System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a text of a law or a paper from a user as an input; means for analyzing the received text and extracting a learning item; means for generating a problem and an explanation using a generative AI model based on the extracted learning item; means for presenting the generated problem and explanation to the user and receiving a user's answer; means for evaluating the user's answer, determining next learning content based on a result of the evaluation, and generating a further problem and explanation using the generative AI model; and means for presenting the next learning content to the user.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] Students and working professionals who want to learn law or academic papers in a short period of time face the challenge of having to create questions and sample answers on their own in fields where no textbooks or workbooks exist, making learning time consuming. Furthermore, it is difficult to obtain appropriate evaluation and feedback on the learning content, making it difficult to progress efficiently. The present invention aims to solve these problems by providing a system that uses generative AI to shorten learning time and efficiently deepen understanding. [Means for solving the problem]

[0005] The learning support system of the present invention includes a means for accepting legal or academic text input by a user, analyzing it, and extracting learning items. It also includes a means for generating questions and explanations using a generative AI model based on the extracted learning items, presenting them to the user, and accepting the user's answers. It also includes a means for evaluating the received answers, determining the next learning content based on the evaluation results, and generating the next questions and explanations using the generative AI model. The system also includes a means for presenting questions and explanations generated according to the user's learning level and prioritizing the items that should be studied intensively based on the content of the analyzed text.

[0006] "User" refers to an individual or group who uses the learning support system to study the contents of laws or papers.

[0007] "Text" refers to the sentences and content of the law or paper that the user inputs into the learning support system.

[0008] "Analysis" refers to the process of extracting and analyzing useful information and learning items from the input text.

[0009] "Learning items" refer to important content and topics for learning extracted through analysis.

[0010] A "generative AI model" refers to a program or algorithm that uses artificial intelligence technology to automatically generate questions and explanations that correspond to the user's learning level.

[0011] "Problems" refer to the questions or tasks that the generative AI model creates to assess the user's learning.

[0012] "Explanation" refers to the relevant explanation or interpretation of a problem provided by a generative AI model.

[0013] "Evaluation" refers to the process of analyzing the answers entered by the user and determining their accuracy and level of understanding.

[0014] "Learning level" refers to an index that indicates the user's current level of understanding and depth of knowledge.

[0015] "Priority" refers to the criteria for determining the importance and order of items to be studied based on the analyzed text and study items. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The learning support system of the present invention analyzes legal or academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. The system evaluates the user's answers and provides interactive learning support by providing the next learning content based on the evaluation results. The operation of the entire system is described in detail below.

[0038] User input

[0039] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[0040] Text analysis and learning item extraction

[0041] 1. The terminal sends the entered text to the server.

[0042] 2. The server passes the received text to an analysis engine, which extracts relevant learning items. For example, the analysis engine extracts items such as "Definition of adulthood" and "Corporate responsibility."

[0043] Generate questions and explanations

[0044] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[0045] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0046] Presenting the problem and explanation

[0047] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0048] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[0049] Evaluate your answers and learn what to do next

[0050] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[0051] 2. The server stores the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step.

[0052] 3. The generative AI model generates questions and explanations to promote deeper understanding. For example, it generates a question and explanation for the question, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0053] Feedback and next steps

[0054] 1. The server presents the newly generated questions and explanations to the user, and also suggests priority learning topics, such as "Details of legal responsibility" or "Historical changes in the age of majority."

[0055] 2. The user uses the device to study these new questions and items.

[0056] In this way, the system of the present invention helps users to understand the contents of laws and academic papers efficiently and in a short time, and also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[0060] Step 2:

[0061] The terminal transmits the text data entered by the user to the server.

[0062] Step 3:

[0063] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[0064] Step 4:

[0065] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[0066] Step 5:

[0067] The server requests the generative AI model to generate questions and explanations based on the extracted learning items.

[0068] Step 6:

[0069] The generative AI model receives requests and generates questions and explanations to check the user's current level of understanding. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0070] Step 7:

[0071] The generative AI model returns the generated questions and explanations to the server.

[0072] Step 8:

[0073] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0074] Step 9:

[0075] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[0076] Step 10:

[0077] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[0078] Step 11:

[0079] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[0080] Step 12:

[0081] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0082] Step 13:

[0083] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[0084] Step 14:

[0085] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[0086] In this way, through a multi-step interactive process, the system helps users to understand the content of laws and papers efficiently and deeply.

[0087] Example 1

[0088] 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."

[0089] Conventional learning support systems have difficulty extracting appropriate learning items based on the text entered by the user and generating and providing questions and explanations that are adapted to each individual's learning level. They also lack a mechanism for effectively determining the next learning step based on the evaluation of the user's answers and generating appropriate questions and explanations again. Furthermore, they lacked the ability to dynamically save and regenerate the generated content according to the user's progress, which resulted in a decrease in learning efficiency.

[0090] 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.

[0091] In this invention, the server includes: [means for accepting text as input from a user;] [means for analyzing the received text and extracting learning items;] [means for generating questions and explanations using a generative AI model based on the extracted learning items;] [means for presenting the generated questions and explanations to the user and accepting the user's answers;] [means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model;] [means for presenting the next learning content to the user;] [means for dynamically generating prompt sentences to be input to the generative AI model; and [means for saving the user's learning progress and regenerating appropriate learning content the next time the server is accessed.] This makes it possible to dynamically generate and provide appropriate questions and explanations according to the user's learning progress, thereby improving learning efficiency.

[0092] "User" refers to an individual who accesses the system, inputs legal or academic text, and uses the generated learning content.

[0093] "Text" refers to character string data including the contents of laws and papers.

[0094] "Means for accepting input" refers to a function that provides an interface for a user to send text to the system via a terminal.

[0095] "Analysis engine" refers to a general term for software that analyzes received text and extracts learning items.

[0096] "Learning items" refer to specific themes or keywords that are the subject of education extracted through text analysis.

[0097] "Generative AI model" refers to an artificial intelligence model that automatically generates questions and explanations based on specified prompts.

[0098] "Means for generating questions and explanations" refers to the process of generating questions and explanations based on the learning items extracted using a generative AI model.

[0099] "Means for presenting questions and explanations" refers to a function for transmitting the generated questions and explanations to a terminal so that the user can view them.

[0100] "Means for accepting answers" refers to a function that provides an interface for the system to receive answer data sent by the user.

[0101] The "means for evaluating the answer" refers to the process of comparing the answer submitted by the user with pre-set correct answer data and determining whether it is correct or incorrect.

[0102] The "means for determining the next learning content" refers to a process for determining the next learning content based on the user's evaluation results.

[0103] A "prompt" is an instruction given to a generative AI model, and refers to the input text used to generate an appropriate question and explanation.

[0104] "Means for saving learning progress" refers to the process of saving the user's learning content and assessment results to a database so that they can be referenced the next time they access the site.

[0105] "Means for regeneration" refers to the process of regenerating new, appropriate learning content based on stored learning progress data.

[0106] The learning support system of the present invention analyzes the legal or academic text entered by the user and extracts appropriate learning topics. It then uses a generative AI model to generate questions and explanations based on these learning topics appropriate to the user's learning level and presents them to the user. It evaluates the user's answers and dynamically determines and generates the next learning content based on the results.

[0107] Hardware and software used

[0108] The server uses the following major software components:

[0109] Analysis engine: Natural language processing tool (e.g., Amazon Comprehend)

[0110] Generative AI models: Machine learning models (e.g., OpenAI's GPT-4)

[0111] A terminal is a device (such as a computer or smartphone) that allows users to access the system and input and view data. It also interfaces with the system through a web browser.

[0112] Details of data processing and calculation

[0113] Users enter the text of a law or paper into the system via a web form. For example, they might enter, "I would like to learn about the contents of Article 4 of the Civil Code."

[0114] The device sends the input text to the server, which then passes the received text to an analysis engine, which extracts learning items. For example, "Definition of adulthood" and "Corporate responsibility" may be extracted.

[0115] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question such as, "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation.

[0116] The generated questions and explanations are sent from the server to the terminal and presented to the user. The user answers the questions on the terminal. For example, the user enters the answer "20 years old."

[0117] The device then sends the user's answer back to the server, which evaluates it and determines that "20 years old" is the correct answer. The evaluation results are saved and used to generate new questions and explanations for the next learning step.

[0118] Furthermore, the server sends a prompt for the next learning step to the generative AI model, generating a new question and its explanation, such as, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" This new content is then presented to the user again.

[0119] Examples of concrete examples and prompts

[0120] Specific examples of prompts are given to the generative AI model in the form of, "According to Article 4 of the Civil Code, what is the age of majority?" or "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" Based on this prompt, an appropriate question and explanation are generated.

[0121] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] The user accesses the system using a terminal and inputs the text they wish to study. The input in this case is a legal or academic paper text. Specifically, the user enters "I would like to learn about the contents of Article 4 of the Civil Code" into the web form and clicks the submit button. The input data is the text information entered by the user, and the output data is an HTTP request sent from the terminal to the server.

[0125] Step 2:

[0126] The terminal sends the entered text to the server. Specifically, it sends the text data to the server using an HTTP POST request. The input data is the user input obtained in step 1, and the output data is a request to the analysis engine.

[0127] Step 3:

[0128] The server passes the received text to the analysis engine. The analysis engine analyzes the received text and extracts learning items. For example, "definition of adulthood" and "responsibility" are extracted. Specifically, the server sends an API request to the analysis engine and receives the analysis results in return. The input data is the text information received from the device, and the output data is the learning items returned by the analysis engine.

[0129] Step 4:

[0130] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation. Specifically, the server sends a prompt to the generative AI model and receives the generated text. The input data are the learning items and the user's learning level information from the analysis engine, and the output data are the questions and explanations generated by the generative AI model.

[0131] Step 5:

[0132] The server compiles the generated questions and explanations into a form and sends it to the user's device. Specifically, the server generates an HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the learning content presented on the user's device.

[0133] Step 6:

[0134] The user answers the questions presented on the terminal. Specifically, the user enters the answer "20 years old" into the presented form and clicks the submit button. The input data is the answer information entered by the user, and the output data is the HTTP request sent from the terminal to the server.

[0135] Step 7:

[0136] The terminal sends the user's answer to the server. Specifically, it sends the answer data to the server using an HTTP POST request. The input data is the user's answer, and the output data is the rating request sent to the server.

[0137] Step 8:

[0138] The server evaluates the received answer. For example, it determines that the answer "20 years old" is correct. Specifically, the server compares the received answer with a correct answer database and evaluates the score. The input data is the user's answer received from the terminal, and the output data is the evaluation result.

[0139] Step 9:

[0140] The server saves the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step. For example, it generates a question asking, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" along with its explanation. Specifically, the server sends a new prompt to the generative AI model and receives the generated text. The input data are the evaluation results and information about the next learning step, and the output data are the generated new questions and explanations.

[0141] Step 10:

[0142] The server sends the newly generated questions and explanations to the user's device. Specifically, the server updates the HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the new learning content presented on the user's device.

[0143] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[0144] (Application example 1)

[0145] 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."

[0146] It is difficult for automobile drivers to efficiently learn necessary traffic laws and driving-related laws. Furthermore, conventional educational materials and training programs are difficult to customize to fit each driver's learning level, limiting the effectiveness of learning. The present invention aims to solve these problems and provide a system that allows drivers to efficiently learn traffic laws and related laws.

[0147] 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.

[0148] In this invention, the server includes means for receiving legal or academic text as input from a user, means for analyzing the received text and extracting learning items, means for generating questions and explanations using a generative AI model based on the extracted learning items, means for presenting the generated questions and explanations to the user and accepting the user's answers, means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model, and means for presenting the generated questions and explanations as learning content for automobile drivers. This enables legal education customized to the learning level of each driver.

[0149] A "user" is someone who inputs legal or academic text into the system and studies it.

[0150] "Law" refers to the rules and norms established to maintain social order.

[0151] A "thesis" is an academic piece of writing that summarizes the results of in-depth research on a particular topic.

[0152] "Text" refers to content written as sentences or character strings.

[0153] "Analysis" is the process of breaking down and analyzing the input text and extracting the necessary information from it.

[0154] "Study items" are specific themes or points that are extracted from the analyzed text and that the user should study.

[0155] A "generative AI model" is a system that uses artificial intelligence to automatically create questions and explanations based on input information.

[0156] A "problem" is a question presented to the user to check their understanding or to stimulate their thinking.

[0157] An "explanation" is a piece of text that provides an answer to a question or additional information to deepen understanding.

[0158] "Traffic rules" refer to laws and rules established to regulate the operation of automobiles and the behavior of pedestrians.

[0159] "Driver" means a person who drives a motor vehicle.

[0160] A "server" is a device or system that processes and stores data and communicates with user terminals.

[0161] "Customization" means adjusting and modifying to suit the needs and learning level of each individual user.

[0162] "Legal education" refers to educational programs that provide knowledge and deepen understanding of laws and regulations.

[0163] The learning support system of the present invention is designed to enable automobile drivers to efficiently study traffic regulations and driving-related laws. The system accepts legal or academic texts as input from the user, analyzes them to extract learning items, and generates questions and explanations using a generative AI model. Specific embodiments of the present invention are described below.

[0164] Hardware and Software Configuration

[0165] The hardware used is mainly mobile devices such as smartphones and head-mounted displays (HMDs). The server is a high-performance computer system, and it is also possible to use a cloud server.

[0166] The software used is as follows:

[0167] Program implementation using Python

[0168] Text analysis engine (Example: TextAnalysisEngine)

[0169] Generative AI models (e.g., ProblemGenerator)

[0170] Server API

[0171] System Operation

[0172] 1. User Input

[0173] Users access the system using a smartphone or HMD and input the text of the traffic regulations or related laws they want to learn about. For example, they can say, "I want to learn about laws regarding autonomous vehicles."

[0174] 2. Text analysis and learning item extraction

[0175] The server sends the received text to an analysis engine, which then analyzes the text and extracts relevant learning items, such as "definition of an autonomous vehicle" and "qualifications for a vehicle operation manager."

[0176] 3. Generating Problems and Explanations

[0177] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model generates an appropriate question and explanation. For example, it generates a question such as, "What qualifications are required to operate an autonomous vehicle?" along with its explanation.

[0178] 4. Presenting the problem and explanation

[0179] The server compiles the generated questions and explanations into a form and sends it to the user's terminal, where the user answers the questions.

[0180] 5. Evaluate your answers and provide next steps

[0181] The server receives the user's answer, evaluates it, and requests the AI ​​model to generate a new question and explanation for the next learning step based on the evaluation results. For example, it generates a more in-depth question such as "Why do autonomous vehicle operation managers need to be certified?" along with its explanation.

[0182] Specific examples

[0183] User Scenario

[0184] The user puts on the HMD and launches the application. They voice-input "I want to learn about the laws regarding autonomous vehicles." The system analyzes the input text and extracts relevant learning items, such as "the definition of an autonomous vehicle" and "responsibility." Based on the extracted learning items, questions such as "What qualifications are required to operate an autonomous vehicle?" and their explanations are generated. The user answers the presented questions, and the system evaluates their answers. If the answer is correct, they proceed to the next learning step; if the answer is incorrect, a detailed explanation of the same item is provided again.

[0185] Prompt Sentence Examples

[0186] Entered law text: "Law Concerning the Operation of Autonomous Vehicles"

[0187] Output format: Choose three relevant learning topics and generate questions and explanations for each.

[0188] Output format:

[0189] 1. Learning Item: Definition of Autonomous Vehicle

[0190] Question: Define what an autonomous vehicle is.

[0191] Explanation: An autonomous vehicle is a vehicle that can drive autonomously without driver intervention.

[0192] 2. Learning items: Operation manager qualifications

[0193] Question: What qualifications are required to operate a self-driving vehicle?

[0194] Explanation: In order to operate an autonomous vehicle, you need to be qualified as an operations manager.

[0195] 3. Learning Item: Responsibility

[0196] The question: Who is liable in the event of an accident while driving a self-driving car?

[0197] Explanation: The responsibility for an accident lies primarily with the operation manager, but in some cases the manufacturer or software provider may also be held responsible.

[0198] This will provide a system that allows drivers to efficiently learn about traffic regulations and driving-related laws.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] Users access the system using a smartphone or head-mounted display (HMD) and input the text of the traffic regulations and related laws they want to learn. The input text is sent by the device to the server. The input here is text data, and this data is analyzed in the next step.

[0202] Step 2:

[0203] The server passes the received text to an analysis engine for text analysis. The analysis engine breaks down the input text, analyzes each provision of the law and related information, and extracts learning items. The extracted learning items are, for example, "Definition of an autonomous vehicle" or "Qualifications of a traffic manager." The input is text data, and the output is a list of extracted learning items.

[0204] Step 3:

[0205] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "What qualifications are required to operate an autonomous vehicle?" along with its explanation. The input is a list of learning items and the user's learning level data, and the output is a pair of generated questions and explanations.

[0206] Step 4:

[0207] The server compiles the generated questions and explanations into a form and sends it to the user's terminal. The user answers the questions on the terminal. The input here is the generated form, and the user's output is the answer data.

[0208] Step 5:

[0209] The server receives the user's answer and evaluates it. The evaluation engine analyzes the answer and determines whether it is correct or incorrect. Based on the evaluation results, it requests the AI ​​model again to generate new questions and explanations for the next learning step. The input is the answer data, and the output is the evaluation results and new questions and explanations for the next learning step.

[0210] Step 6:

[0211] The server presents the newly generated problem and explanation to the user and provides specific feedback to further deepen learning. For example, it provides a problem such as "Who is responsible in the event of an accident during autonomous driving?" along with its explanation. The input is the new problem and explanation, and the output is feedback to the user and instructions for the next learning step.

[0212] These processing steps allow the user to efficiently learn traffic and driving laws.

[0213] 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.

[0214] The learning support system of the present invention analyzes legal and academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions during the learning process, the present invention also provides learning support appropriate to the user's emotional state. The operation of the entire system is explained in detail below.

[0215] User input

[0216] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[0217] Text analysis and learning item extraction

[0218] 1. The terminal sends the entered text data to the server.

[0219] 2. The server passes the received text data to the analysis engine, which analyzes the text content.

[0220] 3. The server uses an analysis engine to extract learning items from the input text, such as "Definition of adulthood" and "Corporate responsibility."

[0221] Emotion recognition by emotion engine

[0222] 1. The server receives sensor data from the camera, microphone, etc. from the user's device and passes it to the emotion engine.

[0223] 2. The emotion engine analyzes sensor data and recognizes the user's emotional state, such as whether the user is confused, focused, or relaxed.

[0224] 3. The server stores the recognized emotional state and records the emotional data along with the learning history.

[0225] Generate questions and explanations

[0226] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[0227] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0228] Emotion-aware adjustment

[0229] 1. The server adjusts the generated questions and explanations to suit the user's emotional state based on the user's emotional state recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[0230] Presenting the problem and explanation

[0231] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0232] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[0233] Evaluate your answers and learn what to do next

[0234] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[0235] 2. The server stores the evaluation results and sends a new request to the generative AI model for the next learning step.

[0236] 3. The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0237] Feedback and next steps

[0238] 1. The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[0239] 2. The user uses the device to check new questions and explanations and learn the next item to study.

[0240] In this way, the system of the present invention takes into account the user's emotional state and helps them understand the content of laws and academic papers efficiently and deeply. It also uses an emotion engine to optimize the user's learning experience, reducing stress and burden, thereby achieving effective learning.

[0241] The processing flow will be explained below.

[0242] Step 1:

[0243] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[0244] Step 2:

[0245] The terminal transmits the input text data to the server.

[0246] Step 3:

[0247] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[0248] Step 4:

[0249] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[0250] Step 5:

[0251] The server receives sensor data from cameras, microphones, and other devices from the user's device and passes it on to the emotion engine.

[0252] Step 6:

[0253] The emotion engine analyzes sensor data to recognize the user's emotional state, for example, whether the user is confused, focused, or relaxed.

[0254] Step 7:

[0255] The server stores the recognized emotional states and records the emotional data along with the learning history.

[0256] Step 8:

[0257] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level and emotional state.

[0258] Step 9:

[0259] The generative AI model receives requests and generates questions and explanations that take into account the user's current level of understanding and emotional state. For example, it generates a question and explanation for the question, "According to Article 4 of the Civil Code, what is the age of majority?"

[0260] Step 10:

[0261] The generative AI model returns the generated questions and explanations to the server.

[0262] Step 11:

[0263] The server then optimally adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[0264] Step 12:

[0265] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0266] Step 13:

[0267] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[0268] Step 14:

[0269] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[0270] Step 15:

[0271] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[0272] Step 16:

[0273] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0274] Step 17:

[0275] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[0276] Step 18:

[0277] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[0278] Through this multi-step interactive process, the system helps users understand the content of laws and papers efficiently and deeply while taking into account their emotional state. It also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[0279] Example 2

[0280] 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."

[0281] Conventional learning support systems have the problem of only providing uniform content without fully considering the user's individual learning level or emotional state. This makes it difficult to improve the user's understanding and maximize learning efficiency. Furthermore, they lack the functionality to focus on specific learning items based on the content of the analyzed text, making it difficult to create an efficient learning plan.

[0282] 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.

[0283] In this invention, the server includes: means for accepting legal or academic text as input from a user; means for analyzing the received text and extracting study items; means for generating questions and explanations using a generative AI model based on the extracted study items; means for presenting the generated questions and explanations to the user and accepting the user's answers; means for evaluating the user's answers, determining the next study content based on the evaluation results, and generating further questions and explanations using the generative AI model; means for presenting the next study content to the user; means for accepting sensor data to recognize the user's emotional state and analyzing the user's emotions using an emotion engine; and means for adjusting the study content based on the user's emotional state. This allows for efficient learning by providing optimal study content and questions based on the user's individual learning level and emotional state. Furthermore, by suggesting key study items based on the content of the analyzed text, the server can also improve the efficiency of study plans.

[0284] A "user" is an entity that operates the learning support system and inputs legal or academic text.

[0285] A "terminal" is an electronic device that a user uses to input legal or academic text, and that also has the ability to communicate with a server.

[0286] The "server" is an information processing device that analyzes data received from the terminal, extracts study items, generates questions and explanations, and recognizes the user's emotional state.

[0287] "Text" refers to textual information about laws and papers that users input into the system.

[0288] An "analysis engine" is a software tool that analyzes received text data and extracts learning items.

[0289] "Learning items" are important concepts or themes that users should learn, extracted from the analyzed text.

[0290] A "generative AI model" is an artificial intelligence technology that generates appropriate questions and explanations based on the user's learning items and learning level.

[0291] A "sensor" is a device, such as a camera or microphone, that collects data about the user's emotional state.

[0292] An "emotion engine" is a software tool that analyzes sensor data and recognizes the user's emotional state.

[0293] "Questions and explanations" are questions and explanations generated by the generative AI model for users to answer.

[0294] The "learning level" is an index that indicates the level of understanding and amount of knowledge of each user.

[0295] A "rating engine" is a software tool that evaluates a user's answers and determines whether they are correct or incorrect.

[0296] A "database" is an information management system for storing data such as a user's learning history and emotional state.

[0297] The learning support system of the present invention is designed to improve users' understanding of the learning content. The system accepts input from users of legal or academic texts, analyzes the input, generates appropriate questions and explanations using a generative AI model, and provides personalized learning support that also takes into account the user's emotional state.

[0298] Hardware and software used

[0299] Hardware:

[0300] 1. User's device: PC, tablet, smartphone, etc. This is the device on which the user inputs text and learns.

[0301] 2. Server: The central information processing unit that performs data analysis and runs models.

[0302] software:

[0303] 1. Analysis engine: A Natural Language Processing (NLP) tool, such as SpaCy or NLTK, is used to analyze text data.

[0304] 2. Generative AI model: For example, use OpenAI's GPT-4 to generate questions and explanations.

[0305] 3. Emotion engine: Analyze the user's emotional state using, for example, Affectiva or Microsoft Azure Emotion API.

[0306] System operation explanation

[0307] 1. A user accesses the system using a terminal and enters the text of the law or paper they wish to study. For example, they may enter, "I would like to learn the contents of Article 4 of the Civil Code."

[0308] 2. The device sends the entered text data to the server, using the HTTPS protocol to ensure secure data transmission.

[0309] 3. The server passes the received text data to an analysis engine (e.g., SpaCy or NLTK) and analyzes the text content through natural language processing, including tokenization, part-of-speech tagging, and dependency analysis.

[0310] 4. The server uses an analysis engine to extract important learning points from the input text, for example, identifying items such as "Definition of Adulthood" and "Corporate Responsibility," and creates a list of learning points.

[0311] 5. The server receives sensor data from the user's device, such as the camera and microphone, and passes it to an emotion engine (e.g., Affectiva or Microsoft Azure Emotion API) to analyze the user's emotional state. For example, it analyzes the user's facial expressions and tone of voice to recognize emotional states such as confusion, concentration, and relaxation.

[0312] 6. The server saves the recognized emotional state information and records the emotional data together with the learning history in a database.

[0313] 7. The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The request also includes a prompt such as "User's learning level: intermediate." The generative AI model generates an appropriate question and explanation based on the request. For example, it generates a question and explanation such as, "According to Article 4 of the Civil Code, what is the age of majority?"

[0314] 8. The server adjusts the generated questions and explanations appropriately based on the user's emotional state recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user.

[0315] 9. The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format or similar.

[0316] 10. The user answers the question on their device. For example, they might type, "According to Article 4 of the Civil Code, the age of majority is 20 years old."

[0317] In this way, efficient and personalized learning support is realized, taking into account the user's individual learning level and emotional state. Furthermore, by suggesting key learning topics based on the analyzed text content, the system can also improve the efficiency of learning plans.

[0318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0319] Step 1:

[0320] A user accesses the system using a terminal and inputs the text of the law or paper they want to study. For example, a user might input "I want to learn the contents of Article 4 of the Civil Code." This input text becomes the data source for the subsequent analysis steps.

[0321] Step 2:

[0322] The terminal sends the entered text data to the server, which securely transmits the data using the HTTPS protocol. The server receives the input data and moves on to the next analysis step.

[0323] Step 3:

[0324] The server passes the received text data to an analysis engine (e.g., SpaCy). This analysis engine tokenizes the text, tags it with parts of speech, and analyzes dependencies. The analysis results in data that includes part-of-speech information and dependencies for each token.

[0325] Step 4:

[0326] The server uses an analysis engine to extract important learning points from the input text. For example, it identifies items such as "definition of adulthood" and "responsibility" and creates a list of learning points. The extracted learning points are passed on to the next step, sentiment analysis.

[0327] Step 5:

[0328] The server receives sensor data from the user's device, such as from the camera and microphone. This sensor data includes facial expressions and vocal tone. The collected sensor data is then analyzed by the emotion engine.

[0329] Step 6:

[0330] The server passes the sensor data to an emotion engine (e.g., Affectiva) to analyze the user's emotional state. The emotion engine uses machine learning models to determine whether the user is confused, focused, relaxed, etc. The analysis results are stored as emotion recognition data.

[0331] Step 7:

[0332] The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The prompt includes information such as "User's learning level: intermediate." The generative AI model generates appropriate questions and explanations based on the request.

[0333] Step 8:

[0334] The generative AI model generates a question and explanation based on the request. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?" This generated data is sent back to the server.

[0335] Step 9:

[0336] The server adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user. This adjustment data is finally sent to the user.

[0337] Step 10:

[0338] The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format, etc. The user answers the questions presented on their own device.

[0339] Step 11:

[0340] The user answers the questions presented on the terminal. For example, they might enter "According to Article 4 of the Civil Code, the age of majority is 20 years old." This input data is sent as the answer to the next evaluation step.

[0341] Step 12:

[0342] The device sends the user's answer to the server, which then analyzes the answer using an evaluation engine to determine whether it is correct. For example, the answer "20 years old" is recorded as the correct answer.

[0343] Step 13:

[0344] The server stores the evaluation results in a database and sends the generative AI model a new request for the next learning step, including a prompt such as "Prepare the next question on accountability."

[0345] Step 14:

[0346] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0347] Step 15:

[0348] The server presents the generated questions and explanations to the user, and also displays a prioritized list of important learning topics, such as "Details of Accountability" and "Historical Changes in the Age of Majority."

[0349] Step 16:

[0350] The user can then use the device to check new questions and explanations and select the next item to study. This provides efficient and personalized learning support that takes into account the user's individual learning level and emotional state.

[0351] (Application example 2)

[0352] 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."

[0353] Current learning support systems provide uniform learning content without considering the user's emotional state, which can lead to confusion and stress. Furthermore, when providing instructions to robots in factory work, it is difficult to provide appropriate feedback based on the situation or environment, making efficient work instruction difficult. Therefore, there is a need to provide dynamic learning support that adapts to the situation of the user or robot.

[0354] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0355] In this invention, the server includes: [means for receiving legal or academic text as input from a user]; [means for analyzing the received text and extracting learning items]; and [means for generating questions and explanations using a generative AI model based on the extracted learning items]. This enables dynamic adjustment of learning content according to the emotional state and environment of the user or robot.

[0356] A "law" is a set of rules established by the national or local government to maintain social order.

[0357] A "paper" is a document that presents the results of academic research in written form.

[0358] "Text" is a body of writing or written content.

[0359] "User" means a person or device that uses the system.

[0360] A "learning item" is a specific content or topic to be learned.

[0361] A "generative AI model" is an algorithm that uses artificial intelligence to automatically generate questions and explanations.

[0362] "Questions" are questions used to evaluate the learning content.

[0363] "Explanation" provides answers, additional information, and explanations to questions.

[0364] An "emotion recognition means" is a device or algorithm for recognizing the emotional state of a user or a robot.

[0365] "Learning content" refers to the specific information and knowledge that users and robots should learn.

[0366] "Evaluation" refers to judging the correctness and quality of the user's answer.

[0367] "Feedback" refers to the provision of guidance and information based on the user's learning results and the robot's working status.

[0368] "Environment" is the physical or situational conditions in which learning or work takes place.

[0369] "Dynamic adjustment" means changing learning content in real time depending on the situation and emotional state.

[0370] This invention applies a learning support system to provide work guidance to robots in a factory. This system uses the following software and hardware.

[0371] Software and hardware used:

[0372] Software: Generative AI models (using Hugging Face's Transformers), text analysis APIs, emotion recognition algorithms

[0373] Hardware: Robot camera (using OpenCV), server, user terminal

[0374] System operation description:

[0375] 1. Text input from the user:

[0376] Users access the system using a terminal and input the text of the law or paper they wish to study.

[0377] This is done by entering a specific prompt sentence, such as "I would like to learn about the contents of Article 4 of the Civil Code."

[0378] 2. Text analysis and learning item extraction:

[0379] The terminal transmits the input text data to the server.

[0380] The server uses a text analysis API to analyze the content of the text and extract learning items.

[0381] 3. Generating Problems and Explanations:

[0382] The server sends a request to the generative AI model based on the extracted learning items.

[0383] The generative AI model generates questions and explanations in response to user prompts.

[0384] For example, the question "According to Article 4 of the Civil Code, what is the age of majority?" and its explanation are generated.

[0385] 4. Emotion Recognition and Feedback:

[0386] The server uses images captured by the robot's camera and passes them to an emotion recognition algorithm to recognize the robot's emotional state.

[0387] Emotion recognition algorithms detect states such as confusion, concentration, and relaxation from the robot's facial expressions and movements.

[0388] The server adjusts the learning content based on the perceived emotional state: for example, if the robot is confused, it will lower the difficulty of the questions or add more detailed explanations.

[0389] 5. Providing Feedback:

[0390] The adjusted learning content is sent to the terminal and presented to the user or robot.

[0391] The user or robot answers the adjusted questions and sends the results back to the server.

[0392] The server evaluates the answers and generates learning content for the next step.

[0393] Examples:

[0394] If a user inputs "I want to learn about Article 4 of the Civil Code," the generative AI model generates a question and explanation: "According to Article 4 of the Civil Code, what is the age of majority?" The robot's camera recognizes the user's confused state and provides a detailed explanation with a lower level of difficulty. This improves the robot's learning efficiency.

[0395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0396] Step 1:

[0397] The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, they input a prompt such as, "I would like to learn about Article 4 of the Civil Code." The input data is text data.

[0398] Step 2:

[0399] The device sends the input text data to the server. The server uses a text analysis API to analyze the content of the text and extracts learning items. For example, items such as "Definition of adulthood" and "Corporate responsibility" are extracted. The input is text data, and the output is learning items.

[0400] Step 3:

[0401] The server sends the extracted learning items as requests to the generative AI model, which then generates questions and explanations. For example, a question and explanation might be generated for "According to Article 4 of the Civil Code, what is the age of majority?" The input is the learning item, and the output is the question and explanation.

[0402] Step 4:

[0403] The server sends the questions and explanations to the terminal to present to the user or robot. The terminal displays the generated questions and explanations to the user and accepts the user's answers. The input is the questions and explanations, and the output is the user's answers.

[0404] Step 5:

[0405] Images captured by the robot's camera are sent to the server, which then uses an emotion recognition algorithm to recognize the robot's emotional state, such as confusion, concentration, or relaxation. The input is image data, and the output is the emotional state.

[0406] Step 6:

[0407] The server adjusts the generated learning content based on the recognized emotional state. For example, if the robot is confused, it may lower the difficulty of the questions or add more detailed explanations. The input is the emotional state and the learning content, and the output is the adjusted learning content.

[0408] Step 7:

[0409] The server sends the adjusted learning content to the terminal and presents it to the user or robot. The input is the adjusted learning content, and the output is the presentation of the learning content.

[0410] Step 8:

[0411] The user or robot answers the adjusted questions and sends the results back to the server via the terminal. The server evaluates the user's answers and sends a request to the generative AI model to determine the next learning step. The input is the user's answer, and the output is the next learning content.

[0412] Step 9:

[0413] The generative AI model generates questions and explanations corresponding to the next learning content and returns them to the server. The server then sends the newly generated questions and explanations to the device and presents them to the user or robot as the next learning content. This provides continuous and dynamic learning support. The input is a learning step request, and the output is a new question and explanation.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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."

[0430] The learning support system of the present invention analyzes legal or academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. The system evaluates the user's answers and provides interactive learning support by providing the next learning content based on the evaluation results. The operation of the entire system is described in detail below.

[0431] User input

[0432] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[0433] Text analysis and learning item extraction

[0434] 1. The terminal sends the entered text to the server.

[0435] 2. The server passes the received text to an analysis engine, which extracts relevant learning items. For example, the analysis engine extracts items such as "Definition of adulthood" and "Corporate responsibility."

[0436] Generate questions and explanations

[0437] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[0438] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0439] Presenting the problem and explanation

[0440] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0441] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[0442] Evaluate your answers and learn what to do next

[0443] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[0444] 2. The server stores the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step.

[0445] 3. The generative AI model generates questions and explanations to promote deeper understanding. For example, it generates a question and explanation for the question, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0446] Feedback and next steps

[0447] 1. The server presents the newly generated questions and explanations to the user, and also suggests priority learning topics, such as "Details of legal responsibility" or "Historical changes in the age of majority."

[0448] 2. The user uses the device to study these new questions and items.

[0449] In this way, the system of the present invention helps users to understand the contents of laws and academic papers efficiently and in a short time, and also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[0453] Step 2:

[0454] The terminal transmits the text data entered by the user to the server.

[0455] Step 3:

[0456] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[0457] Step 4:

[0458] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[0459] Step 5:

[0460] The server requests the generative AI model to generate questions and explanations based on the extracted learning items.

[0461] Step 6:

[0462] The generative AI model receives requests and generates questions and explanations to check the user's current level of understanding. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0463] Step 7:

[0464] The generative AI model returns the generated questions and explanations to the server.

[0465] Step 8:

[0466] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0467] Step 9:

[0468] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[0469] Step 10:

[0470] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[0471] Step 11:

[0472] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[0473] Step 12:

[0474] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0475] Step 13:

[0476] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[0477] Step 14:

[0478] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[0479] In this way, through a multi-step interactive process, the system helps users to understand the content of laws and papers efficiently and deeply.

[0480] Example 1

[0481] 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."

[0482] Conventional learning support systems have difficulty extracting appropriate learning items based on the text entered by the user and generating and providing questions and explanations that are adapted to each individual's learning level. They also lack a mechanism for effectively determining the next learning step based on the evaluation of the user's answers and generating appropriate questions and explanations again. Furthermore, they lacked the ability to dynamically save and regenerate the generated content according to the user's progress, which resulted in a decrease in learning efficiency.

[0483] 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.

[0484] In this invention, the server includes: [means for accepting text as input from a user;] [means for analyzing the received text and extracting learning items;] [means for generating questions and explanations using a generative AI model based on the extracted learning items;] [means for presenting the generated questions and explanations to the user and accepting the user's answers;] [means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model;] [means for presenting the next learning content to the user;] [means for dynamically generating prompt sentences to be input to the generative AI model; and [means for saving the user's learning progress and regenerating appropriate learning content the next time the server is accessed.] This makes it possible to dynamically generate and provide appropriate questions and explanations according to the user's learning progress, thereby improving learning efficiency.

[0485] "User" refers to an individual who accesses the system, inputs legal or academic text, and uses the generated learning content.

[0486] "Text" refers to character string data including the contents of laws and papers.

[0487] "Means for accepting input" refers to a function that provides an interface for a user to send text to the system via a terminal.

[0488] "Analysis engine" refers to a general term for software that analyzes received text and extracts learning items.

[0489] "Learning items" refer to specific themes or keywords that are the subject of education extracted through text analysis.

[0490] "Generative AI model" refers to an artificial intelligence model that automatically generates questions and explanations based on specified prompts.

[0491] "Means for generating questions and explanations" refers to the process of generating questions and explanations based on the learning items extracted using a generative AI model.

[0492] "Means for presenting questions and explanations" refers to a function for transmitting the generated questions and explanations to a terminal so that the user can view them.

[0493] "Means for accepting answers" refers to a function that provides an interface for the system to receive answer data sent by the user.

[0494] The "means for evaluating the answer" refers to the process of comparing the answer submitted by the user with pre-set correct answer data and determining whether it is correct or incorrect.

[0495] The "means for determining the next learning content" refers to a process for determining the next learning content based on the user's evaluation results.

[0496] A "prompt" is an instruction given to a generative AI model, and refers to the input text used to generate an appropriate question and explanation.

[0497] "Means for saving learning progress" refers to the process of saving the user's learning content and assessment results to a database so that they can be referenced the next time they access the site.

[0498] "Means for regeneration" refers to the process of regenerating new, appropriate learning content based on stored learning progress data.

[0499] The learning support system of the present invention analyzes the legal or academic text entered by the user and extracts appropriate learning topics. It then uses a generative AI model to generate questions and explanations based on these learning topics appropriate to the user's learning level and presents them to the user. It evaluates the user's answers and dynamically determines and generates the next learning content based on the results.

[0500] Hardware and software used

[0501] The server uses the following major software components:

[0502] Analysis engine: Natural language processing tool (e.g., Amazon Comprehend)

[0503] Generative AI models: Machine learning models (e.g., OpenAI's GPT-4)

[0504] A terminal is a device (such as a computer or smartphone) that allows users to access the system and input and view data. It also interfaces with the system through a web browser.

[0505] Details of data processing and calculation

[0506] Users enter the text of a law or paper into the system via a web form. For example, they might enter, "I would like to learn about the contents of Article 4 of the Civil Code."

[0507] The device sends the input text to the server, which then passes the received text to an analysis engine, which extracts learning items. For example, "Definition of adulthood" and "Corporate responsibility" may be extracted.

[0508] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question such as, "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation.

[0509] The generated questions and explanations are sent from the server to the terminal and presented to the user. The user answers the questions on the terminal. For example, the user enters the answer "20 years old."

[0510] The device then sends the user's answer back to the server, which evaluates it and determines that "20 years old" is the correct answer. The evaluation results are saved and used to generate new questions and explanations for the next learning step.

[0511] Furthermore, the server sends a prompt for the next learning step to the generative AI model, generating a new question and its explanation, such as, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" This new content is then presented to the user again.

[0512] Examples of concrete examples and prompts

[0513] Specific examples of prompts are given to the generative AI model in the form of, "According to Article 4 of the Civil Code, what is the age of majority?" or "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" Based on this prompt, an appropriate question and explanation are generated.

[0514] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[0515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0516] Step 1:

[0517] The user accesses the system using a terminal and inputs the text they wish to study. The input in this case is a legal or academic paper text. Specifically, the user enters "I would like to learn about the contents of Article 4 of the Civil Code" into the web form and clicks the submit button. The input data is the text information entered by the user, and the output data is an HTTP request sent from the terminal to the server.

[0518] Step 2:

[0519] The terminal sends the entered text to the server. Specifically, it sends the text data to the server using an HTTP POST request. The input data is the user input obtained in step 1, and the output data is a request to the analysis engine.

[0520] Step 3:

[0521] The server passes the received text to the analysis engine. The analysis engine analyzes the received text and extracts learning items. For example, "definition of adulthood" and "responsibility" are extracted. Specifically, the server sends an API request to the analysis engine and receives the analysis results in return. The input data is the text information received from the device, and the output data is the learning items returned by the analysis engine.

[0522] Step 4:

[0523] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation. Specifically, the server sends a prompt to the generative AI model and receives the generated text. The input data are the learning items and the user's learning level information from the analysis engine, and the output data are the questions and explanations generated by the generative AI model.

[0524] Step 5:

[0525] The server compiles the generated questions and explanations into a form and sends it to the user's device. Specifically, the server generates an HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the learning content presented on the user's device.

[0526] Step 6:

[0527] The user answers the questions presented on the terminal. Specifically, the user enters the answer "20 years old" into the presented form and clicks the submit button. The input data is the answer information entered by the user, and the output data is the HTTP request sent from the terminal to the server.

[0528] Step 7:

[0529] The terminal sends the user's answer to the server. Specifically, it sends the answer data to the server using an HTTP POST request. The input data is the user's answer, and the output data is the rating request sent to the server.

[0530] Step 8:

[0531] The server evaluates the received answer. For example, it determines that the answer "20 years old" is correct. Specifically, the server compares the received answer with a correct answer database and evaluates the score. The input data is the user's answer received from the terminal, and the output data is the evaluation result.

[0532] Step 9:

[0533] The server saves the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step. For example, it generates a question asking, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" along with its explanation. Specifically, the server sends a new prompt to the generative AI model and receives the generated text. The input data are the evaluation results and information about the next learning step, and the output data are the generated new questions and explanations.

[0534] Step 10:

[0535] The server sends the newly generated questions and explanations to the user's device. Specifically, the server updates the HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the new learning content presented on the user's device.

[0536] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[0537] (Application example 1)

[0538] 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."

[0539] It is difficult for automobile drivers to efficiently learn necessary traffic laws and driving-related laws. Furthermore, conventional educational materials and training programs are difficult to customize to fit each driver's learning level, limiting the effectiveness of learning. The present invention aims to solve these problems and provide a system that allows drivers to efficiently learn traffic laws and related laws.

[0540] 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.

[0541] In this invention, the server includes means for receiving legal or academic text as input from a user, means for analyzing the received text and extracting learning items, means for generating questions and explanations using a generative AI model based on the extracted learning items, means for presenting the generated questions and explanations to the user and accepting the user's answers, means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model, and means for presenting the generated questions and explanations as learning content for automobile drivers. This enables legal education customized to the learning level of each driver.

[0542] A "user" is someone who inputs legal or academic text into the system and studies it.

[0543] "Law" refers to the rules and norms established to maintain social order.

[0544] A "thesis" is an academic piece of writing that summarizes the results of in-depth research on a particular topic.

[0545] "Text" refers to content written as sentences or character strings.

[0546] "Analysis" is the process of breaking down and analyzing the input text and extracting the necessary information from it.

[0547] "Study items" are specific themes or points that are extracted from the analyzed text and that the user should study.

[0548] A "generative AI model" is a system that uses artificial intelligence to automatically create questions and explanations based on input information.

[0549] A "problem" is a question presented to the user to check their understanding or to stimulate their thinking.

[0550] An "explanation" is a piece of text that provides an answer to a question or additional information to deepen understanding.

[0551] "Traffic rules" refer to laws and rules established to regulate the operation of automobiles and the behavior of pedestrians.

[0552] "Driver" means a person who drives a motor vehicle.

[0553] A "server" is a device or system that processes and stores data and communicates with user terminals.

[0554] "Customization" means adjusting and modifying to suit the needs and learning level of each individual user.

[0555] "Legal education" refers to educational programs that provide knowledge and deepen understanding of laws and regulations.

[0556] The learning support system of the present invention is designed to enable automobile drivers to efficiently study traffic regulations and driving-related laws. The system accepts legal or academic texts as input from the user, analyzes them to extract learning items, and generates questions and explanations using a generative AI model. Specific embodiments of the present invention are described below.

[0557] Hardware and Software Configuration

[0558] The hardware used is mainly mobile devices such as smartphones and head-mounted displays (HMDs). The server is a high-performance computer system, and it is also possible to use a cloud server.

[0559] The software used is as follows:

[0560] Program implementation using Python

[0561] Text analysis engine (Example: TextAnalysisEngine)

[0562] Generative AI models (e.g., ProblemGenerator)

[0563] Server API

[0564] System Operation

[0565] 1. User Input

[0566] Users access the system using a smartphone or HMD and input the text of the traffic regulations or related laws they want to learn about. For example, they can say, "I want to learn about laws regarding autonomous vehicles."

[0567] 2. Text analysis and learning item extraction

[0568] The server sends the received text to an analysis engine, which then analyzes the text and extracts relevant learning items, such as "definition of an autonomous vehicle" and "qualifications for a vehicle operation manager."

[0569] 3. Generating Problems and Explanations

[0570] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model generates an appropriate question and explanation. For example, it generates a question such as, "What qualifications are required to operate an autonomous vehicle?" along with its explanation.

[0571] 4. Presenting the problem and explanation

[0572] The server compiles the generated questions and explanations into a form and sends it to the user's terminal, where the user answers the questions.

[0573] 5. Evaluate your answers and provide next steps

[0574] The server receives the user's answer, evaluates it, and requests the AI ​​model to generate a new question and explanation for the next learning step based on the evaluation results. For example, it generates a more in-depth question such as "Why do autonomous vehicle operation managers need to be certified?" along with its explanation.

[0575] Specific examples

[0576] User Scenario

[0577] The user puts on the HMD and launches the application. They voice-input "I want to learn about the laws regarding autonomous vehicles." The system analyzes the input text and extracts relevant learning items, such as "the definition of an autonomous vehicle" and "responsibility." Based on the extracted learning items, questions such as "What qualifications are required to operate an autonomous vehicle?" and their explanations are generated. The user answers the presented questions, and the system evaluates their answers. If the answer is correct, they proceed to the next learning step; if the answer is incorrect, a detailed explanation of the same item is provided again.

[0578] Prompt Sentence Examples

[0579] Entered law text: "Law Concerning the Operation of Autonomous Vehicles"

[0580] Output format: Choose three relevant learning topics and generate questions and explanations for each.

[0581] Output format:

[0582] 1. Learning Item: Definition of Autonomous Vehicle

[0583] Question: Define what an autonomous vehicle is.

[0584] Explanation: An autonomous vehicle is a vehicle that can drive autonomously without driver intervention.

[0585] 2. Learning items: Operation manager qualifications

[0586] Question: What qualifications are required to operate a self-driving vehicle?

[0587] Explanation: In order to operate an autonomous vehicle, you need to be qualified as an operations manager.

[0588] 3. Learning Item: Responsibility

[0589] The question: Who is liable in the event of an accident while driving a self-driving car?

[0590] Explanation: The responsibility for an accident lies primarily with the operation manager, but in some cases the manufacturer or software provider may also be held responsible.

[0591] This will provide a system that allows drivers to efficiently learn about traffic regulations and driving-related laws.

[0592] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0593] Step 1:

[0594] Users access the system using a smartphone or head-mounted display (HMD) and input the text of the traffic regulations and related laws they want to learn. The input text is sent by the device to the server. The input here is text data, and this data is analyzed in the next step.

[0595] Step 2:

[0596] The server passes the received text to an analysis engine for text analysis. The analysis engine breaks down the input text, analyzes each provision of the law and related information, and extracts learning items. The extracted learning items are, for example, "Definition of an autonomous vehicle" or "Qualifications of a traffic manager." The input is text data, and the output is a list of extracted learning items.

[0597] Step 3:

[0598] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "What qualifications are required to operate an autonomous vehicle?" along with its explanation. The input is a list of learning items and the user's learning level data, and the output is a pair of generated questions and explanations.

[0599] Step 4:

[0600] The server compiles the generated questions and explanations into a form and sends it to the user's terminal. The user answers the questions on the terminal. The input here is the generated form, and the user's output is the answer data.

[0601] Step 5:

[0602] The server receives the user's answer and evaluates it. The evaluation engine analyzes the answer and determines whether it is correct or incorrect. Based on the evaluation results, it requests the AI ​​model again to generate new questions and explanations for the next learning step. The input is the answer data, and the output is the evaluation results and new questions and explanations for the next learning step.

[0603] Step 6:

[0604] The server presents the newly generated problem and explanation to the user and provides specific feedback to further deepen learning. For example, it provides a problem such as "Who is responsible in the event of an accident during autonomous driving?" along with its explanation. The input is the new problem and explanation, and the output is feedback to the user and instructions for the next learning step.

[0605] These processing steps allow the user to efficiently learn traffic and driving laws.

[0606] 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.

[0607] The learning support system of the present invention analyzes legal and academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions during the learning process, the present invention also provides learning support appropriate to the user's emotional state. The operation of the entire system is explained in detail below.

[0608] User input

[0609] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[0610] Text analysis and learning item extraction

[0611] 1. The terminal sends the entered text data to the server.

[0612] 2. The server passes the received text data to the analysis engine, which analyzes the text content.

[0613] 3. The server uses an analysis engine to extract learning items from the input text, such as "Definition of adulthood" and "Corporate responsibility."

[0614] Emotion recognition by emotion engine

[0615] 1. The server receives sensor data from the camera, microphone, etc. from the user's device and passes it to the emotion engine.

[0616] 2. The emotion engine analyzes sensor data and recognizes the user's emotional state, such as whether the user is confused, focused, or relaxed.

[0617] 3. The server stores the recognized emotional state and records the emotional data along with the learning history.

[0618] Generate questions and explanations

[0619] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[0620] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0621] Emotion-aware adjustment

[0622] 1. The server adjusts the generated questions and explanations to suit the user's emotional state based on the user's emotional state recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[0623] Presenting the problem and explanation

[0624] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0625] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[0626] Evaluate your answers and learn what to do next

[0627] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[0628] 2. The server stores the evaluation results and sends a new request to the generative AI model for the next learning step.

[0629] 3. The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0630] Feedback and next steps

[0631] 1. The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[0632] 2. The user uses the device to check new questions and explanations and learn the next item to study.

[0633] In this way, the system of the present invention takes into account the user's emotional state and helps them understand the content of laws and academic papers efficiently and deeply. It also uses an emotion engine to optimize the user's learning experience, reducing stress and burden, thereby achieving effective learning.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[0637] Step 2:

[0638] The terminal transmits the input text data to the server.

[0639] Step 3:

[0640] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[0641] Step 4:

[0642] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[0643] Step 5:

[0644] The server receives sensor data from cameras, microphones, and other devices from the user's device and passes it on to the emotion engine.

[0645] Step 6:

[0646] The emotion engine analyzes sensor data to recognize the user's emotional state, for example, whether the user is confused, focused, or relaxed.

[0647] Step 7:

[0648] The server stores the recognized emotional states and records the emotional data along with the learning history.

[0649] Step 8:

[0650] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level and emotional state.

[0651] Step 9:

[0652] The generative AI model receives requests and generates questions and explanations that take into account the user's current level of understanding and emotional state. For example, it generates a question and explanation for the question, "According to Article 4 of the Civil Code, what is the age of majority?"

[0653] Step 10:

[0654] The generative AI model returns the generated questions and explanations to the server.

[0655] Step 11:

[0656] The server then optimally adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[0657] Step 12:

[0658] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0659] Step 13:

[0660] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[0661] Step 14:

[0662] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[0663] Step 15:

[0664] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[0665] Step 16:

[0666] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0667] Step 17:

[0668] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[0669] Step 18:

[0670] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[0671] Through this multi-step interactive process, the system helps users understand the content of laws and papers efficiently and deeply while taking into account their emotional state. It also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[0672] Example 2

[0673] 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."

[0674] Conventional learning support systems have the problem of only providing uniform content without fully considering the user's individual learning level or emotional state. This makes it difficult to improve the user's understanding and maximize learning efficiency. Furthermore, they lack the functionality to focus on specific learning items based on the content of the analyzed text, making it difficult to create an efficient learning plan.

[0675] 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.

[0676] In this invention, the server includes: means for accepting legal or academic text as input from a user; means for analyzing the received text and extracting study items; means for generating questions and explanations using a generative AI model based on the extracted study items; means for presenting the generated questions and explanations to the user and accepting the user's answers; means for evaluating the user's answers, determining the next study content based on the evaluation results, and generating further questions and explanations using the generative AI model; means for presenting the next study content to the user; means for accepting sensor data to recognize the user's emotional state and analyzing the user's emotions using an emotion engine; and means for adjusting the study content based on the user's emotional state. This allows for efficient learning by providing optimal study content and questions based on the user's individual learning level and emotional state. Furthermore, by suggesting key study items based on the content of the analyzed text, the server can also improve the efficiency of study plans.

[0677] A "user" is an entity that operates the learning support system and inputs legal or academic text.

[0678] A "terminal" is an electronic device that a user uses to input legal or academic text, and that also has the ability to communicate with a server.

[0679] The "server" is an information processing device that analyzes data received from the terminal, extracts study items, generates questions and explanations, and recognizes the user's emotional state.

[0680] "Text" refers to textual information about laws and papers that users input into the system.

[0681] An "analysis engine" is a software tool that analyzes received text data and extracts learning items.

[0682] "Learning items" are important concepts or themes that users should learn, extracted from the analyzed text.

[0683] A "generative AI model" is an artificial intelligence technology that generates appropriate questions and explanations based on the user's learning items and learning level.

[0684] A "sensor" is a device, such as a camera or microphone, that collects data about the user's emotional state.

[0685] An "emotion engine" is a software tool that analyzes sensor data and recognizes the user's emotional state.

[0686] "Questions and explanations" are questions and explanations generated by the generative AI model for users to answer.

[0687] The "learning level" is an index that indicates the level of understanding and amount of knowledge of each user.

[0688] A "rating engine" is a software tool that evaluates a user's answers and determines whether they are correct or incorrect.

[0689] A "database" is an information management system for storing data such as a user's learning history and emotional state.

[0690] The learning support system of the present invention is designed to improve users' understanding of the learning content. The system accepts input from users of legal or academic texts, analyzes the input, generates appropriate questions and explanations using a generative AI model, and provides personalized learning support that also takes into account the user's emotional state.

[0691] Hardware and software used

[0692] Hardware:

[0693] 1. User's device: PC, tablet, smartphone, etc. This is the device on which the user inputs text and learns.

[0694] 2. Server: The central information processing unit that performs data analysis and runs models.

[0695] software:

[0696] 1. Analysis engine: A Natural Language Processing (NLP) tool, such as SpaCy or NLTK, is used to analyze text data.

[0697] 2. Generative AI model: For example, use OpenAI's GPT-4 to generate questions and explanations.

[0698] 3. Emotion engine: Analyze the user's emotional state using, for example, Affectiva or Microsoft Azure Emotion API.

[0699] System operation explanation

[0700] 1. A user accesses the system using a terminal and enters the text of the law or paper they wish to study. For example, they may enter, "I would like to learn the contents of Article 4 of the Civil Code."

[0701] 2. The device sends the entered text data to the server, using the HTTPS protocol to ensure secure data transmission.

[0702] 3. The server passes the received text data to an analysis engine (e.g., SpaCy or NLTK) and analyzes the text content through natural language processing, including tokenization, part-of-speech tagging, and dependency analysis.

[0703] 4. The server uses an analysis engine to extract important learning points from the input text, for example, identifying items such as "Definition of Adulthood" and "Corporate Responsibility," and creates a list of learning points.

[0704] 5. The server receives sensor data from the user's device, such as the camera and microphone, and passes it to an emotion engine (e.g., Affectiva or Microsoft Azure Emotion API) to analyze the user's emotional state. For example, it analyzes the user's facial expressions and tone of voice to recognize emotional states such as confusion, concentration, and relaxation.

[0705] 6. The server saves the recognized emotional state information and records the emotional data together with the learning history in a database.

[0706] 7. The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The request also includes a prompt such as "User's learning level: intermediate." The generative AI model generates an appropriate question and explanation based on the request. For example, it generates a question and explanation such as, "According to Article 4 of the Civil Code, what is the age of majority?"

[0707] 8. The server adjusts the generated questions and explanations appropriately based on the user's emotional state recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user.

[0708] 9. The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format or similar.

[0709] 10. The user answers the question on their device. For example, they might type, "According to Article 4 of the Civil Code, the age of majority is 20 years old."

[0710] In this way, efficient and personalized learning support is realized, taking into account the user's individual learning level and emotional state. Furthermore, by suggesting key learning topics based on the analyzed text content, the system can also improve the efficiency of learning plans.

[0711] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0712] Step 1:

[0713] A user accesses the system using a terminal and inputs the text of the law or paper they want to study. For example, a user might input "I want to learn the contents of Article 4 of the Civil Code." This input text becomes the data source for the subsequent analysis steps.

[0714] Step 2:

[0715] The terminal sends the entered text data to the server, which securely transmits the data using the HTTPS protocol. The server receives the input data and moves on to the next analysis step.

[0716] Step 3:

[0717] The server passes the received text data to an analysis engine (e.g., SpaCy). This analysis engine tokenizes the text, tags it with parts of speech, and analyzes dependencies. The analysis results in data that includes part-of-speech information and dependencies for each token.

[0718] Step 4:

[0719] The server uses an analysis engine to extract important learning points from the input text. For example, it identifies items such as "definition of adulthood" and "responsibility" and creates a list of learning points. The extracted learning points are passed on to the next step, sentiment analysis.

[0720] Step 5:

[0721] The server receives sensor data from the user's device, such as from the camera and microphone. This sensor data includes facial expressions and vocal tone. The collected sensor data is then analyzed by the emotion engine.

[0722] Step 6:

[0723] The server passes the sensor data to an emotion engine (e.g., Affectiva) to analyze the user's emotional state. The emotion engine uses machine learning models to determine whether the user is confused, focused, relaxed, etc. The analysis results are stored as emotion recognition data.

[0724] Step 7:

[0725] The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The prompt includes information such as "User's learning level: intermediate." The generative AI model generates appropriate questions and explanations based on the request.

[0726] Step 8:

[0727] The generative AI model generates a question and explanation based on the request. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?" This generated data is sent back to the server.

[0728] Step 9:

[0729] The server adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user. This adjustment data is finally sent to the user.

[0730] Step 10:

[0731] The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format, etc. The user answers the questions presented on their own device.

[0732] Step 11:

[0733] The user answers the questions presented on the terminal. For example, they might enter "According to Article 4 of the Civil Code, the age of majority is 20 years old." This input data is sent as the answer to the next evaluation step.

[0734] Step 12:

[0735] The device sends the user's answer to the server, which then analyzes the answer using an evaluation engine to determine whether it is correct. For example, the answer "20 years old" is recorded as the correct answer.

[0736] Step 13:

[0737] The server stores the evaluation results in a database and sends the generative AI model a new request for the next learning step, including a prompt such as "Prepare the next question on accountability."

[0738] Step 14:

[0739] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0740] Step 15:

[0741] The server presents the generated questions and explanations to the user, and also displays a prioritized list of important learning topics, such as "Details of Accountability" and "Historical Changes in the Age of Majority."

[0742] Step 16:

[0743] The user can then use the device to check new questions and explanations and select the next item to study. This provides efficient and personalized learning support that takes into account the user's individual learning level and emotional state.

[0744] (Application example 2)

[0745] 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."

[0746] Current learning support systems provide uniform learning content without considering the user's emotional state, which can lead to confusion and stress. Furthermore, when providing instructions to robots in factory work, it is difficult to provide appropriate feedback based on the situation or environment, making efficient work instruction difficult. Therefore, there is a need to provide dynamic learning support that adapts to the situation of the user or robot.

[0747] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0748] In this invention, the server includes: [means for receiving legal or academic text as input from a user]; [means for analyzing the received text and extracting learning items]; and [means for generating questions and explanations using a generative AI model based on the extracted learning items]. This enables dynamic adjustment of learning content according to the emotional state and environment of the user or robot.

[0749] A "law" is a set of rules established by the national or local government to maintain social order.

[0750] A "paper" is a document that presents the results of academic research in written form.

[0751] "Text" is a body of writing or written content.

[0752] "User" means a person or device that uses the system.

[0753] A "learning item" is a specific content or topic to be learned.

[0754] A "generative AI model" is an algorithm that uses artificial intelligence to automatically generate questions and explanations.

[0755] "Questions" are questions used to evaluate the learning content.

[0756] "Explanation" provides answers, additional information, and explanations to questions.

[0757] An "emotion recognition means" is a device or algorithm for recognizing the emotional state of a user or a robot.

[0758] "Learning content" refers to the specific information and knowledge that users and robots should learn.

[0759] "Evaluation" refers to judging the correctness and quality of the user's answer.

[0760] "Feedback" refers to the provision of guidance and information based on the user's learning results and the robot's working status.

[0761] "Environment" is the physical or situational conditions in which learning or work takes place.

[0762] "Dynamic adjustment" means changing learning content in real time depending on the situation and emotional state.

[0763] This invention applies a learning support system to provide work guidance to robots in a factory. This system uses the following software and hardware.

[0764] Software and hardware used:

[0765] Software: Generative AI models (using Hugging Face's Transformers), text analysis APIs, emotion recognition algorithms

[0766] Hardware: Robot camera (using OpenCV), server, user terminal

[0767] System operation description:

[0768] 1. Text input from the user:

[0769] Users access the system using a terminal and input the text of the law or paper they wish to study.

[0770] This is done by entering a specific prompt sentence, such as "I would like to learn about the contents of Article 4 of the Civil Code."

[0771] 2. Text analysis and learning item extraction:

[0772] The terminal transmits the input text data to the server.

[0773] The server uses a text analysis API to analyze the content of the text and extract learning items.

[0774] 3. Generating Problems and Explanations:

[0775] The server sends a request to the generative AI model based on the extracted learning items.

[0776] The generative AI model generates questions and explanations in response to user prompts.

[0777] For example, the question "According to Article 4 of the Civil Code, what is the age of majority?" and its explanation are generated.

[0778] 4. Emotion Recognition and Feedback:

[0779] The server uses images captured by the robot's camera and passes them to an emotion recognition algorithm to recognize the robot's emotional state.

[0780] Emotion recognition algorithms detect states such as confusion, concentration, and relaxation from the robot's facial expressions and movements.

[0781] The server adjusts the learning content based on the perceived emotional state: for example, if the robot is confused, it will lower the difficulty of the questions or add more detailed explanations.

[0782] 5. Providing Feedback:

[0783] The adjusted learning content is sent to the terminal and presented to the user or robot.

[0784] The user or robot answers the adjusted questions and sends the results back to the server.

[0785] The server evaluates the answers and generates learning content for the next step.

[0786] Examples:

[0787] If a user inputs "I want to learn about Article 4 of the Civil Code," the generative AI model generates a question and explanation: "According to Article 4 of the Civil Code, what is the age of majority?" The robot's camera recognizes the user's confused state and provides a detailed explanation with a lower level of difficulty. This improves the robot's learning efficiency.

[0788] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0789] Step 1:

[0790] The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, they input a prompt such as, "I would like to learn about Article 4 of the Civil Code." The input data is text data.

[0791] Step 2:

[0792] The device sends the input text data to the server. The server uses a text analysis API to analyze the content of the text and extracts learning items. For example, items such as "Definition of adulthood" and "Corporate responsibility" are extracted. The input is text data, and the output is learning items.

[0793] Step 3:

[0794] The server sends the extracted learning items as requests to the generative AI model, which then generates questions and explanations. For example, a question and explanation might be generated for "According to Article 4 of the Civil Code, what is the age of majority?" The input is the learning item, and the output is the question and explanation.

[0795] Step 4:

[0796] The server sends the questions and explanations to the terminal to present to the user or robot. The terminal displays the generated questions and explanations to the user and accepts the user's answers. The input is the questions and explanations, and the output is the user's answers.

[0797] Step 5:

[0798] Images captured by the robot's camera are sent to the server, which then uses an emotion recognition algorithm to recognize the robot's emotional state, such as confusion, concentration, or relaxation. The input is image data, and the output is the emotional state.

[0799] Step 6:

[0800] The server adjusts the generated learning content based on the recognized emotional state. For example, if the robot is confused, it may lower the difficulty of the questions or add more detailed explanations. The input is the emotional state and the learning content, and the output is the adjusted learning content.

[0801] Step 7:

[0802] The server sends the adjusted learning content to the terminal and presents it to the user or robot. The input is the adjusted learning content, and the output is the presentation of the learning content.

[0803] Step 8:

[0804] The user or robot answers the adjusted questions and sends the results back to the server via the terminal. The server evaluates the user's answers and sends a request to the generative AI model to determine the next learning step. The input is the user's answer, and the output is the next learning content.

[0805] Step 9:

[0806] The generative AI model generates questions and explanations corresponding to the next learning content and returns them to the server. The server then sends the newly generated questions and explanations to the device and presents them to the user or robot as the next learning content. This provides continuous and dynamic learning support. The input is a learning step request, and the output is a new question and explanation.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] [Third embodiment]

[0811] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0812] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0813] 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).

[0814] 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.

[0815] 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.

[0816] 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).

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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."

[0823] The learning support system of the present invention analyzes legal or academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. The system evaluates the user's answers and provides interactive learning support by providing the next learning content based on the evaluation results. The operation of the entire system is described in detail below.

[0824] User input

[0825] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[0826] Text analysis and learning item extraction

[0827] 1. The terminal sends the entered text to the server.

[0828] 2. The server passes the received text to an analysis engine, which extracts relevant learning items. For example, the analysis engine extracts items such as "Definition of adulthood" and "Corporate responsibility."

[0829] Generate questions and explanations

[0830] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[0831] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0832] Presenting the problem and explanation

[0833] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0834] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[0835] Evaluate your answers and learn what to do next

[0836] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[0837] 2. The server stores the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step.

[0838] 3. The generative AI model generates questions and explanations to promote deeper understanding. For example, it generates a question and explanation for the question, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0839] Feedback and next steps

[0840] 1. The server presents the newly generated questions and explanations to the user, and also suggests priority learning topics, such as "Details of legal responsibility" or "Historical changes in the age of majority."

[0841] 2. The user uses the device to study these new questions and items.

[0842] In this way, the system of the present invention helps users to understand the contents of laws and academic papers efficiently and in a short time, and also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[0843] The processing flow will be explained below.

[0844] Step 1:

[0845] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[0846] Step 2:

[0847] The terminal transmits the text data entered by the user to the server.

[0848] Step 3:

[0849] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[0850] Step 4:

[0851] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[0852] Step 5:

[0853] The server requests the generative AI model to generate questions and explanations based on the extracted learning items.

[0854] Step 6:

[0855] The generative AI model receives requests and generates questions and explanations to check the user's current level of understanding. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[0856] Step 7:

[0857] The generative AI model returns the generated questions and explanations to the server.

[0858] Step 8:

[0859] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[0860] Step 9:

[0861] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[0862] Step 10:

[0863] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[0864] Step 11:

[0865] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[0866] Step 12:

[0867] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[0868] Step 13:

[0869] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[0870] Step 14:

[0871] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[0872] In this way, through a multi-step interactive process, the system helps users to understand the content of laws and papers efficiently and deeply.

[0873] Example 1

[0874] 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."

[0875] Conventional learning support systems have difficulty extracting appropriate learning items based on the text entered by the user and generating and providing questions and explanations that are adapted to each individual's learning level. They also lack a mechanism for effectively determining the next learning step based on the evaluation of the user's answers and generating appropriate questions and explanations again. Furthermore, they lacked the ability to dynamically save and regenerate the generated content according to the user's progress, which resulted in a decrease in learning efficiency.

[0876] 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.

[0877] In this invention, the server includes: [means for accepting text as input from a user;] [means for analyzing the received text and extracting learning items;] [means for generating questions and explanations using a generative AI model based on the extracted learning items;] [means for presenting the generated questions and explanations to the user and accepting the user's answers;] [means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model;] [means for presenting the next learning content to the user;] [means for dynamically generating prompt sentences to be input to the generative AI model; and [means for saving the user's learning progress and regenerating appropriate learning content the next time the server is accessed.] This makes it possible to dynamically generate and provide appropriate questions and explanations according to the user's learning progress, thereby improving learning efficiency.

[0878] "User" refers to an individual who accesses the system, inputs legal or academic text, and uses the generated learning content.

[0879] "Text" refers to character string data including the contents of laws and papers.

[0880] "Means for accepting input" refers to a function that provides an interface for a user to send text to the system via a terminal.

[0881] "Analysis engine" refers to a general term for software that analyzes received text and extracts learning items.

[0882] "Learning items" refer to specific themes or keywords that are the subject of education extracted through text analysis.

[0883] "Generative AI model" refers to an artificial intelligence model that automatically generates questions and explanations based on specified prompts.

[0884] "Means for generating questions and explanations" refers to the process of generating questions and explanations based on the learning items extracted using a generative AI model.

[0885] "Means for presenting questions and explanations" refers to a function for transmitting the generated questions and explanations to a terminal so that the user can view them.

[0886] "Means for accepting answers" refers to a function that provides an interface for the system to receive answer data sent by the user.

[0887] The "means for evaluating the answer" refers to the process of comparing the answer submitted by the user with pre-set correct answer data and determining whether it is correct or incorrect.

[0888] The "means for determining the next learning content" refers to a process for determining the next learning content based on the user's evaluation results.

[0889] A "prompt" is an instruction given to a generative AI model, and refers to the input text used to generate an appropriate question and explanation.

[0890] "Means for saving learning progress" refers to the process of saving the user's learning content and assessment results to a database so that they can be referenced the next time they access the site.

[0891] "Means for regeneration" refers to the process of regenerating new, appropriate learning content based on stored learning progress data.

[0892] The learning support system of the present invention analyzes the legal or academic text entered by the user and extracts appropriate learning topics. It then uses a generative AI model to generate questions and explanations based on these learning topics appropriate to the user's learning level and presents them to the user. It evaluates the user's answers and dynamically determines and generates the next learning content based on the results.

[0893] Hardware and software used

[0894] The server uses the following major software components:

[0895] Analysis engine: Natural language processing tool (e.g., Amazon Comprehend)

[0896] Generative AI models: Machine learning models (e.g., OpenAI's GPT-4)

[0897] A terminal is a device (such as a computer or smartphone) that allows users to access the system and input and view data. It also interfaces with the system through a web browser.

[0898] Details of data processing and calculation

[0899] Users enter the text of a law or paper into the system via a web form. For example, they might enter, "I would like to learn about the contents of Article 4 of the Civil Code."

[0900] The device sends the input text to the server, which then passes the received text to an analysis engine, which extracts learning items. For example, "Definition of adulthood" and "Corporate responsibility" may be extracted.

[0901] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question such as, "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation.

[0902] The generated questions and explanations are sent from the server to the terminal and presented to the user. The user answers the questions on the terminal. For example, the user enters the answer "20 years old."

[0903] The device then sends the user's answer back to the server, which evaluates it and determines that "20 years old" is the correct answer. The evaluation results are saved and used to generate new questions and explanations for the next learning step.

[0904] Furthermore, the server sends a prompt for the next learning step to the generative AI model, generating a new question and its explanation, such as, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" This new content is then presented to the user again.

[0905] Examples of concrete examples and prompts

[0906] Specific examples of prompts are given to the generative AI model in the form of, "According to Article 4 of the Civil Code, what is the age of majority?" or "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" Based on this prompt, an appropriate question and explanation are generated.

[0907] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[0908] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0909] Step 1:

[0910] The user accesses the system using a terminal and inputs the text they wish to study. The input in this case is a legal or academic paper text. Specifically, the user enters "I would like to learn about the contents of Article 4 of the Civil Code" into the web form and clicks the submit button. The input data is the text information entered by the user, and the output data is an HTTP request sent from the terminal to the server.

[0911] Step 2:

[0912] The terminal sends the entered text to the server. Specifically, it sends the text data to the server using an HTTP POST request. The input data is the user input obtained in step 1, and the output data is a request to the analysis engine.

[0913] Step 3:

[0914] The server passes the received text to the analysis engine. The analysis engine analyzes the received text and extracts learning items. For example, "definition of adulthood" and "responsibility" are extracted. Specifically, the server sends an API request to the analysis engine and receives the analysis results in return. The input data is the text information received from the device, and the output data is the learning items returned by the analysis engine.

[0915] Step 4:

[0916] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation. Specifically, the server sends a prompt to the generative AI model and receives the generated text. The input data are the learning items and the user's learning level information from the analysis engine, and the output data are the questions and explanations generated by the generative AI model.

[0917] Step 5:

[0918] The server compiles the generated questions and explanations into a form and sends it to the user's device. Specifically, the server generates an HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the learning content presented on the user's device.

[0919] Step 6:

[0920] The user answers the questions presented on the terminal. Specifically, the user enters the answer "20 years old" into the presented form and clicks the submit button. The input data is the answer information entered by the user, and the output data is the HTTP request sent from the terminal to the server.

[0921] Step 7:

[0922] The terminal sends the user's answer to the server. Specifically, it sends the answer data to the server using an HTTP POST request. The input data is the user's answer, and the output data is the rating request sent to the server.

[0923] Step 8:

[0924] The server evaluates the received answer. For example, it determines that the answer "20 years old" is correct. Specifically, the server compares the received answer with a correct answer database and evaluates the score. The input data is the user's answer received from the terminal, and the output data is the evaluation result.

[0925] Step 9:

[0926] The server saves the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step. For example, it generates a question asking, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" along with its explanation. Specifically, the server sends a new prompt to the generative AI model and receives the generated text. The input data are the evaluation results and information about the next learning step, and the output data are the generated new questions and explanations.

[0927] Step 10:

[0928] The server sends the newly generated questions and explanations to the user's device. Specifically, the server updates the HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the new learning content presented on the user's device.

[0929] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[0930] (Application example 1)

[0931] 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."

[0932] It is difficult for automobile drivers to efficiently learn necessary traffic laws and driving-related laws. Furthermore, conventional educational materials and training programs are difficult to customize to fit each driver's learning level, limiting the effectiveness of learning. The present invention aims to solve these problems and provide a system that allows drivers to efficiently learn traffic laws and related laws.

[0933] 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.

[0934] In this invention, the server includes means for receiving legal or academic text as input from a user, means for analyzing the received text and extracting learning items, means for generating questions and explanations using a generative AI model based on the extracted learning items, means for presenting the generated questions and explanations to the user and accepting the user's answers, means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model, and means for presenting the generated questions and explanations as learning content for automobile drivers. This enables legal education customized to the learning level of each driver.

[0935] A "user" is someone who inputs legal or academic text into the system and studies it.

[0936] "Law" refers to the rules and norms established to maintain social order.

[0937] A "thesis" is an academic piece of writing that summarizes the results of in-depth research on a particular topic.

[0938] "Text" refers to content written as sentences or character strings.

[0939] "Analysis" is the process of breaking down and analyzing the input text and extracting the necessary information from it.

[0940] "Study items" are specific themes or points that are extracted from the analyzed text and that the user should study.

[0941] A "generative AI model" is a system that uses artificial intelligence to automatically create questions and explanations based on input information.

[0942] A "problem" is a question presented to the user to check their understanding or to stimulate their thinking.

[0943] An "explanation" is a piece of text that provides an answer to a question or additional information to deepen understanding.

[0944] "Traffic rules" refer to laws and rules established to regulate the operation of automobiles and the behavior of pedestrians.

[0945] "Driver" means a person who drives a motor vehicle.

[0946] A "server" is a device or system that processes and stores data and communicates with user terminals.

[0947] "Customization" means adjusting and modifying to suit the needs and learning level of each individual user.

[0948] "Legal education" refers to educational programs that provide knowledge and deepen understanding of laws and regulations.

[0949] The learning support system of the present invention is designed to enable automobile drivers to efficiently study traffic regulations and driving-related laws. The system accepts legal or academic texts as input from the user, analyzes them to extract learning items, and generates questions and explanations using a generative AI model. Specific embodiments of the present invention are described below.

[0950] Hardware and Software Configuration

[0951] The hardware used is mainly mobile devices such as smartphones and head-mounted displays (HMDs). The server is a high-performance computer system, and it is also possible to use a cloud server.

[0952] The software used is as follows:

[0953] Program implementation using Python

[0954] Text analysis engine (Example: TextAnalysisEngine)

[0955] Generative AI models (e.g., ProblemGenerator)

[0956] Server API

[0957] System Operation

[0958] 1. User Input

[0959] Users access the system using a smartphone or HMD and input the text of the traffic regulations or related laws they want to learn about. For example, they can say, "I want to learn about laws regarding autonomous vehicles."

[0960] 2. Text analysis and learning item extraction

[0961] The server sends the received text to an analysis engine, which then analyzes the text and extracts relevant learning items, such as "definition of an autonomous vehicle" and "qualifications for a vehicle operation manager."

[0962] 3. Generating Problems and Explanations

[0963] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model generates an appropriate question and explanation. For example, it generates a question such as, "What qualifications are required to operate an autonomous vehicle?" along with its explanation.

[0964] 4. Presenting the problem and explanation

[0965] The server compiles the generated questions and explanations into a form and sends it to the user's terminal, where the user answers the questions.

[0966] 5. Evaluate your answers and provide next steps

[0967] The server receives the user's answer, evaluates it, and requests the AI ​​model to generate a new question and explanation for the next learning step based on the evaluation results. For example, it generates a more in-depth question such as "Why do autonomous vehicle operation managers need to be certified?" along with its explanation.

[0968] Specific examples

[0969] User Scenario

[0970] The user puts on the HMD and launches the application. They voice-input "I want to learn about the laws regarding autonomous vehicles." The system analyzes the input text and extracts relevant learning items, such as "the definition of an autonomous vehicle" and "responsibility." Based on the extracted learning items, questions such as "What qualifications are required to operate an autonomous vehicle?" and their explanations are generated. The user answers the presented questions, and the system evaluates their answers. If the answer is correct, they proceed to the next learning step; if the answer is incorrect, a detailed explanation of the same item is provided again.

[0971] Prompt Sentence Examples

[0972] Entered law text: "Law Concerning the Operation of Autonomous Vehicles"

[0973] Output format: Choose three relevant learning topics and generate questions and explanations for each.

[0974] Output format:

[0975] 1. Learning Item: Definition of Autonomous Vehicle

[0976] Question: Define what an autonomous vehicle is.

[0977] Explanation: An autonomous vehicle is a vehicle that can drive autonomously without driver intervention.

[0978] 2. Learning items: Operation manager qualifications

[0979] Question: What qualifications are required to operate a self-driving vehicle?

[0980] Explanation: In order to operate an autonomous vehicle, you need to be qualified as an operations manager.

[0981] 3. Learning Item: Responsibility

[0982] The question: Who is liable in the event of an accident while driving a self-driving car?

[0983] Explanation: The responsibility for an accident lies primarily with the operation manager, but in some cases the manufacturer or software provider may also be held responsible.

[0984] This will provide a system that allows drivers to efficiently learn about traffic regulations and driving-related laws.

[0985] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0986] Step 1:

[0987] Users access the system using a smartphone or head-mounted display (HMD) and input the text of the traffic regulations and related laws they want to learn. The input text is sent by the device to the server. The input here is text data, and this data is analyzed in the next step.

[0988] Step 2:

[0989] The server passes the received text to an analysis engine for text analysis. The analysis engine breaks down the input text, analyzes each provision of the law and related information, and extracts learning items. The extracted learning items are, for example, "Definition of an autonomous vehicle" or "Qualifications of a traffic manager." The input is text data, and the output is a list of extracted learning items.

[0990] Step 3:

[0991] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "What qualifications are required to operate an autonomous vehicle?" along with its explanation. The input is a list of learning items and the user's learning level data, and the output is a pair of generated questions and explanations.

[0992] Step 4:

[0993] The server compiles the generated questions and explanations into a form and sends it to the user's terminal. The user answers the questions on the terminal. The input here is the generated form, and the user's output is the answer data.

[0994] Step 5:

[0995] The server receives the user's answer and evaluates it. The evaluation engine analyzes the answer and determines whether it is correct or incorrect. Based on the evaluation results, it requests the AI ​​model again to generate new questions and explanations for the next learning step. The input is the answer data, and the output is the evaluation results and new questions and explanations for the next learning step.

[0996] Step 6:

[0997] The server presents the newly generated problem and explanation to the user and provides specific feedback to further deepen learning. For example, it provides a problem such as "Who is responsible in the event of an accident during autonomous driving?" along with its explanation. The input is the new problem and explanation, and the output is feedback to the user and instructions for the next learning step.

[0998] These processing steps allow the user to efficiently learn traffic and driving laws.

[0999] 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.

[1000] The learning support system of the present invention analyzes legal and academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions during the learning process, the present invention also provides learning support appropriate to the user's emotional state. The operation of the entire system is explained in detail below.

[1001] User input

[1002] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[1003] Text analysis and learning item extraction

[1004] 1. The terminal sends the entered text data to the server.

[1005] 2. The server passes the received text data to the analysis engine, which analyzes the text content.

[1006] 3. The server uses an analysis engine to extract learning items from the input text, such as "Definition of adulthood" and "Corporate responsibility."

[1007] Emotion recognition by emotion engine

[1008] 1. The server receives sensor data from the camera, microphone, etc. from the user's device and passes it to the emotion engine.

[1009] 2. The emotion engine analyzes sensor data and recognizes the user's emotional state, such as whether the user is confused, focused, or relaxed.

[1010] 3. The server stores the recognized emotional state and records the emotional data along with the learning history.

[1011] Generate questions and explanations

[1012] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[1013] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[1014] Emotion-aware adjustment

[1015] 1. The server adjusts the generated questions and explanations to suit the user's emotional state based on the user's emotional state recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[1016] Presenting the problem and explanation

[1017] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[1018] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[1019] Evaluate your answers and learn what to do next

[1020] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[1021] 2. The server stores the evaluation results and sends a new request to the generative AI model for the next learning step.

[1022] 3. The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1023] Feedback and next steps

[1024] 1. The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[1025] 2. The user uses the device to check new questions and explanations and learn the next item to study.

[1026] In this way, the system of the present invention takes into account the user's emotional state and helps them understand the content of laws and academic papers efficiently and deeply. It also uses an emotion engine to optimize the user's learning experience, reducing stress and burden, thereby achieving effective learning.

[1027] The processing flow will be explained below.

[1028] Step 1:

[1029] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[1030] Step 2:

[1031] The terminal transmits the input text data to the server.

[1032] Step 3:

[1033] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[1034] Step 4:

[1035] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[1036] Step 5:

[1037] The server receives sensor data from cameras, microphones, and other devices from the user's device and passes it on to the emotion engine.

[1038] Step 6:

[1039] The emotion engine analyzes sensor data to recognize the user's emotional state, for example, whether the user is confused, focused, or relaxed.

[1040] Step 7:

[1041] The server stores the recognized emotional states and records the emotional data along with the learning history.

[1042] Step 8:

[1043] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level and emotional state.

[1044] Step 9:

[1045] The generative AI model receives requests and generates questions and explanations that take into account the user's current level of understanding and emotional state. For example, it generates a question and explanation for the question, "According to Article 4 of the Civil Code, what is the age of majority?"

[1046] Step 10:

[1047] The generative AI model returns the generated questions and explanations to the server.

[1048] Step 11:

[1049] The server then optimally adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[1050] Step 12:

[1051] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[1052] Step 13:

[1053] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[1054] Step 14:

[1055] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[1056] Step 15:

[1057] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[1058] Step 16:

[1059] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1060] Step 17:

[1061] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[1062] Step 18:

[1063] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[1064] Through this multi-step interactive process, the system helps users understand the content of laws and papers efficiently and deeply while taking into account their emotional state. It also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[1065] Example 2

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

[1067] Conventional learning support systems have the problem of only providing uniform content without fully considering the user's individual learning level or emotional state. This makes it difficult to improve the user's understanding and maximize learning efficiency. Furthermore, they lack the functionality to focus on specific learning items based on the content of the analyzed text, making it difficult to create an efficient learning plan.

[1068] 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.

[1069] In this invention, the server includes: means for accepting legal or academic text as input from a user; means for analyzing the received text and extracting study items; means for generating questions and explanations using a generative AI model based on the extracted study items; means for presenting the generated questions and explanations to the user and accepting the user's answers; means for evaluating the user's answers, determining the next study content based on the evaluation results, and generating further questions and explanations using the generative AI model; means for presenting the next study content to the user; means for accepting sensor data to recognize the user's emotional state and analyzing the user's emotions using an emotion engine; and means for adjusting the study content based on the user's emotional state. This allows for efficient learning by providing optimal study content and questions based on the user's individual learning level and emotional state. Furthermore, by suggesting key study items based on the content of the analyzed text, the server can also improve the efficiency of study plans.

[1070] A "user" is an entity that operates the learning support system and inputs legal or academic text.

[1071] A "terminal" is an electronic device that a user uses to input legal or academic text, and that also has the ability to communicate with a server.

[1072] The "server" is an information processing device that analyzes data received from the terminal, extracts study items, generates questions and explanations, and recognizes the user's emotional state.

[1073] "Text" refers to textual information about laws and papers that users input into the system.

[1074] An "analysis engine" is a software tool that analyzes received text data and extracts learning items.

[1075] "Learning items" are important concepts or themes that users should learn, extracted from the analyzed text.

[1076] A "generative AI model" is an artificial intelligence technology that generates appropriate questions and explanations based on the user's learning items and learning level.

[1077] A "sensor" is a device, such as a camera or microphone, that collects data about the user's emotional state.

[1078] An "emotion engine" is a software tool that analyzes sensor data and recognizes the user's emotional state.

[1079] "Questions and explanations" are questions and explanations generated by the generative AI model for users to answer.

[1080] The "learning level" is an index that indicates the level of understanding and amount of knowledge of each user.

[1081] A "rating engine" is a software tool that evaluates a user's answers and determines whether they are correct or incorrect.

[1082] A "database" is an information management system for storing data such as a user's learning history and emotional state.

[1083] The learning support system of the present invention is designed to improve users' understanding of the learning content. The system accepts input from users of legal or academic texts, analyzes the input, generates appropriate questions and explanations using a generative AI model, and provides personalized learning support that also takes into account the user's emotional state.

[1084] Hardware and software used

[1085] Hardware:

[1086] 1. User's device: PC, tablet, smartphone, etc. This is the device on which the user inputs text and learns.

[1087] 2. Server: The central information processing unit that performs data analysis and runs models.

[1088] software:

[1089] 1. Analysis engine: A Natural Language Processing (NLP) tool, such as SpaCy or NLTK, is used to analyze text data.

[1090] 2. Generative AI model: For example, use OpenAI's GPT-4 to generate questions and explanations.

[1091] 3. Emotion engine: Analyze the user's emotional state using, for example, Affectiva or Microsoft Azure Emotion API.

[1092] System operation explanation

[1093] 1. A user accesses the system using a terminal and enters the text of the law or paper they wish to study. For example, they may enter, "I would like to learn the contents of Article 4 of the Civil Code."

[1094] 2. The device sends the entered text data to the server, using the HTTPS protocol to ensure secure data transmission.

[1095] 3. The server passes the received text data to an analysis engine (e.g., SpaCy or NLTK) and analyzes the text content through natural language processing, including tokenization, part-of-speech tagging, and dependency analysis.

[1096] 4. The server uses an analysis engine to extract important learning points from the input text, for example, identifying items such as "Definition of Adulthood" and "Corporate Responsibility," and creates a list of learning points.

[1097] 5. The server receives sensor data from the user's device, such as the camera and microphone, and passes it to an emotion engine (e.g., Affectiva or Microsoft Azure Emotion API) to analyze the user's emotional state. For example, it analyzes the user's facial expressions and tone of voice to recognize emotional states such as confusion, concentration, and relaxation.

[1098] 6. The server saves the recognized emotional state information and records the emotional data together with the learning history in a database.

[1099] 7. The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The request also includes a prompt such as "User's learning level: intermediate." The generative AI model generates an appropriate question and explanation based on the request. For example, it generates a question and explanation such as, "According to Article 4 of the Civil Code, what is the age of majority?"

[1100] 8. The server adjusts the generated questions and explanations appropriately based on the user's emotional state recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user.

[1101] 9. The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format or similar.

[1102] 10. The user answers the question on their device. For example, they might type, "According to Article 4 of the Civil Code, the age of majority is 20 years old."

[1103] In this way, efficient and personalized learning support is realized, taking into account the user's individual learning level and emotional state. Furthermore, by suggesting key learning topics based on the analyzed text content, the system can also improve the efficiency of learning plans.

[1104] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1105] Step 1:

[1106] A user accesses the system using a terminal and inputs the text of the law or paper they want to study. For example, a user might input "I want to learn the contents of Article 4 of the Civil Code." This input text becomes the data source for the subsequent analysis steps.

[1107] Step 2:

[1108] The terminal sends the entered text data to the server, which securely transmits the data using the HTTPS protocol. The server receives the input data and moves on to the next analysis step.

[1109] Step 3:

[1110] The server passes the received text data to an analysis engine (e.g., SpaCy). This analysis engine tokenizes the text, tags it with parts of speech, and analyzes dependencies. The analysis results in data that includes part-of-speech information and dependencies for each token.

[1111] Step 4:

[1112] The server uses an analysis engine to extract important learning points from the input text. For example, it identifies items such as "definition of adulthood" and "responsibility" and creates a list of learning points. The extracted learning points are passed on to the next step, sentiment analysis.

[1113] Step 5:

[1114] The server receives sensor data from the user's device, such as from the camera and microphone. This sensor data includes facial expressions and vocal tone. The collected sensor data is then analyzed by the emotion engine.

[1115] Step 6:

[1116] The server passes the sensor data to an emotion engine (e.g., Affectiva) to analyze the user's emotional state. The emotion engine uses machine learning models to determine whether the user is confused, focused, relaxed, etc. The analysis results are stored as emotion recognition data.

[1117] Step 7:

[1118] The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The prompt includes information such as "User's learning level: intermediate." The generative AI model generates appropriate questions and explanations based on the request.

[1119] Step 8:

[1120] The generative AI model generates a question and explanation based on the request. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?" This generated data is sent back to the server.

[1121] Step 9:

[1122] The server adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user. This adjustment data is finally sent to the user.

[1123] Step 10:

[1124] The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format, etc. The user answers the questions presented on their own device.

[1125] Step 11:

[1126] The user answers the questions presented on the terminal. For example, they might enter "According to Article 4 of the Civil Code, the age of majority is 20 years old." This input data is sent as the answer to the next evaluation step.

[1127] Step 12:

[1128] The device sends the user's answer to the server, which then analyzes the answer using an evaluation engine to determine whether it is correct. For example, the answer "20 years old" is recorded as the correct answer.

[1129] Step 13:

[1130] The server stores the evaluation results in a database and sends the generative AI model a new request for the next learning step, including a prompt such as "Prepare the next question on accountability."

[1131] Step 14:

[1132] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1133] Step 15:

[1134] The server presents the generated questions and explanations to the user, and also displays a prioritized list of important learning topics, such as "Details of Accountability" and "Historical Changes in the Age of Majority."

[1135] Step 16:

[1136] The user can then use the device to check new questions and explanations and select the next item to study. This provides efficient and personalized learning support that takes into account the user's individual learning level and emotional state.

[1137] (Application example 2)

[1138] 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."

[1139] Current learning support systems provide uniform learning content without considering the user's emotional state, which can lead to confusion and stress. Furthermore, when providing instructions to robots in factory work, it is difficult to provide appropriate feedback based on the situation or environment, making efficient work instruction difficult. Therefore, there is a need to provide dynamic learning support that adapts to the situation of the user or robot.

[1140] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1141] In this invention, the server includes: [means for receiving legal or academic text as input from a user]; [means for analyzing the received text and extracting learning items]; and [means for generating questions and explanations using a generative AI model based on the extracted learning items]. This enables dynamic adjustment of learning content according to the emotional state and environment of the user or robot.

[1142] A "law" is a set of rules established by the national or local government to maintain social order.

[1143] A "paper" is a document that presents the results of academic research in written form.

[1144] "Text" is a body of writing or written content.

[1145] "User" means a person or device that uses the system.

[1146] A "learning item" is a specific content or topic to be learned.

[1147] A "generative AI model" is an algorithm that uses artificial intelligence to automatically generate questions and explanations.

[1148] "Questions" are questions used to evaluate the learning content.

[1149] "Explanation" provides answers, additional information, and explanations to questions.

[1150] An "emotion recognition means" is a device or algorithm for recognizing the emotional state of a user or a robot.

[1151] "Learning content" refers to the specific information and knowledge that users and robots should learn.

[1152] "Evaluation" refers to judging the correctness and quality of the user's answer.

[1153] "Feedback" refers to the provision of guidance and information based on the user's learning results and the robot's working status.

[1154] "Environment" is the physical or situational conditions in which learning or work takes place.

[1155] "Dynamic adjustment" means changing learning content in real time depending on the situation and emotional state.

[1156] This invention applies a learning support system to provide work guidance to robots in a factory. This system uses the following software and hardware.

[1157] Software and hardware used:

[1158] Software: Generative AI models (using Hugging Face's Transformers), text analysis APIs, emotion recognition algorithms

[1159] Hardware: Robot camera (using OpenCV), server, user terminal

[1160] System operation description:

[1161] 1. Text input from the user:

[1162] Users access the system using a terminal and input the text of the law or paper they wish to study.

[1163] This is done by entering a specific prompt sentence, such as "I would like to learn about the contents of Article 4 of the Civil Code."

[1164] 2. Text analysis and learning item extraction:

[1165] The terminal transmits the input text data to the server.

[1166] The server uses a text analysis API to analyze the content of the text and extract learning items.

[1167] 3. Generating Problems and Explanations:

[1168] The server sends a request to the generative AI model based on the extracted learning items.

[1169] The generative AI model generates questions and explanations in response to user prompts.

[1170] For example, the question "According to Article 4 of the Civil Code, what is the age of majority?" and its explanation are generated.

[1171] 4. Emotion Recognition and Feedback:

[1172] The server uses images captured by the robot's camera and passes them to an emotion recognition algorithm to recognize the robot's emotional state.

[1173] Emotion recognition algorithms detect states such as confusion, concentration, and relaxation from the robot's facial expressions and movements.

[1174] The server adjusts the learning content based on the perceived emotional state: for example, if the robot is confused, it will lower the difficulty of the questions or add more detailed explanations.

[1175] 5. Providing Feedback:

[1176] The adjusted learning content is sent to the terminal and presented to the user or robot.

[1177] The user or robot answers the adjusted questions and sends the results back to the server.

[1178] The server evaluates the answers and generates learning content for the next step.

[1179] Examples:

[1180] If a user inputs "I want to learn about Article 4 of the Civil Code," the generative AI model generates a question and explanation: "According to Article 4 of the Civil Code, what is the age of majority?" The robot's camera recognizes the user's confused state and provides a detailed explanation with a lower level of difficulty. This improves the robot's learning efficiency.

[1181] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1182] Step 1:

[1183] The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, they input a prompt such as, "I would like to learn about Article 4 of the Civil Code." The input data is text data.

[1184] Step 2:

[1185] The device sends the input text data to the server. The server uses a text analysis API to analyze the content of the text and extracts learning items. For example, items such as "Definition of adulthood" and "Corporate responsibility" are extracted. The input is text data, and the output is learning items.

[1186] Step 3:

[1187] The server sends the extracted learning items as requests to the generative AI model, which then generates questions and explanations. For example, a question and explanation might be generated for "According to Article 4 of the Civil Code, what is the age of majority?" The input is the learning item, and the output is the question and explanation.

[1188] Step 4:

[1189] The server sends the questions and explanations to the terminal to present to the user or robot. The terminal displays the generated questions and explanations to the user and accepts the user's answers. The input is the questions and explanations, and the output is the user's answers.

[1190] Step 5:

[1191] Images captured by the robot's camera are sent to the server, which then uses an emotion recognition algorithm to recognize the robot's emotional state, such as confusion, concentration, or relaxation. The input is image data, and the output is the emotional state.

[1192] Step 6:

[1193] The server adjusts the generated learning content based on the recognized emotional state. For example, if the robot is confused, it may lower the difficulty of the questions or add more detailed explanations. The input is the emotional state and the learning content, and the output is the adjusted learning content.

[1194] Step 7:

[1195] The server sends the adjusted learning content to the terminal and presents it to the user or robot. The input is the adjusted learning content, and the output is the presentation of the learning content.

[1196] Step 8:

[1197] The user or robot answers the adjusted questions and sends the results back to the server via the terminal. The server evaluates the user's answers and sends a request to the generative AI model to determine the next learning step. The input is the user's answer, and the output is the next learning content.

[1198] Step 9:

[1199] The generative AI model generates questions and explanations corresponding to the next learning content and returns them to the server. The server then sends the newly generated questions and explanations to the device and presents them to the user or robot as the next learning content. This provides continuous and dynamic learning support. The input is a learning step request, and the output is a new question and explanation.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] [Fourth embodiment]

[1204] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1205] 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.

[1206] 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).

[1207] 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.

[1208] 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.

[1209] 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).

[1210] 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.

[1211] 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.

[1212] 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.

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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."

[1217] The learning support system of the present invention analyzes legal or academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. The system evaluates the user's answers and provides interactive learning support by providing the next learning content based on the evaluation results. The operation of the entire system is described in detail below.

[1218] User input

[1219] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[1220] Text analysis and learning item extraction

[1221] 1. The terminal sends the entered text to the server.

[1222] 2. The server passes the received text to an analysis engine, which extracts relevant learning items. For example, the analysis engine extracts items such as "Definition of adulthood" and "Corporate responsibility."

[1223] Generate questions and explanations

[1224] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[1225] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[1226] Presenting the problem and explanation

[1227] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[1228] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[1229] Evaluate your answers and learn what to do next

[1230] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[1231] 2. The server stores the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step.

[1232] 3. The generative AI model generates questions and explanations to promote deeper understanding. For example, it generates a question and explanation for the question, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1233] Feedback and next steps

[1234] 1. The server presents the newly generated questions and explanations to the user, and also suggests priority learning topics, such as "Details of legal responsibility" or "Historical changes in the age of majority."

[1235] 2. The user uses the device to study these new questions and items.

[1236] In this way, the system of the present invention helps users to understand the contents of laws and academic papers efficiently and in a short time, and also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[1237] The processing flow will be explained below.

[1238] Step 1:

[1239] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[1240] Step 2:

[1241] The terminal transmits the text data entered by the user to the server.

[1242] Step 3:

[1243] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[1244] Step 4:

[1245] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[1246] Step 5:

[1247] The server requests the generative AI model to generate questions and explanations based on the extracted learning items.

[1248] Step 6:

[1249] The generative AI model receives requests and generates questions and explanations to check the user's current level of understanding. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[1250] Step 7:

[1251] The generative AI model returns the generated questions and explanations to the server.

[1252] Step 8:

[1253] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[1254] Step 9:

[1255] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[1256] Step 10:

[1257] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[1258] Step 11:

[1259] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[1260] Step 12:

[1261] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1262] Step 13:

[1263] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[1264] Step 14:

[1265] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[1266] In this way, through a multi-step interactive process, the system helps users to understand the content of laws and papers efficiently and deeply.

[1267] Example 1

[1268] 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."

[1269] Conventional learning support systems have difficulty extracting appropriate learning items based on the text entered by the user and generating and providing questions and explanations that are adapted to each individual's learning level. They also lack a mechanism for effectively determining the next learning step based on the evaluation of the user's answers and generating appropriate questions and explanations again. Furthermore, they lacked the ability to dynamically save and regenerate the generated content according to the user's progress, which resulted in a decrease in learning efficiency.

[1270] 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.

[1271] In this invention, the server includes: [means for accepting text as input from a user;] [means for analyzing the received text and extracting learning items;] [means for generating questions and explanations using a generative AI model based on the extracted learning items;] [means for presenting the generated questions and explanations to the user and accepting the user's answers;] [means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model;] [means for presenting the next learning content to the user;] [means for dynamically generating prompt sentences to be input to the generative AI model; and [means for saving the user's learning progress and regenerating appropriate learning content the next time the server is accessed.] This makes it possible to dynamically generate and provide appropriate questions and explanations according to the user's learning progress, thereby improving learning efficiency.

[1272] "User" refers to an individual who accesses the system, inputs legal or academic text, and uses the generated learning content.

[1273] "Text" refers to character string data including the contents of laws and papers.

[1274] "Means for accepting input" refers to a function that provides an interface for a user to send text to the system via a terminal.

[1275] "Analysis engine" refers to a general term for software that analyzes received text and extracts learning items.

[1276] "Learning items" refer to specific themes or keywords that are the subject of education extracted through text analysis.

[1277] "Generative AI model" refers to an artificial intelligence model that automatically generates questions and explanations based on specified prompts.

[1278] "Means for generating questions and explanations" refers to the process of generating questions and explanations based on the learning items extracted using a generative AI model.

[1279] "Means for presenting questions and explanations" refers to a function for transmitting the generated questions and explanations to a terminal so that the user can view them.

[1280] "Means for accepting answers" refers to a function that provides an interface for the system to receive answer data sent by the user.

[1281] The "means for evaluating the answer" refers to the process of comparing the answer submitted by the user with pre-set correct answer data and determining whether it is correct or incorrect.

[1282] The "means for determining the next learning content" refers to a process for determining the next learning content based on the user's evaluation results.

[1283] A "prompt" is an instruction given to a generative AI model, and refers to the input text used to generate an appropriate question and explanation.

[1284] "Means for saving learning progress" refers to the process of saving the user's learning content and assessment results to a database so that they can be referenced the next time they access the site.

[1285] "Means for regeneration" refers to the process of regenerating new, appropriate learning content based on stored learning progress data.

[1286] The learning support system of the present invention analyzes the legal or academic text entered by the user and extracts appropriate learning topics. It then uses a generative AI model to generate questions and explanations based on these learning topics appropriate to the user's learning level and presents them to the user. It evaluates the user's answers and dynamically determines and generates the next learning content based on the results.

[1287] Hardware and software used

[1288] The server uses the following major software components:

[1289] Analysis engine: Natural language processing tool (e.g., Amazon Comprehend)

[1290] Generative AI models: Machine learning models (e.g., OpenAI's GPT-4)

[1291] A terminal is a device (such as a computer or smartphone) that allows users to access the system and input and view data. It also interfaces with the system through a web browser.

[1292] Details of data processing and calculation

[1293] Users enter the text of a law or paper into the system via a web form. For example, they might enter, "I would like to learn about the contents of Article 4 of the Civil Code."

[1294] The device sends the input text to the server, which then passes the received text to an analysis engine, which extracts learning items. For example, "Definition of adulthood" and "Corporate responsibility" may be extracted.

[1295] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question such as, "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation.

[1296] The generated questions and explanations are sent from the server to the terminal and presented to the user. The user answers the questions on the terminal. For example, the user enters the answer "20 years old."

[1297] The device then sends the user's answer back to the server, which evaluates it and determines that "20 years old" is the correct answer. The evaluation results are saved and used to generate new questions and explanations for the next learning step.

[1298] Furthermore, the server sends a prompt for the next learning step to the generative AI model, generating a new question and its explanation, such as, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" This new content is then presented to the user again.

[1299] Examples of concrete examples and prompts

[1300] Specific examples of prompts are given to the generative AI model in the form of, "According to Article 4 of the Civil Code, what is the age of majority?" or "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" Based on this prompt, an appropriate question and explanation are generated.

[1301] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[1302] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1303] Step 1:

[1304] The user accesses the system using a terminal and inputs the text they wish to study. The input in this case is a legal or academic paper text. Specifically, the user enters "I would like to learn about the contents of Article 4 of the Civil Code" into the web form and clicks the submit button. The input data is the text information entered by the user, and the output data is an HTTP request sent from the terminal to the server.

[1305] Step 2:

[1306] The terminal sends the entered text to the server. Specifically, it sends the text data to the server using an HTTP POST request. The input data is the user input obtained in step 1, and the output data is a request to the analysis engine.

[1307] Step 3:

[1308] The server passes the received text to the analysis engine. The analysis engine analyzes the received text and extracts learning items. For example, "definition of adulthood" and "responsibility" are extracted. Specifically, the server sends an API request to the analysis engine and receives the analysis results in return. The input data is the text information received from the device, and the output data is the learning items returned by the analysis engine.

[1309] Step 4:

[1310] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "According to Article 4 of the Civil Code, what is the age of majority?" along with its explanation. Specifically, the server sends a prompt to the generative AI model and receives the generated text. The input data are the learning items and the user's learning level information from the analysis engine, and the output data are the questions and explanations generated by the generative AI model.

[1311] Step 5:

[1312] The server compiles the generated questions and explanations into a form and sends it to the user's device. Specifically, the server generates an HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the learning content presented on the user's device.

[1313] Step 6:

[1314] The user answers the questions presented on the terminal. Specifically, the user enters the answer "20 years old" into the presented form and clicks the submit button. The input data is the answer information entered by the user, and the output data is the HTTP request sent from the terminal to the server.

[1315] Step 7:

[1316] The terminal sends the user's answer to the server. Specifically, it sends the answer data to the server using an HTTP POST request. The input data is the user's answer, and the output data is the rating request sent to the server.

[1317] Step 8:

[1318] The server evaluates the received answer. For example, it determines that the answer "20 years old" is correct. Specifically, the server compares the received answer with a correct answer database and evaluates the score. The input data is the user's answer received from the terminal, and the output data is the evaluation result.

[1319] Step 9:

[1320] The server saves the evaluation results and requests the generative AI model to generate new questions and explanations for the next learning step. For example, it generates a question asking, "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?" along with its explanation. Specifically, the server sends a new prompt to the generative AI model and receives the generated text. The input data are the evaluation results and information about the next learning step, and the output data are the generated new questions and explanations.

[1321] Step 10:

[1322] The server sends the newly generated questions and explanations to the user's device. Specifically, the server updates the HTML form and sends it to the user's device as an HTTP response. The input data are the questions and explanations from the generative AI model, and the output data is the new learning content presented on the user's device.

[1323] In this way, the system of the present invention helps users to understand the contents of laws and papers efficiently and in a short time. By dynamically generating and providing questions and explanations according to the user's learning progress, it is possible to provide an effective learning experience.

[1324] (Application example 1)

[1325] 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."

[1326] It is difficult for automobile drivers to efficiently learn necessary traffic laws and driving-related laws. Furthermore, conventional educational materials and training programs are difficult to customize to fit each driver's learning level, limiting the effectiveness of learning. The present invention aims to solve these problems and provide a system that allows drivers to efficiently learn traffic laws and related laws.

[1327] 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.

[1328] In this invention, the server includes means for receiving legal or academic text as input from a user, means for analyzing the received text and extracting learning items, means for generating questions and explanations using a generative AI model based on the extracted learning items, means for presenting the generated questions and explanations to the user and accepting the user's answers, means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using the generative AI model, and means for presenting the generated questions and explanations as learning content for automobile drivers. This enables legal education customized to the learning level of each driver.

[1329] A "user" is someone who inputs legal or academic text into the system and studies it.

[1330] "Law" refers to the rules and norms established to maintain social order.

[1331] A "thesis" is an academic piece of writing that summarizes the results of in-depth research on a particular topic.

[1332] "Text" refers to content written as sentences or character strings.

[1333] "Analysis" is the process of breaking down and analyzing the input text and extracting the necessary information from it.

[1334] "Study items" are specific themes or points that are extracted from the analyzed text and that the user should study.

[1335] A "generative AI model" is a system that uses artificial intelligence to automatically create questions and explanations based on input information.

[1336] A "problem" is a question presented to the user to check their understanding or to stimulate their thinking.

[1337] An "explanation" is a piece of text that provides an answer to a question or additional information to deepen understanding.

[1338] "Traffic rules" refer to laws and rules established to regulate the operation of automobiles and the behavior of pedestrians.

[1339] "Driver" means a person who drives a motor vehicle.

[1340] A "server" is a device or system that processes and stores data and communicates with user terminals.

[1341] "Customization" means adjusting and modifying to suit the needs and learning level of each individual user.

[1342] "Legal education" refers to educational programs that provide knowledge and deepen understanding of laws and regulations.

[1343] The learning support system of the present invention is designed to enable automobile drivers to efficiently study traffic regulations and driving-related laws. The system accepts legal or academic texts as input from the user, analyzes them to extract learning items, and generates questions and explanations using a generative AI model. Specific embodiments of the present invention are described below.

[1344] Hardware and Software Configuration

[1345] The hardware used is mainly mobile devices such as smartphones and head-mounted displays (HMDs). The server is a high-performance computer system, and it is also possible to use a cloud server.

[1346] The software used is as follows:

[1347] Program implementation using Python

[1348] Text analysis engine (Example: TextAnalysisEngine)

[1349] Generative AI models (e.g., ProblemGenerator)

[1350] Server API

[1351] System Operation

[1352] 1. User Input

[1353] Users access the system using a smartphone or HMD and input the text of the traffic regulations or related laws they want to learn about. For example, they can say, "I want to learn about laws regarding autonomous vehicles."

[1354] 2. Text analysis and learning item extraction

[1355] The server sends the received text to an analysis engine, which then analyzes the text and extracts relevant learning items, such as "definition of an autonomous vehicle" and "qualifications for a vehicle operation manager."

[1356] 3. Generating Problems and Explanations

[1357] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model generates an appropriate question and explanation. For example, it generates a question such as, "What qualifications are required to operate an autonomous vehicle?" along with its explanation.

[1358] 4. Presenting the problem and explanation

[1359] The server compiles the generated questions and explanations into a form and sends it to the user's terminal, where the user answers the questions.

[1360] 5. Evaluate your answers and provide next steps

[1361] The server receives the user's answer, evaluates it, and requests the AI ​​model to generate a new question and explanation for the next learning step based on the evaluation results. For example, it generates a more in-depth question such as "Why do autonomous vehicle operation managers need to be certified?" along with its explanation.

[1362] Specific examples

[1363] User Scenario

[1364] The user puts on the HMD and launches the application. They voice-input "I want to learn about the laws regarding autonomous vehicles." The system analyzes the input text and extracts relevant learning items, such as "the definition of an autonomous vehicle" and "responsibility." Based on the extracted learning items, questions such as "What qualifications are required to operate an autonomous vehicle?" and their explanations are generated. The user answers the presented questions, and the system evaluates their answers. If the answer is correct, they proceed to the next learning step; if the answer is incorrect, a detailed explanation of the same item is provided again.

[1365] Prompt Sentence Examples

[1366] Entered law text: "Law Concerning the Operation of Autonomous Vehicles"

[1367] Output format: Choose three relevant learning topics and generate questions and explanations for each.

[1368] Output format:

[1369] 1. Learning Item: Definition of Autonomous Vehicle

[1370] Question: Define what an autonomous vehicle is.

[1371] Explanation: An autonomous vehicle is a vehicle that can drive autonomously without driver intervention.

[1372] 2. Learning items: Operation manager qualifications

[1373] Question: What qualifications are required to operate a self-driving vehicle?

[1374] Explanation: In order to operate an autonomous vehicle, you need to be qualified as an operations manager.

[1375] 3. Learning Item: Responsibility

[1376] The question: Who is liable in the event of an accident while driving a self-driving car?

[1377] Explanation: The responsibility for an accident lies primarily with the operation manager, but in some cases the manufacturer or software provider may also be held responsible.

[1378] This will provide a system that allows drivers to efficiently learn about traffic regulations and driving-related laws.

[1379] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1380] Step 1:

[1381] Users access the system using a smartphone or head-mounted display (HMD) and input the text of the traffic regulations and related laws they want to learn. The input text is sent by the device to the server. The input here is text data, and this data is analyzed in the next step.

[1382] Step 2:

[1383] The server passes the received text to an analysis engine for text analysis. The analysis engine breaks down the input text, analyzes each provision of the law and related information, and extracts learning items. The extracted learning items are, for example, "Definition of an autonomous vehicle" or "Qualifications of a traffic manager." The input is text data, and the output is a list of extracted learning items.

[1384] Step 3:

[1385] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates the question "What qualifications are required to operate an autonomous vehicle?" along with its explanation. The input is a list of learning items and the user's learning level data, and the output is a pair of generated questions and explanations.

[1386] Step 4:

[1387] The server compiles the generated questions and explanations into a form and sends it to the user's terminal. The user answers the questions on the terminal. The input here is the generated form, and the user's output is the answer data.

[1388] Step 5:

[1389] The server receives the user's answer and evaluates it. The evaluation engine analyzes the answer and determines whether it is correct or incorrect. Based on the evaluation results, it requests the AI ​​model again to generate new questions and explanations for the next learning step. The input is the answer data, and the output is the evaluation results and new questions and explanations for the next learning step.

[1390] Step 6:

[1391] The server presents the newly generated problem and explanation to the user and provides specific feedback to further deepen learning. For example, it provides a problem such as "Who is responsible in the event of an accident during autonomous driving?" along with its explanation. The input is the new problem and explanation, and the output is feedback to the user and instructions for the next learning step.

[1392] These processing steps allow the user to efficiently learn traffic and driving laws.

[1393] 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.

[1394] The learning support system of the present invention analyzes legal and academic texts entered by the user, extracts appropriate learning topics based on the analysis, and uses a generative AI model to generate and provide questions and explanations appropriate to the user's learning level. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions during the learning process, the present invention also provides learning support appropriate to the user's emotional state. The operation of the entire system is explained in detail below.

[1395] User input

[1396] 1. The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, the user may input, "I would like to learn the contents of Article 4 of the Civil Code."

[1397] Text analysis and learning item extraction

[1398] 1. The terminal sends the entered text data to the server.

[1399] 2. The server passes the received text data to the analysis engine, which analyzes the text content.

[1400] 3. The server uses an analysis engine to extract learning items from the input text, such as "Definition of adulthood" and "Corporate responsibility."

[1401] Emotion recognition by emotion engine

[1402] 1. The server receives sensor data from the camera, microphone, etc. from the user's device and passes it to the emotion engine.

[1403] 2. The emotion engine analyzes sensor data and recognizes the user's emotional state, such as whether the user is confused, focused, or relaxed.

[1404] 3. The server stores the recognized emotional state and records the emotional data along with the learning history.

[1405] Generate questions and explanations

[1406] 1. The server sends a request to the generative AI model based on the extracted learning items and the user's learning level.

[1407] 2. The generative AI model receives the request and generates an appropriate question and explanation. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?"

[1408] Emotion-aware adjustment

[1409] 1. The server adjusts the generated questions and explanations to suit the user's emotional state based on the user's emotional state recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[1410] Presenting the problem and explanation

[1411] 1. The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[1412] 2. The user answers the questions displayed on the terminal. For example, they enter the answer "20 years old."

[1413] Evaluate your answers and learn what to do next

[1414] 1. The device sends the user's answer to the server, which evaluates the answer. The server determines that the answer "20 years old" is correct.

[1415] 2. The server stores the evaluation results and sends a new request to the generative AI model for the next learning step.

[1416] 3. The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1417] Feedback and next steps

[1418] 1. The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[1419] 2. The user uses the device to check new questions and explanations and learn the next item to study.

[1420] In this way, the system of the present invention takes into account the user's emotional state and helps them understand the content of laws and academic papers efficiently and deeply. It also uses an emotion engine to optimize the user's learning experience, reducing stress and burden, thereby achieving effective learning.

[1421] The processing flow will be explained below.

[1422] Step 1:

[1423] The user accesses the learning support system from a terminal and inputs the text of the law or paper they wish to study.

[1424] Step 2:

[1425] The terminal transmits the input text data to the server.

[1426] Step 3:

[1427] The server passes the received text data to an analysis engine, which analyzes the content of the text.

[1428] Step 4:

[1429] The server uses an analysis engine to extract learning items from the input text, such as "definition of adulthood" and "personal responsibility."

[1430] Step 5:

[1431] The server receives sensor data from cameras, microphones, and other devices from the user's device and passes it on to the emotion engine.

[1432] Step 6:

[1433] The emotion engine analyzes sensor data to recognize the user's emotional state, for example, whether the user is confused, focused, or relaxed.

[1434] Step 7:

[1435] The server stores the recognized emotional states and records the emotional data along with the learning history.

[1436] Step 8:

[1437] The server sends a request to the generative AI model based on the extracted learning items and the user's learning level and emotional state.

[1438] Step 9:

[1439] The generative AI model receives requests and generates questions and explanations that take into account the user's current level of understanding and emotional state. For example, it generates a question and explanation for the question, "According to Article 4 of the Civil Code, what is the age of majority?"

[1440] Step 10:

[1441] The generative AI model returns the generated questions and explanations to the server.

[1442] Step 11:

[1443] The server then optimally adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, if the user is confused, the server may lower the difficulty of the questions or add more detailed explanations.

[1444] Step 12:

[1445] The server compiles the generated questions and explanations into a form and sends it to the user's terminal.

[1446] Step 13:

[1447] The user answers the questions presented on the terminal and sends the answers from the terminal to the server.

[1448] Step 14:

[1449] The server receives the user's answer and evaluates whether it is correct. For example, it determines that the answer "20 years old" is correct.

[1450] Step 15:

[1451] Based on the user's answers, the server sends a new request to the generative AI model for the next learning step.

[1452] Step 16:

[1453] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1454] Step 17:

[1455] The server presents the newly generated questions and explanations to the user, and also prioritizes important learning topics, such as "Details of Responsibility" and "Historical Changes in the Age of Majority."

[1456] Step 18:

[1457] Users can use their devices to check new questions and explanations, and then look at the next item they need to study and continue their studies.

[1458] Through this multi-step interactive process, the system helps users understand the content of laws and papers efficiently and deeply while taking into account their emotional state. It also provides an effective learning experience by dynamically generating and providing content according to the user's learning progress.

[1459] Example 2

[1460] 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."

[1461] Conventional learning support systems have the problem of only providing uniform content without fully considering the user's individual learning level or emotional state. This makes it difficult to improve the user's understanding and maximize learning efficiency. Furthermore, they lack the functionality to focus on specific learning items based on the content of the analyzed text, making it difficult to create an efficient learning plan.

[1462] 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.

[1463] In this invention, the server includes: means for accepting legal or academic text as input from a user; means for analyzing the received text and extracting study items; means for generating questions and explanations using a generative AI model based on the extracted study items; means for presenting the generated questions and explanations to the user and accepting the user's answers; means for evaluating the user's answers, determining the next study content based on the evaluation results, and generating further questions and explanations using the generative AI model; means for presenting the next study content to the user; means for accepting sensor data to recognize the user's emotional state and analyzing the user's emotions using an emotion engine; and means for adjusting the study content based on the user's emotional state. This allows for efficient learning by providing optimal study content and questions based on the user's individual learning level and emotional state. Furthermore, by suggesting key study items based on the content of the analyzed text, the server can also improve the efficiency of study plans.

[1464] A "user" is an entity that operates the learning support system and inputs legal or academic text.

[1465] A "terminal" is an electronic device that a user uses to input legal or academic text, and that also has the ability to communicate with a server.

[1466] The "server" is an information processing device that analyzes data received from the terminal, extracts study items, generates questions and explanations, and recognizes the user's emotional state.

[1467] "Text" refers to textual information about laws and papers that users input into the system.

[1468] An "analysis engine" is a software tool that analyzes received text data and extracts learning items.

[1469] "Learning items" are important concepts or themes that users should learn, extracted from the analyzed text.

[1470] A "generative AI model" is an artificial intelligence technology that generates appropriate questions and explanations based on the user's learning items and learning level.

[1471] A "sensor" is a device, such as a camera or microphone, that collects data about the user's emotional state.

[1472] An "emotion engine" is a software tool that analyzes sensor data and recognizes the user's emotional state.

[1473] "Questions and explanations" are questions and explanations generated by the generative AI model for users to answer.

[1474] The "learning level" is an index that indicates the level of understanding and amount of knowledge of each user.

[1475] A "rating engine" is a software tool that evaluates a user's answers and determines whether they are correct or incorrect.

[1476] A "database" is an information management system for storing data such as a user's learning history and emotional state.

[1477] The learning support system of the present invention is designed to improve users' understanding of the learning content. The system accepts input from users of legal or academic texts, analyzes the input, generates appropriate questions and explanations using a generative AI model, and provides personalized learning support that also takes into account the user's emotional state.

[1478] Hardware and software used

[1479] Hardware:

[1480] 1. User's device: PC, tablet, smartphone, etc. This is the device on which the user inputs text and learns.

[1481] 2. Server: The central information processing unit that performs data analysis and runs models.

[1482] software:

[1483] 1. Analysis engine: A Natural Language Processing (NLP) tool, such as SpaCy or NLTK, is used to analyze text data.

[1484] 2. Generative AI model: For example, use OpenAI's GPT-4 to generate questions and explanations.

[1485] 3. Emotion engine: Analyze the user's emotional state using, for example, Affectiva or Microsoft Azure Emotion API.

[1486] System operation explanation

[1487] 1. A user accesses the system using a terminal and enters the text of the law or paper they wish to study. For example, they may enter, "I would like to learn the contents of Article 4 of the Civil Code."

[1488] 2. The device sends the entered text data to the server, using the HTTPS protocol to ensure secure data transmission.

[1489] 3. The server passes the received text data to an analysis engine (e.g., SpaCy or NLTK) and analyzes the text content through natural language processing, including tokenization, part-of-speech tagging, and dependency analysis.

[1490] 4. The server uses an analysis engine to extract important learning points from the input text, for example, identifying items such as "Definition of Adulthood" and "Corporate Responsibility," and creates a list of learning points.

[1491] 5. The server receives sensor data from the user's device, such as the camera and microphone, and passes it to an emotion engine (e.g., Affectiva or Microsoft Azure Emotion API) to analyze the user's emotional state. For example, it analyzes the user's facial expressions and tone of voice to recognize emotional states such as confusion, concentration, and relaxation.

[1492] 6. The server saves the recognized emotional state information and records the emotional data together with the learning history in a database.

[1493] 7. The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The request also includes a prompt such as "User's learning level: intermediate." The generative AI model generates an appropriate question and explanation based on the request. For example, it generates a question and explanation such as, "According to Article 4 of the Civil Code, what is the age of majority?"

[1494] 8. The server adjusts the generated questions and explanations appropriately based on the user's emotional state recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user.

[1495] 9. The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format or similar.

[1496] 10. The user answers the question on their device. For example, they might type, "According to Article 4 of the Civil Code, the age of majority is 20 years old."

[1497] In this way, efficient and personalized learning support is realized, taking into account the user's individual learning level and emotional state. Furthermore, by suggesting key learning topics based on the analyzed text content, the system can also improve the efficiency of learning plans.

[1498] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1499] Step 1:

[1500] A user accesses the system using a terminal and inputs the text of the law or paper they want to study. For example, a user might input "I want to learn the contents of Article 4 of the Civil Code." This input text becomes the data source for the subsequent analysis steps.

[1501] Step 2:

[1502] The terminal sends the entered text data to the server, which securely transmits the data using the HTTPS protocol. The server receives the input data and moves on to the next analysis step.

[1503] Step 3:

[1504] The server passes the received text data to an analysis engine (e.g., SpaCy). This analysis engine tokenizes the text, tags it with parts of speech, and analyzes dependencies. The analysis results in data that includes part-of-speech information and dependencies for each token.

[1505] Step 4:

[1506] The server uses an analysis engine to extract important learning points from the input text. For example, it identifies items such as "definition of adulthood" and "responsibility" and creates a list of learning points. The extracted learning points are passed on to the next step, sentiment analysis.

[1507] Step 5:

[1508] The server receives sensor data from the user's device, such as from the camera and microphone. This sensor data includes facial expressions and vocal tone. The collected sensor data is then analyzed by the emotion engine.

[1509] Step 6:

[1510] The server passes the sensor data to an emotion engine (e.g., Affectiva) to analyze the user's emotional state. The emotion engine uses machine learning models to determine whether the user is confused, focused, relaxed, etc. The analysis results are stored as emotion recognition data.

[1511] Step 7:

[1512] The server sends a request to a generative AI model (e.g., GPT-4) based on the specific learning topic and the user's learning level. The prompt includes information such as "User's learning level: intermediate." The generative AI model generates appropriate questions and explanations based on the request.

[1513] Step 8:

[1514] The generative AI model generates a question and explanation based on the request. For example, it generates a question and explanation for "According to Article 4 of the Civil Code, what is the age of majority?" This generated data is sent back to the server.

[1515] Step 9:

[1516] The server adjusts the generated questions and explanations based on the user's emotional state as recognized by the emotion engine. For example, it may lower the difficulty of the questions or provide additional detailed explanations for a confused user. This adjustment data is finally sent to the user.

[1517] Step 10:

[1518] The server compiles the generated questions and explanations into a form and sends it to the user's device in HTML format, etc. The user answers the questions presented on their own device.

[1519] Step 11:

[1520] The user answers the questions presented on the terminal. For example, they might enter "According to Article 4 of the Civil Code, the age of majority is 20 years old." This input data is sent as the answer to the next evaluation step.

[1521] Step 12:

[1522] The device sends the user's answer to the server, which then analyzes the answer using an evaluation engine to determine whether it is correct. For example, the answer "20 years old" is recorded as the correct answer.

[1523] Step 13:

[1524] The server stores the evaluation results in a database and sends the generative AI model a new request for the next learning step, including a prompt such as "Prepare the next question on accountability."

[1525] Step 14:

[1526] The generative AI model generates questions and explanations for the next learning step and returns them to the server. For example, it generates a question and explanation for "How does the definition of adulthood in Article 4 of the Civil Code affect legal responsibility?"

[1527] Step 15:

[1528] The server presents the generated questions and explanations to the user, and also displays a prioritized list of important learning topics, such as "Details of Accountability" and "Historical Changes in the Age of Majority."

[1529] Step 16:

[1530] The user can then use the device to check new questions and explanations and select the next item to study. This provides efficient and personalized learning support that takes into account the user's individual learning level and emotional state.

[1531] (Application example 2)

[1532] 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."

[1533] Current learning support systems provide uniform learning content without considering the user's emotional state, which can lead to confusion and stress. Furthermore, when providing instructions to robots in factory work, it is difficult to provide appropriate feedback based on the situation or environment, making efficient work instruction difficult. Therefore, there is a need to provide dynamic learning support that adapts to the situation of the user or robot.

[1534] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1535] In this invention, the server includes: [means for receiving legal or academic text as input from a user]; [means for analyzing the received text and extracting learning items]; and [means for generating questions and explanations using a generative AI model based on the extracted learning items]. This enables dynamic adjustment of learning content according to the emotional state and environment of the user or robot.

[1536] A "law" is a set of rules established by the national or local government to maintain social order.

[1537] A "paper" is a document that presents the results of academic research in written form.

[1538] "Text" is a body of writing or written content.

[1539] "User" means a person or device that uses the system.

[1540] A "learning item" is a specific content or topic to be learned.

[1541] A "generative AI model" is an algorithm that uses artificial intelligence to automatically generate questions and explanations.

[1542] "Questions" are questions used to evaluate the learning content.

[1543] "Explanation" provides answers, additional information, and explanations to questions.

[1544] An "emotion recognition means" is a device or algorithm for recognizing the emotional state of a user or a robot.

[1545] "Learning content" refers to the specific information and knowledge that users and robots should learn.

[1546] "Evaluation" refers to judging the correctness and quality of the user's answer.

[1547] "Feedback" refers to the provision of guidance and information based on the user's learning results and the robot's working status.

[1548] "Environment" is the physical or situational conditions in which learning or work takes place.

[1549] "Dynamic adjustment" means changing learning content in real time depending on the situation and emotional state.

[1550] This invention applies a learning support system to provide work guidance to robots in a factory. This system uses the following software and hardware.

[1551] Software and hardware used:

[1552] Software: Generative AI models (using Hugging Face's Transformers), text analysis APIs, emotion recognition algorithms

[1553] Hardware: Robot camera (using OpenCV), server, user terminal

[1554] System operation description:

[1555] 1. Text input from the user:

[1556] Users access the system using a terminal and input the text of the law or paper they wish to study.

[1557] This is done by entering a specific prompt sentence, such as "I would like to learn about the contents of Article 4 of the Civil Code."

[1558] 2. Text analysis and learning item extraction:

[1559] The terminal transmits the input text data to the server.

[1560] The server uses a text analysis API to analyze the content of the text and extract learning items.

[1561] 3. Generating Problems and Explanations:

[1562] The server sends a request to the generative AI model based on the extracted learning items.

[1563] The generative AI model generates questions and explanations in response to user prompts.

[1564] For example, the question "According to Article 4 of the Civil Code, what is the age of majority?" and its explanation are generated.

[1565] 4. Emotion Recognition and Feedback:

[1566] The server uses images captured by the robot's camera and passes them to an emotion recognition algorithm to recognize the robot's emotional state.

[1567] Emotion recognition algorithms detect states such as confusion, concentration, and relaxation from the robot's facial expressions and movements.

[1568] The server adjusts the learning content based on the perceived emotional state: for example, if the robot is confused, it will lower the difficulty of the questions or add more detailed explanations.

[1569] 5. Providing Feedback:

[1570] The adjusted learning content is sent to the terminal and presented to the user or robot.

[1571] The user or robot answers the adjusted questions and sends the results back to the server.

[1572] The server evaluates the answers and generates learning content for the next step.

[1573] Examples:

[1574] If a user inputs "I want to learn about Article 4 of the Civil Code," the generative AI model generates a question and explanation: "According to Article 4 of the Civil Code, what is the age of majority?" The robot's camera recognizes the user's confused state and provides a detailed explanation with a lower level of difficulty. This improves the robot's learning efficiency.

[1575] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1576] Step 1:

[1577] The user accesses the system using a terminal and inputs the text of the law or paper they wish to study. For example, they input a prompt such as, "I would like to learn about Article 4 of the Civil Code." The input data is text data.

[1578] Step 2:

[1579] The device sends the input text data to the server. The server uses a text analysis API to analyze the content of the text and extracts learning items. For example, items such as "Definition of adulthood" and "Corporate responsibility" are extracted. The input is text data, and the output is learning items.

[1580] Step 3:

[1581] The server sends the extracted learning items as requests to the generative AI model, which then generates questions and explanations. For example, a question and explanation might be generated for "According to Article 4 of the Civil Code, what is the age of majority?" The input is the learning item, and the output is the question and explanation.

[1582] Step 4:

[1583] The server sends the questions and explanations to the terminal to present to the user or robot. The terminal displays the generated questions and explanations to the user and accepts the user's answers. The input is the questions and explanations, and the output is the user's answers.

[1584] Step 5:

[1585] Images captured by the robot's camera are sent to the server, which then uses an emotion recognition algorithm to recognize the robot's emotional state, such as confusion, concentration, or relaxation. The input is image data, and the output is the emotional state.

[1586] Step 6:

[1587] The server adjusts the generated learning content based on the recognized emotional state. For example, if the robot is confused, it may lower the difficulty of the questions or add more detailed explanations. The input is the emotional state and the learning content, and the output is the adjusted learning content.

[1588] Step 7:

[1589] The server sends the adjusted learning content to the terminal and presents it to the user or robot. The input is the adjusted learning content, and the output is the presentation of the learning content.

[1590] Step 8:

[1591] The user or robot answers the adjusted questions and sends the results back to the server via the terminal. The server evaluates the user's answers and sends a request to the generative AI model to determine the next learning step. The input is the user's answer, and the output is the next learning content.

[1592] Step 9:

[1593] The generative AI model generates questions and explanations corresponding to the next learning content and returns them to the server. The server then sends the newly generated questions and explanations to the device and presents them to the user or robot as the next learning content. This provides continuous and dynamic learning support. The input is a learning step request, and the output is a new question and explanation.

[1594] 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.

[1595] 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.

[1596] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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).

[1601] 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.

[1602] 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."

[1603] 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.

[1604] 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).

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] The following is further disclosed regarding the above embodiment.

[1616] (Claim 1)

[1617] [means for accepting legal or treatise text as input from a user;

[1618] [Means for analyzing received text and extracting learning items;

[1619] [Means for generating questions and explanations using a generative AI model based on the extracted learning items;

[1620] [Means for presenting the generated questions and explanations to the user and accepting the user's answers;

[1621] [Means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using a generative AI model;

[1622] [Means of presenting the user with next learning content;

[1623] A system including:

[1624] (Claim 2)

[1625] The system according to claim 1, further comprising means for presenting the generated questions and explanations in accordance with the user's learning level.

[1626] (Claim 3)

[1627] The system according to claim 1, further comprising means for indicating prioritized items to be studied based on the content of the analyzed text.

[1628] "Example 1"

[1629] (Claim 1)

[1630] [means for accepting text as input from a user;

[1631] [Means for analyzing received text and extracting learning items;

[1632] [Means for generating questions and explanations using a generative AI model based on the extracted learning items;

[1633] [Means for presenting the generated questions and explanations to the user and accepting the user's answers;

[1634] [Means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using a generative AI model;

[1635] [Means of presenting the user with next learning content;

[1636] [Means for dynamically generating prompt sentences to be input to the generative AI model;

[1637] [Means to save the user's learning progress and regenerate appropriate learning content the next time the user accesses the site;

[1638] A system including:

[1639] (Claim 2)

[1640] The system according to claim 1, further comprising means for presenting the generated questions and explanations in accordance with the user's learning level.

[1641] (Claim 3)

[1642] The system according to claim 1, further comprising means for indicating prioritized items to be studied based on the content of the analyzed text.

[1643] "Application Example 1"

[1644] (Claim 1)

[1645] [means for accepting legal or treatise text as input from a user;

[1646] [Means for analyzing received text and extracting learning items;

[1647] [Means for generating questions and explanations using a generative AI model based on the extracted learning items;

[1648] [Means for presenting the generated questions and explanations to the user and accepting the user's answers;

[1649] [Means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using a generative AI model;

[1650] [Means for presenting the generated questions and explanations as learning content for motor vehicle drivers;

[1651] A system including:

[1652] (Claim 2)

[1653] [The system according to claim 1, wherein the generated questions and explanations are presented according to the user's learning level.

[1654] (Claim 3)

[1655] [The system according to claim 1, which indicates traffic rules and driving-related legal knowledge as items to be learned with priority based on the content of the analyzed text.]

[1656] "Example 2: Combining Emotion Engines"

[1657] (Claim 1)

[1658] [means for accepting legal or treatise text as input from a user;

[1659] [Means for analyzing received text and extracting learning items;

[1660] [Means for generating questions and explanations using a generative AI model based on the extracted learning items;

[1661] [Means for presenting the generated questions and explanations to the user and accepting the user's answers;

[1662] [Means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using a generative AI model;

[1663] [Means of presenting the user with next learning content;

[1664] [Means for accepting sensor data and analyzing the user's emotions using an emotion engine to recognize the user's emotional state;

[1665] [A system including a means for adjusting learning content based on emotional state.

[1666] (Claim 2)

[1667] The system according to claim 1, further comprising means for presenting the generated questions and explanations in accordance with the user's learning level.

[1668] (Claim 3)

[1669] The system according to claim 1, further comprising means for indicating prioritized items to be studied based on the content of the analyzed text.

[1670] "Application example 2 when combining emotion engines"

[1671] (Claim 1)

[1672] [means for accepting legal or treatise text as input from a user;

[1673] [Means for analyzing received text and extracting learning items;

[1674] [Means for generating questions and explanations using a generative AI model based on the extracted learning items;

[1675] [Means for presenting the generated questions and explanations to the user and accepting the user's answers;

[1676] [an emotion recognition means for recognizing an emotional state of a user, and a means for adjusting learning content based on the recognized emotional state;

[1677] [Means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using a generative AI model;

[1678] [Means of presenting the user with next learning content;

[1679] A system including:

[1680] (Claim 2)

[1681] The system of claim 1, further comprising means for presenting the generated questions and explanations according to the user's learning level and emotional state.

[1682] (Claim 3)

[1683] The system of claim 1 further comprising: [means for indicating prioritized items to be studied based on the content of the analyzed text; and [means for dynamically adjusting the study content based on the recognized emotional state. [Explanation of symbols]

[1684] 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. means for accepting legal or treatise text as input from a user; A means for analyzing the received text and extracting learning items; A means for generating questions and explanations using a generative AI model based on the extracted learning items; means for presenting the generated questions and explanations to a user and accepting answers from the user; a means for evaluating the user's answers, determining the next learning content based on the evaluation results, and generating further questions and explanations using a generative AI model; a means for presenting the user with next learning content; A system including:

2. 2. The system according to claim 1, further comprising means for presenting the generated questions and explanations in accordance with the learning level of the user.

3. 2. The system according to claim 1, further comprising means for indicating, in order of priority, items to be studied intensively based on the contents of the analyzed text.

Images