System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an answer input by a user to determine a learning level of the user; means for determining whether the answer of the user is correct or incorrect using artificial intelligence for evaluating the answer; means for updating the learning level of the user based on a result of the determination; and means for generating a new question according to the updated learning level and presenting the new question to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional learning support systems lack the ability to accurately assess a user's learning level and provide appropriate questions accordingly, making it difficult to provide an optimal learning experience for each individual user. Furthermore, they lacked a mechanism to provide appropriate explanations when a user struggles, making it difficult to improve learning efficiency. This made it difficult for users to effectively manage their own learning progress. [Means for solving the problem]

[0005] The present invention provides a system that automatically determines a user's learning level and provides appropriate questions based on that level. Specifically, the system includes a means for receiving answers entered by the user, determining whether the answers are correct using artificial intelligence, and updating the user's learning level based on the determination result. The system also includes a means for generating new questions based on the updated learning level and presenting them to the user. Furthermore, the system includes a means for generating an explanation using artificial intelligence and presenting it to the user when the user requests an explanation for a specific question. The system provides a system that can automatically determine where a user is having trouble and provide an explanation, even if the user does not request an explanation.

[0006] "User" refers to the entity that uses the system to learn.

[0007] "Learning level" is an indicator of the user's level of knowledge and skill.

[0008] "Answer" refers to the answer that a user enters in response to a question presented to them.

[0009] "Artificial intelligence" refers to the technology that enables computer programs or systems to behave in a way that mimics human intelligence.

[0010] "Correct or incorrect" refers to an evaluation that indicates whether the user's answer is correct or incorrect.

[0011] "Problems" refer to learning questions or tasks presented to users.

[0012] "Judgment" refers to the process by which the artificial intelligence evaluates the user's answer and determines whether it is correct or incorrect.

[0013] "Update" refers to changing a user's learning level to the latest state.

[0014] "Explanation" refers to something that provides a detailed explanation of a problem or question.

[0015] "Trouble spots" refer to parts that users find difficult to understand or make mistakes in.

[0016] "Generation" refers to the process by which artificial intelligence creates new problems and explanations. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a learning support system that determines a user's learning level and provides appropriate questions. This system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions appropriate to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[0039] System configuration

[0040] 1. Receiving the user's answer

[0041] The user uses a terminal to access the system and input answers to the questions presented.

[0042] The server receives the user's answer and proceeds to the next step.

[0043] 2. Evaluating your answers

[0044] The server uses artificial intelligence to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[0045] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[0046] 3. Update user learning level

[0047] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[0048] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[0049] 4. Creating new problems

[0050] The server generates new questions according to the user's updated learning level.

[0051] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[0052] 5. Providing commentary

[0053] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[0054] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[0055] 6. Automatic detection of stumbling blocks and provision of explanations

[0056] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[0057] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[0058] Specific examples

[0059] 1. User accesses the system for the first time

[0060] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[0061] 2. New questions

[0062] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[0063] 3. Requesting and Providing Explanations

[0064] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[0065] 4. Automatic detection of stumbling blocks

[0066] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[0067] As described above, according to the present invention, it is possible to provide questions and explanations that are optimal for the user's learning progress, thereby significantly improving learning efficiency.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] A user accesses the system using a terminal, which presents the user with a welcome or login screen.

[0071] Step 2:

[0072] When the user enters the answer to the question on the terminal and presses the send button, the answer data is sent to the server.

[0073] Step 3:

[0074] The server receives the answer data sent from the device and extracts the user ID and answer content.

[0075] Step 4:

[0076] The server uses artificial intelligence to evaluate the user's answers, using pre-trained data to determine whether the answers are correct or incorrect.

[0077] Step 5:

[0078] The server updates the user's learning level based on the evaluation of the answer (correct or incorrect), for example, raising the level if the answer is correct and lowering the level if the answer is incorrect.

[0079] Step 6:

[0080] The server selects or generates the next questions based on the user's updated learning level. Questions are either selected from a database or newly generated using artificial intelligence.

[0081] Step 7:

[0082] The server sends the selected or generated questions to the terminal and displays them to the user.

[0083] Step 8:

[0084] When a user requests an explanation for a problem, the terminal sends an explanation request to the server.

[0085] Step 9:

[0086] The server receives the explanation request and generates an explanation using artificial intelligence based on the user's current learning level and the requested problem.

[0087] Step 10:

[0088] The server sends the generated commentary to the terminal and displays it to the user.

[0089] Step 11:

[0090] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically determines where the user is having trouble.

[0091] Step 12:

[0092] The server uses artificial intelligence to generate an explanation for the problem, sends the explanation to the terminal, and displays it to the user.

[0093] The above is the specific process flow for presenting questions according to the user's learning level and providing explanations as needed.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Conventional learning support systems have difficulty providing appropriate questions according to the user's learning level or providing specific explanations for the user's stumbling points, which can lead to reduced learning efficiency. The present invention aims to support efficient learning by providing questions optimized for the user's learning level, identifying the areas where the user is stumbling, and providing appropriate explanations.

[0097] 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.

[0098] In this invention, the server includes means for receiving the user's answers at the terminal and transmitting them to the server, means for determining whether the answers are correct using artificial intelligence, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for automatically determining where the user is having difficulty and providing explanations for those parts. This allows the user to receive questions and explanations that are optimal for their learning progress, thereby improving the efficiency of their learning.

[0099] "Terminal" means an electronic device through which a user accesses the system and inputs answers to questions.

[0100] The "server" is a central computer that processes answers received from users and operates the entire learning support system, including evaluating questions, updating learning levels, and generating new questions.

[0101] "Artificial intelligence" refers to technology that includes advanced algorithms and databases used to evaluate user answers, generate explanations, and automatically identify stumbling blocks.

[0102] "Correctness of answer" is an evaluation result that indicates whether the answer entered by the user is correct for the presented question.

[0103] "Learning level" is an indicator that shows the user's current state according to their knowledge and understanding, and is used to determine the difficulty of the questions the system presents.

[0104] A "new problem" is the next learning task that is generated based on the user's learning level.

[0105] "Explanation" is additional explanation or information provided to help users better understand a particular issue.

[0106] "Trouble spots" refer to areas where users have made many incorrect answers or lacked understanding in their past answers to questions.

[0107] A "question generation module" is a program with a series of functions for extracting questions from a database or generating new questions appropriate to the user's learning level.

[0108] The "explanation generation module" is a program that uses artificial intelligence to generate explanations for problems and provide them to users in an easy-to-understand format.

[0109] MODE FOR CARRYING OUT THE INVENTION

[0110] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions according to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[0111] System configuration

[0112] 1. Receiving the user's answer

[0113] The user uses a terminal to access the system and input answers to the questions presented.

[0114] The device receives the user's input and sends it to the server, which records the received answers.

[0115] 2. Evaluating your answers

[0116] The server uses artificial intelligence (AI) to determine whether the answer is correct or not. The server first passes the answer data to the evaluation module.

[0117] The evaluation module references a pre-trained database and uses an algorithm to analyze the answers.

[0118] For example, if a user answers "4" to the question "What is 2+2?", the server will determine this as the correct answer.

[0119] 3. Update user learning level

[0120] The server performs a process to update the user's learning level based on the evaluation result of the answer.

[0121] The server first retrieves the user's current learning level from the database, then applies the update logic based on the new assessment results.

[0122] For example, if a user with a learning level of "easy" answers a question correctly, the server updates the learning level to "medium."

[0123] 4. Creating new problems

[0124] The server generates new questions based on the updated learning level using a question generation module.

[0125] The question generation module selects questions from a database appropriate for the user's learning level or generates new questions.

[0126] For example, a user with a learning level of "medium" might be asked the question "Please explain the process of photosynthesis."

[0127] 5. Providing commentary

[0128] When a user requests an explanation for a specific question, the server generates the explanation using artificial intelligence. The server first sends a request to the explanation generation module.

[0129] The explanation generation module creates a detailed explanation of the question and forms a document to be provided to the user.

[0130] For example, in response to the question "What is 2 + 2?", it generates an explanation such as "This problem is a basic addition problem, where 2 added to another 2 equals 4."

[0131] 6. Automatic detection of stumbling blocks and provision of explanations

[0132] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[0133] The server first inputs the answer history into an analysis algorithm, which identifies which questions the user gets wrong the most.

[0134] For the identified stumbling points, the server again uses the explanation generation module to create appropriate explanations and provide them to the user.

[0135] Specific examples

[0136] 1. When you receive your answer

[0137] When a user types "4" into a "2+2" problem on a terminal, the terminal sends the answer to the server, which records the answer in a database.

[0138] 2. Evaluating your answers

[0139] The server retrieves the answer "4" from the database and passes it to the evaluation module. The evaluation module checks whether it matches the correct answer "4" in the database and returns the result to the server. The server stores the result as the "correct answer."

[0140] 3. Learning Level Update

[0141] The server retrieves the user's current learning level as "easy" from the database and updates it to "medium" based on the new evaluation results.

[0142] 4. Creating new problems

[0143] The server searches the database for questions suitable for the "medium" level and sends the question "Please explain the process of photosynthesis" to the user.

[0144] 5. Providing commentary

[0145] When a user requests an explanation, the server sends a request to the explanation generation module, which generates an explanation such as "2 + 2 is a basic addition problem and the answer is 4" and provides it to the user.

[0146] 6. Automatic detection of stumbling blocks and provision of explanations

[0147] The server analyzes the user's answer history and detects if the user has made consecutive mistakes on any of the questions. Using this result, it generates an explanation for the relevant part and provides it to the user.

[0148] In this way, each component of the system works in tandem to provide questions and explanations that are optimal for the user's learning progress, significantly improving learning efficiency.

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

[0150] Step 1:

[0151] Receiving user answers

[0152] Users access the system using a terminal and enter answers to questions presented to them. The terminal receives the user's input and sends it to the server.

[0153] Input: The answer entered by the user into the device (e.g., "4" as the answer to "2+2")

[0154] Output: User's answer data sent to the server

[0155] Step 2:

[0156] Evaluating answers

[0157] The server uses artificial intelligence (AI) to determine whether the answer data is correct or not. First, the answer data is passed to the evaluation module.

[0158] Input: User's answer data received by the server

[0159] Data processing / data calculation: The evaluation module refers to a database that has been previously trained, compares the answer with the correct data, and determines whether it is correct or incorrect.

[0160] Output: The answer is judged as "correct" or "incorrect".

[0161] Step 3:

[0162] Update user learning level

[0163] The server updates the user's learning level based on the evaluation of the answer. First, it retrieves the user's current learning level from the database. Then it applies the update logic based on the new evaluation result.

[0164] Input: The user's current learning level and the evaluation result of the answer

[0165] Data processing / data calculation: Based on the new assessment results, the user's learning level is updated appropriately (e.g., from "easy" to "medium").

[0166] Output: Updated user learning level

[0167] Step 4:

[0168] Creating a new problem

[0169] The server generates new questions based on the updated learning level. Using the question generation module, the server selects questions from the database that are appropriate for the user's learning level, or generates new questions.

[0170] Input: Updated user learning level

[0171] Data processing / data calculation: The problem generation module selects or generates appropriate problems from the database and presents them to the user.

[0172] Output: New question (e.g., "Describe the process of photosynthesis.")

[0173] Step 5:

[0174] Providing commentary

[0175] When a user requests an explanation for a specific question, the server uses artificial intelligence to generate an explanation and sends a request to the explanation generation module to create a detailed explanation.

[0176] Input: A request from a user asking for clarification on a specific question.

[0177] Data processing / data calculation: The explanation generation module creates a detailed explanation of the relevant question and forms a document to be provided to the user.

[0178] Output: Generated explanation (e.g. "2 + 2 is a basic addition problem, adding 2 to another 2 makes 4")

[0179] Step 6:

[0180] Automatically identify stumbling blocks and provide explanations

[0181] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[0182] Input: User's answer history

[0183] Data processing / data calculation: AI algorithms analyze answer history and identify which questions users get wrong most often, generating explanations for identified stumbling blocks.

[0184] Output: Identified stumbling blocks and their explanations

[0185] The above are the specific processing steps of the program of this system, including input, data processing, data calculation, and output at each step.

[0186] (Application example 1)

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

[0188] In recent years, demand for online learning platforms has increased, creating a need for personalized learning experiences for each user. However, many systems are unable to effectively provide questions and explanations tailored to the user's learning level, making it difficult to improve learning efficiency. In particular, there is a lack of intelligent systems that can automatically identify where users are struggling and provide appropriate explanations. Given these factors, it is necessary to provide a system that improves learning efficiency by providing users with appropriate learning questions and explanations in real time and visually displaying their learning progress.

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

[0190] In this invention, the server includes means for receiving answers entered by a user, means for determining whether the user's answers are correct or incorrect using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for visually displaying the user's learning progress. This makes it possible to provide users with personalized study questions and explanations in real time, thereby improving their learning efficiency.

[0191] "User" refers to an individual or organization that uses the system to answer study questions.

[0192] "Answer" refers to the answer entered by the user in response to the presented study question.

[0193] "Means for receiving" refers to the mechanism and process for capturing user-entered answers on the server.

[0194] "Artificial intelligence" refers to a program or system that uses machine learning or deep learning techniques to evaluate a user's answers and generate appropriate questions and explanations.

[0195] "Means for determining correctness" refers to a mechanism that uses artificial intelligence to determine whether a user's answer is correct or incorrect.

[0196] "Learning level" refers to an indicator that shows the user's current academic ability and level of understanding.

[0197] "Means for updating" refers to a mechanism that appropriately changes the user's learning level based on the evaluation of the answers.

[0198] "Means for generating questions" refers to a mechanism for creating appropriate learning questions according to the user's learning level and presenting them to the user.

[0199] "Visual display means" refers to mechanisms that show users their learning progress and outcomes in visual formats such as graphs and dashboards.

[0200] "Means for generating explanations" refers to a mechanism that uses artificial intelligence to create explanations for parts that the user does not understand.

[0201] "Generative AI model" refers to an advanced machine learning algorithm or model used to generate explanations, questions, etc.

[0202] A "prompt" refers to an instruction or question that is input into a generative AI model.

[0203] "Trouble spots" refer to points where users had difficulty answering questions or where they did not fully understand the questions.

[0204] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user in real time, evaluates the answers using artificial intelligence, and updates the user's learning level. It then generates new, appropriate questions based on the updated learning level and presents them to the user. It can also provide explanations when the user requests an explanation for a specific question or when it automatically identifies an area where the user is having difficulty.

[0205] System configuration and operation

[0206] The system mainly consists of a server and a user terminal. The server plays a central role in analyzing users' learning activities and providing appropriate feedback. The user terminal provides an interface for users to answer learning questions and receive feedback.

[0207] 1. Receiving the user's answer

[0208] Users access the learning support system using their own devices (e.g., smartphones, tablets, PCs), enter answers to questions, and these answers are sent to and received from the server.

[0209] 2. Evaluating your answers

[0210] The server uses artificial intelligence, especially generative AI models (e.g., GPT-4), to determine whether a user's answer is correct. For example, if a user answers "4" to a simple arithmetic problem like "What is 2 + 2?", the answer is considered correct.

[0211] 3. Learning Level Update

[0212] The server updates the user's learning level based on the evaluation of the answer. For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[0213] 4. Creating new problems

[0214] The server generates new questions based on the updated learning level and presents them to the user. A user with a learning level of "medium" will be provided with a medium-level question such as "Please explain the process of photosynthesis."

[0215] 5. Visual display of learning progress

[0216] Users' learning progress is displayed visually in the form of dashboards and graphs, allowing them to see their progress at a glance, making it easier for users to understand their own learning progress.

[0217] 6. Commentary

[0218] When a user requests an explanation for a specific problem, the server uses the generative AI model to generate a detailed explanation for the problem and provide it to the user. An example of a prompt sentence to generate is "Explain the process of photosynthesis in plants."

[0219] 7. Automatic detection of stumbling blocks and provision of explanations

[0220] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the part where the user is having trouble. Then, it generates an explanation for that part using a generative AI model and provides it to the user. An example of a specific prompt is "Explain where common mistakes occur in solving quadratic equations."

[0221] This not only allows users to study efficiently, but also provides timely support for difficult-to-understand parts. In addition, by intuitively understanding their learning progress, they can study more systematically.

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] The user accesses the learning support system and inputs answers to the learning questions.

[0225] Input: The user enters the answer to the question (e.g., "4") into the terminal.

[0226] How it works: The device sends user input to the server in real time.

[0227] Output: The server receives the user's answer data.

[0228] Step 2:

[0229] The server evaluates the received answers using artificial intelligence (generative AI model).

[0230] Input: The user's answer data received by the server.

[0231] How it works: A generative AI model (e.g., GPT-4) analyzes the answer data and determines whether the answer is correct. For example, the answer "4" to the question "What is 2 + 2?" is determined to be correct.

[0232] Output: The server obtains the evaluation result (correct / incorrect).

[0233] Step 3:

[0234] Based on the result of the correct / incorrect judgment, the server updates the user's learning level.

[0235] Input: The evaluation result obtained by the server.

[0236] How it works: The server checks the user's current learning level based on the assessment results and upgrades or downgrades the level as necessary. For example, if a user answers correctly at the initial "easy" level, they will be upgraded to "medium" level.

[0237] Output: Updated user learning level information.

[0238] Step 4:

[0239] The server generates new questions based on the updated learning level and presents them to the user.

[0240] Input: Updated learning level information.

[0241] How it works: Using a generative AI model, the server generates appropriate questions, such as "Please explain the process of photosynthesis" for a "medium" level user.

[0242] Output: A new training problem.

[0243] Step 5:

[0244] The server presents the user with a new problem.

[0245] Input: A new study question.

[0246] Operation: The generated question is sent to the user's terminal, which displays it.

[0247] Output: User sees new issue.

[0248] Step 6:

[0249] The server visually displays the user's learning progress.

[0250] Input: Updated learning level information and answer history.

[0251] How it works: The server uses this information to generate a dashboard and graphs of the user's progress.

[0252] Output: Visually displayed learning progress data.

[0253] Step 7:

[0254] When a user requests an explanation for a particular problem, the server generates the explanation using a generative AI model.

[0255] Input: User clarification request and applicable problem information.

[0256] How it works: An appropriate prompt (e.g., "Explain the process of photosynthesis in plants.") is input into the generative AI model to generate an explanation.

[0257] Output: The generated commentary.

[0258] Step 8:

[0259] The server presents the generated explanation to the user.

[0260] Input: The generated description.

[0261] What it does: Sends a description to the user's terminal, which displays it.

[0262] Output: User checks the explanation.

[0263] Step 9:

[0264] Even if the user does not request an explanation, the server automatically identifies the user's stumbling block and generates an explanation using a generative AI model.

[0265] Input: User's answer history and stumbling block information.

[0266] How it works: Enter an appropriate prompt (e.g., "Explain where common mistakes occur in solving quadratic equations.") into the generative AI model to generate an explanation.

[0267] Output: The generated commentary.

[0268] Step 10:

[0269] The server provides the user with an explanation of the problem.

[0270] Input: The generated description.

[0271] What it does: Sends a description to the user's terminal, which displays it.

[0272] Output: User checks the explanation.

[0273] 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.

[0274] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[0275] System configuration

[0276] 1. Receiving the user's answer

[0277] The user uses a terminal to access the system and input answers to the questions presented.

[0278] The server receives the user's answer and proceeds to the next step.

[0279] 2. Evaluating your answers

[0280] The server uses artificial intelligence to determine whether the user's answer is correct or not, using a pre-trained database and evaluation algorithms.

[0281] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[0282] 3. Update user learning level

[0283] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[0284] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[0285] 4. Creating new problems

[0286] The server generates new questions according to the user's updated learning level.

[0287] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[0288] 5. Providing commentary

[0289] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[0290] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[0291] 6. Automatic detection of stumbling blocks and provision of explanations

[0292] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[0293] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[0294] Introducing the Emotion Engine

[0295] 1. User Emotion Recognition

[0296] The server uses the camera and microphone installed on the user's device to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state.

[0297] For example, if a user is feeling frustrated about a problem, the emotion engine will recognize this as "stress."

[0298] 2. Adjusting problems based on emotional state

[0299] The server adjusts the difficulty and content of the questions based on the user's emotional state.

[0300] For example, if a user is feeling stressed, the system will provide a relaxed learning environment by presenting them with slightly easier questions.

[0301] 3. Adjusting commentary based on emotional state

[0302] The server provides commentary according to the user's emotional state.

[0303] For example, if a user is confused, provide a more detailed and understandable explanation.

[0304] 4. Real-time emotion monitoring and response

[0305] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed.

[0306] For example, if a user is feeling very stressed, a message will be sent encouraging them to take a break.

[0307] Specific examples

[0308] 1. User accesses the system for the first time

[0309] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[0310] In addition, the system evaluates the user's emotions and, if it determines that the user is not feeling stressed, presents a more difficult question next.

[0311] 2. New questions and emotional responses

[0312] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[0313] If the user begins to get confused by a question, the emotion engine will recognize this and the server will simplify the problem or add a detailed explanation.

[0314] 3. Requesting and Providing Explanations

[0315] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[0316] If the user appears calm and understanding, we will provide additional explanations of more complex content.

[0317] 4. Automatic detection of stumbling blocks

[0318] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[0319] If the user is stressed about a particular issue, add advice to help ease that stress.

[0320] The present invention provides questions and explanations that are optimal for the user's learning progress and emotional state, thereby significantly improving learning efficiency.

[0321] The processing flow will be explained below.

[0322] Step 1:

[0323] A user accesses the system using a terminal, which presents the user with a login or welcome screen.

[0324] Step 2:

[0325] The user enters the answer to the question on the device and presses the send button, which sends the answer data to the server.

[0326] Step 3:

[0327] The server analyzes the answer data received from the device and extracts the user ID and answer content.

[0328] Step 4:

[0329] The server uses artificial intelligence to evaluate the accuracy of the user's answer. For example, if the answer is "4", it will be evaluated as "correct".

[0330] Step 5:

[0331] The server updates the user's learning level based on the evaluation results: if the answer is correct, the level is raised; if the answer is incorrect, the level is lowered.

[0332] Step 6:

[0333] The server selects or generates the next questions based on the updated learning level, either retrieved from a database or created using artificial intelligence.

[0334] Step 7:

[0335] The server sends the generated or selected questions to the terminal and displays them to the user.

[0336] Step 8:

[0337] If the user experiences difficulty with a problem, the emotion engine uses the device's camera and microphone to analyze the user's emotional state in real time, for example, by analyzing facial expressions and evaluating voice tone.

[0338] Step 9:

[0339] The emotion engine determines the user's emotional state, and if it detects negative emotions such as stress or confusion, it sends that information to the server.

[0340] Step 10:

[0341] The server adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state. For example, if the user is feeling stressed, the questions will be made slightly easier.

[0342] Step 11:

[0343] When a user requests an explanation for a particular question, the terminal sends an explanation request to the server.

[0344] Step 12:

[0345] The server receives the explanation request and generates an explanation using artificial intelligence, taking into account the user's learning level and emotional state.

[0346] Step 13:

[0347] The server sends the generated explanation to the terminal and displays it to the user. For example, the explanation for "What is 2 + 2?" is "This is a basic addition problem, adding 2 to another 2 gives you 4."

[0348] Step 14:

[0349] Even if the user does not request an explanation, the server will analyze the answer history and automatically determine the areas where the user has trouble.

[0350] Step 15:

[0351] The server uses artificial intelligence to generate explanations for the stumbling blocks and presents them to the user. For example, if a user repeatedly makes mistakes on a particular problem, the server will provide a detailed explanation for that problem.

[0352] Step 16:

[0353] The system monitors the user's emotional state in real time, and if the user feels severe stress, the server sends a message to the device recommending relaxation advice or a break.

[0354] In this way, a system is constructed in which the server, terminal, and user cooperate to provide a learning experience that is optimal for the user's learning progress and emotional state.

[0355] Example 2

[0356] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0357] Conventional learning support systems judge whether a user's answers are correct and update their learning level, but do not adjust their level based on the user's emotional state, which can lead to reduced learning efficiency. Another issue is that they do not provide appropriate support even when the user does not request explanations. Furthermore, if questions and explanations are not adjusted based on the user's emotional state, this can affect the user's motivation and level of understanding.

[0358] 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.

[0359] In this invention, the server includes means for receiving answers entered by the user, means for determining whether the user's answers are correct using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, means for analyzing the user's facial expressions and voice using a sensor on the device and determining the user's emotional state using an emotion engine in order to recognize the user's emotional state, means for adjusting the difficulty of the questions based on the user's emotional state, and means for adjusting the content and presentation method of the explanations based on the user's emotional state. This allows the server to present appropriate questions and explanations to the user, improving the learning experience according to the user's emotional state.

[0360] "User learning level" is an index of the user's knowledge and skill proficiency.

[0361] The "means for receiving answers" refers to a mechanism for transferring answers entered by the user from the terminal to the server and acquiring the data.

[0362] The "means for determining whether the answer is correct" is a system that uses artificial intelligence to determine whether the user's answer is correct or incorrect.

[0363] The "means for updating the learning level" is a mechanism for changing the user's current learning level based on whether the user's answer is correct or incorrect.

[0364] "Means for generating questions and presenting them to the user" refers to a mechanism that creates new questions based on the user's learning level and displays them on the screen for the user.

[0365] The "means for recognizing emotional states" is a mechanism that uses the device's sensors to collect and analyze the user's emotional responses, such as facial expressions and voice, and then identifies the user's emotions using an emotion engine.

[0366] The "means for adjusting the difficulty of questions based on the emotional state" is a mechanism for appropriately changing the difficulty of questions presented in accordance with the recognized emotional state of the user.

[0367] The "means for adjusting the content and presentation method of the commentary based on the emotional state" is a mechanism for adjusting the optimal content and presentation method of the commentary taking into account the emotional state of the user.

[0368] MODE FOR CARRYING OUT THE INVENTION

[0369] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[0370] System configuration

[0371] Receiving user answers

[0372] A user uses a terminal to access the system and input answers to the questions presented. The terminal sends this answer data to the server. The server receives the answer data and prepares it for the next process. For example, if a user inputs "4" in response to the question "What is 2+2?", that data is sent to the server.

[0373] Evaluating answers

[0374] The server uses artificial intelligence to determine whether the user's answer is correct. The AI ​​uses a pre-trained database and evaluation algorithm to do this. Specifically, the server sends the answer data "4" to the AI ​​model, and the AI ​​model determines that "4" is the correct answer.

[0375] Update user learning level

[0376] The server updates the user's learning level based on whether the answer is correct or incorrect. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level. For example, if a user whose initial learning level is "easy" answers correctly, the level is updated to "medium."

[0377] Creating a new problem

[0378] The server generates new questions based on the updated learning level. At this time, it selects appropriate questions from a pre-prepared question bank and sends them to the device. The device then displays the new questions to the user. For example, a user at the "medium" level might be presented with the question "Please explain the process of photosynthesis."

[0379] Providing commentary

[0380] If a user requests an explanation, the server uses artificial intelligence to generate a detailed explanation for the problem and send it to the device. For example, if a user requests an explanation for the question "What is 2 + 2?", an explanation such as "This is a basic addition problem, and adding 2 to another 2 makes 4" will be generated and displayed.

[0381] Automatically identify stumbling blocks and provide explanations

[0382] The server analyzes the user's answer history, automatically identifies the areas where the user has trouble, generates explanations for those areas, and sends them to the device. This allows the user to receive appropriate explanations for the parts they do not understand. For example, if the user incorrectly answers "2 + 2 = 5," an explanation based on the theme of "the basics of addition" is provided.

[0383] Introducing the Emotion Engine

[0384] User emotion recognition

[0385] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. If the user is feeling irritated by a problem, the emotion engine will recognize this as "stress."

[0386] Adjusting for problems based on emotional state

[0387] The server adjusts the difficulty of the questions based on the user's emotional state. For example, if the user is feeling stressed, it will provide easier questions to help them relax and learn.

[0388] Adjusting commentary based on emotional state

[0389] The server takes into account the user's emotional state and adjusts the optimal explanation content and presentation method: if the user is confused, a more detailed and easy-to-understand explanation will be provided.

[0390] Real-time emotion monitoring and response

[0391] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed. For example, if the user is feeling very stressed, a message urging them to take a break will be sent.

[0392] Specific prompt examples

[0393] Below are some example prompts to use as input to a generative AI model:

[0394] Please provide a detailed explanation for the problem "What is 2 + 2?". Explain in simple terms so that users can understand, and include examples where necessary.

[0395]

[0396] Generate messages to advise users on how to relax if they are feeling stressed.

[0397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0398] Step 1:

[0399] The user uses the terminal to input the answer to the displayed question. The terminal sends this answer data to the server. The server receives the answer data and prepares to proceed to the next step.

[0400] Specifically, the user enters "4" in response to the question "What is 2+2?", and the device sends this answer data to the server. The server receives this input and saves it as answer data.

[0401] Step 2:

[0402] The server uses an artificial intelligence model to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[0403] Specifically, the server sends the answer data "4" to the AI ​​model. Based on this input, the AI ​​model determines that "4" is the correct answer and generates the output "correct answer."

[0404] Step 3:

[0405] The server updates the user's learning level based on the correctness of the answer. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level.

[0406] Specifically, the server receives the "correct" result and checks the user's learning level. If the initial learning level is "easy," it generates an output to update the learning level to "medium."

[0407] Step 4:

[0408] The server generates new questions based on the updated learning level, selects appropriate questions from a pre-prepared question bank, and sends them to the terminal, which then displays the new questions to the user.

[0409] Specifically, the server selects the problem "Please explain the process of photosynthesis" from the "medium" level problems. The server sends this problem to the terminal, and the terminal generates an output that displays the problem.

[0410] Step 5:

[0411] If the user requests an explanation, the server uses artificial intelligence to generate an explanation for the problem and send it to the terminal.

[0412] Specifically, the user presses the "Request Explanation" button, and the device sends the requested data to the server. The server generates an explanation for the problem "What is 2 + 2?", saying "This is a basic addition problem, adding 2 to another 2 gives you 4," and sends the output to the device.

[0413] Step 6:

[0414] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the areas where the user is having trouble. The server generates an explanation for that area and sends it to the terminal.

[0415] Specifically, the server analyzes the user's answer history and determines that the user mistakenly thought "2+2=5." The server then generates an explanation about the "basics of addition" and sends it to the terminal.

[0416] Step 7:

[0417] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. The server then adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state.

[0418] Specifically, the server analyzes facial images captured by a camera and audio data recorded by a microphone to determine whether the user is feeling stressed. The server then generates an output to send to the device, such as "asking simple questions to help the user relax."

[0419] (Application example 2)

[0420] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0421] Conventional learning support systems do not adequately adjust feedback and tasks according to the user's learning level and emotional state, which can result in insufficient learning effectiveness.In particular, when training employees in factories, real-time feedback and emotional recognition are required, but current systems have problems meeting these requirements.

[0422] 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.

[0423] In this invention, the server includes means for receiving answers entered by a user to determine the user's learning level, means for determining whether the user's answers are correct using a machine learning model for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for recognizing the user's emotional state and adjusting the difficulty of the questions and explanations based on the emotional state. This makes it possible to provide learning content and feedback optimized for the user's learning level and emotional state, thereby improving the efficiency and effectiveness of employee training.

[0424] "User" refers to an individual or employee who uses the system to learn or train.

[0425] "Learning level" is an indicator of the user's current level of knowledge and skills.

[0426] An "answer" is a response entered by a user to a question presented to them.

[0427] A "machine learning model" is an artificial intelligence algorithm that learns from data and makes predictions and classifications.

[0428] "Correctness" is the standard for evaluating whether a user's answer is correct or incorrect.

[0429] "Updating" means updating the user's learning level and other information to the latest version.

[0430] A "new problem" is the next task or question the system generates based on your updated learning level.

[0431] "Present" refers to the act of the system displaying information or issues to the user.

[0432] "Emotional state" indicates the type and intensity of the emotion the user is feeling.

[0433] "Recognizing" means that the system can distinguish and understand the user's emotional state.

[0434] "Tuning" means changing system settings and question content to optimize the user's learning experience.

[0435] "Feedback" refers to the evaluation and advice the system provides to the user.

[0436] "Training" refers to learning activities that enable employees in a factory to acquire the skills and knowledge necessary for their work.

[0437] The in-factory training support system, which is an application example of the present invention, is implemented in the following steps.

[0438] Hardware used:

[0439] Factory robots: Used as an interface to provide training guidance and feedback.

[0440] Server: A central computing resource responsible for data processing and management.

[0441] Emotion-aware cameras and microphones: Used to analyze employees' facial expressions and voices to recognize their emotional state in real time (e.g., Logitech Brio 4K camera, Microsoft Surface headphones).

[0442] Software used:

[0443] Machine learning models (e.g., TensorFlow, PyTorch): Used to determine whether an answer is correct or incorrect and update the learning level.

[0444] Emotion recognition software (e.g., Affectiva): Used to analyze employees' emotional states.

[0445] Generative explanation models (e.g., GPT-4): Used to generate explanations and provide feedback.

[0446] User interface (e.g. smartphone app, tablet app): Used by employees to interact with the training system.

[0447] Data processing and calculation procedures:

[0448] 1. Receiving Answers:

[0449] The factory robot sends the work performed and answers given by employees as part of their training to a server.

[0450] Example: { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}

[0451] 2. True or False:

[0452] The server uses machine learning models to assess the accuracy of the answers and the quality of the work.

[0453] Example: { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}

[0454] 3. Learning Level Update:

[0455] The server updates the user's learning level based on the evaluation results.

[0456] Example: { "user_id": "12345", "new_level": "medium"}

[0457] 4. Generate a new problem:

[0458] Generate new training content and questions according to updated learning levels.

[0459] Example: { "user_id": "12345", "new_tasks": ["task_next_medium"]}

[0460] 5. Emotion recognition:

[0461] Real-time data is collected from emotion recognition cameras and microphones to analyze emotional states.

[0462] Example: { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}

[0463] 6. Real-time support:

[0464] The server adjusts messages and training content depending on the emotional state and provides feedback through the robot.

[0465] Example: { "user_id": "12345", "message": "Take a short break and relax!"}

[0466] Examples and prompts:

[0467] Did your employees assemble the parts correctly?

[0468] Prompt: "Evaluate the task completion: \nTask: assemble_part \nUser answer: correct \nReminder: Provide feedback accordingly."

[0469] In this way, the system provides highly personalized learning content and feedback based on the user's learning level and emotional state, maximizing the efficiency and effectiveness of training.

[0470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0471] Step 1:

[0472] Receiving answers

[0473] Input: Work details and response data entered by users (employees) through factory robots.

[0474] How it works: Factory robots capture employees' actions and responses and send them to a server.

[0475] Data Calculation: The server parses the received data and converts it into the appropriate format.

[0476] Output: The converted answer data (e.g., { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}).

[0477] Step 2:

[0478] True or false

[0479] Input: The answer data generated in step 1.

[0480] How it works: The server uses a machine learning model (e.g., TensorFlow or PyTorch) to evaluate the user's answer.

[0481] Data calculation: The AI ​​model determines the accuracy of the answer and the quality of the work.

[0482] Output: Verification result (e.g., { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}).

[0483] Step 3:

[0484] Learning Level Update

[0485] Input: The result of step 2.

[0486] How it works: The server updates the learning level based on the user's evaluation results.

[0487] Data calculation: Applying algorithms to update the learning level.

[0488] Output: Updated learning level (e.g. { "user_id": "12345", "new_level": "medium"}).

[0489] Step 4:

[0490] Creating a new problem

[0491] Input: The learning level updated in step 3.

[0492] How it works: The server generates new training content and questions.

[0493] Data Computing: Using AI models to create questions of appropriate difficulty based on updated learning levels.

[0494] Output: The new problem data (e.g. { "user_id": "12345", "new_tasks": ["task_next_medium"]}).

[0495] Step 5:

[0496] emotion recognition

[0497] Input: Real-time data from camera and microphone for emotion recognition.

[0498] How it works: The server uses emotion recognition software (e.g., Affectiva) to analyze the user's emotional state.

[0499] Data calculation: Analyzes camera and microphone data to determine emotional state.

[0500] Output: Emotional state data (e.g., { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}).

[0501] Step 6:

[0502] Real-time support

[0503] Input: New problem data from step 4 and emotional state data from step 5.

[0504] Behavior: The server will provide feedback and adjustments as needed based on the emotional state.

[0505] Data calculations: Analyze emotional state data and tailor appropriate messages and problem content.

[0506] Output: Feedback data (e.g., { "user_id": "12345", "message": "Take a short break and relax!"}).

[0507] The above is the flow of specific processing steps of the system that realizes the application example.

[0508] 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.

[0509] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0510] 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.

[0511] [Second embodiment]

[0512] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0513] 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.

[0514] 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).

[0515] 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.

[0516] 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.

[0517] 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).

[0518] 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.

[0519] 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.

[0520] 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.

[0521] 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.

[0522] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0523] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0524] The present invention is a learning support system that determines a user's learning level and provides appropriate questions. This system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions appropriate to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[0525] System configuration

[0526] 1. Receiving the user's answer

[0527] The user uses a terminal to access the system and input answers to the questions presented.

[0528] The server receives the user's answer and proceeds to the next step.

[0529] 2. Evaluating your answers

[0530] The server uses artificial intelligence to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[0531] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[0532] 3. Update user learning level

[0533] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[0534] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[0535] 4. Creating new problems

[0536] The server generates new questions according to the user's updated learning level.

[0537] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[0538] 5. Providing commentary

[0539] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[0540] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[0541] 6. Automatic detection of stumbling blocks and provision of explanations

[0542] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[0543] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[0544] Specific examples

[0545] 1. User accesses the system for the first time

[0546] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[0547] 2. New questions

[0548] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[0549] 3. Requesting and Providing Explanations

[0550] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[0551] 4. Automatic detection of stumbling blocks

[0552] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[0553] As described above, according to the present invention, it is possible to provide questions and explanations that are optimal for the user's learning progress, thereby significantly improving learning efficiency.

[0554] The processing flow will be explained below.

[0555] Step 1:

[0556] A user accesses the system using a terminal, which presents the user with a welcome or login screen.

[0557] Step 2:

[0558] When the user enters the answer to the question on the terminal and presses the send button, the answer data is sent to the server.

[0559] Step 3:

[0560] The server receives the answer data sent from the device and extracts the user ID and answer content.

[0561] Step 4:

[0562] The server uses artificial intelligence to evaluate the user's answers, using pre-trained data to determine whether the answers are correct or incorrect.

[0563] Step 5:

[0564] The server updates the user's learning level based on the evaluation of the answer (correct or incorrect), for example, raising the level if the answer is correct and lowering the level if the answer is incorrect.

[0565] Step 6:

[0566] The server selects or generates the next questions based on the user's updated learning level. Questions are either selected from a database or newly generated using artificial intelligence.

[0567] Step 7:

[0568] The server sends the selected or generated questions to the terminal and displays them to the user.

[0569] Step 8:

[0570] When a user requests an explanation for a problem, the terminal sends an explanation request to the server.

[0571] Step 9:

[0572] The server receives the explanation request and generates an explanation using artificial intelligence based on the user's current learning level and the requested problem.

[0573] Step 10:

[0574] The server sends the generated commentary to the terminal and displays it to the user.

[0575] Step 11:

[0576] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically determines where the user is having trouble.

[0577] Step 12:

[0578] The server uses artificial intelligence to generate an explanation for the problem, sends the explanation to the terminal, and displays it to the user.

[0579] The above is the specific process flow for presenting questions according to the user's learning level and providing explanations as needed.

[0580] Example 1

[0581] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0582] Conventional learning support systems have difficulty providing appropriate questions according to the user's learning level or providing specific explanations for the user's stumbling points, which can lead to reduced learning efficiency. The present invention aims to support efficient learning by providing questions optimized for the user's learning level, identifying the areas where the user is stumbling, and providing appropriate explanations.

[0583] 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.

[0584] In this invention, the server includes means for receiving the user's answers at the terminal and transmitting them to the server, means for determining whether the answers are correct using artificial intelligence, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for automatically determining where the user is having difficulty and providing explanations for those parts. This allows the user to receive questions and explanations that are optimal for their learning progress, thereby improving the efficiency of their learning.

[0585] "Terminal" means an electronic device through which a user accesses the system and inputs answers to questions.

[0586] The "server" is a central computer that processes answers received from users and operates the entire learning support system, including evaluating questions, updating learning levels, and generating new questions.

[0587] "Artificial intelligence" refers to technology that includes advanced algorithms and databases used to evaluate user answers, generate explanations, and automatically identify stumbling blocks.

[0588] "Correctness of answer" is an evaluation result that indicates whether the answer entered by the user is correct for the presented question.

[0589] "Learning level" is an indicator that shows the user's current state according to their knowledge and understanding, and is used to determine the difficulty of the questions the system presents.

[0590] A "new problem" is the next learning task that is generated based on the user's learning level.

[0591] "Explanation" is additional explanation or information provided to help users better understand a particular issue.

[0592] "Trouble spots" refer to areas where users have made many incorrect answers or lacked understanding in their past answers to questions.

[0593] A "question generation module" is a program with a series of functions for extracting questions from a database or generating new questions appropriate to the user's learning level.

[0594] The "explanation generation module" is a program that uses artificial intelligence to generate explanations for problems and provide them to users in an easy-to-understand format.

[0595] MODE FOR CARRYING OUT THE INVENTION

[0596] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions according to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[0597] System configuration

[0598] 1. Receiving the user's answer

[0599] The user uses a terminal to access the system and input answers to the questions presented.

[0600] The device receives the user's input and sends it to the server, which records the received answers.

[0601] 2. Evaluating your answers

[0602] The server uses artificial intelligence (AI) to determine whether the answer is correct or not. The server first passes the answer data to the evaluation module.

[0603] The evaluation module references a pre-trained database and uses an algorithm to analyze the answers.

[0604] For example, if a user answers "4" to the question "What is 2+2?", the server will determine this as the correct answer.

[0605] 3. Update user learning level

[0606] The server performs a process to update the user's learning level based on the evaluation result of the answer.

[0607] The server first retrieves the user's current learning level from the database, then applies the update logic based on the new assessment results.

[0608] For example, if a user with a learning level of "easy" answers a question correctly, the server updates the learning level to "medium."

[0609] 4. Creating new problems

[0610] The server generates new questions based on the updated learning level using a question generation module.

[0611] The question generation module selects questions from a database appropriate for the user's learning level or generates new questions.

[0612] For example, a user with a learning level of "medium" might be asked the question "Please explain the process of photosynthesis."

[0613] 5. Providing commentary

[0614] When a user requests an explanation for a specific question, the server generates the explanation using artificial intelligence. The server first sends a request to the explanation generation module.

[0615] The explanation generation module creates a detailed explanation of the question and forms a document to be provided to the user.

[0616] For example, in response to the question "What is 2 + 2?", it generates an explanation such as "This problem is a basic addition problem, where 2 added to another 2 equals 4."

[0617] 6. Automatic detection of stumbling blocks and provision of explanations

[0618] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[0619] The server first inputs the answer history into an analysis algorithm, which identifies which questions the user gets wrong the most.

[0620] For the identified stumbling points, the server again uses the explanation generation module to create appropriate explanations and provide them to the user.

[0621] Specific examples

[0622] 1. When you receive your answer

[0623] When a user types "4" into a "2+2" problem on a terminal, the terminal sends the answer to the server, which records the answer in a database.

[0624] 2. Evaluating your answers

[0625] The server retrieves the answer "4" from the database and passes it to the evaluation module. The evaluation module checks whether it matches the correct answer "4" in the database and returns the result to the server. The server stores the result as the "correct answer."

[0626] 3. Learning Level Update

[0627] The server retrieves the user's current learning level as "easy" from the database and updates it to "medium" based on the new evaluation results.

[0628] 4. Creating new problems

[0629] The server searches the database for questions suitable for the "medium" level and sends the question "Please explain the process of photosynthesis" to the user.

[0630] 5. Providing commentary

[0631] When a user requests an explanation, the server sends a request to the explanation generation module, which generates an explanation such as "2 + 2 is a basic addition problem and the answer is 4" and provides it to the user.

[0632] 6. Automatic detection of stumbling blocks and provision of explanations

[0633] The server analyzes the user's answer history and detects if the user has made consecutive mistakes on any of the questions. Using this result, it generates an explanation for the relevant part and provides it to the user.

[0634] In this way, each component of the system works in tandem to provide questions and explanations that are optimal for the user's learning progress, significantly improving learning efficiency.

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Step 1:

[0637] Receiving user answers

[0638] Users access the system using a terminal and enter answers to questions presented to them. The terminal receives the user's input and sends it to the server.

[0639] Input: The answer entered by the user into the device (e.g., "4" as the answer to "2+2")

[0640] Output: User's answer data sent to the server

[0641] Step 2:

[0642] Evaluating answers

[0643] The server uses artificial intelligence (AI) to determine whether the answer data is correct or not. First, the answer data is passed to the evaluation module.

[0644] Input: User's answer data received by the server

[0645] Data processing / data calculation: The evaluation module refers to a database that has been previously trained, compares the answer with the correct data, and determines whether it is correct or incorrect.

[0646] Output: The answer is judged as "correct" or "incorrect".

[0647] Step 3:

[0648] Update user learning level

[0649] The server updates the user's learning level based on the evaluation of the answer. First, it retrieves the user's current learning level from the database. Then it applies the update logic based on the new evaluation result.

[0650] Input: The user's current learning level and the evaluation result of the answer

[0651] Data processing / data calculation: Based on the new assessment results, the user's learning level is updated appropriately (e.g., from "easy" to "medium").

[0652] Output: Updated user learning level

[0653] Step 4:

[0654] Creating a new problem

[0655] The server generates new questions based on the updated learning level. Using the question generation module, the server selects questions from the database that are appropriate for the user's learning level, or generates new questions.

[0656] Input: Updated user learning level

[0657] Data processing / data calculation: The problem generation module selects or generates appropriate problems from the database and presents them to the user.

[0658] Output: New question (e.g., "Describe the process of photosynthesis.")

[0659] Step 5:

[0660] Providing commentary

[0661] When a user requests an explanation for a specific question, the server uses artificial intelligence to generate an explanation and sends a request to the explanation generation module to create a detailed explanation.

[0662] Input: A request from a user asking for clarification on a specific question.

[0663] Data processing / data calculation: The explanation generation module creates a detailed explanation of the relevant question and forms a document to be provided to the user.

[0664] Output: Generated explanation (e.g. "2 + 2 is a basic addition problem, adding 2 to another 2 makes 4")

[0665] Step 6:

[0666] Automatically identify stumbling blocks and provide explanations

[0667] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[0668] Input: User's answer history

[0669] Data processing / data calculation: AI algorithms analyze answer history and identify which questions users get wrong most often, generating explanations for identified stumbling blocks.

[0670] Output: Identified stumbling blocks and their explanations

[0671] The above are the specific processing steps of the program of this system, including input, data processing, data calculation, and output at each step.

[0672] (Application example 1)

[0673] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0674] In recent years, demand for online learning platforms has increased, creating a need for personalized learning experiences for each user. However, many systems are unable to effectively provide questions and explanations tailored to the user's learning level, making it difficult to improve learning efficiency. In particular, there is a lack of intelligent systems that can automatically identify where users are struggling and provide appropriate explanations. Given these factors, it is necessary to provide a system that improves learning efficiency by providing users with appropriate learning questions and explanations in real time and visually displaying their learning progress.

[0675] 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.

[0676] In this invention, the server includes means for receiving answers entered by a user, means for determining whether the user's answers are correct or incorrect using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for visually displaying the user's learning progress. This makes it possible to provide users with personalized study questions and explanations in real time, thereby improving their learning efficiency.

[0677] "User" refers to an individual or organization that uses the system to answer study questions.

[0678] "Answer" refers to the answer entered by the user in response to the presented study question.

[0679] "Means for receiving" refers to the mechanism and process for capturing user-entered answers on the server.

[0680] "Artificial intelligence" refers to a program or system that uses machine learning or deep learning techniques to evaluate a user's answers and generate appropriate questions and explanations.

[0681] "Means for determining correctness" refers to a mechanism that uses artificial intelligence to determine whether a user's answer is correct or incorrect.

[0682] "Learning level" refers to an indicator that shows the user's current academic ability and level of understanding.

[0683] "Means for updating" refers to a mechanism that appropriately changes the user's learning level based on the evaluation of the answers.

[0684] "Means for generating questions" refers to a mechanism for creating appropriate learning questions according to the user's learning level and presenting them to the user.

[0685] "Visual display means" refers to mechanisms that show users their learning progress and outcomes in visual formats such as graphs and dashboards.

[0686] "Means for generating explanations" refers to a mechanism that uses artificial intelligence to create explanations for parts that the user does not understand.

[0687] "Generative AI model" refers to an advanced machine learning algorithm or model used to generate explanations, questions, etc.

[0688] A "prompt" refers to an instruction or question that is input into a generative AI model.

[0689] "Trouble spots" refer to points where users had difficulty answering questions or where they did not fully understand the questions.

[0690] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user in real time, evaluates the answers using artificial intelligence, and updates the user's learning level. It then generates new, appropriate questions based on the updated learning level and presents them to the user. It can also provide explanations when the user requests an explanation for a specific question or when it automatically identifies an area where the user is having difficulty.

[0691] System configuration and operation

[0692] The system mainly consists of a server and a user terminal. The server plays a central role in analyzing users' learning activities and providing appropriate feedback. The user terminal provides an interface for users to answer learning questions and receive feedback.

[0693] 1. Receiving the user's answer

[0694] Users access the learning support system using their own devices (e.g., smartphones, tablets, PCs), enter answers to questions, and these answers are sent to and received from the server.

[0695] 2. Evaluating your answers

[0696] The server uses artificial intelligence, especially generative AI models (e.g., GPT-4), to determine whether a user's answer is correct. For example, if a user answers "4" to a simple arithmetic problem like "What is 2 + 2?", the answer is considered correct.

[0697] 3. Learning Level Update

[0698] The server updates the user's learning level based on the evaluation of the answer. For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[0699] 4. Creating new problems

[0700] The server generates new questions based on the updated learning level and presents them to the user. A user with a learning level of "medium" will be provided with a medium-level question such as "Please explain the process of photosynthesis."

[0701] 5. Visual display of learning progress

[0702] Users' learning progress is displayed visually in the form of dashboards and graphs, allowing them to see their progress at a glance, making it easier for users to understand their own learning progress.

[0703] 6. Commentary

[0704] When a user requests an explanation for a specific problem, the server uses the generative AI model to generate a detailed explanation for the problem and provide it to the user. An example of a prompt sentence to generate is "Explain the process of photosynthesis in plants."

[0705] 7. Automatic detection of stumbling blocks and provision of explanations

[0706] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the part where the user is having trouble. Then, it generates an explanation for that part using a generative AI model and provides it to the user. An example of a specific prompt is "Explain where common mistakes occur in solving quadratic equations."

[0707] This not only allows users to study efficiently, but also provides timely support for difficult-to-understand parts. In addition, by intuitively understanding their learning progress, they can study more systematically.

[0708] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0709] Step 1:

[0710] The user accesses the learning support system and inputs answers to the learning questions.

[0711] Input: The user enters the answer to the question (e.g., "4") into the terminal.

[0712] How it works: The device sends user input to the server in real time.

[0713] Output: The server receives the user's answer data.

[0714] Step 2:

[0715] The server evaluates the received answers using artificial intelligence (generative AI model).

[0716] Input: The user's answer data received by the server.

[0717] How it works: A generative AI model (e.g., GPT-4) analyzes the answer data and determines whether the answer is correct. For example, the answer "4" to the question "What is 2 + 2?" is determined to be correct.

[0718] Output: The server obtains the evaluation result (correct / incorrect).

[0719] Step 3:

[0720] Based on the result of the correct / incorrect judgment, the server updates the user's learning level.

[0721] Input: The evaluation result obtained by the server.

[0722] How it works: The server checks the user's current learning level based on the assessment results and upgrades or downgrades the level as necessary. For example, if a user answers correctly at the initial "easy" level, they will be upgraded to "medium" level.

[0723] Output: Updated user learning level information.

[0724] Step 4:

[0725] The server generates new questions based on the updated learning level and presents them to the user.

[0726] Input: Updated learning level information.

[0727] How it works: Using a generative AI model, the server generates appropriate questions, such as "Please explain the process of photosynthesis" for a "medium" level user.

[0728] Output: A new training problem.

[0729] Step 5:

[0730] The server presents the user with a new problem.

[0731] Input: A new study question.

[0732] Operation: The generated question is sent to the user's terminal, which displays it.

[0733] Output: User sees new issue.

[0734] Step 6:

[0735] The server visually displays the user's learning progress.

[0736] Input: Updated learning level information and answer history.

[0737] How it works: The server uses this information to generate a dashboard and graphs of the user's progress.

[0738] Output: Visually displayed learning progress data.

[0739] Step 7:

[0740] When a user requests an explanation for a particular problem, the server generates the explanation using a generative AI model.

[0741] Input: User clarification request and applicable problem information.

[0742] How it works: An appropriate prompt (e.g., "Explain the process of photosynthesis in plants.") is input into the generative AI model to generate an explanation.

[0743] Output: The generated commentary.

[0744] Step 8:

[0745] The server presents the generated explanation to the user.

[0746] Input: The generated description.

[0747] What it does: Sends a description to the user's terminal, which displays it.

[0748] Output: User checks the explanation.

[0749] Step 9:

[0750] Even if the user does not request an explanation, the server automatically identifies the user's stumbling block and generates an explanation using a generative AI model.

[0751] Input: User's answer history and stumbling block information.

[0752] How it works: Enter an appropriate prompt (e.g., "Explain where common mistakes occur in solving quadratic equations.") into the generative AI model to generate an explanation.

[0753] Output: The generated commentary.

[0754] Step 10:

[0755] The server provides the user with an explanation of the problem.

[0756] Input: The generated description.

[0757] What it does: Sends a description to the user's terminal, which displays it.

[0758] Output: User checks the explanation.

[0759] 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.

[0760] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[0761] System configuration

[0762] 1. Receiving the user's answer

[0763] The user uses a terminal to access the system and input answers to the questions presented.

[0764] The server receives the user's answer and proceeds to the next step.

[0765] 2. Evaluating your answers

[0766] The server uses artificial intelligence to determine whether the user's answer is correct or not, using a pre-trained database and evaluation algorithms.

[0767] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[0768] 3. Update user learning level

[0769] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[0770] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[0771] 4. Creating new problems

[0772] The server generates new questions according to the user's updated learning level.

[0773] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[0774] 5. Providing commentary

[0775] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[0776] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[0777] 6. Automatic detection of stumbling blocks and provision of explanations

[0778] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[0779] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[0780] Introducing the Emotion Engine

[0781] 1. User Emotion Recognition

[0782] The server uses the camera and microphone installed on the user's device to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state.

[0783] For example, if a user is feeling frustrated about a problem, the emotion engine will recognize this as "stress."

[0784] 2. Adjusting problems based on emotional state

[0785] The server adjusts the difficulty and content of the questions based on the user's emotional state.

[0786] For example, if a user is feeling stressed, the system will provide a relaxed learning environment by presenting them with slightly easier questions.

[0787] 3. Adjusting commentary based on emotional state

[0788] The server provides commentary according to the user's emotional state.

[0789] For example, if a user is confused, provide a more detailed and understandable explanation.

[0790] 4. Real-time emotion monitoring and response

[0791] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed.

[0792] For example, if a user is feeling very stressed, a message will be sent encouraging them to take a break.

[0793] Specific examples

[0794] 1. User accesses the system for the first time

[0795] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[0796] In addition, the system evaluates the user's emotions and, if it determines that the user is not feeling stressed, presents a more difficult question next.

[0797] 2. New questions and emotional responses

[0798] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[0799] If the user begins to get confused by a question, the emotion engine will recognize this and the server will simplify the problem or add a detailed explanation.

[0800] 3. Requesting and Providing Explanations

[0801] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[0802] If the user appears calm and understanding, we will provide additional explanations of more complex content.

[0803] 4. Automatic detection of stumbling blocks

[0804] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[0805] If the user is stressed about a particular issue, add advice to help ease that stress.

[0806] The present invention provides questions and explanations that are optimal for the user's learning progress and emotional state, thereby significantly improving learning efficiency.

[0807] The processing flow will be explained below.

[0808] Step 1:

[0809] A user accesses the system using a terminal, which presents the user with a login or welcome screen.

[0810] Step 2:

[0811] The user enters the answer to the question on the device and presses the send button, which sends the answer data to the server.

[0812] Step 3:

[0813] The server analyzes the answer data received from the device and extracts the user ID and answer content.

[0814] Step 4:

[0815] The server uses artificial intelligence to evaluate the accuracy of the user's answer. For example, if the answer is "4", it will be evaluated as "correct".

[0816] Step 5:

[0817] The server updates the user's learning level based on the evaluation results: if the answer is correct, the level is raised; if the answer is incorrect, the level is lowered.

[0818] Step 6:

[0819] The server selects or generates the next questions based on the updated learning level, either retrieved from a database or created using artificial intelligence.

[0820] Step 7:

[0821] The server sends the generated or selected questions to the terminal and displays them to the user.

[0822] Step 8:

[0823] If the user experiences difficulty with a problem, the emotion engine uses the device's camera and microphone to analyze the user's emotional state in real time, for example, by analyzing facial expressions and evaluating voice tone.

[0824] Step 9:

[0825] The emotion engine determines the user's emotional state, and if it detects negative emotions such as stress or confusion, it sends that information to the server.

[0826] Step 10:

[0827] The server adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state. For example, if the user is feeling stressed, the questions will be made slightly easier.

[0828] Step 11:

[0829] When a user requests an explanation for a particular question, the terminal sends an explanation request to the server.

[0830] Step 12:

[0831] The server receives the explanation request and generates an explanation using artificial intelligence, taking into account the user's learning level and emotional state.

[0832] Step 13:

[0833] The server sends the generated explanation to the terminal and displays it to the user. For example, the explanation for "What is 2 + 2?" is "This is a basic addition problem, adding 2 to another 2 gives you 4."

[0834] Step 14:

[0835] Even if the user does not request an explanation, the server will analyze the answer history and automatically determine the areas where the user has trouble.

[0836] Step 15:

[0837] The server uses artificial intelligence to generate explanations for the stumbling blocks and presents them to the user. For example, if a user repeatedly makes mistakes on a particular problem, the server will provide a detailed explanation for that problem.

[0838] Step 16:

[0839] The system monitors the user's emotional state in real time, and if the user feels severe stress, the server sends a message to the device recommending relaxation advice or a break.

[0840] In this way, a system is constructed in which the server, terminal, and user cooperate to provide a learning experience that is optimal for the user's learning progress and emotional state.

[0841] Example 2

[0842] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0843] Conventional learning support systems judge whether a user's answers are correct and update their learning level, but do not adjust their level based on the user's emotional state, which can lead to reduced learning efficiency. Another issue is that they do not provide appropriate support even when the user does not request explanations. Furthermore, if questions and explanations are not adjusted based on the user's emotional state, this can affect the user's motivation and level of understanding.

[0844] 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.

[0845] In this invention, the server includes means for receiving answers entered by the user, means for determining whether the user's answers are correct using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, means for analyzing the user's facial expressions and voice using a sensor on the device and determining the user's emotional state using an emotion engine in order to recognize the user's emotional state, means for adjusting the difficulty of the questions based on the user's emotional state, and means for adjusting the content and presentation method of the explanations based on the user's emotional state. This allows the server to present appropriate questions and explanations to the user, improving the learning experience according to the user's emotional state.

[0846] "User learning level" is an index of the user's knowledge and skill proficiency.

[0847] The "means for receiving answers" refers to a mechanism for transferring answers entered by the user from the terminal to the server and acquiring the data.

[0848] The "means for determining whether the answer is correct" is a system that uses artificial intelligence to determine whether the user's answer is correct or incorrect.

[0849] The "means for updating the learning level" is a mechanism for changing the user's current learning level based on whether the user's answer is correct or incorrect.

[0850] "Means for generating questions and presenting them to the user" refers to a mechanism that creates new questions based on the user's learning level and displays them on the screen for the user.

[0851] The "means for recognizing emotional states" is a mechanism that uses the device's sensors to collect and analyze the user's emotional responses, such as facial expressions and voice, and then identifies the user's emotions using an emotion engine.

[0852] The "means for adjusting the difficulty of questions based on the emotional state" is a mechanism for appropriately changing the difficulty of questions presented in accordance with the recognized emotional state of the user.

[0853] The "means for adjusting the content and presentation method of the commentary based on the emotional state" is a mechanism for adjusting the optimal content and presentation method of the commentary taking into account the emotional state of the user.

[0854] MODE FOR CARRYING OUT THE INVENTION

[0855] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[0856] System configuration

[0857] Receiving user answers

[0858] A user uses a terminal to access the system and input answers to the questions presented. The terminal sends this answer data to the server. The server receives the answer data and prepares it for the next process. For example, if a user inputs "4" in response to the question "What is 2+2?", that data is sent to the server.

[0859] Evaluating answers

[0860] The server uses artificial intelligence to determine whether the user's answer is correct. The AI ​​uses a pre-trained database and evaluation algorithm to do this. Specifically, the server sends the answer data "4" to the AI ​​model, and the AI ​​model determines that "4" is the correct answer.

[0861] Update user learning level

[0862] The server updates the user's learning level based on whether the answer is correct or incorrect. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level. For example, if a user whose initial learning level is "easy" answers correctly, the level is updated to "medium."

[0863] Creating a new problem

[0864] The server generates new questions based on the updated learning level. At this time, it selects appropriate questions from a pre-prepared question bank and sends them to the device. The device then displays the new questions to the user. For example, a user at the "medium" level might be presented with the question "Please explain the process of photosynthesis."

[0865] Providing commentary

[0866] If a user requests an explanation, the server uses artificial intelligence to generate a detailed explanation for the problem and send it to the device. For example, if a user requests an explanation for the question "What is 2 + 2?", an explanation such as "This is a basic addition problem, and adding 2 to another 2 makes 4" will be generated and displayed.

[0867] Automatically identify stumbling blocks and provide explanations

[0868] The server analyzes the user's answer history, automatically identifies the areas where the user has trouble, generates explanations for those areas, and sends them to the device. This allows the user to receive appropriate explanations for the parts they do not understand. For example, if the user incorrectly answers "2 + 2 = 5," an explanation based on the theme of "the basics of addition" is provided.

[0869] Introducing the Emotion Engine

[0870] User emotion recognition

[0871] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. If the user is feeling irritated by a problem, the emotion engine will recognize this as "stress."

[0872] Adjusting for problems based on emotional state

[0873] The server adjusts the difficulty of the questions based on the user's emotional state. For example, if the user is feeling stressed, it will provide easier questions to help them relax and learn.

[0874] Adjusting commentary based on emotional state

[0875] The server takes into account the user's emotional state and adjusts the optimal explanation content and presentation method: if the user is confused, a more detailed and easy-to-understand explanation will be provided.

[0876] Real-time emotion monitoring and response

[0877] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed. For example, if the user is feeling very stressed, a message urging them to take a break will be sent.

[0878] Specific prompt examples

[0879] Below are some example prompts to use as input to a generative AI model:

[0880] Please provide a detailed explanation for the problem "What is 2 + 2?". Explain in simple terms so that users can understand, and include examples where necessary.

[0881]

[0882] Generate messages to advise users on how to relax if they are feeling stressed.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Step 1:

[0885] The user uses the terminal to input the answer to the displayed question. The terminal sends this answer data to the server. The server receives the answer data and prepares to proceed to the next step.

[0886] Specifically, the user enters "4" in response to the question "What is 2+2?", and the device sends this answer data to the server. The server receives this input and saves it as answer data.

[0887] Step 2:

[0888] The server uses an artificial intelligence model to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[0889] Specifically, the server sends the answer data "4" to the AI ​​model. Based on this input, the AI ​​model determines that "4" is the correct answer and generates the output "correct answer."

[0890] Step 3:

[0891] The server updates the user's learning level based on the correctness of the answer. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level.

[0892] Specifically, the server receives the "correct" result and checks the user's learning level. If the initial learning level is "easy," it generates an output to update the learning level to "medium."

[0893] Step 4:

[0894] The server generates new questions based on the updated learning level, selects appropriate questions from a pre-prepared question bank, and sends them to the terminal, which then displays the new questions to the user.

[0895] Specifically, the server selects the problem "Please explain the process of photosynthesis" from the "medium" level problems. The server sends this problem to the terminal, and the terminal generates an output that displays the problem.

[0896] Step 5:

[0897] If the user requests an explanation, the server uses artificial intelligence to generate an explanation for the problem and send it to the terminal.

[0898] Specifically, the user presses the "Request Explanation" button, and the device sends the requested data to the server. The server generates an explanation for the problem "What is 2 + 2?", saying "This is a basic addition problem, adding 2 to another 2 gives you 4," and sends the output to the device.

[0899] Step 6:

[0900] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the areas where the user is having trouble. The server generates an explanation for that area and sends it to the terminal.

[0901] Specifically, the server analyzes the user's answer history and determines that the user mistakenly thought "2+2=5." The server then generates an explanation about the "basics of addition" and sends it to the terminal.

[0902] Step 7:

[0903] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. The server then adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state.

[0904] Specifically, the server analyzes facial images captured by a camera and audio data recorded by a microphone to determine whether the user is feeling stressed. The server then generates an output to send to the device, such as "asking simple questions to help the user relax."

[0905] (Application example 2)

[0906] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0907] Conventional learning support systems do not adequately adjust feedback and tasks according to the user's learning level and emotional state, which can result in insufficient learning effectiveness.In particular, when training employees in factories, real-time feedback and emotional recognition are required, but current systems have problems meeting these requirements.

[0908] 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.

[0909] In this invention, the server includes means for receiving answers entered by a user to determine the user's learning level, means for determining whether the user's answers are correct using a machine learning model for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for recognizing the user's emotional state and adjusting the difficulty of the questions and explanations based on the emotional state. This makes it possible to provide learning content and feedback optimized for the user's learning level and emotional state, thereby improving the efficiency and effectiveness of employee training.

[0910] "User" refers to an individual or employee who uses the system to learn or train.

[0911] "Learning level" is an indicator of the user's current level of knowledge and skills.

[0912] An "answer" is a response entered by a user to a question presented to them.

[0913] A "machine learning model" is an artificial intelligence algorithm that learns from data and makes predictions and classifications.

[0914] "Correctness" is the standard for evaluating whether a user's answer is correct or incorrect.

[0915] "Updating" means updating the user's learning level and other information to the latest version.

[0916] A "new problem" is the next task or question the system generates based on your updated learning level.

[0917] "Present" refers to the act of the system displaying information or issues to the user.

[0918] "Emotional state" indicates the type and intensity of the emotion the user is feeling.

[0919] "Recognizing" means that the system can distinguish and understand the user's emotional state.

[0920] "Tuning" means changing system settings and question content to optimize the user's learning experience.

[0921] "Feedback" refers to the evaluation and advice the system provides to the user.

[0922] "Training" refers to learning activities that enable employees in a factory to acquire the skills and knowledge necessary for their work.

[0923] The in-factory training support system, which is an application example of the present invention, is implemented in the following steps.

[0924] Hardware used:

[0925] Factory robots: Used as an interface to provide training guidance and feedback.

[0926] Server: A central computing resource responsible for data processing and management.

[0927] Emotion-aware cameras and microphones: Used to analyze employees' facial expressions and voices to recognize their emotional state in real time (e.g., Logitech Brio 4K camera, Microsoft Surface headphones).

[0928] Software used:

[0929] Machine learning models (e.g., TensorFlow, PyTorch): Used to determine whether an answer is correct or incorrect and update the learning level.

[0930] Emotion recognition software (e.g., Affectiva): Used to analyze employees' emotional states.

[0931] Generative explanation models (e.g., GPT-4): Used to generate explanations and provide feedback.

[0932] User interface (e.g. smartphone app, tablet app): Used by employees to interact with the training system.

[0933] Data processing and calculation procedures:

[0934] 1. Receiving Answers:

[0935] The factory robot sends the work performed and answers given by employees as part of their training to a server.

[0936] Example: { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}

[0937] 2. True or False:

[0938] The server uses machine learning models to assess the accuracy of the answers and the quality of the work.

[0939] Example: { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}

[0940] 3. Learning Level Update:

[0941] The server updates the user's learning level based on the evaluation results.

[0942] Example: { "user_id": "12345", "new_level": "medium"}

[0943] 4. Generate a new problem:

[0944] Generate new training content and questions according to updated learning levels.

[0945] Example: { "user_id": "12345", "new_tasks": ["task_next_medium"]}

[0946] 5. Emotion recognition:

[0947] Real-time data is collected from emotion recognition cameras and microphones to analyze emotional states.

[0948] Example: { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}

[0949] 6. Real-time support:

[0950] The server adjusts messages and training content depending on the emotional state and provides feedback through the robot.

[0951] Example: { "user_id": "12345", "message": "Take a short break and relax!"}

[0952] Examples and prompts:

[0953] Did your employees assemble the parts correctly?

[0954] Prompt: "Evaluate the task completion: \nTask: assemble_part \nUser answer: correct \nReminder: Provide feedback accordingly."

[0955] In this way, the system provides highly personalized learning content and feedback based on the user's learning level and emotional state, maximizing the efficiency and effectiveness of training.

[0956] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0957] Step 1:

[0958] Receiving answers

[0959] Input: Work details and response data entered by users (employees) through factory robots.

[0960] How it works: Factory robots capture employees' actions and responses and send them to a server.

[0961] Data Calculation: The server parses the received data and converts it into the appropriate format.

[0962] Output: The converted answer data (e.g., { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}).

[0963] Step 2:

[0964] True or false

[0965] Input: The answer data generated in step 1.

[0966] How it works: The server uses a machine learning model (e.g., TensorFlow or PyTorch) to evaluate the user's answer.

[0967] Data calculation: The AI ​​model determines the accuracy of the answer and the quality of the work.

[0968] Output: Verification result (e.g., { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}).

[0969] Step 3:

[0970] Learning Level Update

[0971] Input: The result of step 2.

[0972] How it works: The server updates the learning level based on the user's evaluation results.

[0973] Data calculation: Applying algorithms to update the learning level.

[0974] Output: Updated learning level (e.g. { "user_id": "12345", "new_level": "medium"}).

[0975] Step 4:

[0976] Creating a new problem

[0977] Input: The learning level updated in step 3.

[0978] How it works: The server generates new training content and questions.

[0979] Data Computing: Using AI models to create questions of appropriate difficulty based on updated learning levels.

[0980] Output: The new problem data (e.g. { "user_id": "12345", "new_tasks": ["task_next_medium"]}).

[0981] Step 5:

[0982] emotion recognition

[0983] Input: Real-time data from camera and microphone for emotion recognition.

[0984] How it works: The server uses emotion recognition software (e.g., Affectiva) to analyze the user's emotional state.

[0985] Data calculation: Analyzes camera and microphone data to determine emotional state.

[0986] Output: Emotional state data (e.g., { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}).

[0987] Step 6:

[0988] Real-time support

[0989] Input: New problem data from step 4 and emotional state data from step 5.

[0990] Behavior: The server will provide feedback and adjustments as needed based on the emotional state.

[0991] Data calculations: Analyze emotional state data and tailor appropriate messages and problem content.

[0992] Output: Feedback data (e.g., { "user_id": "12345", "message": "Take a short break and relax!"}).

[0993] The above is the flow of specific processing steps of the system that realizes the application example.

[0994] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0995] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0996] 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.

[0997] [Third embodiment]

[0998] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0999] 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.

[1000] 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).

[1001] 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.

[1002] 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.

[1003] 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).

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] 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.

[1009] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1010] The present invention is a learning support system that determines a user's learning level and provides appropriate questions. This system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions appropriate to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[1011] System configuration

[1012] 1. Receiving the user's answer

[1013] The user uses a terminal to access the system and input answers to the questions presented.

[1014] The server receives the user's answer and proceeds to the next step.

[1015] 2. Evaluating your answers

[1016] The server uses artificial intelligence to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[1017] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[1018] 3. Update user learning level

[1019] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[1020] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[1021] 4. Creating new problems

[1022] The server generates new questions according to the user's updated learning level.

[1023] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[1024] 5. Providing commentary

[1025] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[1026] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[1027] 6. Automatic detection of stumbling blocks and provision of explanations

[1028] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[1029] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[1030] Specific examples

[1031] 1. User accesses the system for the first time

[1032] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[1033] 2. New questions

[1034] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[1035] 3. Requesting and Providing Explanations

[1036] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[1037] 4. Automatic detection of stumbling blocks

[1038] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[1039] As described above, according to the present invention, it is possible to provide questions and explanations that are optimal for the user's learning progress, thereby significantly improving learning efficiency.

[1040] The processing flow will be explained below.

[1041] Step 1:

[1042] A user accesses the system using a terminal, which presents the user with a welcome or login screen.

[1043] Step 2:

[1044] When the user enters the answer to the question on the terminal and presses the send button, the answer data is sent to the server.

[1045] Step 3:

[1046] The server receives the answer data sent from the device and extracts the user ID and answer content.

[1047] Step 4:

[1048] The server uses artificial intelligence to evaluate the user's answers, using pre-trained data to determine whether the answers are correct or incorrect.

[1049] Step 5:

[1050] The server updates the user's learning level based on the evaluation of the answer (correct or incorrect), for example, raising the level if the answer is correct and lowering the level if the answer is incorrect.

[1051] Step 6:

[1052] The server selects or generates the next questions based on the user's updated learning level. Questions are either selected from a database or newly generated using artificial intelligence.

[1053] Step 7:

[1054] The server sends the selected or generated questions to the terminal and displays them to the user.

[1055] Step 8:

[1056] When a user requests an explanation for a problem, the terminal sends an explanation request to the server.

[1057] Step 9:

[1058] The server receives the explanation request and generates an explanation using artificial intelligence based on the user's current learning level and the requested problem.

[1059] Step 10:

[1060] The server sends the generated commentary to the terminal and displays it to the user.

[1061] Step 11:

[1062] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically determines where the user is having trouble.

[1063] Step 12:

[1064] The server uses artificial intelligence to generate an explanation for the problem, sends the explanation to the terminal, and displays it to the user.

[1065] The above is the specific process flow for presenting questions according to the user's learning level and providing explanations as needed.

[1066] Example 1

[1067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1068] Conventional learning support systems have difficulty providing appropriate questions according to the user's learning level or providing specific explanations for the user's stumbling points, which can lead to reduced learning efficiency. The present invention aims to support efficient learning by providing questions optimized for the user's learning level, identifying the areas where the user is stumbling, and providing appropriate explanations.

[1069] 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.

[1070] In this invention, the server includes means for receiving the user's answers at the terminal and transmitting them to the server, means for determining whether the answers are correct using artificial intelligence, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for automatically determining where the user is having difficulty and providing explanations for those parts. This allows the user to receive questions and explanations that are optimal for their learning progress, thereby improving the efficiency of their learning.

[1071] "Terminal" means an electronic device through which a user accesses the system and inputs answers to questions.

[1072] The "server" is a central computer that processes answers received from users and operates the entire learning support system, including evaluating questions, updating learning levels, and generating new questions.

[1073] "Artificial intelligence" refers to technology that includes advanced algorithms and databases used to evaluate user answers, generate explanations, and automatically identify stumbling blocks.

[1074] "Correctness of answer" is an evaluation result that indicates whether the answer entered by the user is correct for the presented question.

[1075] "Learning level" is an indicator that shows the user's current state according to their knowledge and understanding, and is used to determine the difficulty of the questions the system presents.

[1076] A "new problem" is the next learning task that is generated based on the user's learning level.

[1077] "Explanation" is additional explanation or information provided to help users better understand a particular issue.

[1078] "Trouble spots" refer to areas where users have made many incorrect answers or lacked understanding in their past answers to questions.

[1079] A "question generation module" is a program with a series of functions for extracting questions from a database or generating new questions appropriate to the user's learning level.

[1080] The "explanation generation module" is a program that uses artificial intelligence to generate explanations for problems and provide them to users in an easy-to-understand format.

[1081] MODE FOR CARRYING OUT THE INVENTION

[1082] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions according to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[1083] System configuration

[1084] 1. Receiving the user's answer

[1085] The user uses a terminal to access the system and input answers to the questions presented.

[1086] The device receives the user's input and sends it to the server, which records the received answers.

[1087] 2. Evaluating your answers

[1088] The server uses artificial intelligence (AI) to determine whether the answer is correct or not. The server first passes the answer data to the evaluation module.

[1089] The evaluation module references a pre-trained database and uses an algorithm to analyze the answers.

[1090] For example, if a user answers "4" to the question "What is 2+2?", the server will determine this as the correct answer.

[1091] 3. Update user learning level

[1092] The server performs a process to update the user's learning level based on the evaluation result of the answer.

[1093] The server first retrieves the user's current learning level from the database, then applies the update logic based on the new assessment results.

[1094] For example, if a user with a learning level of "easy" answers a question correctly, the server updates the learning level to "medium."

[1095] 4. Creating new problems

[1096] The server generates new questions based on the updated learning level using a question generation module.

[1097] The question generation module selects questions from a database appropriate for the user's learning level or generates new questions.

[1098] For example, a user with a learning level of "medium" might be asked the question "Please explain the process of photosynthesis."

[1099] 5. Providing commentary

[1100] When a user requests an explanation for a specific question, the server generates the explanation using artificial intelligence. The server first sends a request to the explanation generation module.

[1101] The explanation generation module creates a detailed explanation of the question and forms a document to be provided to the user.

[1102] For example, in response to the question "What is 2 + 2?", it generates an explanation such as "This problem is a basic addition problem, where 2 added to another 2 equals 4."

[1103] 6. Automatic detection of stumbling blocks and provision of explanations

[1104] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[1105] The server first inputs the answer history into an analysis algorithm, which identifies which questions the user gets wrong the most.

[1106] For the identified stumbling points, the server again uses the explanation generation module to create appropriate explanations and provide them to the user.

[1107] Specific examples

[1108] 1. When you receive your answer

[1109] When a user types "4" into a "2+2" problem on a terminal, the terminal sends the answer to the server, which records the answer in a database.

[1110] 2. Evaluating your answers

[1111] The server retrieves the answer "4" from the database and passes it to the evaluation module. The evaluation module checks whether it matches the correct answer "4" in the database and returns the result to the server. The server stores the result as the "correct answer."

[1112] 3. Learning Level Update

[1113] The server retrieves the user's current learning level as "easy" from the database and updates it to "medium" based on the new evaluation results.

[1114] 4. Creating new problems

[1115] The server searches the database for questions suitable for the "medium" level and sends the question "Please explain the process of photosynthesis" to the user.

[1116] 5. Providing commentary

[1117] When a user requests an explanation, the server sends a request to the explanation generation module, which generates an explanation such as "2 + 2 is a basic addition problem and the answer is 4" and provides it to the user.

[1118] 6. Automatic detection of stumbling blocks and provision of explanations

[1119] The server analyzes the user's answer history and detects if the user has made consecutive mistakes on any of the questions. Using this result, it generates an explanation for the relevant part and provides it to the user.

[1120] In this way, each component of the system works in tandem to provide questions and explanations that are optimal for the user's learning progress, significantly improving learning efficiency.

[1121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1122] Step 1:

[1123] Receiving user answers

[1124] Users access the system using a terminal and enter answers to questions presented to them. The terminal receives the user's input and sends it to the server.

[1125] Input: The answer entered by the user into the device (e.g., "4" as the answer to "2+2")

[1126] Output: User's answer data sent to the server

[1127] Step 2:

[1128] Evaluating answers

[1129] The server uses artificial intelligence (AI) to determine whether the answer data is correct or not. First, the answer data is passed to the evaluation module.

[1130] Input: User's answer data received by the server

[1131] Data processing / data calculation: The evaluation module refers to a database that has been previously trained, compares the answer with the correct data, and determines whether it is correct or incorrect.

[1132] Output: The answer is judged as "correct" or "incorrect".

[1133] Step 3:

[1134] Update user learning level

[1135] The server updates the user's learning level based on the evaluation of the answer. First, it retrieves the user's current learning level from the database. Then it applies the update logic based on the new evaluation result.

[1136] Input: The user's current learning level and the evaluation result of the answer

[1137] Data processing / data calculation: Based on the new assessment results, the user's learning level is updated appropriately (e.g., from "easy" to "medium").

[1138] Output: Updated user learning level

[1139] Step 4:

[1140] Creating a new problem

[1141] The server generates new questions based on the updated learning level. Using the question generation module, the server selects questions from the database that are appropriate for the user's learning level, or generates new questions.

[1142] Input: Updated user learning level

[1143] Data processing / data calculation: The problem generation module selects or generates appropriate problems from the database and presents them to the user.

[1144] Output: New question (e.g., "Describe the process of photosynthesis.")

[1145] Step 5:

[1146] Providing commentary

[1147] When a user requests an explanation for a specific question, the server uses artificial intelligence to generate an explanation and sends a request to the explanation generation module to create a detailed explanation.

[1148] Input: A request from a user asking for clarification on a specific question.

[1149] Data processing / data calculation: The explanation generation module creates a detailed explanation of the relevant question and forms a document to be provided to the user.

[1150] Output: Generated explanation (e.g. "2 + 2 is a basic addition problem, adding 2 to another 2 makes 4")

[1151] Step 6:

[1152] Automatically identify stumbling blocks and provide explanations

[1153] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[1154] Input: User's answer history

[1155] Data processing / data calculation: AI algorithms analyze answer history and identify which questions users get wrong most often, generating explanations for identified stumbling blocks.

[1156] Output: Identified stumbling blocks and their explanations

[1157] The above are the specific processing steps of the program of this system, including input, data processing, data calculation, and output at each step.

[1158] (Application example 1)

[1159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1160] In recent years, demand for online learning platforms has increased, creating a need for personalized learning experiences for each user. However, many systems are unable to effectively provide questions and explanations tailored to the user's learning level, making it difficult to improve learning efficiency. In particular, there is a lack of intelligent systems that can automatically identify where users are struggling and provide appropriate explanations. Given these factors, it is necessary to provide a system that improves learning efficiency by providing users with appropriate learning questions and explanations in real time and visually displaying their learning progress.

[1161] 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.

[1162] In this invention, the server includes means for receiving answers entered by a user, means for determining whether the user's answers are correct or incorrect using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for visually displaying the user's learning progress. This makes it possible to provide users with personalized study questions and explanations in real time, thereby improving their learning efficiency.

[1163] "User" refers to an individual or organization that uses the system to answer study questions.

[1164] "Answer" refers to the answer entered by the user in response to the presented study question.

[1165] "Means for receiving" refers to the mechanism and process for capturing user-entered answers on the server.

[1166] "Artificial intelligence" refers to a program or system that uses machine learning or deep learning techniques to evaluate a user's answers and generate appropriate questions and explanations.

[1167] "Means for determining correctness" refers to a mechanism that uses artificial intelligence to determine whether a user's answer is correct or incorrect.

[1168] "Learning level" refers to an indicator that shows the user's current academic ability and level of understanding.

[1169] "Means for updating" refers to a mechanism that appropriately changes the user's learning level based on the evaluation of the answers.

[1170] "Means for generating questions" refers to a mechanism for creating appropriate learning questions according to the user's learning level and presenting them to the user.

[1171] "Visual display means" refers to mechanisms that show users their learning progress and outcomes in visual formats such as graphs and dashboards.

[1172] "Means for generating explanations" refers to a mechanism that uses artificial intelligence to create explanations for parts that the user does not understand.

[1173] "Generative AI model" refers to an advanced machine learning algorithm or model used to generate explanations, questions, etc.

[1174] A "prompt" refers to an instruction or question that is input into a generative AI model.

[1175] "Trouble spots" refer to points where users had difficulty answering questions or where they did not fully understand the questions.

[1176] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user in real time, evaluates the answers using artificial intelligence, and updates the user's learning level. It then generates new, appropriate questions based on the updated learning level and presents them to the user. It can also provide explanations when the user requests an explanation for a specific question or when it automatically identifies an area where the user is having difficulty.

[1177] System configuration and operation

[1178] The system mainly consists of a server and a user terminal. The server plays a central role in analyzing users' learning activities and providing appropriate feedback. The user terminal provides an interface for users to answer learning questions and receive feedback.

[1179] 1. Receiving the user's answer

[1180] Users access the learning support system using their own devices (e.g., smartphones, tablets, PCs), enter answers to questions, and these answers are sent to and received from the server.

[1181] 2. Evaluating your answers

[1182] The server uses artificial intelligence, especially generative AI models (e.g., GPT-4), to determine whether a user's answer is correct. For example, if a user answers "4" to a simple arithmetic problem like "What is 2 + 2?", the answer is considered correct.

[1183] 3. Learning Level Update

[1184] The server updates the user's learning level based on the evaluation of the answer. For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[1185] 4. Creating new problems

[1186] The server generates new questions based on the updated learning level and presents them to the user. A user with a learning level of "medium" will be provided with a medium-level question such as "Please explain the process of photosynthesis."

[1187] 5. Visual display of learning progress

[1188] Users' learning progress is displayed visually in the form of dashboards and graphs, allowing them to see their progress at a glance, making it easier for users to understand their own learning progress.

[1189] 6. Commentary

[1190] When a user requests an explanation for a specific problem, the server uses the generative AI model to generate a detailed explanation for the problem and provide it to the user. An example of a prompt sentence to generate is "Explain the process of photosynthesis in plants."

[1191] 7. Automatic detection of stumbling blocks and provision of explanations

[1192] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the part where the user is having trouble. Then, it generates an explanation for that part using a generative AI model and provides it to the user. An example of a specific prompt is "Explain where common mistakes occur in solving quadratic equations."

[1193] This not only allows users to study efficiently, but also provides timely support for difficult-to-understand parts. In addition, by intuitively understanding their learning progress, they can study more systematically.

[1194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1195] Step 1:

[1196] The user accesses the learning support system and inputs answers to the learning questions.

[1197] Input: The user enters the answer to the question (e.g., "4") into the terminal.

[1198] How it works: The device sends user input to the server in real time.

[1199] Output: The server receives the user's answer data.

[1200] Step 2:

[1201] The server evaluates the received answers using artificial intelligence (generative AI model).

[1202] Input: The user's answer data received by the server.

[1203] How it works: A generative AI model (e.g., GPT-4) analyzes the answer data and determines whether the answer is correct. For example, the answer "4" to the question "What is 2 + 2?" is determined to be correct.

[1204] Output: The server obtains the evaluation result (correct / incorrect).

[1205] Step 3:

[1206] Based on the result of the correct / incorrect judgment, the server updates the user's learning level.

[1207] Input: The evaluation result obtained by the server.

[1208] How it works: The server checks the user's current learning level based on the assessment results and upgrades or downgrades the level as necessary. For example, if a user answers correctly at the initial "easy" level, they will be upgraded to "medium" level.

[1209] Output: Updated user learning level information.

[1210] Step 4:

[1211] The server generates new questions based on the updated learning level and presents them to the user.

[1212] Input: Updated learning level information.

[1213] How it works: Using a generative AI model, the server generates appropriate questions, such as "Please explain the process of photosynthesis" for a "medium" level user.

[1214] Output: A new training problem.

[1215] Step 5:

[1216] The server presents the user with a new problem.

[1217] Input: A new study question.

[1218] Operation: The generated question is sent to the user's terminal, which displays it.

[1219] Output: User sees new issue.

[1220] Step 6:

[1221] The server visually displays the user's learning progress.

[1222] Input: Updated learning level information and answer history.

[1223] How it works: The server uses this information to generate a dashboard and graphs of the user's progress.

[1224] Output: Visually displayed learning progress data.

[1225] Step 7:

[1226] When a user requests an explanation for a particular problem, the server generates the explanation using a generative AI model.

[1227] Input: User clarification request and applicable problem information.

[1228] How it works: An appropriate prompt (e.g., "Explain the process of photosynthesis in plants.") is input into the generative AI model to generate an explanation.

[1229] Output: The generated commentary.

[1230] Step 8:

[1231] The server presents the generated explanation to the user.

[1232] Input: The generated description.

[1233] What it does: Sends a description to the user's terminal, which displays it.

[1234] Output: User checks the explanation.

[1235] Step 9:

[1236] Even if the user does not request an explanation, the server automatically identifies the user's stumbling block and generates an explanation using a generative AI model.

[1237] Input: User's answer history and stumbling block information.

[1238] How it works: Enter an appropriate prompt (e.g., "Explain where common mistakes occur in solving quadratic equations.") into the generative AI model to generate an explanation.

[1239] Output: The generated commentary.

[1240] Step 10:

[1241] The server provides the user with an explanation of the problem.

[1242] Input: The generated description.

[1243] What it does: Sends a description to the user's terminal, which displays it.

[1244] Output: User checks the explanation.

[1245] 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.

[1246] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[1247] System configuration

[1248] 1. Receiving the user's answer

[1249] The user uses a terminal to access the system and input answers to the questions presented.

[1250] The server receives the user's answer and proceeds to the next step.

[1251] 2. Evaluating your answers

[1252] The server uses artificial intelligence to determine whether the user's answer is correct or not, using a pre-trained database and evaluation algorithms.

[1253] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[1254] 3. Update user learning level

[1255] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[1256] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[1257] 4. Creating new problems

[1258] The server generates new questions according to the user's updated learning level.

[1259] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[1260] 5. Providing commentary

[1261] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[1262] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[1263] 6. Automatic detection of stumbling blocks and provision of explanations

[1264] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[1265] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[1266] Introducing the Emotion Engine

[1267] 1. User Emotion Recognition

[1268] The server uses the camera and microphone installed on the user's device to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state.

[1269] For example, if a user is feeling frustrated about a problem, the emotion engine will recognize this as "stress."

[1270] 2. Adjusting problems based on emotional state

[1271] The server adjusts the difficulty and content of the questions based on the user's emotional state.

[1272] For example, if a user is feeling stressed, the system will provide a relaxed learning environment by presenting them with slightly easier questions.

[1273] 3. Adjusting commentary based on emotional state

[1274] The server provides commentary according to the user's emotional state.

[1275] For example, if a user is confused, provide a more detailed and understandable explanation.

[1276] 4. Real-time emotion monitoring and response

[1277] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed.

[1278] For example, if a user is feeling very stressed, a message will be sent encouraging them to take a break.

[1279] Specific examples

[1280] 1. User accesses the system for the first time

[1281] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[1282] In addition, the system evaluates the user's emotions and, if it determines that the user is not feeling stressed, presents a more difficult question next.

[1283] 2. New questions and emotional responses

[1284] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[1285] If the user begins to get confused by a question, the emotion engine will recognize this and the server will simplify the problem or add a detailed explanation.

[1286] 3. Requesting and Providing Explanations

[1287] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[1288] If the user appears calm and understanding, we will provide additional explanations of more complex content.

[1289] 4. Automatic detection of stumbling blocks

[1290] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[1291] If the user is stressed about a particular issue, add advice to help ease that stress.

[1292] The present invention provides questions and explanations that are optimal for the user's learning progress and emotional state, thereby significantly improving learning efficiency.

[1293] The processing flow will be explained below.

[1294] Step 1:

[1295] A user accesses the system using a terminal, which presents the user with a login or welcome screen.

[1296] Step 2:

[1297] The user enters the answer to the question on the device and presses the send button, which sends the answer data to the server.

[1298] Step 3:

[1299] The server analyzes the answer data received from the device and extracts the user ID and answer content.

[1300] Step 4:

[1301] The server uses artificial intelligence to evaluate the accuracy of the user's answer. For example, if the answer is "4", it will be evaluated as "correct".

[1302] Step 5:

[1303] The server updates the user's learning level based on the evaluation results: if the answer is correct, the level is raised; if the answer is incorrect, the level is lowered.

[1304] Step 6:

[1305] The server selects or generates the next questions based on the updated learning level, either retrieved from a database or created using artificial intelligence.

[1306] Step 7:

[1307] The server sends the generated or selected questions to the terminal and displays them to the user.

[1308] Step 8:

[1309] If the user experiences difficulty with a problem, the emotion engine uses the device's camera and microphone to analyze the user's emotional state in real time, for example, by analyzing facial expressions and evaluating voice tone.

[1310] Step 9:

[1311] The emotion engine determines the user's emotional state, and if it detects negative emotions such as stress or confusion, it sends that information to the server.

[1312] Step 10:

[1313] The server adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state. For example, if the user is feeling stressed, the questions will be made slightly easier.

[1314] Step 11:

[1315] When a user requests an explanation for a particular question, the terminal sends an explanation request to the server.

[1316] Step 12:

[1317] The server receives the explanation request and generates an explanation using artificial intelligence, taking into account the user's learning level and emotional state.

[1318] Step 13:

[1319] The server sends the generated explanation to the terminal and displays it to the user. For example, the explanation for "What is 2 + 2?" is "This is a basic addition problem, adding 2 to another 2 gives you 4."

[1320] Step 14:

[1321] Even if the user does not request an explanation, the server will analyze the answer history and automatically determine the areas where the user has trouble.

[1322] Step 15:

[1323] The server uses artificial intelligence to generate explanations for the stumbling blocks and presents them to the user. For example, if a user repeatedly makes mistakes on a particular problem, the server will provide a detailed explanation for that problem.

[1324] Step 16:

[1325] The system monitors the user's emotional state in real time, and if the user feels severe stress, the server sends a message to the device recommending relaxation advice or a break.

[1326] In this way, a system is constructed in which the server, terminal, and user cooperate to provide a learning experience that is optimal for the user's learning progress and emotional state.

[1327] Example 2

[1328] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1329] Conventional learning support systems judge whether a user's answers are correct and update their learning level, but do not adjust their level based on the user's emotional state, which can lead to reduced learning efficiency. Another issue is that they do not provide appropriate support even when the user does not request explanations. Furthermore, if questions and explanations are not adjusted based on the user's emotional state, this can affect the user's motivation and level of understanding.

[1330] 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.

[1331] In this invention, the server includes means for receiving answers entered by the user, means for determining whether the user's answers are correct using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, means for analyzing the user's facial expressions and voice using a sensor on the device and determining the user's emotional state using an emotion engine in order to recognize the user's emotional state, means for adjusting the difficulty of the questions based on the user's emotional state, and means for adjusting the content and presentation method of the explanations based on the user's emotional state. This allows the server to present appropriate questions and explanations to the user, improving the learning experience according to the user's emotional state.

[1332] "User learning level" is an index of the user's knowledge and skill proficiency.

[1333] The "means for receiving answers" refers to a mechanism for transferring answers entered by the user from the terminal to the server and acquiring the data.

[1334] The "means for determining whether the answer is correct" is a system that uses artificial intelligence to determine whether the user's answer is correct or incorrect.

[1335] The "means for updating the learning level" is a mechanism for changing the user's current learning level based on whether the user's answer is correct or incorrect.

[1336] "Means for generating questions and presenting them to the user" refers to a mechanism that creates new questions based on the user's learning level and displays them on the screen for the user.

[1337] The "means for recognizing emotional states" is a mechanism that uses the device's sensors to collect and analyze the user's emotional responses, such as facial expressions and voice, and then identifies the user's emotions using an emotion engine.

[1338] The "means for adjusting the difficulty of questions based on the emotional state" is a mechanism for appropriately changing the difficulty of questions presented in accordance with the recognized emotional state of the user.

[1339] The "means for adjusting the content and presentation method of the commentary based on the emotional state" is a mechanism for adjusting the optimal content and presentation method of the commentary taking into account the emotional state of the user.

[1340] MODE FOR CARRYING OUT THE INVENTION

[1341] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[1342] System configuration

[1343] Receiving user answers

[1344] A user uses a terminal to access the system and input answers to the questions presented. The terminal sends this answer data to the server. The server receives the answer data and prepares it for the next process. For example, if a user inputs "4" in response to the question "What is 2+2?", that data is sent to the server.

[1345] Evaluating answers

[1346] The server uses artificial intelligence to determine whether the user's answer is correct. The AI ​​uses a pre-trained database and evaluation algorithm to do this. Specifically, the server sends the answer data "4" to the AI ​​model, and the AI ​​model determines that "4" is the correct answer.

[1347] Update user learning level

[1348] The server updates the user's learning level based on whether the answer is correct or incorrect. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level. For example, if a user whose initial learning level is "easy" answers correctly, the level is updated to "medium."

[1349] Creating a new problem

[1350] The server generates new questions based on the updated learning level. At this time, it selects appropriate questions from a pre-prepared question bank and sends them to the device. The device then displays the new questions to the user. For example, a user at the "medium" level might be presented with the question "Please explain the process of photosynthesis."

[1351] Providing commentary

[1352] If a user requests an explanation, the server uses artificial intelligence to generate a detailed explanation for the problem and send it to the device. For example, if a user requests an explanation for the question "What is 2 + 2?", an explanation such as "This is a basic addition problem, and adding 2 to another 2 makes 4" will be generated and displayed.

[1353] Automatically identify stumbling blocks and provide explanations

[1354] The server analyzes the user's answer history, automatically identifies the areas where the user has trouble, generates explanations for those areas, and sends them to the device. This allows the user to receive appropriate explanations for the parts they do not understand. For example, if the user incorrectly answers "2 + 2 = 5," an explanation based on the theme of "the basics of addition" is provided.

[1355] Introducing the Emotion Engine

[1356] User emotion recognition

[1357] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. If the user is feeling irritated by a problem, the emotion engine will recognize this as "stress."

[1358] Adjusting for problems based on emotional state

[1359] The server adjusts the difficulty of the questions based on the user's emotional state. For example, if the user is feeling stressed, it will provide easier questions to help them relax and learn.

[1360] Adjusting commentary based on emotional state

[1361] The server takes into account the user's emotional state and adjusts the optimal explanation content and presentation method: if the user is confused, a more detailed and easy-to-understand explanation will be provided.

[1362] Real-time emotion monitoring and response

[1363] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed. For example, if the user is feeling very stressed, a message urging them to take a break will be sent.

[1364] Specific prompt examples

[1365] Below are some example prompts to use as input to a generative AI model:

[1366] Please provide a detailed explanation for the problem "What is 2 + 2?". Explain in simple terms so that users can understand, and include examples where necessary.

[1367]

[1368] Generate messages to advise users on how to relax if they are feeling stressed.

[1369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1370] Step 1:

[1371] The user uses the terminal to input the answer to the displayed question. The terminal sends this answer data to the server. The server receives the answer data and prepares to proceed to the next step.

[1372] Specifically, the user enters "4" in response to the question "What is 2+2?", and the device sends this answer data to the server. The server receives this input and saves it as answer data.

[1373] Step 2:

[1374] The server uses an artificial intelligence model to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[1375] Specifically, the server sends the answer data "4" to the AI ​​model. Based on this input, the AI ​​model determines that "4" is the correct answer and generates the output "correct answer."

[1376] Step 3:

[1377] The server updates the user's learning level based on the correctness of the answer. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level.

[1378] Specifically, the server receives the "correct" result and checks the user's learning level. If the initial learning level is "easy," it generates an output to update the learning level to "medium."

[1379] Step 4:

[1380] The server generates new questions based on the updated learning level, selects appropriate questions from a pre-prepared question bank, and sends them to the terminal, which then displays the new questions to the user.

[1381] Specifically, the server selects the problem "Please explain the process of photosynthesis" from the "medium" level problems. The server sends this problem to the terminal, and the terminal generates an output that displays the problem.

[1382] Step 5:

[1383] If the user requests an explanation, the server uses artificial intelligence to generate an explanation for the problem and send it to the terminal.

[1384] Specifically, the user presses the "Request Explanation" button, and the device sends the requested data to the server. The server generates an explanation for the problem "What is 2 + 2?", saying "This is a basic addition problem, adding 2 to another 2 gives you 4," and sends the output to the device.

[1385] Step 6:

[1386] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the areas where the user is having trouble. The server generates an explanation for that area and sends it to the terminal.

[1387] Specifically, the server analyzes the user's answer history and determines that the user mistakenly thought "2+2=5." The server then generates an explanation about the "basics of addition" and sends it to the terminal.

[1388] Step 7:

[1389] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. The server then adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state.

[1390] Specifically, the server analyzes facial images captured by a camera and audio data recorded by a microphone to determine whether the user is feeling stressed. The server then generates an output to send to the device, such as "asking simple questions to help the user relax."

[1391] (Application example 2)

[1392] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1393] Conventional learning support systems do not adequately adjust feedback and tasks according to the user's learning level and emotional state, which can result in insufficient learning effectiveness.In particular, when training employees in factories, real-time feedback and emotional recognition are required, but current systems have problems meeting these requirements.

[1394] 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.

[1395] In this invention, the server includes means for receiving answers entered by a user to determine the user's learning level, means for determining whether the user's answers are correct using a machine learning model for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for recognizing the user's emotional state and adjusting the difficulty of the questions and explanations based on the emotional state. This makes it possible to provide learning content and feedback optimized for the user's learning level and emotional state, thereby improving the efficiency and effectiveness of employee training.

[1396] "User" refers to an individual or employee who uses the system to learn or train.

[1397] "Learning level" is an indicator of the user's current level of knowledge and skills.

[1398] An "answer" is a response entered by a user to a question presented to them.

[1399] A "machine learning model" is an artificial intelligence algorithm that learns from data and makes predictions and classifications.

[1400] "Correctness" is the standard for evaluating whether a user's answer is correct or incorrect.

[1401] "Updating" means updating the user's learning level and other information to the latest version.

[1402] A "new problem" is the next task or question the system generates based on your updated learning level.

[1403] "Present" refers to the act of the system displaying information or issues to the user.

[1404] "Emotional state" indicates the type and intensity of the emotion the user is feeling.

[1405] "Recognizing" means that the system can distinguish and understand the user's emotional state.

[1406] "Tuning" means changing system settings and question content to optimize the user's learning experience.

[1407] "Feedback" refers to the evaluation and advice the system provides to the user.

[1408] "Training" refers to learning activities that enable employees in a factory to acquire the skills and knowledge necessary for their work.

[1409] The in-factory training support system, which is an application example of the present invention, is implemented in the following steps.

[1410] Hardware used:

[1411] Factory robots: Used as an interface to provide training guidance and feedback.

[1412] Server: A central computing resource responsible for data processing and management.

[1413] Emotion-aware cameras and microphones: Used to analyze employees' facial expressions and voices to recognize their emotional state in real time (e.g., Logitech Brio 4K camera, Microsoft Surface headphones).

[1414] Software used:

[1415] Machine learning models (e.g., TensorFlow, PyTorch): Used to determine whether an answer is correct or incorrect and update the learning level.

[1416] Emotion recognition software (e.g., Affectiva): Used to analyze employees' emotional states.

[1417] Generative explanation models (e.g., GPT-4): Used to generate explanations and provide feedback.

[1418] User interface (e.g. smartphone app, tablet app): Used by employees to interact with the training system.

[1419] Data processing and calculation procedures:

[1420] 1. Receiving Answers:

[1421] The factory robot sends the work performed and answers given by employees as part of their training to a server.

[1422] Example: { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}

[1423] 2. True or False:

[1424] The server uses machine learning models to assess the accuracy of the answers and the quality of the work.

[1425] Example: { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}

[1426] 3. Learning Level Update:

[1427] The server updates the user's learning level based on the evaluation results.

[1428] Example: { "user_id": "12345", "new_level": "medium"}

[1429] 4. Generate a new problem:

[1430] Generate new training content and questions according to updated learning levels.

[1431] Example: { "user_id": "12345", "new_tasks": ["task_next_medium"]}

[1432] 5. Emotion recognition:

[1433] Real-time data is collected from emotion recognition cameras and microphones to analyze emotional states.

[1434] Example: { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}

[1435] 6. Real-time support:

[1436] The server adjusts messages and training content depending on the emotional state and provides feedback through the robot.

[1437] Example: { "user_id": "12345", "message": "Take a short break and relax!"}

[1438] Examples and prompts:

[1439] Did your employees assemble the parts correctly?

[1440] Prompt: "Evaluate the task completion: \nTask: assemble_part \nUser answer: correct \nReminder: Provide feedback accordingly."

[1441] In this way, the system provides highly personalized learning content and feedback based on the user's learning level and emotional state, maximizing the efficiency and effectiveness of training.

[1442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1443] Step 1:

[1444] Receiving answers

[1445] Input: Work details and response data entered by users (employees) through factory robots.

[1446] How it works: Factory robots capture employees' actions and responses and send them to a server.

[1447] Data Calculation: The server parses the received data and converts it into the appropriate format.

[1448] Output: The converted answer data (e.g., { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}).

[1449] Step 2:

[1450] True or false

[1451] Input: The answer data generated in step 1.

[1452] How it works: The server uses a machine learning model (e.g., TensorFlow or PyTorch) to evaluate the user's answer.

[1453] Data calculation: The AI ​​model determines the accuracy of the answer and the quality of the work.

[1454] Output: Verification result (e.g., { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}).

[1455] Step 3:

[1456] Learning Level Update

[1457] Input: The result of step 2.

[1458] How it works: The server updates the learning level based on the user's evaluation results.

[1459] Data calculation: Applying algorithms to update the learning level.

[1460] Output: Updated learning level (e.g. { "user_id": "12345", "new_level": "medium"}).

[1461] Step 4:

[1462] Creating a new problem

[1463] Input: The learning level updated in step 3.

[1464] How it works: The server generates new training content and questions.

[1465] Data Computing: Using AI models to create questions of appropriate difficulty based on updated learning levels.

[1466] Output: The new problem data (e.g. { "user_id": "12345", "new_tasks": ["task_next_medium"]}).

[1467] Step 5:

[1468] emotion recognition

[1469] Input: Real-time data from camera and microphone for emotion recognition.

[1470] How it works: The server uses emotion recognition software (e.g., Affectiva) to analyze the user's emotional state.

[1471] Data calculation: Analyzes camera and microphone data to determine emotional state.

[1472] Output: Emotional state data (e.g., { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}).

[1473] Step 6:

[1474] Real-time support

[1475] Input: New problem data from step 4 and emotional state data from step 5.

[1476] Behavior: The server will provide feedback and adjustments as needed based on the emotional state.

[1477] Data calculations: Analyze emotional state data and tailor appropriate messages and problem content.

[1478] Output: Feedback data (e.g., { "user_id": "12345", "message": "Take a short break and relax!"}).

[1479] The above is the flow of specific processing steps of the system that realizes the application example.

[1480] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1481] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1482] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1483] [Fourth embodiment]

[1484] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1485] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1486] 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).

[1487] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1488] 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.

[1489] 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).

[1490] 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.

[1491] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1492] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1493] 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.

[1494] 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.

[1495] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1496] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1497] The present invention is a learning support system that determines a user's learning level and provides appropriate questions. This system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions appropriate to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[1498] System configuration

[1499] 1. Receiving the user's answer

[1500] The user uses a terminal to access the system and input answers to the questions presented.

[1501] The server receives the user's answer and proceeds to the next step.

[1502] 2. Evaluating your answers

[1503] The server uses artificial intelligence to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[1504] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[1505] 3. Update user learning level

[1506] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[1507] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[1508] 4. Creating new problems

[1509] The server generates new questions according to the user's updated learning level.

[1510] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[1511] 5. Providing commentary

[1512] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[1513] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[1514] 6. Automatic detection of stumbling blocks and provision of explanations

[1515] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[1516] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[1517] Specific examples

[1518] 1. User accesses the system for the first time

[1519] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[1520] 2. New questions

[1521] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[1522] 3. Requesting and Providing Explanations

[1523] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[1524] 4. Automatic detection of stumbling blocks

[1525] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[1526] As described above, according to the present invention, it is possible to provide questions and explanations that are optimal for the user's learning progress, thereby significantly improving learning efficiency.

[1527] The processing flow will be explained below.

[1528] Step 1:

[1529] A user accesses the system using a terminal, which presents the user with a welcome or login screen.

[1530] Step 2:

[1531] When the user enters the answer to the question on the terminal and presses the send button, the answer data is sent to the server.

[1532] Step 3:

[1533] The server receives the answer data sent from the device and extracts the user ID and answer content.

[1534] Step 4:

[1535] The server uses artificial intelligence to evaluate the user's answers, using pre-trained data to determine whether the answers are correct or incorrect.

[1536] Step 5:

[1537] The server updates the user's learning level based on the evaluation of the answer (correct or incorrect), for example, raising the level if the answer is correct and lowering the level if the answer is incorrect.

[1538] Step 6:

[1539] The server selects or generates the next questions based on the user's updated learning level. Questions are either selected from a database or newly generated using artificial intelligence.

[1540] Step 7:

[1541] The server sends the selected or generated questions to the terminal and displays them to the user.

[1542] Step 8:

[1543] When a user requests an explanation for a problem, the terminal sends an explanation request to the server.

[1544] Step 9:

[1545] The server receives the explanation request and generates an explanation using artificial intelligence based on the user's current learning level and the requested problem.

[1546] Step 10:

[1547] The server sends the generated commentary to the terminal and displays it to the user.

[1548] Step 11:

[1549] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically determines where the user is having trouble.

[1550] Step 12:

[1551] The server uses artificial intelligence to generate an explanation for the problem, sends the explanation to the terminal, and displays it to the user.

[1552] The above is the specific process flow for presenting questions according to the user's learning level and providing explanations as needed.

[1553] Example 1

[1554] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1555] Conventional learning support systems have difficulty providing appropriate questions according to the user's learning level or providing specific explanations for the user's stumbling points, which can lead to reduced learning efficiency. The present invention aims to support efficient learning by providing questions optimized for the user's learning level, identifying the areas where the user is stumbling, and providing appropriate explanations.

[1556] 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.

[1557] In this invention, the server includes means for receiving the user's answers at the terminal and transmitting them to the server, means for determining whether the answers are correct using artificial intelligence, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for automatically determining where the user is having difficulty and providing explanations for those parts. This allows the user to receive questions and explanations that are optimal for their learning progress, thereby improving the efficiency of their learning.

[1558] "Terminal" means an electronic device through which a user accesses the system and inputs answers to questions.

[1559] The "server" is a central computer that processes answers received from users and operates the entire learning support system, including evaluating questions, updating learning levels, and generating new questions.

[1560] "Artificial intelligence" refers to technology that includes advanced algorithms and databases used to evaluate user answers, generate explanations, and automatically identify stumbling blocks.

[1561] "Correctness of answer" is an evaluation result that indicates whether the answer entered by the user is correct for the presented question.

[1562] "Learning level" is an indicator that shows the user's current state according to their knowledge and understanding, and is used to determine the difficulty of the questions the system presents.

[1563] A "new problem" is the next learning task that is generated based on the user's learning level.

[1564] "Explanation" is additional explanation or information provided to help users better understand a particular issue.

[1565] "Trouble spots" refer to areas where users have made many incorrect answers or lacked understanding in their past answers to questions.

[1566] A "question generation module" is a program with a series of functions for extracting questions from a database or generating new questions appropriate to the user's learning level.

[1567] The "explanation generation module" is a program that uses artificial intelligence to generate explanations for problems and provide them to users in an easy-to-understand format.

[1568] MODE FOR CARRYING OUT THE INVENTION

[1569] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user, evaluates the answers, updates the user's learning level, and generates and presents new questions according to the updated learning level. It can also provide explanations when the user requests an explanation for a specific question or automatically identify areas where the user is having difficulty.

[1570] System configuration

[1571] 1. Receiving the user's answer

[1572] The user uses a terminal to access the system and input answers to the questions presented.

[1573] The device receives the user's input and sends it to the server, which records the received answers.

[1574] 2. Evaluating your answers

[1575] The server uses artificial intelligence (AI) to determine whether the answer is correct or not. The server first passes the answer data to the evaluation module.

[1576] The evaluation module references a pre-trained database and uses an algorithm to analyze the answers.

[1577] For example, if a user answers "4" to the question "What is 2+2?", the server will determine this as the correct answer.

[1578] 3. Update user learning level

[1579] The server performs a process to update the user's learning level based on the evaluation result of the answer.

[1580] The server first retrieves the user's current learning level from the database, then applies the update logic based on the new assessment results.

[1581] For example, if a user with a learning level of "easy" answers a question correctly, the server updates the learning level to "medium."

[1582] 4. Creating new problems

[1583] The server generates new questions based on the updated learning level using a question generation module.

[1584] The question generation module selects questions from a database appropriate for the user's learning level or generates new questions.

[1585] For example, a user with a learning level of "medium" might be asked the question "Please explain the process of photosynthesis."

[1586] 5. Providing commentary

[1587] When a user requests an explanation for a specific question, the server generates the explanation using artificial intelligence. The server first sends a request to the explanation generation module.

[1588] The explanation generation module creates a detailed explanation of the question and forms a document to be provided to the user.

[1589] For example, in response to the question "What is 2 + 2?", it generates an explanation such as "This problem is a basic addition problem, where 2 added to another 2 equals 4."

[1590] 6. Automatic detection of stumbling blocks and provision of explanations

[1591] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[1592] The server first inputs the answer history into an analysis algorithm, which identifies which questions the user gets wrong the most.

[1593] For the identified stumbling points, the server again uses the explanation generation module to create appropriate explanations and provide them to the user.

[1594] Specific examples

[1595] 1. When you receive your answer

[1596] When a user types "4" into a "2+2" problem on a terminal, the terminal sends the answer to the server, which records the answer in a database.

[1597] 2. Evaluating your answers

[1598] The server retrieves the answer "4" from the database and passes it to the evaluation module. The evaluation module checks whether it matches the correct answer "4" in the database and returns the result to the server. The server stores the result as the "correct answer."

[1599] 3. Learning Level Update

[1600] The server retrieves the user's current learning level as "easy" from the database and updates it to "medium" based on the new evaluation results.

[1601] 4. Creating new problems

[1602] The server searches the database for questions suitable for the "medium" level and sends the question "Please explain the process of photosynthesis" to the user.

[1603] 5. Providing commentary

[1604] When a user requests an explanation, the server sends a request to the explanation generation module, which generates an explanation such as "2 + 2 is a basic addition problem and the answer is 4" and provides it to the user.

[1605] 6. Automatic detection of stumbling blocks and provision of explanations

[1606] The server analyzes the user's answer history and detects if the user has made consecutive mistakes on any of the questions. Using this result, it generates an explanation for the relevant part and provides it to the user.

[1607] In this way, each component of the system works in tandem to provide questions and explanations that are optimal for the user's learning progress, significantly improving learning efficiency.

[1608] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1609] Step 1:

[1610] Receiving user answers

[1611] Users access the system using a terminal and enter answers to questions presented to them. The terminal receives the user's input and sends it to the server.

[1612] Input: The answer entered by the user into the device (e.g., "4" as the answer to "2+2")

[1613] Output: User's answer data sent to the server

[1614] Step 2:

[1615] Evaluating answers

[1616] The server uses artificial intelligence (AI) to determine whether the answer data is correct or not. First, the answer data is passed to the evaluation module.

[1617] Input: User's answer data received by the server

[1618] Data processing / data calculation: The evaluation module refers to a database that has been previously trained, compares the answer with the correct data, and determines whether it is correct or incorrect.

[1619] Output: The answer is judged as "correct" or "incorrect".

[1620] Step 3:

[1621] Update user learning level

[1622] The server updates the user's learning level based on the evaluation of the answer. First, it retrieves the user's current learning level from the database. Then it applies the update logic based on the new evaluation result.

[1623] Input: The user's current learning level and the evaluation result of the answer

[1624] Data processing / data calculation: Based on the new assessment results, the user's learning level is updated appropriately (e.g., from "easy" to "medium").

[1625] Output: Updated user learning level

[1626] Step 4:

[1627] Creating a new problem

[1628] The server generates new questions based on the updated learning level. Using the question generation module, the server selects questions from the database that are appropriate for the user's learning level, or generates new questions.

[1629] Input: Updated user learning level

[1630] Data processing / data calculation: The problem generation module selects or generates appropriate problems from the database and presents them to the user.

[1631] Output: New question (e.g., "Describe the process of photosynthesis.")

[1632] Step 5:

[1633] Providing commentary

[1634] When a user requests an explanation for a specific question, the server uses artificial intelligence to generate an explanation and sends a request to the explanation generation module to create a detailed explanation.

[1635] Input: A request from a user asking for clarification on a specific question.

[1636] Data processing / data calculation: The explanation generation module creates a detailed explanation of the relevant question and forms a document to be provided to the user.

[1637] Output: Generated explanation (e.g. "2 + 2 is a basic addition problem, adding 2 to another 2 makes 4")

[1638] Step 6:

[1639] Automatically identify stumbling blocks and provide explanations

[1640] The server analyzes the user's answer history and automatically identifies the areas where the user has difficulty, using an AI algorithm.

[1641] Input: User's answer history

[1642] Data processing / data calculation: AI algorithms analyze answer history and identify which questions users get wrong most often, generating explanations for identified stumbling blocks.

[1643] Output: Identified stumbling blocks and their explanations

[1644] The above are the specific processing steps of the program of this system, including input, data processing, data calculation, and output at each step.

[1645] (Application example 1)

[1646] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1647] In recent years, demand for online learning platforms has increased, creating a need for personalized learning experiences for each user. However, many systems are unable to effectively provide questions and explanations tailored to the user's learning level, making it difficult to improve learning efficiency. In particular, there is a lack of intelligent systems that can automatically identify where users are struggling and provide appropriate explanations. Given these factors, it is necessary to provide a system that improves learning efficiency by providing users with appropriate learning questions and explanations in real time and visually displaying their learning progress.

[1648] 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.

[1649] In this invention, the server includes means for receiving answers entered by a user, means for determining whether the user's answers are correct or incorrect using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for visually displaying the user's learning progress. This makes it possible to provide users with personalized study questions and explanations in real time, thereby improving their learning efficiency.

[1650] "User" refers to an individual or organization that uses the system to answer study questions.

[1651] "Answer" refers to the answer entered by the user in response to the presented study question.

[1652] "Means for receiving" refers to the mechanism and process for capturing user-entered answers on the server.

[1653] "Artificial intelligence" refers to a program or system that uses machine learning or deep learning techniques to evaluate a user's answers and generate appropriate questions and explanations.

[1654] "Means for determining correctness" refers to a mechanism that uses artificial intelligence to determine whether a user's answer is correct or incorrect.

[1655] "Learning level" refers to an indicator that shows the user's current academic ability and level of understanding.

[1656] "Means for updating" refers to a mechanism that appropriately changes the user's learning level based on the evaluation of the answers.

[1657] "Means for generating questions" refers to a mechanism for creating appropriate learning questions according to the user's learning level and presenting them to the user.

[1658] "Visual display means" refers to mechanisms that show users their learning progress and outcomes in visual formats such as graphs and dashboards.

[1659] "Means for generating explanations" refers to a mechanism that uses artificial intelligence to create explanations for parts that the user does not understand.

[1660] "Generative AI model" refers to an advanced machine learning algorithm or model used to generate explanations, questions, etc.

[1661] A "prompt" refers to an instruction or question that is input into a generative AI model.

[1662] "Trouble spots" refer to points where users had difficulty answering questions or where they did not fully understand the questions.

[1663] This invention is a learning support system that determines a user's learning level and provides appropriate questions. The system receives answers entered by the user in real time, evaluates the answers using artificial intelligence, and updates the user's learning level. It then generates new, appropriate questions based on the updated learning level and presents them to the user. It can also provide explanations when the user requests an explanation for a specific question or when it automatically identifies an area where the user is having difficulty.

[1664] System configuration and operation

[1665] The system mainly consists of a server and a user terminal. The server plays a central role in analyzing users' learning activities and providing appropriate feedback. The user terminal provides an interface for users to answer learning questions and receive feedback.

[1666] 1. Receiving the user's answer

[1667] Users access the learning support system using their own devices (e.g., smartphones, tablets, PCs), enter answers to questions, and these answers are sent to and received from the server.

[1668] 2. Evaluating your answers

[1669] The server uses artificial intelligence, especially generative AI models (e.g., GPT-4), to determine whether a user's answer is correct. For example, if a user answers "4" to a simple arithmetic problem like "What is 2 + 2?", the answer is considered correct.

[1670] 3. Learning Level Update

[1671] The server updates the user's learning level based on the evaluation of the answer. For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[1672] 4. Creating new problems

[1673] The server generates new questions based on the updated learning level and presents them to the user. A user with a learning level of "medium" will be provided with a medium-level question such as "Please explain the process of photosynthesis."

[1674] 5. Visual display of learning progress

[1675] Users' learning progress is displayed visually in the form of dashboards and graphs, allowing them to see their progress at a glance, making it easier for users to understand their own learning progress.

[1676] 6. Commentary

[1677] When a user requests an explanation for a specific problem, the server uses the generative AI model to generate a detailed explanation for the problem and provide it to the user. An example of a prompt sentence to generate is "Explain the process of photosynthesis in plants."

[1678] 7. Automatic detection of stumbling blocks and provision of explanations

[1679] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the part where the user is having trouble. Then, it generates an explanation for that part using a generative AI model and provides it to the user. An example of a specific prompt is "Explain where common mistakes occur in solving quadratic equations."

[1680] This not only allows users to study efficiently, but also provides timely support for difficult-to-understand parts. In addition, by intuitively understanding their learning progress, they can study more systematically.

[1681] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1682] Step 1:

[1683] The user accesses the learning support system and inputs answers to the learning questions.

[1684] Input: The user enters the answer to the question (e.g., "4") into the terminal.

[1685] How it works: The device sends user input to the server in real time.

[1686] Output: The server receives the user's answer data.

[1687] Step 2:

[1688] The server evaluates the received answers using artificial intelligence (generative AI model).

[1689] Input: The user's answer data received by the server.

[1690] How it works: A generative AI model (e.g., GPT-4) analyzes the answer data and determines whether the answer is correct. For example, the answer "4" to the question "What is 2 + 2?" is determined to be correct.

[1691] Output: The server obtains the evaluation result (correct / incorrect).

[1692] Step 3:

[1693] Based on the result of the correct / incorrect judgment, the server updates the user's learning level.

[1694] Input: The evaluation result obtained by the server.

[1695] How it works: The server checks the user's current learning level based on the assessment results and upgrades or downgrades the level as necessary. For example, if a user answers correctly at the initial "easy" level, they will be upgraded to "medium" level.

[1696] Output: Updated user learning level information.

[1697] Step 4:

[1698] The server generates new questions based on the updated learning level and presents them to the user.

[1699] Input: Updated learning level information.

[1700] How it works: Using a generative AI model, the server generates appropriate questions, such as "Please explain the process of photosynthesis" for a "medium" level user.

[1701] Output: A new training problem.

[1702] Step 5:

[1703] The server presents the user with a new problem.

[1704] Input: A new study question.

[1705] Operation: The generated question is sent to the user's terminal, which displays it.

[1706] Output: User sees new issue.

[1707] Step 6:

[1708] The server visually displays the user's learning progress.

[1709] Input: Updated learning level information and answer history.

[1710] How it works: The server uses this information to generate a dashboard and graphs of the user's progress.

[1711] Output: Visually displayed learning progress data.

[1712] Step 7:

[1713] When a user requests an explanation for a particular problem, the server generates the explanation using a generative AI model.

[1714] Input: User clarification request and applicable problem information.

[1715] How it works: An appropriate prompt (e.g., "Explain the process of photosynthesis in plants.") is input into the generative AI model to generate an explanation.

[1716] Output: The generated commentary.

[1717] Step 8:

[1718] The server presents the generated explanation to the user.

[1719] Input: The generated description.

[1720] What it does: Sends a description to the user's terminal, which displays it.

[1721] Output: User checks the explanation.

[1722] Step 9:

[1723] Even if the user does not request an explanation, the server automatically identifies the user's stumbling block and generates an explanation using a generative AI model.

[1724] Input: User's answer history and stumbling block information.

[1725] How it works: Enter an appropriate prompt (e.g., "Explain where common mistakes occur in solving quadratic equations.") into the generative AI model to generate an explanation.

[1726] Output: The generated commentary.

[1727] Step 10:

[1728] The server provides the user with an explanation of the problem.

[1729] Input: The generated description.

[1730] What it does: Sends a description to the user's terminal, which displays it.

[1731] Output: User checks the explanation.

[1732] 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.

[1733] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[1734] System configuration

[1735] 1. Receiving the user's answer

[1736] The user uses a terminal to access the system and input answers to the questions presented.

[1737] The server receives the user's answer and proceeds to the next step.

[1738] 2. Evaluating your answers

[1739] The server uses artificial intelligence to determine whether the user's answer is correct or not, using a pre-trained database and evaluation algorithms.

[1740] For example, in a simple calculation problem ("What is 2 + 2?"), if the answer is "4", it is judged to be correct and treated as "incorrect".

[1741] 3. Update user learning level

[1742] The server updates the user's learning level based on whether the user's answers are correct or incorrect.

[1743] For example, if a user whose initial level is "easy" answers correctly, their learning level will be updated to "medium."

[1744] 4. Creating new problems

[1745] The server generates new questions according to the user's updated learning level.

[1746] For example, a user with a learning level of "medium" will be presented with a medium-level question such as "Please explain the process of photosynthesis."

[1747] 5. Providing commentary

[1748] If a user requests an explanation for a particular question, the server uses artificial intelligence to generate a detailed explanation for the problem and present it to the user.

[1749] For example, in response to the question "What is 2 + 2?", an explanation is provided such as "This is a basic addition problem, where 2 added to another 2 equals 4."

[1750] 6. Automatic detection of stumbling blocks and provision of explanations

[1751] Even if the user does not request an explanation, the server automatically determines where the user is having trouble, uses artificial intelligence to generate an explanation for that part, and presents it to the user.

[1752] This allows users to receive appropriate explanations for the parts they do not understand, improving learning efficiency.

[1753] Introducing the Emotion Engine

[1754] 1. User Emotion Recognition

[1755] The server uses the camera and microphone installed on the user's device to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state.

[1756] For example, if a user is feeling frustrated about a problem, the emotion engine will recognize this as "stress."

[1757] 2. Adjusting problems based on emotional state

[1758] The server adjusts the difficulty and content of the questions based on the user's emotional state.

[1759] For example, if a user is feeling stressed, the system will provide a relaxed learning environment by presenting them with slightly easier questions.

[1760] 3. Adjusting commentary based on emotional state

[1761] The server provides commentary according to the user's emotional state.

[1762] For example, if a user is confused, provide a more detailed and understandable explanation.

[1763] 4. Real-time emotion monitoring and response

[1764] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed.

[1765] For example, if a user is feeling very stressed, a message will be sent encouraging them to take a break.

[1766] Specific examples

[1767] 1. User accesses the system for the first time

[1768] The server presents the user with a simple question: "What is 2 + 2?" If the user answers "4," the server determines that this is the correct answer and updates the user's learning level to "medium."

[1769] In addition, the system evaluates the user's emotions and, if it determines that the user is not feeling stressed, presents a more difficult question next.

[1770] 2. New questions and emotional responses

[1771] Based on the updated learning level, the server presents the user with a medium-difficulty question: "Please explain the process of photosynthesis."

[1772] If the user begins to get confused by a question, the emotion engine will recognize this and the server will simplify the problem or add a detailed explanation.

[1773] 3. Requesting and Providing Explanations

[1774] When a user requests an explanation for the question "What is 2 + 2?", the server uses artificial intelligence to provide the user with an explanation that "This is a basic addition problem, adding 2 to another 2 makes 4."

[1775] If the user appears calm and understanding, we will provide additional explanations of more complex content.

[1776] 4. Automatic detection of stumbling blocks

[1777] The server analyzes the user's answer history, automatically determines the points where the user has difficulty, generates explanations for those points, and provides them to the user.

[1778] If the user is stressed about a particular issue, add advice to help ease that stress.

[1779] The present invention provides questions and explanations that are optimal for the user's learning progress and emotional state, thereby significantly improving learning efficiency.

[1780] The processing flow will be explained below.

[1781] Step 1:

[1782] A user accesses the system using a terminal, which presents the user with a login or welcome screen.

[1783] Step 2:

[1784] The user enters the answer to the question on the device and presses the send button, which sends the answer data to the server.

[1785] Step 3:

[1786] The server analyzes the answer data received from the device and extracts the user ID and answer content.

[1787] Step 4:

[1788] The server uses artificial intelligence to evaluate the accuracy of the user's answer. For example, if the answer is "4", it will be evaluated as "correct".

[1789] Step 5:

[1790] The server updates the user's learning level based on the evaluation results: if the answer is correct, the level is raised; if the answer is incorrect, the level is lowered.

[1791] Step 6:

[1792] The server selects or generates the next questions based on the updated learning level, either retrieved from a database or created using artificial intelligence.

[1793] Step 7:

[1794] The server sends the generated or selected questions to the terminal and displays them to the user.

[1795] Step 8:

[1796] If the user experiences difficulty with a problem, the emotion engine uses the device's camera and microphone to analyze the user's emotional state in real time, for example, by analyzing facial expressions and evaluating voice tone.

[1797] Step 9:

[1798] The emotion engine determines the user's emotional state, and if it detects negative emotions such as stress or confusion, it sends that information to the server.

[1799] Step 10:

[1800] The server adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state. For example, if the user is feeling stressed, the questions will be made slightly easier.

[1801] Step 11:

[1802] When a user requests an explanation for a particular question, the terminal sends an explanation request to the server.

[1803] Step 12:

[1804] The server receives the explanation request and generates an explanation using artificial intelligence, taking into account the user's learning level and emotional state.

[1805] Step 13:

[1806] The server sends the generated explanation to the terminal and displays it to the user. For example, the explanation for "What is 2 + 2?" is "This is a basic addition problem, adding 2 to another 2 gives you 4."

[1807] Step 14:

[1808] Even if the user does not request an explanation, the server will analyze the answer history and automatically determine the areas where the user has trouble.

[1809] Step 15:

[1810] The server uses artificial intelligence to generate explanations for the stumbling blocks and presents them to the user. For example, if a user repeatedly makes mistakes on a particular problem, the server will provide a detailed explanation for that problem.

[1811] Step 16:

[1812] The system monitors the user's emotional state in real time, and if the user feels severe stress, the server sends a message to the device recommending relaxation advice or a break.

[1813] In this way, a system is constructed in which the server, terminal, and user cooperate to provide a learning experience that is optimal for the user's learning progress and emotional state.

[1814] Example 2

[1815] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1816] Conventional learning support systems judge whether a user's answers are correct and update their learning level, but do not adjust their level based on the user's emotional state, which can lead to reduced learning efficiency. Another issue is that they do not provide appropriate support even when the user does not request explanations. Furthermore, if questions and explanations are not adjusted based on the user's emotional state, this can affect the user's motivation and level of understanding.

[1817] 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.

[1818] In this invention, the server includes means for receiving answers entered by the user, means for determining whether the user's answers are correct using artificial intelligence for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, means for analyzing the user's facial expressions and voice using a sensor on the device and determining the user's emotional state using an emotion engine in order to recognize the user's emotional state, means for adjusting the difficulty of the questions based on the user's emotional state, and means for adjusting the content and presentation method of the explanations based on the user's emotional state. This allows the server to present appropriate questions and explanations to the user, improving the learning experience according to the user's emotional state.

[1819] "User learning level" is an index of the user's knowledge and skill proficiency.

[1820] The "means for receiving answers" refers to a mechanism for transferring answers entered by the user from the terminal to the server and acquiring the data.

[1821] The "means for determining whether the answer is correct" is a system that uses artificial intelligence to determine whether the user's answer is correct or incorrect.

[1822] The "means for updating the learning level" is a mechanism for changing the user's current learning level based on whether the user's answer is correct or incorrect.

[1823] "Means for generating questions and presenting them to the user" refers to a mechanism that creates new questions based on the user's learning level and displays them on the screen for the user.

[1824] The "means for recognizing emotional states" is a mechanism that uses the device's sensors to collect and analyze the user's emotional responses, such as facial expressions and voice, and then identifies the user's emotions using an emotion engine.

[1825] The "means for adjusting the difficulty of questions based on the emotional state" is a mechanism for appropriately changing the difficulty of questions presented in accordance with the recognized emotional state of the user.

[1826] The "means for adjusting the content and presentation method of the commentary based on the emotional state" is a mechanism for adjusting the optimal content and presentation method of the commentary taking into account the emotional state of the user.

[1827] MODE FOR CARRYING OUT THE INVENTION

[1828] This invention is a learning support system that determines a user's learning level and emotional state, presents appropriate questions, and provides explanations as needed. This system receives answers entered by the user, evaluates the accuracy of the answers using artificial intelligence, updates the user's learning level based on the results, and generates and presents new questions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a learning experience that is tailored to the user's emotional state.

[1829] System configuration

[1830] Receiving user answers

[1831] A user uses a terminal to access the system and input answers to the questions presented. The terminal sends this answer data to the server. The server receives the answer data and prepares it for the next process. For example, if a user inputs "4" in response to the question "What is 2+2?", that data is sent to the server.

[1832] Evaluating answers

[1833] The server uses artificial intelligence to determine whether the user's answer is correct. The AI ​​uses a pre-trained database and evaluation algorithm to do this. Specifically, the server sends the answer data "4" to the AI ​​model, and the AI ​​model determines that "4" is the correct answer.

[1834] Update user learning level

[1835] The server updates the user's learning level based on whether the answer is correct or incorrect. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level. For example, if a user whose initial learning level is "easy" answers correctly, the level is updated to "medium."

[1836] Creating a new problem

[1837] The server generates new questions based on the updated learning level. At this time, it selects appropriate questions from a pre-prepared question bank and sends them to the device. The device then displays the new questions to the user. For example, a user at the "medium" level might be presented with the question "Please explain the process of photosynthesis."

[1838] Providing commentary

[1839] If a user requests an explanation, the server uses artificial intelligence to generate a detailed explanation for the problem and send it to the device. For example, if a user requests an explanation for the question "What is 2 + 2?", an explanation such as "This is a basic addition problem, and adding 2 to another 2 makes 4" will be generated and displayed.

[1840] Automatically identify stumbling blocks and provide explanations

[1841] The server analyzes the user's answer history, automatically identifies the areas where the user has trouble, generates explanations for those areas, and sends them to the device. This allows the user to receive appropriate explanations for the parts they do not understand. For example, if the user incorrectly answers "2 + 2 = 5," an explanation based on the theme of "the basics of addition" is provided.

[1842] Introducing the Emotion Engine

[1843] User emotion recognition

[1844] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. If the user is feeling irritated by a problem, the emotion engine will recognize this as "stress."

[1845] Adjusting for problems based on emotional state

[1846] The server adjusts the difficulty of the questions based on the user's emotional state. For example, if the user is feeling stressed, it will provide easier questions to help them relax and learn.

[1847] Adjusting commentary based on emotional state

[1848] The server takes into account the user's emotional state and adjusts the optimal explanation content and presentation method: if the user is confused, a more detailed and easy-to-understand explanation will be provided.

[1849] Real-time emotion monitoring and response

[1850] The server monitors the user's emotional state in real time and provides relaxation techniques and encouraging messages as needed. For example, if the user is feeling very stressed, a message urging them to take a break will be sent.

[1851] Specific prompt examples

[1852] Below are some example prompts to use as input to a generative AI model:

[1853] Please provide a detailed explanation for the problem "What is 2 + 2?". Explain in simple terms so that users can understand, and include examples where necessary.

[1854]

[1855] Generate messages to advise users on how to relax if they are feeling stressed.

[1856] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1857] Step 1:

[1858] The user uses the terminal to input the answer to the displayed question. The terminal sends this answer data to the server. The server receives the answer data and prepares to proceed to the next step.

[1859] Specifically, the user enters "4" in response to the question "What is 2+2?", and the device sends this answer data to the server. The server receives this input and saves it as answer data.

[1860] Step 2:

[1861] The server uses an artificial intelligence model to determine whether the user's answer is correct or incorrect, using a pre-trained database and evaluation algorithms.

[1862] Specifically, the server sends the answer data "4" to the AI ​​model. Based on this input, the AI ​​model determines that "4" is the correct answer and generates the output "correct answer."

[1863] Step 3:

[1864] The server updates the user's learning level based on the correctness of the answer. The result is stored in an internal database, and the server compares the current learning level with the answer to calculate and update the new learning level.

[1865] Specifically, the server receives the "correct" result and checks the user's learning level. If the initial learning level is "easy," it generates an output to update the learning level to "medium."

[1866] Step 4:

[1867] The server generates new questions based on the updated learning level, selects appropriate questions from a pre-prepared question bank, and sends them to the terminal, which then displays the new questions to the user.

[1868] Specifically, the server selects the problem "Please explain the process of photosynthesis" from the "medium" level problems. The server sends this problem to the terminal, and the terminal generates an output that displays the problem.

[1869] Step 5:

[1870] If the user requests an explanation, the server uses artificial intelligence to generate an explanation for the problem and send it to the terminal.

[1871] Specifically, the user presses the "Request Explanation" button, and the device sends the requested data to the server. The server generates an explanation for the problem "What is 2 + 2?", saying "This is a basic addition problem, adding 2 to another 2 gives you 4," and sends the output to the device.

[1872] Step 6:

[1873] Even if the user does not request an explanation, the server analyzes the user's answer history and automatically identifies the areas where the user is having trouble. The server generates an explanation for that area and sends it to the terminal.

[1874] Specifically, the server analyzes the user's answer history and determines that the user mistakenly thought "2+2=5." The server then generates an explanation about the "basics of addition" and sends it to the terminal.

[1875] Step 7:

[1876] The server uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice, and uses an emotion engine to recognize the user's emotional state. The server then adjusts the difficulty of the questions and the content of the explanations based on the user's emotional state.

[1877] Specifically, the server analyzes facial images captured by a camera and audio data recorded by a microphone to determine whether the user is feeling stressed. The server then generates an output to send to the device, such as "asking simple questions to help the user relax."

[1878] (Application example 2)

[1879] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1880] Conventional learning support systems do not adequately adjust feedback and tasks according to the user's learning level and emotional state, which can result in insufficient learning effectiveness.In particular, when training employees in factories, real-time feedback and emotional recognition are required, but current systems have problems meeting these requirements.

[1881] 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.

[1882] In this invention, the server includes means for receiving answers entered by a user to determine the user's learning level, means for determining whether the user's answers are correct using a machine learning model for evaluating the answers, means for updating the user's learning level based on the determination result, means for generating new questions according to the updated learning level and presenting them to the user, and means for recognizing the user's emotional state and adjusting the difficulty of the questions and explanations based on the emotional state. This makes it possible to provide learning content and feedback optimized for the user's learning level and emotional state, thereby improving the efficiency and effectiveness of employee training.

[1883] "User" refers to an individual or employee who uses the system to learn or train.

[1884] "Learning level" is an indicator of the user's current level of knowledge and skills.

[1885] An "answer" is a response entered by a user to a question presented to them.

[1886] A "machine learning model" is an artificial intelligence algorithm that learns from data and makes predictions and classifications.

[1887] "Correctness" is the standard for evaluating whether a user's answer is correct or incorrect.

[1888] "Updating" means updating the user's learning level and other information to the latest version.

[1889] A "new problem" is the next task or question the system generates based on your updated learning level.

[1890] "Present" refers to the act of the system displaying information or issues to the user.

[1891] "Emotional state" indicates the type and intensity of the emotion the user is feeling.

[1892] "Recognizing" means that the system can distinguish and understand the user's emotional state.

[1893] "Tuning" means changing system settings and question content to optimize the user's learning experience.

[1894] "Feedback" refers to the evaluation and advice the system provides to the user.

[1895] "Training" refers to learning activities that enable employees in a factory to acquire the skills and knowledge necessary for their work.

[1896] The in-factory training support system, which is an application example of the present invention, is implemented in the following steps.

[1897] Hardware used:

[1898] Factory robots: Used as an interface to provide training guidance and feedback.

[1899] Server: A central computing resource responsible for data processing and management.

[1900] Emotion-aware cameras and microphones: Used to analyze employees' facial expressions and voices to recognize their emotional state in real time (e.g., Logitech Brio 4K camera, Microsoft Surface headphones).

[1901] Software used:

[1902] Machine learning models (e.g., TensorFlow, PyTorch): Used to determine whether an answer is correct or incorrect and update the learning level.

[1903] Emotion recognition software (e.g., Affectiva): Used to analyze employees' emotional states.

[1904] Generative explanation models (e.g., GPT-4): Used to generate explanations and provide feedback.

[1905] User interface (e.g. smartphone app, tablet app): Used by employees to interact with the training system.

[1906] Data processing and calculation procedures:

[1907] 1. Receiving Answers:

[1908] The factory robot sends the work performed and answers given by employees as part of their training to a server.

[1909] Example: { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}

[1910] 2. True or False:

[1911] The server uses machine learning models to assess the accuracy of the answers and the quality of the work.

[1912] Example: { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}

[1913] 3. Learning Level Update:

[1914] The server updates the user's learning level based on the evaluation results.

[1915] Example: { "user_id": "12345", "new_level": "medium"}

[1916] 4. Generate a new problem:

[1917] Generate new training content and questions according to updated learning levels.

[1918] Example: { "user_id": "12345", "new_tasks": ["task_next_medium"]}

[1919] 5. Emotion recognition:

[1920] Real-time data is collected from emotion recognition cameras and microphones to analyze emotional states.

[1921] Example: { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}

[1922] 6. Real-time support:

[1923] The server adjusts messages and training content depending on the emotional state and provides feedback through the robot.

[1924] Example: { "user_id": "12345", "message": "Take a short break and relax!"}

[1925] Examples and prompts:

[1926] Did your employees assemble the parts correctly?

[1927] Prompt: "Evaluate the task completion: \nTask: assemble_part \nUser answer: correct \nReminder: Provide feedback accordingly."

[1928] In this way, the system provides highly personalized learning content and feedback based on the user's learning level and emotional state, maximizing the efficiency and effectiveness of training.

[1929] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1930] Step 1:

[1931] Receiving answers

[1932] Input: Work details and response data entered by users (employees) through factory robots.

[1933] How it works: Factory robots capture employees' actions and responses and send them to a server.

[1934] Data Calculation: The server parses the received data and converts it into the appropriate format.

[1935] Output: The converted answer data (e.g., { "user_id": "12345", "task": "assemble_part", "status": "completed", "answers": {"question_1":"correct","question_2":"incorrect"}}).

[1936] Step 2:

[1937] True or false

[1938] Input: The answer data generated in step 1.

[1939] How it works: The server uses a machine learning model (e.g., TensorFlow or PyTorch) to evaluate the user's answer.

[1940] Data calculation: The AI ​​model determines the accuracy of the answer and the quality of the work.

[1941] Output: Verification result (e.g., { "user_id": "12345", "task": "assemble_part", "evaluation": {"question_1":"correct","question_2":"incorrect"}, "quality": 80}).

[1942] Step 3:

[1943] Learning Level Update

[1944] Input: The result of step 2.

[1945] How it works: The server updates the learning level based on the user's evaluation results.

[1946] Data calculation: Applying algorithms to update the learning level.

[1947] Output: Updated learning level (e.g. { "user_id": "12345", "new_level": "medium"}).

[1948] Step 4:

[1949] Creating a new problem

[1950] Input: The learning level updated in step 3.

[1951] How it works: The server generates new training content and questions.

[1952] Data Computing: Using AI models to create questions of appropriate difficulty based on updated learning levels.

[1953] Output: The new problem data (e.g. { "user_id": "12345", "new_tasks": ["task_next_medium"]}).

[1954] Step 5:

[1955] emotion recognition

[1956] Input: Real-time data from camera and microphone for emotion recognition.

[1957] How it works: The server uses emotion recognition software (e.g., Affectiva) to analyze the user's emotional state.

[1958] Data calculation: Analyzes camera and microphone data to determine emotional state.

[1959] Output: Emotional state data (e.g., { "user_id": "12345", "emotions": {"stress": 0.75, "interest": 0.60}}).

[1960] Step 6:

[1961] Real-time support

[1962] Input: New problem data from step 4 and emotional state data from step 5.

[1963] Behavior: The server will provide feedback and adjustments as needed based on the emotional state.

[1964] Data calculations: Analyze emotional state data and tailor appropriate messages and problem content.

[1965] Output: Feedback data (e.g., { "user_id": "12345", "message": "Take a short break and relax!"}).

[1966] The above is the flow of specific processing steps of the system that realizes the application example.

[1967] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1968] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1969] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1970] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1971] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1972] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1973] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1974] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1975] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1976] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1977] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1978] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1979] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1980] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1981] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1982] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1983] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1984] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1985] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1986] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1987] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1988] The following is further disclosed regarding the above embodiment.

[1989] (Claim 1)

[1990] To determine the user's learning level,

[1991] means for receiving the user-entered answers;

[1992] means for determining whether a user's answer is correct or incorrect using artificial intelligence to evaluate said answer;

[1993] means for updating the user's learning level based on the determination result;

[1994] means for generating new questions according to the updated learning level and presenting the questions to the user;

[1995] A system including:

[1996] (Claim 2)

[1997] When a user requests clarification on a specific question,

[1998] means for generating explanations based on the user's learning level and the problem, using artificial intelligence for generating the explanations;

[1999] means for presenting the generated commentary to a user;

[2000] 10. The system of claim 1, comprising:

[2001] (Claim 3)

[2002] Even if the user does not request an explanation,

[2003] A means for automatically determining a part where a user has difficulty and generating an explanation for the part using artificial intelligence;

[2004] means for presenting the generated commentary to a user;

[2005] 10. The system of claim 1, comprising:

[2006] "Example 1"

[2007] (Claim 1)

[2008] means for receiving the user's answers at the terminal and transmitting them to the server;

[2009] A means for the server to determine whether an answer is correct or not using artificial intelligence;

[2010] means for the server to update the user's learning level based on the determination result;

[2011] a means for the server to generate new questions according to the updated learning level and present the questions to the user;

[2012] The server automatically identifies the part where the user has trouble through the answer history and provides an explanation for that part.

[2013] A system including:

[2014] (Claim 2)

[2015] When a user requests clarification on a specific question,

[2016] means for generating explanations based on the user's learning level and the problem, using artificial intelligence for generating the explanations;

[2017] means for presenting the generated commentary to a user;

[2018] 10. The system of claim 1, comprising:

[2019] (Claim 3)

[2020] Even if the user does not request an explanation,

[2021] A means for automatically determining a part where a user has difficulty and generating an explanation for the part using artificial intelligence;

[2022] means for presenting the generated commentary to a user;

[2023] 10. The system of claim 1, comprising:

[2024] "Application Example 1"

[2025] (Claim 1)

[2026] To determine the user's learning level,

[2027] means for receiving the user-entered answers;

[2028] means for determining whether a user's answer is correct or incorrect using artificial intelligence to evaluate said answer;

[2029] means for updating the user's learning level based on the determination result;

[2030] means for generating new questions according to the updated learning level and presenting the questions to the user;

[2031] a means of visually displaying the user's learning progress;

[2032] A system including:

[2033] (Claim 2)

[2034] When a user requests clarification on a specific question,

[2035] means for generating explanations based on the user's learning level and the problem, using artificial intelligence for generating the explanations;

[2036] means for presenting the generated commentary to a user;

[2037] means for using a generative AI model to generate an explanation for the problem and inputting an appropriate prompt sentence;

[2038] 10. The system of claim 1, comprising:

[2039] (Claim 3)

[2040] Even if the user does not request an explanation,

[2041] A means for automatically determining a part where a user has difficulty and generating an explanation for the part using artificial intelligence;

[2042] means for presenting the generated commentary to a user;

[2043] means for using a generative AI model to generate an explanation for the stumbling block and inputting an appropriate prompt sentence;

[2044] 10. The system of claim 1, comprising:

[2045] "Example 2: Combining Emotion Engines"

[2046] (Claim 1)

[2047] To determine the user's learning level,

[2048] means for receiving the user-entered answers;

[2049] means for determining whether a user's answer is correct or incorrect using artificial intelligence to evaluate said answer;

[2050] means for updating the user's learning level based on the determination result;

[2051] means for generating new questions according to the updated learning level and presenting the questions to the user;

[2052] A means for analyzing the user's facial expressions and voice using sensors on the device and determining the user's emotional state using an emotion engine in order to recognize the user's emotional state;

[2053] a means for adjusting the difficulty of the problem based on the user's emotional state;

[2054] A means for adjusting the content and presentation of commentary based on the user's emotional state; and

[2055] A system including:

[2056] (Claim 2)

[2057] When a user requests clarification on a specific question,

[2058] means for generating explanations based on the user's learning level and the problem, using artificial intelligence for generating the explanations;

[2059] means for presenting the generated commentary to a user;

[2060] means for adjusting commentary based on the emotional state of the user;

[2061] 10. The system of claim 1, comprising:

[2062] (Claim 3)

[2063] Even if the user does not request an explanation,

[2064] A means for automatically determining a part where a user has difficulty and generating an explanation for the part using artificial intelligence;

[2065] means for presenting the generated commentary to a user;

[2066] A means of adjusting commentary or providing additional advice based on the user's emotional state; and

[2067] 10. The system of claim 1, comprising:

[2068] "Application example 2 when combining emotion engines"

[2069] (Claim 1)

[2070] To determine the user's learning level,

[2071] means for receiving the user-entered answers;

[2072] means for determining whether a user's answer is correct or incorrect using a machine learning model for evaluating the answer;

[2073] means for updating the user's learning level based on the determination result;

[2074] means for generating new questions according to the updated learning level and presenting the questions to the user;

[2075] means for recognizing the emotional state of the user and adjusting the difficulty of questions and explanations based on said emotional state;

[2076] A system including:

[2077] (Claim 2)

[2078] When a user requests clarification on a specific question,

[2079] means for generating explanations based on a user's learning level and the problem using a machine learning model for generating the explanations;

[2080] means for presenting the generated commentary to a user;

[2081] a means for adjusting the commentary according to the user's emotional state;

[2082] 10. The system of claim 1, comprising:

[2083] (Claim 3)

[2084] Even if the user does not request an explanation,

[2085] A means for automatically determining a part where a user has difficulty and generating an explanation for the part using a machine learning model for generating an explanation;

[2086] means for presenting the generated commentary to a user;

[2087] A means of monitoring the user's emotional state in real time and responding as needed;

[2088] 10. The system of claim 1, comprising: [Explanation of symbols]

[2089] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. To determine the user's learning level, means for receiving the user-entered answers; means for determining whether a user's answer is correct or incorrect using artificial intelligence to evaluate said answer; means for updating the user's learning level based on the determination result; means for generating new questions according to the updated learning level and presenting the questions to the user; A system including:

2. When a user requests clarification on a specific question, means for generating explanations based on the user's learning level and the problem, using artificial intelligence for generating the explanations; means for presenting the generated commentary to a user; The system of claim 1 , comprising:

3. Even if the user does not request an explanation, A means for automatically determining a part where a user has difficulty and generating an explanation for the part using artificial intelligence; means for presenting the generated commentary to a user; The system of claim 1 , comprising:

Images