System

Abstract

To provide a system.SOLUTION: A system includes: means, which is a tool for learning, for instructing a user to learn a range to be learned corresponding to a level of the user; means for analyzing a trend from a learning history; means for causing contents for deepening understanding of the range to be learned to be read; means for generating a question on the basis of the read contents; means for receiving an answer to the generated question; means for evaluating user's understanding on the basis of the answer and generating a question again according to an evaluation result; means for acquiring feeling data of the user and adjusting learning contents on the basis of feeling; means for calculating and displaying progress of learning on the basis of the learning history; and means for instructing the user to learn the range when there are many wrong questions in a specific range.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] Conventional learning tools have made it difficult to provide individual learning schemes that correspond to the learner's level of understanding and learning progress, which means that learners are unable to progress efficiently in their studies according to their own level of understanding. [Means for solving the problem]

[0005] The learning tool of the present invention includes means for focusing learning on areas that should be studied according to the learner's level, means for performing trend analysis from learning history, means for loading content to deepen understanding, means for generating questions based on the loaded content, means for accepting answers to the generated questions, means for evaluating the level of understanding based on the answers and for generating new questions according to the evaluation results. This provides an individual learning scheme according to the learner's level of understanding and learning progress, enabling the learner to efficiently study according to their own level of understanding. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The learning tool of the present invention allows a learner to select the range of study to be done according to their own level, and generates problems based on that range. Specifically, if a learner is studying "differential calculus" in mathematics, the learner selects a range from basic concepts to applications of differentiation according to their level, and generates problems based on that range.

[0029] "Example 2"

[0030] The learning tool of the present invention evaluates the learner's level of understanding based on their answers and generates new questions based on the evaluation results. Specifically, after the learner answers the generated questions, the level of understanding is evaluated based on the accuracy of the answers and the time it took to answer, and the next question is generated based on the evaluation results. For example, if the learner correctly answers a basic question on differential calculus, the next question will be a more applied question. Conversely, if the learner makes a mistake on a basic question, another basic question within the same range will be generated.

[0031] "Example 3"

[0032] The learning tool of the present invention saves the learner's learning history and manages the learner's learning progress based on the saved learning history. Specifically, information such as which range the learner has studied and to what extent, and which questions the learner got wrong, is saved as a learning history, and the learner's learning progress is displayed based on the learning history. For example, if a learner has studied the entire range of differential calculus, the learner's learning progress is displayed as 100%. Furthermore, if the learner has made many mistakes on questions in a specific range, the learner is instructed to focus on studying that range.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Learners choose the range of material they should study based on their own level. For example, if a learner is studying "differential calculus" in mathematics, they should choose a range of material from the basic concepts of differentiation to its applications based on their level.

[0036] Step 2: Generate problems based on the selected range. For example, if a learner selects the basic concept of differentiation, generate basic differentiation problems based on that range.

[0037] "Example 2"

[0038] Step 1: The learner answers the generated questions.

[0039] Step 2: Evaluate the learner's level of understanding based on the accuracy of their answers and the time it took to complete them.

[0040] Step 3: Generate the next question based on the evaluation results. For example, if the learner correctly answers a basic problem on differentiation, the next question will be a more applied problem. Conversely, if the learner makes a mistake on a basic problem, another basic problem in the same area will be generated.

[0041] "Example 3"

[0042] Step 1: Save information such as what areas the learner has studied, how much they have studied, and which questions they got wrong as a learning history.

[0043] Step 2: Display the learning progress based on the saved learning history. For example, if a learner has learned the entire range of differentiation, the learning progress will be displayed as 100%.

[0044] Step 3: If the student makes many mistakes in a particular area, instruct them to focus on that area.

[0045] Example 1

[0046] Next, a description will be given of Example 1 of Form 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."

[0047] With conventional learning tools, it was difficult to select an appropriate learning area according to the learner's level or to generate individually tailored questions. Furthermore, effective learning progress management based on learning history and learning trends was not sufficiently implemented. This made it difficult for learners to progress efficiently and hindered improvement in comprehension.

[0048] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for focusing on learning areas to be studied according to level, a means for performing trend analysis from the learning history, a means for loading content to deepen understanding, a means for generating questions based on prompt sentences using a generative AI model, a means for accepting answers to the generated questions, and a means for evaluating the level of understanding based on the answers and generating questions again according to the evaluation results. This makes it possible to select an appropriate learning area according to the learner's level and generate individually tailored questions, thereby realizing effective learning progress management based on the learning history and learning trends.

[0049] A "learning tool" is a device or software that a learner uses to acquire specific knowledge or skills.

[0050] "Level" is an indicator of a learner's level of knowledge and skill proficiency.

[0051] A "study scope" is the range of specific content or topics that a learner should study.

[0052] "Means for focused learning" are methods or functions that allow learners to concentrate on a specific learning area and progress with their studies.

[0053] "Learning history" is data that records what a learner has learned in the past and their progress.

[0054] "Trend analysis" refers to analyzing a learner's learning patterns and progress based on their learning history.

[0055] "Deepening content" is information or material provided to help learners gain a deeper understanding of a particular topic.

[0056] A "generative AI model" is a model that uses artificial intelligence to perform a specific task (in this case, problem generation).

[0057] A "prompt" is text that gives specific instructions or questions to a generative AI model.

[0058] A "means for generating problems" is a method or function for automatically creating problems for learners to solve.

[0059] "Means for accepting answers" refers to the method or function by which the system receives the answers given by the learner.

[0060] "Means for assessing comprehension" refers to methods or functions for measuring the learner's comprehension based on their answers.

[0061] The "means for generating questions again based on the evaluation results" refers to a method or function for creating new questions based on the results of the evaluation of the level of understanding.

[0062] The present invention relates to a learning tool that allows a learner to select a learning range according to his or her own level and generates questions based on that range. A specific embodiment of this system will be described below.

[0063] System configuration

[0064] This system consists of three main components: a server, a terminal, and a user. The server selects the study area, generates prompts, generates questions, displays the questions, accepts answers, and evaluates comprehension. The terminal provides an interface for the user to select the study area and answer the generated questions. The user selects the study area and solves the questions through the terminal.

[0065] Hardware and software used

[0066] The server generates questions using a generative AI model, such as OpenAI's GPT-4 (registered trademark). The device uses a standard web browser or mobile application to provide an interface for users to select a learning area and answer questions.

[0067] Data processing and calculation

[0068] The server generates a prompt based on the learning content selected by the user and sends the prompt to the generative AI model. The generative AI model generates an appropriate question based on the prompt and returns the result to the server. The server then sends the generated question to the device and displays it to the user. When the user answers the question, the device sends the answer to the server, and the server evaluates the user's level of understanding based on the answer.

[0069] Specific examples

[0070] For example, if the user selects "Fundamental Concepts of Differentiation," the server sends the following prompt to the generative AI model:

[0071] Example prompt sentence:

[0072] "Generate problems that address the fundamental concepts of differentiation. The problems should be beginner-level and focus on the definition of differentiation and basic calculation methods."

[0073] Based on this prompt, the generative AI model generates the following questions:

[0074] "Find the derivative of the following function \( f(x) = x^2 \)."

[0075] The server receives the problem and sends it to the terminal. The terminal displays the problem to the user, who solves it. When the user enters the answer, the terminal sends the answer to the server, and the server evaluates the user's understanding based on the answer.

[0076] The above is a specific embodiment for carrying out this invention. This system allows learners to select the appropriate study area according to their own level and solve problems that are individually tailored to them. This is expected to improve the learner's understanding.

[0077] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0078] Step 1: Select your study area

[0079] The user selects the learning topic using the terminal. For example, if the user wants to learn "differential calculus" in mathematics, the user selects "differential calculus" through the terminal interface.

[0080] Input: User-selected learning area (e.g., "Differential")

[0081] Output: Information about the selected study area

[0082] Specific operation: The user selects "differentiation" from the drop-down menu displayed on the terminal screen, and the terminal sends the selection information to the server.

[0083] Step 2: Generate a prompt statement

[0084] The server generates a prompt based on the received learning scope. For example, if the user selects "Basic concepts of differentiation," the server generates the prompt "Please generate problems related to the basic concepts of differentiation. The problems should be aimed at beginners and focus on the definition of differentiation and basic calculation methods."

[0085] Input: Information about the selected study area

[0086] Output: Generated prompt statement

[0087] Specific operation: The server analyzes the information in the selected learning area and generates an appropriate prompt sentence.

[0088] Step 3: Generate the problem

[0089] The server sends the generated prompt to the generative AI model, which generates an appropriate question based on the prompt and returns the result to the server.

[0090] Input: Generated prompt text

[0091] Output: Generated problem

[0092] Specific operation: The server sends a prompt to the generative AI model, which then analyzes the prompt and generates a problem. For example, it generates a problem such as, "Find the derivative of the following function \( f(x) = x^2 \)."

[0093] Step 4: View the problem

[0094] The server receives the generated questions and sends them to the terminal, which displays them to the user.

[0095] Input: Generated question

[0096] Output: The problem as seen by the user

[0097] Specific operation: The server sends the generated problem to the terminal, which displays it to the user, who then solves it.

[0098] Step 5: Accepting responses

[0099] The user solves the problem and enters the answer into the terminal, which then sends the answer to the server.

[0100] Input: User's answer

[0101] Output: The answer sent to the server

[0102] Specific operation: The user enters the answer in the input field of the terminal and presses the send button. The terminal then sends the answer to the server.

[0103] Step 6: Assess understanding

[0104] The server evaluates the user's level of understanding based on the received answers, and generates new questions based on the evaluation results.

[0105] Input: User's answer

[0106] Output: Comprehension assessment results and new questions

[0107] Specific operation: The server analyzes the user's answers and evaluates their level of understanding. Based on the evaluation results, it generates new prompts and sends them to the generative AI model again to generate new questions.

[0108] The above is the specific processing flow of the program of this system.

[0109] (Application example 1)

[0110] Next, a description will be given of Application Example 1 of Embodiment 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."

[0111] Conventional learning tools are inadequate in generating questions and adjusting learning content according to the learner's level, and there is a lack of means for factory workers in particular to efficiently learn robot operation and maintenance skills. Furthermore, there is an issue that the generated questions and explanations are not appropriately adjusted according to the learner's level of understanding, resulting in a decrease in learning effectiveness.

[0112] 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.

[0113] In this invention, the server includes: means for focusing learning on areas to be learned according to level; means for performing trend analysis from learning history; means for loading content to deepen understanding; means for generating questions based on the loaded content; means for accepting answers to the generated questions; means for evaluating the level of understanding based on the answers and generating new questions according to the evaluation results; means for factory workers to learn robot operation and maintenance skills; means for generating questions related to robot operation and maintenance according to the learner's level; means for generating detailed explanations using a generative AI model; and means for displaying the generated explanations. This enables appropriate question generation and explanations according to the learner's level, making it possible for factory workers in particular to efficiently learn robot operation and maintenance skills.

[0114] "Means for focusing on learning areas that should be studied according to level" refers to a means for selecting content to be studied based on the learner's current knowledge and skill level, and for focusing on learning that content.

[0115] "Means for analyzing trends from learning history" refers to a means for analyzing a learner's past learning history and understanding learning trends and patterns.

[0116] "Means for loading content to deepen understanding" refers to a means for learners to input the content they wish to learn into the system and proceed with their learning based on that content.

[0117] The "means for generating questions based on the content that has been read" refers to a means for automatically generating appropriate questions based on the learning content that the learner has input.

[0118] The "means for accepting answers to questions that have been generated" refers to the means by which the system accepts answers to questions that have been answered by learners.

[0119] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" refers to a means for evaluating the answers of the learner and generating new questions based on the evaluation results.

[0120] "Means for factory workers to learn robot operation and maintenance skills" refers to means for factory workers to learn knowledge and skills related to robot operation and maintenance.

[0121] The "means for generating problems relating to the operation and maintenance of a robot according to the level of the learner" refers to a means for automatically generating problems relating to the operation and maintenance of a robot according to the skill level of the learner.

[0122] "Means for generating detailed explanations using a generative AI model" refers to means for automatically generating detailed explanations that are easy for learners to understand, using a generative AI model.

[0123] "Means for displaying the generated explanation" refers to means for displaying the explanation generated by the generative AI model to the learner.

[0124] A system for implementing this invention is a learning tool for factory workers to learn robot operation and maintenance skills. This system selects an appropriate learning area based on the learner's level, generates questions based on that area, and provides detailed explanations using a generative AI model.

[0125] System configuration

[0126] 1. Hardware:

[0127] Factory robots

[0128] PC or tablet

[0129] server

[0130] 2. Software:

[0131] Python

[0132] Generative AI models (e.g., GPT-3 (registered trademark))

[0133] Database Management Systems

[0134] Program processing explanation

[0135] The server selects a learning area based on the learner's level and generates questions based on that area. Specifically, when a learner selects one of the levels "beginner," "intermediate," or "advanced," questions related to robot operation and maintenance appropriate for that level are generated.

[0136] The generated questions are displayed on the learner's device (PC or tablet), and the learner enters their answers. The server accepts the learner's answers and evaluates their level of understanding. Based on the evaluation results, the server generates new appropriate questions and provides them to the learner.

[0137] Furthermore, a generative AI model is used to automatically generate detailed explanations that are easy for learners to understand, and the generated explanations are displayed on the learner's device.

[0138] Specific examples

[0139] For example, if the learner selects the "Intermediate" level, the following prompt will be generated:

[0140] Prompt: "Please explain how to calibrate the robot's sensors."

[0141] If we feed this prompt into a generative AI model, it will generate a detailed explanation like this:

[0142] To calibrate the robot's sensors, first place the robot in a stable position and perform the initial sensor setup. Then, use a calibration standard to adjust the sensor readings. Finally, save the calibration results and test them to verify accuracy.

[0143] In this way, learners can efficiently learn robot operation and maintenance skills.

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

[0145] Step 1:

[0146] A user logs in to the system using a terminal and selects their learning level (beginner, intermediate, or advanced). The input is the user's learning level, and the output is the information on the selected learning level. The server receives this information and proceeds to the next step.

[0147] Step 2:

[0148] The server selects the appropriate learning area based on the selected learning level. The input is the user's learning level, and the output is the selected learning area. The server retrieves the data for the corresponding learning area from the database and proceeds to the next process.

[0149] Step 3:

[0150] The server generates questions based on the selected learning scope. The input is the data from the learning scope, and the output is the generated questions. The server uses the generative AI model to generate questions appropriate for the learning scope and proceeds to the next step.

[0151] Step 4:

[0152] The server sends the generated questions to the user's terminal. The input is the generated question, and the output is the question displayed on the user's terminal. The user checks the question on the terminal and enters the answer.

[0153] Step 5:

[0154] The user inputs the answer to the question using a terminal and sends it to the server. The input is the user's answer, and the output is the answer data sent to the server. The server receives this data and proceeds to the next step.

[0155] Step 6:

[0156] The server evaluates the user's answers and determines the level of understanding. The input is the user's answer data, and the output is the evaluation result of the level of understanding. The server uses an evaluation algorithm to evaluate the user's level of understanding and proceeds to the next step.

[0157] Step 7:

[0158] The server generates new questions based on the evaluation results. The input is the evaluation result of the level of understanding, and the output is the newly generated questions. The server uses the generative AI model to generate new questions based on the evaluation results and proceeds to the next process.

[0159] Step 8:

[0160] The server generates a detailed explanation using a generative AI model. The input is a newly generated problem, and the output is a detailed explanation. The server inputs a prompt sentence into the generative AI model and generates a detailed explanation.

[0161] Step 9:

[0162] The server sends the generated detailed explanation to the user's device. The input is the detailed explanation, and the output is the explanation displayed on the user's device. The user checks the detailed explanation on the device and proceeds with their learning.

[0163] Example 2

[0164] Next, a description will be given of Example 2 of Form 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."

[0165] Conventional learning tools have difficulty generating appropriate questions based on the learner's level of understanding, which has led to problems with insufficient learning outcomes. Furthermore, they lack a mechanism for effectively utilizing the learner's response data to generate the next question, resulting in insufficient learning support tailored to each learner's individual level of understanding.

[0166] 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.

[0167] In this invention, the server includes a means for collecting learner response data, a means for evaluating the learner's level of understanding, a means for generating the next question using a generative AI model, and a means for delivering the generated question to the learner. This makes it possible to automatically generate appropriate questions according to the learner's level of understanding and provide learning support according to the learner's individual level of understanding.

[0168] A "learning tool" is a system or software that a learner uses to acquire specific knowledge or skills.

[0169] "Means for focusing on areas that should be studied according to level" is a function that selects an appropriate learning area based on the learner's current level of understanding and progress, and allows them to focus on studying that area.

[0170] "Means for analyzing trends from learning history" is a function for analyzing a learner's past learning data and extracting learning trends and patterns.

[0171] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[0172] "Means for generating questions based on the content that has been read" is a function for creating appropriate questions for learners based on the teaching materials and information provided.

[0173] The "means for accepting answers to questions generated" is a function for inputting answers to questions answered by learners into the system and recording them.

[0174] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for analyzing the learner's answer data and automatically generating the next question based on the results.

[0175] "Means for collecting learner response data" is a function for collecting data on questions answered by learners and storing it in the system.

[0176] The "means for assessing the learner's level of understanding" is a function for analyzing the learner's response data and assessing the learner's level of understanding based on the results.

[0177] "Means for generating the next question using a generative AI model" is a function that uses artificial intelligence to automatically generate the next question based on the learner's level of understanding.

[0178] The "means for delivering generated questions to learners" is a function for presenting generated questions to learners and encouraging them to answer them.

[0179] The present invention is a system that automatically generates questions according to the learner's level of understanding and effectively supports the learner's learning. A specific embodiment of this system will be described below.

[0180] System configuration

[0181] This system is mainly composed of three elements: a server, a terminal, and a user. The server collects learners' response data, evaluates their level of understanding, and generates the next question. The terminal provides an interface for learners to answer questions and sends the answer data to the server. Users answer questions through their terminals and progress through their studies.

[0182] Hardware and software used

[0183] The server is a computer with high-performance computing capabilities, implemented using a programming language such as Python. Machine learning libraries include Tensorflow (registered trademark) and PyTorch. Generative AI models include advanced natural language processing models such as GPT-4.

[0184] Data processing and calculation

[0185] The server receives the learner's response data sent from the terminal and performs the following data processing and calculations.

[0186] 1. Data collection: The device collects data on the questions answered by the learner and sends it to the server. This data includes whether the answer was correct or incorrect, the time it took to answer, the type of question, etc.

[0187] 2. Data analysis: The server analyzes the received data and evaluates the learner's level of understanding. Specifically, it calculates a score based on the percentage of correct answers and the time it took to answer.

[0188] 3. Problem generation: The server generates the next problem based on the evaluation results. It uses a generative AI model (e.g., GPT-4) to generate a problem of appropriate difficulty. It uses prompts to provide instructions to the model.

[0189] 4. Question distribution: The server sends the generated questions to the terminal and presents them to the learner.

[0190] Specific examples

[0191] For example, consider a case where a user answers a basic question on differentiation. If the user correctly answers "2x" to the question "Find the derivative of f(x) = x^2," the server will evaluate the user's level of understanding as high. Next, it will generate an applied question such as "Find the derivative of f(x) = x^3 + 3x^2."

[0192] Conversely, if the user makes a mistake in a basic problem, for example, if they answer "x" to "Find the derivative of f(x) = x^2," the server will evaluate the user's level of understanding as low. It will then generate another basic problem in the same range, such as "Find the derivative of f(x) = 2x."

[0193] Prompt Sentence Examples

[0194] Examples of prompts to use with generative AI models include:

[0195] "Once students have correctly answered the basic differentiation problem, generate a more advanced problem. For example, generate a problem that asks them to find the derivative of f(x) = x^3 + 3x^2."

[0196] In this way, the server generates appropriate questions according to the learner's level of understanding and provides them to the learner via their device, allowing the learner to tackle questions that correspond to their own level of understanding, enabling effective learning.

[0197] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0198] Step 1:

[0199] Data collection

[0200] The terminal collects data on questions answered by the user. Specifically, the user answers questions displayed on the terminal, and the terminal records the answers. Input includes the user's answer, answer time, question type, etc. The terminal sends this data to the server. The output is the answer data sent to the server.

[0201] Step 2:

[0202] Data analysis

[0203] The server analyzes the response data received from the device. The input includes the user's response data. The server executes an algorithm to evaluate the learner's level of understanding based on the accuracy of the answers and the time it took to answer. Specifically, it calculates a score based on the percentage of correct answers and the time it took to answer. The output is a score that indicates the learner's level of understanding.

[0204] Step 3:

[0205] Problem generation

[0206] The server generates the next problem based on the evaluation results. The input includes a score indicating the learner's level of understanding. The server uses a generative AI model (e.g., GPT-4) to generate a problem of appropriate difficulty. Specifically, it uses prompt sentences to provide instructions to the generative AI model. The output is the generated new problem.

[0207] Step 4:

[0208] Problem distribution

[0209] The server sends the generated questions to the terminal. The input contains the new questions that have been generated. The terminal presents the received questions to the user. Specifically, the new questions are displayed on the terminal, ready for the user to answer. The output is the new questions presented to the user.

[0210] Step 5:

[0211] User Answers

[0212] The user answers new questions presented on the terminal. The input includes new questions sent from the server. The user inputs the answers to the questions and sends them to the terminal. The output is the user's new answer data.

[0213] In this way, the server generates appropriate questions according to the learner's level of understanding and provides them to the learner via their device, allowing the learner to tackle questions that correspond to their own level of understanding, enabling effective learning.

[0214] (Application example 2)

[0215] Next, a description will be given of Application Example 2 of Form 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."

[0216] Conventional learning tools are inadequate in generating questions that correspond to the learner's level of understanding, and are not particularly suited to improving the specialized skills of factory robot maintenance engineers. Furthermore, the level of understanding is not evaluated based on the correctness of the engineer's answers or the time it takes to answer, and the next questions are not generated appropriately, making efficient learning difficult. This poses the problem of delaying the improvement of engineers' skills and reducing the operational efficiency of factories.

[0217] 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.

[0218] In this invention, the server is a learning tool for people of all ages who have learning problems, and includes: means for focusing learning on areas that should be studied according to level; means for performing trend analysis from learning history; means for loading content to deepen understanding; means for generating questions based on the loaded content; means for accepting answers to the generated questions; means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results; means for generating questions for factory robot maintenance technicians to improve their maintenance procedure and troubleshooting skills; and means for evaluating the technician's level of understanding based on the accuracy of their answers and the time it took to answer them and generating the next questions. This makes it possible to generate appropriate questions according to the technician's level of understanding, thereby achieving efficient skill improvement.

[0219] A "learning tool" is a device or software that a learner uses to acquire specific knowledge or skills.

[0220] "Level" is an indicator that shows the learner's level of understanding and skill.

[0221] "Learning history" refers to data that records a learner's past learning activities and their results.

[0222] "Trend analysis" is a method of analyzing a learner's learning patterns and progress based on their learning history.

[0223] "Understanding" is an indicator of how well a learner understands specific knowledge or skills.

[0224] "Question generation" is the process of creating new questions based on the learner's level of understanding and the content of their learning.

[0225] An "answer" is a response that a learner gives to a generated question.

[0226] The "evaluation result" is the result of evaluating the level of understanding calculated based on the learner's answers.

[0227] A "factory robot" is a mechanical device used to perform automated tasks in a factory.

[0228] A "maintenance technician" is a professional who maintains and repairs factory robots and other mechanical equipment.

[0229] "Maintenance procedures" are specific procedures for maintaining and repairing factory robots and machinery.

[0230] "Troubleshooting" is the technique of diagnosing and resolving malfunctions and problems in mechanical equipment.

[0231] "Skill improvement" refers to acquiring specific knowledge and skills and improving one's abilities.

[0232] As an embodiment of the present invention, a system is described that provides a learning tool for factory robot maintenance technicians to improve their maintenance procedures and troubleshooting skills.

[0233] System Configuration

[0234] The system uses the following hardware and software:

[0235] Hardware: Smartphones, tablets, computers

[0236] Software: Python, random module (random), time measurement module (time)

[0237] Program processing

[0238] The server executes a program that includes the following means:

[0239] 1. Problem generation method: Generate problems related to maintenance procedures and troubleshooting according to the learner's level. Specifically, basic and applied problems are randomly selected.

[0240] 2. Answer acceptance means: Learners enter answers to the generated questions.

[0241] 3. Comprehension assessment method: The learner's comprehension is assessed based on the accuracy of their answers and the time it took to complete them. If the answer is correct, a more advanced question is generated, and if the answer is incorrect, a basic question is generated again.

[0242] 4. Next question generation method: Generate the next question based on the results of the comprehension assessment.

[0243] Data processing and calculation

[0244] The server performs the following data processing and calculations.

[0245] Question generation: A random module is used to randomly select questions according to the current level of understanding.

[0246] Comprehension assessment: Compare the learner's answer with the correct answer to determine whether it is correct or incorrect. Also, use the timing module to record the answer time.

[0247] Next question generation: Based on the results of the comprehension assessment, the next question is generated. If the answer is correct, an applied question is generated again, and if the answer is incorrect, a basic question is generated again.

[0248] Specific examples

[0249] For example, if a learner correctly answers the question "Please explain the basic maintenance procedure," the next question generated will be "Please explain the applied maintenance procedure."

[0250] Prompt Sentence Examples

[0251] "If the user answers the basic maintenance procedure correctly, generate a question for the next advanced maintenance procedure."

[0252] In this way, it becomes possible to generate appropriate questions according to the engineer's level of understanding, thereby enabling efficient skill improvement.

[0253] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0254] Step 1:

[0255] The server generates questions according to the learner's level. Specifically, it uses a random module to randomly select basic or applied questions.

[0256] Input: The learner's current level of understanding

[0257] Data manipulation: Select questions using a random module

[0258] Output: Selected problems

[0259] Step 2:

[0260] The terminal presents the generated questions to the learner, who then inputs answers to the questions.

[0261] Input: Question sent by server

[0262] Data processing: None

[0263] Output: Learner's answer

[0264] Step 3:

[0265] The server receives the learner's answer and judges whether it is correct or not. If the answer is correct, it generates a more advanced question, and if it is incorrect, it generates a basic question again.

[0266] Input: Learner's answers, correct answer data

[0267] Data processing: Compare the answers with the correct data to determine whether they are correct or not

[0268] Output: Correct / incorrect result

[0269] Step 4:

[0270] The server measures the time taken by the learner to answer questions and evaluates their level of understanding. The server records the answer time using a time measurement module.

[0271] Input: Learner response time

[0272] Data processing: Record answer times using the time measurement module

[0273] Output: Answer time data

[0274] Step 5:

[0275] The server generates the next question based on the results of the comprehension assessment. If the answer is correct, it generates an applied question, and if the answer is incorrect, it generates a basic question again.

[0276] Input: Correct / incorrect result, answer time data

[0277] Data processing: Use comprehension assessment algorithms to select the next question

[0278] Output: Next problem

[0279] Step 6:

[0280] The terminal presents the next question to the learner and accepts the answer again.

[0281] Input: Next question sent from the server

[0282] Data processing: None

[0283] Output: Learner's next answer

[0284] Example 3

[0285] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0286] With conventional learning tools, it was difficult to grasp a learner's progress and level of understanding in real time and make individual adjustments. Furthermore, there was a lack of a way to effectively utilize learning history to manage learning progress, making it difficult to accurately grasp which areas a learner had studied and to what extent. Furthermore, if a learner made many mistakes in a specific area, there was a lack of a function to instruct the learner to focus on that area. This resulted in reduced learning efficiency and made it difficult for the learner's level of understanding to improve.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0288] In this invention, the server includes a means for a user to start learning and display the learning content, a means for the user to progress with the learning, a means for the terminal to send the learning progress to the server, a means for the server to save the learning history in a database, a means for the server to calculate the learning progress, a means for the terminal to display the learning progress, and a means for the user to end the learning. This makes it possible to grasp the learner's progress and level of understanding in real time and make individual adjustments. In addition, the learning history can be effectively utilized to manage the learning progress, allowing the learner to accurately grasp which areas and to what extent they have studied. Furthermore, if a learner makes many mistakes in a specific area, the system can instruct the learner to focus on studying that area, improving learning efficiency and the learner's level of understanding.

[0289] A "learning tool" is a device or software that a learner uses to acquire specific knowledge or skills.

[0290] "Means for focusing on areas that should be studied according to level" is a function that allows learners to concentrate on studying specific areas based on their current level of understanding and progress.

[0291] "Means for trend analysis from learning history" is a function that analyzes data on what learning a learner has done in the past and identifies learning trends and patterns.

[0292] "Means for reading content to deepen understanding" is a function that provides learners with the information and materials they need to gain a deeper understanding of specific knowledge or skills.

[0293] "Means for generating questions based on the content that has been read" is a function that automatically creates questions for learners to solve based on the teaching materials and information provided.

[0294] "Means for accepting answers to generated questions" is a function that allows the learner to input answers to the questions they have solved and receive them into the system.

[0295] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the answers of the learner and creating new questions based on the results.

[0296] The "means for the user to start learning and display the learning content" is a function for displaying the learning content on the screen when the learner starts learning.

[0297] "Means for users to advance their learning" refers to functions that provide operations and interfaces for learners to advance their learning.

[0298] The "means for the terminal to transmit the learning progress status to the server" is a function for recording the progress status of the learner and transmitting it to the server.

[0299] "Means for the server to save learning history in a database" is a function for saving a learner's progress and answer history in a database.

[0300] The "means for the server to calculate the learning progress" is a function for calculating the progress of the learner based on the saved learning history.

[0301] The "means for the terminal to display the learning progress" is a function for displaying the calculated learning progress to the learner.

[0302] The "means for the user to end learning" is a function that allows the learner to inform the system when they have finished learning.

[0303] This invention relates to a learning tool that saves a learner's learning history and manages the learner's learning progress based on that history. Specifically, this system saves information such as what areas the learner has studied and to what extent, and which questions they got wrong, as a learning history, and displays the learner's learning progress based on that learning history.

[0304] Hardware and software used

[0305] The system is implemented using the following hardware and software:

[0306] Server: A central processing unit that stores learning history and calculates learning progress. It uses SQLite as its database.

[0307] Terminal: A device that provides an interface for learners to progress through their studies. It displays the learning content using HTML and JavaScript (registered trademark).

[0308] User: The learner who is progressing through the learning.

[0309] Program processing

[0310] The server receives information about what the learner has learned and the questions they got wrong, and stores it in an SQLite database. Specifically, each time the learner progresses with their studies, information about the learning scope, progress, and questions they got wrong is sent to the server. The server stores this information in a database and manages it as a learning history.

[0311] The device provides an interface for learners to progress through their studies. When a learner begins studying, the device retrieves their study history from the server and displays their progress. For example, if a learner has covered the entire range of differential calculus, the device will display their progress as 100%. Furthermore, if a learner makes many mistakes in a particular range, the device will instruct them to focus on that range.

[0312] Users study through their devices. Each time a user progresses in their studies, their study history is updated and sent to the server, allowing users to check their own learning progress in real time.

[0313] Specific examples

[0314] As a concrete example, consider the case where a user is studying differentiation. When the user begins solving basic differentiation problems, the device sends the progress status to the server. The server saves this information in a database and manages it as a learning history. When the user has solved all the basic problems, the device displays the learning progress as 100%. Furthermore, if the user makes a mistake on a particular problem, this information is also saved and the device is instructed to focus on that area the next time they study.

[0315] Prompt Sentence Examples

[0316] An example of a prompt to input to a generative AI model is as follows:

[0317] "The user has started solving basic problems in differential calculus. Please send the progress to the server and save it in the database. If the user has solved all the basic problems, show the progress as 100%. If the user made a mistake on a particular problem, save that information and instruct them to focus on that problem the next time they study."

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

[0319] Step 1:

[0320] The user begins learning.

[0321] The user opens a learning app on their device and selects what they want to learn (e.g., basic differential calculus problems). The device receives the user's selection and sends a request to the server to start learning. The input is the user's selection information, and the output is the request sent to the server.

[0322] Step 2:

[0323] The device will display the learning content.

[0324] The server receives the user's request and sends the learning content to the terminal. The terminal displays the received learning content. For example, it displays the problem "Find the derivative of f(x) = x^2." The input is the learning content data from the server, and the output is the display on the terminal.

[0325] Step 3:

[0326] The user progresses through the learning process.

[0327] The user solves the problem on the terminal and inputs the answer. For example, the user inputs the answer "2x." The input is the user's answer, and the output is the answer input to the terminal.

[0328] Step 4:

[0329] The device sends the learning progress to the server.

[0330] The terminal receives the user's answer and sends the information to the server using an HTTP request. The input is the user's answer data, and the output is the data sent to the server.

[0331] Step 5:

[0332] The server stores the learning history in a database.

[0333] The server stores the received answer data in an SQLite database. The stored data includes the user ID, learning scope, progress, and information on questions answered incorrectly. The input is the answer data from the device, and the output is stored in the database.

[0334] Step 6:

[0335] The server calculates the learning progress.

[0336] The server calculates the learning progress based on the stored learning history. For example, if you solve 1 out of 10 questions, your progress is 10%. The input is the learning history stored in the database, and the output is the calculated progress.

[0337] Step 7:

[0338] The device displays your learning progress.

[0339] The server sends the calculated progress to the terminal. The terminal displays the received progress to the user. For example, it displays "Learning progress: 10%". The input is the progress data from the server, and the output is the display on the terminal.

[0340] Step 8:

[0341] The user finishes learning.

[0342] The user ends the learning, and the device sends that information to the server. The server updates the learning history and prepares for the next learning. The input is the user's end operation, and the output is the sending of the end information to the server.

[0343] (Application example 3)

[0344] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0345] With conventional learning tools, it was difficult to effectively manage a learner's learning history and properly evaluate their learning progress. It was also impossible to identify areas where a learner was having particular problems and provide instructions for focused learning. Furthermore, the lack of functionality to save learning history and load it as needed sometimes led to a loss of continuity in learning. To solve these issues, a system is needed that can effectively manage learning history, properly evaluate learning progress, and provide instructions on areas where students should focus their learning.

[0346] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0347] In this invention, the server includes means for saving the learning history and managing the learning progress based on the saved learning history, means for indicating the areas to be studied intensively based on the learning history, and means for saving the learning history in a file and reading it out as needed. This makes it possible to effectively manage the learner's learning history, appropriately evaluate the learning progress, and indicate the areas to be studied intensively.

[0348] "Study history" is data that records information such as what areas a learner has studied and to what extent, and which questions they got wrong.

[0349] "Progress" is an indicator that shows the learner's level of achievement in the entire range of what he or she has studied.

[0350] The "areas that should be studied intensively" refer to areas where the learner has a particular lack of understanding or makes many mistakes.

[0351] "Trend analysis" refers to analyzing a learner's learning patterns and problems based on their learning history.

[0352] "Means for getting the content to be absorbed" refers to the method of providing learners with the materials and information they need to study.

[0353] "Means of generating questions" are ways in which learners create new questions based on what they have learned.

[0354] The "means for accepting answers" refers to the method by which the learner inputs the answers to the questions into the system.

[0355] A "means of assessing comprehension" is a method for measuring the learner's comprehension based on their responses.

[0356] "Means of saving to a file" refers to a method of saving learning history and other data as a digital file.

[0357] "Means for loading when needed" refers to a method for loading saved data into the system again when needed.

[0358] As an embodiment of the present invention, a system is constructed that manages the learning history of a factory robot, evaluates the progress of the learning, and indicates the areas that should be prioritized for learning. A specific embodiment of this system is shown below.

[0359] System Configuration

[0360] The system consists of the following major components:

[0361] 1. Server:

[0362] Learning history storage means: Records the tasks performed by the robot and their success / failure.

[0363] Progress management tool: Calculate learning progress based on learning history.

[0364] Means for indicating areas of focus for learning: Identify tasks with many errors and indicate areas for focused learning.

[0365] File storage method: Save learning history to a file in JSON format and load it as needed.

[0366] 2. Terminal:

[0367] User interface: Provides an interface to display the robot's learning history and progress, and to indicate the areas of focus for learning.

[0368] 3. User:

[0369] Operational method: Check the robot's learning history and adjust the learning content as needed.

[0370] Hardware and software used

[0371] Hardware: Factory robots, servers, terminals

[0372] Software: Python, JSON, user interface (e.g. web browser)

[0373] Data processing and calculation

[0374] The server records the tasks performed by the robot and their success or failure, saving it as a learning history. Based on the saved learning history, the server calculates the learning progress and identifies tasks with a high number of errors. This makes it possible to indicate the areas that should be focused on for learning. The learning history is also saved to a file in JSON format, which can be loaded as needed.

[0375] Specific examples

[0376] For example, when a robot performs welding, painting, and assembly tasks, the server records the success or failure of each task. If welding is successful, painting is unsuccessful, and assembly is successful, the server calculates the learning progress based on this information and instructs the robot to focus on painting.

[0377] Prompt Sentence Examples

[0378] An example of a prompt sentence to input to the generative AI model is as follows:

[0379] Create a Python program to manage the robot's learning history. Record the tasks performed by the robot and their success / failure, and calculate the learning progress. Also, identify tasks with many errors and indicate the areas to focus on for learning. Save the learning history to a file in JSON format and load it as needed.

[0380] This prompt sentence can be used to ask the generative AI model to generate a program.

[0381] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0382] Step 1:

[0383] The server records the tasks performed by the robot and their success / failure. As input, it receives task data from the robot (task name, success / failure, timestamp) and saves this as learning history. The output is updated learning history data. Specifically, the server saves the received task data in JSON format.

[0384] Step 2:

[0385] The server calculates the learning progress based on the saved learning history. It uses the learning history data as input and calculates the percentage of successful tasks. The output is the calculated progress (percentage). Specifically, the server analyzes the learning history data, counts the number of successful tasks, and calculates the percentage of the total number of tasks.

[0386] Step 3:

[0387] The server indicates the areas that should be prioritized for learning based on the learning history. As input, it uses the learning history data to identify tasks with a high number of errors. The output is a list of priority learning areas. Specifically, the server analyzes the learning history data, counts the frequency of failed tasks, and lists the tasks with the highest frequency.

[0388] Step 4:

[0389] The server saves the learning history in a file in JSON format and reads it as needed. It uses the learning history data as input and writes it to a file. The output is the saved file. Specifically, the server writes the learning history data to a file in JSON format and reads the file as needed.

[0390] Step 5:

[0391] The terminal displays the robot's learning history and progress through a user interface and indicates the areas of focus for learning. As input, it receives learning history data, progress data, and key learning area data from the server. The output is information displayed on the user interface. In concrete terms, the terminal visually displays the received data and indicates the learning progress and key learning areas to the user.

[0392] Step 6:

[0393] The user checks the robot's learning history through the terminal and adjusts the learning content as necessary. The input is the information displayed on the terminal, and the decision is made based on that information. The output is the adjusted learning content. Specifically, the user operates the terminal interface and inputs instructions to adjust the robot's learning content.

[0394] 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.

[0395] "Example 1"

[0396] As one embodiment of the present invention, a learning system incorporating an emotion engine is provided. This system analyzes a user's learning history and adjusts the learning content based on the results. Specifically, the emotion engine recognizes the emotions the user expresses while learning and adjusts the learning content based on those emotions. For example, if the user feels that they are struggling with learning, the system adjusts the learning content to be easier. Also, if the user expresses high excitement about learning, the system adjusts the learning content to be more difficult.

[0397] "Example 2"

[0398] Another embodiment of the present invention provides a system for adjusting a learning progress using an emotion engine. Specifically, the system adjusts the learning progress based on the user's emotion. For example, if the user is highly excited about learning, the system accelerates the learning progress. Conversely, if the user is less excited about learning, the system slows down the learning progress.

[0399] "Example 3"

[0400] Furthermore, another embodiment of the present invention provides a system for individually tailoring learning content using an emotion engine. Specifically, the learning content is individually tailored based on the user's emotions. For example, if the user is highly excited about a particular learning content, the system will provide that learning content in a focused manner. Conversely, if the user is less excited about a particular learning content, the system will reduce that learning content.

[0401] The processing flow of each embodiment will be described below.

[0402] "Example 1"

[0403] Step 1: The user begins learning.

[0404] Step 2: The system analyzes the user's learning history.

[0405] Step 3: The emotion engine recognizes the user's emotion.

[0406] Step 4: The system adjusts its learning based on the emotions recognized by the emotion engine.

[0407] "Example 2"

[0408] Step 1: The user begins learning.

[0409] Step 2: The emotion engine recognizes the user's emotion.

[0410] Step 3: The system adjusts the learning progress based on the emotions recognized by the emotion engine.

[0411] "Example 3"

[0412] Step 1: The user begins learning.

[0413] Step 2: The emotion engine recognizes the user's emotion.

[0414] Step 3: The system personalizes learning based on the emotions recognized by the emotion engine.

[0415] Example 1

[0416] Next, a description will be given of Example 1 of Form 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."

[0417] Conventional learning tools can adjust learning content based on the learner's level and learning history, but they do not take into account the learner's emotional state, which can lead to learners feeling stressed or, conversely, losing interest because the content is too easy. Furthermore, when generating questions, only fixed questions can be provided, which means they cannot flexibly respond to learners' needs.

[0418] 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.

[0419] In this invention, the server includes means for performing trend analysis from learning history, means for loading content to deepen understanding, means for generating questions based on the loaded content, means for recognizing the user's emotions and adjusting the learning content based on those emotions, and means for automatically generating questions using a generative AI model. This makes it possible to flexibly adjust the learning content according to the learner's emotional state and generate questions that meet individual needs.

[0420] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[0421] "Means for focusing on areas that should be studied according to level" is a function that allows learners to select the content that should be studied based on their current knowledge and skill level, and focus on learning that area.

[0422] "Means for trend analysis from learning history" is a function for analyzing a learner's past learning data and understanding the progress and trends of learning.

[0423] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[0424] "Means for generating questions based on the content that has been read" is a function that automatically creates questions for learners to check their level of understanding based on the teaching materials and information provided.

[0425] "Means for accepting answers to questions generated" is a function that allows the system to receive and record answers to questions answered by learners.

[0426] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the learner's answers and generating new questions based on the results.

[0427] "Means for recognizing the user's emotions and adjusting the learning content based on those emotions" is a function for detecting the learner's emotional state and changing the learning content according to that state.

[0428] "Means for automatically generating questions using a generative AI model" refers to a function that uses an artificial intelligence model to automatically generate questions to be provided to learners.

[0429] MODE FOR CARRYING OUT THE INVENTION

[0430] This invention is a learning tool that allows learners to select a learning area according to their own level and generates questions based on that area. It also has the ability to recognize the user's emotions and adjust the learning content based on those emotions. This system operates in cooperation with the server, the terminal, and the user.

[0431] server

[0432] The server generates questions based on the learning range selected by the learner. Specifically, if a learner is studying "differential calculus" in mathematics, the server selects a range from basic concepts to applications of differentiation according to the learner's level and generates questions based on that range. The server automatically generates questions using a generative AI model (e.g., OpenAI's GPT-4). It sends the following prompt to the generative AI model:

[0433] Example prompt sentence:

[0434] "Generate math problems appropriate to the learner's level, ranging from basic concepts to applications of differentiation."

[0435] The generative AI model generates questions based on the prompt and returns the results to the server, which then receives the questions and sends them to the device.

[0436] Terminal

[0437] The device records the user's learning history and recognizes the user's emotions using an emotion engine. Specifically, the device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and identifies the user's emotions using an emotion engine (e.g., Affectiva or Microsoft® Azure® Emotion API). The device sends this data to a server, which uses it as information to adjust the learning content.

[0438] User

[0439] Users select the range of study they want to do based on their level. For example, if a user wants to learn the basic concepts of differential calculus, they select that range. If the user is struggling while studying, the emotion engine recognizes that emotion and the server adjusts the learning content to be easier. Also, if the user shows high levels of excitement, the server adjusts the learning content to be more difficult.

[0440] Specific examples

[0441] Example 1: Selecting a study area and generating questions

[0442] Suppose a user wants to learn "differential calculus" in mathematics and selects a range from basic concepts to applications. The server uses a generative AI model to generate problems like the one below.

[0443] Example prompt sentence:

[0444] "Generate math problems appropriate to the learner's level, ranging from basic concepts to applications of differentiation."

[0445] Example 2: Adjusting learning content using an emotion engine

[0446] If a user feels that they are struggling while studying, the device's camera and microphone will analyze their facial expressions and tone of voice, and the emotion engine will recognize that emotion. The server will then receive that information and adjust the learning content to make it easier.

[0447] Example prompt sentence:

[0448] "If a user is struggling with a lesson, generate questions to adjust the learning experience to something easier."

[0449] In this way, a system is realized in which the server, terminal, and user work together to optimize learning content.

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

[0451] Program processing flow

[0452] Step 1: Select your study area

[0453] User

[0454] Users can select the area they want to learn through the device interface, for example, selecting the area from basic concepts to applications of "differential calculus" in mathematics.

[0455] Input: The study area selected by the user.

[0456] Output: Information about the selected study area.

[0457] Step 2: Submit your study material

[0458] Terminal

[0459] The terminal receives the user's selection and transmits that information to the server.

[0460] Input: Information about the study area selected by the user.

[0461] Output: The learning scope information sent to the server.

[0462] Step 3: Generate the problem

[0463] server

[0464] The server sends a prompt to the generative AI model based on the received learning information. An example of a prompt is as follows:

[0465] "Generate math problems appropriate to the learner's level, ranging from basic concepts to applications of differentiation."

[0466] Input: Study information, prompt.

[0467] Output: The prompt sent to the generative AI model.

[0468] Generative AI Models

[0469] The generative AI model generates questions based on the prompt sentence and returns the results to the server.

[0470] Input: Prompt statement.

[0471] Output: The generated questions.

[0472] server

[0473] The server receives the generated questions and sends them to the terminal.

[0474] Input: The generated question.

[0475] Output: The problem sent to the terminal.

[0476] Step 4: View the problem

[0477] Terminal

[0478] The terminal displays the questions received from the server to the user.

[0479] Input: The problem sent by the server.

[0480] Output: The problem as seen by the user.

[0481] Step 5: Learning progression and emotional awareness

[0482] User

[0483] The user begins solving the problem displayed on the terminal.

[0484] Input: The problem displayed.

[0485] Output: The user's answer.

[0486] Terminal

[0487] The device uses a camera and microphone to monitor the user's facial expressions and tone of voice in real time.

[0488] Input: User's facial expression data, tone of voice data.

[0489] Output: Collected emotion data.

[0490] Terminal

[0491] The device sends the collected data to an emotion engine to recognize the user's emotions.

[0492] Input: Collected emotion data.

[0493] Output: Emotion recognition results from the emotion engine.

[0494] Step 6: Sending Emotion Data

[0495] Terminal

[0496] The device receives the emotion recognition results from the emotion engine and transmits the information to the server.

[0497] Input: Emotion recognition results.

[0498] Output: Emotion recognition results sent to the server.

[0499] Step 7: Adjust your learning

[0500] server

[0501] The server adjusts the learning content based on the emotion recognition results. For example, if the user is distressed, the server sends the following prompt to the generative AI model:

[0502] "If a user is struggling with a lesson, generate questions to adjust the learning experience to something easier."

[0503] Input: Emotion recognition result, prompt sentence.

[0504] Output: The new prompt sent to the generative AI model.

[0505] Generative AI Models

[0506] The generative AI model generates questions based on the new prompt sentence and returns the results to the server.

[0507] Input: New prompt statement.

[0508] Output: The new problem that was generated.

[0509] server

[0510] The server receives new questions and sends them to the terminal.

[0511] Input: The new problem that is generated.

[0512] Output: The new problem sent to the terminal.

[0513] Step 8: View the new issue

[0514] Terminal

[0515] The terminal displays the new problem to the user.

[0516] Input: New problem sent from the server.

[0517] Output: The new issue displayed to the user.

[0518] In this way, a system is realized in which the server, terminal, and user work together to optimize learning content.

[0519] (Application example 1)

[0520] Next, a description will be given of Application Example 1 of Embodiment 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."

[0521] Conventional learning tools and training systems have difficulty responding flexibly to the user's skill level and emotional state, which means that they are unable to maximize the effectiveness of learning and training. In addition, providing uniform content without considering the user's emotions can reduce motivation to learn or train.

[0522] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for focusing on learning areas that should be studied according to level, a means for performing trend analysis from learning history, and a means for loading content to deepen understanding. This enables flexible learning and training according to the user's skill level and emotional state.

[0523] "A means of focusing on areas that should be studied according to level" is a function that selects study content according to the user's skill level and allows them to concentrate on studying those areas.

[0524] "Means for trend analysis from learning history" is a function that analyzes a user's past learning data and grasps their learning progress and trends.

[0525] "Means for loading content to deepen understanding" is a function that allows users to import learning materials and resources into the system and provide them to users.

[0526] "Means for generating questions based on the content that has been loaded" is a function that automatically creates questions for the user to solve based on the teaching materials and documents that have been loaded.

[0527] "Means for accepting answers to questions generated" is a function that allows the system to receive and record answers to questions answered by users.

[0528] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the user's answers and creating new questions based on the evaluation results.

[0529] "Means for recognizing the user's emotions and adjusting the learning content based on those emotions" refers to a function that detects the user's emotional state and changes the difficulty and type of learning content according to those emotions.

[0530] "Means for providing training content according to the skill level of the operator" refers to a function for selecting and providing appropriate training content according to the technical level of the operator.

[0531] The "means for adjusting training content based on emotions" is a function for detecting the emotional state of the operator and changing the difficulty and type of training content according to that emotion.

[0532] The system for implementing the present invention can flexibly adjust learning and training content according to the user's skill level and emotional state. Specific embodiments are described below.

[0533] System Configuration

[0534] The system consists of the following main components:

[0535] 1. User device: PC or tablet used by learners and operators.

[0536] 2. Server: Manages learning and training content and adjusts it based on the user's skill level and emotional state.

[0537] 3. Cameras and sensors for emotion recognition: Hardware for detecting the user's emotional state.

[0538] Software used

[0539] 1. Python program: A program for generating and adjusting learning and training content.

[0540] 2. Emotion Engine (EmotionEngine class): Software for analyzing and recognizing user emotions.

[0541] 3. Training System (TrainingSystem class): Software that provides training content tailored to the user's skill level and adjusts based on emotions.

[0542] Data processing and calculation

[0543] The server performs the following data processing and calculations:

[0544] 1. Emotion Recognition: The emotion engine analyzes user input and camera footage to recognize emotions.

[0545] 2. Learning content generation: Generate appropriate learning and training content based on the user's skill level.

[0546] 3. Content Adjustment: Adjust the difficulty and type of learning or training content based on perceived emotions.

[0547] Specific examples

[0548] For example, if an operator is set as "Intermediate," the system will provide "Intermediate Operation Training." If the operator shows "Frustration," the system will easily adjust the training content.

[0549] Prompt Sentence Examples

[0550] Below are some example prompts to input to the generative AI model:

[0551] Write a Python program that generates training content based on the user's skill level and adjusts it based on their emotions. The emotion engine analyzes user input and recognizes emotions. The training system generates training content based on the operator's skill level and adjusts it based on their emotions.

[0552] In this way, flexible learning and training can be achieved according to the user's skill level and emotional state.

[0553] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0554] Step 1:

[0555] The user's terminal inputs the user's skill level. The input skill level is sent to the server. The server processes the data to select appropriate learning and training content based on the skill level.

[0556] Step 2:

[0557] The server receives data from emotion recognition cameras and sensors. The emotion engine analyzes this data and recognizes the user's emotional state. The recognized emotional state is sent to the server, which performs data calculations to adjust learning and training content based on this emotional state.

[0558] Step 3:

[0559] The server generates appropriate learning and training content based on the user's skill level and emotional state, and sends the generated content to the user's device, which then displays it to the user.

[0560] Step 4:

[0561] The user terminal accepts the user's answers. The accepted answers are sent to the server, which processes the data to evaluate the user's level of understanding based on the answers.

[0562] Step 5:

[0563] The server generates new questions based on the evaluation results, and sends the generated questions to the user's terminal, which then displays the questions to the user.

[0564] Step 6:

[0565] The server stores the user's learning history, which is used to generate and tailor future learning and training content.

[0566] Step 7:

[0567] The server adjusts the learning and training content based on the user's emotional state, and sends the adjusted content to the user's device, which then displays it to the user.

[0568] The above steps enable flexible learning and training according to the user's skill level and emotional state.

[0569] Example 2

[0570] Next, a description will be given of Example 2 of Form 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."

[0571] With conventional learning tools, it was difficult to properly evaluate a learner's level of understanding and learning progress and adjust the next learning content based on that. Furthermore, because the learning progress was not adjusted taking into account the learner's emotional state, it was difficult to maintain the learner's motivation. Furthermore, because question generation was not automated using a generative AI model, it was not possible to provide a personalized learning experience.

[0572] 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.

[0573] In this invention, the server includes a means for performing trend analysis from learning history, a means for loading content to deepen understanding, and a means for generating questions based on the loaded content. This makes it possible to appropriately evaluate the learner's level of understanding and generate the next question based on that assessment. The server also includes a means for collecting user emotional data and adjusting the learning progress, a means for generating the next question using a generative AI model, and a means for generating prompt sentences and inputting them into the generative AI model. This makes it possible to adjust the learning progress taking into account the learner's emotional state, providing a personalized learning experience.

[0574] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[0575] "Means for focusing on learning areas that should be studied according to level" is a function that selects and focuses on content to be studied based on the learner's current level of understanding and skill.

[0576] "Means for trend analysis from learning history" is a function that analyzes a learner's past learning data and grasps the progress of their learning and trends in their level of understanding.

[0577] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[0578] "Means for generating questions based on the content that has been loaded" is a function for automatically creating new study questions based on the teaching materials and information provided.

[0579] The "means for accepting answers to questions that have been generated" is a function that allows a learner to input answers to questions that have been answered and send them to the system.

[0580] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for analyzing the learner's answers, evaluating their level of understanding, and then generating the next learning question.

[0581] "Means for collecting user emotional data and adjusting the learning progress" refers to a function for analyzing the learner's emotional state and adjusting the learning progress speed and difficulty based on that.

[0582] "Means for generating the next question using a generative AI model" is a function that uses an artificial intelligence model to automatically generate new learning questions based on the learner's level of understanding and learning history.

[0583] "Means for generating prompt sentences and inputting them into a generative AI model" refers to a function for creating text to provide appropriate instructions to a generative AI model and inputting it into the model.

[0584] This invention relates to a learning tool that evaluates a learner's level of understanding and adjusts the next learning content based on that evaluation. Specifically, it provides a system in which the elements of a server, a terminal, and a user work together.

[0585] Server Roles

[0586] The server receives the learner's response data and analyzes it. Specifically, the server uses Python to run an algorithm that evaluates the accuracy of the learner's response and the time it took to complete it. Based on the evaluation results, the server uses a generative AI model (e.g., a general-purpose artificial intelligence model) to generate the next problem. If the learner correctly answers a basic calculus problem, the server generates an applied problem as the next problem. Conversely, if the learner makes a mistake on a basic problem, the server generates another basic problem in the same area.

[0587] Device Role

[0588] The device provides an interface for the learner to answer questions. Specifically, the device uses an application that runs on a web browser to display questions to the learner and prompts them to enter their answers. The device then sends the learner's answer data to a server. The device also uses a camera and microphone to connect to an emotion engine (e.g., emotion analysis software) to collect the learner's emotional data.

[0589] User Roles

[0590] The user answers questions displayed on the device. When the user answers a question, the answer data is sent from the device to the server. The user's emotional state is also collected and sent to the server. For example, if the user correctly answers a basic problem on differential calculus, the next question will be a more applied problem. If the user shows a high level of excitement about learning, the system will speed up the learning progress.

[0591] Specific examples

[0592] 1. If a learner correctly answers the basic calculus problem "Find the derivative of f(x) = x^2," the next problem generated will be "Find the derivative of f(x) = x^2 e^x."

[0593] 2. If a learner makes a mistake on the basic problem of differentiation, "Find the derivative of f(x) = x^2," the next problem generated will be "Find the derivative of f(x) = x^3."

[0594] 3. If the learner is highly excited about learning, the difficulty of the next question will increase.

[0595] Prompt Sentence Examples

[0596] "If a student correctly answers a basic calculus problem, generate a follow-up problem. For example, if the basic problem was 'Find the derivative of f(x) = x^2,' generate the next problem as 'Find the derivative of f(x) = x^2 e^x.'"

[0597] "If a student makes a mistake on a basic calculus problem, generate another basic problem in the same area. For example, if the basic problem was 'Find the derivative of f(x) = x^2,' generate the next problem as 'Find the derivative of f(x) = x^3.'"

[0598] "If the learner shows high levels of excitement about the lesson, increase the difficulty of the next problem. For example, if the basic problem was 'Find the derivative of f(x) = x^2,' generate the next problem as 'Find the derivative of f(x) = x^2 e^x.'"

[0599] In this way, a system is provided that can dynamically adjust learning content based on the learner's level of understanding and emotional state.

[0600] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0601] Step 1:

[0602] Collecting learner response data

[0603] Subject: Terminal

[0604] The terminal provides an interface for the learner to answer questions. Specifically, the terminal uses an application that runs on a web browser to display questions to the learner and prompts them to enter their answers. When the learner enters their answer, the answer data is saved on the terminal. The input data is the learner's answer, and the output data is the answer data sent to the server. For example, if a learner answers "2x" to the question "Find the derivative of f(x) = x^2," the answer data is sent to the server.

[0605] Step 2:

[0606] Evaluation of response data

[0607] Subject: Server

[0608] The server receives the response data sent from the device and analyzes it. Specifically, the server uses Python to execute an algorithm that evaluates the correctness of the learner's response and the time it took to answer. The input data is the learner's response data, and the output data is the evaluation result. For example, the server checks whether the answer "2x" is correct and also records the time it took to answer. This evaluation result becomes the basic data for generating the next question.

[0609] Step 3:

[0610] Generate the next problem

[0611] Subject: Server

[0612] The server uses the generative AI model to generate the next problem based on the evaluation results. The server inputs the evaluation results as a prompt into the generative AI model to generate a new problem. The input data are the evaluation results and the prompt, and the output data is the generated new problem. For example, if a learner correctly answers a basic differentiation problem, the server next generates an applied problem. Specifically, the server inputs the prompt, "Since the learner correctly answered 'Find the derivative of f(x) = x^2,' please generate the next applied problem," into the generative AI model.

[0613] Step 4:

[0614] Emotion data collection and evaluation

[0615] Subject: Terminal

[0616] The device connects to the emotion engine using a camera and microphone to collect emotional data from the learner. While the learner is answering questions, the device analyzes the learner's facial expressions and tone of voice to collect emotional data. The input data is the learner's facial expressions and tone of voice, and the output data is the emotional evaluation result by the emotion engine. For example, if the learner shows high excitement in response to a question, that data is sent to the server.

[0617] Step 5:

[0618] Adjusting learning progress

[0619] Subject: Server

[0620] The server receives the emotional data and analyzes it. Specifically, the server evaluates the learner's excitement and stress level based on the data provided by the emotion engine. The input data is the emotional evaluation result, and the output data is the adjusted learning progress. The learning progress is adjusted based on the evaluation result. For example, if the learner shows high excitement, the server increases the difficulty of the next question. Conversely, if the learner shows low excitement, the learning progress is slowed down.

[0621] Step 6:

[0622] Present the next question

[0623] Subject: Terminal

[0624] The terminal presents the learner with new problems sent from the server. Specifically, the terminal displays the new problems on a web browser, allowing the learner to answer them again. The input data is the new problem sent from the server, and the output data is the problem presented to the learner. For example, when the server sends a new problem such as "Find the derivative of f(x) = x^2 e^x," the terminal displays it to the learner.

[0625] (Application example 2)

[0626] Next, a description will be given of Application Example 2 of Form 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."

[0627] While conventional learning tools have the ability to generate questions based on the learner's level of understanding, they have the problem of not being able to generate appropriate work instructions that take into account the worker's skill level and emotional state. Furthermore, they lack the ability to adjust the progress of work according to the worker's emotional state, making it difficult to provide an efficient work environment.

[0628] 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.

[0629] In this invention, the server includes means for focusing learning on areas to be studied according to level, means for performing trend analysis from learning history, means for loading content to deepen understanding, means for generating questions based on the loaded content, means for accepting answers to the generated questions, means for evaluating the level of understanding based on the answers and generating new questions according to the evaluation results, means for evaluating the skill level of the worker and generating the next work instructions, and means for sensing the emotional state of the worker and adjusting the progress of the work. This makes it possible to generate appropriate work instructions according to the skill level and emotional state of the worker, providing an efficient work environment.

[0630] A "learning tool" is a system that a learner uses to acquire specific knowledge or skills.

[0631] "Means for focusing on areas that should be studied according to level" refers to means that have the function of selecting appropriate learning content and focusing on learning based on the learner's current level of understanding and skill.

[0632] "Means for trend analysis based on learning history" refers to means that have the function of analyzing a learner's past learning data and understanding learning trends and patterns.

[0633] "Means for loading content to deepen understanding" refers to means that have the function of inputting information and teaching materials necessary for learners to deepen their understanding into the system.

[0634] "Means for generating questions based on the content that has been read" refers to means that has the function of automatically generating appropriate questions for learners based on the learning content that has been input into the system.

[0635] The "means for accepting answers to questions that have been generated" refers to a means that allows the system to receive and record answers to questions that have been answered by learners.

[0636] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" refers to a means that analyzes the learner's answers, evaluates their level of understanding, and then automatically generates the next questions to be asked.

[0637] The "means for evaluating the skill level of a worker and generating the next work instructions" is a means that has the function of evaluating the current skill level of a worker and automatically generating the next work instructions to be performed based on the evaluation results.

[0638] "Means for sensing the emotional state of the worker and adjusting the progress of the work" refers to means that have the function of sensing the emotional state of the worker using sensors or cameras and adjusting the progress of the work according to that state.

[0639] The system for implementing this invention evaluates the learner's level of understanding, the worker's skill level, and the worker's emotional state, and generates appropriate questions and work instructions based on these. A specific embodiment of this system will be described below.

[0640] Hardware used

[0641] Factory robots: Robots for carrying out work instructions (e.g., general industrial robots)

[0642] Emotion recognition camera: A camera that detects the emotional state of a worker (e.g., a general emotion recognition camera)

[0643] Sensors: Sensors (e.g., wearable devices) for collecting worker data

[0644] Software used

[0645] Data analysis software: Software for analyzing the working data (e.g., Python, TensorFlow)

[0646] Emotion recognition software: Software for analyzing emotional states from facial expression data (e.g., Affectiva)

[0647] Work instruction generation software: Software for generating next work instructions based on the evaluation results (e.g., generative AI model)

[0648] Data processing and calculation

[0649] 1. Data Collection:

[0650] The server uses sensors to collect worker work data (work time, accuracy, etc.).

[0651] An emotion recognition camera is used to collect facial expression data from workers.

[0652] 2. Data Analysis:

[0653] The server uses Python and TensorFlow to analyze the collected work data and evaluate the worker's skill level.

[0654] Using Affectiva, we analyze the emotional state of workers from the collected facial expression data.

[0655] 3. Work order generation:

[0656] The server uses the generative AI model to generate the next work instructions based on the evaluation results.

[0657] To adjust the progress of work according to the emotional state of a worker.

[0658] Specific examples

[0659] For example, if a worker is assembling parts, the first-time worker will be instructed on basic assembly steps. If the worker completes the task correctly, the next instruction will be a more complex assembly procedure. Conversely, if the worker makes a mistake, the next instruction will be a different basic procedure within the same range. Also, if the worker is tired, instructions will be given to slow down the progress of the task.

[0660] Prompt Sentence Examples

[0661] Evaluate the skill level of your workers and generate the next work order. Adjust the progress based on the worker's emotional state.

[0662] Task data: {Time: 10 minutes, Accuracy: 95%}

[0663] Emotion data: {Expression: "Tired", Emotion score: 0.3}

[0664] In this way, the server can generate appropriate work instructions according to the worker's skill level and emotional state, providing an efficient work environment.

[0665] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0666] Step 1:

[0667] The server uses sensors to collect worker work data (such as work time and accuracy). The input is real-time data from the sensors, and the output is the collected work data. Specifically, the sensors monitor the worker's actions and send the data to the server.

[0668] Step 2:

[0669] The server collects facial expression data from workers using an emotion recognition camera. The input is real-time video data from the camera, and the output is the collected facial expression data. Specifically, the camera captures the worker's face and sends the video data to the server.

[0670] Step 3:

[0671] The server uses Python and TensorFlow to analyze the collected work data and evaluate the worker's skill level. The input is the collected work data, and the output is the worker's skill level evaluation result. Specifically, the server analyzes the work data and quantifies the skill level.

[0672] Step 4:

[0673] The server uses Affectiva to analyze the worker's emotional state from the collected facial expression data. The input is the collected facial expression data, and the output is the worker's emotional state evaluation result. Specifically, the server analyzes the facial expression data and quantifies the emotional state.

[0674] Step 5:

[0675] The server uses the generative AI model to generate the next work instruction based on the evaluation results. The input is the skill level evaluation result and the emotional state evaluation result, and the output is the next work instruction. Specifically, the server inputs the evaluation result into the generative AI model as a prompt sentence and generates appropriate work instructions.

[0676] Step 6:

[0677] The server adjusts the progress of the work according to the worker's emotional state. The input is the emotional state evaluation result, and the output is the adjusted progress of the work. Specifically, the server adjusts the progress speed and content of the work based on the worker's emotional state.

[0678] Step 7:

[0679] The server sends the generated work instructions and adjusted work progress to the factory robot. The input is the work instructions and work progress, and the output is instructions to the factory robot. In concrete terms, the server sends the generated instructions to the robot, and the robot operates according to those instructions.

[0680] Example 3

[0681] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0682] With conventional learning tools, it was difficult to accurately grasp a learner's progress and level of understanding and make individual adjustments. Furthermore, because the learning content was not adjusted to take into account the learner's emotional state, the learning effect was sometimes not fully realized. Furthermore, there was a lack of functionality to instruct learners to focus on specific areas when they made many mistakes in that area.

[0683] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0684] In this invention, the server includes means for acquiring the user's emotional data and adjusting the learning content based on the emotion, means for calculating and displaying the learning progress based on the learning history, and means for instructing the learner to focus on studying a specific range if the learner has made many mistakes in that range. This makes it possible to accurately grasp the learner's progress and level of understanding and make individual adjustments. Furthermore, since the learning content is adjusted taking the learner's emotional state into consideration, the effectiveness of learning is improved. Furthermore, by instructing the learner to focus on studying a specific range if the learner has made many mistakes in that range, efficient learning is possible.

[0685] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[0686] "Means for focusing on areas that should be studied according to level" is a function that allows students to prioritize specific study areas based on their current level of understanding and progress.

[0687] "Means for trend analysis from learning history" is a function that analyzes the results of what a learner has learned in the past and extracts learning trends and patterns.

[0688] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[0689] "Means for generating questions based on the content that has been read" is a function that automatically creates questions for learners to answer based on the teaching materials and information provided.

[0690] "Means for accepting answers to questions generated" is a function for inputting answers to questions answered by learners into the system and receiving them.

[0691] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the learner's answers and creating new questions based on the results.

[0692] "Means for acquiring user emotional data and adjusting learning content based on emotions" refers to a function that detects the learner's emotional state and changes or adjusts learning content based on that data.

[0693] "Means for calculating and displaying learning progress based on learning history" is a function that calculates the current learning progress based on the learner's past learning history and visually displays the results.

[0694] "A means to instruct students to focus on studying a specific area if they have made many mistakes in that area" is a function that prompts students to study that area again if they have made many mistakes in that area.

[0695] This invention relates to a learning tool that stores a learner's learning history and manages the progress of learning based on the stored learning history. It also has the function of acquiring user emotion data and adjusting the learning content based on the emotion.

[0696] Hardware and software used

[0697] This system uses the following hardware and software:

[0698] Server: A database management system (e.g., MySQL (registered trademark), PostgreSQL) is used to store learning history and calculate learning progress.

[0699] Devices: Use a web browser or mobile application to show learners their progress and focus areas.

[0700] User devices: Emotion data is captured using wearable devices (e.g., heart rate monitors, facial recognition cameras).

[0701] Program processing

[0702] Server Processing

[0703] The server receives the results of the questions answered by the learner and stores them in a database. Based on the saved learning history, it calculates the learning progress and sends it to the device. If there are many questions answered incorrectly in a specific area, it will instruct the learner to focus on that area. It also obtains the user's emotional data and adjusts the learning content based on their emotions.

[0704] Terminal handling

[0705] The device visually displays the progress of the study and the range of questions that were answered incorrectly based on the study history data obtained from the server. For example, the progress can be displayed as a graph or percentage, and if there are many questions that were answered incorrectly in a specific range, the device will prompt the user to study that range again.

[0706] User Action

[0707] Users log in to the learning tool using their device and begin studying. As they study, their progress and any questions they get wrong are automatically recorded. Users can check their learning progress through their device and know which areas they should focus on. Furthermore, emotional data is collected using the wearable device and sent to the server.

[0708] Specific examples

[0709] For example, suppose a user is studying the range of differentiation. When the user solves a differentiation problem, the results are sent to the server. The server records which problems the user got wrong and calculates the user's learning progress. The device displays the user's learning progress based on the data obtained from the server. If the user gets many problems wrong in a specific range, the device instructs the user to focus on studying that range.

[0710] Prompt Sentence Examples

[0711] "Send the results of the user's differential calculus problems to the server and save them as a learning history. Calculate the learning progress based on the saved learning history and display it on the device. Also, if the user makes many mistakes in a specific range of problems, instruct them to focus on that range. Furthermore, obtain the user's emotional data and adjust the learning content based on their emotions."

[0712] In this way, the roles of the server, terminal, and user are clarified and specific processing contents are explained, thereby making it easier to understand the operation of the system. The flow of the specific processing in the third embodiment will be explained with reference to FIG.

[0713] Step 1:

[0714] The user begins learning

[0715] The user logs in to the learning tool using a device and begins learning. Specifically, the user opens a web browser, accesses the learning tool's URL, and logs in. The user's login information (user ID and password) is required as input, and the learning tool's home screen is displayed as output.

[0716] Step 2:

[0717] The user solves the problem

[0718] The user solves problems provided by the learning tool. Specifically, a differential problem is displayed and the user inputs the answer. The input requires the displayed problem and the user's answer, and the output generates the answer.

[0719] Step 3:

[0720] The device sends the answer to the server

[0721] The terminal sends the answer results entered by the user to the server. Specifically, when the user enters an answer and clicks the "Send" button, the terminal sends the answer data to the server. The input requires the user's answer data, and the output is that the answer data is saved on the server.

[0722] Step 4:

[0723] The server stores the learning history

[0724] The server stores the received answer results in a database. Specifically, it creates a "learning history" table in the MySQL database and stores information such as the user ID, question ID, and answer results. The input requires the user's answer data, and the output generates the learning history stored in the database.

[0725] Step 5:

[0726] The server calculates the learning progress

[0727] The server calculates the learning progress based on the saved learning history. Specifically, if the user has learned the entire range of differentiation, the server calculates the progress as 100%. The learning history data is required as input, and the calculated progress is generated as output.

[0728] Step 6:

[0729] Your device will display your learning progress

[0730] The device displays the progress data retrieved from the server to the user, specifically by displaying a graph or percentage to show that progress is 100%. As input, it requires the progress data retrieved from the server, and as output, it generates a visual representation of the progress.

[0731] Step 7:

[0732] The server specifies the focus of study

[0733] Based on the learning history, if the user has made many mistakes in a specific area, the server will instruct the user to focus on that area. For example, if the user has made many mistakes in a specific chapter on differential calculus, the server will instruct the user to restudy that chapter. The input requires learning history data, and the output generates instructions on the areas to focus on.

[0734] Step 8:

[0735] The user studies the key learning areas

[0736] The user follows instructions from the server to re-study the key learning areas. Specifically, they re-study a specific chapter on differentiation and solve problems. The inputs are instructions from the server and learning materials, and the output is the results of the re-solved problems.

[0737] Step 9:

[0738] The server acquires the user's emotional data.

[0739] The server acquires the user's emotional data. Specifically, the user uses a wearable device to collect heart rate and facial expression data during learning, and sends the data to the server. The input requires emotional data from the wearable device, and the output generates emotional data stored on the server.

[0740] Step 10:

[0741] The server adjusts learning content based on emotions

[0742] The server adjusts the learning content based on the acquired emotional data. Specifically, if the user shows high excitement about a particular learning content, it will provide that learning content with emphasis. Conversely, if the user shows low excitement, it will reduce that learning content. Emotional data and learning history data are required as input, and the adjusted learning content is generated as output.

[0743] (Application example 3)

[0744] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0745] With conventional learning tools and maintenance support systems, it was difficult to adjust individual learning and work content to appropriately reflect the progress and emotional state of the learner or worker. Furthermore, there was a lack of means to effectively utilize learning and maintenance history, which led to problems such as reduced learning and work efficiency.

[0746] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for focusing on learning areas to be studied according to level, means for performing trend analysis from the learning history, means for loading content to deepen understanding, means for generating questions based on the loaded content, means for accepting answers to the generated questions, means for evaluating the level of understanding based on the answers and generating new questions according to the evaluation results, means for individually adjusting the learning content using an emotion engine, means for saving a maintenance history and managing the progress based on the history, and means for adjusting the work content based on the worker's emotions using the emotion engine. This makes it possible to adjust the individual learning content and work content to appropriately reflect the progress and emotional state of the learner or worker.

[0747] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[0748] "Means for focusing on areas that should be studied according to level" is a function that selects content to be studied and focuses on that area based on the learner's current level of understanding and progress.

[0749] "Means for analyzing trends from learning history" is a function that analyzes a learner's past learning data and extracts learning trends and patterns.

[0750] "Means for reading content to deepen understanding" is a function that provides learners with the information and materials they need to gain a deeper understanding of specific knowledge or skills.

[0751] The "means for generating questions based on the content that has been read" is a function that automatically generates questions for the learner to answer based on the learning content that has been provided.

[0752] The "means for accepting answers to questions that have been generated" is a function for inputting and accepting answers to questions that have been answered by learners.

[0753] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the answers of the learner and generating new questions based on the evaluation results.

[0754] "Means for individually adjusting learning content using an emotional engine" is a function that analyzes the learner's emotional state and individually adjusts learning content based on the results.

[0755] The "means for saving a maintenance history and managing the progress based on that history" is a function for recording the history of maintenance work and managing the progress of the work based on that record.

[0756] The "means for adjusting the work content based on the worker's emotions using an emotion engine" is a function that analyzes the worker's emotional state and adjusts the work content based on the results.

[0757] As an embodiment of the present invention, a "Smart Maintenance Assistant" system that assists in the maintenance work of factory robots will be described as an example.

[0758] System Program

[0759] The system consists of the following main components:

[0760] 1. Maintenance history management module: Saves the history of maintenance work and manages progress based on that history.

[0761] 2. Emotion engine: Analyzes the worker's emotional state and adjusts the work content based on the results.

[0762] 3. Task generation module: Generates new maintenance tasks based on the maintenance history and the analysis results of the emotion engine.

[0763] Hardware and software used

[0764] Hardware: Servers, sensors to detect worker emotions (e.g., heart rate monitors, facial recognition cameras)

[0765] Software: EmotionEngine (emotion analysis engine), MaintenanceTracker (maintenance history management software)

[0766] Data processing and calculation

[0767] 1. Maintenance history storage: The server stores records of maintenance work performed by workers in JSON format. For example, it stores data such as "Oil change completed on 2023-10-01."

[0768] 2. Calculation of progress: The server calculates the progress based on the stored maintenance history and displays it to the worker.

[0769] 3. Emotion analysis: The server uses an emotion engine to analyze the worker's emotional data (e.g., excitement level, stress level).

[0770] 4. Task coordination: The server generates and provides maintenance tasks appropriate for the worker based on the results of sentiment analysis.

[0771] Specific examples

[0772] For example, if a worker "completed an oil change on 2023-10-01," that record is saved as maintenance history. Next, if the worker's emotional data is analyzed as "excitement level: 0.8, stress level: 0.2," the server will use this data to generate a new maintenance task appropriate for the worker.

[0773] Prompt Sentence Examples

[0774] Use the following prompt for the generative AI model:

[0775] Analyze user emotional data and adjust maintenance tasks accordingly: if a user is highly agitated, prioritize complex tasks, and if a user is highly stressed, prioritize simple tasks.

[0776] In this way, it becomes possible to adjust individual learning and work content to appropriately reflect the progress and emotional state of the learner or worker.

[0777] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0778] Step 1:

[0779] The server receives records of maintenance work performed by the worker. As input, it takes the details of the maintenance work completed by the worker (e.g., "Oil change completed on 2023-10-01") and stores this in JSON format. As output, it generates the stored maintenance history data.

[0780] Step 2:

[0781] The server calculates the progress based on the stored maintenance history. As input, it reads the maintenance history data and analyzes the completion status of each task. As data processing, it compares the number of completed tasks with the total number of tasks and calculates the progress as a percentage. As output, the calculated progress is generated and displayed to the worker.

[0782] Step 3:

[0783] The server receives the worker's emotional data. As input, it receives data obtained from emotion sensors (e.g., heart rate monitors, facial recognition cameras) and sends it to the emotion engine. As data processing, the emotion engine analyzes the received data and quantifies the worker's emotional state (e.g., excitement level, stress level). As output, the analyzed emotional data is generated.

[0784] Step 4:

[0785] The server generates maintenance tasks appropriate for each worker based on the analysis results from the emotion engine. It receives the analyzed emotion data and maintenance history data as input. As data calculations, it adjusts the difficulty of the task based on the emotion data and selects the next necessary work from the maintenance history. As output, it generates an adjusted maintenance task and provides it to the worker.

[0786] Step 5:

[0787] The server notifies the worker of the generated maintenance task. As input, it receives the adjusted maintenance task and sends it to the worker's terminal. As a specific operation, it displays the task details (e.g., "The next task is filter replacement") on the worker's terminal. As output, it clearly shows the task that the worker should perform next.

[0788] In this way, the server can effectively utilize the maintenance history and emotion data to provide the most appropriate maintenance tasks to the worker.

[0789] 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.

[0790] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0791] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0792] 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.

[0793] [Second embodiment]

[0794] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0795] 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.

[0796] 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).

[0797] 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.

[0798] 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.

[0799] 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).

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] In the smart glasses 214, 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.

[0805] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0806] "Example 1"

[0807] The learning tool of the present invention allows a learner to select the range of study to be done according to their own level, and generates problems based on that range. Specifically, if a learner is studying "differential calculus" in mathematics, the learner selects a range from basic concepts to applications of differentiation according to their level, and generates problems based on that range.

[0808] "Example 2"

[0809] The learning tool of the present invention evaluates the learner's level of understanding based on their answers and generates new questions based on the evaluation results. Specifically, after the learner answers the generated questions, the level of understanding is evaluated based on the accuracy of the answers and the time it took to answer, and the next question is generated based on the evaluation results. For example, if the learner correctly answers a basic question on differential calculus, the next question will be a more applied question. Conversely, if the learner makes a mistake on a basic question, another basic question within the same range will be generated.

[0810] "Example 3"

[0811] The learning tool of the present invention saves the learner's learning history and manages the learner's learning progress based on the saved learning history. Specifically, information such as which range the learner has studied and to what extent, and which questions the learner got wrong, is saved as a learning history, and the learner's learning progress is displayed based on the learning history. For example, if a learner has studied the entire range of differential calculus, the learner's learning progress is displayed as 100%. Furthermore, if the learner has made many mistakes on questions in a specific range, the learner is instructed to focus on studying that range.

[0812] The processing flow of each embodiment will be described below.

[0813] "Example 1"

[0814] Step 1: Learners choose the range of material they should study based on their own level. For example, if a learner is studying "differential calculus" in mathematics, they should choose a range of material from the basic concepts of differentiation to its applications based on their level.

[0815] Step 2: Generate problems based on the selected range. For example, if a learner selects the basic concept of differentiation, generate basic differentiation problems based on that range.

[0816] "Example 2"

[0817] Step 1: The learner answers the generated questions.

[0818] Step 2: Evaluate the learner's level of understanding based on the accuracy of their answers and the time it took to complete them.

[0819] Step 3: Generate the next question based on the evaluation results. For example, if the learner correctly answers a basic problem on differentiation, the next question will be a more applied problem. Conversely, if the learner makes a mistake on a basic problem, another basic problem in the same area will be generated.

[0820] "Example 3"

[0821] Step 1: Save information such as what areas the learner has studied, how much they have studied, and which questions they got wrong as a learning history.

[0822] Step 2: Display the learning progress based on the saved learning history. For example,

[0823] When you have completed the entire range of minutes, your learning progress will be displayed as 100%.

[0824] Step 3: If the student makes many mistakes in a particular area, instruct them to focus on that area.

[0825] Example 1

[0826] Next, a description will be given of Example 1 of Form 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."

[0827] With conventional learning tools, it was difficult to select an appropriate learning area according to the learner's level or to generate individually tailored questions. Furthermore, effective learning progress management based on learning history and learning trends was not sufficiently implemented. This made it difficult for learners to progress efficiently and hindered improvement in comprehension.

[0828] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for focusing on learning areas to be studied according to level, a means for performing trend analysis from the learning history, a means for loading content to deepen understanding, a means for generating questions based on prompt sentences using a generative AI model, a means for accepting answers to the generated questions, and a means for evaluating the level of understanding based on the answers and generating questions again according to the evaluation results. This makes it possible to select an appropriate learning area according to the learner's level and generate individually tailored questions, thereby realizing effective learning progress management based on the learning history and learning trends.

[0829] A "learning tool" is a device or software that a learner uses to acquire specific knowledge or skills.

[0830] "Level" is an indicator of a learner's level of knowledge and skill proficiency.

[0831] A "study scope" is the range of specific content or topics that a learner should study.

[0832] "Means for focused learning" are methods or functions that allow learners to concentrate on a specific learning area and progress with their studies.

[0833] "Learning history" is data that records what a learner has learned in the past and their progress.

[0834] "Trend analysis" refers to analyzing a learner's learning patterns and progress based on their learning history.

[0835] "Deepening content" is information or material provided to help learners gain a deeper understanding of a particular topic.

[0836] A "generative AI model" is a model that uses artificial intelligence to perform a specific task (in this case, problem generation).

[0837] A "prompt" is text that gives specific instructions or questions to a generative AI model.

[0838] A "means for generating problems" is a method or function for automatically creating problems for learners to solve.

[0839] "Means for accepting answers" refers to the method or function by which the system receives the answers given by the learner.

[0840] "Means for assessing comprehension" refers to methods or functions for measuring the learner's comprehension based on their answers.

[0841] The "means for generating questions again based on the evaluation results" refers to a method or function for creating new questions based on the results of the evaluation of the level of understanding.

[0842] The present invention relates to a learning tool that allows a learner to select a learning range according to his or her own level and generates questions based on that range. A specific embodiment of this system will be described below.

[0843] System configuration

[0844] This system consists of three main components: a server, a terminal, and a user. The server selects the study area, generates prompts, generates questions, displays the questions, accepts answers, and evaluates comprehension. The terminal provides an interface for the user to select the study area and answer the generated questions. The user selects the study area and solves the questions through the terminal.

[0845] Hardware and software used

[0846] The server generates questions using a generative AI model, such as OpenAI's GPT-4, while the device uses a standard web browser or mobile application to provide an interface for users to select the learning area and answer questions.

[0847] Data processing and calculation

[0848] The server generates a prompt based on the learning content selected by the user and sends the prompt to the generative AI model. The generative AI model generates an appropriate question based on the prompt and returns the result to the server. The server then sends the generated question to the device and displays it to the user. When the user answers the question, the device sends the answer to the server, and the server evaluates the user's level of understanding based on the answer.

[0849] Specific examples

[0850] For example, if the user selects "Fundamental Concepts of Differentiation," the server sends the following prompt to the generative AI model:

[0851] Example prompt sentence:

[0852] "Generate problems that address the fundamental concepts of differentiation. The problems should be beginner-level and focus on the definition of differentiation and basic calculation methods."

[0853] Based on this prompt, the generative AI model generates the following questions:

[0854] "Find the derivative of the following function \( f(x) = x^2 \)."

[0855] The server receives the problem and sends it to the terminal. The terminal displays the problem to the user, who solves it. When the user enters the answer, the terminal sends the answer to the server, and the server evaluates the user's understanding based on the answer.

[0856] The above is a specific embodiment for carrying out the present invention. This system allows learners to select an appropriate learning area according to their own level and solve problems that are individually tailored to them. This is expected to improve the learner's level of understanding.

[0857] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0858] Step 1: Select your study area

[0859] The user selects the learning topic using the terminal. For example, if the user wants to learn "differential calculus" in mathematics, the user selects "differential calculus" through the terminal interface.

[0860] Input: User-selected learning area (e.g., "Differential")

[0861] Output: Information about the selected study area

[0862] Specific operation: The user selects "differentiation" from the drop-down menu displayed on the terminal screen, and the terminal sends the selection information to the server.

[0863] Step 2: Generate a prompt statement

[0864] The server generates a prompt based on the received learning scope. For example, if the user selects "Basic concepts of differentiation," the server generates the prompt "Please generate problems related to the basic concepts of differentiation. The problems should be aimed at beginners and focus on the definition of differentiation and basic calculation methods."

[0865] Input: Information about the selected study area

[0866] Output: Generated prompt statement

[0867] Specific operation: The server analyzes the information in the selected learning area and generates an appropriate prompt sentence.

[0868] Step 3: Generate the problem

[0869] The server sends the generated prompt to the generative AI model, which generates an appropriate question based on the prompt and returns the result to the server.

[0870] Input: Generated prompt text

[0871] Output: Generated problem

[0872] Specific operation: The server sends a prompt to the generative AI model, which then analyzes the prompt and generates a problem. For example, it generates a problem such as, "Find the derivative of the following function \( f(x) = x^2 \)."

[0873] Step 4: View the problem

[0874] The server receives the generated questions and sends them to the terminal, which displays them to the user.

[0875] Input: Generated question

[0876] Output: The problem as seen by the user

[0877] Specific operation: The server sends the generated problem to the terminal, which displays it to the user, who then solves it.

[0878] Step 5: Accepting responses

[0879] The user solves the problem and enters the answer into the terminal, which then sends the answer to the server.

[0880] Input: User's answer

[0881] Output: The answer sent to the server

[0882] Specific operation: The user enters the answer in the input field of the terminal and presses the send button. The terminal then sends the answer to the server.

[0883] Step 6: Assess understanding

[0884] The server evaluates the user's level of understanding based on the received answers, and generates new questions based on the evaluation results.

[0885] Input: User's answer

[0886] Output: Comprehension assessment results and new questions

[0887] Specific operation: The server analyzes the user's answers and evaluates their level of understanding. Based on the evaluation results, it generates new prompts and sends them to the generative AI model again to generate new questions.

[0888] The above is the specific processing flow of the program of this system.

[0889] (Application example 1)

[0890] Next, a description will be given of Application Example 1 of Form 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."

[0891] Conventional learning tools are inadequate in generating questions and adjusting learning content according to the learner's level, and there is a lack of means for factory workers in particular to efficiently learn robot operation and maintenance skills. Furthermore, there is an issue that the generated questions and explanations are not appropriately adjusted according to the learner's level of understanding, resulting in a decrease in learning effectiveness.

[0892] 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.

[0893] In this invention, the server includes: means for focusing learning on areas to be learned according to level; means for performing trend analysis from learning history; means for loading content to deepen understanding; means for generating questions based on the loaded content; means for accepting answers to the generated questions; means for evaluating the level of understanding based on the answers and generating new questions according to the evaluation results; means for factory workers to learn robot operation and maintenance skills; means for generating questions related to robot operation and maintenance according to the learner's level; means for generating detailed explanations using a generative AI model; and means for displaying the generated explanations. This enables appropriate question generation and explanations according to the learner's level, making it possible for factory workers in particular to efficiently learn robot operation and maintenance skills.

[0894] "Means for focusing on learning areas that should be studied according to level" refers to a means for selecting content to be studied based on the learner's current knowledge and skill level, and for focusing on learning that content.

[0895] "Means for analyzing trends from learning history" refers to a means for analyzing a learner's past learning history and understanding learning trends and patterns.

[0896] "Means for loading content to deepen understanding" refers to a means for learners to input the content they wish to learn into the system and proceed with their learning based on that content.

[0897] The "means for generating questions based on the content that has been read" refers to a means for automatically generating appropriate questions based on the learning content that the learner has input.

[0898] The "means for accepting answers to questions that have been generated" refers to the means by which the system accepts answers to questions that have been answered by learners.

[0899] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" refers to a means for evaluating the answers of the learner and generating new questions based on the evaluation results.

[0900] "Means for factory workers to learn robot operation and maintenance skills" refers to means for factory workers to learn knowledge and skills related to robot operation and maintenance.

[0901] The "means for generating problems relating to the operation and maintenance of a robot according to the level of the learner" refers to a means for automatically generating problems relating to the operation and maintenance of a robot according to the skill level of the learner.

[0902] "Means for generating detailed explanations using a generative AI model" refers to means for automatically generating detailed explanations that are easy for learners to understand, using a generative AI model.

[0903] "Means for displaying the generated explanation" refers to means for displaying the explanation generated by the generative AI model to the learner.

[0904] A system for implementing this invention is a learning tool for factory workers to learn robot operation and maintenance skills. This system selects an appropriate learning area based on the learner's level, generates questions based on that area, and provides detailed explanations using a generative AI model.

[0905] System configuration

[0906] 1. Hardware:

[0907] Factory robots

[0908] PC or tablet

[0909] server

[0910] 2. Software:

[0911] Python

[0912] Generative AI models (e.g., GPT-3)

[0913] Database Management Systems

[0914] Program processing explanation

[0915] The server selects a learning area based on the learner's level and generates questions based on that area. Specifically, when a learner selects one of the levels "beginner," "intermediate," or "advanced," questions related to robot operation and maintenance appropriate for that level are generated.

[0916] The generated questions are displayed on the learner's device (PC or tablet), and the learner enters their answers. The server accepts the learner's answers and evaluates their level of understanding. Based on the evaluation results, the server generates new appropriate questions and provides them to the learner.

[0917] Furthermore, a generative AI model is used to automatically generate detailed explanations that are easy for learners to understand, and the generated explanations are displayed on the learner's device.

[0918] Specific examples

[0919] For example, if the learner selects the "Intermediate" level, the following prompt will be generated:

[0920] Prompt: "Please explain how to calibrate the robot's sensors."

[0921] If we feed this prompt into a generative AI model, it will generate a detailed explanation like this:

[0922] To calibrate the robot's sensors, first place the robot in a stable position and perform the initial sensor setup. Then, use a calibration standard to adjust the sensor readings. Finally, save the calibration results and test them to verify accuracy.

[0923] In this way, learners can efficiently learn robot operation and maintenance skills.

[0924] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0925] Step 1:

[0926] A user logs in to the system using a terminal and selects their learning level (beginner, intermediate, or advanced). The input is the user's learning level, and the output is the information on the selected learning level. The server receives this information and proceeds to the next step.

[0927] Step 2:

[0928] The server selects the appropriate learning area based on the selected learning level. The input is the user's learning level, and the output is the selected learning area. The server retrieves the data for the corresponding learning area from the database and proceeds to the next process.

[0929] Step 3:

[0930] The server generates questions based on the selected learning scope. The input is the data from the learning scope, and the output is the generated questions. The server uses the generative AI model to generate questions appropriate for the learning scope and proceeds to the next step.

[0931] Step 4:

[0932] The server sends the generated questions to the user's terminal. The input is the generated question, and the output is the question displayed on the user's terminal. The user checks the question on the terminal and enters the answer.

[0933] Step 5:

[0934] The user inputs the answer to the question using a terminal and sends it to the server. The input is the user's answer, and the output is the answer data sent to the server. The server receives this data and proceeds to the next step.

[0935] Step 6:

[0936] The server evaluates the user's answers and determines the level of understanding. The input is the user's answer data, and the output is the evaluation result of the level of understanding. The server uses an evaluation algorithm to evaluate the user's level of understanding and proceeds to the next step.

[0937] Step 7:

[0938] The server generates new questions based on the evaluation results. The input is the evaluation result of the level of understanding, and the output is the newly generated questions. The server uses the generative AI model to generate new questions based on the evaluation results and proceeds to the next process.

[0939] Step 8:

[0940] The server generates a detailed explanation using a generative AI model. The input is a newly generated problem, and the output is a detailed explanation. The server inputs a prompt sentence into the generative AI model and generates a detailed explanation.

[0941] Step 9:

[0942] The server sends the generated detailed explanation to the user's device. The input is the detailed explanation, and the output is the explanation displayed on the user's device. The user checks the detailed explanation on the device and proceeds with their learning.

[0943] Example 2

[0944] Next, a description will be given of Example 2 of Form 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."

[0945] Conventional learning tools have difficulty generating appropriate questions based on the learner's level of understanding, which has led to problems with insufficient learning outcomes. Furthermore, they lack a mechanism for effectively utilizing the learner's response data to generate the next question, resulting in insufficient learning support tailored to each learner's individual level of understanding.

[0946] 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.

[0947] In this invention, the server includes a means for collecting learner response data, a means for evaluating the learner's level of understanding, a means for generating the next question using a generative AI model, and a means for delivering the generated question to the learner. This makes it possible to automatically generate appropriate questions according to the learner's level of understanding and provide learning support according to the learner's individual level of understanding.

[0948] A "learning tool" is a system or software that a learner uses to acquire specific knowledge or skills.

[0949] "Means for focusing on areas that should be studied according to level" is a function that selects an appropriate learning area based on the learner's current level of understanding and progress, and allows them to focus on studying that area.

[0950] "Means for analyzing trends from learning history" is a function for analyzing a learner's past learning data and extracting learning trends and patterns.

[0951] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[0952] "Means for generating questions based on the content that has been read" is a function for creating appropriate questions for learners based on the teaching materials and information provided.

[0953] The "means for accepting answers to questions generated" is a function for inputting answers to questions answered by learners into the system and recording them.

[0954] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for analyzing the learner's answer data and automatically generating the next question based on the results.

[0955] "Means for collecting learner response data" is a function for collecting data on questions answered by learners and storing it in the system.

[0956] The "means for assessing the learner's level of understanding" is a function for analyzing the learner's response data and assessing the learner's level of understanding based on the results.

[0957] "Means for generating the next question using a generative AI model" is a function that uses artificial intelligence to automatically generate the next question based on the learner's level of understanding.

[0958] The "means for delivering generated questions to learners" is a function for presenting generated questions to learners and encouraging them to answer them.

[0959] The present invention is a system that automatically generates questions according to the learner's level of understanding and effectively supports the learner's learning. A specific embodiment of this system will be described below.

[0960] System configuration

[0961] This system is mainly composed of three elements: a server, a terminal, and a user. The server collects learners' response data, evaluates their level of understanding, and generates the next question. The terminal provides an interface for learners to answer questions and sends the answer data to the server. Users answer questions through their terminals and progress through their studies.

[0962] Hardware and software used

[0963] The server is a computer with high-performance computing capabilities, implemented using a programming language such as Python, TensorFlow or PyTorch as machine learning libraries, and an advanced natural language processing model such as GPT-4 as a generative AI model.

[0964] Data processing and calculation

[0965] The server receives the learner's response data sent from the terminal and performs the following data processing and calculations.

[0966] 1. Data collection: The device collects data on the questions answered by the learner and sends it to the server. This data includes whether the answer was correct or incorrect, the time it took to answer, the type of question, etc.

[0967] 2. Data analysis: The server analyzes the received data and evaluates the learner's level of understanding. Specifically, it calculates a score based on the percentage of correct answers and the time it took to answer.

[0968] 3. Problem generation: The server generates the next problem based on the evaluation results. It uses a generative AI model (e.g., GPT-4) to generate a problem of appropriate difficulty. It uses prompts to provide instructions to the model.

[0969] 4. Question distribution: The server sends the generated questions to the terminal and presents them to the learner.

[0970] Specific examples

[0971] For example, consider a case where a user answers a basic question on differentiation. If the user correctly answers "2x" to the question "Find the derivative of f(x) = x^2," the server will evaluate the user's level of understanding as high. Next, it will generate an applied question such as "Find the derivative of f(x) = x^3 + 3x^2."

[0972] Conversely, if the user makes a mistake in a basic problem, for example, if they answer "x" to "Find the derivative of f(x) = x^2," the server will evaluate the user's level of understanding as low. It will then generate another basic problem in the same range, such as "Find the derivative of f(x) = 2x."

[0973] Prompt Sentence Examples

[0974] Examples of prompts to use with generative AI models include:

[0975] "Once students have correctly answered the basic differentiation problem, generate a more advanced problem. For example, generate a problem that asks them to find the derivative of f(x) = x^3 + 3x^2."

[0976] In this way, the server generates appropriate questions according to the learner's level of understanding and provides them to the learner via their device, allowing the learner to tackle questions that correspond to their own level of understanding, enabling effective learning.

[0977] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0978] Step 1:

[0979] Data collection

[0980] The terminal collects data on questions answered by the user. Specifically, the user answers questions displayed on the terminal, and the terminal records the answers. Input includes the user's answer, answer time, question type, etc. The terminal sends this data to the server. The output is the answer data sent to the server.

[0981] Step 2:

[0982] Data analysis

[0983] The server analyzes the response data received from the device. The input includes the user's response data. The server executes an algorithm to evaluate the learner's level of understanding based on the accuracy of the answers and the time it took to answer. Specifically, it calculates a score based on the percentage of correct answers and the time it took to answer. The output is a score that indicates the learner's level of understanding.

[0984] Step 3:

[0985] Problem generation

[0986] The server generates the next problem based on the evaluation results. The input includes a score indicating the learner's level of understanding. The server uses a generative AI model (e.g., GPT-4) to generate a problem of appropriate difficulty. Specifically, it uses prompt sentences to provide instructions to the generative AI model. The output is the generated new problem.

[0987] Step 4:

[0988] Problem distribution

[0989] The server sends the generated questions to the terminal. The input contains the new questions that have been generated. The terminal presents the received questions to the user. Specifically, the new questions are displayed on the terminal, ready for the user to answer. The output is the new questions presented to the user.

[0990] Step 5:

[0991] User Answers

[0992] The user answers new questions presented on the terminal. The input includes new questions sent from the server. The user inputs the answers to the questions and sends them to the terminal. The output is the user's new answer data.

[0993] In this way, the server generates appropriate questions according to the learner's level of understanding and provides them to the learner via their device, allowing the learner to tackle questions that correspond to their own level of understanding, enabling effective learning.

[0994] (Application example 2)

[0995] Next, a description will be given of Application Example 2 of Form 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."

[0996] Conventional learning tools are inadequate in generating questions that correspond to the learner's level of understanding, and are not particularly suited to improving the specialized skills of factory robot maintenance engineers. Furthermore, the level of understanding is not evaluated based on the correctness of the engineer's answers or the time it takes to answer, and the next questions are not generated appropriately, making efficient learning difficult. This poses the problem of delaying the improvement of engineers' skills and reducing the operational efficiency of factories.

[0997] 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.

[0998] In this invention, the server is a learning tool for people of all ages who have learning problems, and includes: means for focusing learning on areas that should be studied according to level; means for performing trend analysis from learning history; means for loading content to deepen understanding; means for generating questions based on the loaded content; means for accepting answers to the generated questions; means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results; means for generating questions for factory robot maintenance technicians to improve their maintenance procedure and troubleshooting skills; and means for evaluating the technician's level of understanding based on the accuracy of their answers and the time it took to answer them and generating the next questions. This makes it possible to generate appropriate questions according to the technician's level of understanding, thereby achieving efficient skill improvement.

[0999] A "learning tool" is a device or software that a learner uses to acquire specific knowledge or skills.

[1000] "Level" is an indicator that shows the learner's level of understanding and skill.

[1001] "Learning history" refers to data that records a learner's past learning activities and their results.

[1002] "Trend analysis" is a method of analyzing a learner's learning patterns and progress based on their learning history.

[1003] "Understanding" is an indicator of how well a learner understands specific knowledge or skills.

[1004] "Question generation" is the process of creating new questions based on the learner's level of understanding and the content of their learning.

[1005] An "answer" is a response that a learner gives to a generated question.

[1006] The "evaluation result" is the result of evaluating the level of understanding calculated based on the learner's answers.

[1007] A "factory robot" is a mechanical device used to perform automated tasks in a factory.

[1008] A "maintenance technician" is a professional who maintains and repairs factory robots and other mechanical equipment.

[1009] "Maintenance procedures" are specific procedures for maintaining and repairing factory robots and machinery.

[1010] "Troubleshooting" is the technique of diagnosing and resolving malfunctions and problems in mechanical equipment.

[1011] "Skill improvement" refers to acquiring specific knowledge and skills and improving one's abilities.

[1012] As an embodiment of the present invention, a system is described that provides a learning tool for factory robot maintenance technicians to improve their maintenance procedures and troubleshooting skills.

[1013] System Configuration

[1014] The system uses the following hardware and software:

[1015] Hardware: Smartphones, tablets, computers

[1016] Software: Python, random module (random), time measurement module (time)

[1017] Program processing

[1018] The server executes a program that includes the following means:

[1019] 1. Problem generation method: Generate problems related to maintenance procedures and troubleshooting according to the learner's level. Specifically, basic and applied problems are randomly selected.

[1020] 2. Answer acceptance means: Learners enter answers to the generated questions.

[1021] 3. Comprehension assessment method: The learner's comprehension is assessed based on the accuracy of their answers and the time it took to complete them. If the answer is correct, a more advanced question is generated, and if the answer is incorrect, a basic question is generated again.

[1022] 4. Next question generation method: Generate the next question based on the results of the comprehension assessment.

[1023] Data processing and calculation

[1024] The server performs the following data processing and calculations.

[1025] Question generation: A random module is used to randomly select questions according to the current level of understanding.

[1026] Comprehension assessment: Compare the learner's answer with the correct answer to determine whether it is correct or incorrect. Also, use the timing module to record the answer time.

[1027] Next question generation: Based on the results of the comprehension assessment, the next question is generated. If the answer is correct, an applied question is generated again, and if the answer is incorrect, a basic question is generated again.

[1028] Specific examples

[1029] For example, if a learner correctly answers the question "Please explain the basic maintenance procedure," the next question generated will be "Please explain the applied maintenance procedure."

[1030] Prompt Sentence Examples

[1031] "If the user answers the basic maintenance procedure correctly, generate a question for the next advanced maintenance procedure."

[1032] In this way, it becomes possible to generate appropriate questions according to the engineer's level of understanding, thereby enabling efficient skill improvement.

[1033] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1034] Step 1:

[1035] The server generates questions according to the learner's level. Specifically, it uses a random module to randomly select basic or applied questions.

[1036] Input: The learner's current level of understanding

[1037] Data manipulation: Select questions using a random module

[1038] Output: Selected problems

[1039] Step 2:

[1040] The terminal presents the generated questions to the learner, who then inputs answers to the questions.

[1041] Input: Question sent by server

[1042] Data processing: None

[1043] Output: Learner's answer

[1044] Step 3:

[1045] The server receives the learner's answer and judges whether it is correct or not. If the answer is correct, it generates a more advanced question, and if it is incorrect, it generates a basic question again.

[1046] Input: Learner's answers, correct answer data

[1047] Data processing: Compare the answers with the correct data to determine whether they are correct or not

[1048] Output: Correct / incorrect result

[1049] Step 4:

[1050] The server measures the time taken by the learner to answer questions and evaluates their level of understanding. The server records the answer time using a time measurement module.

[1051] Input: Learner response time

[1052] Data processing: Record answer times using the time measurement module

[1053] Output: Answer time data

[1054] Step 5:

[1055] The server generates the next question based on the results of the comprehension assessment. If the answer is correct, it generates an applied question, and if the answer is incorrect, it generates a basic question again.

[1056] Input: Correct / incorrect result, answer time data

[1057] Data processing: Use comprehension assessment algorithms to select the next question

[1058] Output: Next problem

[1059] Step 6:

[1060] The terminal presents the next question to the learner and accepts the answer again.

[1061] Input: Next question sent from the server

[1062] Data processing: None

[1063] Output: Learner's next answer

[1064] Example 3

[1065] Next, a description will be given of Example 3 of Form Example 3. 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."

[1066] With conventional learning tools, it was difficult to grasp a learner's progress and level of understanding in real time and make individual adjustments. Furthermore, there was a lack of a way to effectively utilize learning history to manage learning progress, making it difficult to accurately grasp which areas a learner had studied and to what extent. Furthermore, if a learner made many mistakes in a specific area, there was a lack of a function to instruct the learner to focus on that area. This resulted in reduced learning efficiency and made it difficult for the learner's level of understanding to improve.

[1067] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1068] In this invention, the server includes a means for a user to start learning and display the learning content, a means for the user to progress with the learning, a means for the terminal to send the learning progress to the server, a means for the server to save the learning history in a database, a means for the server to calculate the learning progress, a means for the terminal to display the learning progress, and a means for the user to end the learning. This makes it possible to grasp the learner's progress and level of understanding in real time and make individual adjustments. In addition, the learning history can be effectively utilized to manage the learning progress, allowing the learner to accurately grasp which areas and to what extent they have studied. Furthermore, if a learner makes many mistakes in a specific area, the system can instruct the learner to focus on studying that area, improving learning efficiency and the learner's level of understanding.

[1069] A "learning tool" is a device or software that a learner uses to acquire specific knowledge or skills.

[1070] "Means for focusing on areas that should be studied according to level" is a function that allows learners to concentrate on studying specific areas based on their current level of understanding and progress.

[1071] "Means for trend analysis from learning history" is a function that analyzes data on what learning a learner has done in the past and identifies learning trends and patterns.

[1072] "Means for reading content to deepen understanding" is a function that provides learners with the information and materials they need to gain a deeper understanding of specific knowledge or skills.

[1073] "Means for generating questions based on the content that has been read" is a function that automatically creates questions for learners to solve based on the teaching materials and information provided.

[1074] "Means for accepting answers to generated questions" is a function that allows the learner to input answers to the questions they have solved and receive them into the system.

[1075] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the answers of the learner and creating new questions based on the results.

[1076] The "means for the user to start learning and display the learning content" is a function for displaying the learning content on the screen when the learner starts learning.

[1077] "Means for users to advance their learning" refers to functions that provide operations and interfaces for learners to advance their learning.

[1078] The "means for the terminal to transmit the learning progress status to the server" is a function for recording the progress status of the learner and transmitting it to the server.

[1079] "Means for the server to save learning history in a database" is a function for saving a learner's progress and answer history in a database.

[1080] The "means for the server to calculate the learning progress" is a function for calculating the progress of the learner based on the saved learning history.

[1081] The "means for the terminal to display the learning progress" is a function for displaying the calculated learning progress to the learner.

[1082] The "means for the user to end learning" is a function that allows the learner to inform the system when they have finished learning.

[1083] This invention relates to a learning tool that saves a learner's learning history and manages the learner's learning progress based on that history. Specifically, this system saves information such as what areas the learner has studied and to what extent, and which questions they got wrong, as a learning history, and displays the learner's learning progress based on that learning history.

[1084] Hardware and software used

[1085] The system is implemented using the following hardware and software:

[1086] Server: A central processing unit that stores learning history and calculates learning progress. It uses SQLite as its database.

[1087] Device: A device that provides an interface for learners to progress through their learning. It displays the learning content using HTML and JavaScript.

[1088] User: The learner who is progressing through the learning.

[1089] Program processing

[1090] The server receives information about what the learner has learned and the questions they got wrong, and stores it in an SQLite database. Specifically, each time the learner progresses with their studies, information about the learning scope, progress, and questions they got wrong is sent to the server. The server stores this information in a database and manages it as a learning history.

[1091] The device provides an interface for learners to progress through their studies. When a learner begins studying, the device retrieves their study history from the server and displays their progress. For example, if a learner has covered the entire range of differential calculus, the device will display their progress as 100%. Furthermore, if a learner makes many mistakes in a particular range, the device will instruct them to focus on that range.

[1092] Users study through their devices. Each time a user progresses in their studies, their study history is updated and sent to the server, allowing users to check their own learning progress in real time.

[1093] Specific examples

[1094] As a concrete example, consider the case where a user is studying differentiation. When the user begins solving basic differentiation problems, the device sends the progress status to the server. The server saves this information in a database and manages it as a learning history. When the user has solved all the basic problems, the device displays the learning progress as 100%. Furthermore, if the user makes a mistake on a particular problem, this information is also saved and the device is instructed to focus on that area the next time they study.

[1095] Prompt Sentence Examples

[1096] An example of a prompt to input to a generative AI model is as follows:

[1097] "The user has started solving basic problems in differential calculus. Please send the progress to the server and save it in the database. If the user has solved all the basic problems, show the progress as 100%. If the user made a mistake on a particular problem, save that information and instruct them to focus on that problem the next time they study."

[1098] The flow of the identification process in the third embodiment will be described with reference to FIG.

[1099] Step 1:

[1100] The user begins learning.

[1101] The user opens a learning app on their device and selects what they want to learn (e.g., basic differential calculus problems). The device receives the user's selection and sends a request to the server to start learning. The input is the user's selection information, and the output is the request sent to the server.

[1102] Step 2:

[1103] The device will display the learning content.

[1104] The server receives the user's request and sends the learning content to the terminal. The terminal displays the received learning content. For example, it displays the problem "Find the derivative of f(x) = x^2." The input is the learning content data from the server, and the output is the display on the terminal.

[1105] Step 3:

[1106] The user progresses through the learning process.

[1107] The user solves the problem on the terminal and inputs the answer. For example, the user inputs the answer "2x." The input is the user's answer, and the output is the answer input to the terminal.

[1108] Step 4:

[1109] The device sends the learning progress to the server.

[1110] The terminal receives the user's answer and sends the information to the server using an HTTP request. The input is the user's answer data, and the output is the data sent to the server.

[1111] Step 5:

[1112] The server stores the learning history in a database.

[1113] The server stores the received answer data in an SQLite database. The stored data includes the user ID, learning scope, progress, and information on questions answered incorrectly. The input is the answer data from the device, and the output is stored in the database.

[1114] Step 6:

[1115] The server calculates the learning progress.

[1116] The server calculates the learning progress based on the stored learning history. For example, if you solve 1 out of 10 questions, your progress is 10%. The input is the learning history stored in the database, and the output is the calculated progress.

[1117] Step 7:

[1118] The device displays your learning progress.

[1119] The server sends the calculated progress to the terminal. The terminal displays the received progress to the user. For example, it displays "Learning progress: 10%". The input is the progress data from the server, and the output is the display on the terminal.

[1120] Step 8:

[1121] The user finishes learning.

[1122] The user ends the learning, and the device sends that information to the server. The server updates the learning history and prepares for the next learning. The input is the user's end operation, and the output is the sending of the end information to the server.

[1123] (Application example 3)

[1124] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1125] With conventional learning tools, it was difficult to effectively manage a learner's learning history and properly evaluate their learning progress. It was also impossible to identify areas where a learner was having particular problems and provide instructions for focused learning. Furthermore, the lack of functionality to save learning history and load it as needed sometimes led to a loss of continuity in learning. To solve these issues, a system is needed that can effectively manage learning history, properly evaluate learning progress, and provide instructions on areas where students should focus their learning.

[1126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1127] In this invention, the server includes means for saving the learning history and managing the learning progress based on the saved learning history, means for indicating the areas to be studied intensively based on the learning history, and means for saving the learning history in a file and reading it out as needed. This makes it possible to effectively manage the learner's learning history, appropriately evaluate the learning progress, and indicate the areas to be studied intensively.

[1128] "Study history" is data that records information such as what areas a learner has studied and to what extent, and which questions they got wrong.

[1129] "Progress" is an indicator that shows the learner's level of achievement in the entire range of what he or she has studied.

[1130] The "areas that should be studied intensively" refer to areas where the learner has a particular lack of understanding or makes many mistakes.

[1131] "Trend analysis" refers to analyzing a learner's learning patterns and problems based on their learning history.

[1132] "Means for getting the content to be absorbed" refers to the method of providing learners with the materials and information they need to study.

[1133] "Means of generating questions" are ways in which learners create new questions based on what they have learned.

[1134] The "means for accepting answers" refers to the method by which the learner inputs the answers to the questions into the system.

[1135] A "means of assessing comprehension" is a method for measuring the learner's comprehension based on their responses.

[1136] "Means of saving to a file" refers to a method of saving learning history and other data as a digital file.

[1137] "Means for loading when needed" refers to a method for loading saved data into the system again when needed.

[1138] As an embodiment of the present invention, a system is constructed that manages the learning history of a factory robot, evaluates the progress of the learning, and indicates the areas that should be prioritized for learning. A specific embodiment of this system is shown below.

[1139] System Configuration

[1140] The system consists of the following major components:

[1141] 1. Server:

[1142] Learning history storage means: Records the tasks performed by the robot and their success / failure.

[1143] Progress management tool: Calculate learning progress based on learning history.

[1144] Means for indicating areas of focus for learning: Identify tasks with many errors and indicate areas for focused learning.

[1145] File storage method: Save learning history to a file in JSON format and load it as needed.

[1146] 2. Terminal:

[1147] User interface: Provides an interface to display the robot's learning history and progress, and to indicate the areas of focus for learning.

[1148] 3. User:

[1149] Operational method: Check the robot's learning history and adjust the learning content as needed.

[1150] Hardware and software used

[1151] Hardware: Factory robots, servers, terminals

[1152] Software: Python, JSON, user interface (e.g. web browser)

[1153] Data processing and calculation

[1154] The server records the tasks performed by the robot and their success or failure, saving it as a learning history. Based on the saved learning history, the server calculates the learning progress and identifies tasks with a high number of errors. This makes it possible to indicate the areas that should be focused on for learning. The learning history is also saved to a file in JSON format, which can be loaded as needed.

[1155] Specific examples

[1156] For example, when a robot performs welding, painting, and assembly tasks, the server records the success or failure of each task. If welding is successful, painting is unsuccessful, and assembly is successful, the server calculates the learning progress based on this information and instructs the robot to focus on painting.

[1157] Prompt Sentence Examples

[1158] An example of a prompt sentence to input to the generative AI model is as follows:

[1159] Create a Python program to manage the robot's learning history. Record the tasks performed by the robot and their success / failure, and calculate the learning progress. Also, identify tasks with many errors and indicate the areas to focus on for learning. Save the learning history to a file in JSON format and load it as needed.

[1160] This prompt sentence can be used to ask the generative AI model to generate a program.

[1161] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1162] Step 1:

[1163] The server records the tasks performed by the robot and their success / failure. As input, it receives task data from the robot (task name, success / failure, timestamp) and saves this as learning history. The output is updated learning history data. Specifically, the server saves the received task data in JSON format.

[1164] Step 2:

[1165] The server calculates the learning progress based on the saved learning history. It uses the learning history data as input and calculates the percentage of successful tasks. The output is the calculated progress (percentage). Specifically, the server analyzes the learning history data, counts the number of successful tasks, and calculates the percentage of the total number of tasks.

[1166] Step 3:

[1167] The server indicates the areas that should be prioritized for learning based on the learning history. As input, it uses the learning history data to identify tasks with a high number of errors. The output is a list of priority learning areas. Specifically, the server analyzes the learning history data, counts the frequency of failed tasks, and lists the tasks with the highest frequency.

[1168] Step 4:

[1169] The server saves the learning history in a file in JSON format and reads it as needed. It uses the learning history data as input and writes it to a file. The output is the saved file. Specifically, the server writes the learning history data to a file in JSON format and reads the file as needed.

[1170] Step 5:

[1171] The terminal displays the robot's learning history and progress through a user interface and indicates the areas of focus for learning. As input, it receives learning history data, progress data, and key learning area data from the server. The output is information displayed on the user interface. In concrete terms, the terminal visually displays the received data and indicates the learning progress and key learning areas to the user.

[1172] Step 6:

[1173] The user checks the robot's learning history through the terminal and adjusts the learning content as necessary. The input is the information displayed on the terminal, and the decision is made based on that information. The output is the adjusted learning content. Specifically, the user operates the terminal interface and inputs instructions to adjust the robot's learning content.

[1174] 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.

[1175] "Example 1"

[1176] As one embodiment of the present invention, a learning system incorporating an emotion engine is provided. This system analyzes a user's learning history and adjusts the learning content based on the results. Specifically, the emotion engine recognizes the emotions the user expresses while learning and adjusts the learning content based on those emotions. For example, if the user feels that they are struggling with learning, the system adjusts the learning content to be easier. Also, if the user expresses high excitement about learning, the system adjusts the learning content to be more difficult.

[1177] "Example 2"

[1178] Another embodiment of the present invention provides a system for adjusting a learning progress using an emotion engine. Specifically, the system adjusts the learning progress based on the user's emotion. For example, if the user is highly excited about learning, the system accelerates the learning progress. Conversely, if the user is less excited about learning, the system slows down the learning progress.

[1179] "Example 3"

[1180] Furthermore, another embodiment of the present invention provides a system for individually tailoring learning content using an emotion engine. Specifically, the learning content is individually tailored based on the user's emotions. For example, if the user is highly excited about a particular learning content, the system will provide that learning content in a focused manner. Conversely, if the user is less excited about a particular learning content, the system will reduce that learning content.

[1181] The processing flow of each embodiment will be described below.

[1182] "Example 1"

[1183] Step 1: The user begins learning.

[1184] Step 2: The system analyzes the user's learning history.

[1185] Step 3: The emotion engine recognizes the user's emotion.

[1186] Step 4: The system adjusts its learning based on the emotions recognized by the emotion engine.

[1187] "Example 2"

[1188] Step 1: The user begins learning.

[1189] Step 2: The emotion engine recognizes the user's emotion.

[1190] Step 3: The system adjusts the learning progress based on the emotions recognized by the emotion engine.

[1191] "Example 3"

[1192] Step 1: The user begins learning.

[1193] Step 2: The emotion engine recognizes the user's emotion.

[1194] Step 3: The system personalizes learning based on the emotions recognized by the emotion engine.

[1195] Example 1

[1196] Next, a description will be given of Example 1 of Form 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."

[1197] Conventional learning tools can adjust learning content based on the learner's level and learning history, but they do not take into account the learner's emotional state, which can lead to learners feeling stressed or, conversely, losing interest because the content is too easy. Furthermore, when generating questions, only fixed questions can be provided, which means they cannot flexibly respond to learners' needs.

[1198] 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.

[1199] In this invention, the server includes means for performing trend analysis from learning history, means for loading content to deepen understanding, means for generating questions based on the loaded content, means for recognizing the user's emotions and adjusting the learning content based on those emotions, and means for automatically generating questions using a generative AI model. This makes it possible to flexibly adjust the learning content according to the learner's emotional state and generate questions that meet individual needs.

[1200] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[1201] "Means for focusing on areas that should be studied according to level" is a function that allows learners to select the content that should be studied based on their current knowledge and skill level, and focus on learning that area.

[1202] "Means for trend analysis from learning history" is a function for analyzing a learner's past learning data and understanding the progress and trends of learning.

[1203] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[1204] "Means for generating questions based on the content that has been read" is a function that automatically creates questions for learners to check their level of understanding based on the teaching materials and information provided.

[1205] "Means for accepting answers to questions generated" is a function that allows the system to receive and record answers to questions answered by learners.

[1206] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the learner's answers and generating new questions based on the results.

[1207] "Means for recognizing the user's emotions and adjusting the learning content based on those emotions" is a function for detecting the learner's emotional state and changing the learning content according to that state.

[1208] "Means for automatically generating questions using a generative AI model" refers to a function that uses an artificial intelligence model to automatically generate questions to be provided to learners.

[1209] MODE FOR CARRYING OUT THE INVENTION

[1210] This invention is a learning tool that allows learners to select a learning area according to their own level and generates questions based on that area. It also has the ability to recognize the user's emotions and adjust the learning content based on those emotions. This system operates in cooperation with the server, the terminal, and the user.

[1211] server

[1212] The server generates questions based on the learning range selected by the learner. Specifically, if a learner is studying "differential calculus" in mathematics, the server selects a range from basic concepts to applications of differentiation according to the learner's level and generates questions based on that range. The server automatically generates questions using a generative AI model (e.g., OpenAI's GPT-4). It sends the following prompt to the generative AI model:

[1213] Example prompt sentence:

[1214] "Generate math problems appropriate to the learner's level, ranging from basic concepts to applications of differentiation."

[1215] The generative AI model generates questions based on the prompt and returns the results to the server, which then receives the questions and sends them to the device.

[1216] Terminal

[1217] The device records the user's learning history and recognizes the user's emotions using an emotion engine. Specifically, the device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and identifies the user's emotions using an emotion engine (e.g., Affectiva or Microsoft Azure Emotion API). The device sends this data to a server, which uses it as information to adjust the learning content.

[1218] User

[1219] Users select the range of study they want to do based on their level. For example, if a user wants to learn the basic concepts of differential calculus, they select that range. If the user is struggling while studying, the emotion engine recognizes that emotion and the server adjusts the learning content to be easier. Also, if the user shows high levels of excitement, the server adjusts the learning content to be more difficult.

[1220] Specific examples

[1221] Example 1: Selecting a study area and generating questions

[1222] Suppose a user wants to learn "differential calculus" in mathematics and selects a range from basic concepts to applications. The server uses a generative AI model to generate problems like the one below.

[1223] Example prompt sentence:

[1224] "Generate math problems appropriate to the learner's level, ranging from basic concepts to applications of differentiation."

[1225] Example 2: Adjusting learning content using an emotion engine

[1226] If a user feels they are struggling while studying, the device's camera and microphone will analyze their facial expressions and tone of voice, and the emotion engine will recognize their emotions. The server will then receive this information and adjust the learning content to make it easier.

[1227] Example prompt sentence:

[1228] "If a user is struggling with a lesson, generate questions to adjust the learning experience to something easier."

[1229] In this way, a system is realized in which the server, terminal, and user work together to optimize learning content.

[1230] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1231] Program processing flow

[1232] Step 1: Select your study area

[1233] User

[1234] Users can select the area they want to learn through the device interface, for example, selecting the area from basic concepts to applications of "differential calculus" in mathematics.

[1235] Input: The study area selected by the user.

[1236] Output: Information about the selected study area.

[1237] Step 2: Submit your study material

[1238] Terminal

[1239] The terminal receives the user's selection and transmits that information to the server.

[1240] Input: Information about the study area selected by the user.

[1241] Output: The learning scope information sent to the server.

[1242] Step 3: Generate the problem

[1243] server

[1244] The server sends a prompt to the generative AI model based on the received learning information. An example of a prompt is as follows:

[1245] "Generate math problems appropriate to the learner's level, ranging from basic concepts to applications of differentiation."

[1246] Input: Study information, prompt.

[1247] Output: The prompt sent to the generative AI model.

[1248] Generative AI Models

[1249] The generative AI model generates questions based on the prompt sentence and returns the results to the server.

[1250] Input: Prompt statement.

[1251] Output: The generated questions.

[1252] server

[1253] The server receives the generated questions and sends them to the terminal.

[1254] Input: The generated question.

[1255] Output: The problem sent to the terminal.

[1256] Step 4: View the problem

[1257] Terminal

[1258] The terminal displays the questions received from the server to the user.

[1259] Input: The problem sent by the server.

[1260] Output: The problem as seen by the user.

[1261] Step 5: Learning progression and emotional awareness

[1262] User

[1263] The user begins solving the problem displayed on the terminal.

[1264] Input: The problem displayed.

[1265] Output: The user's answer.

[1266] Terminal

[1267] The device uses a camera and microphone to monitor the user's facial expressions and tone of voice in real time.

[1268] Input: User's facial expression data, tone of voice data.

[1269] Output: Collected emotion data.

[1270] Terminal

[1271] The device sends the collected data to an emotion engine to recognize the user's emotions.

[1272] Input: Collected emotion data.

[1273] Output: Emotion recognition results from the emotion engine.

[1274] Step 6: Sending Emotion Data

[1275] Terminal

[1276] The device receives the emotion recognition results from the emotion engine and transmits the information to the server.

[1277] Input: Emotion recognition results.

[1278] Output: Emotion recognition results sent to the server.

[1279] Step 7: Adjust your learning

[1280] server

[1281] The server adjusts the learning content based on the emotion recognition results. For example, if the user is distressed, the server sends the following prompt to the generative AI model:

[1282] "If a user is struggling with a lesson, generate questions to adjust the learning experience to something easier."

[1283] Input: Emotion recognition result, prompt sentence.

[1284] Output: The new prompt sent to the generative AI model.

[1285] Generative AI Models

[1286] The generative AI model generates questions based on the new prompt sentence and returns the results to the server.

[1287] Input: New prompt statement.

[1288] Output: The new problem that was generated.

[1289] server

[1290] The server receives new questions and sends them to the terminal.

[1291] Input: The new problem that is generated.

[1292] Output: The new problem sent to the terminal.

[1293] Step 8: View the new issue

[1294] Terminal

[1295] The terminal displays the new problem to the user.

[1296] Input: New problem sent from the server.

[1297] Output: The new issue displayed to the user.

[1298] In this way, a system is realized in which the server, terminal, and user work together to optimize learning content.

[1299] (Application example 1)

[1300] Next, a description will be given of Application Example 1 of Form 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."

[1301] Conventional learning tools and training systems have difficulty responding flexibly to the user's skill level and emotional state, which means that they are unable to maximize the effectiveness of learning and training. In addition, providing uniform content without considering the user's emotions can reduce motivation to learn or train.

[1302] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for focusing on learning areas that should be studied according to level, a means for performing trend analysis from learning history, and a means for loading content to deepen understanding. This enables flexible learning and training according to the user's skill level and emotional state.

[1303] "A means of focusing on areas that should be studied according to level" is a function that selects study content according to the user's skill level and allows them to concentrate on studying those areas.

[1304] "Means for trend analysis from learning history" is a function that analyzes a user's past learning data and grasps their learning progress and trends.

[1305] "Means for loading content to deepen understanding" is a function that allows users to import learning materials and resources into the system and provide them to users.

[1306] "Means for generating questions based on the content that has been loaded" is a function that automatically creates questions for the user to solve based on the teaching materials and documents that have been loaded.

[1307] "Means for accepting answers to questions generated" is a function that allows the system to receive and record answers to questions answered by users.

[1308] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the user's answers and creating new questions based on the evaluation results.

[1309] "Means for recognizing the user's emotions and adjusting the learning content based on those emotions" refers to a function that detects the user's emotional state and changes the difficulty and type of learning content according to those emotions.

[1310] "Means for providing training content according to the skill level of the operator" refers to a function for selecting and providing appropriate training content according to the technical level of the operator.

[1311] The "means for adjusting training content based on emotions" is a function for detecting the emotional state of the operator and changing the difficulty and type of training content according to that emotion.

[1312] The system for implementing the present invention can flexibly adjust learning and training content according to the user's skill level and emotional state. Specific embodiments are described below.

[1313] System Configuration

[1314] The system consists of the following main components:

[1315] 1. User device: PC or tablet used by learners and operators.

[1316] 2. Server: Manages learning and training content and adjusts it based on the user's skill level and emotional state.

[1317] 3. Cameras and sensors for emotion recognition: Hardware for detecting the user's emotional state.

[1318] Software used

[1319] 1. Python program: A program for generating and adjusting learning and training content.

[1320] 2. Emotion Engine (EmotionEngine class): Software for analyzing and recognizing user emotions.

[1321] 3. Training System (TrainingSystem class): Software that provides training content tailored to the user's skill level and adjusts based on emotions.

[1322] Data processing and calculation

[1323] The server performs the following data processing and calculations:

[1324] 1. Emotion Recognition: The emotion engine analyzes user input and camera footage to recognize emotions.

[1325] 2. Learning content generation: Generate appropriate learning and training content based on the user's skill level.

[1326] 3. Content Adjustment: Adjust the difficulty and type of learning or training content based on perceived emotions.

[1327] Specific examples

[1328] For example, if an operator is set as "Intermediate," the system will provide "Intermediate Operation Training." If the operator shows "Frustration," the system will easily adjust the training content.

[1329] Prompt Sentence Examples

[1330] Below are some example prompts to input to the generative AI model:

[1331] Write a Python program that generates training content based on the user's skill level and adjusts it based on their emotions. The emotion engine analyzes user input and recognizes emotions. The training system generates training content based on the operator's skill level and adjusts it based on their emotions.

[1332] In this way, flexible learning and training can be achieved according to the user's skill level and emotional state.

[1333] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1334] Step 1:

[1335] The user's terminal inputs the user's skill level. The input skill level is sent to the server. The server processes the data to select appropriate learning and training content based on the skill level.

[1336] Step 2:

[1337] The server receives data from emotion recognition cameras and sensors. The emotion engine analyzes this data and recognizes the user's emotional state. The recognized emotional state is sent to the server, which performs data calculations to adjust learning and training content based on this emotional state.

[1338] Step 3:

[1339] The server generates appropriate learning and training content based on the user's skill level and emotional state, and sends the generated content to the user's device, which then displays it to the user.

[1340] Step 4:

[1341] The user terminal accepts the user's answers. The accepted answers are sent to the server, which processes the data to evaluate the user's level of understanding based on the answers.

[1342] Step 5:

[1343] The server generates new questions based on the evaluation results, and sends the generated questions to the user's terminal, which then displays the questions to the user.

[1344] Step 6:

[1345] The server stores the user's learning history, which is used to generate and tailor future learning and training content.

[1346] Step 7:

[1347] The server adjusts the learning and training content based on the user's emotional state, and sends the adjusted content to the user's device, which then displays it to the user.

[1348] The above steps enable flexible learning and training according to the user's skill level and emotional state.

[1349] Example 2

[1350] Next, a description will be given of Example 2 of Form 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."

[1351] With conventional learning tools, it was difficult to properly evaluate a learner's level of understanding and learning progress and adjust the next learning content based on that. Furthermore, because the learning progress was not adjusted taking into account the learner's emotional state, it was difficult to maintain the learner's motivation. Furthermore, because question generation was not automated using a generative AI model, it was not possible to provide a personalized learning experience.

[1352] 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.

[1353] In this invention, the server includes a means for performing trend analysis from learning history, a means for loading content to deepen understanding, and a means for generating questions based on the loaded content. This makes it possible to appropriately evaluate the learner's level of understanding and generate the next question based on that assessment. The server also includes a means for collecting user emotional data and adjusting the learning progress, a means for generating the next question using a generative AI model, and a means for generating prompt sentences and inputting them into the generative AI model. This makes it possible to adjust the learning progress taking into account the learner's emotional state, providing a personalized learning experience.

[1354] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[1355] "Means for focusing on learning areas that should be studied according to level" is a function that selects and focuses on content to be studied based on the learner's current level of understanding and skill.

[1356] "Means for trend analysis from learning history" is a function that analyzes a learner's past learning data and grasps the progress of their learning and trends in their level of understanding.

[1357] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[1358] "Means for generating questions based on the content that has been loaded" is a function for automatically creating new study questions based on the teaching materials and information provided.

[1359] The "means for accepting answers to questions that have been generated" is a function that allows a learner to input answers to questions that have been answered and send them to the system.

[1360] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for analyzing the learner's answers, evaluating their level of understanding, and then generating the next learning question.

[1361] "Means for collecting user emotional data and adjusting the learning progress" refers to a function for analyzing the learner's emotional state and adjusting the learning progress speed and difficulty based on that.

[1362] "Means for generating the next question using a generative AI model" is a function that uses an artificial intelligence model to automatically generate new learning questions based on the learner's level of understanding and learning history.

[1363] "Means for generating prompt sentences and inputting them into a generative AI model" refers to a function for creating text to provide appropriate instructions to a generative AI model and inputting it into the model.

[1364] This invention relates to a learning tool that evaluates a learner's level of understanding and adjusts the next learning content based on that evaluation. Specifically, it provides a system in which the elements of a server, a terminal, and a user work together.

[1365] Server Roles

[1366] The server receives the learner's response data and analyzes it. Specifically, the server uses Python to run an algorithm that evaluates the accuracy of the learner's response and the time it took to complete it. Based on the evaluation results, the server uses a generative AI model (e.g., a general-purpose artificial intelligence model) to generate the next problem. If the learner correctly answers a basic calculus problem, the server generates an applied problem as the next problem. Conversely, if the learner makes a mistake on a basic problem, the server generates another basic problem in the same area.

[1367] Device Role

[1368] The device provides an interface for the learner to answer questions. Specifically, the device uses an application that runs on a web browser to display questions to the learner and prompts them to enter their answers. The device then sends the learner's answer data to a server. The device also uses a camera and microphone to connect to an emotion engine (e.g., emotion analysis software) to collect the learner's emotional data.

[1369] User Roles

[1370] The user answers questions displayed on the device. When the user answers a question, the answer data is sent from the device to the server. The user's emotional state is also collected and sent to the server. For example, if the user correctly answers a basic problem on differential calculus, the next question will be a more applied problem. If the user shows a high level of excitement about learning, the system will speed up the learning progress.

[1371] Specific examples

[1372] 1. If a learner correctly answers the basic calculus problem "Find the derivative of f(x) = x^2," the next problem generated will be "Find the derivative of f(x) = x^2 e^x."

[1373] 2. If a learner makes a mistake on the basic problem of differentiation, "Find the derivative of f(x) = x^2," the next problem generated will be "Find the derivative of f(x) = x^3."

[1374] 3. If the learner is highly excited about learning, the difficulty of the next question will increase.

[1375] Prompt Sentence Examples

[1376] "If a student correctly answers a basic calculus problem, generate a follow-up problem. For example, if the basic problem was 'Find the derivative of f(x) = x^2,' generate the next problem as 'Find the derivative of f(x) = x^2 e^x.'"

[1377] "If a student makes a mistake on a basic calculus problem, generate another basic problem in the same area. For example, if the basic problem was 'Find the derivative of f(x) = x^2,' generate the next problem as 'Find the derivative of f(x) = x^3.'"

[1378] "If the learner shows high levels of excitement about the lesson, increase the difficulty of the next problem. For example, if the basic problem was 'Find the derivative of f(x) = x^2,' generate the next problem as 'Find the derivative of f(x) = x^2 e^x.'"

[1379] In this way, a system is provided that can dynamically adjust learning content based on the learner's level of understanding and emotional state.

[1380] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1381] Step 1:

[1382] Collecting learner response data

[1383] Subject: Terminal

[1384] The terminal provides an interface for the learner to answer questions. Specifically, the terminal uses an application that runs on a web browser to display questions to the learner and prompts them to enter their answers. When the learner enters their answer, the answer data is saved on the terminal. The input data is the learner's answer, and the output data is the answer data sent to the server. For example, if a learner answers "2x" to the question "Find the derivative of f(x) = x^2," the answer data is sent to the server.

[1385] Step 2:

[1386] Evaluation of response data

[1387] Subject: Server

[1388] The server receives the response data sent from the device and analyzes it. Specifically, the server uses Python to execute an algorithm that evaluates the correctness of the learner's response and the time it took to answer. The input data is the learner's response data, and the output data is the evaluation result. For example, the server checks whether the answer "2x" is correct and also records the time it took to answer. This evaluation result becomes the basic data for generating the next question.

[1389] Step 3:

[1390] Generate the next problem

[1391] Subject: Server

[1392] The server uses the generative AI model to generate the next problem based on the evaluation results. The server inputs the evaluation results as a prompt into the generative AI model to generate a new problem. The input data are the evaluation results and the prompt, and the output data is the generated new problem. For example, if a learner correctly answers a basic differentiation problem, the server next generates an applied problem. Specifically, the server inputs the prompt, "Since the learner correctly answered 'Find the derivative of f(x) = x^2,' please generate the next applied problem," into the generative AI model.

[1393] Step 4:

[1394] Emotion data collection and evaluation

[1395] Subject: Terminal

[1396] The device connects to the emotion engine using a camera and microphone to collect emotional data from the learner. While the learner is answering questions, the device analyzes the learner's facial expressions and tone of voice to collect emotional data. The input data is the learner's facial expressions and tone of voice, and the output data is the emotional evaluation result by the emotion engine. For example, if the learner shows high excitement in response to a question, that data is sent to the server.

[1397] Step 5:

[1398] Adjusting learning progress

[1399] Subject: Server

[1400] The server receives the emotional data and analyzes it. Specifically, the server evaluates the learner's excitement and stress level based on the data provided by the emotion engine. The input data is the emotional evaluation result, and the output data is the adjusted learning progress. The learning progress is adjusted based on the evaluation result. For example, if the learner shows high excitement, the server increases the difficulty of the next question. Conversely, if the learner shows low excitement, the learning progress is slowed down.

[1401] Step 6:

[1402] Present the next question

[1403] Subject: Terminal

[1404] The terminal presents the learner with new problems sent from the server. Specifically, the terminal displays the new problems on a web browser, allowing the learner to answer them again. The input data is the new problem sent from the server, and the output data is the problem presented to the learner. For example, when the server sends a new problem such as "Find the derivative of f(x) = x^2 e^x," the terminal displays it to the learner.

[1405] (Application example 2)

[1406] Next, a description will be given of Application Example 2 of Form 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."

[1407] While conventional learning tools have the ability to generate questions based on the learner's level of understanding, they have the problem of not being able to generate appropriate work instructions that take into account the worker's skill level and emotional state. Furthermore, they lack the ability to adjust the progress of work according to the worker's emotional state, making it difficult to provide an efficient work environment.

[1408] 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.

[1409] In this invention, the server includes means for focusing learning on areas to be studied according to level, means for performing trend analysis from learning history, means for loading content to deepen understanding, means for generating questions based on the loaded content, means for accepting answers to the generated questions, means for evaluating the level of understanding based on the answers and generating new questions according to the evaluation results, means for evaluating the skill level of the worker and generating the next work instructions, and means for sensing the emotional state of the worker and adjusting the progress of the work. This makes it possible to generate appropriate work instructions according to the skill level and emotional state of the worker, providing an efficient work environment.

[1410] A "learning tool" is a system that a learner uses to acquire specific knowledge or skills.

[1411] "Means for focusing on areas that should be studied according to level" refers to means that have the function of selecting appropriate learning content and focusing on learning based on the learner's current level of understanding and skill.

[1412] "Means for trend analysis based on learning history" refers to means that have the function of analyzing a learner's past learning data and understanding learning trends and patterns.

[1413] "Means for loading content to deepen understanding" refers to means that have the function of inputting information and teaching materials necessary for learners to deepen their understanding into the system.

[1414] "Means for generating questions based on the content that has been read" refers to means that has the function of automatically generating appropriate questions for learners based on the learning content that has been input into the system.

[1415] The "means for accepting answers to questions that have been generated" refers to a means that allows the system to receive and record answers to questions that have been answered by learners.

[1416] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" refers to a means that analyzes the learner's answers, evaluates their level of understanding, and then automatically generates the next questions to be asked.

[1417] The "means for evaluating the skill level of a worker and generating the next work instructions" is a means that has the function of evaluating the current skill level of a worker and automatically generating the next work instructions to be performed based on the evaluation results.

[1418] "Means for sensing the emotional state of the worker and adjusting the progress of the work" refers to means that have the function of sensing the emotional state of the worker using sensors or cameras and adjusting the progress of the work according to that state.

[1419] The system for implementing this invention evaluates the learner's level of understanding, the worker's skill level, and the worker's emotional state, and generates appropriate questions and work instructions based on these. A specific embodiment of this system will be described below.

[1420] Hardware used

[1421] Factory robots: Robots for carrying out work instructions (e.g., general industrial robots)

[1422] Emotion recognition camera: A camera that detects the emotional state of a worker (e.g., a general emotion recognition camera)

[1423] Sensors: Sensors (e.g., wearable devices) for collecting worker data

[1424] Software used

[1425] Data analysis software: Software for analyzing the working data (e.g., Python, TensorFlow)

[1426] Emotion recognition software: Software for analyzing emotional states from facial expression data (e.g., Affectiva)

[1427] Work instruction generation software: Software for generating next work instructions based on the evaluation results (e.g., generative AI model)

[1428] Data processing and calculation

[1429] 1. Data Collection:

[1430] The server uses sensors to collect worker work data (work time, accuracy, etc.).

[1431] An emotion recognition camera is used to collect facial expression data from workers.

[1432] 2. Data Analysis:

[1433] The server uses Python and TensorFlow to analyze the collected work data and evaluate the worker's skill level.

[1434] Using Affectiva, we analyze the emotional state of workers from the collected facial expression data.

[1435] 3. Work order generation:

[1436] The server uses the generative AI model to generate the next work instructions based on the evaluation results.

[1437] To adjust the progress of work according to the emotional state of a worker.

[1438] Specific examples

[1439] For example, if a worker is assembling parts, the first-time worker will be instructed on basic assembly steps. If the worker completes the task correctly, the next instruction will be a more complex assembly procedure. Conversely, if the worker makes a mistake, the next instruction will be a different basic procedure within the same range. Also, if the worker is tired, instructions will be given to slow down the progress of the task.

[1440] Prompt Sentence Examples

[1441] Evaluate the skill level of your workers and generate the next work order. Adjust the progress based on the worker's emotional state.

[1442] Task data: {Time: 10 minutes, Accuracy: 95%}

[1443] Emotion data: {Expression: "Tired", Emotion score: 0.3}

[1444] In this way, the server can generate appropriate work instructions according to the worker's skill level and emotional state, providing an efficient work environment.

[1445] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1446] Step 1:

[1447] The server uses sensors to collect worker work data (such as work time and accuracy). The input is real-time data from the sensors, and the output is the collected work data. Specifically, the sensors monitor the worker's actions and send the data to the server.

[1448] Step 2:

[1449] The server collects facial expression data from workers using an emotion recognition camera. The input is real-time video data from the camera, and the output is the collected facial expression data. Specifically, the camera captures the worker's face and sends the video data to the server.

[1450] Step 3:

[1451] The server uses Python and TensorFlow to analyze the collected work data and evaluate the worker's skill level. The input is the collected work data, and the output is the worker's skill level evaluation result. Specifically, the server analyzes the work data and quantifies the skill level.

[1452] Step 4:

[1453] The server uses Affectiva to analyze the worker's emotional state from the collected facial expression data. The input is the collected facial expression data, and the output is the worker's emotional state evaluation result. Specifically, the server analyzes the facial expression data and quantifies the emotional state.

[1454] Step 5:

[1455] The server uses the generative AI model to generate the next work instruction based on the evaluation results. The input is the skill level evaluation result and the emotional state evaluation result, and the output is the next work instruction. Specifically, the server inputs the evaluation result into the generative AI model as a prompt sentence and generates appropriate work instructions.

[1456] Step 6:

[1457] The server adjusts the progress of the work according to the worker's emotional state. The input is the emotional state evaluation result, and the output is the adjusted progress of the work. Specifically, the server adjusts the progress speed and content of the work based on the worker's emotional state.

[1458] Step 7:

[1459] The server sends the generated work instructions and adjusted work progress to the factory robot. The input is the work instructions and work progress, and the output is instructions to the factory robot. In concrete terms, the server sends the generated instructions to the robot, and the robot operates according to those instructions.

[1460] Example 3

[1461] Next, a description will be given of Example 3 of Form Example 3. 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."

[1462] With conventional learning tools, it was difficult to accurately grasp a learner's progress and level of understanding and make individual adjustments. Furthermore, because the learning content was not adjusted to take into account the learner's emotional state, the learning effect was sometimes not fully realized. Furthermore, there was a lack of functionality to instruct learners to focus on specific areas when they made many mistakes in that area.

[1463] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1464] In this invention, the server includes means for acquiring the user's emotional data and adjusting the learning content based on the emotion, means for calculating and displaying the learning progress based on the learning history, and means for instructing the learner to focus on studying a specific range if the learner has made many mistakes in that range. This makes it possible to accurately grasp the learner's progress and level of understanding and make individual adjustments. Furthermore, since the learning content is adjusted taking the learner's emotional state into consideration, the effectiveness of learning is improved. Furthermore, by instructing the learner to focus on studying a specific range if the learner has made many mistakes in that range, efficient learning is possible.

[1465] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[1466] "Means for focusing on areas that should be studied according to level" is a function that allows students to prioritize specific study areas based on their current level of understanding and progress.

[1467] "Means for analyzing trends from learning history" is a function that analyzes the results of what a learner has learned in the past and extracts learning trends and patterns.

[1468] "Means for reading content to deepen understanding" is a function that provides learners with the learning materials and information they need to gain a deeper understanding of specific knowledge or skills.

[1469] "Means for generating questions based on the content that has been read" is a function that automatically creates questions for learners to answer based on the teaching materials and information provided.

[1470] "Means for accepting answers to questions generated" is a function for inputting answers to questions answered by learners into the system and receiving them.

[1471] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the learner's answers and creating new questions based on the results.

[1472] "Means for acquiring user emotional data and adjusting learning content based on emotions" refers to a function that detects the learner's emotional state and changes or adjusts learning content based on that data.

[1473] "Means for calculating and displaying learning progress based on learning history" is a function that calculates the current learning progress based on the learner's past learning history and visually displays the results.

[1474] "A means to instruct learners to focus on studying a specific area if they make many mistakes in that area" is a function that prompts learners to study that area again if they make many mistakes in that area.

[1475] This invention relates to a learning tool that stores a learner's learning history and manages the progress of learning based on the stored learning history. It also has the function of acquiring user emotion data and adjusting the learning content based on the emotion.

[1476] Hardware and software used

[1477] This system uses the following hardware and software:

[1478] Server: Uses a database management system (e.g., MySQL, PostgreSQL) to store learning history and calculate learning progress.

[1479] Devices: Use a web browser or mobile application to show learners their progress and focus areas.

[1480] User devices: Emotion data is captured using wearable devices (e.g., heart rate monitors, facial recognition cameras).

[1481] Program processing

[1482] Server Processing

[1483] The server receives the results of the questions answered by the learner and stores them in a database. Based on the saved learning history, it calculates the learning progress and sends it to the device. If there are many questions answered incorrectly in a specific area, it will instruct the learner to focus on that area. It also obtains the user's emotional data and adjusts the learning content based on their emotions.

[1484] Terminal handling

[1485] The device visually displays the progress of the study and the range of questions that were answered incorrectly based on the study history data obtained from the server. For example, the progress can be displayed as a graph or percentage, and if there are many questions that were answered incorrectly in a specific range, the device will prompt the user to study that range again.

[1486] User Action

[1487] Users log in to the learning tool using their device and begin studying. As they study, their progress and any questions they get wrong are automatically recorded. Users can check their learning progress through their device and know which areas they should focus on. Furthermore, emotional data is collected using the wearable device and sent to the server.

[1488] Specific examples

[1489] For example, suppose a user is studying the range of differentiation. When the user solves a differentiation problem, the results are sent to the server. The server records which problems the user got wrong and calculates the user's learning progress. The device displays the user's learning progress based on the data obtained from the server. If the user gets many problems wrong in a specific range, the device instructs the user to focus on studying that range.

[1490] Prompt Sentence Examples

[1491] "Send the results of the user's differential calculus problems to the server and save them as a learning history. Calculate the learning progress based on the saved learning history and display it on the device. Also, if the user makes many mistakes in a specific range of problems, instruct them to focus on that range. Furthermore, obtain the user's emotional data and adjust the learning content based on their emotions."

[1492] In this way, the roles of the server, terminal, and user are clarified and specific processing contents are explained, thereby making it easier to understand the operation of the system. The flow of the specific processing in the third embodiment will be explained with reference to FIG.

[1493] Step 1:

[1494] The user begins learning

[1495] The user logs in to the learning tool using a device and begins learning. Specifically, the user opens a web browser, accesses the learning tool's URL, and logs in. The user's login information (user ID and password) is required as input, and the learning tool's home screen is displayed as output.

[1496] Step 2:

[1497] The user solves the problem

[1498] The user solves problems provided by the learning tool. Specifically, a differential problem is displayed and the user inputs the answer. The input requires the displayed problem and the user's answer, and the output generates the answer.

[1499] Step 3:

[1500] The device sends the answer to the server

[1501] The terminal sends the answer results entered by the user to the server. Specifically, when the user enters an answer and clicks the "Send" button, the terminal sends the answer data to the server. The input requires the user's answer data, and the output is that the answer data is saved on the server.

[1502] Step 4:

[1503] The server stores the learning history

[1504] The server stores the received answer results in a database. Specifically, it creates a "learning history" table in the MySQL database and stores information such as the user ID, question ID, and answer results. The input requires the user's answer data, and the output generates the learning history stored in the database.

[1505] Step 5:

[1506] The server calculates the learning progress

[1507] The server calculates the learning progress based on the saved learning history. Specifically, if the user has learned the entire range of differentiation, the server calculates the progress as 100%. The learning history data is required as input, and the calculated progress is generated as output.

[1508] Step 6:

[1509] Your device will display your learning progress

[1510] The device displays the progress data retrieved from the server to the user, specifically by displaying a graph or percentage to show that progress is 100%. As input, it requires the progress data retrieved from the server, and as output, it generates a visual representation of the progress.

[1511] Step 7:

[1512] The server specifies the focus of study

[1513] Based on the learning history, if the user has made many mistakes in a specific area, the server will instruct the user to focus on that area. For example, if the user has made many mistakes in a specific chapter on differential calculus, the server will instruct the user to restudy that chapter. The input requires learning history data, and the output generates instructions on the areas to focus on.

[1514] Step 8:

[1515] The user studies the key learning areas

[1516] The user follows instructions from the server to re-study the key learning areas. Specifically, they re-study a specific chapter on differentiation and solve problems. The inputs are instructions from the server and learning materials, and the output is the results of the re-solved problems.

[1517] Step 9:

[1518] The server acquires the user's emotional data.

[1519] The server acquires the user's emotional data. Specifically, the user uses a wearable device to collect heart rate and facial expression data during learning, and sends the data to the server. The input requires emotional data from the wearable device, and the output generates emotional data stored on the server.

[1520] Step 10:

[1521] The server adjusts learning content based on emotions

[1522] The server adjusts the learning content based on the acquired emotional data. Specifically, if the user shows high excitement about a particular learning content, it will provide that learning content with emphasis. Conversely, if the user shows low excitement, it will reduce that learning content. Emotional data and learning history data are required as input, and the adjusted learning content is generated as output.

[1523] (Application example 3)

[1524] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1525] With conventional learning tools and maintenance support systems, it was difficult to adjust individual learning and work content to appropriately reflect the progress and emotional state of the learner or worker. Furthermore, there was a lack of means to effectively utilize learning and maintenance history, which led to problems such as reduced learning and work efficiency.

[1526] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for focusing on learning areas to be studied according to level, means for performing trend analysis from the learning history, means for loading content to deepen understanding, means for generating questions based on the loaded content, means for accepting answers to the generated questions, means for evaluating the level of understanding based on the answers and generating new questions according to the evaluation results, means for individually adjusting the learning content using an emotion engine, means for saving a maintenance history and managing the progress based on the history, and means for adjusting the work content based on the worker's emotions using the emotion engine. This makes it possible to adjust the individual learning content and work content to appropriately reflect the progress and emotional state of the learner or worker.

[1527] A "learning tool" is a software or hardware system that a learner uses to acquire specific knowledge or skills.

[1528] "Means for focusing on areas that should be studied according to level" is a function that selects content to be studied and focuses on that area based on the learner's current level of understanding and progress.

[1529] "Means for analyzing trends from learning history" is a function that analyzes a learner's past learning data and extracts learning trends and patterns.

[1530] "Means for reading content to deepen understanding" is a function that provides learners with the information and materials they need to gain a deeper understanding of specific knowledge or skills.

[1531] The "means for generating questions based on the content that has been read" is a function that automatically generates questions for the learner to answer based on the learning content that has been provided.

[1532] The "means for accepting answers to questions that have been generated" is a function for inputting and accepting answers to questions that have been answered by learners.

[1533] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for evaluating the answers of the learner and generating new questions based on the evaluation results.

[1534] "Means for individually adjusting learning content using an emotional engine" is a function that analyzes the learner's emotional state and individually adjusts learning content based on the results.

[1535] The "means for saving a maintenance history and managing the progress based on that history" is a function for recording the history of maintenance work and managing the progress of the work based on that record.

[1536] The "means for adjusting the work content based on the worker's emotions using an emotion engine" is a function that analyzes the worker's emotional state and adjusts the work content based on the results.

[1537] As an embodiment of the present invention, a "Smart Maintenance Assistant" system that assists in the maintenance work of factory robots will be described as an example.

[1538] System Program

[1539] The system consists of the following main components:

[1540] 1. Maintenance history management module: Saves the history of maintenance work and manages progress based on that history.

[1541] 2. Emotion engine: Analyzes the worker's emotional state and adjusts the work content based on the results.

[1542] 3. Task generation module: Generates new maintenance tasks based on the maintenance history and the analysis results of the emotion engine.

[1543] Hardware and software used

[1544] Hardware: Servers, sensors to detect worker emotions (e.g., heart rate monitors, facial recognition cameras)

[1545] Software: EmotionEngine (emotion analysis engine), MaintenanceTracker (maintenance history management software)

[1546] Data processing and calculation

[1547] 1. Maintenance history storage: The server stores records of maintenance work performed by workers in JSON format. For example, it stores data such as "Oil change completed on 2023-10-01."

[1548] 2. Calculation of progress: The server calculates the progress based on the stored maintenance history and displays it to the worker.

[1549] 3. Emotion analysis: The server uses an emotion engine to analyze the worker's emotional data (e.g., excitement level, stress level).

[1550] 4. Task coordination: The server generates and provides maintenance tasks appropriate for the worker based on the results of sentiment analysis.

[1551] Specific examples

[1552] For example, if a worker "completed an oil change on 2023-10-01," that record is saved as maintenance history. Next, if the worker's emotional data is analyzed as "excitement level: 0.8, stress level: 0.2," the server will use this data to generate a new maintenance task appropriate for the worker.

[1553] Prompt Sentence Examples

[1554] Use the following prompt for the generative AI model:

[1555] Analyze user emotional data and adjust maintenance tasks accordingly: if a user is highly agitated, prioritize complex tasks, and if a user is highly stressed, prioritize simple tasks.

[1556] In this way, it becomes possible to adjust individual learning and work content to appropriately reflect the progress and emotional state of the learner or worker.

[1557] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1558] Step 1:

[1559] The server receives records of maintenance work performed by the worker. As input, it takes the details of the maintenance work completed by the worker (e.g., "Oil change completed on 2023-10-01") and stores this in JSON format. As output, it generates the stored maintenance history data.

[1560] Step 2:

[1561] The server calculates the progress based on the stored maintenance history. As input, it reads the maintenance history data and analyzes the completion status of each task. As data processing, it compares the number of completed tasks with the total number of tasks and calculates the progress as a percentage. As output, the calculated progress is generated and displayed to the worker.

[1562] Step 3:

[1563] The server receives the worker's emotional data. As input, it receives data obtained from emotion sensors (e.g., heart rate monitors, facial recognition cameras) and sends it to the emotion engine. As data processing, the emotion engine analyzes the received data and quantifies the worker's emotional state (e.g., excitement level, stress level). As output, the analyzed emotional data is generated.

[1564] Step 4:

[1565] The server generates maintenance tasks appropriate for each worker based on the analysis results from the emotion engine. It receives the analyzed emotion data and maintenance history data as input. As data calculations, it adjusts the difficulty of the task based on the emotion data and selects the next necessary work from the maintenance history. As output, it generates an adjusted maintenance task and provides it to the worker.

[1566] Step 5:

[1567] The server notifies the worker of the generated maintenance task. As input, it receives the adjusted maintenance task and sends it to the worker's terminal. As a specific operation, it displays the task details (e.g., "The next task is filter replacement") on the worker's terminal. As output, it clearly shows the task that the worker should perform next.

[1568] In this way, the server can effectively utilize the maintenance history and emotion data to provide the most appropriate maintenance tasks to the worker.

[1569] 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 a voice indicating a user input regarding the result of the specific processing. The control unit 46A decodes the voice data indicating the user input acquired by the microphone 238.

[1570] The audio data is transmitted to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1571] 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> ) 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.

[1572] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1573] 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.

[1574] [Third embodiment]

[1575] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1576] 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.

[1577] 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).

[1578] 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.

[1579] 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.

[1580] 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).

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1587] "Example 1"

[1588] The learning tool of the present invention allows a learner to select the range of study to be done according to their own level, and generates problems based on that range. Specifically, if a learner is studying "differential calculus" in mathematics, the learner selects a range from basic concepts to applications of differentiation according to their level, and generates problems based on that range.

[1589] "Example 2"

[1590] The learning tool of the present invention evaluates the learner's level of understanding based on their answers and generates new questions based on the evaluation results. Specifically, after the learner answers the generated questions, the level of understanding is evaluated based on the accuracy of the answers and the time it took to answer, and the next question is generated based on the evaluation results. For example, if the learner correctly answers a basic question on differential calculus, the next question will be a more applied question. Conversely, if the learner makes a mistake on a basic question, another basic question within the same range will be generated.

[1591] "Example 3"

[1592] The learning tool of the present invention saves the learner's learning history and manages the learner's learning progress based on the saved learning history. Specifically, information such as which range the learner has studied and to what extent, and which questions the learner got wrong, is saved as a learning history, and the learner's learning progress is displayed based on the learning history. For example, if a learner has studied the entire range of differential calculus, the learner's learning progress is displayed as 100%. Furthermore, if the learner has made many mistakes on questions in a specific range, the learner is instructed to focus on studying that range.

[1593] The processing flow of each embodiment will be described below.

[1594] "Example 1"

[1595] Step 1: Learners choose the range of material they should study based on their own level. For example, if a learner is studying "differential calculus" in mathematics, they should choose a range of material from the basic concepts of differentiation to its applications based on their level.

[1596] Step 2: Generate problems based on the selected range. For example, if a learner selects the basic concept of differentiation, generate basic differentiation problems based on that range.

[1597] "Example 2"

[1598] Step 1: The learner answers the generated questions.

[1599] Step 2: Evaluate the learner's level of understanding based on the accuracy of their answers and the time it took to complete them.

[1600] Step 3: Generate the next question based on the evaluation results. For example, if the learner correctly answers a basic problem on differentiation, the next question will be a more applied problem. Conversely, if the learner makes a mistake on a basic problem, another basic problem in the same area will be generated.

[1601] "Example 3"

[1602] Step 1: Save information such as what areas the learner has studied, how much they have studied, and which questions they got wrong as a learning history.

[1603] Step 2: Display the learning progress based on the saved learning history. For example, if a learner has learned the entire range of differentiation, the learning progress will be displayed as 100%.

[1604] Step 3: If the student makes many mistakes in a particular area, instruct them to focus on that area.

[1605] Example 1

[1606] Next, a description will be given of Example 1 of Form 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."

[1607] With conventional learning tools, it was difficult to select an appropriate learning area according to the learner's level or to generate individually tailored questions. Furthermore, effective learning progress management based on learning history and learning trends was not sufficiently implemented. This made it difficult for learners to progress efficiently and hindered improvement in comprehension.

[1608] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for focusing on learning areas to be studied according to level, a means for performing trend analysis from the learning history, a means for loading content to deepen understanding, a means for generating questions based on prompt sentences using a generative AI model, a means for accepting answers to the generated questions, and a means for evaluating the level of understanding based on the answers and generating questions again according to the evaluation results. This makes it possible to select an appropriate learning area according to the learner's level and generate individually tailored questions, thereby realizing effective learning progress management based on the learning history and learning trends.

[1609] A "learning tool" is a device or software that a learner uses to acquire specific knowledge or skills.

[1610] "Level" is an indicator of a learner's level of knowledge and skill proficiency.

[1611] A "study scope" is the range of specific content or topics that a learner should study.

[1612] "Means for focused learning" are methods or functions that allow learners to concentrate on a specific learning area and progress with their studies.

[1613] "Learning history" is data that records what a learner has learned in the past and their progress.

[1614] "Trend analysis" refers to analyzing a learner's learning patterns and progress based on their learning history.

[1615] "Deepening content" is information or material provided to help learners gain a deeper understanding of a particular topic.

[1616] A "generative AI model" is a model that uses artificial intelligence to perform a specific task (in this case, problem generation).

[1617] A "prompt" is text that gives specific instructions or questions to a generative AI model.

[1618] A "means for generating problems" is a method or function for automatically creating problems for learners to solve.

[1619] "Means for accepting answers" refers to the method or function by which the system receives the answers given by the learner.

[1620] "Means for assessing comprehension" refers to methods or functions for measuring the learner's comprehension based on their answers.

[1621] The "means for generating questions again based on the evaluation results" refers to a method or function for creating new questions based on the results of the evaluation of the level of understanding.

[1622] The present invention relates to a learning tool that allows a learner to select a learning range according to his or her own level and generates questions based on that range. A specific embodiment of this system will be described below.

[1623] System configuration

[1624] This system consists of three main components: a server, a terminal, and a user. The server selects the study area, generates prompts, generates questions, displays the questions, accepts answers, and evaluates comprehension. The terminal provides an interface for the user to select the study area and answer the generated questions. The user selects the study area and solves the questions through the terminal.

[1625] Hardware and software used

[1626] The server generates questions using a generative AI model, such as OpenAI's GPT-4, while the device uses a standard web browser or mobile application to provide an interface for users to select the learning area and answer questions.

[1627] Data processing and calculation

[1628] The server generates a prompt based on the learning content selected by the user and sends the prompt to the generative AI model. The generative AI model generates an appropriate question based on the prompt and returns the result to the server. The server then sends the generated question to the device and displays it to the user. When the user answers the question, the device sends the answer to the server, and the server evaluates the user's level of understanding based on the answer.

[1629] Specific examples

[1630] For example, if the user selects "Fundamental Concepts of Differentiation," the server sends the following prompt to the generative AI model:

[1631] Example prompt sentence:

[1632] "Generate problems that address the fundamental concepts of differentiation. The problems should be beginner-level and focus on the definition of differentiation and basic calculation methods."

[1633] Based on this prompt, the generative AI model generates the following questions:

[1634] "Find the derivative of the following function \( f(x) = x^2 \)."

[1635] The server receives the problem and sends it to the terminal. The terminal displays the problem to the user, who solves it. When the user enters the answer, the terminal sends the answer to the server, and the server evaluates the user's understanding based on the answer.

[1636] The above is a specific embodiment for carrying out the present invention. This system allows learners to select an appropriate learning area according to their own level and solve problems that are individually tailored to them. This is expected to improve the learner's level of understanding.

[1637] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1638] Step 1: Select your study area

[1639] The user selects the learning topic using the terminal. For example, if the user wants to learn "differential calculus" in mathematics, the user selects "differential calculus" through the terminal interface.

[1640] Input: User-selected learning area (e.g., "Differential")

[1641] Output: Information about the selected study area

[1642] Specific operation: The user selects "differentiation" from the drop-down menu displayed on the terminal screen, and the terminal sends the selection information to the server.

[1643] Step 2: Generate a prompt statement

[1644] The server generates a prompt based on the received learning scope. For example, if the user selects "Basic concepts of differentiation," the server generates the prompt "Please generate problems related to the basic concepts of differentiation. The problems should be aimed at beginners and focus on the definition of differentiation and basic calculation methods."

[1645] Input: Information about the selected study area

[1646] Output: Generated prompt statement

[1647] Specific operation: The server analyzes the information in the selected learning area and generates an appropriate prompt sentence.

[1648] Step 3: Generate the problem

[1649] The server sends the generated prompt to the generative AI model, which generates an appropriate question based on the prompt and returns the result to the server.

[1650] Input: Generated prompt text

[1651] Output: Generated problem

[1652] Specific operation: The server sends a prompt to the generative AI model, which then analyzes the prompt and generates a problem. For example, it generates a problem such as, "Find the derivative of the following function \( f(x) = x^2 \)."

[1653] Step 4: View the problem

[1654] The server receives the generated questions and sends them to the terminal, which displays them to the user.

[1655] Input: Generated question

[1656] Output: The problem as seen by the user

[1657] Specific operation: The server sends the generated problem to the terminal, which displays it to the user, who then solves it.

[1658] Step 5: Accepting responses

[1659] The user solves the problem and enters the answer into the terminal, which then sends the answer to the server.

[1660] Input: User's answer

[1661] Output: The answer sent to the server

[1662] Specific operation: The user enters the answer in the input field of the terminal and presses the send button. The terminal then sends the answer to the server.

[1663] Step 6: Assess understanding

[1664] The server evaluates the user's level of understanding based on the received answers, and generates new questions based on the evaluation results.

[1665] Input: User's answer

[1666] Output: Comprehension assessment results and new questions

[1667] Specific operation: The server analyzes the user's answers and evaluates their level of understanding. Based on the evaluation results, it generates new prompts and sends them to the generative AI model again to generate new questions.

[1668] The above is the specific processing flow of the program of this system.

[1669] (Application example 1)

[1670] Next, a description will be given of Application Example 1 of Form 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."

[1671] Conventional learning tools are inadequate in generating questions and adjusting learning content according to the learner's level, and there is a lack of means for factory workers in particular to efficiently learn robot operation and maintenance skills. Furthermore, there is an issue that the generated questions and explanations are not appropriately adjusted according to the learner's level of understanding, resulting in a decrease in learning effectiveness.

[1672] 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.

[1673] In this invention, the server includes: means for focusing learning on areas to be learned according to level; means for performing trend analysis from learning history; means for loading content to deepen understanding; means for generating questions based on the loaded content; means for accepting answers to the generated questions; means for evaluating the level of understanding based on the answers and generating new questions according to the evaluation results; means for factory workers to learn robot operation and maintenance skills; means for generating questions related to robot operation and maintenance according to the learner's level; means for generating detailed explanations using a generative AI model; and means for displaying the generated explanations. This enables appropriate question generation and explanations according to the learner's level, making it possible for factory workers in particular to efficiently learn robot operation and maintenance skills.

[1674] "Means for focusing on learning areas that should be studied according to level" refers to a means for selecting content to be studied based on the learner's current knowledge and skill level, and for focusing on learning that content.

[1675] "Means for analyzing trends from learning history" refers to a means for analyzing a learner's past learning history and understanding learning trends and patterns.

[1676] "Means for loading content to deepen understanding" refers to a means for learners to input the content they wish to learn into the system and proceed with their learning based on that content.

[1677] The "means for generating questions based on the content that has been read" refers to a means for automatically generating appropriate questions based on the learning content that the learner has input.

[1678] The "means for accepting answers to questions that have been generated" refers to the means by which the system accepts answers to questions that have been answered by learners.

[1679] The "means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" refers to a means for evaluating the answers of the learner and generating new questions based on the evaluation results.

[1680] "Means for factory workers to learn robot operation and maintenance skills" refers to means for factory workers to learn knowledge and skills related to robot operation and maintenance.

[1681] The "means for generating problems relating to the operation and maintenance of a robot according to the level of the learner" refers to a means for automatically generating problems relating to the operation and maintenance of a robot according to the skill level of the learner.

[1682] "Means for generating detailed explanations using a generative AI model" refers to means for automatically generating detailed explanations that are easy for learners to understand, using a generative AI model.

[1683] "Means for displaying the generated explanation" refers to means for displaying the explanation generated by the generative AI model to the learner.

[1684] A system for implementing this invention is a learning tool for factory workers to learn robot operation and maintenance skills. This system selects an appropriate learning area based on the learner's level, generates questions based on that area, and provides detailed explanations using a generative AI model.

[1685] System configuration

[1686] 1. Hardware:

[1687] Factory robots

[1688] PC or tablet

[1689] server

[1690] 2. Software:

[1691] Python

[1692] Generative AI models (e.g., GPT-3)

[1693] Database Management Systems

[1694] Program processing explanation

[1695] The server selects a learning area based on the learner's level and generates questions based on that area. Specifically, when a learner selects one of the levels "beginner," "intermediate," or "advanced," questions related to robot operation and maintenance appropriate for that level are generated.

[1696] The generated questions are displayed on the learner's device (PC or tablet), and the learner enters their answers. The server accepts the learner's answers and evaluates their level of understanding. Based on the evaluation results, the server generates new appropriate questions and provides them to the learner.

[1697] Furthermore, a generative AI model is used to automatically generate detailed explanations that are easy for learners to understand, and the generated explanations are displayed on the learner's device.

[1698] Specific examples

[1699] For example, if the learner selects the "Intermediate" level, the following prompt will be generated:

[1700] Prompt: "Please explain how to calibrate the robot's sensors."

[1701] If we feed this prompt into a generative AI model, it will generate a detailed explanation like this:

[1702] To calibrate the robot's sensors, first place the robot in a stable position and perform the initial sensor setup. Then, use a calibration standard to adjust the sensor readings. Finally, save the calibration results and test them to verify accuracy.

[1703] In this way, learners can efficiently learn robot operation and maintenance skills.

[1704] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1705] Step 1:

[1706] A user logs in to the system using a terminal and selects their learning level (beginner, intermediate, or advanced). The input is the user's learning level, and the output is the information on the selected learning level. The server receives this information and proceeds to the next step.

[1707] Step 2:

[1708] The server selects the appropriate learning area based on the selected learning level. The input is the user's learning level, and the output is the selected learning area. The server retrieves the data for the corresponding learning area from the database and proceeds to the next process.

[1709] Step 3:

[1710] The server generates questions based on the selected learning scope. The input is the data from the learning scope, and the output is the generated questions. The server uses the generative AI model to generate questions appropriate for the learning scope and proceeds to the next step.

[1711] Step 4:

[1712] The server sends the generated questions to the user's terminal. The input is the generated question, and the output is the question displayed on the user's terminal. The user checks the question on the terminal and enters the answer.

[1713] Step 5:

[1714] The user inputs the answer to the question using a terminal and sends it to the server. The input is the user's answer, and the output is the answer data sent to the server. The server receives this data and proceeds to the next step.

[1715] Step 6:

[1716] The server evaluates the user's answers and determines the level of understanding. The input is the user's answer data, and the output is the evaluation result of the level of understanding. The server uses an evaluation algorithm to evaluate the user's level of understanding and proceeds to the next step.

[1717] Step 7:

[1718] The server generates new questions based on the evaluation results. The input is the evaluation result of the level of understanding, and the output is the newly generated questions. The server uses the generative AI model to generate new questions based on the evaluation results and proceeds to the next process.

[1719] Step 8:

[1720] The server generates a detailed explanation using a generative AI model. The input is a newly generated problem, and the output is a detailed explanation. The server inputs a prompt sentence into the generative AI model and generates a detailed explanation.

[1721] Step 9:

[1722] The server sends the generated detailed explanation to the user's device. The input is the detailed explanation, and the output is the explanation displayed on the user's device. The user checks the detailed explanation on the device and proceeds with their learning.

[1723] Example 2

[1724] Next, a description will be given of Example 2 of Form 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."

[1725] Conventional learning tools have difficulty generating appropriate questions based on the learner's level of understanding, which has led to problems with insufficient learning outcomes. Furthermore, they lack a mechanism for effectively utilizing the learner's response data to generate the next question, resulting in insufficient learning support tailored to each learner's individual level of understanding.

[1726] 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.

[1727] In this invention, the server includes a means for collecting learner response data, a means for evaluating the learner's level of understanding, a means for generating the next question using a generative AI model, and a means for delivering the generated question to the learner. This makes it possible to automatically generate appropriate questions according to the learner's level of understanding and provide learning support according to the learner's individual level of understanding.

[1728] A "learning tool" is a system or software that a learner uses to acquire specific knowledge or skills.

[1729] "Means for focusing on areas that should be studied according to level" is a function that selects an appropriate learning area based on the learner's current level of understanding and progress, and allows them to focus on studying that area.

[1730] "Means for analyzing trends from learning history" is a function for analyzing a learner's past learning data and extracting learning trends and patterns.

[1731] "Means for reading content to deepen understanding" is a function that provides the learning materials and information necessary for learners to gain a deeper understanding of specific knowledge or skills.

[1732] "Means for generating questions based on the content that has been read" is a function for creating appropriate questions for learners based on the teaching materials and information provided.

[1733] The "means for accepting answers to questions generated" is a function for inputting answers to questions answered by learners into the system and recording them.

[1734] "Means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results" is a function for analyzing the learner's answer data and automatically generating the next question based on the results.

[1735] "Means for collecting learner response data" is a function for collecting data on questions answered by learners and storing it in the system.

[1736] The "means for assessing the learner's level of understanding" is a function for analyzing the learner's response data and assessing the learner's level of understanding based on the results.

[1737] "Means for generating the next question using a generative AI model" is a function that uses artificial intelligence to automatically generate the next question based on the learner's level of understanding.

[1738] The "means for delivering generated questions to learners" is a function for presenting generated questions to learners and encouraging them to answer them.

[1739] The present invention is a system that automatically generates questions according to the learner's level of understanding and effectively supports the learner's learning. A specific embodiment of this system will be described below.

[1740] System configuration

[1741] This system is mainly composed of three elements: a server, a terminal, and a user. The server collects learners' response data, evaluates their level of understanding, and generates the next question. The terminal provides an interface for learners to answer questions and sends the answer data to the server. Users answer questions through their terminals and progress through their studies.

[1742] Hardware and software used

[1743] The server is a computer with high-performance computing capabilities, implemented using a programming language such as Python, TensorFlow or PyTorch as machine learning libraries, and an advanced natural language processing model such as GPT-4 as a generative AI model.

[1744] Data processing and calculation

[1745] The server receives the learner's response data sent from the terminal and performs the following data processing and calculations.

[1746] 1. Data collection: The device collects data on the questions answered by the learner and sends it to the server. This data includes whether the answer was correct or incorrect, the time it took to answer, the type of question, etc.

[1747] 2. Data analysis: The server analyzes the received data and evaluates the learner's level of understanding. Specifically, it calculates a score based on the percentage of correct answers and the time it took to answer.

[1748] 3. Problem generation: The server generates the next problem based on the evaluation results. It uses a generative AI model (e.g., GPT-4) to generate a problem of appropriate difficulty. It uses prompts to provide instructions to the model.

[1749] 4. Question distribution: The server sends the generated questions to the terminal and presents them to the learner.

[1750] Specific examples

[1751] For example, consider a case where a user answers a basic question on differentiation. If the user correctly answers "2x" to the question "Find the derivative of f(x) = x^2," the server will evaluate the user's level of understanding as high. Next, it will generate an applied question such as "Find the derivative of f(x) = x^3 + 3x^2."

[1752] Conversely, if the user makes a mistake in a basic problem, for example, if they answer "x" to "Find the derivative of f(x) = x^2," the server will evaluate the user's level of understanding as low. It will then generate another basic problem in the same range, such as "Find the derivative of f(x) = 2x."

[1753] Prompt Sentence Examples

[1754] Examples of prompts to use with generative AI models include:

[1755] "Once students have correctly answered the basic differentiation problem, generate a more advanced problem. For example, generate a problem that asks them to find the derivative of f(x) = x^3 + 3x^2."

[1756] In this way, the server generates appropriate questions according to the learner's level of understanding and provides them to the learner via their device, allowing the learner to tackle questions that correspond to their own level of understanding, enabling effective learning.

[1757] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1758] Step 1:

[1759] Data collection

[1760] The terminal collects data on questions answered by the user. Specifically, the user answers questions displayed on the terminal, and the terminal records the answers. Input includes the user's answer, answer time, question type, etc. The terminal sends this data to the server. The output is the answer data sent to the server.

[1761] Step 2:

[1762] Data analysis

[1763] The server analyzes the response data received from the device. The input includes the user's response data. The server executes an algorithm to evaluate the learner's level of understanding based on the accuracy of the answers and the time it took to answer. Specifically, it calculates a score based on the percentage of correct answers and the time it took to answer. The output is a score that indicates the learner's level of understanding.

[1764] Step 3:

[1765] Problem generation

[1766] The server generates the next problem based on the evaluation results. The input includes a score indicating the learner's level of understanding. The server uses a generative AI model (e.g., GPT-4) to generate a problem of appropriate difficulty. Specifically, it uses prompt sentences to provide instructions to the generative AI model. The output is the generated new problem.

[1767] Step 4:

[1768] Problem distribution

[1769] The server sends the generated questions to the terminal. The input contains the new questions that have been generated. The terminal presents the received questions to the user. Specifically, the new questions are displayed on the terminal, ready for the user to answer. The output is the new questions presented to the user.

[1770] Step 5:

[1771] User Answers

[1772] The user answers new questions presented on the terminal. The input includes new questions sent from the server. The user inputs the answers to the questions and sends them to the terminal. The output is the user's new answer data.

[1773] In this way, the server generates appropriate questions according to the learner's level of understanding and provides them to the learner via their device, allowing the learner to tackle questions that correspond to their own level of understanding, enabling effective learning.

[1774] (Application example 2)

[1775] Next, a description will be given of Application Example 2 of Form 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."

[1776] Conventional learning tools are inadequate in generating questions that correspond to the learner's level of understanding, and are not particularly suited to improving the specialized skills of factory robot maintenance engineers. Furthermore, the level of understanding is not evaluated based on the correctness of the engineer's answers or the time it takes to answer, and the next questions are not generated appropriately, making efficient learning difficult. This poses the problem of delaying the improvement of engineers' skills and reducing the operational efficiency of factories.

[1777] 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.

[1778] In this invention, the server is a learning tool for people of all ages who have learning problems, and includes: means for focusing learning on areas that should be studied according to level; means for performing trend analysis from learning history; means for loading content to deepen understanding; means for generating questions based on the loaded content; means for accepting answers to the generated questions; means for evaluating the level of understanding based on the answers and generating new questions based on the evaluation results; means for generating questions for factory ...

Claims

1. A learning tool, comprising a means for instructing a user to learn a range of study that corresponds to the user's level; A means for conducting trend analysis based on learning history; A means for reading content for deepening understanding of the range to be studied; A means for generating questions based on the content loaded; A means for accepting answers to the generated questions; A means for evaluating the user's level of understanding based on the answers and generating questions again according to the evaluation results; A means for acquiring user emotion data and adjusting learning content based on the emotion; and A means for calculating and displaying a learning progress based on a learning history; If there are many incorrect questions in a particular range, a means for instructing the user to study the range; A system including:

2. 2. The system according to claim 1, further comprising a means for storing a user's learning history and managing a learning progress based on the stored learning history.

3. The system of claim 1 , further comprising means for individually adjusting learning content based on a user's learning tendencies.

Images