System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting a learning material; means for using an artificial intelligence model to analyze the input learning material; means for generating a quiz based on an analysis result; means for storing the generated quiz; means for providing the stored quiz; and means for receiving an answer to the quiz and generating feedback.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] In today's world, quizzes are extremely important for checking learners' understanding when learning e-learning or business procedures. However, creating these quizzes manually by the learning material creator is both time-consuming and labor-intensive. It is particularly difficult to consistently provide quizzes based on the latest content for learning materials that are frequently updated. As a result, learning effectiveness may not be fully realized. A system that can solve these problems and enable efficient learning is needed. [Means for solving the problem]

[0005] The present invention provides a system in which, when learning materials are input, an artificial intelligence model analyzes the content and automatically generates quizzes. Specifically, the system includes a means for inputting learning materials, a means for using an artificial intelligence model to analyze the input learning materials, a means for generating quizzes based on the analysis results, a means for saving the generated quizzes, a means for providing the saved quizzes, and a means for receiving answers to the quizzes and generating feedback. This system saves learning material creators the effort of creating quizzes and allows them to provide quizzes based on the latest learning material content. Furthermore, learners can progress through their studies efficiently and improve their understanding by receiving appropriate evaluations and feedback on their level of understanding.

[0006] "Learning materials" refers to educational content and teaching materials provided to learners, and examples include PDF files, text files, and slide decks.

[0007] An "artificial intelligence model" refers to technology that uses computer programs and algorithms to analyze knowledge and automatically perform specific tasks based on what it has learned.

[0008] A "quiz" is a set of questions or problems, which may be multiple choice or short answer, that a learner answers to assess specific knowledge or skills.

[0009] "Analysis" refers to breaking down input data and processing it to understand its content and structure.

[0010] "Generation" refers to the process of creating new information or data (in this case, quiz questions) based on the results of analysis.

[0011] "Storage" refers to keeping the generated quiz and data in a database or storage for later use.

[0012] "Serving" means delivering or displaying a stored quiz in an accessible format to a learner or user.

[0013] "Answering" refers to the act of a learner making a choice or writing a response to a presented quiz question based on their own knowledge and thoughts.

[0014] "Feedback" refers to the process of providing feedback and comments based on the learner's quiz answers, indicating the learner's level of understanding and areas for improvement. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[0037] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0038] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an artificial intelligence model.

[0039] The server reads the stored learning materials and inputs them into an AI model, which then uses natural language processing techniques to analyze the content of the learning materials. This analysis involves extracting key points and keywords for each chapter or section of the learning materials.

[0040] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0041] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[0042] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0043] Finally, the server generates and provides the user with feedback based on the results, including detailed comments on the user's understanding of a particular chapter and areas for improvement.

[0044] As a concrete example, let's take corporate training materials. A user uploads a PDF document on business ethics. The server analyzes the content and generates quiz questions such as "What is business ethics?" and "What are the important elements of business ethics?". The user answers these questions and receives feedback based on their answers. This allows the user to study efficiently and improve their understanding.

[0045] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[0049] Step 2:

[0050] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[0051] Step 3:

[0052] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server properly manages the naming and storage location of the files.

[0053] Step 4:

[0054] The server reads the stored learning material and prepares it as data to input into the artificial intelligence model.

[0055] Step 5:

[0056] The AI ​​model receives input data from the server and analyzes the learning material. Using natural language processing technology, the model analyzes the content of the learning material by chapter and section, extracting key points and keywords.

[0057] Step 6:

[0058] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[0059] Step 7:

[0060] The AI ​​model generates quiz questions based on the analysis results, automatically generating multiple-choice and essay-style questions.

[0061] Step 8:

[0062] The server stores the generated quizzes in a database or in the " / quizzes / " folder, which ensures that the generated quizzes are kept for future use.

[0063] Step 9:

[0064] A user selects the "Take Quiz" option on the learning platform and requests a quiz based on a particular learning module or topic.

[0065] Step 10:

[0066] Upon receiving a user request, the server reads the corresponding quiz from the " / quizzes / " folder and sends the quiz to the user's terminal.

[0067] Step 11:

[0068] The user answers the quiz received on the terminal by selecting or writing a question and pressing the "Submit Answer" button.

[0069] Step 12:

[0070] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each question, as well as a total score.

[0071] Step 13:

[0072] The server generates feedback based on the user's answers, such as detailed feedback comments that include the user's level of understanding and areas for improvement.

[0073] Step 14:

[0074] The server sends the generated feedback to the user's device and displays it on the user's screen, where the user can check the feedback and use it to improve their learning.

[0075] Example 1

[0076] 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."

[0077] In today's educational environment, there is a demand for systems that can efficiently assess learning progress based on individual learning materials. However, in conventional systems, the analysis of learning materials and the generation of quizzes appropriate to the content are often done manually, which often leads to inefficient or inaccurate assessments. Another problem is the lack of a mechanism for properly providing the created quizzes to users and providing appropriate feedback based on their answers.

[0078] 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.

[0079] In this invention, the server includes means for preparing learning materials, means for inputting learning materials and uploading them to the learning platform, means for receiving and saving the uploaded learning materials, means for inputting the saved learning materials into an artificial intelligence model and analyzing them using natural language processing technology, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for receiving quiz requests from users and providing the saved quizzes, means for receiving answers to the quizzes and automatically evaluating and calculating scores, and means for generating and providing feedback based on the evaluation results. This enables efficient operations from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0080] "Learning Materials" means educational content, including formats such as PDF files, text files, and slide decks.

[0081] "Learning Platform" means a software environment that allows users to upload, manage, and use learning materials.

[0082] "Saving" means storing the received data in a specific folder or database on the server.

[0083] An "artificial intelligence model" is a system that uses programmed algorithms and machine learning techniques to analyze data and generate knowledge.

[0084] "Analyzing" means analyzing the content of the learning material using natural language processing technology and extracting important points and keywords.

[0085] A "quiz" is a set of questions created to assess a user's level of understanding, and includes multiple choice questions and written questions.

[0086] "Generating" means creating new quiz questions based on the analysis results.

[0087] "Providing" means distributing the generated quiz to users and making it available for use.

[0088] "Evaluating" means scoring the user's answers to the quiz and determining whether they are correct or incorrect.

[0089] The "score" is the score given to the user for the quiz answer, and is a numerical value that indicates the overall level of understanding.

[0090] "Feedback" refers to detailed comments and improvements on the evaluation results provided to the user.

[0091] MODE FOR CARRYING OUT THE INVENTION

[0092] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. The series of processes in this system are particularly configured as follows:

[0093] First, the user prepares learning materials using their device. These learning materials include educational content in various formats, such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0094] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an AI model. Specifically, the server reads the saved learning materials and inputs them into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials. This analysis involves extracting important points and keywords for each chapter and section of the learning materials.

[0095] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0096] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[0097] The user displays the submitted quiz on the screen and answers each question. Once all questions have been answered, the user presses the "Submit Answers" button. The server then receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the overall score. Feedback based on the results is then generated and provided to the user. For example, detailed comments about the user's understanding of a particular chapter and areas for improvement are displayed to the user.

[0098] As a concrete example, taking corporate training materials as an example, users upload PDF materials on "business ethics." The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" Users answer these quizzes and receive feedback based on their answers. This allows users to study efficiently and improve their understanding.

[0099] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] The user prepares learning materials using a terminal. The learning materials can be in the form of PDF files, text files, slides, etc. The user logs in to the learning platform and clicks the "Upload" button. The user selects the learning materials from the file selection dialog and presses the "Send" button. The terminal divides the selected learning materials into packet data and sends them to the server. The input learning materials are processed as data to be sent from the terminal to the server. Packet data is generated as output.

[0103] Step 2:

[0104] The server receives packet data sent from the terminal. It reconstructs the packet data to generate a complete learning material file. It saves this data in the " / uploaded_materials / " folder in storage. For example, it saves it as " / uploaded_materials / material1.pdf". As input, it receives packet data from the terminal and creates a complete file through data reconstruction. As output, it saves the complete learning material file.

[0105] Step 3:

[0106] The server reads the stored learning materials. The learning material files are input into an AI model, and the content is analyzed using natural language processing technology. The analysis involves extracting key points and keywords for each chapter and section of the learning material. The learning material files are provided to the AI ​​model as input. Data processing involves analysis using natural language processing. The output is the key points and keywords obtained as the analysis results.

[0107] Step 4:

[0108] The server instructs the AI ​​model to generate a quiz based on the analysis results. The AI ​​model generates quiz questions in the form of multiple choice or written questions based on the extracted points and keywords. The generated quizzes are saved in the " / quizzes / " folder or in a database. The analysis results are used as input as basic data for quiz generation. Quiz questions are generated as data calculations. A quiz file is saved as output.

[0109] Step 5:

[0110] A user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. The device sends the user's request to the server. As input, the user's request information is sent to the server. As output, the request data is generated.

[0111] Step 6:

[0112] The server receives a user request, reads the corresponding quiz file from the " / quizzes / " folder, and sends the read quiz to the user's device. As input, the target quiz file based on the user request is searched and read. As output, the quiz file is delivered.

[0113] Step 7:

[0114] The user answers the quiz displayed on the device. For each question, they click on the answer option or enter a written response. After answering all questions, they press the "Submit Answers" button. The user's answer data is sent from the device to the server as input. The answer data is generated as output.

[0115] Step 8:

[0116] The server receives the user's answers. It automatically evaluates whether they are correct or incorrect using an artificial intelligence model. It calculates the score for each question and calculates the overall score. It generates detailed feedback based on the results and provides it to the user. As input, the user's answer data is evaluated. As data calculations, it determines whether they are correct or incorrect and calculates the score. As output, the generated feedback is provided to the user.

[0117] (Application example 1)

[0118] 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."

[0119] In modern industrial settings, it is important for workers to thoroughly understand work procedures and safety rules in order to perform their work accurately and safely. However, traditional methods often rely on text-based manuals, which can lead to inconsistent levels of understanding. Furthermore, manually creating quizzes and tests to assess work comprehension is time-consuming and laborious, so efficient training methods are needed.

[0120] 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.

[0121] In this invention, the server includes a means for inputting learning materials, a means for using an AI model to analyze the input learning materials, a means for generating quizzes based on the analysis results, and a means for saving the generated quizzes. This allows the server to be installed on an industrial robot and automatically generate quizzes based on work procedures and safety rules, and provide them to workers. As a result, safe and effective work training can be achieved by efficiently evaluating the worker's level of understanding and providing appropriate feedback.

[0122] "Learning materials" are materials containing educational content, such as PDF files, text files, and slide decks.

[0123] An "artificial intelligence model" is an algorithm or software that can analyze text data using natural language processing technology and extract important points and keywords.

[0124] A "quiz" is a question generated to assess the level of understanding of learning material, and may take the form of multiple choice or essay questions.

[0125] "Means for saving" refers to the function for storing the analysis results and generated quizzes in a database or file system.

[0126] "Means for providing" refers to the functionality of sending and receiving data via a user interface to display saved quizzes to a user and accept answers.

[0127] "Means for generating feedback" refers to a function that determines whether a user's answers are correct or incorrect based on the user's quiz answers, and generates detailed comments and scores to notify the user.

[0128] An "industrial robot" is a robotic device used in factories to assist with work and train workers.

[0129] A "work procedure" is a method or step for properly and efficiently performing a specific task in an industrial setting.

[0130] "Safety rules" refer to the guidelines and protocols that must be followed when working within a factory, and are rules necessary to ensure safety.

[0131] A "worker" is an employee who operates machinery and equipment at an industrial site and performs specific tasks.

[0132] The present invention is a system that is installed on an industrial robot, inputs learning materials, and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[0133] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0134] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage. The saved learning materials are then analyzed by an AI model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords.

[0135] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated. The generated quizzes are saved in a specific folder or database by the server.

[0136] When a user wants to take a quiz, they select the "Take Quiz" option on the learning platform. They request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[0137] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0138] Finally, the server generates and provides feedback based on the results to the user, including detailed comments on the level of understanding and areas for improvement for a particular chapter, allowing the user to study efficiently and improve their comprehension.

[0139] As a specific example, an industrial robot can upload a work procedure manual in PDF format, and the robot will analyze the uploaded manual content and generate quizzes based on important procedures and safety rules, which can then be provided to workers. This allows workers to check their understanding and study efficiently.

[0140] Example prompt sentence:

[0141] Input the manual contents and use the AI ​​model to generate a quiz based on work procedures and safety rules. Use multiple choice questions for the quiz questions, and output the generated quiz questions and options.

[0142] Learning materials: [Manual content text]

[0143] The hardware used includes industrial robots, user terminals, and servers, while the software includes AI models using Python language and natural language processing technology.

[0144] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0145] Step 1:

[0146] Users prepare learning materials on their devices and upload them to the learning platform, using educational content in the form of PDF files, text files, slide decks, etc. Users click the "Upload" button on the platform, select the appropriate learning materials from the file selection dialog, and then press the "Submit" button.

[0147] Input: User selected learning material file.

[0148] Output: The learning material is sent to the server and stored.

[0149] Step 2:

[0150] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage (e.g., " / uploaded_materials / ").

[0151] Input: Learning material file sent from the user's device.

[0152] Output: The learning materials will be saved in the specified folder.

[0153] Step 3:

[0154] The server reads the stored learning materials and inputs them into an AI model, which uses natural language processing technology to analyze the content of the learning materials and extract key points and keywords for each chapter and section.

[0155] Input: Saved learning material file.

[0156] Data processing: Text analysis using natural language processing techniques.

[0157] Output: Key points and keywords as analysis results.

[0158] Step 4:

[0159] The server instructs the AI ​​model to generate quizzes based on the analysis results. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple-choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated.

[0160] Input: Analysis result data.

[0161] Data Computation: Question generation based on quiz generation algorithms.

[0162] Output: The generated quiz questions.

[0163] Step 5:

[0164] The generated quizzes are stored by the server in a specific folder or database (e.g. " / quizzes / " folder or database).

[0165] Input: The generated quiz questions.

[0166] Output: Saved quiz questions.

[0167] Step 6:

[0168] A user selects the "Take a Quiz" option to request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[0169] Input: The user's quiz request.

[0170] Output: The corresponding quiz question is sent to the user's device.

[0171] Step 7:

[0172] The user displays the sent quiz on the screen of the terminal and answers each question. When all questions have been answered, the user presses the "Submit Answers" button.

[0173] Input: Quiz questions and user answers.

[0174] Output: The user's answer is sent to the server.

[0175] Step 8:

[0176] The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0177] Input: The user's answer.

[0178] Data calculation: determining whether an answer is correct or incorrect and calculating scores.

[0179] Output: Total score.

[0180] Step 9:

[0181] The server generates and provides feedback to the user based on the results, including detailed comments on the level of understanding and areas for improvement for a particular chapter.

[0182] Input: Overall score and comprehension assessment data.

[0183] Data processing: Comment generation using a feedback generation algorithm.

[0184] Output: Feedback for the user.

[0185] The above are the specific processing steps of the system that realizes the application example.

[0186] 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.

[0187] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[0188] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. To do this, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0189] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server then inputs the saved learning materials into the AI ​​model to prepare for analysis.

[0190] The server inputs the stored learning materials into the AI ​​model, which then uses natural language processing techniques to analyze the content of the learning materials, including extracting key points and keywords from each chapter or section of the learning materials.

[0191] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0192] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[0193] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[0194] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[0195] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[0196] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[0197] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[0198] The processing flow will be explained below.

[0199] Step 1:

[0200] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[0201] Step 2:

[0202] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[0203] Step 3:

[0204] The server receives the learning materials sent from the user's device and stores them in the " / uploaded_materials / " folder. The server properly manages the naming and storage location of the files.

[0205] Step 4:

[0206] The server reads the stored learning material and prepares it as input data for the artificial intelligence model.

[0207] Step 5:

[0208] The AI ​​model receives input data from the server and analyzes the learning material. The model uses natural language processing techniques to extract key points and keywords for each chapter or section of the learning material.

[0209] Step 6:

[0210] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[0211] Step 7:

[0212] The AI ​​model generates quiz questions based on the analysis results. For example, in the "Chapter on Business Ethics," it generates questions such as "What is business ethics?" and "What are the key elements of business ethics?"

[0213] Step 8:

[0214] The server saves the generated quiz in the " / quizzes / " folder or in a database, which ensures that the generated quiz is kept for future use.

[0215] Step 9:

[0216] A user selects the "Take Quiz" option on a learning platform, requesting a quiz based on a specific learning module or topic.

[0217] Step 10:

[0218] Upon receiving a user request, the server reads the relevant quiz from the " / quizzes / " folder and sends it to the user's device.

[0219] Step 11:

[0220] While the device is running the quiz, it uses its built-in camera and microphone to transmit the user's facial expressions and tone of voice to the emotion engine, which then analyzes the information and evaluates the user's current emotional state.

[0221] Step 12:

[0222] The server receives data on the user's emotional state and adjusts the difficulty of the quiz and the type of questions in real time. For example, if the user is feeling stressed, the server will lower the difficulty of the questions or display encouraging messages.

[0223] Step 13:

[0224] The user answers the quiz on the device by selecting or writing for each question, and when all questions have been answered, they press the "Submit Answers" button.

[0225] Step 14:

[0226] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each quiz question.

[0227] Step 15:

[0228] The server again analyzes the user's emotional state while answering the quiz and generates feedback based on the results, including positive feedback and encouraging comments if the user is feeling stressed.

[0229] Step 16:

[0230] The server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to check the feedback and use it to improve their learning.

[0231] Example 2

[0232] 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."

[0233] Conventional learning systems often provide uniform quizzes and feedback, making it difficult to fully utilize users' learning effects. Furthermore, they lack the ability to monitor the user's emotional state and adjust the learning content accordingly, resulting in reduced learning efficiency and motivation. To address this issue, it is necessary to monitor the user's emotional state in real time and adjust the difficulty and format of the quiz based on that state to achieve more effective learning.

[0234] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0235] In this invention, the server includes means for inputting learning materials, means for using an artificial intelligence model to analyze the input learning materials, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for providing the saved quizzes, means for receiving answers to the quizzes and generating feedback, means for monitoring the emotional state of the user and analyzing the emotional data, means for adjusting the difficulty and format of the quiz based on the emotional data, and means for generating feedback in accordance with the emotional state of the user, thereby enabling flexible learning support that takes the user's emotional state into consideration.

[0236] "Learning materials" refers to data such as teaching materials and documents that users use for learning purposes.

[0237] "Input means" refers to devices or programs that provide the functionality for incorporating learning materials into the system.

[0238] An "analytical artificial intelligence model" refers to an algorithm that understands the content of input learning material and extracts important points and keywords.

[0239] "Quiz generating means" refers to a function or device that automatically creates appropriate quiz questions (multiple choice questions, written questions, etc.) based on the analysis results.

[0240] "Storage means" refers to a device or program for storing the generated quiz in a digital storage device or database.

[0241] The "means for providing" refers to a function or device that presents the saved quiz to the user.

[0242] The "means for receiving answers and generating feedback" refers to a function for receiving the results of a user's answers to a quiz and creating evaluations and comments for improvement based on the results.

[0243] "Means for monitoring emotional states and analyzing emotional data" refers to algorithms or devices that use sensors such as cameras and microphones to monitor a user's facial expressions and voice in real time and evaluate their emotions.

[0244] "Means for adjusting the difficulty and format of quizzes based on emotional data" refers to a function that changes the content of the quiz according to the user's emotional state, providing an optimal learning experience.

[0245] "Means for generating feedback according to the user's emotional state" refers to a device or program that appropriately generates comments to alleviate stress, encouraging messages, etc., based on the user's emotional state.

[0246] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[0247] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0248] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in its storage. The server then inputs the saved learning materials into the AI ​​model, preparing it for analysis.

[0249] The server inputs the learning material into an AI model, which then uses natural language processing techniques to analyze the content of the learning material, including extracting key points and keywords from each chapter or section of the material.

[0250] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0251] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[0252] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[0253] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[0254] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[0255] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[0256] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[0257] Example prompts to input to a generative AI model:

[0258] "Upload a PDF file on business ethics. Based on this material, please generate multiple-choice and essay questions. Include key points and keywords."

[0259] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0260] Step 1:

[0261] The user prepares the learning materials.

[0262] The user uses a device to prepare the learning materials (PDF files, text files, slides, etc.) required for learning. These learning materials are used as input. The output is the prepared learning materials. Specifically, the user collects learning materials from folders on the device or from cloud storage.

[0263] Step 2:

[0264] Users upload learning materials.

[0265] The user accesses the learning platform using a terminal and clicks the "Upload" button. A file selection dialog appears, and the user selects the learning material. Then, the user presses the "Send" button. The input of this operation is the prepared learning material, and the output is the learning material sent to the server. In concrete terms, the user selects the learning material file and uploads it to the platform.

[0266] Step 3:

[0267] The server receives and stores the learning materials.

[0268] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The input is the learning materials sent to the server, and the output is the saved learning materials. Specifically, the server writes the files to a specific folder.

[0269] Step 4:

[0270] The server prepares to analyze the learning material.

[0271] The server prepares the saved learning material for input into the AI ​​model. It checks the file path and format and converts it into the appropriate format. The input is the saved learning material, and the output is data in a format suitable for analysis. Specifically, the server obtains the file path and formats the data as needed.

[0272] Step 5:

[0273] An artificial intelligence model analyzes the learning material.

[0274] The server inputs learning materials into the AI ​​model. The model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords. The input is data in a format suitable for analysis, and the output is the extracted points and keywords. Specifically, the AI ​​model performs text analysis and extracts important information.

[0275] Step 6:

[0276] The server instructs the artificial intelligence model to generate the quiz.

[0277] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The input is the extracted points and keywords, and the output is the generated quiz questions. Specifically, the server sends the analysis results to the model and provides prompts for quiz generation.

[0278] Step 7:

[0279] An artificial intelligence model generates the quiz.

[0280] Based on the analysis results, the AI ​​model automatically generates quizzes such as multiple choice and written questions. The server saves the generated quizzes in the " / quizzes / " folder or in a database. The input is the quiz generation prompt and the analysis results, and the output is the generated quiz questions. Specifically, the model generates quizzes in an appropriate question format, and the server performs the save operation.

[0281] Step 8:

[0282] The user takes the quiz.

[0283] A user accesses the learning platform on their device and selects the "Take a Quiz" option. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device. The input is a request to take the quiz, and the output is the quiz questions that are displayed on the user's device. Specifically, the user selects a quiz, and the server sends the quiz questions to the device.

[0284] Step 9:

[0285] The terminal monitors the user's emotional state.

[0286] The device uses a camera and microphone to monitor the user's facial expressions and voice in real time. This emotional data is sent to the emotion engine for analysis. The input is the user's real-time facial expressions and voice, and the output is the analyzed emotional data. Specifically, the device's sensors operate, and the emotion engine analyzes the data.

[0287] Step 10:

[0288] The server receives the emotion data and adjusts the quiz.

[0289] The server receives the analyzed emotional data and adjusts the difficulty and format of the quiz according to the user's emotional state. The input is the emotional data, and the output is the adjusted quiz questions. Specifically, the server changes the difficulty parameters of the quiz based on the emotional data.

[0290] Step 11:

[0291] The user answers the quiz.

[0292] The user answers the quiz displayed on the terminal. Once all questions have been answered, the user presses the "Submit Answers" button. The input is the user's answer data, and the output is the answer sent to the server. Specifically, the user selects an answer and performs the submit operation.

[0293] Step 12:

[0294] The server evaluates the quiz answers.

[0295] The server receives the answers sent by the user and evaluates whether they are correct or incorrect. It then calculates the score for each quiz question. The input is the user's answer data, and the output is the evaluation result and score. Specifically, the server analyzes the answer data and calculates the score.

[0296] Step 13:

[0297] The server analyzes the emotional data and generates feedback.

[0298] The server again analyzes the user's emotional state and generates feedback based on the results. For example, if the user is feeling stressed, it generates positive feedback or encouraging comments. It also provides specific comments about the user's level of understanding and areas for improvement. The input is the emotional data during the quiz answer, and the output is the generated feedback. Specifically, the server analyzes the emotional data and creates feedback comments.

[0299] Step 14:

[0300] The server sends feedback.

[0301] The server sends the generated feedback to the user's terminal and displays it on the screen. The input is the generated feedback, and the output is the feedback displayed on the user's terminal. In concrete terms, the server transfers the feedback data to the user's terminal, and the terminal displays it.

[0302] (Application example 2)

[0303] 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."

[0304] Conventional learning systems provide quizzes with a uniform level of difficulty and format without considering the learner's emotional state, resulting in poor learning efficiency. Furthermore, when autonomous vehicle engineers learn new technologies, there is a lack of a way to analyze individual levels of understanding and concentration in real time and provide appropriate feedback accordingly. There is a need to solve these issues and realize more effective learning support.

[0305] 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 a means for inputting learning materials, a means for using an artificial intelligence model to analyze the input learning materials, a means for generating quizzes based on the analysis results, a means for saving the generated quizzes, a means for providing the saved quizzes, a means for receiving answers to the quizzes and generating feedback, and a means for monitoring the user's emotional state and adjusting the difficulty and format of the quiz. This makes it possible to provide quizzes with the optimal difficulty and format according to the learner's emotional state, thereby realizing efficient learning support tailored to each learner. Furthermore, automated vehicle engineers can also receive appropriate feedback through real-time emotion analysis, improving the efficiency of their technical acquisition.

[0306] "Learning materials" refers to teaching materials used in education and training, including PDF files, text files, slides, etc.

[0307] An "artificial intelligence model" is an algorithm or program that can analyze data using techniques such as machine learning and deep learning to perform specific tasks.

[0308] A "quiz" is an assessment tool in the form of questions generated based on learning materials, and can take the form of multiple choice questions or essay questions.

[0309] "Emotional state" refers to data that represents the user's current emotions, including those acquired in real time through facial expressions, voice, etc.

[0310] "Feedback" refers to advice or comments provided based on the evaluation of the user's answers to the quiz.

[0311] "Difficulty" refers to the level that indicates how difficult it is to answer a quiz or assignment.

[0312] "Real-time monitoring" refers to tracking the user's situation in real time and acquiring and analyzing data.

[0313] "Analysis" refers to the process of breaking down learning materials and user data and extracting important elements and patterns.

[0314] "Storage" refers to storing data and generated quizzes in storage so that they can be accessed later.

[0315] "Providing" refers to sending and making accessible the saved quiz and feedback to the user.

[0316] "Monitoring" refers to the process of continuously observing and collecting data about a user's behavior and state.

[0317] The present invention relates to a training system for assisting learning about autonomous vehicles. Specific embodiments of the present invention will be described below.

[0318] Hardware and software used

[0319] 1. Hardware:

[0320] Smartphones, smart glasses, head-mounted displays (hereinafter referred to as "devices")

[0321] Terminal devices with a camera and microphone

[0322] server

[0323] 2. Software:

[0324] Python (data analysis and model execution)

[0325] TensorFlow / PyTorch (training and running artificial intelligence models)

[0326] OpenCV (camera image analysis)

[0327] NLTK / spaCy (Natural Language Processing)

[0328] Flask / Django (Web application framework)

[0329] Data processing and calculation

[0330] The server first receives and stores the learning materials (PDF files, text files, slides, etc.) sent from the device. It then analyzes the stored learning materials using natural language processing technology to extract key points and keywords. Based on the results of this analysis, an artificial intelligence model automatically generates quizzes, including multiple-choice and written questions.

[0331] The generated quiz is stored in a database in the server. When the user selects the "Take Quiz" option, the server sends the corresponding quiz to the terminal.

[0332] While answering the quiz, the device monitors the user's facial expressions and voice in real time through a camera and microphone. This data is analyzed using OpenCV and an emotion analysis model, and data corresponding to the user's emotional state is sent to the server.

[0333] The server adjusts the difficulty and format of the quiz based on the received emotional data, and after the quiz is completed, generates feedback based on the analysis results and sends it to the device.

[0334] Specific examples

[0335] For example, consider a company engineer who wants to learn about a new control algorithm for autonomous vehicles. The engineer uploads a PDF study guide about the control algorithm for autonomous vehicles to the app. The server analyzes the study guide and generates quiz questions such as, "How does the control algorithm for autonomous vehicles work?" and "What are the main risks?"

[0336] As the technician answers the quiz, the technician's facial expressions and voice are monitored through a camera and microphone, and the difficulty of the quiz is adjusted in real time based on the analyzed emotional data, allowing the technician to learn efficiently.

[0337] Example of input prompt for generative AI model:

[0338] Based on the learning material on the theme "Discuss the risks associated with the safety of autonomous vehicles," a quiz was generated in the following format:

[0339] 1. Multiple choice questions:

[0340] 2. Essay questions: 0 questions

[0341] Here is an example of a multiple choice question:

[0342] 1. What are the biggest risks with self-driving vehicles?

[0343] a) Energy efficiency

[0344] b) Sensor failure

[0345] c) Ignoring traffic signals

[0346] Through the above process, a flexible and efficient training system is provided to maximize the learning effect of users.

[0347] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0348] Step 1:

[0349] Users upload learning materials to their devices by selecting PDF files, text files, slide decks, etc., and clicking the "Upload" button in the application. The selected files are then sent to the learning platform.

[0350] Step 2:

[0351] The server receives the learning materials sent from the device. The received files are saved in the " / uploaded_materials / " folder on the server. This saving is done as a preparation for analyzing the learning materials.

[0352] Step 3:

[0353] The server analyzes the stored learning materials using natural language processing technology. Specifically, it uses Python and NLTK or spaCy to extract important points and keywords from the content of the learning materials. This analysis clarifies the main points of the learning materials.

[0354] Step 4:

[0355] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The generative AI model (built with TensorFlow / PyTorch) automatically generates quizzes in the form of multiple choice or essay questions based on the analyzed data. This process creates questions that are in line with the content of the learning material.

[0356] Step 5:

[0357] The generated quizzes are saved in the " / quizzes / " folder on the server or in a database, where they are recorded for later access by users.

[0358] Step 6:

[0359] When a user selects the "Take Quiz" option, the server sends the saved quiz to the device. The user selects a specific learning module or topic and sends a request to the server, which delivers the corresponding quiz to the device.

[0360] Step 7:

[0361] While answering the quiz, the device monitors the user's facial expressions and voice in real time using a camera and microphone. The acquired data is analyzed using OpenCV and an emotion analysis model to determine the user's emotional state. This emotion data is sent to the server while answering the quiz.

[0362] Step 8:

[0363] The server then adjusts the difficulty and format of the quiz based on the received emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or change the format. This adjustment allows the user to learn more effectively.

[0364] Step 9:

[0365] When the user has finished answering the quiz, he / she presses the "Submit Answers" button. The server receives the user's answers and automatically evaluates them, determining whether they are correct or incorrect and calculating the score for each quiz question.

[0366] Step 10:

[0367] The server generates feedback based on the evaluation results and sentiment analysis data. For example, if the user is feeling stressed, the server will provide positive feedback and specific advice, allowing the user to clearly identify areas for improvement.

[0368] Step 11:

[0369] Finally, the server sends the generated feedback to the device. The feedback is displayed on the user's screen and can be used to improve their learning. The analysis results and feedback are also recorded as the user's learning history.

[0370] 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.

[0371] 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.

[0372] 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.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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."

[0386] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[0387] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0388] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an artificial intelligence model.

[0389] The server reads the stored learning materials and inputs them into an AI model, which then uses natural language processing techniques to analyze the content of the learning materials. This analysis involves extracting key points and keywords for each chapter or section of the learning materials.

[0390] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0391] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[0392] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0393] Finally, the server generates and provides the user with feedback based on the results, including detailed comments on the user's understanding of a particular chapter and areas for improvement.

[0394] As a concrete example, let's take corporate training materials. A user uploads a PDF document on business ethics. The server analyzes the content and generates quiz questions such as "What is business ethics?" and "What are the important elements of business ethics?". The user answers these questions and receives feedback based on their answers. This allows the user to study efficiently and improve their understanding.

[0395] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0396] The processing flow will be explained below.

[0397] Step 1:

[0398] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[0399] Step 2:

[0400] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[0401] Step 3:

[0402] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server properly manages the naming and storage location of the files.

[0403] Step 4:

[0404] The server reads the stored learning material and prepares it as data to input into the artificial intelligence model.

[0405] Step 5:

[0406] The AI ​​model receives input data from the server and analyzes the learning material. Using natural language processing technology, the model analyzes the content of the learning material by chapter and section, extracting key points and keywords.

[0407] Step 6:

[0408] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[0409] Step 7:

[0410] The AI ​​model generates quiz questions based on the analysis results, automatically generating multiple-choice and essay-style questions.

[0411] Step 8:

[0412] The server stores the generated quizzes in a database or in the " / quizzes / " folder, which ensures that the generated quizzes are kept for future use.

[0413] Step 9:

[0414] A user selects the "Take Quiz" option on the learning platform and requests a quiz based on a particular learning module or topic.

[0415] Step 10:

[0416] Upon receiving a user request, the server reads the corresponding quiz from the " / quizzes / " folder and sends the quiz to the user's terminal.

[0417] Step 11:

[0418] The user answers the quiz received on the terminal by selecting or writing a question and pressing the "Submit Answer" button.

[0419] Step 12:

[0420] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each question, as well as a total score.

[0421] Step 13:

[0422] The server generates feedback based on the user's answers, such as detailed feedback comments that include the user's level of understanding and areas for improvement.

[0423] Step 14:

[0424] The server sends the generated feedback to the user's device and displays it on the user's screen, where the user can check the feedback and use it to improve their learning.

[0425] Example 1

[0426] 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."

[0427] In today's educational environment, there is a demand for systems that can efficiently assess learning progress based on individual learning materials. However, in conventional systems, the analysis of learning materials and the generation of quizzes appropriate to the content are often done manually, which often leads to inefficient or inaccurate assessments. Another problem is the lack of a mechanism for properly providing the created quizzes to users and providing appropriate feedback based on their answers.

[0428] 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.

[0429] In this invention, the server includes means for preparing learning materials, means for inputting learning materials and uploading them to the learning platform, means for receiving and saving the uploaded learning materials, means for inputting the saved learning materials into an artificial intelligence model and analyzing them using natural language processing technology, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for receiving quiz requests from users and providing the saved quizzes, means for receiving answers to the quizzes and automatically evaluating and calculating scores, and means for generating and providing feedback based on the evaluation results. This enables efficient operations from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0430] "Learning Materials" means educational content, including formats such as PDF files, text files, and slide decks.

[0431] "Learning Platform" means a software environment that allows users to upload, manage, and use learning materials.

[0432] "Saving" means storing the received data in a specific folder or database on the server.

[0433] An "artificial intelligence model" is a system that uses programmed algorithms and machine learning techniques to analyze data and generate knowledge.

[0434] "Analyzing" means analyzing the content of the learning material using natural language processing technology and extracting important points and keywords.

[0435] A "quiz" is a set of questions created to assess a user's level of understanding, and includes multiple choice questions and written questions.

[0436] "Generating" means creating new quiz questions based on the analysis results.

[0437] "Providing" means distributing the generated quiz to users and making it available for use.

[0438] "Evaluating" means scoring the user's answers to the quiz and determining whether they are correct or incorrect.

[0439] The "score" is the score given to the user for the quiz answer, and is a numerical value that indicates the overall level of understanding.

[0440] "Feedback" refers to detailed comments and improvements on the evaluation results provided to the user.

[0441] MODE FOR CARRYING OUT THE INVENTION

[0442] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. The series of processes in this system are particularly configured as follows:

[0443] First, the user prepares learning materials using their device. These learning materials include educational content in various formats, such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0444] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an AI model. Specifically, the server reads the saved learning materials and inputs them into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials. This analysis involves extracting important points and keywords for each chapter and section of the learning materials.

[0445] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0446] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[0447] The user displays the submitted quiz on the screen and answers each question. Once all questions have been answered, the user presses the "Submit Answers" button. The server then receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the overall score. Feedback based on the results is then generated and provided to the user. For example, detailed comments about the user's understanding of a particular chapter and areas for improvement are displayed to the user.

[0448] As a concrete example, taking corporate training materials as an example, users upload PDF materials on "business ethics." The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" Users answer these quizzes and receive feedback based on their answers. This allows users to study efficiently and improve their understanding.

[0449] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0450] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0451] Step 1:

[0452] The user prepares learning materials using a terminal. The learning materials can be in the form of PDF files, text files, slides, etc. The user logs in to the learning platform and clicks the "Upload" button. The user selects the learning materials from the file selection dialog and presses the "Send" button. The terminal divides the selected learning materials into packet data and sends them to the server. The input learning materials are processed as data to be sent from the terminal to the server. Packet data is generated as output.

[0453] Step 2:

[0454] The server receives packet data sent from the terminal. It reconstructs the packet data to generate a complete learning material file. It saves this data in the " / uploaded_materials / " folder in storage. For example, it saves it as " / uploaded_materials / material1.pdf". As input, it receives packet data from the terminal and creates a complete file through data reconstruction. As output, it saves the complete learning material file.

[0455] Step 3:

[0456] The server reads the stored learning materials. The learning material files are input into an AI model, and the content is analyzed using natural language processing technology. The analysis involves extracting key points and keywords for each chapter and section of the learning material. The learning material files are provided to the AI ​​model as input. Data processing involves analysis using natural language processing. The output is the key points and keywords obtained as the analysis results.

[0457] Step 4:

[0458] The server instructs the AI ​​model to generate a quiz based on the analysis results. The AI ​​model generates quiz questions in the form of multiple choice or written questions based on the extracted points and keywords. The generated quizzes are saved in the " / quizzes / " folder or in a database. The analysis results are used as input as basic data for quiz generation. Quiz questions are generated as data calculations. A quiz file is saved as output.

[0459] Step 5:

[0460] A user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. The device sends the user's request to the server. As input, the user's request information is sent to the server. As output, the request data is generated.

[0461] Step 6:

[0462] The server receives a user request, reads the corresponding quiz file from the " / quizzes / " folder, and sends the read quiz to the user's device. As input, the target quiz file based on the user request is searched and read. As output, the quiz file is delivered.

[0463] Step 7:

[0464] The user answers the quiz displayed on the device. For each question, they click on the answer option or enter a written response. After answering all questions, they press the "Submit Answers" button. The user's answer data is sent from the device to the server as input. The answer data is generated as output.

[0465] Step 8:

[0466] The server receives the user's answers. It automatically evaluates whether they are correct or incorrect using an artificial intelligence model. It calculates the score for each question and calculates the overall score. It generates detailed feedback based on the results and provides it to the user. As input, the user's answer data is evaluated. As data calculations, it determines whether they are correct or incorrect and calculates the score. As output, the generated feedback is provided to the user.

[0467] (Application example 1)

[0468] 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."

[0469] In modern industrial settings, it is important for workers to thoroughly understand work procedures and safety rules in order to perform their work accurately and safely. However, traditional methods often rely on text-based manuals, which can lead to inconsistent levels of understanding. Furthermore, manually creating quizzes and tests to assess work comprehension is time-consuming and laborious, so efficient training methods are needed.

[0470] 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.

[0471] In this invention, the server includes a means for inputting learning materials, a means for using an AI model to analyze the input learning materials, a means for generating quizzes based on the analysis results, and a means for saving the generated quizzes. This allows the server to be installed on an industrial robot and automatically generate quizzes based on work procedures and safety rules, and provide them to workers. As a result, safe and effective work training can be achieved by efficiently evaluating the worker's level of understanding and providing appropriate feedback.

[0472] "Learning materials" are materials containing educational content, such as PDF files, text files, and slide decks.

[0473] An "artificial intelligence model" is an algorithm or software that can analyze text data using natural language processing technology and extract important points and keywords.

[0474] A "quiz" is a question generated to assess the level of understanding of learning material, and may take the form of multiple choice or essay questions.

[0475] "Means for saving" refers to the function for storing the analysis results and generated quizzes in a database or file system.

[0476] "Means for providing" refers to the functionality of sending and receiving data via a user interface to display saved quizzes to a user and accept answers.

[0477] "Means for generating feedback" refers to a function that determines whether a user's answers are correct or incorrect based on the user's quiz answers, and generates detailed comments and scores to notify the user.

[0478] An "industrial robot" is a robotic device used in factories to assist with work and train workers.

[0479] A "work procedure" is a method or step for properly and efficiently performing a specific task in an industrial setting.

[0480] "Safety rules" refer to the guidelines and protocols that must be followed when working within a factory, and are rules necessary to ensure safety.

[0481] A "worker" is an employee who operates machinery and equipment at an industrial site and performs specific tasks.

[0482] The present invention is a system that is installed on an industrial robot, inputs learning materials, and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[0483] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0484] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage. The saved learning materials are then analyzed by an AI model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords.

[0485] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated. The generated quizzes are saved in a specific folder or database by the server.

[0486] When a user wants to take a quiz, they select the "Take Quiz" option on the learning platform. They request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[0487] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0488] Finally, the server generates and provides feedback based on the results to the user, including detailed comments on the level of understanding and areas for improvement for a particular chapter, allowing the user to study efficiently and improve their comprehension.

[0489] As a specific example, an industrial robot can upload a work procedure manual in PDF format, and the robot will analyze the uploaded manual content and generate quizzes based on important procedures and safety rules, which can then be provided to workers. This allows workers to check their understanding and study efficiently.

[0490] Example prompt sentence:

[0491] Input the manual contents and use the AI ​​model to generate a quiz based on work procedures and safety rules. Use multiple choice questions for the quiz questions, and output the generated quiz questions and options.

[0492] Learning materials: [Manual content text]

[0493] The hardware used includes industrial robots, user terminals, and servers, while the software includes AI models using Python language and natural language processing technology.

[0494] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0495] Step 1:

[0496] Users prepare learning materials on their devices and upload them to the learning platform, using educational content in the form of PDF files, text files, slide decks, etc. Users click the "Upload" button on the platform, select the appropriate learning materials from the file selection dialog, and then press the "Submit" button.

[0497] Input: User selected learning material file.

[0498] Output: The learning material is sent to the server and stored.

[0499] Step 2:

[0500] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage (e.g., " / uploaded_materials / ").

[0501] Input: Learning material file sent from the user's device.

[0502] Output: The learning materials will be saved in the specified folder.

[0503] Step 3:

[0504] The server reads the stored learning materials and inputs them into an AI model, which uses natural language processing technology to analyze the content of the learning materials and extract key points and keywords for each chapter and section.

[0505] Input: Saved learning material file.

[0506] Data processing: Text analysis using natural language processing techniques.

[0507] Output: Key points and keywords as analysis results.

[0508] Step 4:

[0509] The server instructs the AI ​​model to generate quizzes based on the analysis results. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple-choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated.

[0510] Input: Analysis result data.

[0511] Data Computation: Question generation based on quiz generation algorithms.

[0512] Output: The generated quiz questions.

[0513] Step 5:

[0514] The generated quizzes are stored by the server in a specific folder or database (e.g. " / quizzes / " folder or database).

[0515] Input: The generated quiz questions.

[0516] Output: Saved quiz questions.

[0517] Step 6:

[0518] A user selects the "Take a Quiz" option to request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[0519] Input: The user's quiz request.

[0520] Output: The corresponding quiz question is sent to the user's device.

[0521] Step 7:

[0522] The user displays the sent quiz on the screen of the terminal and answers each question. When all questions have been answered, the user presses the "Submit Answers" button.

[0523] Input: Quiz questions and user answers.

[0524] Output: The user's answer is sent to the server.

[0525] Step 8:

[0526] The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0527] Input: The user's answer.

[0528] Data calculation: determining whether an answer is correct or incorrect and calculating scores.

[0529] Output: Total score.

[0530] Step 9:

[0531] The server generates and provides feedback to the user based on the results, including detailed comments on the level of understanding and areas for improvement for a particular chapter.

[0532] Input: Overall score and comprehension assessment data.

[0533] Data processing: Comment generation using a feedback generation algorithm.

[0534] Output: Feedback for the user.

[0535] The above are the specific processing steps of the system that realizes the application example.

[0536] 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.

[0537] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[0538] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. To do this, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0539] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server then inputs the saved learning materials into the AI ​​model to prepare for analysis.

[0540] The server inputs the stored learning materials into the AI ​​model, which then uses natural language processing techniques to analyze the content of the learning materials, including extracting key points and keywords from each chapter or section of the learning materials.

[0541] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0542] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[0543] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[0544] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[0545] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[0546] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[0547] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[0548] The processing flow will be explained below.

[0549] Step 1:

[0550] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[0551] Step 2:

[0552] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[0553] Step 3:

[0554] The server receives the learning materials sent from the user's device and stores them in the " / uploaded_materials / " folder. The server properly manages the naming and storage location of the files.

[0555] Step 4:

[0556] The server reads the stored learning material and prepares it as input data for the artificial intelligence model.

[0557] Step 5:

[0558] The AI ​​model receives input data from the server and analyzes the learning material. The model uses natural language processing techniques to extract key points and keywords for each chapter or section of the learning material.

[0559] Step 6:

[0560] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[0561] Step 7:

[0562] The AI ​​model generates quiz questions based on the analysis results. For example, in the "Chapter on Business Ethics," it generates questions such as "What is business ethics?" and "What are the key elements of business ethics?"

[0563] Step 8:

[0564] The server saves the generated quiz in the " / quizzes / " folder or in a database, which ensures that the generated quiz is kept for future use.

[0565] Step 9:

[0566] A user selects the "Take Quiz" option on a learning platform, requesting a quiz based on a specific learning module or topic.

[0567] Step 10:

[0568] Upon receiving a user request, the server reads the relevant quiz from the " / quizzes / " folder and sends it to the user's device.

[0569] Step 11:

[0570] While the device is running the quiz, it uses its built-in camera and microphone to transmit the user's facial expressions and tone of voice to the emotion engine, which then analyzes the information and evaluates the user's current emotional state.

[0571] Step 12:

[0572] The server receives data on the user's emotional state and adjusts the difficulty of the quiz and the type of questions in real time. For example, if the user is feeling stressed, the server will lower the difficulty of the questions or display encouraging messages.

[0573] Step 13:

[0574] The user answers the quiz on the device by selecting or writing for each question, and when all questions have been answered, they press the "Submit Answers" button.

[0575] Step 14:

[0576] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each quiz question.

[0577] Step 15:

[0578] The server again analyzes the user's emotional state while answering the quiz and generates feedback based on the results, including positive feedback and encouraging comments if the user is feeling stressed.

[0579] Step 16:

[0580] The server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to check the feedback and use it to improve their learning.

[0581] Example 2

[0582] 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."

[0583] Conventional learning systems often provide uniform quizzes and feedback, making it difficult to fully utilize users' learning effects. Furthermore, they lack the ability to monitor the user's emotional state and adjust the learning content accordingly, resulting in reduced learning efficiency and motivation. To address this issue, it is necessary to monitor the user's emotional state in real time and adjust the difficulty and format of the quiz based on that state to achieve more effective learning.

[0584] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0585] In this invention, the server includes means for inputting learning materials, means for using an artificial intelligence model to analyze the input learning materials, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for providing the saved quizzes, means for receiving answers to the quizzes and generating feedback, means for monitoring the emotional state of the user and analyzing the emotional data, means for adjusting the difficulty and format of the quiz based on the emotional data, and means for generating feedback in accordance with the emotional state of the user, thereby enabling flexible learning support that takes the user's emotional state into consideration.

[0586] "Learning materials" refers to data such as teaching materials and documents that users use for learning purposes.

[0587] "Input means" refers to devices or programs that provide the functionality for incorporating learning materials into the system.

[0588] An "analytical artificial intelligence model" refers to an algorithm that understands the content of input learning material and extracts important points and keywords.

[0589] "Quiz generating means" refers to a function or device that automatically creates appropriate quiz questions (multiple choice questions, written questions, etc.) based on the analysis results.

[0590] "Storage means" refers to a device or program for storing the generated quiz in a digital storage device or database.

[0591] The "means for providing" refers to a function or device that presents the saved quiz to the user.

[0592] The "means for receiving answers and generating feedback" refers to a function for receiving the results of a user's answers to a quiz and creating evaluations and comments for improvement based on the results.

[0593] "Means for monitoring emotional states and analyzing emotional data" refers to algorithms or devices that use sensors such as cameras and microphones to monitor a user's facial expressions and voice in real time and evaluate their emotions.

[0594] "Means for adjusting the difficulty and format of quizzes based on emotional data" refers to a function that changes the content of the quiz according to the user's emotional state, providing an optimal learning experience.

[0595] "Means for generating feedback according to the user's emotional state" refers to a device or program that appropriately generates comments to alleviate stress, encouraging messages, etc., based on the user's emotional state.

[0596] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[0597] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0598] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in its storage. The server then inputs the saved learning materials into the AI ​​model, preparing it for analysis.

[0599] The server inputs the learning material into an AI model, which then uses natural language processing techniques to analyze the content of the learning material, including extracting key points and keywords from each chapter or section of the material.

[0600] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0601] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[0602] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[0603] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[0604] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[0605] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[0606] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[0607] Example prompts to input to a generative AI model:

[0608] "Upload a PDF file on business ethics. Based on this material, please generate multiple-choice and essay questions. Include key points and keywords."

[0609] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0610] Step 1:

[0611] The user prepares the learning materials.

[0612] The user uses a device to prepare the learning materials (PDF files, text files, slides, etc.) required for learning. These learning materials are used as input. The output is the prepared learning materials. Specifically, the user collects learning materials from folders on the device or from cloud storage.

[0613] Step 2:

[0614] Users upload learning materials.

[0615] The user accesses the learning platform using a terminal and clicks the "Upload" button. A file selection dialog appears, and the user selects the learning material. Then, the user presses the "Send" button. The input of this operation is the prepared learning material, and the output is the learning material sent to the server. In concrete terms, the user selects the learning material file and uploads it to the platform.

[0616] Step 3:

[0617] The server receives and stores the learning materials.

[0618] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The input is the learning materials sent to the server, and the output is the saved learning materials. Specifically, the server writes the files to a specific folder.

[0619] Step 4:

[0620] The server prepares to analyze the learning material.

[0621] The server prepares the saved learning material for input into the AI ​​model. It checks the file path and format and converts it into the appropriate format. The input is the saved learning material, and the output is data in a format suitable for analysis. Specifically, the server obtains the file path and formats the data as needed.

[0622] Step 5:

[0623] An artificial intelligence model analyzes the learning material.

[0624] The server inputs learning materials into the AI ​​model. The model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords. The input is data in a format suitable for analysis, and the output is the extracted points and keywords. Specifically, the AI ​​model performs text analysis and extracts important information.

[0625] Step 6:

[0626] The server instructs the artificial intelligence model to generate the quiz.

[0627] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The input is the extracted points and keywords, and the output is the generated quiz questions. Specifically, the server sends the analysis results to the model and provides prompts for quiz generation.

[0628] Step 7:

[0629] An artificial intelligence model generates the quiz.

[0630] Based on the analysis results, the AI ​​model automatically generates quizzes such as multiple choice and written questions. The server saves the generated quizzes in the " / quizzes / " folder or in a database. The input is the quiz generation prompt and the analysis results, and the output is the generated quiz questions. Specifically, the model generates quizzes in an appropriate question format, and the server performs the save operation.

[0631] Step 8:

[0632] The user takes the quiz.

[0633] A user accesses the learning platform on their device and selects the "Take a Quiz" option. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device. The input is a request to take the quiz, and the output is the quiz questions that are displayed on the user's device. Specifically, the user selects a quiz, and the server sends the quiz questions to the device.

[0634] Step 9:

[0635] The terminal monitors the user's emotional state.

[0636] The device uses a camera and microphone to monitor the user's facial expressions and voice in real time. This emotional data is sent to the emotion engine for analysis. The input is the user's real-time facial expressions and voice, and the output is the analyzed emotional data. Specifically, the device's sensors operate, and the emotion engine analyzes the data.

[0637] Step 10:

[0638] The server receives the emotion data and adjusts the quiz.

[0639] The server receives the analyzed emotional data and adjusts the difficulty and format of the quiz according to the user's emotional state. The input is the emotional data, and the output is the adjusted quiz questions. Specifically, the server changes the difficulty parameters of the quiz based on the emotional data.

[0640] Step 11:

[0641] The user answers the quiz.

[0642] The user answers the quiz displayed on the terminal. Once all questions have been answered, the user presses the "Submit Answers" button. The input is the user's answer data, and the output is the answer sent to the server. Specifically, the user selects an answer and performs the submit operation.

[0643] Step 12:

[0644] The server evaluates the quiz answers.

[0645] The server receives the answers sent by the user and evaluates whether they are correct or incorrect. It then calculates the score for each quiz question. The input is the user's answer data, and the output is the evaluation result and score. Specifically, the server analyzes the answer data and calculates the score.

[0646] Step 13:

[0647] The server analyzes the emotional data and generates feedback.

[0648] The server again analyzes the user's emotional state and generates feedback based on the results. For example, if the user is feeling stressed, it generates positive feedback or encouraging comments. It also provides specific comments about the user's level of understanding and areas for improvement. The input is the emotional data during the quiz answer, and the output is the generated feedback. Specifically, the server analyzes the emotional data and creates feedback comments.

[0649] Step 14:

[0650] The server sends feedback.

[0651] The server sends the generated feedback to the user's terminal and displays it on the screen. The input is the generated feedback, and the output is the feedback displayed on the user's terminal. In concrete terms, the server transfers the feedback data to the user's terminal, and the terminal displays it.

[0652] (Application example 2)

[0653] 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."

[0654] Conventional learning systems provide quizzes with a uniform level of difficulty and format without considering the learner's emotional state, resulting in poor learning efficiency. Furthermore, when autonomous vehicle engineers learn new technologies, there is a lack of a way to analyze individual levels of understanding and concentration in real time and provide appropriate feedback accordingly. There is a need to solve these issues and realize more effective learning support.

[0655] 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 a means for inputting learning materials, a means for using an artificial intelligence model to analyze the input learning materials, a means for generating quizzes based on the analysis results, a means for saving the generated quizzes, a means for providing the saved quizzes, a means for receiving answers to the quizzes and generating feedback, and a means for monitoring the user's emotional state and adjusting the difficulty and format of the quiz. This makes it possible to provide quizzes with the optimal difficulty and format according to the learner's emotional state, thereby realizing efficient learning support tailored to each learner. Furthermore, automated vehicle engineers can also receive appropriate feedback through real-time emotion analysis, improving the efficiency of their technical acquisition.

[0656] "Learning materials" refers to teaching materials used in education and training, including PDF files, text files, slides, etc.

[0657] An "artificial intelligence model" is an algorithm or program that can analyze data using techniques such as machine learning and deep learning to perform specific tasks.

[0658] A "quiz" is an assessment tool in the form of questions generated based on learning materials, and can take the form of multiple choice questions or essay questions.

[0659] "Emotional state" refers to data that represents the user's current emotions, including those acquired in real time through facial expressions, voice, etc.

[0660] "Feedback" refers to advice or comments provided based on the evaluation of the user's answers to the quiz.

[0661] "Difficulty" refers to the level that indicates how difficult it is to answer a quiz or assignment.

[0662] "Real-time monitoring" refers to tracking the user's situation in real time and acquiring and analyzing data.

[0663] "Analysis" refers to the process of breaking down learning materials and user data and extracting important elements and patterns.

[0664] "Storage" refers to storing data and generated quizzes in storage so that they can be accessed later.

[0665] "Providing" refers to sending and making accessible the saved quiz and feedback to the user.

[0666] "Monitoring" refers to the process of continuously observing and collecting data about a user's behavior and state.

[0667] The present invention relates to a training system for assisting learning about autonomous vehicles. Specific embodiments of the present invention will be described below.

[0668] Hardware and software used

[0669] 1. Hardware:

[0670] Smartphones, smart glasses, head-mounted displays (hereinafter referred to as "devices")

[0671] Terminal devices with a camera and microphone

[0672] server

[0673] 2. Software:

[0674] Python (data analysis and model execution)

[0675] TensorFlow / PyTorch (training and running artificial intelligence models)

[0676] OpenCV (camera image analysis)

[0677] NLTK / spaCy (Natural Language Processing)

[0678] Flask / Django (Web application framework)

[0679] Data processing and calculation

[0680] The server first receives and stores the learning materials (PDF files, text files, slides, etc.) sent from the device. It then analyzes the stored learning materials using natural language processing technology to extract key points and keywords. Based on the results of this analysis, an artificial intelligence model automatically generates quizzes, including multiple-choice and written questions.

[0681] The generated quiz is stored in a database in the server. When the user selects the "Take Quiz" option, the server sends the corresponding quiz to the terminal.

[0682] While answering the quiz, the device monitors the user's facial expressions and voice in real time through a camera and microphone. This data is analyzed using OpenCV and an emotion analysis model, and data corresponding to the user's emotional state is sent to the server.

[0683] The server adjusts the difficulty and format of the quiz based on the received emotional data, and after the quiz is completed, generates feedback based on the analysis results and sends it to the device.

[0684] Specific examples

[0685] For example, consider a company engineer who wants to learn about a new control algorithm for autonomous vehicles. The engineer uploads a PDF study guide about the control algorithm for autonomous vehicles to the app. The server analyzes the study guide and generates quiz questions such as, "How does the control algorithm for autonomous vehicles work?" and "What are the main risks?"

[0686] As the technician answers the quiz, the technician's facial expressions and voice are monitored through a camera and microphone, and the difficulty of the quiz is adjusted in real time based on the analyzed emotional data, allowing the technician to learn efficiently.

[0687] Example of input prompt for generative AI model:

[0688] Based on the learning material on the theme "Discuss the risks associated with the safety of autonomous vehicles," a quiz was generated in the following format:

[0689] 1. Multiple choice questions:

[0690] 2. Essay questions: 0 questions

[0691] Here is an example of a multiple choice question:

[0692] 1. What are the biggest risks with self-driving vehicles?

[0693] a) Energy efficiency

[0694] b) Sensor failure

[0695] c) Ignoring traffic signals

[0696] Through the above process, a flexible and efficient training system is provided to maximize the learning effect of users.

[0697] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0698] Step 1:

[0699] Users upload learning materials to their devices by selecting PDF files, text files, slide decks, etc., and clicking the "Upload" button in the application. The selected files are then sent to the learning platform.

[0700] Step 2:

[0701] The server receives the learning materials sent from the device. The received files are saved in the " / uploaded_materials / " folder on the server. This saving is done as a preparation for analyzing the learning materials.

[0702] Step 3:

[0703] The server analyzes the stored learning materials using natural language processing technology. Specifically, it uses Python and NLTK or spaCy to extract important points and keywords from the content of the learning materials. This analysis clarifies the main points of the learning materials.

[0704] Step 4:

[0705] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The generative AI model (built with TensorFlow / PyTorch) automatically generates quizzes in the form of multiple choice or essay questions based on the analyzed data. This process creates questions that are in line with the content of the learning material.

[0706] Step 5:

[0707] The generated quizzes are saved in the " / quizzes / " folder on the server or in a database, where they are recorded for later access by users.

[0708] Step 6:

[0709] When a user selects the "Take Quiz" option, the server sends the saved quiz to the device. The user selects a specific learning module or topic and sends a request to the server, which delivers the corresponding quiz to the device.

[0710] Step 7:

[0711] While answering the quiz, the device monitors the user's facial expressions and voice in real time using a camera and microphone. The acquired data is analyzed using OpenCV and an emotion analysis model to determine the user's emotional state. This emotion data is sent to the server while answering the quiz.

[0712] Step 8:

[0713] The server then adjusts the difficulty and format of the quiz based on the received emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or change the format. This adjustment allows the user to learn more effectively.

[0714] Step 9:

[0715] When the user has finished answering the quiz, he / she presses the "Submit Answers" button. The server receives the user's answers and automatically evaluates them, determining whether they are correct or incorrect and calculating the score for each quiz question.

[0716] Step 10:

[0717] The server generates feedback based on the evaluation results and sentiment analysis data. For example, if the user is feeling stressed, the server will provide positive feedback and specific advice, allowing the user to clearly identify areas for improvement.

[0718] Step 11:

[0719] Finally, the server sends the generated feedback to the device. The feedback is displayed on the user's screen and can be used to improve their learning. The analysis results and feedback are also recorded as the user's learning history.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] [Third embodiment]

[0724] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0725] 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.

[0726] 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).

[0727] 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.

[0728] 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.

[0729] 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).

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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."

[0736] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[0737] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0738] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an artificial intelligence model.

[0739] The server reads the stored learning materials and inputs them into an AI model, which then uses natural language processing techniques to analyze the content of the learning materials. This analysis involves extracting key points and keywords for each chapter or section of the learning materials.

[0740] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0741] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[0742] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0743] Finally, the server generates and provides the user with feedback based on the results, including detailed comments on the user's understanding of a particular chapter and areas for improvement.

[0744] As a concrete example, let's take corporate training materials. A user uploads a PDF document on business ethics. The server analyzes the content and generates quiz questions such as "What is business ethics?" and "What are the important elements of business ethics?". The user answers these questions and receives feedback based on their answers. This allows the user to study efficiently and improve their understanding.

[0745] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0746] The processing flow will be explained below.

[0747] Step 1:

[0748] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[0749] Step 2:

[0750] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[0751] Step 3:

[0752] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server properly manages the naming and storage location of the files.

[0753] Step 4:

[0754] The server reads the stored learning material and prepares it as data to input into the artificial intelligence model.

[0755] Step 5:

[0756] The AI ​​model receives input data from the server and analyzes the learning material. Using natural language processing technology, the model analyzes the content of the learning material by chapter and section, extracting key points and keywords.

[0757] Step 6:

[0758] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[0759] Step 7:

[0760] The AI ​​model generates quiz questions based on the analysis results, automatically generating multiple-choice and essay-style questions.

[0761] Step 8:

[0762] The server stores the generated quizzes in a database or in the " / quizzes / " folder, which ensures that the generated quizzes are kept for future use.

[0763] Step 9:

[0764] A user selects the "Take Quiz" option on the learning platform and requests a quiz based on a particular learning module or topic.

[0765] Step 10:

[0766] Upon receiving a user request, the server reads the corresponding quiz from the " / quizzes / " folder and sends the quiz to the user's terminal.

[0767] Step 11:

[0768] The user answers the quiz received on the terminal by selecting or writing a question and pressing the "Submit Answer" button.

[0769] Step 12:

[0770] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each question, as well as a total score.

[0771] Step 13:

[0772] The server generates feedback based on the user's answers, such as detailed feedback comments that include the user's level of understanding and areas for improvement.

[0773] Step 14:

[0774] The server sends the generated feedback to the user's device and displays it on the user's screen, where the user can check the feedback and use it to improve their learning.

[0775] Example 1

[0776] 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."

[0777] In today's educational environment, there is a demand for systems that can efficiently assess learning progress based on individual learning materials. However, in conventional systems, the analysis of learning materials and the generation of quizzes appropriate to the content are often done manually, which often leads to inefficient or inaccurate assessments. Another problem is the lack of a mechanism for properly providing the created quizzes to users and providing appropriate feedback based on their answers.

[0778] 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.

[0779] In this invention, the server includes means for preparing learning materials, means for inputting learning materials and uploading them to the learning platform, means for receiving and saving the uploaded learning materials, means for inputting the saved learning materials into an artificial intelligence model and analyzing them using natural language processing technology, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for receiving quiz requests from users and providing the saved quizzes, means for receiving answers to the quizzes and automatically evaluating and calculating scores, and means for generating and providing feedback based on the evaluation results. This enables efficient operations from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0780] "Learning Materials" means educational content, including formats such as PDF files, text files, and slide decks.

[0781] "Learning Platform" means a software environment that allows users to upload, manage, and use learning materials.

[0782] "Saving" means storing the received data in a specific folder or database on the server.

[0783] An "artificial intelligence model" is a system that uses programmed algorithms and machine learning techniques to analyze data and generate knowledge.

[0784] "Analyzing" means analyzing the content of the learning material using natural language processing technology and extracting important points and keywords.

[0785] A "quiz" is a set of questions created to assess a user's level of understanding, and includes multiple choice questions and written questions.

[0786] "Generating" means creating new quiz questions based on the analysis results.

[0787] "Providing" means distributing the generated quiz to users and making it available for use.

[0788] "Evaluating" means scoring the user's answers to the quiz and determining whether they are correct or incorrect.

[0789] The "score" is the score given to the user for the quiz answer, and is a numerical value that indicates the overall level of understanding.

[0790] "Feedback" refers to detailed comments and improvements on the evaluation results provided to the user.

[0791] MODE FOR CARRYING OUT THE INVENTION

[0792] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. The series of processes in this system are particularly configured as follows:

[0793] First, the user prepares learning materials using their device. These learning materials include educational content in various formats, such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0794] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an AI model. Specifically, the server reads the saved learning materials and inputs them into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials. This analysis involves extracting important points and keywords for each chapter and section of the learning materials.

[0795] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0796] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[0797] The user displays the submitted quiz on the screen and answers each question. Once all questions have been answered, the user presses the "Submit Answers" button. The server then receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the overall score. Feedback based on the results is then generated and provided to the user. For example, detailed comments about the user's understanding of a particular chapter and areas for improvement are displayed to the user.

[0798] As a concrete example, taking corporate training materials as an example, users upload PDF materials on "business ethics." The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" Users answer these quizzes and receive feedback based on their answers. This allows users to study efficiently and improve their understanding.

[0799] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[0800] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0801] Step 1:

[0802] The user prepares learning materials using a terminal. The learning materials can be in the form of PDF files, text files, slides, etc. The user logs in to the learning platform and clicks the "Upload" button. The user selects the learning materials from the file selection dialog and presses the "Send" button. The terminal divides the selected learning materials into packet data and sends them to the server. The input learning materials are processed as data to be sent from the terminal to the server. Packet data is generated as output.

[0803] Step 2:

[0804] The server receives packet data sent from the terminal. It reconstructs the packet data to generate a complete learning material file. It saves this data in the " / uploaded_materials / " folder in storage. For example, it saves it as " / uploaded_materials / material1.pdf". As input, it receives packet data from the terminal and creates a complete file through data reconstruction. As output, it saves the complete learning material file.

[0805] Step 3:

[0806] The server reads the stored learning materials. The learning material files are input into an AI model, and the content is analyzed using natural language processing technology. The analysis involves extracting key points and keywords for each chapter and section of the learning material. The learning material files are provided to the AI ​​model as input. Data processing involves analysis using natural language processing. The output is the key points and keywords obtained as the analysis results.

[0807] Step 4:

[0808] The server instructs the AI ​​model to generate a quiz based on the analysis results. The AI ​​model generates quiz questions in the form of multiple choice or written questions based on the extracted points and keywords. The generated quizzes are saved in the " / quizzes / " folder or in a database. The analysis results are used as input as basic data for quiz generation. Quiz questions are generated as data calculations. A quiz file is saved as output.

[0809] Step 5:

[0810] A user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. The device sends the user's request to the server. As input, the user's request information is sent to the server. As output, the request data is generated.

[0811] Step 6:

[0812] The server receives a user request, reads the corresponding quiz file from the " / quizzes / " folder, and sends the read quiz to the user's device. As input, the target quiz file based on the user request is searched and read. As output, the quiz file is delivered.

[0813] Step 7:

[0814] The user answers the quiz displayed on the device. For each question, they click on the answer option or enter a written response. After answering all questions, they press the "Submit Answers" button. The user's answer data is sent from the device to the server as input. The answer data is generated as output.

[0815] Step 8:

[0816] The server receives the user's answers. It automatically evaluates whether they are correct or incorrect using an artificial intelligence model. It calculates the score for each question and calculates the overall score. It generates detailed feedback based on the results and provides it to the user. As input, the user's answer data is evaluated. As data calculations, it determines whether they are correct or incorrect and calculates the score. As output, the generated feedback is provided to the user.

[0817] (Application example 1)

[0818] 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."

[0819] In modern industrial settings, it is important for workers to thoroughly understand work procedures and safety rules in order to perform their work accurately and safely. However, traditional methods often rely on text-based manuals, which can lead to inconsistent levels of understanding. Furthermore, manually creating quizzes and tests to assess work comprehension is time-consuming and laborious, so efficient training methods are needed.

[0820] 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.

[0821] In this invention, the server includes a means for inputting learning materials, a means for using an AI model to analyze the input learning materials, a means for generating quizzes based on the analysis results, and a means for saving the generated quizzes. This allows the server to be installed on an industrial robot and automatically generate quizzes based on work procedures and safety rules, and provide them to workers. As a result, safe and effective work training can be achieved by efficiently evaluating the worker's level of understanding and providing appropriate feedback.

[0822] "Learning materials" are materials containing educational content, such as PDF files, text files, and slide decks.

[0823] An "artificial intelligence model" is an algorithm or software that can analyze text data using natural language processing technology and extract important points and keywords.

[0824] A "quiz" is a question generated to assess the level of understanding of learning material, and may take the form of multiple choice or essay questions.

[0825] "Means for saving" refers to the function for storing the analysis results and generated quizzes in a database or file system.

[0826] "Means for providing" refers to the functionality of sending and receiving data via a user interface to display saved quizzes to a user and accept answers.

[0827] "Means for generating feedback" refers to a function that determines whether a user's answers are correct or incorrect based on the user's quiz answers, and generates detailed comments and scores to notify the user.

[0828] An "industrial robot" is a robotic device used in factories to assist with work and train workers.

[0829] A "work procedure" is a method or step for properly and efficiently performing a specific task in an industrial setting.

[0830] "Safety rules" refer to the guidelines and protocols that must be followed when working within a factory, and are rules necessary to ensure safety.

[0831] A "worker" is an employee who operates machinery and equipment at an industrial site and performs specific tasks.

[0832] The present invention is a system that is installed on an industrial robot, inputs learning materials, and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[0833] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0834] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage. The saved learning materials are then analyzed by an AI model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords.

[0835] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated. The generated quizzes are saved in a specific folder or database by the server.

[0836] When a user wants to take a quiz, they select the "Take Quiz" option on the learning platform. They request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[0837] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0838] Finally, the server generates and provides feedback based on the results to the user, including detailed comments on the level of understanding and areas for improvement for a particular chapter, allowing the user to study efficiently and improve their comprehension.

[0839] As a specific example, an industrial robot can upload a work procedure manual in PDF format, and the robot will analyze the uploaded manual content and generate quizzes based on important procedures and safety rules, which can then be provided to workers. This allows workers to check their understanding and study efficiently.

[0840] Example prompt sentence:

[0841] Input the manual contents and use the AI ​​model to generate a quiz based on work procedures and safety rules. Use multiple choice questions for the quiz questions, and output the generated quiz questions and options.

[0842] Learning materials: [Manual content text]

[0843] The hardware used includes industrial robots, user terminals, and servers, while the software includes AI models using Python language and natural language processing technology.

[0844] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0845] Step 1:

[0846] Users prepare learning materials on their devices and upload them to the learning platform, using educational content in the form of PDF files, text files, slide decks, etc. Users click the "Upload" button on the platform, select the appropriate learning materials from the file selection dialog, and then press the "Submit" button.

[0847] Input: User selected learning material file.

[0848] Output: The learning material is sent to the server and stored.

[0849] Step 2:

[0850] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage (e.g., " / uploaded_materials / ").

[0851] Input: Learning material file sent from the user's device.

[0852] Output: The learning materials will be saved in the specified folder.

[0853] Step 3:

[0854] The server reads the stored learning materials and inputs them into an AI model, which uses natural language processing technology to analyze the content of the learning materials and extract key points and keywords for each chapter and section.

[0855] Input: Saved learning material file.

[0856] Data processing: Text analysis using natural language processing techniques.

[0857] Output: Key points and keywords as analysis results.

[0858] Step 4:

[0859] The server instructs the AI ​​model to generate quizzes based on the analysis results. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple-choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated.

[0860] Input: Analysis result data.

[0861] Data Computation: Question generation based on quiz generation algorithms.

[0862] Output: The generated quiz questions.

[0863] Step 5:

[0864] The generated quizzes are stored by the server in a specific folder or database (e.g. " / quizzes / " folder or database).

[0865] Input: The generated quiz questions.

[0866] Output: Saved quiz questions.

[0867] Step 6:

[0868] A user selects the "Take a Quiz" option to request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[0869] Input: The user's quiz request.

[0870] Output: The corresponding quiz question is sent to the user's device.

[0871] Step 7:

[0872] The user displays the sent quiz on the screen of the terminal and answers each question. When all questions have been answered, the user presses the "Submit Answers" button.

[0873] Input: Quiz questions and user answers.

[0874] Output: The user's answer is sent to the server.

[0875] Step 8:

[0876] The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[0877] Input: The user's answer.

[0878] Data calculation: determining whether an answer is correct or incorrect and calculating scores.

[0879] Output: Total score.

[0880] Step 9:

[0881] The server generates and provides feedback to the user based on the results, including detailed comments on the level of understanding and areas for improvement for a particular chapter.

[0882] Input: Overall score and comprehension assessment data.

[0883] Data processing: Comment generation using a feedback generation algorithm.

[0884] Output: Feedback for the user.

[0885] The above are the specific processing steps of the system that realizes the application example.

[0886] 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.

[0887] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[0888] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. To do this, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0889] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server then inputs the saved learning materials into the AI ​​model to prepare for analysis.

[0890] The server inputs the stored learning materials into the AI ​​model, which then uses natural language processing techniques to analyze the content of the learning materials, including extracting key points and keywords from each chapter or section of the learning materials.

[0891] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0892] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[0893] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[0894] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[0895] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[0896] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[0897] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[0901] Step 2:

[0902] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[0903] Step 3:

[0904] The server receives the learning materials sent from the user's device and stores them in the " / uploaded_materials / " folder. The server properly manages the naming and storage location of the files.

[0905] Step 4:

[0906] The server reads the stored learning material and prepares it as input data for the artificial intelligence model.

[0907] Step 5:

[0908] The AI ​​model receives input data from the server and analyzes the learning material. The model uses natural language processing techniques to extract key points and keywords for each chapter or section of the learning material.

[0909] Step 6:

[0910] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[0911] Step 7:

[0912] The AI ​​model generates quiz questions based on the analysis results. For example, in the "Chapter on Business Ethics," it generates questions such as "What is business ethics?" and "What are the key elements of business ethics?"

[0913] Step 8:

[0914] The server saves the generated quiz in the " / quizzes / " folder or in a database, which ensures that the generated quiz is kept for future use.

[0915] Step 9:

[0916] A user selects the "Take Quiz" option on a learning platform, requesting a quiz based on a specific learning module or topic.

[0917] Step 10:

[0918] Upon receiving a user request, the server reads the relevant quiz from the " / quizzes / " folder and sends it to the user's device.

[0919] Step 11:

[0920] While the device is running the quiz, it uses its built-in camera and microphone to transmit the user's facial expressions and tone of voice to the emotion engine, which then analyzes the information and evaluates the user's current emotional state.

[0921] Step 12:

[0922] The server receives data on the user's emotional state and adjusts the difficulty of the quiz and the type of questions in real time. For example, if the user is feeling stressed, the server will lower the difficulty of the questions or display encouraging messages.

[0923] Step 13:

[0924] The user answers the quiz on the device by selecting or writing for each question, and when all questions have been answered, they press the "Submit Answers" button.

[0925] Step 14:

[0926] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each quiz question.

[0927] Step 15:

[0928] The server again analyzes the user's emotional state while answering the quiz and generates feedback based on the results, including positive feedback and encouraging comments if the user is feeling stressed.

[0929] Step 16:

[0930] The server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to check the feedback and use it to improve their learning.

[0931] Example 2

[0932] 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."

[0933] Conventional learning systems often provide uniform quizzes and feedback, making it difficult to fully utilize users' learning effects. Furthermore, they lack the ability to monitor the user's emotional state and adjust the learning content accordingly, resulting in reduced learning efficiency and motivation. To address this issue, it is necessary to monitor the user's emotional state in real time and adjust the difficulty and format of the quiz based on that state to achieve more effective learning.

[0934] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0935] In this invention, the server includes means for inputting learning materials, means for using an artificial intelligence model to analyze the input learning materials, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for providing the saved quizzes, means for receiving answers to the quizzes and generating feedback, means for monitoring the emotional state of the user and analyzing the emotional data, means for adjusting the difficulty and format of the quiz based on the emotional data, and means for generating feedback in accordance with the emotional state of the user, thereby enabling flexible learning support that takes the user's emotional state into consideration.

[0936] "Learning materials" refers to data such as teaching materials and documents that users use for learning purposes.

[0937] "Input means" refers to devices or programs that provide the functionality for incorporating learning materials into the system.

[0938] An "analytical artificial intelligence model" refers to an algorithm that understands the content of input learning material and extracts important points and keywords.

[0939] "Quiz generating means" refers to a function or device that automatically creates appropriate quiz questions (multiple choice questions, written questions, etc.) based on the analysis results.

[0940] "Storage means" refers to a device or program for storing the generated quiz in a digital storage device or database.

[0941] The "means for providing" refers to a function or device that presents the saved quiz to the user.

[0942] The "means for receiving answers and generating feedback" refers to a function for receiving the results of a user's answers to a quiz and creating evaluations and comments for improvement based on the results.

[0943] "Means for monitoring emotional states and analyzing emotional data" refers to algorithms or devices that use sensors such as cameras and microphones to monitor a user's facial expressions and voice in real time and evaluate their emotions.

[0944] "Means for adjusting the difficulty and format of quizzes based on emotional data" refers to a function that changes the content of the quiz according to the user's emotional state, providing an optimal learning experience.

[0945] "Means for generating feedback according to the user's emotional state" refers to a device or program that appropriately generates comments to alleviate stress, encouraging messages, etc., based on the user's emotional state.

[0946] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[0947] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[0948] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in its storage. The server then inputs the saved learning materials into the AI ​​model, preparing it for analysis.

[0949] The server inputs the learning material into an AI model, which then uses natural language processing techniques to analyze the content of the learning material, including extracting key points and keywords from each chapter or section of the material.

[0950] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[0951] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[0952] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[0953] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[0954] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[0955] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[0956] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[0957] Example prompts to input to a generative AI model:

[0958] "Upload a PDF file on business ethics. Based on this material, please generate multiple-choice and essay questions. Include key points and keywords."

[0959] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0960] Step 1:

[0961] The user prepares the learning materials.

[0962] The user uses a device to prepare the learning materials (PDF files, text files, slides, etc.) required for learning. These learning materials are used as input. The output is the prepared learning materials. Specifically, the user collects learning materials from folders on the device or from cloud storage.

[0963] Step 2:

[0964] Users upload learning materials.

[0965] The user accesses the learning platform using a terminal and clicks the "Upload" button. A file selection dialog appears, and the user selects the learning material. Then, the user presses the "Send" button. The input of this operation is the prepared learning material, and the output is the learning material sent to the server. In concrete terms, the user selects the learning material file and uploads it to the platform.

[0966] Step 3:

[0967] The server receives and stores the learning materials.

[0968] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The input is the learning materials sent to the server, and the output is the saved learning materials. Specifically, the server writes the files to a specific folder.

[0969] Step 4:

[0970] The server prepares to analyze the learning material.

[0971] The server prepares the saved learning material for input into the AI ​​model. It checks the file path and format and converts it into the appropriate format. The input is the saved learning material, and the output is data in a format suitable for analysis. Specifically, the server obtains the file path and formats the data as needed.

[0972] Step 5:

[0973] An artificial intelligence model analyzes the learning material.

[0974] The server inputs learning materials into the AI ​​model. The model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords. The input is data in a format suitable for analysis, and the output is the extracted points and keywords. Specifically, the AI ​​model performs text analysis and extracts important information.

[0975] Step 6:

[0976] The server instructs the artificial intelligence model to generate the quiz.

[0977] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The input is the extracted points and keywords, and the output is the generated quiz questions. Specifically, the server sends the analysis results to the model and provides prompts for quiz generation.

[0978] Step 7:

[0979] An artificial intelligence model generates the quiz.

[0980] Based on the analysis results, the AI ​​model automatically generates quizzes such as multiple choice and written questions. The server saves the generated quizzes in the " / quizzes / " folder or in a database. The input is the quiz generation prompt and the analysis results, and the output is the generated quiz questions. Specifically, the model generates quizzes in an appropriate question format, and the server performs the save operation.

[0981] Step 8:

[0982] The user takes the quiz.

[0983] A user accesses the learning platform on their device and selects the "Take a Quiz" option. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device. The input is a request to take the quiz, and the output is the quiz questions that are displayed on the user's device. Specifically, the user selects a quiz, and the server sends the quiz questions to the device.

[0984] Step 9:

[0985] The terminal monitors the user's emotional state.

[0986] The device uses a camera and microphone to monitor the user's facial expressions and voice in real time. This emotional data is sent to the emotion engine for analysis. The input is the user's real-time facial expressions and voice, and the output is the analyzed emotional data. Specifically, the device's sensors operate, and the emotion engine analyzes the data.

[0987] Step 10:

[0988] The server receives the emotion data and adjusts the quiz.

[0989] The server receives the analyzed emotional data and adjusts the difficulty and format of the quiz according to the user's emotional state. The input is the emotional data, and the output is the adjusted quiz questions. Specifically, the server changes the difficulty parameters of the quiz based on the emotional data.

[0990] Step 11:

[0991] The user answers the quiz.

[0992] The user answers the quiz displayed on the terminal. Once all questions have been answered, the user presses the "Submit Answers" button. The input is the user's answer data, and the output is the answer sent to the server. Specifically, the user selects an answer and performs the submit operation.

[0993] Step 12:

[0994] The server evaluates the quiz answers.

[0995] The server receives the answers sent by the user and evaluates whether they are correct or incorrect. It then calculates the score for each quiz question. The input is the user's answer data, and the output is the evaluation result and score. Specifically, the server analyzes the answer data and calculates the score.

[0996] Step 13:

[0997] The server analyzes the emotional data and generates feedback.

[0998] The server again analyzes the user's emotional state and generates feedback based on the results. For example, if the user is feeling stressed, it generates positive feedback or encouraging comments. It also provides specific comments about the user's level of understanding and areas for improvement. The input is the emotional data during the quiz answer, and the output is the generated feedback. Specifically, the server analyzes the emotional data and creates feedback comments.

[0999] Step 14:

[1000] The server sends feedback.

[1001] The server sends the generated feedback to the user's terminal and displays it on the screen. The input is the generated feedback, and the output is the feedback displayed on the user's terminal. In concrete terms, the server transfers the feedback data to the user's terminal, and the terminal displays it.

[1002] (Application example 2)

[1003] 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."

[1004] Conventional learning systems provide quizzes with a uniform level of difficulty and format without considering the learner's emotional state, resulting in poor learning efficiency. Furthermore, when autonomous vehicle engineers learn new technologies, there is a lack of a way to analyze individual levels of understanding and concentration in real time and provide appropriate feedback accordingly. There is a need to solve these issues and realize more effective learning support.

[1005] 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 a means for inputting learning materials, a means for using an artificial intelligence model to analyze the input learning materials, a means for generating quizzes based on the analysis results, a means for saving the generated quizzes, a means for providing the saved quizzes, a means for receiving answers to the quizzes and generating feedback, and a means for monitoring the user's emotional state and adjusting the difficulty and format of the quiz. This makes it possible to provide quizzes with the optimal difficulty and format according to the learner's emotional state, thereby realizing efficient learning support tailored to each learner. Furthermore, automated vehicle engineers can also receive appropriate feedback through real-time emotion analysis, improving the efficiency of their technical acquisition.

[1006] "Learning materials" refers to teaching materials used in education and training, including PDF files, text files, slides, etc.

[1007] An "artificial intelligence model" is an algorithm or program that can analyze data using techniques such as machine learning and deep learning to perform specific tasks.

[1008] A "quiz" is an assessment tool in the form of questions generated based on learning materials, and can take the form of multiple choice questions or essay questions.

[1009] "Emotional state" refers to data that represents the user's current emotions, including those acquired in real time through facial expressions, voice, etc.

[1010] "Feedback" refers to advice or comments provided based on the evaluation of the user's answers to the quiz.

[1011] "Difficulty" refers to the level that indicates how difficult it is to answer a quiz or assignment.

[1012] "Real-time monitoring" refers to tracking the user's situation in real time and acquiring and analyzing data.

[1013] "Analysis" refers to the process of breaking down learning materials and user data and extracting important elements and patterns.

[1014] "Storage" refers to storing data and generated quizzes in storage so that they can be accessed later.

[1015] "Providing" refers to sending and making accessible the saved quiz and feedback to the user.

[1016] "Monitoring" refers to the process of continuously observing and collecting data about a user's behavior and state.

[1017] The present invention relates to a training system for assisting learning about autonomous vehicles. Specific embodiments of the present invention will be described below.

[1018] Hardware and software used

[1019] 1. Hardware:

[1020] Smartphones, smart glasses, head-mounted displays (hereinafter referred to as "devices")

[1021] Terminal devices with a camera and microphone

[1022] server

[1023] 2. Software:

[1024] Python (data analysis and model execution)

[1025] TensorFlow / PyTorch (training and running artificial intelligence models)

[1026] OpenCV (camera image analysis)

[1027] NLTK / spaCy (Natural Language Processing)

[1028] Flask / Django (Web application framework)

[1029] Data processing and calculation

[1030] The server first receives and stores the learning materials (PDF files, text files, slides, etc.) sent from the device. It then analyzes the stored learning materials using natural language processing technology to extract key points and keywords. Based on the results of this analysis, an artificial intelligence model automatically generates quizzes, including multiple-choice and written questions.

[1031] The generated quiz is stored in a database in the server. When the user selects the "Take Quiz" option, the server sends the corresponding quiz to the terminal.

[1032] While answering the quiz, the device monitors the user's facial expressions and voice in real time through a camera and microphone. This data is analyzed using OpenCV and an emotion analysis model, and data corresponding to the user's emotional state is sent to the server.

[1033] The server adjusts the difficulty and format of the quiz based on the received emotional data, and after the quiz is completed, generates feedback based on the analysis results and sends it to the device.

[1034] Specific examples

[1035] For example, consider a company engineer who wants to learn about a new control algorithm for autonomous vehicles. The engineer uploads a PDF study guide about the control algorithm for autonomous vehicles to the app. The server analyzes the study guide and generates quiz questions such as, "How does the control algorithm for autonomous vehicles work?" and "What are the main risks?"

[1036] As the technician answers the quiz, the technician's facial expressions and voice are monitored through a camera and microphone, and the difficulty of the quiz is adjusted in real time based on the analyzed emotional data, allowing the technician to learn efficiently.

[1037] Example of input prompt for generative AI model:

[1038] Based on the learning material on the theme "Discuss the risks associated with the safety of autonomous vehicles," a quiz was generated in the following format:

[1039] 1. Multiple choice questions:

[1040] 2. Essay questions: 0 questions

[1041] Here is an example of a multiple choice question:

[1042] 1. What are the biggest risks with self-driving vehicles?

[1043] a) Energy efficiency

[1044] b) Sensor failure

[1045] c) Ignoring traffic signals

[1046] Through the above process, a flexible and efficient training system is provided to maximize the learning effect of users.

[1047] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1048] Step 1:

[1049] Users upload learning materials to their devices by selecting PDF files, text files, slide decks, etc., and clicking the "Upload" button in the application. The selected files are then sent to the learning platform.

[1050] Step 2:

[1051] The server receives the learning materials sent from the device. The received files are saved in the " / uploaded_materials / " folder on the server. This saving is done as a preparation for analyzing the learning materials.

[1052] Step 3:

[1053] The server analyzes the stored learning materials using natural language processing technology. Specifically, it uses Python and NLTK or spaCy to extract important points and keywords from the content of the learning materials. This analysis clarifies the main points of the learning materials.

[1054] Step 4:

[1055] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The generative AI model (built with TensorFlow / PyTorch) automatically generates quizzes in the form of multiple choice or essay questions based on the analyzed data. This process creates questions that are in line with the content of the learning material.

[1056] Step 5:

[1057] The generated quizzes are saved in the " / quizzes / " folder on the server or in a database, where they are recorded for later access by users.

[1058] Step 6:

[1059] When a user selects the "Take Quiz" option, the server sends the saved quiz to the device. The user selects a specific learning module or topic and sends a request to the server, which delivers the corresponding quiz to the device.

[1060] Step 7:

[1061] While answering the quiz, the device monitors the user's facial expressions and voice in real time using a camera and microphone. The acquired data is analyzed using OpenCV and an emotion analysis model to determine the user's emotional state. This emotion data is sent to the server while answering the quiz.

[1062] Step 8:

[1063] The server then adjusts the difficulty and format of the quiz based on the received emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or change the format. This adjustment allows the user to learn more effectively.

[1064] Step 9:

[1065] When the user has finished answering the quiz, he / she presses the "Submit Answers" button. The server receives the user's answers and automatically evaluates them, determining whether they are correct or incorrect and calculating the score for each quiz question.

[1066] Step 10:

[1067] The server generates feedback based on the evaluation results and sentiment analysis data. For example, if the user is feeling stressed, the server will provide positive feedback and specific advice, allowing the user to clearly identify areas for improvement.

[1068] Step 11:

[1069] Finally, the server sends the generated feedback to the device. The feedback is displayed on the user's screen and can be used to improve their learning. The analysis results and feedback are also recorded as the user's learning history.

[1070] 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.

[1071] 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.

[1072] 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.

[1073] [Fourth embodiment]

[1074] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1075] 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.

[1076] 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).

[1077] 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.

[1078] 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.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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.

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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."

[1087] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[1088] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[1089] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an artificial intelligence model.

[1090] The server reads the stored learning materials and inputs them into an AI model, which then uses natural language processing techniques to analyze the content of the learning materials. This analysis involves extracting key points and keywords for each chapter or section of the learning materials.

[1091] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[1092] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[1093] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[1094] Finally, the server generates and provides the user with feedback based on the results, including detailed comments on the user's understanding of a particular chapter and areas for improvement.

[1095] As a concrete example, let's take corporate training materials. A user uploads a PDF document on business ethics. The server analyzes the content and generates quiz questions such as "What is business ethics?" and "What are the important elements of business ethics?". The user answers these questions and receives feedback based on their answers. This allows the user to study efficiently and improve their understanding.

[1096] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[1097] The processing flow will be explained below.

[1098] Step 1:

[1099] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[1100] Step 2:

[1101] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[1102] Step 3:

[1103] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server properly manages the naming and storage location of the files.

[1104] Step 4:

[1105] The server reads the stored learning material and prepares it as data to input into the artificial intelligence model.

[1106] Step 5:

[1107] The AI ​​model receives input data from the server and analyzes the learning material. Using natural language processing technology, the model analyzes the content of the learning material by chapter and section, extracting key points and keywords.

[1108] Step 6:

[1109] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[1110] Step 7:

[1111] The AI ​​model generates quiz questions based on the analysis results, automatically generating multiple-choice and essay-style questions.

[1112] Step 8:

[1113] The server stores the generated quizzes in a database or in the " / quizzes / " folder, which ensures that the generated quizzes are kept for future use.

[1114] Step 9:

[1115] A user selects the "Take Quiz" option on the learning platform and requests a quiz based on a particular learning module or topic.

[1116] Step 10:

[1117] Upon receiving a user request, the server reads the corresponding quiz from the " / quizzes / " folder and sends the quiz to the user's terminal.

[1118] Step 11:

[1119] The user answers the quiz received on the terminal by selecting or writing a question and pressing the "Submit Answer" button.

[1120] Step 12:

[1121] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each question, as well as a total score.

[1122] Step 13:

[1123] The server generates feedback based on the user's answers, such as detailed feedback comments that include the user's level of understanding and areas for improvement.

[1124] Step 14:

[1125] The server sends the generated feedback to the user's device and displays it on the user's screen, where the user can check the feedback and use it to improve their learning.

[1126] Example 1

[1127] 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."

[1128] In today's educational environment, there is a demand for systems that can efficiently assess learning progress based on individual learning materials. However, in conventional systems, the analysis of learning materials and the generation of quizzes appropriate to the content are often done manually, which often leads to inefficient or inaccurate assessments. Another problem is the lack of a mechanism for properly providing the created quizzes to users and providing appropriate feedback based on their answers.

[1129] 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.

[1130] In this invention, the server includes means for preparing learning materials, means for inputting learning materials and uploading them to the learning platform, means for receiving and saving the uploaded learning materials, means for inputting the saved learning materials into an artificial intelligence model and analyzing them using natural language processing technology, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for receiving quiz requests from users and providing the saved quizzes, means for receiving answers to the quizzes and automatically evaluating and calculating scores, and means for generating and providing feedback based on the evaluation results. This enables efficient operations from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[1131] "Learning Materials" means educational content, including formats such as PDF files, text files, and slide decks.

[1132] "Learning Platform" means a software environment that allows users to upload, manage, and use learning materials.

[1133] "Saving" means storing the received data in a specific folder or database on the server.

[1134] An "artificial intelligence model" is a system that uses programmed algorithms and machine learning techniques to analyze data and generate knowledge.

[1135] "Analyzing" means analyzing the content of the learning material using natural language processing technology and extracting important points and keywords.

[1136] A "quiz" is a set of questions created to assess a user's level of understanding, and includes multiple choice questions and written questions.

[1137] "Generating" means creating new quiz questions based on the analysis results.

[1138] "Providing" means distributing the generated quiz to users and making it available for use.

[1139] "Evaluating" means scoring the user's answers to the quiz and determining whether they are correct or incorrect.

[1140] The "score" is the score given to the user for the quiz answer, and is a numerical value that indicates the overall level of understanding.

[1141] "Feedback" refers to detailed comments and improvements on the evaluation results provided to the user.

[1142] MODE FOR CARRYING OUT THE INVENTION

[1143] The present invention is a system that inputs learning materials and automatically generates and provides quizzes using an artificial intelligence model. The series of processes in this system are particularly configured as follows:

[1144] First, the user prepares learning materials using their device. These learning materials include educational content in various formats, such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[1145] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The saved learning materials are then analyzed by an AI model. Specifically, the server reads the saved learning materials and inputs them into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials. This analysis involves extracting important points and keywords for each chapter and section of the learning materials.

[1146] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[1147] Next, let's consider a scenario where a user takes a quiz. The user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. Upon receiving the user's request, the server retrieves the corresponding quiz from the " / quizzes / " folder and sends it to the user's device.

[1148] The user displays the submitted quiz on the screen and answers each question. Once all questions have been answered, the user presses the "Submit Answers" button. The server then receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the overall score. Feedback based on the results is then generated and provided to the user. For example, detailed comments about the user's understanding of a particular chapter and areas for improvement are displayed to the user.

[1149] As a concrete example, taking corporate training materials as an example, users upload PDF materials on "business ethics." The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" Users answer these quizzes and receive feedback based on their answers. This allows users to study efficiently and improve their understanding.

[1150] In this way, the system of the present invention efficiently supports a series of steps from uploading learning materials to generating, providing, answering, and providing feedback on quizzes.

[1151] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1152] Step 1:

[1153] The user prepares learning materials using a terminal. The learning materials can be in the form of PDF files, text files, slides, etc. The user logs in to the learning platform and clicks the "Upload" button. The user selects the learning materials from the file selection dialog and presses the "Send" button. The terminal divides the selected learning materials into packet data and sends them to the server. The input learning materials are processed as data to be sent from the terminal to the server. Packet data is generated as output.

[1154] Step 2:

[1155] The server receives packet data sent from the terminal. It reconstructs the packet data to generate a complete learning material file. It saves this data in the " / uploaded_materials / " folder in storage. For example, it saves it as " / uploaded_materials / material1.pdf". As input, it receives packet data from the terminal and creates a complete file through data reconstruction. As output, it saves the complete learning material file.

[1156] Step 3:

[1157] The server reads the stored learning materials. The learning material files are input into an AI model, and the content is analyzed using natural language processing technology. The analysis involves extracting key points and keywords for each chapter and section of the learning material. The learning material files are provided to the AI ​​model as input. Data processing involves analysis using natural language processing. The output is the key points and keywords obtained as the analysis results.

[1158] Step 4:

[1159] The server instructs the AI ​​model to generate a quiz based on the analysis results. The AI ​​model generates quiz questions in the form of multiple choice or written questions based on the extracted points and keywords. The generated quizzes are saved in the " / quizzes / " folder or in a database. The analysis results are used as input as basic data for quiz generation. Quiz questions are generated as data calculations. A quiz file is saved as output.

[1160] Step 5:

[1161] A user selects the "Take Quiz" option on the learning platform. The user requests a quiz based on a specific learning module or topic. The device sends the user's request to the server. As input, the user's request information is sent to the server. As output, the request data is generated.

[1162] Step 6:

[1163] The server receives a user request, reads the corresponding quiz file from the " / quizzes / " folder, and sends the read quiz to the user's device. As input, the target quiz file based on the user request is searched and read. As output, the quiz file is delivered.

[1164] Step 7:

[1165] The user answers the quiz displayed on the device. For each question, they click on the answer option or enter a written response. After answering all questions, they press the "Submit Answers" button. The user's answer data is sent from the device to the server as input. The answer data is generated as output.

[1166] Step 8:

[1167] The server receives the user's answers. It automatically evaluates whether they are correct or incorrect using an artificial intelligence model. It calculates the score for each question and calculates the overall score. It generates detailed feedback based on the results and provides it to the user. As input, the user's answer data is evaluated. As data calculations, it determines whether they are correct or incorrect and calculates the score. As output, the generated feedback is provided to the user.

[1168] (Application example 1)

[1169] 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."

[1170] In modern industrial settings, it is important for workers to thoroughly understand work procedures and safety rules in order to perform their work accurately and safely. However, traditional methods often rely on text-based manuals, which can lead to inconsistent levels of understanding. Furthermore, manually creating quizzes and tests to assess work comprehension is time-consuming and laborious, so efficient training methods are needed.

[1171] 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.

[1172] In this invention, the server includes a means for inputting learning materials, a means for using an AI model to analyze the input learning materials, a means for generating quizzes based on the analysis results, and a means for saving the generated quizzes. This allows the server to be installed on an industrial robot and automatically generate quizzes based on work procedures and safety rules, and provide them to workers. As a result, safe and effective work training can be achieved by efficiently evaluating the worker's level of understanding and providing appropriate feedback.

[1173] "Learning materials" are materials containing educational content, such as PDF files, text files, and slide decks.

[1174] An "artificial intelligence model" is an algorithm or software that can analyze text data using natural language processing technology and extract important points and keywords.

[1175] A "quiz" is a question generated to assess the level of understanding of learning material, and may take the form of multiple choice or essay questions.

[1176] "Means for saving" refers to the function for storing the analysis results and generated quizzes in a database or file system.

[1177] "Means for providing" refers to the functionality of sending and receiving data via a user interface to display saved quizzes to a user and accept answers.

[1178] "Means for generating feedback" refers to a function that determines whether a user's answers are correct or incorrect based on the user's quiz answers, and generates detailed comments and scores to notify the user.

[1179] An "industrial robot" is a robotic device used in factories to assist with work and train workers.

[1180] A "work procedure" is a method or step for properly and efficiently performing a specific task in an industrial setting.

[1181] "Safety rules" refer to the guidelines and protocols that must be followed when working within a factory, and are rules necessary to ensure safety.

[1182] A "worker" is an employee who operates machinery and equipment at an industrial site and performs specific tasks.

[1183] The present invention is a system that is installed on an industrial robot, inputs learning materials, and automatically generates and provides quizzes using an artificial intelligence model. Specific embodiments of this system are described below.

[1184] First, the user prepares learning materials using their device. These learning materials include various educational content such as PDF files, text files, and slide decks. The user then uploads the learning materials to the learning platform. To do this, the user clicks the "Upload" button on the learning platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[1185] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage. The saved learning materials are then analyzed by an AI model. The AI ​​model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords.

[1186] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated. The generated quizzes are saved in a specific folder or database by the server.

[1187] When a user wants to take a quiz, they select the "Take Quiz" option on the learning platform. They request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[1188] The user displays the sent quiz on the screen and answers each question. Once all questions have been answered, they press the "Submit Answers" button. The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[1189] Finally, the server generates and provides feedback based on the results to the user, including detailed comments on the level of understanding and areas for improvement for a particular chapter, allowing the user to study efficiently and improve their comprehension.

[1190] As a specific example, an industrial robot can upload a work procedure manual in PDF format, and the robot will analyze the uploaded manual content and generate quizzes based on important procedures and safety rules, which can then be provided to workers. This allows workers to check their understanding and study efficiently.

[1191] Example prompt sentence:

[1192] Input the manual contents and use the AI ​​model to generate a quiz based on work procedures and safety rules. Use multiple choice questions for the quiz questions, and output the generated quiz questions and options.

[1193] Learning materials: [Manual content text]

[1194] The hardware used includes industrial robots, user terminals, and servers, while the software includes AI models using Python language and natural language processing technology.

[1195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1196] Step 1:

[1197] Users prepare learning materials on their devices and upload them to the learning platform, using educational content in the form of PDF files, text files, slide decks, etc. Users click the "Upload" button on the platform, select the appropriate learning materials from the file selection dialog, and then press the "Submit" button.

[1198] Input: User selected learning material file.

[1199] Output: The learning material is sent to the server and stored.

[1200] Step 2:

[1201] The server receives the learning materials sent from the user's device and stores them in a specific folder in the storage (e.g., " / uploaded_materials / ").

[1202] Input: Learning material file sent from the user's device.

[1203] Output: The learning materials will be saved in the specified folder.

[1204] Step 3:

[1205] The server reads the stored learning materials and inputs them into an AI model, which uses natural language processing technology to analyze the content of the learning materials and extract key points and keywords for each chapter and section.

[1206] Input: Saved learning material file.

[1207] Data processing: Text analysis using natural language processing techniques.

[1208] Output: Key points and keywords as analysis results.

[1209] Step 4:

[1210] The server instructs the AI ​​model to generate quizzes based on the analysis results. The AI ​​model generates appropriate quiz questions based on the extracted information. Quiz question formats include multiple-choice and written questions. Quizzes on work procedures and safety rules specific to industrial robots are also generated.

[1211] Input: Analysis result data.

[1212] Data Computation: Question generation based on quiz generation algorithms.

[1213] Output: The generated quiz questions.

[1214] Step 5:

[1215] The generated quizzes are stored by the server in a specific folder or database (e.g. " / quizzes / " folder or database).

[1216] Input: The generated quiz questions.

[1217] Output: Saved quiz questions.

[1218] Step 6:

[1219] A user selects the "Take a Quiz" option to request a quiz based on a specific learning module or topic. The server receives the user's request, retrieves the appropriate quiz from its stored collection, and sends it to the user's device.

[1220] Input: The user's quiz request.

[1221] Output: The corresponding quiz question is sent to the user's device.

[1222] Step 7:

[1223] The user displays the sent quiz on the screen of the terminal and answers each question. When all questions have been answered, the user presses the "Submit Answers" button.

[1224] Input: Quiz questions and user answers.

[1225] Output: The user's answer is sent to the server.

[1226] Step 8:

[1227] The server receives the user's answers and automatically evaluates whether they are correct or incorrect. The server calculates the score for each question and calculates the total score.

[1228] Input: The user's answer.

[1229] Data calculation: determining whether an answer is correct or incorrect and calculating scores.

[1230] Output: Total score.

[1231] Step 9:

[1232] The server generates and provides feedback to the user based on the results, including detailed comments on the level of understanding and areas for improvement for a particular chapter.

[1233] Input: Overall score and comprehension assessment data.

[1234] Data processing: Comment generation using a feedback generation algorithm.

[1235] Output: Feedback for the user.

[1236] The above are the specific processing steps of the system that realizes the application example.

[1237] 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.

[1238] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[1239] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. To do this, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[1240] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The server then inputs the saved learning materials into the AI ​​model to prepare for analysis.

[1241] The server inputs the stored learning materials into the AI ​​model, which then uses natural language processing techniques to analyze the content of the learning materials, including extracting key points and keywords from each chapter or section of the learning materials.

[1242] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[1243] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[1244] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[1245] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[1246] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[1247] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[1248] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[1249] The processing flow will be explained below.

[1250] Step 1:

[1251] The user prepares the learning materials. The educational content is available on the user's device in the form of PDF, text, slides, etc.

[1252] Step 2:

[1253] The user logs in to the learning platform and clicks the "Upload" button on the screen. A file selection dialog box appears, allowing the user to select the learning material and press the "Submit" button.

[1254] Step 3:

[1255] The server receives the learning materials sent from the user's device and stores them in the " / uploaded_materials / " folder. The server properly manages the naming and storage location of the files.

[1256] Step 4:

[1257] The server reads the stored learning material and prepares it as input data for the artificial intelligence model.

[1258] Step 5:

[1259] The AI ​​model receives input data from the server and analyzes the learning material. The model uses natural language processing techniques to extract key points and keywords for each chapter or section of the learning material.

[1260] Step 6:

[1261] The server receives the analysis results from the artificial intelligence model and instructs the generation of a quiz based on them.

[1262] Step 7:

[1263] The AI ​​model generates quiz questions based on the analysis results. For example, in the "Chapter on Business Ethics," it generates questions such as "What is business ethics?" and "What are the key elements of business ethics?"

[1264] Step 8:

[1265] The server saves the generated quiz in the " / quizzes / " folder or in a database, which ensures that the generated quiz is kept for future use.

[1266] Step 9:

[1267] A user selects the "Take Quiz" option on a learning platform, requesting a quiz based on a specific learning module or topic.

[1268] Step 10:

[1269] Upon receiving a user request, the server reads the relevant quiz from the " / quizzes / " folder and sends it to the user's device.

[1270] Step 11:

[1271] While the device is running the quiz, it uses its built-in camera and microphone to transmit the user's facial expressions and tone of voice to the emotion engine, which then analyzes the information and evaluates the user's current emotional state.

[1272] Step 12:

[1273] The server receives data on the user's emotional state and adjusts the difficulty of the quiz and the type of questions in real time. For example, if the user is feeling stressed, the server will lower the difficulty of the questions or display encouraging messages.

[1274] Step 13:

[1275] The user answers the quiz on the device by selecting or writing for each question, and when all questions have been answered, they press the "Submit Answers" button.

[1276] Step 14:

[1277] The server receives the user's answers, automatically evaluates whether they are correct or incorrect, and calculates a score for each quiz question.

[1278] Step 15:

[1279] The server again analyzes the user's emotional state while answering the quiz and generates feedback based on the results, including positive feedback and encouraging comments if the user is feeling stressed.

[1280] Step 16:

[1281] The server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to check the feedback and use it to improve their learning.

[1282] Example 2

[1283] 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."

[1284] Conventional learning systems often provide uniform quizzes and feedback, making it difficult to fully utilize users' learning effects. Furthermore, they lack the ability to monitor the user's emotional state and adjust the learning content accordingly, resulting in reduced learning efficiency and motivation. To address this issue, it is necessary to monitor the user's emotional state in real time and adjust the difficulty and format of the quiz based on that state to achieve more effective learning.

[1285] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1286] In this invention, the server includes means for inputting learning materials, means for using an artificial intelligence model to analyze the input learning materials, means for generating quizzes based on the analysis results, means for saving the generated quizzes, means for providing the saved quizzes, means for receiving answers to the quizzes and generating feedback, means for monitoring the emotional state of the user and analyzing the emotional data, means for adjusting the difficulty and format of the quiz based on the emotional data, and means for generating feedback in accordance with the emotional state of the user, thereby enabling flexible learning support that takes the user's emotional state into consideration.

[1287] "Learning materials" refers to data such as teaching materials and documents that users use for learning purposes.

[1288] "Input means" refers to devices or programs that provide the functionality for incorporating learning materials into the system.

[1289] An "analytical artificial intelligence model" refers to an algorithm that understands the content of input learning material and extracts important points and keywords.

[1290] "Quiz generating means" refers to a function or device that automatically creates appropriate quiz questions (multiple choice questions, written questions, etc.) based on the analysis results.

[1291] "Storage means" refers to a device or program for storing the generated quiz in a digital storage device or database.

[1292] The "means for providing" refers to a function or device that presents the saved quiz to the user.

[1293] The "means for receiving answers and generating feedback" refers to a function for receiving the results of a user's answers to a quiz and creating evaluations and comments for improvement based on the results.

[1294] "Means for monitoring emotional states and analyzing emotional data" refers to algorithms or devices that use sensors such as cameras and microphones to monitor a user's facial expressions and voice in real time and evaluate their emotions.

[1295] "Means for adjusting the difficulty and format of quizzes based on emotional data" refers to a function that changes the content of the quiz according to the user's emotional state, providing an optimal learning experience.

[1296] "Means for generating feedback according to the user's emotional state" refers to a device or program that appropriately generates comments to alleviate stress, encouraging messages, etc., based on the user's emotional state.

[1297] The present invention is a system that inputs learning materials, automatically generates and provides quizzes using an artificial intelligence model, and further improves learning effectiveness by recognizing the user's emotional state. Specific embodiments of this system are described below.

[1298] First, the user prepares learning materials using their device. These learning materials include PDF files, text files, slides, etc. The user then uploads these learning materials to the learning platform. Specifically, the user clicks the "Upload" button on the platform screen, selects the learning materials from the file selection dialog, and presses the "Submit" button.

[1299] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in its storage. The server then inputs the saved learning materials into the AI ​​model, preparing it for analysis.

[1300] The server inputs the learning material into an AI model, which then uses natural language processing techniques to analyze the content of the learning material, including extracting key points and keywords from each chapter or section of the material.

[1301] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The AI ​​model automatically generates quiz questions in various formats (e.g., multiple choice, written) based on the analysis results. The generated quizzes are saved by the server in the " / quizzes / " folder or in a database.

[1302] Next, let us consider the case where a user selects the "Take Quiz" option on the learning platform to take a quiz based on a specific learning module or topic. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device.

[1303] This is where the emotion engine comes into play. The user's device uses a camera and microphone to monitor the user's facial expressions and voice in real time, and the emotion engine analyzes their emotional state. The analyzed emotional data is sent to the server, which then adjusts the difficulty and format of the quiz according to the user's emotional state.

[1304] The user answers the quiz and presses the "Submit Answers" button when they have completed answering all questions. The server receives the answers, automatically evaluates whether they are correct or incorrect, and calculates the score for each quiz question.

[1305] The server also analyzes the user's emotional state while answering the quiz and generates feedback based on the results. For example, if the user is feeling stressed, the server may provide positive feedback and encouraging comments. Specific comments about the user's understanding and areas for improvement may also be provided.

[1306] Finally, the server sends the generated feedback to the user's device and displays it on the user's screen, allowing the user to review the provided feedback and use it to improve their learning.

[1307] As a concrete example, taking corporate training materials, a user uploads PDF materials on business ethics. The server analyzes the content and generates quiz questions such as "What are business ethics?" and "What are the important elements of business ethics?" As the user answers these quizzes, an emotion engine monitors the user's emotional state in real time and adjusts the difficulty of the answers as the user progresses. Feedback based on the results is provided, allowing the user to progress efficiently. This type of system provides flexible support tailored to the state of each individual learner.

[1308] Example prompts to input to a generative AI model:

[1309] "Upload a PDF file on business ethics. Based on this material, please generate multiple-choice and essay questions. Include key points and keywords."

[1310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1311] Step 1:

[1312] The user prepares the learning materials.

[1313] The user uses a device to prepare the learning materials (PDF files, text files, slides, etc.) required for learning. These learning materials are used as input. The output is the prepared learning materials. Specifically, the user collects learning materials from folders on the device or from cloud storage.

[1314] Step 2:

[1315] Users upload learning materials.

[1316] The user accesses the learning platform using a terminal and clicks the "Upload" button. A file selection dialog appears, and the user selects the learning material. Then, the user presses the "Send" button. The input of this operation is the prepared learning material, and the output is the learning material sent to the server. In concrete terms, the user selects the learning material file and uploads it to the platform.

[1317] Step 3:

[1318] The server receives and stores the learning materials.

[1319] The server receives the learning materials sent from the user's device and saves them in the " / uploaded_materials / " folder in the storage. The input is the learning materials sent to the server, and the output is the saved learning materials. Specifically, the server writes the files to a specific folder.

[1320] Step 4:

[1321] The server prepares to analyze the learning material.

[1322] The server prepares the saved learning material for input into the AI ​​model. It checks the file path and format and converts it into the appropriate format. The input is the saved learning material, and the output is data in a format suitable for analysis. Specifically, the server obtains the file path and formats the data as needed.

[1323] Step 5:

[1324] An artificial intelligence model analyzes the learning material.

[1325] The server inputs learning materials into the AI ​​model. The model uses natural language processing technology to analyze the content of the learning materials and extract important points and keywords. The input is data in a format suitable for analysis, and the output is the extracted points and keywords. Specifically, the AI ​​model performs text analysis and extracts important information.

[1326] Step 6:

[1327] The server instructs the artificial intelligence model to generate the quiz.

[1328] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The input is the extracted points and keywords, and the output is the generated quiz questions. Specifically, the server sends the analysis results to the model and provides prompts for quiz generation.

[1329] Step 7:

[1330] An artificial intelligence model generates the quiz.

[1331] Based on the analysis results, the AI ​​model automatically generates quizzes such as multiple choice and written questions. The server saves the generated quizzes in the " / quizzes / " folder or in a database. The input is the quiz generation prompt and the analysis results, and the output is the generated quiz questions. Specifically, the model generates quizzes in an appropriate question format, and the server performs the save operation.

[1332] Step 8:

[1333] The user takes the quiz.

[1334] A user accesses the learning platform on their device and selects the "Take a Quiz" option. The server receives the user's request, selects the appropriate quiz from the " / quizzes / " folder, and sends it to the user's device. The input is a request to take the quiz, and the output is the quiz questions that are displayed on the user's device. Specifically, the user selects a quiz, and the server sends the quiz questions to the device.

[1335] Step 9:

[1336] The terminal monitors the user's emotional state.

[1337] The device uses a camera and microphone to monitor the user's facial expressions and voice in real time. This emotional data is sent to the emotion engine for analysis. The input is the user's real-time facial expressions and voice, and the output is the analyzed emotional data. Specifically, the device's sensors operate, and the emotion engine analyzes the data.

[1338] Step 10:

[1339] The server receives the emotion data and adjusts the quiz.

[1340] The server receives the analyzed emotional data and adjusts the difficulty and format of the quiz according to the user's emotional state. The input is the emotional data, and the output is the adjusted quiz questions. Specifically, the server changes the difficulty parameters of the quiz based on the emotional data.

[1341] Step 11:

[1342] The user answers the quiz.

[1343] The user answers the quiz displayed on the terminal. Once all questions have been answered, the user presses the "Submit Answers" button. The input is the user's answer data, and the output is the answer sent to the server. Specifically, the user selects an answer and performs the submit operation.

[1344] Step 12:

[1345] The server evaluates the quiz answers.

[1346] The server receives the answers sent by the user and evaluates whether they are correct or incorrect. It then calculates the score for each quiz question. The input is the user's answer data, and the output is the evaluation result and score. Specifically, the server analyzes the answer data and calculates the score.

[1347] Step 13:

[1348] The server analyzes the emotional data and generates feedback.

[1349] The server again analyzes the user's emotional state and generates feedback based on the results. For example, if the user is feeling stressed, it generates positive feedback or encouraging comments. It also provides specific comments about the user's level of understanding and areas for improvement. The input is the emotional data during the quiz answer, and the output is the generated feedback. Specifically, the server analyzes the emotional data and creates feedback comments.

[1350] Step 14:

[1351] The server sends feedback.

[1352] The server sends the generated feedback to the user's terminal and displays it on the screen. The input is the generated feedback, and the output is the feedback displayed on the user's terminal. In concrete terms, the server transfers the feedback data to the user's terminal, and the terminal displays it.

[1353] (Application example 2)

[1354] 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."

[1355] Conventional learning systems provide quizzes with a uniform level of difficulty and format without considering the learner's emotional state, resulting in poor learning efficiency. Furthermore, when autonomous vehicle engineers learn new technologies, there is a lack of a way to analyze individual levels of understanding and concentration in real time and provide appropriate feedback accordingly. There is a need to solve these issues and realize more effective learning support.

[1356] 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 a means for inputting learning materials, a means for using an artificial intelligence model to analyze the input learning materials, a means for generating quizzes based on the analysis results, a means for saving the generated quizzes, a means for providing the saved quizzes, a means for receiving answers to the quizzes and generating feedback, and a means for monitoring the user's emotional state and adjusting the difficulty and format of the quiz. This makes it possible to provide quizzes with the optimal difficulty and format according to the learner's emotional state, thereby realizing efficient learning support tailored to each learner. Furthermore, automated vehicle engineers can also receive appropriate feedback through real-time emotion analysis, improving the efficiency of their technical acquisition.

[1357] "Learning materials" refers to teaching materials used in education and training, including PDF files, text files, slides, etc.

[1358] An "artificial intelligence model" is an algorithm or program that can analyze data using techniques such as machine learning and deep learning to perform specific tasks.

[1359] A "quiz" is an assessment tool in the form of questions generated based on learning materials, and can take the form of multiple choice questions or essay questions.

[1360] "Emotional state" refers to data that represents the user's current emotions, including those acquired in real time through facial expressions, voice, etc.

[1361] "Feedback" refers to advice or comments provided based on the evaluation of the user's answers to the quiz.

[1362] "Difficulty" refers to the level that indicates how difficult it is to answer a quiz or assignment.

[1363] "Real-time monitoring" refers to tracking the user's situation in real time and acquiring and analyzing data.

[1364] "Analysis" refers to the process of breaking down learning materials and user data and extracting important elements and patterns.

[1365] "Storage" refers to storing data and generated quizzes in storage so that they can be accessed later.

[1366] "Providing" refers to sending and making accessible the saved quiz and feedback to the user.

[1367] "Monitoring" refers to the process of continuously observing and collecting data about a user's behavior and state.

[1368] The present invention relates to a training system for assisting learning about autonomous vehicles. Specific embodiments of the present invention will be described below.

[1369] Hardware and software used

[1370] 1. Hardware:

[1371] Smartphones, smart glasses, head-mounted displays (hereinafter referred to as "devices")

[1372] Terminal devices with a camera and microphone

[1373] server

[1374] 2. Software:

[1375] Python (data analysis and model execution)

[1376] TensorFlow / PyTorch (training and running artificial intelligence models)

[1377] OpenCV (camera image analysis)

[1378] NLTK / spaCy (Natural Language Processing)

[1379] Flask / Django (Web application framework)

[1380] Data processing and calculation

[1381] The server first receives and stores the learning materials (PDF files, text files, slides, etc.) sent from the device. It then analyzes the stored learning materials using natural language processing technology to extract key points and keywords. Based on the results of this analysis, an artificial intelligence model automatically generates quizzes, including multiple-choice and written questions.

[1382] The generated quiz is stored in a database in the server. When the user selects the "Take Quiz" option, the server sends the corresponding quiz to the terminal.

[1383] While answering the quiz, the device monitors the user's facial expressions and voice in real time through a camera and microphone. This data is analyzed using OpenCV and an emotion analysis model, and data corresponding to the user's emotional state is sent to the server.

[1384] The server adjusts the difficulty and format of the quiz based on the received emotional data, and after the quiz is completed, generates feedback based on the analysis results and sends it to the device.

[1385] Specific examples

[1386] For example, consider a company engineer who wants to learn about a new control algorithm for autonomous vehicles. The engineer uploads a PDF study guide about the control algorithm for autonomous vehicles to the app. The server analyzes the study guide and generates quiz questions such as, "How does the control algorithm for autonomous vehicles work?" and "What are the main risks?"

[1387] As the technician answers the quiz, the technician's facial expressions and voice are monitored through a camera and microphone, and the difficulty of the quiz is adjusted in real time based on the analyzed emotional data, allowing the technician to learn efficiently.

[1388] Example of input prompt for generative AI model:

[1389] Based on the learning material on the theme "Discuss the risks associated with the safety of autonomous vehicles," a quiz was generated in the following format:

[1390] 1. Multiple choice questions:

[1391] 2. Essay questions: 0 questions

[1392] Here is an example of a multiple choice question:

[1393] 1. What are the biggest risks with self-driving vehicles?

[1394] a) Energy efficiency

[1395] b) Sensor failure

[1396] c) Ignoring traffic signals

[1397] Through the above process, a flexible and efficient training system is provided to maximize the learning effect of users.

[1398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1399] Step 1:

[1400] Users upload learning materials to their devices by selecting PDF files, text files, slide decks, etc., and clicking the "Upload" button in the application. The selected files are then sent to the learning platform.

[1401] Step 2:

[1402] The server receives the learning materials sent from the device. The received files are saved in the " / uploaded_materials / " folder on the server. This saving is done as a preparation for analyzing the learning materials.

[1403] Step 3:

[1404] The server analyzes the stored learning materials using natural language processing technology. Specifically, it uses Python and NLTK or spaCy to extract important points and keywords from the content of the learning materials. This analysis clarifies the main points of the learning materials.

[1405] Step 4:

[1406] Based on the analysis results, the server instructs the AI ​​model to generate a quiz. The generative AI model (built with TensorFlow / PyTorch) automatically generates quizzes in the form of multiple choice or essay questions based on the analyzed data. This process creates questions that are in line with the content of the learning material.

[1407] Step 5:

[1408] The generated quizzes are saved in the " / quizzes / " folder on the server or in a database, where they are recorded for later access by users.

[1409] Step 6:

[1410] When a user selects the "Take Quiz" option, the server sends the saved quiz to the device. The user selects a specific learning module or topic and sends a request to the server, which delivers the corresponding quiz to the device.

[1411] Step 7:

[1412] While answering the quiz, the device monitors the user's facial expressions and voice in real time using a camera and microphone. The acquired data is analyzed using OpenCV and an emotion analysis model to determine the user's emotional state. This emotion data is sent to the server while answering the quiz.

[1413] Step 8:

[1414] The server then adjusts the difficulty and format of the quiz based on the received emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or change the format. This adjustment allows the user to learn more effectively.

[1415] Step 9:

[1416] When the user has finished answering the quiz, he / she presses the "Submit Answers" button. The server receives the user's answers and automatically evaluates them, determining whether they are correct or incorrect and calculating the score for each quiz question.

[1417] Step 10:

[1418] The server generates feedback based on the evaluation results and sentiment analysis data. For example, if the user is feeling stressed, the server will provide positive feedback and specific advice, allowing the user to clearly identify areas for improvement.

[1419] Step 11:

[1420] Finally, the server sends the generated feedback to the device. The feedback is displayed on the user's screen and can be used to improve their learning. The analysis results and feedback are also recorded as the user's learning history.

[1421] 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.

[1422] 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.

[1423] 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 robot 414.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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).

[1428] 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.

[1429] 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."

[1430] 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.

[1431] 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).

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] The following is further disclosed regarding the above embodiment.

[1443] (Claim 1)

[1444] a means for inputting learning materials;

[1445] a means for using an artificial intelligence model to analyze the input learning material;

[1446] means for generating a quiz based on the analysis results;

[1447] a means for saving the generated quiz;

[1448] a means for providing the stored quiz;

[1449] a means for receiving responses to the quiz and generating feedback;

[1450] A system including:

[1451] (Claim 2)

[1452] 2. The system of claim 1, wherein the system analyzes the learning material by chapter or section and generates quizzes based on extracted key points and keywords.

[1453] (Claim 3)

[1454] 2. The system according to claim 1, wherein the quiz generation generates quizzes in a number of formats, such as multiple choice questions and essay questions.

[1455] "Example 1"

[1456] (Claim 1)

[1457] means of preparing learning materials;

[1458] a means of inputting and uploading learning materials to the learning platform;

[1459] means for receiving and storing the uploaded learning materials;

[1460] A means for inputting the stored learning material into an artificial intelligence model and analyzing it using natural language processing technology;

[1461] means for generating a quiz based on the analysis results;

[1462] a means for saving the generated quiz;

[1463] means for receiving a quiz request from a user and providing the stored quiz;

[1464] a means for receiving answers to the quiz and automatically evaluating and calculating a score;

[1465] a means for generating and providing feedback based on the evaluation results;

[1466] A system including:

[1467] (Claim 2)

[1468] 2. The system of claim 1, wherein the system analyzes the learning material by chapter or section and generates quizzes based on extracted key points and keywords.

[1469] (Claim 3)

[1470] 2. The system according to claim 1, wherein the quiz generation generates quizzes in a number of formats, such as multiple choice questions and essay questions.

[1471] "Application Example 1"

[1472] (Claim 1)

[1473] a means for inputting learning materials;

[1474] a means for using an artificial intelligence model to analyze the input learning material;

[1475] means for generating a quiz based on the analysis results;

[1476] a means for saving the generated quiz;

[1477] a means for providing the stored quiz;

[1478] a means for receiving responses to the quiz and generating feedback;

[1479] a means for generating quizzes based on work procedures and safety rules, the quiz being installed on the industrial robot;

[1480] a means for presenting the generated quiz to the worker and receiving an answer;

[1481] A system including:

[1482] (Claim 2)

[1483] 2. The system of claim 1, wherein the system analyzes the learning material by chapter or section and generates quizzes based on extracted key points and keywords.

[1484] (Claim 3)

[1485] 2. The system according to claim 1, wherein the quiz generation generates quizzes in a variety of formats, such as multiple choice questions and written questions, and generates quizzes including questions about work procedures and safety rules.

[1486] "Example 2: Combining Emotion Engines"

[1487] (Claim 1)

[1488] a means for inputting learning materials;

[1489] a means for using an artificial intelligence model to analyze the input learning material;

[1490] means for generating a quiz based on the analysis results;

[1491] a means for saving the generated quiz;

[1492] a means for providing the stored quiz;

[1493] a means for receiving responses to the quiz and generating feedback;

[1494] means for monitoring the user's emotional state and analyzing the emotional data;

[1495] a means for adjusting the difficulty level or format of the quiz based on the emotional data;

[1496] means for generating feedback in response to the user's emotional state;

[1497] A system including:

[1498] (Claim 2)

[1499] 2. The system of claim 1, wherein the system analyzes the learning material by chapter or section and generates quizzes based on extracted key points and keywords.

[1500] (Claim 3)

[1501] 2. The system according to claim 1, wherein the quiz generation generates quizzes in a number of formats, such as multiple choice questions and essay questions.

[1502] "Application example 2 when combining emotion engines"

[1503] (Claim 1)

[1504] a means for inputting learning materials;

[1505] a means for using an artificial intelligence model to analyze the input learning material;

[1506] means for generating a quiz based on the analysis results;

[1507] a means for saving the generated quiz;

[1508] a means for providing the stored quiz;

[1509] a means for receiving responses to the quiz and generating feedback;

[1510] means for monitoring the user's emotional state and adjusting the difficulty and format of the quiz;

[1511] A system including:

[1512] (Claim 2)

[1513] 2. The system of claim 1, wherein the system analyzes the learning material by chapter or section and generates quizzes based on extracted key points and keywords.

[1514] (Claim 3)

[1515] 2. The system according to claim 1, wherein the quiz generation generates quizzes in a number of formats, such as multiple choice questions and essay questions.

[1516] (Claim 4)

[1517] 10. The system of claim 1, further comprising means for monitoring the user's facial expressions and voice in real time and analyzing their emotional state.

[1518] (Claim 5)

[1519] 10. The system of claim 1, further comprising means for generating feedback as positive comments and specific improvements based on the user's emotional state. [Explanation of symbols]

[1520] 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 inputting learning materials; a means for using an artificial intelligence model to analyze the input learning material; means for generating a quiz based on the analysis results; a means for saving the generated quiz; a means for providing the stored quiz; a means for receiving responses to the quiz and generating feedback; A system including:

2. 2. The system according to claim 1, wherein the learning material is analyzed by chapter or section, and quizzes are generated based on extracted key points and keywords.

3. The system according to claim 1, wherein the quiz generation generates quizzes in a variety of formats, such as multiple choice questions and written questions.

Images