes the user ID, question ID, the user's answer, and whether or not the answer was correct.

[1141] 4. Weakness analysis and personalization:

[1142] The server analyzes the user's learning data and identifies their weak areas. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the smart glasses or head-mounted display. For example, if a user scores low in the "machine operation" category, questions related to that category will be provided.

[1143] 5. Emotion engine combination:

[1144] Furthermore, the server is equipped with an emotion engine. The smart glasses or head-mounted display detects the user's facial expressions and voice and transmits this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[1145] 6. Emotion-based personalization and feedback:

[1146] The server personalizes learning content and feedback based on emotional data. For example, if a user is feeling stressed, it will send a message encouraging them to pause and relax. If a user shows high levels of concentration, it will provide them with more challenging problems.

[1147] Specific examples

[1148] For example, if a user named "Tanaka" uses this system to learn a new machine operation technique, the system records his learning progress, analyzes his weak areas, and provides appropriate feedback in real time based on the analysis results and his emotional data.

[1149] Specific prompt examples

[1150] "Analyze the user's emotional data to determine the level of stress. Then provide feedback messages according to the results. For example, if the user is feeling stressed, generate a message saying, 'You are feeling stressed. Take a short break.' If the user is showing high concentration, generate a message saying, 'You are highly focused. Great! Keep it up!'"

[1151] In this way, the training system according to the present invention can improve the user's learning efficiency and provide appropriate feedback according to the user's emotional state.

[1152] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1153] Step 1:

[1154] The server stores past training data in a database. Specifically, it collects and assigns metadata such as the year, difficulty level, and category to each training task. The input is past training data, and the output is a database containing training data with the metadata.

[1155] Step 2:

[1156] A user creates an account and logs in using smart glasses or a head-mounted display. The user enters their name, email address, and password, and this information is sent from the device to the server. The input is the user's registration information, and the output is the user information stored in the database.

[1157] Step 3:

[1158] The server uses a generative AI model to generate new problems based on the past training database. It analyzes past data patterns and creates new problems. The input is the past training data in the database, and the output is the generated new training problem.

[1159] Step 4:

[1160] The user works on the problems provided through smart glasses or a head-mounted display. The user's answers and progress are sent from the device to the server. The input is the user's answer data, and the output is progress data stored in a database.

[1161] Step 5:

[1162] The server analyzes the user's learning data and identifies areas of weakness. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. The input is the user's learning progress data, and the output is personalized questions.

[1163] Step 6:

[1164] The server is equipped with an emotion engine that analyzes the user's facial expressions and voice data sent from the device. The input is the user's emotional data, and the output is the analyzed emotional state.

[1165] Step 7:

[1166] The server personalizes learning content and feedback based on the emotional data. For example, it provides messages encouraging the user to relax if the user is feeling stressed, or provides challenging problems if the user is highly focused. The input is the analyzed emotional data, and the output is personalized feedback messages and problems.

[1167] Step 8:

[1168] It then retrains based on the feedback and new questions received by the user via the device. This process continues in real time. The input is personalized feedback and new questions, and the output is the user's ongoing learning progress data.

[1169] Through these steps, the factory robot training system can provide personalized feedback based on the user's progress and emotional state, improving learning efficiency.

[1170] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1171] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1172] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1173] [Fourth embodiment]

[1174] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1175] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1176] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1177] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1178] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1179] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1180] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1181] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1182] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1183] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1184] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1185] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1186] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1187] The present invention provides a learning support system for preparing for qualification exams. The system includes a means for storing past exam questions in a database, generating new questions using a generative AI model, recording and analyzing the user's learning progress data, and providing personalized questions.

[1188] Database of past exam questions

[1189] The server collects past exam questions and stores them in a database, along with metadata such as exam year, difficulty level, and category.

[1190] For example, past exam questions may be stored in the following format:

[1191] Question ID: 1

[1192] Question: Which of the following is the correct algorithm?

[1193] Correct answer: A

[1194] Exam year: 2020

[1195] Difficulty: Moderate

[1196] Category: Algorithms

[1197] User Registration and Login

[1198] The device helps users register and log in. When a user installs the app and creates a new account, information such as name, email address, and password is sent to the server and stored in a database. When users log in, the information they enter is checked against the records in the database.

[1199] Problem Generation

[1200] The server uses a generative AI model to generate new questions based on past exam questions in the database. This model learns the patterns and answer trends of past exam questions and creates new questions that are in line with the actual exam.

[1201] For example, a new question of the form:

[1202] Question: What protocols are used at the network layer?

[1203] Choices: TCP, UDP, IP, HTTP

[1204] Record your learning progress

[1205] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server stores this in a database and records and manages each user's learning progress.

[1206] Weakness analysis and personalization

[1207] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and provides them to the device.

[1208] For example, if a user scores low in the networking section, they will be offered questions like the following:

[1209] Question: Explain network layer protocols.

[1210] Choices: TCP, IP, HTTP, SMTP

[1211] User learning experience

[1212] The user operates the app on their device and works on the personalized questions provided. The answers are then sent back to the server and reflected as new data in their learning progress. This allows users to focus on their weak areas and effectively prepare for qualification exams.

[1213] This system will provide efficient support for studying for qualification exams, allowing users to practice a wide range of questions at low cost and to carry out personalized learning to strengthen their weak areas.

[1214] The processing flow will be explained below.

[1215] Step 1:

[1216] The server collects past exam questions and stores them in a database. Questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[1217] Step 2:

[1218] The terminal prompts the user to enter their registration information. The user enters information such as their name, email address, and password, and sends it to the server. The server receives this information and stores it in a database.

[1219] Step 3:

[1220] A user logs in at a terminal. The entered email address and password are sent to the server and checked against the information in the database. If authentication is successful, the user is granted access to the system.

[1221] Step 4:

[1222] The server uses the generative AI model to generate new questions. Based on a database of past exam questions, the generative AI model analyzes question patterns and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[1223] Step 5:

[1224] The user works on the questions generated on the device. The user selects an answer from the options and sends the answer to the server. The server stores the answer in a database and records it as the user's learning progress data.

[1225] Step 6:

[1226] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect questions, etc., and identifies the user's weak areas. For example, it may be discovered that the user has a low correct answer rate for questions in the "Network" category.

[1227] Step 7:

[1228] The server generates personalized questions based on weak areas, and the generative AI model creates more practice questions related to the "Network" category and sends them to the device.

[1229] Step 8:

[1230] The user works on the personalized questions on their device. The answers are then sent back to the server and recorded as learning progress data. By repeating this process, the user can improve their weak areas while efficiently progressing through their studies.

[1231] Step 9:

[1232] The server periodically evaluates the user's learning progress and sends the results back to the device, allowing the user to create their next learning plan based on this information.

[1233] Example 1

[1234] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1235] Conventional learning support systems mainly provide static questions, making it difficult to provide questions tailored to each user's learning progress and weak areas. This makes it difficult to create an environment where users can study efficiently. In addition, a limited collection of questions is not sufficient to handle a variety of exam questions.

[1236] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1237] In this invention, the server includes means for saving past test data, means for generating new test questions from a past test database using a generation processing model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating and providing the user with personalized test questions based on the weak areas, means for creating and authenticating an account, and means for transmitting answers to the generated test questions and personalized test questions to the server, thereby enabling users to study effectively and prepare for exams more efficiently.

[1238] "Past exam data" refers to data that includes information such as questions and answers from previously administered exams, exam years, difficulty levels, and categories.

[1239] "Means of storage" refers to a system that stores data and allows it to be retrieved as needed. Generally, this refers to a database or storage.

[1240] A "generative processing model" is an algorithm or AI model that generates new test questions based on past test data. Examples include machine learning and generative AI models.

[1241] "Study progress data" refers to information about the progress of a user's study, such as the results of questions answered during the study, the progress of the study, and the study time.

[1242] "Recording means" refers to the systems and mechanisms that capture, store, and keep data in a state where it can be reused later if necessary.

[1243] "Learning data" refers to a series of data generated by a user through learning activities. Specifically, it includes answer results, study time, and percentage of correct answers to questions.

[1244] "Means of analysis" refers to the technology and equipment used to analyze acquired data and extract useful information.

[1245] A "weak area" is an area in which a user has a low score and insufficient understanding in a particular field or topic during their studies.

[1246] "Means of identification" refers to methods or techniques for using data to reveal specific information or conditions.

[1247] "Individualized test questions" refer to test questions that are customized to take into account the individual user's learning progress and areas of weakness.

[1248] "Means of delivery" refers to the mechanism by which questions and data are delivered, displayed, or made accessible to users.

[1249] "Account creation and authentication method" refers to the process by which a user registers with a system and gains access, typically through authentication using information such as a username, password, and email address.

[1250] A "transmission medium" is a technique or method for transmitting data from one point to another, usually over a network.

[1251] The present invention is a study support system for preparing for qualification examinations, and can be implemented as follows.

[1252] Hardware and Software Use

[1253] server

[1254] Storage of past exam data: The server collects past exam data and stores it in a relational database (e.g., MySQL, PostgreSQL). The collected data includes the exam questions themselves as well as metadata such as exam year, difficulty level, and category.

[1255] Generative processing model: The server uses a generative AI model such as OpenAI's GPT-3.5 as a generative processing model, which generates new test questions based on past test data.

[1256] Recording and analyzing learning progress data: The server records the user's learning progress data and stores it in a database. Furthermore, this data is analyzed to identify the user's weak areas.

[1257] Terminal

[1258] User input assistance: The device (e.g., smartphone, tablet, PC) assists the user in registering a new account and logging in through the application, and also sends the results of the user's answers to the server.

[1259] Providing personalized questions: Displaying personalized test questions sent from the server and providing them to the user.

[1260] Examples of specific examples and prompts

[1261] Collecting and storing past test data

[1262] The server collects past exam data from certification exam providers and public databases and stores it in a database in the following format:

[1263] Question ID: 1

[1264] Question: Which of the following is the correct algorithm?

[1265] Correct Answer: A

[1266] Exam year: 2020

[1267] Difficulty: Moderate

[1268] Category: Algorithms

[1269] Generate new exam questions

[1270] The server sends the following prompt to the generative AI model to generate a new test question:

[1271] Past exam questions:

[1272] 1. Question: Which of the following is the correct algorithm?

[1273] Choices: A, B, C, D

[1274] Correct Answer: A

[1275] Create a new question:

[1276] The generative AI model generates new test questions such as:

[1277] Question: What protocols are used at the network layer?

[1278] Choices: TCP, UDP, IP, HTTP

[1279] Recording and analyzing user answers

[1280] When the user enters the answer on the device, the result is sent to the server and recorded in the following format:

[1281] User ID: 12345

[1282] Question ID: 1

[1283] User Answer: B

[1284] Correct Answer: Incorrect

[1285] The server analyzes this data to identify the user's areas of weakness, and based on this analysis, it sends prompts back to the generative AI model to generate personalized questions.

[1286] Personalized Question Generation

[1287] For example, if the analysis shows that the user scores low in the networking area, the following prompt sentence will be sent to the generative AI model:

[1288] User weaknesses: Network layer

[1289] Past exam questions:

[1290] 1. Question: What protocols are used at the network layer?

[1291] Choices: TCP, IP, HTTP, SMTP

[1292] Correct Answer: IP

[1293] Generate a new personalized question:

[1294] The generative AI model generates problems like this:

[1295] Question: Explain network layer protocols.

[1296] Choices: TCP, IP, HTTP, SMTP

[1297] Update user learning progress

[1298] When the user answers the newly generated questions, the results are sent back to the server and recorded and analyzed as learning progress data, allowing users to efficiently prepare for qualification exams.

[1299] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1300] Step 1: Collect and store historical test data

[1301] The server collects past exam data from certification exam providers and public databases, including test questions, exam years, difficulty levels, and categories.

[1302] Input: Qualification exam question data and its metadata.

[1303] Data processing: Organize the collected data by category and difficulty level, and convert it into a format that can be stored in the database.

[1304] Output: Organized historical test data is stored in a database.

[1305] Step 2: User Registration and Login

[1306] The device receives the user's input information (name, email address, password, etc.) and registers a new account.

[1307] Input: The registration information entered by the user.

[1308] Data calculation: The input information is sent to the server and saved in the database. The information entered at login is also verified against the database for authentication.

[1309] Output: Display a sign-up success or login success message to the user.

[1310] Step 3: Generate new exam questions

[1311] The server sends prompt sentences to the generative AI model based on past test data in a database.

[1312] Input: Past test data and prompt for the question to be generated.

[1313] Data calculation: A generative AI model generates new test questions based on prompts.

[1314] Output: The generated new test questions are saved in the database so that they are available for the next test.

[1315] Step 4: Record your learning progress

[1316] The terminal receives the user's answer and sends the result to the server.

[1317] Input: User's answer, user ID, question ID, whether the answer was correct, etc.

[1318] Data calculation: The server records the received answer data in the database.

[1319] Output: The recorded answer data is saved in the database as learning progress data.

[1320] Step 5: Analyze weak areas and generate personalized test questions

[1321] The server analyzes the learning progress data in the database and identifies areas where the user is weak.

[1322] Input: Learning progress data (answer results, correct answer rate, etc.).

[1323] Data calculation: Using data analysis algorithms, we identify areas of weakness for each user.

[1324] Output: Generate prompts based on the identified weaknesses, which are then used by the generative AI model to generate new questions.

[1325] Step 6: Providing personalized questions

[1326] The server sends personalized questions generated by the generative AI model to the device.

[1327] Input: Personalized problem data.

[1328] Data calculation: The problem data is sent from the server to the terminal.

[1329] Output: Users can access personalized questions through their devices and advance their learning.

[1330] Step 7: Update your learning progress

[1331] The terminal transmits the results of the questions answered by the user to the server.

[1332] Input: New answer result (user ID, question ID, user's answer, whether the answer was correct or not).

[1333] Data calculation: The server saves the new answer results in the database and updates the learning progress data.

[1334] Output: Updated learning progress data is saved in the database for future analysis.

[1335] Through the above steps, this system effectively supports users' studies and enables them to prepare for qualification exams more efficiently.

[1336] (Application example 1)

[1337] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1338] Current certification exam preparation systems mainly require users to study individually at home or online, and lack real-time feedback and face-to-face learning support in brick-and-mortar stores. Furthermore, the lack of personalized study questions and immediate instruction from trainers makes effective learning difficult.

[1339] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1340] In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording a user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for the user to work on the personalized study questions using a terminal installed in a physical store, and means for a trainer to provide feedback in real time. This enables face-to-face learning in a physical store and realizes the provision of individual instruction and personalized study questions to users.

[1341] "Past exam questions" refer to questions that were asked in previous qualification exams, which are saved in a database and can be reused.

[1342] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate new problems from data.

[1343] A "database" is a structured collection of information for storing past exam questions and user learning progress data.

[1344] "User's learning progress data" is data that records the results of the problems the user has worked on and the progress of their learning.

[1345] The "weak area" refers to an area or category in which the user has particular difficulty in studying for a qualification exam.

[1346] "Personalized questions" refer to questions that are individually set based on the user's learning data and areas of weakness.

[1347] "Terminals installed in physical stores" refers to electronic devices for learning that are installed in physical stores to prepare for qualification exams.

[1348] A "trainer" is an expert who guides users in preparing for qualification exams and provides real-time feedback.

[1349] This invention is a system that supports users in preparing for qualification exams by utilizing terminals and servers installed in physical stores. This system stores past exam questions in a database and generates new questions using a generative AI model. This system also has the function of recording and analyzing the user's learning progress data to provide personalized questions.

[1350] Hardware and software used

[1351] This system uses the following hardware and software:

[1352] Hardware: Fixed kiosks, tablets, and smartphones installed in brick-and-mortar stores.

[1353] software:

[1354] Server side: Use Flask (a lightweight web application framework written in Python) to perform server-side processing.

[1355] Database: A relational database management system (RDBMS) such as SQLite or MySQL.

[1356] Front-end: Building the user interface using HTML / CSS / JavaScript.

[1357] Data processing and calculation

[1358] The server processes and calculates data in the following procedure.

[1359] 1. Database creation:

[1360] Past exam questions are collected and stored in a database along with metadata such as exam year, difficulty level, and category.

[1361] 2. Problem generation:

[1362] New questions are generated from a database of past exam questions using a generative AI model. The generative AI model learns the patterns of past exam questions and answer trends, and creates new questions that are in line with the actual exam.

[1363] For example, create a new question in the following format:

[1364] Question: "What protocols are used at the network layer?"

[1365] Choices: TCP, UDP, IP, HTTP

[1366] 3. Recording and analyzing your learning progress:

[1367] The server receives the answer results sent from the user's device and stores them in a database. The recorded data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. Based on this, the user's weak areas are analyzed.

[1368] 4. Providing personalized questions:

[1369] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if the user scored low in the network section, the following questions will be provided:

[1370] Question: "Explain network layer protocols."

[1371] Choices: TCP, IP, HTTP, SMTP

[1372] User learning experience

[1373] Users can operate devices installed in physical stores and work on personalized study questions. The devices are tablets or smartphones, and the user's answers are instantly sent to a server. Furthermore, trainers can provide real-time feedback, enabling effective study support.

[1374] For example, if a user requests that a problem be generated on demand, the following prompt sentence is input to the generative AI model:

[1375] "Generate a question asking, 'What protocol is used at the network layer?' The options are TCP, UDP, IP, and HTTP."

[1376] In this way, a system can be constructed that can provide individualized instruction and personalized problems to users.

[1377] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1378] Step 1: Collecting and creating a database of past exam questions

[1379] The server collects past exam questions and stores them in a database along with metadata such as exam year, difficulty level, category, etc. Specifically, the data for each question is formatted as shown below and registered in the database.

[1380] Input: Past exam questions (e.g., question text, answers, exam year)

[1381] Output: Structured data stored in a database

[1382] Step 2: User Registration and Login

[1383] A user creates an account using a device and sends information such as name, email address, and password to the server, which stores this information in a database and collates it with the information entered when logging in.

[1384] Input: User information (e.g. name, email address, password)

[1385] Output: User authentication status (registration complete, login success / failure)

[1386] Step 3: Generate a new problem

[1387] The server uses a generative AI model to generate new questions from a database of past exam questions. The model learns the patterns of past questions and creates new questions that are relevant to the actual exam.

[1388] Input: Generative AI model, past exam question data

[1389] Output: A newly generated question (e.g., "What protocol is used at the network layer?")

[1390] Step 4: Record your learning progress

[1391] When a user answers a study question on their device, the answer is sent to the server, which stores the answer in a database. The recorded data includes the user ID, question ID, the user's answer, and whether the answer was correct.

[1392] Input: User's answer result (e.g., user ID, question ID, user's answer)

[1393] Output: Learning progress data stored in a database

[1394] Step 5: Analyze your weaknesses

[1395] The server analyzes the user's learning progress data and identifies areas in which the user is weak. Based on the analysis results, if the user has a low score in a particular area, the server recognizes that area as a "weak area."

[1396] Input: User's learning progress data

[1397] Output: Identification of weak areas

[1398] Step 6: Deliver personalized questions

[1399] Based on the analysis results, the server generates personalized questions that focus on the user's weak areas and sends them to the terminal. For example, if the user scores low in the networking area, the server creates related questions.

[1400] Input: Identification of weak areas, AI model for generating new problems

[1401] Output: A personalized question sent to the device (e.g., "What protocol is used at the network layer?")

[1402] Step 7: Provide real-time feedback

[1403] The trainer monitors the user's answers and provides real-time feedback. Each time the user submits an answer, the trainer provides advice based on the results.

[1404] Input: User's answer result

[1405] Output: Feedback from the trainer

[1406] The above processing steps enable face-to-face learning in a brick-and-mortar store, providing users with individualized instruction and personalized learning problems. For example, a new problem can be generated by inputting the prompt sentence, "Generate the question: What protocol is used in the network layer? The options are TCP, UDP, IP, and HTTP." into the generative AI model.

[1407] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1408] This invention combines an emotion engine with a learning support system for preparing for qualification exams. The system stores past exam questions in a database, generates new questions using a generative AI model, and includes a means for recording and analyzing the user's learning progress data and providing personalized questions. Furthermore, the system has the added function of recognizing the user's emotions and providing personalized feedback based on the emotion data.

[1409] Database of past exam questions

[1410] The server collects past exam questions and stores them in a database. These questions are assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[1411] User Registration and Login

[1412] The terminal prompts the user to enter registration information. The user enters information such as name, email address, and password, and sends this to the server. The server stores the received information in a database. When logging in, the entered email address and password are sent to the server and compared with the information in the database. Users who are successfully authenticated can access the system.

[1413] Problem Generation

[1414] The server uses the generative AI model to generate new questions based on past questions in the database. The generative AI model analyzes the patterns of past questions and creates new questions. For example, it generates a question such as, "What protocol is used at the network layer?"

[1415] Record your learning progress

[1416] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, whether the answer was correct, etc. The server saves the answer results in a database and records them as the user's learning progress data.

[1417] Weakness analysis and personalization

[1418] The server analyzes the user's weak areas based on their learning data. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. For example, if a user scores low in the "Network" category, questions related to that category will be provided.

[1419] Combining Emotion Engines

[1420] Furthermore, the server is equipped with an emotion engine. The device detects the user's facial expressions and voice during learning and sends this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[1421] Emotion-based personalization and feedback

[1422] The server uses emotional data to personalize learning content and feedback. For example, if a user is feeling stressed, it sends a message encouraging them to pause and relax. Also, if a user shows high levels of concentration, it provides them with more challenging problems.

[1423] User learning experience

[1424] As users navigate the app on their devices and tackle the personalized questions provided, the emotion engine continuously collects emotional data. Based on this, the learning experience is adapted in real time. For example, if a user is feeling down, an encouraging message will be displayed. This feedback helps users maintain their motivation to study and efficiently prepare for exams.

[1425] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide more effective preparation for qualification exams.

[1426] The processing flow will be explained below.

[1427] Step 1:

[1428] The server collects past exam questions and stores them in a database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" will have metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network" added to it.

[1429] Step 2:

[1430] The terminal accepts the user's registration information. The user enters information such as their name, email address, and password into the terminal and sends it to the server. The server stores the received information in a database.

[1431] Step 3:

[1432] The user logs in at the terminal. The email address and password entered by the user are sent to the server and checked against the information in the database. If authentication is successful, the user is allowed to access the system.

[1433] Step 4:

[1434] The server uses the generative AI model to generate new questions based on past questions in the database. For example, a new question such as "What protocol is used in the network layer?" is generated from a past question. The newly generated question is then provided to the user.

[1435] Step 5:

[1436] The user works on the questions generated on the device. The user selects an answer and sends the answer to the server. The server stores the received answer in a database and records it as the user's learning progress data.

[1437] Step 6:

[1438] The server analyzes the user's learning data. It analyzes the correct answer rate, answer time, category of incorrect answers, etc. to identify the user's weak areas. For example, if the user has a low correct answer rate on questions in the "Network" category, that category will be identified as the user's weak area.

[1439] Step 7:

[1440] The server generates personalized questions based on the user's weak areas. The generative AI model creates new questions related to the user's weak areas and sends them to the device. For example, questions in the "Network" category are provided with a focus on the user.

[1441] Step 8:

[1442] The device detects the user's facial expressions and voice while studying and sends this emotional data to the server, where the emotion engine analyzes the user's emotions (stress, joy, concentration, etc.).

[1443] Step 9:

[1444] The server then uses the emotional data to personalize learning feedback. For example, if the user is feeling stressed, it will display a message on the device encouraging them to relax. If the user is highly focused, it will provide more challenging problems.

[1445] Step 10:

[1446] As users work through personalized exercises, learning progress and emotional data is continuously collected and analyzed, allowing the user's learning experience to adapt in real time, enabling more efficient learning.

[1447] Step 11:

[1448] The server periodically evaluates the user's learning progress and emotional data, and sends the results back to the device, allowing the user to plan their next learning plan based on this information.

[1449] Example 2

[1450] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1451] While conventional learning support systems analyze users' learning progress and areas of weakness, they do not provide individualized support that takes into account the user's emotional state, which creates challenges in maintaining learning efficiency and motivation. Furthermore, personalization based solely on the user's answers and learning data has its limitations, making it difficult to provide effective preparation for qualification exams.

[1452] The identification process by the identification 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 saving past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means having an emotion engine for collecting and analyzing the user's facial expression and voice data, and means for providing personalized feedback based on the emotion data. This makes it possible to improve learning efficiency and maintain motivation by understanding the user's emotional state in real time and individually adjusting the learning content and feedback based on that data.

[1453] "Past exam questions" means all questions previously asked in a particular qualification examination.

[1454] A "database" is a system for storing, managing, and retrieving data efficiently and systematically.

[1455] A "generative AI model" is an algorithmic model that uses artificial intelligence to generate new data, and often refers specifically to a natural language processing model.

[1456] "Study progress data" refers to data that records the results of answers given by a user while studying and the progress of that user.

[1457] "User learning data" refers to all data related to learning, such as the user's answer results, study time, correct answer rate, and answer tendencies.

[1458] "Weak areas" are specific areas or topics where a user has poor performance or understanding in their studies.

[1459] "Personalized questions" are questions that are customized to a user's specific learning needs or areas of weakness.

[1460] "Facial expression and voice data" refers to data such as facial expressions, voice tone, speed, and rhythm that represent the user's emotional state.

[1461] An "emotion engine" is software or algorithms that analyze facial and voice data to identify a user's emotional state.

[1462] "Personalized feedback" refers to feedback and advice that is individually tailored based on the user's learning status and emotions.

[1463] This invention is a learning support system for preparing for qualification exams, which provides users with a personalized learning experience by combining an emotion engine. This system consists of a server, a terminal, and a user.

[1464] Database of past exam questions

[1465] The server collects past exam questions from the internet and cooperating institutions and stores them in a PostgreSQL database. Each question is assigned metadata such as exam year, difficulty level, and category. For example, the question "What is the role of the network layer?" is assigned metadata such as "Year: 2021," "Difficulty: Low," and "Category: Network."

[1466] User Registration and Login

[1467] The terminal provides an interface for the user to enter information such as name, email address, and password. The user enters this information and sends it to the server. The server stores the received information in a PostgreSQL database, and the password is hashed using bcrypt. When logging in, the email address and password entered by the user are sent to the server and compared with the information stored in the database. If the comparison is successful, the user is allowed to access the system.

[1468] Problem Generation

[1469] The server uses the generative AI model to generate new questions based on past questions in the database. For example, the following prompt is input to the generative AI model: "Generate new questions based on questions in the network category from the past five years." Based on this prompt, the generative AI model (e.g., GPT-4) generates a new question: "What protocol is used in the network layer?"

[1470] Record your learning progress

[1471] The device sends the user's answer results to the server. The answer data includes the user ID, question ID, the user's answer, and whether the answer was correct. The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data.

[1472] Weakness analysis and personalization

[1473] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. For example, if a user scores low in the "Network" category, questions related to that category will be provided. Using the generative AI model, a prompt sentence such as the following is input: "Please generate new questions based on past exam questions in the Network field."

[1474] Combining Emotion Engines

[1475] The server is equipped with an emotion engine, and the device uses a camera and microphone to collect the user's facial expressions and voice data in real time. This data is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The analysis results are reflected in learning content and feedback in real time.

[1476] Emotion-based personalization and feedback

[1477] The server uses emotional data to personalize learning content and feedback. For example, it inputs the following prompt into the generative AI model: "If the user is concentrating, provide problems with a moderate level of difficulty." If the user is feeling stressed, it sends a message encouraging them to pause their learning and relax.

[1478] User learning experience

[1479] As users interact with the app on their devices and complete the personalized tasks provided, the emotion engine continuously collects emotional data, allowing the server to adapt the learning experience in real time. For example, if a user is feeling down, it can display encouraging messages to keep the user motivated to learn.

[1480] In this way, by combining emotion recognition functionality, the system of the present invention can highly personalize the user's learning experience and provide efficient preparation for qualification exams.

[1481] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1482] Step 1: Collect past exam questions and save them in a database

[1483] Specific behavior:

[1484] The server collects past exam questions from the Internet and cooperating institutions. The input data are exam questions provided in various formats. The server converts these questions into a standardized format and stores them in a PostgreSQL database. The output data are the standardized exam questions and their metadata. For example, the metadata "Year: 2021," "Difficulty: Low," and "Category: Network" are added to the question "What is the role of the network layer?"

[1485] Step 2: User Registration and Login

[1486] Specific behavior:

[1487] The terminal provides an interface that lets the user enter information such as name, email address, and password. The input data is the user's registration information. This is sent to the server and stored in a PostgreSQL database. The password is hashed using bcrypt. The output data is the user information stored in the database. When logging in, the user enters their email address and password and sends it to the server. The server checks it against the information stored in the database, and if it matches, authentication is successful. The output is a success or failure status.

[1488] Step 3: Generate a new problem

[1489] Specific behavior:

[1490] The server creates and sends a prompt to the generative AI model. The input data is the metadata and text information of past questions. As an example, the prompt is "Please generate a new question based on questions in the network category from the past five years." The generative AI model (e.g., GPT-4) generates a new question based on this. The output data is the generated new question, such as "What protocol is used in the network layer?" The server stores this in a database and sends it to the terminal to provide to the user.

[1491] Step 4: Record your learning progress

[1492] Specific behavior:

[1493] The user answers a new question, and the device sends the results to the server. The input data is the user's answer (user ID, question ID, user answer, whether the answer was correct or not). The server saves these answer results in a PostgreSQL database and records them as the user's learning progress data. The output data is an updated record of learning progress.

[1494] Step 5: Analyze weak areas and personalize

[1495] Specific behavior:

[1496] The server analyzes the user's cumulative learning data and identifies weak areas based on the percentage of correct answers and answer time. The input data is the user's learning data. Based on this, the server identifies areas where the user scored low, for example, in the "Network" category. Using a generative AI model, the server uses a prompt such as "Please generate new questions based on past exam questions in the Network category." The output data are the generated new personalized questions, which are sent to the terminal and provided to the user.

[1497] Step 6: Collect and analyze emotion data

[1498] Specific behavior:

[1499] The device uses a camera and microphone to collect the user's facial and voice data in real time. The input data is the user's facial and voice data. This is sent to the server, where the emotion engine analyzes it to identify the user's emotional state (e.g., stress, joy, concentration, etc.). The output data is the user's emotional state.

[1500] Step 7: Provide emotion-based feedback

[1501] Specific behavior:

[1502] The server personalizes learning content and feedback based on the emotional data. The input data is the analyzed emotional data. A prompt such as "If the user is concentrating, please provide questions with a moderate level of difficulty" is input to the generative AI model. The output data is personalized learning content and feedback, which is sent to the device and provided to the user.

[1503] Step 8: Adapting the learning experience on an ongoing basis

[1504] Specific behavior:

[1505] The device continuously collects emotional data while the user is learning, and the server analyzes it. The input data is real-time emotional data. Based on this, the server adaptively adjusts the learning experience and feedback and provides it to the user via the device. The output data is the learning experience and feedback updated in real time. For example, if the user is feeling down, an encouraging message is displayed, and if the user is concentrating well, challenging problems are provided.

[1506] (Application example 2)

[1507] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1508] While conventional learning support systems focus on analyzing users' progress and weak areas, they do not provide feedback based on the user's emotional state, making it difficult to maintain learning efficiency and motivation.In addition, appropriate feedback based on real-time emotional recognition is important for factory robot operators to efficiently improve their skills, but no system with such functionality existed.

[1509] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing past exam questions in a database, means for generating new questions from the past exam question database using a generative AI model, means for recording the user's learning progress data, means for analyzing the user's learning data and identifying weak areas, means for generating personalized questions based on the weak areas and providing them to the user, means for recognizing and analyzing the user's emotional data, and means for providing feedback based on the emotional data. This not only analyzes the user's progress and weak areas, but also enables the provision of feedback tailored to the user's emotional state, which is expected to improve learning efficiency and maintain motivation. It also enables efficient training of factory robot operators.

[1510] The "means for storing past test questions in a database" refers to a device or function that collects test questions that have been given in the past and stores those questions in a database.

[1511] "Means for generating new questions from a database of past exam questions using a generative AI model" refers to a device or function that uses an artificial intelligence model to analyze a database of past exam questions and create new exam questions.

[1512] The "means for recording user's learning progress data" refers to a device or function for recording the results of the user's answers and the progress of the user.

[1513] The "means for analyzing the user's learning data and identifying weak areas" refers to a device or function that analyzes the user's learning data and identifies the areas or regions in which the user is weak.

[1514] The "means for generating personalized questions based on weak areas and providing them to the user" is a device or function that generates questions appropriate to the identified weak areas and provides them to the user individually.

[1515] The "means for recognizing and analyzing user emotional data" refers to a device or function that collects and analyzes emotional data such as the user's facial expressions and voice.

[1516] The "means for providing feedback based on emotion data" is a device or function that provides appropriate feedback or advice to the user based on the analyzed emotion data.

[1517] The present invention provides a training system for factory robot operators that uses past training data and a generative AI model to generate new training questions and provides personalized feedback based on the user's learning progress and emotional data.

[1518] Specifically, the following means are used:

[1519] 1. Database of past training data:

[1520] The server collects past training data and stores it in a database. This data is assigned metadata such as the training year, difficulty level, and category. For example, to a training task such as "What is the procedure for replacing parts on an industrial robot?", metadata such as "Year: 2021," "Difficulty: Medium," and "Category: Machine Operation" are added.

[1521] 2. Training problem generation:

[1522] The server uses a generative AI model to generate new questions based on past training data in the database. The generative AI model analyzes patterns in past training data and creates new questions. For example, a question might be generated: "What sensor technology is used in industrial robots?"

[1523] 3. Record your learning progress:

[1524] Users train through smart glasses or a head-mounted display. Their answers and progress data are sent from the device to a server, which records them. The recorded data includes the user ID, question ID, the user's answer, and whether or not the answer was correct.

[1525] 4. Weakness analysis and personalization:

[1526] The server analyzes the user's learning data and identifies their weak areas. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the smart glasses or head-mounted display. For example, if a user scores low in the "machine operation" category, questions related to that category will be provided.

[1527] 5. Emotion engine combination:

[1528] Furthermore, the server is equipped with an emotion engine. The smart glasses or head-mounted display detects the user's facial expressions and voice and transmits this data to the server. The emotion engine analyzes this data and identifies the user's emotions (e.g., stress, joy, concentration, etc.).

[1529] 6. Emotion-based personalization and feedback:

[1530] The server personalizes learning content and feedback based on emotional data. For example, if a user is feeling stressed, it will send a message encouraging them to pause and relax. If a user shows high levels of concentration, it will provide them with more challenging problems.

[1531] Specific examples

[1532] For example, if a user named "Tanaka" uses this system to learn a new machine operation technique, the system records his learning progress, analyzes his weak areas, and provides appropriate feedback in real time based on the analysis results and his emotional data.

[1533] Specific prompt examples

[1534] "Analyze the user's emotional data to determine the level of stress. Then provide feedback messages according to the results. For example, if the user is feeling stressed, generate a message saying, 'You are feeling stressed. Take a short break.' If the user is showing high concentration, generate a message saying, 'You are highly focused. Great! Keep it up!'"

[1535] In this way, the training system according to the present invention can improve the user's learning efficiency and provide appropriate feedback according to the user's emotional state.

[1536] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1537] Step 1:

[1538] The server stores past training data in a database. Specifically, it collects and assigns metadata such as the year, difficulty level, and category to each training task. The input is past training data, and the output is a database containing training data with the metadata.

[1539] Step 2:

[1540] A user creates an account and logs in using smart glasses or a head-mounted display. The user enters their name, email address, and password, and this information is sent from the device to the server. The input is the user's registration information, and the output is the user information stored in the database.

[1541] Step 3:

[1542] The server uses a generative AI model to generate new problems based on the past training database. It analyzes past data patterns and creates new problems. The input is the past training data in the database, and the output is the generated new training problem.

[1543] Step 4:

[1544] The user works on the problems provided through smart glasses or a head-mounted display. The user's answers and progress are sent from the device to the server. The input is the user's answer data, and the output is progress data stored in a database.

[1545] Step 5:

[1546] The server analyzes the user's learning data and identifies areas of weakness. Based on the analysis results, the generative AI model generates personalized questions that focus on the user's weak areas and sends them to the device. The input is the user's learning progress data, and the output is personalized questions.

[1547] Step 6:

[1548] The server is equipped with an emotion engine that analyzes the user's facial expressions and voice data sent from the device. The input is the user's emotional data, and the output is the analyzed emotional state.

[1549] Step 7:

[1550] The server personalizes learning content and feedback based on the emotional data. For example, it provides messages encouraging the user to relax if the user is feeling stressed, or provides challenging problems if the user is highly focused. The input is the analyzed emotional data, and the output is personalized feedback messages and problems.

[1551] Step 8:

[1552] It then retrains based on the feedback and new questions received by the user via the device. This process continues in real time. The input is personalized feedback and new questions, and the output is the user's ongoing learning progress data.

[1553] Through these steps, the factory robot training system can provide personalized feedback based on the user's progress and emotional state, improving learning efficiency.

[1554] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1555] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1556] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1557] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1558] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1559] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1560] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1561] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1562] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1563] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1564] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1565] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1566] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1567] 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.

[1568] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1569] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1570] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1571] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1572] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1573] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1574] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1575] The following is further disclosed regarding the above embodiment.

[1576] (Claim 1)

[1577] a means for storing past examination questions in a database;

[1578] A means for generating new questions from a database of past exam questions using a generative AI model;

[1579] means for recording user learning progress data;

[1580] A means for analyzing the user's learning data and identifying weak areas;

[1581] A means for generating and providing personalized questions to a user based on weak areas;

[1582] A system including:

[1583] (Claim 2)

[1584] 10. The system of claim 1, further comprising means for a user to create an account and log in.

[1585] (Claim 3)

[1586] 10. The system of claim 1, further comprising means for transmitting answers to the generated questions and personalized questions to the server.

[1587] "Example 1"

[1588] (Claim 1)

[1589] a means for storing past test data;

[1590] means for generating new test questions from a database of past tests using the generative process model;

[1591] a means for recording user learning progress data;

[1592] A means of analyzing users' learning data and identifying areas of weakness;

[1593] A means for generating and providing user-specific test questions based on areas of weakness;

[1594] A system including:

[1595] (Claim 2)

[1596] 10. The system of claim 1, further comprising means for a user to create and authenticate an account.

[1597] (Claim 3)

[1598] 10. The system of claim 1, further comprising means for transmitting answers to the generated test questions and / or personalized test questions to the server.

[1599] "Application Example 1"

[1600] (Claim 1)

[1601] a means for storing past examination questions in a database;

[1602] A means for generating new questions from a database of past exam questions using a generative AI model;

[1603] means for recording user learning progress data;

[1604] A means for analyzing the user's learning data and identifying weak areas;

[1605] A means for generating and providing personalized questions to a user based on weak areas;

[1606] A means for users to work on personalized learning problems using terminals installed in the physical store;

[1607] a means for trainers to provide real-time feedback;

[1608] A system including:

[1609] (Claim 2)

[1610] 10. The system of claim 1, further comprising means for a user to create an account and log in.

[1611] (Claim 3)

[1612] 10. The system of claim 1, further comprising means for transmitting answers to the generated questions and personalized questions to the server.

[1613] "Example 2: Combining Emotion Engines"

[1614] (Claim 1)

[1615] a means for storing past examination questions in a database;

[1616] A means for generating new questions from a database of past exam questions using a generative AI model;

[1617] means for recording user learning progress data;

[1618] A means for analyzing the user's learning data and identifying weak areas;

[1619] A means for generating and providing personalized questions to a user based on weak areas;

[1620] a means for collecting and analyzing facial expressions and voice data of a user, the means including an emotion engine;

[1621] a means for providing personalized feedback based on the emotional data;

[1622] A system including:

[1623] (Claim 2)

[1624] 10. The system of claim 1, further comprising means for a user to create an account and log in.

[1625] (Claim 3)

[1626] 10. The system of claim 1, further comprising means for transmitting answers to the generated questions and personalized questions to the server.

[1627] "Application example 2 when combining emotion engines"

[1628] (Claim 1)

[1629] a means for storing past examination questions in a database;

[1630] A means for generating new questions from a database of past exam questions using a generative AI model;

[1631] means for recording user learning progress data;

[1632] A means for analyzing the user's learning data and identifying weak areas;

[1633] A means for generating and providing personalized questions to a user based on weak areas;

[1634] means for recognizing and analyzing user emotion data;

[1635] a means for providing feedback based on the emotion data;

[1636] A system including:

[1637] (Claim 2)

[1638] 10. The system of claim 1, further comprising means for a user to create an account and log in.

[1639] (Claim 3)

[1640] 10. The system of claim 1, further comprising means for transmitting answers to the generated questions and personalized questions to the server. [Explanation of symbols]

[1641] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for storing past examination questions in a database; A means for generating new questions from a database of past exam questions using a generative AI model; means for recording user learning progress data; A means for analyzing the user's learning data and identifying weak areas; A means for generating and providing personalized questions to a user based on weak areas; A system including:

2. 10. The system of claim 1, further comprising means for a user to create an account and log in.

3. 2. The system of claim 1, further comprising means for transmitting answers to the generated questions and personalized questions to the server.

Images