System

Abstract

A system is provided.SOLUTION: A schedule optimizing means for dynamically adjusting the learning plan based on the progress of the learner, an automatic answering means for immediately answering a question from the learner through a messenger application such as LINE, a detailed explanation means for providing a detailed explanation for an answer to a past question, and a real-time monitoring means for monitoring the learning progress of the learner in real time and providing appropriate feedback. AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's learning environment, many learners find it difficult to formulate optimal study plans due to busy schedules and information overload. They also face challenges in obtaining prompt answers to questions that arise during their studies and in effectively managing their schedules. These factors increase learner stress and reduce learning effectiveness, creating problems. Therefore, there is a need for a system that proposes optimal study plans that take individual learning styles into account, as well as real-time question and progress management during learning. [Means for solving the problem]

[0005] The present invention provides an AI analysis means that collects learner input data and analyzes it using AI. It also provides a plan proposal means that proposes an optimal study plan for the learner based on the analysis results. It also includes a schedule optimization means that dynamically adjusts the study plan based on the learner's progress, and an automatic response means that instantly answers questions from the learner via a messenger application. It also includes a detailed explanation means that provides detailed explanations for answers to past exam questions, and a real-time monitoring means that monitors the learner's learning progress in real time and provides appropriate feedback. This allows learners to study effectively and efficiently under an optimal study plan, maximizing learning effectiveness while reducing stress.

[0006] "AI analysis means" is a system that uses artificial intelligence technology to analyze collected learner input data and identify learning styles and learning progress.

[0007] The "plan suggestion means" is a system that suggests optimal learning plans and learning content to learners based on the analysis results obtained by the AI ​​analysis means.

[0008] The "schedule optimization means" is a system that dynamically adjusts the learning schedule based on the learner's progress and learning pace, and provides the optimal learning schedule.

[0009] An "automatic response means" is a system that receives questions from learners through messenger applications such as LINE and instantly generates and provides appropriate answers.

[0010] The "detailed explanation means" is a system that provides detailed explanations and feedback on answers to past exam questions submitted by learners.

[0011] "Real-time monitoring means" refers to a system for monitoring learners' learning progress in real time and providing appropriate feedback and warnings.

[0012] The "learning style analysis means" is a system that uses the learner's input data and analysis results to identify individual learning styles and generate learning plans based on those styles.

[0013] "Natural language processing means" is a system that uses technology to analyze learners' questions in natural language and search for or generate appropriate answers. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention relates to a system that enables learners to easily receive learning support using a messenger application such as LINE, and specific embodiments thereof will be described below.

[0036] 1.Collection and analysis of learning data

[0037] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, and other information.

[0038] Examples:

[0039] When a user sends a message on LINE saying, "I didn't understand yesterday's math problem," the server receives the data and uses AI analysis to identify which areas the user is weak in.

[0040] 2.Suggested study plan

[0041] Based on the analysis results obtained by the AI ​​analysis means, the plan proposal means generates and proposes an optimal learning plan for the learner. The proposed content is personalized and tailored to the learner's level of understanding and learning progress.

[0042] Examples:

[0043] If the AI ​​analysis means identifies that the user has a low level of understanding of mathematics, the plan suggestion means will suggest a specific study plan such as "Focus on mathematics for one hour every day for the next week."

[0044] 3. Schedule optimization

[0045] The server dynamically adjusts the learning schedule based on the learner's progress and learning pace using a schedule optimization means, allowing the learner to progress efficiently.

[0046] Examples:

[0047] When a user types into LINE, "There are only 10 days left until the next exam," the server recalculates the schedule based on that information and presents a specific schedule such as, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[0048] 4. Automated Question Answering

[0049] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[0050] Examples:

[0051] When a user asks a question on LINE such as "Please tell me about the law of conservation of energy," the server analyzes the question, automatically generates an answer - "The law of conservation of energy is the law that energy remains constant over time" - and sends it to the device, which then displays it to the user.

[0052] 5. Detailed explanations of past exam answers

[0053] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[0054] Examples:

[0055] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[0056] 6. Real-time monitoring and feedback

[0057] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provide timely feedback, allowing the learner to always be aware of their learning situation and make corrections as needed.

[0058] Examples:

[0059] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends feedback such as "This is going well" or "Your progress in math is falling behind. Give it a little more time."

[0060] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing study plans to answering questions and managing progress, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Users use the LINE application to input their learning data, including progress reports, questions, and answers to past exam questions.

[0064] Step 2:

[0065] The device sends the data entered by the user to the server using LINE's API.

[0066] Step 3:

[0067] The server receives the data and stores it in a database.

[0068] Step 4:

[0069] The server analyzes the stored data using AI analytics, which are used to identify learning progress, comprehension, and specific areas of weakness.

[0070] Step 5:

[0071] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which includes prioritizing learning content and allocating learning time.

[0072] Step 6:

[0073] The server sends the generated learning plan to the device.

[0074] Step 7:

[0075] The device displays the learning plan to the user as a LINE message.

[0076] Step 8:

[0077] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[0078] Step 9:

[0079] The terminal sends a question from the user to the server.

[0080] Step 10:

[0081] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[0082] Step 11:

[0083] The server generates a response and sends it to the terminal.

[0084] Step 12:

[0085] The terminal displays the answer to the user.

[0086] Step 13:

[0087] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[0088] Step 14:

[0089] The terminal sends the answer data for past questions to the server.

[0090] Step 15:

[0091] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[0092] Step 16:

[0093] The server generates commentary and sends feedback to the device.

[0094] Step 17:

[0095] The device displays detailed instructions and feedback to the user.

[0096] Step 18:

[0097] Users report their learning progress via LINE, for example, "I studied for two hours today."

[0098] Step 19:

[0099] The device sends progress data to the server.

[0100] Step 20:

[0101] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[0102] Step 21:

[0103] Based on the analysis, the server generates progress-based feedback, including suggestions for additional study time and motivational messages.

[0104] Step 22:

[0105] The server generates feedback and sends it to the device.

[0106] Step 23:

[0107] The device displays the feedback to the user.

[0108] Step 24:

[0109] The learning plan is compared with actual progress, and the server dynamically adjusts the learning schedule as needed.

[0110] Step 25:

[0111] The server transmits the adjusted schedule to the terminal.

[0112] Step 26:

[0113] The terminal displays the new schedule to the user.

[0114] Example 1

[0115] 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."

[0116] Conventional learning support systems lack comprehensive support for learners to efficiently progress through their studies in real time. In particular, they do not propose dynamic learning plans or optimize schedules based on individual learners' progress and level of understanding, which means that learning effectiveness is not fully improved. Furthermore, they lack the ability to respond immediately to questions and provide detailed feedback.

[0117] 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.

[0118] In this invention, the server includes AI analysis means for collecting and analyzing learner input data, plan proposal means for proposing an optimal study plan for the learner based on the analysis results, schedule optimization means for dynamically adjusting the study plan based on the learner's progress, automatic response means for instantly answering questions from the learner through communication software, detailed explanation means for providing detailed explanations of answers to past exam questions, real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a terminal for transferring the learner's questions and progress to the server through communication software, and a server for transmitting answers and feedback generated based on the analysis results to the learner through communication software. This enables the learner to receive real-time and comprehensive learning support.

[0119] "AI analysis means" refers to a device or software that analyzes learner input data and identifies the learner's learning style and level of understanding.

[0120] "Plan proposal means" refers to a device or software that proposes the optimal learning plan to a learner based on the analysis results obtained by the AI ​​analysis means.

[0121] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learning plan based on a learner's progress and learning pace.

[0122] "Automatic response means" means a device or software that generates and provides immediate answers to questions posed by learners through communication software.

[0123] "Detailed explanation means" refers to a device or software for providing detailed explanations for answers to past exam questions.

[0124] "Real-time monitoring means" refers to a device or software for monitoring a learner's learning progress in real time and providing appropriate feedback.

[0125] "Terminal" refers to a device that transfers learners' questions and progress to the server via communication software.

[0126] "Server" refers to a device or system for transmitting answers and feedback generated based on the analysis results to learners via communication software.

[0127] "Communications software" refers to software that provides a means of communication, such as a messenger application.

[0128] The present invention relates to a system that allows learners to easily receive learning support using communication software (e.g., a messenger application). This system is composed of a server, a terminal, and a user, and specific embodiments thereof are described below.

[0129] Collection and analysis of training data

[0130] The user sends learning data (study progress, questions, answers to past exam questions, etc.) through communication software. The device receives the data and automatically transfers it to the server. The server stores the received data in an internal database and analyzes it using AI analysis tools. This analysis is carried out to identify the learner's learning style and level of understanding.

[0131] Examples:

[0132] When a user sends a message via communication software saying, "I didn't understand yesterday's math problem," the device forwards the message to the server, which analyzes the message and identifies the user's weak areas.

[0133] Study plan suggestions

[0134] The server generates an optimal learning plan using the plan suggestion means based on the analysis results obtained by the AI ​​analysis means. This learning plan is personalized based on the learner's level of understanding and learning progress.

[0135] Examples:

[0136] From the analysis results, the server determines that the user has a low level of understanding of mathematics, and then uses the plan suggestion means to generate a study plan such as "Focus on mathematics for one hour every day for the next week" and send it to the user.

[0137] Schedule optimization

[0138] When a user sends a specific condition (e.g., "There are only 10 days left until the next exam") via the communication software, the device forwards the information to the server, which uses a schedule optimization tool to calculate a new schedule and sends the optimized schedule to the user.

[0139] Examples:

[0140] When a user sends an email saying, "There are only 10 days left until the next exam," the server uses that information to suggest a schedule that includes "focusing on physics for the first three days, chemistry for the next three days, and reviewing all subjects for the remaining four days."

[0141] Automated Question Answering

[0142] When a user inputs a question into the communication software, the terminal transfers the question to the server, which uses an automatic response means to analyze the question and generate an appropriate answer, which is then sent to the user.

[0143] Examples:

[0144] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[0145] Detailed explanations of past exam answers

[0146] When a user sends answers to past exam questions using the communication software, the terminal transfers the answers to the server, which uses the detailed explanation means to analyze the answers and generate detailed feedback, which is then sent to the user.

[0147] Examples:

[0148] When a user submits their "answer to a past exam question," the server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[0149] Real-time monitoring and feedback

[0150] The user periodically reports their learning progress through the communication software, and the terminal forwards the report to the server, which uses real-time monitoring means to monitor the progress and generate the necessary feedback, which is then sent to the user.

[0151] Examples:

[0152] When a user types, "I solved 10 English problems today," the server sends feedback such as, "That's good enough" or "You're making slow progress on math. Give it a little more time."

[0153] Example prompt sentence:

[0154] 1. "If you find that the user has a low level of understanding of mathematics, please suggest an appropriate learning plan."

[0155] 2. "If the user reports that there are only 10 days until their next exam, generate an efficient study schedule."

[0156] 3. "Generate an answer that explains the law of conservation of energy."

[0157] 4. "Generate detailed explanations for solving past exam questions."

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1: Collect training data

[0160] input:

[0161] Study data (e.g., study progress, questions, answers to past exam questions) sent by users via communication software (e.g., messenger applications)

[0162] Specific behavior:

[0163] The user sends a message saying, "I didn't understand the math problem yesterday." The device receives this message and forwards it to the server.

[0164] output:

[0165] The server receives the message and stores it in a database.

[0166] Step 2: Analyze the training data

[0167] input:

[0168] Learning data stored on the server

[0169] Specific behavior:

[0170] The server uses AI analytics to analyze the data and identify the learner's learning style and level of understanding.

[0171] output:

[0172] Analysis results regarding learners' learning styles and comprehension levels

[0173] Step 3: Propose a study plan

[0174] input:

[0175] Learner analysis results obtained using AI analysis methods

[0176] Specific behavior:

[0177] The server uses the plan suggestion means to generate an optimal learning plan for the learner, and the generated learning plan is sent to the user via the communication software.

[0178] output:

[0179] Personalized learning plans suggested to users

[0180] Examples:

[0181] The server generates a study plan such as "Focus on mathematics for one hour every day for the next week" and sends it to the user.

[0182] Step 4: Optimize your schedule

[0183] input:

[0184] Specific conditions submitted by the user (e.g., "I only have 10 days left until my next exam")

[0185] Specific behavior:

[0186] When a user sends a message via the communication software saying "I only have 10 days until my next exam," the device forwards that information to the server, which uses a schedule optimization tool to calculate a new schedule.

[0187] output:

[0188] User-optimized learning schedule

[0189] Examples:

[0190] The server sends the user a schedule that reads, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[0191] Step 5: Automated Question Answering

[0192] input:

[0193] Questions entered by users in communication software

[0194] Specific behavior:

[0195] When a user submits a question, the terminal forwards the question to the server, which uses an automatic response mechanism to analyze the question and generate an appropriate answer.

[0196] output:

[0197] Instant answers sent to users

[0198] Examples:

[0199] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[0200] Step 6: Detailed explanation of past exam answers

[0201] input:

[0202] Answers to past exam questions sent by users via communication software

[0203] Specific behavior:

[0204] Once the user submits the answer, the device forwards the answer to the server, which uses the detailed explanation means to analyze the answer and generate detailed feedback.

[0205] output:

[0206] Detailed explanation sent to users

[0207] Examples:

[0208] The server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[0209] Step 7: Real-time monitoring and feedback

[0210] input:

[0211] Learning progress reports sent by users via communication software

[0212] Specific behavior:

[0213] The user periodically sends reports, which the terminal then forwards to the server, which uses real-time monitoring means to monitor the progress and generate feedback accordingly.

[0214] output:

[0215] Feedback sent to users

[0216] Examples:

[0217] When a user sends a message saying, "Today I solved 10 English problems," the server generates feedback such as, "That's fine," or "You're not making much progress on math. Give it a little more time," and sends it to the user.

[0218] (Application example 1)

[0219] 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."

[0220] Conventional learning support systems have issues such as being unable to fully address the individual needs of learners, lacking means to properly manage learning progress, limited functionality for responding to questions in real time, and difficulty in dynamically adjusting learning plans. As a result, learners often find it difficult to progress effectively and end up with an inadequate learning experience. The present invention aims to solve these issues by utilizing content delivery and AI models to build a system that provides learning support that meets the individual needs of learners.

[0221] 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.

[0222] In this invention, the server includes: an AI analysis means for analyzing learner input data; a plan proposal means for proposing an optimal study plan for the learner based on the analysis results; a schedule optimization means for dynamically adjusting the study plan based on the learner's progress; an automatic response means for instantly answering questions from the learner via a messenger application; a detailed explanation means for providing detailed explanations of answers to past exam questions; a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback; a content delivery means that is an application installed on a smartphone and delivers content; a generative AI model means that uses a generative AI model for response generation; and a schedule proposal means that proposes an optimal study schedule by using prompt sentences. This allows learners to efficiently receive learning support that meets their individual needs and maximizes their learning effectiveness.

[0223] "Learner" refers to an individual or group of people who learn, understand, and acquire knowledge of content.

[0224] "Input data" refers to information provided by learners to the system, and includes a wide range of information such as progress, questions, and answers to past exam questions.

[0225] "Analysis" refers to the process of understanding, classifying, and evaluating the meaning and characteristics of collected input data.

[0226] "AI analysis means" refers to a part of a system or device that uses artificial intelligence technology to analyze input data.

[0227] "Plan suggestion means" refers to a device or software for generating and suggesting an optimal learning plan for a learner based on the analysis results.

[0228] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learner's learning plan based on the learner's progress and learning pace.

[0229] "Messenger application" refers to software for instant messaging and real-time communication.

[0230] "Automatic response means" refers to a function or device that provides immediate answers to questions from learners.

[0231] "Detailed explanation means" refers to a function or device for providing detailed feedback and explanations on answers to past questions.

[0232] "Real-time monitoring means" refers to a function or device for monitoring a learner's learning progress in real time and providing timely feedback.

[0233] "Content delivery means" refers to a function or device for delivering information and materials necessary for learning to learners.

[0234] "Generative AI model" refers to an artificial intelligence model that uses generative AI technology to generate answers and suggestions based on learners' questions and requests.

[0235] "Prompt sentence" refers to the input sentence that a generative AI model uses to generate appropriate answers or suggestions.

[0236] The "schedule suggestion means" refers to a function or device for suggesting an optimal learning schedule to a learner using prompt sentences.

[0237] The present invention provides a system that allows learners to receive effective learning support through a dedicated application installed on their smartphones.

[0238] The system includes the following means:

[0239] 1. Collecting and analyzing learner data

[0240] Learners use a messenger application to input their progress, questions, answers to past exam questions, etc. The server collects this data and analyzes it using AI analysis tools, such as generative AI models like OpenAI's GPT-3. This makes it possible to identify the learner's level of understanding, weaknesses, and learning progress.

[0241] 2. Study plan suggestions

[0242] Based on the analysis results, the plan suggestion tool proposes the optimal learning plan for the learner. This plan is individually generated based on the learner's level of understanding and progress. The generated plan is provided to the learner via a smartphone application.

[0243] 3. Schedule optimization

[0244] The server uses a schedule optimization method to dynamically adjust the learning schedule based on the learner's progress and learning pace, enabling the learner to progress efficiently.

[0245] 4. Automated Question Answering

[0246] When a learner enters a question through the messenger application, the data is sent to the server, which uses an automatic response tool to analyze the question and generate an appropriate answer. The automatic response tool uses natural language processing technology.

[0247] 5. Detailed explanations of past exam questions

[0248] When a learner submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution steps and related knowledge.

[0249] 6. Real-time monitoring and feedback

[0250] The server uses real-time monitoring means to constantly monitor learning progress and provide appropriate feedback. Progress is reported to the user on a regular basis.

[0251] 7. Content Delivery

[0252] Use content delivery methods to provide learners with materials and information necessary for their studies, including workbooks, instructional videos, and reference materials.

[0253] 8. Generative AI Model and Prompts

[0254] It employs a generative AI model to generate responses and suggest optimal study schedules and answers based on prompts, such as "If there are only 10 days until the next exam, please suggest the optimal study schedule."

[0255] Through these measures, learners can receive learning support tailored to their individual needs, enabling them to study effectively.

[0256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0257] Step 1:

[0258] Using an application installed on their smartphone, users input their study progress, questions, answers to past exam questions, etc. The input data is sent to the server via a messenger application.

[0259] Step 2:

[0260] The server collects the received input data and analyzes it using AI analysis methods, specifically, passing the collected data to a generative AI model to identify the learner's level of understanding and progress.

[0261] Input: User input data (progress information, question content, past exam answers)

[0262] Output: Analysis results (student's understanding, weaknesses, progress)

[0263] Step 3:

[0264] The server generates an individualized learning plan based on the analysis results. Using the plan suggestion means, the server inputs prompt sentences into the generative AI model and proposes the optimal learning plan.

[0265] Input: Analysis results

[0266] Output: Learning plan

[0267] Step 4:

[0268] The server dynamically adjusts the generated learning plan based on the learner's progress, and uses a schedule optimization tool to recalculate the schedule according to the user's current situation.

[0269] Input: Learning plan, learner progress information

[0270] Output: Optimized study schedule

[0271] Step 5:

[0272] When a user enters a question through the messenger application, the data is sent to the server, which uses an automated response tool to analyze the question and generate an appropriate answer using natural language processing technology.

[0273] Input: Question

[0274] Output: The generated answer

[0275] Step 6:

[0276] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation method. Using a generative AI model, it generates a detailed explanation including the solution steps and related knowledge, and provides it to the user.

[0277] Input: Answers to past questions

[0278] Output:Detailed explanation

[0279] Step 7:

[0280] The server constantly monitors the learner's progress using real-time monitoring means, periodically analyzing the progress data and generating and sending appropriate feedback to the user.

[0281] Input: Progress data collected in real time

[0282] Output: Feedback

[0283] Step 8:

[0284] The server uses content distribution means to distribute materials and information necessary for learning to learners, including workbooks, explanatory videos, reference materials, and so on.

[0285] Input: Learner needs and progress information

[0286] Output: The content to be delivered

[0287] Through the above processing steps, users can receive learning support tailored to their individual needs, maximizing the effectiveness of their learning.

[0288] 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.

[0289] The present invention relates to a system that allows learners to easily receive learning support using messenger applications such as LINE, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments of the system are described below.

[0290] 1.Collection and analysis of learning data

[0291] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, etc. The server also uses an emotion engine to analyze the learner's emotional state from the input data.

[0292] Examples:

[0293] When a user sends a message on LINE saying, "I'm tired today, but I want to review math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[0294] 2.Suggested study plan

[0295] Based on the analysis results obtained by the AI ​​analysis means and the emotion analysis results by the emotion engine, the plan proposal means generates and proposes the optimal learning plan for the learner. The proposed content is tailored to the learner's level of understanding and learning progress, and is personalized taking into account their emotional state.

[0296] Examples:

[0297] If the emotion engine identifies the user as being in a "tired" state, the plan suggestion means will suggest a study plan such as "Let's focus on light review questions today."

[0298] 3. Schedule optimization

[0299] The server dynamically adjusts the learning schedule based on the learner's progress, learning pace, and emotional state using a schedule optimization means, allowing the learner to study efficiently and comfortably.

[0300] Examples:

[0301] When a user types into LINE, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to alleviate the pressure.

[0302] 4. Automated Question Answering

[0303] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[0304] Examples:

[0305] When a user asks a question on LINE such as "Please tell me about the law of conservation of energy," the server analyzes the question and searches for or generates an appropriate answer, providing the answer, "The law of conservation of energy is the law that energy remains constant over time."

[0306] 5. Detailed explanations of past exam answers

[0307] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[0308] Examples:

[0309] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[0310] 6. Real-time monitoring and feedback

[0311] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provides timely feedback, and also uses an emotion engine to provide feedback that takes into account the learner's emotional state.

[0312] Examples:

[0313] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends specific feedback such as "This is fine" or "Your progress in math is behind, but please don't rush." ​​based on the emotional state obtained from the emotion engine.

[0314] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing learning plans to answering questions, progress management, and feedback that takes into account their emotional state, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[0315] The processing flow will be explained below.

[0316] DETAILED DESCRIPTION OF THE INVENTION - PROCESS STEPS

[0317] Step 1:

[0318] Users use the LINE application to input learning data, including progress reports, questions, answers to past exam questions, and emotional messages.

[0319] Step 2:

[0320] The device sends the data entered by the user to the server using LINE's API.

[0321] Step 3:

[0322] The server receives the transmitted data and stores it in a database, allowing users' learning status and emotional data to be managed in a unified manner.

[0323] Step 4:

[0324] The server analyzes the stored data using AI analysis tools, including learning style analysis tools to identify learning progress, level of understanding, and specific areas of weakness.

[0325] Step 5:

[0326] The emotion engine analyzes the input data and identifies the learner's emotional state. For example, it extracts emotions such as "tired" or "stressed" from the input text.

[0327] Step 6:

[0328] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which is personalized based on the user's level of understanding, progress, and emotional state.

[0329] Step 7:

[0330] The server sends the generated learning plan to the device.

[0331] Step 8:

[0332] The device will display the study plan to the user as a LINE message, allowing the user to check their daily study plan.

[0333] Step 9:

[0334] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[0335] Step 10:

[0336] The terminal sends a question from the user to the server.

[0337] Step 11:

[0338] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[0339] Step 12:

[0340] The server generates a response and sends it to the terminal.

[0341] Step 13:

[0342] The terminal displays the answer to the user.

[0343] Step 14:

[0344] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[0345] Step 15:

[0346] The terminal sends the answer data for past questions to the server.

[0347] Step 16:

[0348] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[0349] Step 17:

[0350] The server generates commentary and sends feedback to the device.

[0351] Step 18:

[0352] The device displays detailed instructions and feedback to the user.

[0353] Step 19:

[0354] Users report their learning progress via LINE, for example, "I studied for two hours today."

[0355] Step 20:

[0356] The device sends progress data to the server.

[0357] Step 21:

[0358] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[0359] Step 22:

[0360] The server also takes into account the emotional state captured by the emotion engine and generates progress-based feedback, including suggestions for additional study time and motivational messages.

[0361] Step 23:

[0362] The server generates feedback and sends it to the device.

[0363] Step 24:

[0364] The device displays the feedback to the user.

[0365] Step 25:

[0366] The server compares the learning plan with actual progress and dynamically adjusts the learning schedule as needed, taking into account the results of the emotion engine.

[0367] Step 26:

[0368] The server transmits the adjusted schedule to the terminal.

[0369] Step 27:

[0370] The terminal displays the new schedule to the user.

[0371] Example 2

[0372] 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."

[0373] Conventional learning support systems lack the emotional state of learners, making it difficult to provide personalized learning plans based on individual levels of understanding and progress. They also struggle to respond quickly and accurately to learners' questions, significantly impairing learning efficiency. Furthermore, they lack the ability to monitor and provide feedback on learners' progress in real time, often hindering learners' motivation and preventing effective learning.

[0374] 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.

[0375] In this invention, the server includes a data analysis means, a plan proposal means, a schedule optimization means, an automatic response means, a detailed explanation means, a real-time monitoring means, and an emotion analysis means, which enable the server to propose a personalized study plan that takes into account the user's learning progress and emotional state, to provide quick and accurate question responses, to provide detailed explanations, and to monitor and provide feedback on progress in real time.

[0376] "Data analysis means" refers to a means of analyzing input data collected from learners and using the results to grasp the learners' level of understanding and progress.

[0377] The "plan suggestion means" is a means for generating and proposing an optimal learning plan for a learner based on information obtained from the data analysis means and the emotion analysis means.

[0378] A "schedule optimization method" is a method that dynamically adjusts a learner's learning schedule, taking into account the learner's progress and emotional state.

[0379] An "automatic response method" is a method that instantly analyzes questions from learners via a messenger application and generates and provides appropriate answers.

[0380] "Detailed explanation means" is a means of analyzing the content of past questions answered by learners and providing detailed feedback such as solution procedures and related knowledge.

[0381] "Real-time monitoring means" refers to means for constantly monitoring a learner's learning progress and providing immediate feedback as necessary.

[0382] "Emotion analysis means" is a means for analyzing the emotional state of a learner from input data and utilizing that information in other analytical means.

[0383] "Messenger application" refers to a communication platform that enables real-time communication, such as LINE, and is a means for learners to interact with the system.

[0384] "Natural language processing means" refers to means that use technology to analyze and understand questions and input data from learners in natural language.

[0385] This invention relates to a system that allows learners to easily receive learning support using a messenger application, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments are described below.

[0386] The server receives learning data sent by the user through the messenger application. This learning data includes learning progress, questions, answers to past exam questions, etc. The received data is stored in the server and analyzed using data analysis means. This analysis identifies the learner's learning style, level of understanding, and progress. In addition, the emotional state of the learner is analyzed from the input data using emotion analysis means.

[0387] Examples:

[0388] When a user sends a message in a messenger application saying, "I'm tired today, but I want to review my math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[0389] Next, the server uses the plan suggestion means to generate and propose an optimal learning plan for the user based on the information obtained from the data analysis means and emotion analysis means. This learning plan is customized according to the user's level of understanding and progress, and also takes into account their emotional state.

[0390] Examples:

[0391] If the emotion engine identifies the user as being "tired," the server will suggest a study plan such as "Focus on light review questions today."

[0392] Furthermore, the server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state, allowing the user to study efficiently and comfortably.

[0393] Examples:

[0394] When a user types into a messenger application, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to reduce the pressure.

[0395] When a user enters a question through the messenger application, the device sends the question to the server, which then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the user to instantly resolve their doubts.

[0396] Examples:

[0397] When a user asks a question in a messenger application, such as "Tell me about the law of conservation of energy," the server analyzes the question and provides the answer, "The law of conservation of energy is the law that energy remains constant over time."

[0398] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[0399] Examples:

[0400] When a user submits their answer to a past exam question, the server analyzes the answer and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the terminal. The terminal then displays it to the user.

[0401] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide appropriate feedback. Furthermore, by using emotion analysis means, the server can provide feedback that takes into account the user's emotional state.

[0402] Examples:

[0403] When a user periodically reports their learning progress via a messenger application, the server uses that information to evaluate their progress and sends specific feedback based on the emotional state obtained from the emotion engine, such as "You're doing fine" or "You're making slow progress in math, but don't rush."

[0404] As described above, this system allows users to easily receive learning support through a messenger application, and by providing a series of functions ranging from proposing study plans to answering questions, progress management, and feedback that takes into account emotional state, it is possible to reduce users' stress and maximize the effectiveness of their learning.

[0405] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0406] Step 1:

[0407] The user sends the learning data through a messenger application.

[0408] Specific behavior:

[0409] A user types, "I'm tired today but I want to review math," and sends it through a messenger application.

[0410] input:

[0411] User message data (e.g., "I'm tired today, but I want to review math")

[0412] output:

[0413] The user's message data is sent to the server.

[0414] Step 2:

[0415] The terminal transfers the message data received from the user to the server.

[0416] Specific behavior:

[0417] The terminal transmits message data received through the messenger application to the server.

[0418] input:

[0419] Message data received from the user

[0420] output:

[0421] The message data is sent to the server.

[0422] Step 3:

[0423] The server stores the received data and analyzes it using a data analysis means.

[0424] Specific behavior:

[0425] The server stores the message data in a database and analyzes the message content using AI analysis tools.

[0426] input:

[0427] Stored message data

[0428] output:

[0429] Analyzed learning progress data and comprehension data

[0430] Step 4:

[0431] The server uses emotion analysis means to analyze the user's emotional state from the data.

[0432] Specific behavior:

[0433] The server uses an AI model to perform emotion analysis and identify the user's emotional state.

[0434] input:

[0435] User message data

[0436] output:

[0437] Sentiment analysis results (e.g., "Tired")

[0438] Step 5:

[0439] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the user based on the information obtained from the data analysis means and the emotion analysis means.

[0440] Specific behavior:

[0441] Based on the analysis results, the server uses an AI model to generate an optimal study plan and suggests it through the messenger application.

[0442] input:

[0443] Analysis results (learning progress data, emotion analysis results)

[0444] output:

[0445] Generated study plans (e.g., "Focus on light review questions today")

[0446] Step 6:

[0447] The server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state.

[0448] Specific behavior:

[0449] The server uses the AI ​​model to recalculate the user's schedule and provides the adjusted schedule to the user through the messenger application.

[0450] input:

[0451] User progress data, emotional state data

[0452] output:

[0453] Coordinated study schedule

[0454] Step 7:

[0455] The user enters a question through a messenger application, and the device sends the question to the server.

[0456] Specific behavior:

[0457] The user asks a question such as "Please tell me about the law of conservation of energy," and the device sends the question to the server.

[0458] input:

[0459] User question data

[0460] output:

[0461] The query data is sent to the server.

[0462] Step 8:

[0463] The server uses an automatic response means to analyze the question and automatically generate and provide an appropriate answer.

[0464] Specific behavior:

[0465] The server uses natural language processing means to analyze the question, generate an appropriate answer, and send it back to the user through the messenger application.

[0466] input:

[0467] User question data

[0468] output:

[0469] Generated answers (e.g., "The law of conservation of energy is the law that energy remains constant over time.")

[0470] Step 9:

[0471] When a user submits an answer to a past question, the terminal transfers the answer to the server.

[0472] Specific behavior:

[0473] The user inputs the answer, and the terminal transmits the answer data to the server.

[0474] input:

[0475] User's past exam answer data

[0476] output:

[0477] The answer data is sent to the server.

[0478] Step 10:

[0479] The server uses a detailed explanation facility to analyze the answer and provide detailed feedback.

[0480] Specific behavior:

[0481] The server analyzes the answers to past exam questions, generates detailed explanations including the steps and thinking behind the solutions, and provides them to users via a messenger application.

[0482] input:

[0483] User's past exam answer data

[0484] output:

[0485] Detailed explanation (e.g., "You need to solve this problem using Newton's second law. First, consider the balance of forces...")

[0486] Step 11:

[0487] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide immediate feedback as needed.

[0488] Specific behavior:

[0489] The server uses an AI model to analyze the user's learning progress in real time and sends feedback based on the progress through a messenger application.

[0490] input:

[0491] User progress data

[0492] output:

[0493] Feedback (e.g., "You're doing well" or "You're not making much progress in math, but please keep trying")

[0494] (Application example 2)

[0495] 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."

[0496] Conventional learning support systems are primarily designed for use in online environments and lack integration with in-store learning support. Furthermore, it is difficult to provide personalized feedback and propose learning plans that take into account the learner's emotional state, making it difficult to maximize learning efficiency. Furthermore, the lack of features such as real-time learning progress monitoring and instant question-answering in the in-store environment makes it difficult for learners to effectively advance their learning in-store.

[0497] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an AI analysis means for collecting and analyzing learner input data, a plan proposal means for proposing an optimal study plan for the learner based on the analysis results, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering questions from the learner via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback, a physical store linkage means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state via a smartphone application. This enables the learner to effectively study at a physical store and receive personalized feedback and study plan proposals based on their emotional state.

[0498] "Learner" refers to an individual who participates in a learning activity to acquire knowledge or skills.

[0499] "Input data" refers to the information that learners provide to the learning system, including their learning progress, questions, and answers to past questions.

[0500] "AI analysis methods" refers to technology that uses artificial intelligence to analyze input data and identify a learner's learning style, level of understanding, emotional state, etc.

[0501] "Plan proposal means" refers to technology for generating and proposing optimal learning plans for learners based on the analysis results of the AI ​​analysis means.

[0502] "Schedule optimization means" refers to technology that dynamically adjusts learning plans based on a learner's progress and provides an optimal schedule.

[0503] "Messenger application" refers to application software for sending and receiving messages in real time over the Internet.

[0504] "Automatic response means" refers to technology that generates and provides instant answers to questions from learners.

[0505] "Detailed explanation means" refers to technology for generating and providing detailed explanations for answers to past questions.

[0506] "Real-time monitoring means" refers to technology that constantly monitors learners' learning progress and provides appropriate feedback in real time.

[0507] "Physical store integration means" refers to the technology and systems established to provide learning support within physical stores.

[0508] "Emotion analysis means" refers to technology for analyzing a learner's emotional state and providing emotion-based feedback.

[0509] A system for implementing this invention includes an AI analysis means for collecting and analyzing input data from learners, a plan proposal means for proposing an optimal study plan for a learner, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering learners' questions via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a physical store collaboration means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state.

[0510] The server first collects the learner's input data and analyzes it using AI analysis tools. At this time, it uses natural language processing technology to understand the content of the message entered by the learner and extract important information. It also uses emotion analysis tools (e.g., Emotion API) to identify the learner's emotional state.

[0511] Based on the analysis results obtained by the AI ​​analysis means and the emotional state obtained by the emotion analysis means, the server uses the plan suggestion means to generate and suggest an optimal learning plan for each learner. This learning plan is personalized, taking into consideration the learner's progress, level of understanding, and emotional state.

[0512] Depending on the progress, the server dynamically adjusts the learning plan using a schedule optimization means, providing the learner with a schedule that includes relaxation and appropriate breaks.

[0513] When a learner enters a question on the messenger application, the server analyzes the question using an automatic response means, generates an appropriate answer, and provides it immediately, using natural language processing means to understand the meaning of the question and retrieve the answer from a related knowledge database.

[0514] Furthermore, when a learner submits an answer to a past question, the server uses a detailed explanation means to analyze the answer and provide detailed feedback including the solution procedure and related knowledge.

[0515] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback and advice in real time as needed. It also uses emotion analysis means to provide feedback that takes into account the learner's emotional state.

[0516] To realize learning support in physical stores, a smartphone application is provided via a physical store linkage method. This application is designed to allow learners to adjust their learning plans, receive questions and receive emotional feedback in real time while studying in the store.

[0517] As a specific example, if a learner sends a message saying, "I'm a little tired today, but I'd like to review science," the server will use emotion analysis to identify the state of "tired" and suggest, "You seem tired today. Let's start with some light review questions."

[0518] An example of a prompt is:

[0519] "My child is not making progress in math, what should I do?"

[0520] The server would respond with, "It looks like you're not making much progress with math. Take your time and try this plan: easy-to-follow video tutorials and light practice problems."

[0521] In this way, by using the system of the present invention, learners can receive consistent learning support even in a physical store environment, allowing them to study effectively and efficiently.

[0522] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0523] Step 1:

[0524] A user sends input data related to their learning (e.g., learning progress, questions, emotional state) through a messenger application. Input: User's message. Output: Message data received by the server.

[0525] Step 2:

[0526] The server uses AI analysis means to analyze message data received from users. At this time, natural language processing technology (e.g., NLP model) is used to extract important information (e.g., learning content, questions, emotional expressions). Input: Message data. Output: Analyzed information (e.g., learning content, questions, emotional state).

[0527] Step 3:

[0528] Using emotion analysis tools (e.g., Emotion API), analyze the learner's emotional state contained in the message data. Input: Message data. Output: Learner's emotional state (e.g., tired, nervous).

[0529] Step 4:

[0530] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the learner based on the analysis results and emotional state. Input: Analyzed information and emotional state. Output: Individualized learning plan.

[0531] Step 5:

[0532] The server uses schedule optimization techniques to dynamically adjust the learning plan according to the user's progress. Input: Learning plan and progress data. Output: Optimized learning schedule.

[0533] Step 6:

[0534] When a user inputs a question through the messenger application, the server uses an automatic response means to analyze the question and utilizes natural language processing means to generate an appropriate answer. Input: Question message. Output: Generated answer.

[0535] Step 7:

[0536] When a user submits an answer to a past question, the server analyzes the answer using detailed explanation means and generates detailed feedback including solution steps and related knowledge. Input: Answer to past question. Output: Detailed explanation feedback.

[0537] Step 8:

[0538] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback in real time as needed. Input: Progress data. Output: Real-time feedback.

[0539] Step 9:

[0540] Through the brick-and-mortar integration method, as learners progress through their learning in-store, the smartphone application supports all of the above steps, adjusting their learning plans, answering questions, and providing emotional feedback in real time. Input: Learning data from the brick-and-mortar store. Output: Real-time support provided in-store.

[0541] 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.

[0542] 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.

[0543] 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.

[0544] [Second embodiment]

[0545] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] 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.

[0556] 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."

[0557] The present invention relates to a system that enables learners to easily receive learning support using a messenger application such as LINE, and specific embodiments thereof will be described below.

[0558] 1.Collection and analysis of learning data

[0559] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, and other information.

[0560] Examples:

[0561] When a user sends a message on LINE saying, "I didn't understand yesterday's math problem," the server receives the data and uses AI analysis to identify which areas the user is weak in.

[0562] 2.Suggested study plan

[0563] Based on the analysis results obtained by the AI ​​analysis means, the plan proposal means generates and proposes an optimal learning plan for the learner. The proposed content is personalized and tailored to the learner's level of understanding and learning progress.

[0564] Examples:

[0565] If the AI ​​analysis means identifies that the user has a low level of understanding of mathematics, the plan suggestion means will suggest a specific study plan such as "Focus on mathematics for one hour every day for the next week."

[0566] 3. Schedule optimization

[0567] The server dynamically adjusts the learning schedule based on the learner's progress and learning pace using a schedule optimization means, allowing the learner to progress efficiently.

[0568] Examples:

[0569] When a user types into LINE, "There are only 10 days left until the next exam," the server recalculates the schedule based on that information and presents a specific schedule such as, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[0570] 4. Automated Question Answering

[0571] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[0572] Examples:

[0573] When a user asks a question on LINE, such as "Please tell me about the law of conservation of energy," the server analyzes the question, automatically generates an answer -- "The law of conservation of energy is the law that energy remains constant over time" -- and sends it to the device, which then displays it to the user.

[0574] 5. Detailed explanations of past exam answers

[0575] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[0576] Examples:

[0577] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[0578] 6. Real-time monitoring and feedback

[0579] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provide timely feedback, allowing the learner to always be aware of their learning situation and make corrections as needed.

[0580] Examples:

[0581] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends feedback such as "This is going well" or "Your progress in math is falling behind. Give it a little more time."

[0582] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing study plans to answering questions and managing progress, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[0583] The processing flow will be explained below.

[0584] Step 1:

[0585] Users use the LINE application to input their learning data, including progress reports, questions, and answers to past exam questions.

[0586] Step 2:

[0587] The device sends the data entered by the user to the server using LINE's API.

[0588] Step 3:

[0589] The server receives the data and stores it in a database.

[0590] Step 4:

[0591] The server analyzes the stored data using AI analytics, which are used to identify learning progress, comprehension, and specific areas of weakness.

[0592] Step 5:

[0593] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which includes prioritizing learning content and allocating learning time.

[0594] Step 6:

[0595] The server sends the generated learning plan to the device.

[0596] Step 7:

[0597] The device displays the learning plan to the user as a LINE message.

[0598] Step 8:

[0599] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[0600] Step 9:

[0601] The terminal sends a question from the user to the server.

[0602] Step 10:

[0603] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[0604] Step 11:

[0605] The server generates a response and sends it to the terminal.

[0606] Step 12:

[0607] The terminal displays the answer to the user.

[0608] Step 13:

[0609] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[0610] Step 14:

[0611] The terminal sends the answer data for past questions to the server.

[0612] Step 15:

[0613] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[0614] Step 16:

[0615] The server generates commentary and sends feedback to the device.

[0616] Step 17:

[0617] The device displays detailed instructions and feedback to the user.

[0618] Step 18:

[0619] Users report their learning progress via LINE, for example, "I studied for two hours today."

[0620] Step 19:

[0621] The device sends progress data to the server.

[0622] Step 20:

[0623] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[0624] Step 21:

[0625] Based on the analysis, the server generates progress-based feedback, including suggestions for additional study time and motivational messages.

[0626] Step 22:

[0627] The server generates feedback and sends it to the device.

[0628] Step 23:

[0629] The device displays the feedback to the user.

[0630] Step 24:

[0631] The learning plan is compared with actual progress, and the server dynamically adjusts the learning schedule as needed.

[0632] Step 25:

[0633] The server transmits the adjusted schedule to the terminal.

[0634] Step 26:

[0635] The terminal displays the new schedule to the user.

[0636] Example 1

[0637] 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."

[0638] Conventional learning support systems lack comprehensive support for learners to efficiently progress through their studies in real time. In particular, they do not propose dynamic learning plans or optimize schedules based on individual learners' progress and level of understanding, which means that learning effectiveness is not fully improved. Furthermore, they lack the ability to respond immediately to questions and provide detailed feedback.

[0639] 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.

[0640] In this invention, the server includes AI analysis means for collecting and analyzing learner input data, plan proposal means for proposing an optimal study plan for the learner based on the analysis results, schedule optimization means for dynamically adjusting the study plan based on the learner's progress, automatic response means for instantly answering questions from the learner through communication software, detailed explanation means for providing detailed explanations of answers to past exam questions, real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a terminal for transferring the learner's questions and progress to the server through communication software, and a server for transmitting answers and feedback generated based on the analysis results to the learner through communication software. This enables the learner to receive real-time and comprehensive learning support.

[0641] "AI analysis means" refers to a device or software that analyzes learner input data and identifies the learner's learning style and level of understanding.

[0642] "Plan proposal means" refers to a device or software that proposes the optimal learning plan to a learner based on the analysis results obtained by the AI ​​analysis means.

[0643] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learning plan based on a learner's progress and learning pace.

[0644] "Automatic response means" means a device or software that generates and provides immediate answers to questions posed by learners through communication software.

[0645] "Detailed explanation means" refers to a device or software for providing detailed explanations for answers to past exam questions.

[0646] "Real-time monitoring means" refers to a device or software for monitoring a learner's learning progress in real time and providing appropriate feedback.

[0647] "Terminal" refers to a device that transfers learners' questions and progress to the server via communication software.

[0648] "Server" refers to a device or system for transmitting answers and feedback generated based on the analysis results to learners via communication software.

[0649] "Communications software" refers to software that provides a means of communication, such as a messenger application.

[0650] The present invention relates to a system that allows learners to easily receive learning support using communication software (e.g., a messenger application). This system is composed of a server, a terminal, and a user, and specific embodiments thereof are described below.

[0651] Collection and analysis of training data

[0652] The user sends learning data (study progress, questions, answers to past exam questions, etc.) through communication software. The device receives the data and automatically transfers it to the server. The server stores the received data in an internal database and analyzes it using AI analysis tools. This analysis is carried out to identify the learner's learning style and level of understanding.

[0653] Examples:

[0654] When a user sends a message via communication software saying, "I didn't understand yesterday's math problem," the device forwards the message to the server, which analyzes the message and identifies the user's weak areas.

[0655] Study plan suggestions

[0656] The server generates an optimal learning plan using the plan suggestion means based on the analysis results obtained by the AI ​​analysis means. This learning plan is personalized based on the learner's level of understanding and learning progress.

[0657] Examples:

[0658] From the analysis results, the server determines that the user has a low level of understanding of mathematics, and then uses the plan suggestion means to generate a study plan such as "Focus on mathematics for one hour every day for the next week" and send it to the user.

[0659] Schedule optimization

[0660] When a user sends a specific condition (e.g., "There are only 10 days left until the next exam") via the communication software, the device forwards the information to the server, which uses a schedule optimization tool to calculate a new schedule and sends the optimized schedule to the user.

[0661] Examples:

[0662] When a user sends an email saying, "There are only 10 days left until the next exam," the server uses that information to suggest a schedule that includes "focusing on physics for the first three days, chemistry for the next three days, and reviewing all subjects for the remaining four days."

[0663] Automated Question Answering

[0664] When a user inputs a question into the communication software, the terminal transfers the question to the server, which uses an automatic response means to analyze the question and generate an appropriate answer, which is then sent to the user.

[0665] Examples:

[0666] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[0667] Detailed explanations of past exam answers

[0668] When a user sends answers to past exam questions using the communication software, the terminal transfers the answers to the server, which uses the detailed explanation means to analyze the answers and generate detailed feedback, which is then sent to the user.

[0669] Examples:

[0670] When a user submits their "answer to a past exam question," the server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[0671] Real-time monitoring and feedback

[0672] The user periodically reports their learning progress through the communication software, and the terminal forwards the report to the server, which uses real-time monitoring means to monitor the progress and generate the necessary feedback, which is then sent to the user.

[0673] Examples:

[0674] When a user types, "I solved 10 English problems today," the server sends feedback such as, "That's good enough" or "You're making slow progress on math. Give it a little more time."

[0675] Example prompt sentence:

[0676] 1. "If you find that the user has a low level of understanding of mathematics, please suggest an appropriate learning plan."

[0677] 2. "If the user reports that there are only 10 days until their next exam, generate an efficient study schedule."

[0678] 3. "Generate an answer that explains the law of conservation of energy."

[0679] 4. "Generate detailed explanations for solving past exam questions."

[0680] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0681] Step 1: Collect training data

[0682] input:

[0683] Study data (e.g., study progress, questions, answers to past exam questions) sent by users via communication software (e.g., messenger applications)

[0684] Specific behavior:

[0685] The user sends a message saying, "I didn't understand the math problem yesterday." The device receives this message and forwards it to the server.

[0686] output:

[0687] The server receives the message and stores it in a database.

[0688] Step 2: Analyze the training data

[0689] input:

[0690] Learning data stored on the server

[0691] Specific behavior:

[0692] The server uses AI analytics to analyze the data and identify the learner's learning style and level of understanding.

[0693] output:

[0694] Analysis results regarding learners' learning styles and comprehension levels

[0695] Step 3: Propose a study plan

[0696] input:

[0697] Learner analysis results obtained using AI analysis methods

[0698] Specific behavior:

[0699] The server uses the plan suggestion means to generate an optimal learning plan for the learner, and the generated learning plan is sent to the user via the communication software.

[0700] output:

[0701] Personalized learning plans suggested to users

[0702] Examples:

[0703] The server generates a study plan such as "Focus on mathematics for one hour every day for the next week" and sends it to the user.

[0704] Step 4: Optimize your schedule

[0705] input:

[0706] Specific conditions submitted by the user (e.g., "I only have 10 days left until my next exam")

[0707] Specific behavior:

[0708] When a user sends a message via the communication software saying "I only have 10 days until my next exam," the device forwards that information to the server, which uses a schedule optimization tool to calculate a new schedule.

[0709] output:

[0710] User-optimized learning schedule

[0711] Examples:

[0712] The server sends the user a schedule that reads, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[0713] Step 5: Automated Question Answering

[0714] input:

[0715] Questions entered by users in communication software

[0716] Specific behavior:

[0717] When a user submits a question, the terminal forwards the question to the server, which uses an automatic response mechanism to analyze the question and generate an appropriate answer.

[0718] output:

[0719] Instant answers sent to users

[0720] Examples:

[0721] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[0722] Step 6: Detailed explanation of past exam answers

[0723] input:

[0724] Answers to past exam questions sent by users via communication software

[0725] Specific behavior:

[0726] Once the user submits the answer, the device forwards the answer to the server, which uses the detailed explanation means to analyze the answer and generate detailed feedback.

[0727] output:

[0728] Detailed explanation sent to users

[0729] Examples:

[0730] The server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[0731] Step 7: Real-time monitoring and feedback

[0732] input:

[0733] Learning progress reports sent by users via communication software

[0734] Specific behavior:

[0735] The user periodically sends reports, which the terminal then forwards to the server, which uses real-time monitoring means to monitor the progress and generate feedback accordingly.

[0736] output:

[0737] Feedback sent to users

[0738] Examples:

[0739] When a user sends a message saying, "Today I solved 10 English problems," the server generates feedback such as, "That's fine," or "You're not making much progress on math. Give it a little more time," and sends it to the user.

[0740] (Application example 1)

[0741] 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."

[0742] Conventional learning support systems have issues such as being unable to fully address the individual needs of learners, lacking means to properly manage learning progress, limited functionality for responding to questions in real time, and difficulty in dynamically adjusting learning plans. As a result, learners often find it difficult to progress effectively and end up with an inadequate learning experience. The present invention aims to solve these issues by utilizing content delivery and AI models to build a system that provides learning support that meets the individual needs of learners.

[0743] 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.

[0744] In this invention, the server includes: an AI analysis means for analyzing learner input data; a plan proposal means for proposing an optimal study plan for the learner based on the analysis results; a schedule optimization means for dynamically adjusting the study plan based on the learner's progress; an automatic response means for instantly answering questions from the learner via a messenger application; a detailed explanation means for providing detailed explanations of answers to past exam questions; a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback; a content delivery means that is an application installed on a smartphone and delivers content; a generative AI model means that uses a generative AI model for response generation; and a schedule proposal means that proposes an optimal study schedule by using prompt sentences. This allows learners to efficiently receive learning support that meets their individual needs and maximizes their learning effectiveness.

[0745] "Learner" refers to an individual or group of people who learn, understand, and acquire knowledge of content.

[0746] "Input data" refers to information provided by learners to the system, and includes a wide range of information such as progress, questions, and answers to past exam questions.

[0747] "Analysis" refers to the process of understanding, classifying, and evaluating the meaning and characteristics of collected input data.

[0748] "AI analysis means" refers to a part of a system or device that uses artificial intelligence technology to analyze input data.

[0749] "Plan suggestion means" refers to a device or software for generating and suggesting an optimal learning plan for a learner based on the analysis results.

[0750] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learner's learning plan based on the learner's progress and learning pace.

[0751] "Messenger application" refers to software for instant messaging and real-time communication.

[0752] "Automatic response means" refers to a function or device that provides immediate answers to questions from learners.

[0753] "Detailed explanation means" refers to a function or device for providing detailed feedback and explanations on answers to past questions.

[0754] "Real-time monitoring means" refers to a function or device for monitoring a learner's learning progress in real time and providing timely feedback.

[0755] "Content delivery means" refers to a function or device for delivering information and materials necessary for learning to learners.

[0756] "Generative AI model" refers to an artificial intelligence model that uses generative AI technology to generate answers and suggestions based on learners' questions and requests.

[0757] "Prompt sentence" refers to the input sentence that a generative AI model uses to generate appropriate answers or suggestions.

[0758] The "schedule suggestion means" refers to a function or device for suggesting an optimal learning schedule to a learner using prompt sentences.

[0759] The present invention provides a system that allows learners to receive effective learning support through a dedicated application installed on their smartphones.

[0760] The system includes the following means:

[0761] 1. Collecting and analyzing learner data

[0762] Learners use a messenger application to input their progress, questions, answers to past exam questions, etc. The server collects this data and analyzes it using AI analysis tools, such as generative AI models like OpenAI's GPT-3. This makes it possible to identify the learner's level of understanding, weaknesses, and learning progress.

[0763] 2. Study plan suggestions

[0764] Based on the analysis results, the plan suggestion tool proposes the optimal learning plan for the learner. This plan is individually generated based on the learner's level of understanding and progress. The generated plan is provided to the learner via a smartphone application.

[0765] 3. Schedule optimization

[0766] The server uses a schedule optimization method to dynamically adjust the learning schedule based on the learner's progress and learning pace, enabling the learner to progress efficiently.

[0767] 4. Automated Question Answering

[0768] When a learner enters a question through the messenger application, the data is sent to the server, which uses an automatic response tool to analyze the question and generate an appropriate answer. The automatic response tool uses natural language processing technology.

[0769] 5. Detailed explanations of past exam questions

[0770] When a learner submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution steps and related knowledge.

[0771] 6. Real-time monitoring and feedback

[0772] The server uses real-time monitoring means to constantly monitor learning progress and provide appropriate feedback. Progress is reported to the user on a regular basis.

[0773] 7. Content Delivery

[0774] Use content delivery methods to provide learners with materials and information necessary for their studies, including workbooks, instructional videos, and reference materials.

[0775] 8. Generative AI Model and Prompts

[0776] It employs a generative AI model to generate responses and suggest optimal study schedules and answers based on prompts, such as "If there are only 10 days until the next exam, please suggest the optimal study schedule."

[0777] Through these measures, learners can receive learning support tailored to their individual needs, enabling them to study effectively.

[0778] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0779] Step 1:

[0780] Using an application installed on their smartphone, users input their study progress, questions, answers to past exam questions, etc. The input data is sent to the server via a messenger application.

[0781] Step 2:

[0782] The server collects the received input data and analyzes it using AI analysis methods, specifically, passing the collected data to a generative AI model to identify the learner's level of understanding and progress.

[0783] Input: User input data (progress information, question content, past exam answers)

[0784] Output: Analysis results (student's understanding, weaknesses, progress)

[0785] Step 3:

[0786] The server generates an individualized learning plan based on the analysis results. Using the plan suggestion means, the server inputs prompt sentences into the generative AI model and proposes the optimal learning plan.

[0787] Input: Analysis results

[0788] Output: Learning plan

[0789] Step 4:

[0790] The server dynamically adjusts the generated learning plan based on the learner's progress, and uses a schedule optimization tool to recalculate the schedule according to the user's current situation.

[0791] Input: Learning plan, learner progress information

[0792] Output: Optimized study schedule

[0793] Step 5:

[0794] When a user enters a question through the messenger application, the data is sent to the server, which uses an automated response tool to analyze the question and generate an appropriate answer using natural language processing technology.

[0795] Input: Question

[0796] Output: The generated answer

[0797] Step 6:

[0798] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation method. Using a generative AI model, it generates a detailed explanation including the solution steps and related knowledge, and provides it to the user.

[0799] Input: Answers to past questions

[0800] Output:Detailed explanation

[0801] Step 7:

[0802] The server constantly monitors the learner's progress using real-time monitoring means, periodically analyzing the progress data and generating and sending appropriate feedback to the user.

[0803] Input: Progress data collected in real time

[0804] Output: Feedback

[0805] Step 8:

[0806] The server uses content distribution means to distribute materials and information necessary for learning to learners, including workbooks, explanatory videos, reference materials, and so on.

[0807] Input: Learner needs and progress information

[0808] Output: The content to be delivered

[0809] Through the above processing steps, users can receive learning support tailored to their individual needs, maximizing the effectiveness of their learning.

[0810] 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.

[0811] The present invention relates to a system that allows learners to easily receive learning support using messenger applications such as LINE, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments of the system are described below.

[0812] 1.Collection and analysis of learning data

[0813] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, etc. The server also uses an emotion engine to analyze the learner's emotional state from the input data.

[0814] Examples:

[0815] When a user sends a message on LINE saying, "I'm tired today, but I want to review math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[0816] 2.Suggested study plan

[0817] Based on the analysis results obtained by the AI ​​analysis means and the emotion analysis results by the emotion engine, the plan proposal means generates and proposes the optimal learning plan for the learner. The proposed content is tailored to the learner's level of understanding and learning progress, and is personalized taking into account their emotional state.

[0818] Examples:

[0819] If the emotion engine identifies the user as being in a "tired" state, the plan suggestion means will suggest a study plan such as "Let's focus on light review questions today."

[0820] 3. Schedule optimization

[0821] The server dynamically adjusts the learning schedule based on the learner's progress, learning pace, and emotional state using a schedule optimization means, allowing the learner to study efficiently and comfortably.

[0822] Examples:

[0823] When a user types into LINE, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to alleviate the pressure.

[0824] 4. Automated Question Answering

[0825] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[0826] Examples:

[0827] When a user asks a question on LINE such as "Please tell me about the law of conservation of energy," the server analyzes the question and searches for or generates an appropriate answer, providing the answer, "The law of conservation of energy is the law that energy remains constant over time."

[0828] 5. Detailed explanations of past exam answers

[0829] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[0830] Examples:

[0831] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[0832] 6. Real-time monitoring and feedback

[0833] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provides timely feedback, and also uses an emotion engine to provide feedback that takes into account the learner's emotional state.

[0834] Examples:

[0835] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends specific feedback such as "This is fine" or "Your progress in math is behind, but please don't rush." ​​based on the emotional state obtained from the emotion engine.

[0836] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing learning plans to answering questions, progress management, and feedback that takes into account their emotional state, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[0837] The processing flow will be explained below.

[0838] DETAILED DESCRIPTION OF THE INVENTION - PROCESS STEPS

[0839] Step 1:

[0840] Users use the LINE application to input learning data, including progress reports, questions, answers to past exam questions, and emotional messages.

[0841] Step 2:

[0842] The device sends the data entered by the user to the server using LINE's API.

[0843] Step 3:

[0844] The server receives the transmitted data and stores it in a database, allowing users' learning status and emotional data to be managed in a unified manner.

[0845] Step 4:

[0846] The server analyzes the stored data using AI analysis tools, including learning style analysis tools to identify learning progress, level of understanding, and specific areas of weakness.

[0847] Step 5:

[0848] The emotion engine analyzes the input data and identifies the learner's emotional state. For example, it extracts emotions such as "tired" or "stressed" from the input text.

[0849] Step 6:

[0850] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which is personalized based on the user's level of understanding, progress, and emotional state.

[0851] Step 7:

[0852] The server sends the generated learning plan to the device.

[0853] Step 8:

[0854] The device will display the study plan to the user as a LINE message, allowing the user to check their daily study plan.

[0855] Step 9:

[0856] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[0857] Step 10:

[0858] The terminal sends a question from the user to the server.

[0859] Step 11:

[0860] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[0861] Step 12:

[0862] The server generates a response and sends it to the terminal.

[0863] Step 13:

[0864] The terminal displays the answer to the user.

[0865] Step 14:

[0866] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[0867] Step 15:

[0868] The terminal sends the answer data for past questions to the server.

[0869] Step 16:

[0870] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[0871] Step 17:

[0872] The server generates commentary and sends feedback to the device.

[0873] Step 18:

[0874] The device displays detailed instructions and feedback to the user.

[0875] Step 19:

[0876] Users report their learning progress via LINE, for example, "I studied for two hours today."

[0877] Step 20:

[0878] The device sends progress data to the server.

[0879] Step 21:

[0880] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[0881] Step 22:

[0882] The server also takes into account the emotional state captured by the emotion engine and generates feedback based on progress, including suggestions for additional study time and motivational messages.

[0883] Step 23:

[0884] The server generates feedback and sends it to the device.

[0885] Step 24:

[0886] The device displays the feedback to the user.

[0887] Step 25:

[0888] The server compares the learning plan with actual progress and dynamically adjusts the learning schedule as needed, taking into account the results of the emotion engine.

[0889] Step 26:

[0890] The server transmits the adjusted schedule to the terminal.

[0891] Step 27:

[0892] The terminal displays the new schedule to the user.

[0893] Example 2

[0894] 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."

[0895] Conventional learning support systems lack the emotional state of learners, making it difficult to provide personalized learning plans based on individual levels of understanding and progress. They also struggle to respond quickly and accurately to learners' questions, significantly impairing learning efficiency. Furthermore, they lack the ability to monitor and provide feedback on learners' progress in real time, often hindering learners' motivation and preventing effective learning.

[0896] 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.

[0897] In this invention, the server includes a data analysis means, a plan proposal means, a schedule optimization means, an automatic response means, a detailed explanation means, a real-time monitoring means, and an emotion analysis means, which enable the server to propose a personalized study plan that takes into account the user's learning progress and emotional state, to provide quick and accurate question responses, to provide detailed explanations, and to monitor and provide feedback on progress in real time.

[0898] "Data analysis means" refers to a means of analyzing input data collected from learners and using the results to grasp the learners' level of understanding and progress.

[0899] The "plan suggestion means" is a means for generating and proposing an optimal learning plan for a learner based on information obtained from the data analysis means and the emotion analysis means.

[0900] A "schedule optimization method" is a method that dynamically adjusts a learner's learning schedule, taking into account the learner's progress and emotional state.

[0901] An "automatic response method" is a method that instantly analyzes questions from learners via a messenger application and generates and provides appropriate answers.

[0902] "Detailed explanation means" is a means of analyzing the content of past questions answered by learners and providing detailed feedback such as solution procedures and related knowledge.

[0903] "Real-time monitoring means" refers to means for constantly monitoring a learner's learning progress and providing immediate feedback as necessary.

[0904] "Emotion analysis means" is a means for analyzing the emotional state of a learner from input data and utilizing that information in other analytical means.

[0905] "Messenger application" refers to a communication platform that enables real-time communication, such as LINE, and is a means for learners to interact with the system.

[0906] "Natural language processing means" refers to means that use technology to analyze and understand questions and input data from learners in natural language.

[0907] This invention relates to a system that allows learners to easily receive learning support using a messenger application, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments are described below.

[0908] The server receives learning data sent by the user through the messenger application. This learning data includes learning progress, questions, answers to past exam questions, etc. The received data is stored in the server and analyzed using data analysis means. This analysis identifies the learner's learning style, level of understanding, and progress. In addition, the emotional state of the learner is analyzed from the input data using emotion analysis means.

[0909] Examples:

[0910] When a user sends a message in a messenger application saying, "I'm tired today, but I want to review my math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[0911] Next, the server uses the plan suggestion means to generate and propose an optimal learning plan for the user based on the information obtained from the data analysis means and emotion analysis means. This learning plan is customized according to the user's level of understanding and progress, and also takes into account their emotional state.

[0912] Examples:

[0913] If the emotion engine identifies the user as being "tired," the server will suggest a study plan such as "Focus on light review questions today."

[0914] Furthermore, the server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state, allowing the user to study efficiently and comfortably.

[0915] Examples:

[0916] When a user types into a messenger application, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to reduce the pressure.

[0917] When a user enters a question through the messenger application, the device sends the question to the server, which then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the user to instantly resolve their doubts.

[0918] Examples:

[0919] When a user asks a question in a messenger application, such as "Tell me about the law of conservation of energy," the server analyzes the question and provides the answer, "The law of conservation of energy is the law that energy remains constant over time."

[0920] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[0921] Examples:

[0922] When a user submits their answer to a past exam question, the server analyzes the answer and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the terminal. The terminal then displays it to the user.

[0923] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide appropriate feedback. Furthermore, by using emotion analysis means, the server can provide feedback that takes into account the user's emotional state.

[0924] Examples:

[0925] When a user periodically reports their learning progress via a messenger application, the server uses that information to evaluate their progress and sends specific feedback based on the emotional state obtained from the emotion engine, such as "You're doing fine" or "You're making slow progress in math, but don't rush."

[0926] As described above, this system allows users to easily receive learning support through a messenger application, and by providing a series of functions ranging from proposing study plans to answering questions, progress management, and feedback that takes into account emotional state, it is possible to reduce users' stress and maximize the effectiveness of their learning.

[0927] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0928] Step 1:

[0929] The user sends the learning data through a messenger application.

[0930] Specific behavior:

[0931] A user types, "I'm tired today but I want to review math," and sends it through a messenger application.

[0932] input:

[0933] User message data (e.g., "I'm tired today, but I want to review math")

[0934] output:

[0935] The user's message data is sent to the server.

[0936] Step 2:

[0937] The terminal transfers the message data received from the user to the server.

[0938] Specific behavior:

[0939] The terminal transmits message data received through the messenger application to the server.

[0940] input:

[0941] Message data received from the user

[0942] output:

[0943] The message data is sent to the server.

[0944] Step 3:

[0945] The server stores the received data and analyzes it using a data analysis means.

[0946] Specific behavior:

[0947] The server stores the message data in a database and analyzes the message content using AI analysis tools.

[0948] input:

[0949] Stored message data

[0950] output:

[0951] Analyzed learning progress data and comprehension data

[0952] Step 4:

[0953] The server uses emotion analysis means to analyze the user's emotional state from the data.

[0954] Specific behavior:

[0955] The server uses an AI model to perform emotion analysis and identify the user's emotional state.

[0956] input:

[0957] User message data

[0958] output:

[0959] Sentiment analysis results (e.g., "Tired")

[0960] Step 5:

[0961] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the user based on the information obtained from the data analysis means and the emotion analysis means.

[0962] Specific behavior:

[0963] Based on the analysis results, the server uses an AI model to generate an optimal study plan and suggests it through the messenger application.

[0964] input:

[0965] Analysis results (learning progress data, emotion analysis results)

[0966] output:

[0967] Generated study plans (e.g., "Focus on light review questions today")

[0968] Step 6:

[0969] The server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state.

[0970] Specific behavior:

[0971] The server uses the AI ​​model to recalculate the user's schedule and provides the adjusted schedule to the user through the messenger application.

[0972] input:

[0973] User progress data, emotional state data

[0974] output:

[0975] Coordinated study schedule

[0976] Step 7:

[0977] The user enters a question through a messenger application, and the device sends the question to the server.

[0978] Specific behavior:

[0979] The user asks a question such as "Please tell me about the law of conservation of energy," and the device sends the question to the server.

[0980] input:

[0981] User question data

[0982] output:

[0983] The query data is sent to the server.

[0984] Step 8:

[0985] The server uses an automatic response means to analyze the question and automatically generate and provide an appropriate answer.

[0986] Specific behavior:

[0987] The server uses natural language processing means to analyze the question, generate an appropriate answer, and send it back to the user through the messenger application.

[0988] input:

[0989] User question data

[0990] output:

[0991] Generated answers (e.g., "The law of conservation of energy is the law that energy remains constant over time.")

[0992] Step 9:

[0993] When a user submits an answer to a past question, the terminal transfers the answer to the server.

[0994] Specific behavior:

[0995] The user inputs the answer, and the terminal transmits the answer data to the server.

[0996] input:

[0997] User's past exam answer data

[0998] output:

[0999] The answer data is sent to the server.

[1000] Step 10:

[1001] The server uses a detailed explanation facility to analyze the answer and provide detailed feedback.

[1002] Specific behavior:

[1003] The server analyzes the answers to past exam questions, generates detailed explanations including the steps and thinking behind the solutions, and provides them to users via a messenger application.

[1004] input:

[1005] User's past exam answer data

[1006] output:

[1007] Detailed explanation (e.g., "You need to solve this problem using Newton's second law. First, consider the balance of forces...")

[1008] Step 11:

[1009] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide immediate feedback as needed.

[1010] Specific behavior:

[1011] The server uses an AI model to analyze the user's learning progress in real time and sends feedback based on the progress through a messenger application.

[1012] input:

[1013] User progress data

[1014] output:

[1015] Feedback (e.g., "You're doing well" or "You're not making much progress in math, but please keep trying")

[1016] (Application example 2)

[1017] 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."

[1018] Conventional learning support systems are primarily designed for use in online environments and lack integration with in-store learning support. Furthermore, it is difficult to provide personalized feedback and propose learning plans that take into account the learner's emotional state, making it difficult to maximize learning efficiency. Furthermore, the lack of features such as real-time learning progress monitoring and instant question-answering in the in-store environment makes it difficult for learners to effectively advance their learning in-store.

[1019] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an AI analysis means for collecting and analyzing learner input data, a plan proposal means for proposing an optimal study plan for the learner based on the analysis results, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering questions from the learner via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback, a physical store linkage means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state via a smartphone application. This enables the learner to effectively study at a physical store and receive personalized feedback and study plan proposals based on their emotional state.

[1020] "Learner" refers to an individual who participates in a learning activity to acquire knowledge or skills.

[1021] "Input data" refers to the information that learners provide to the learning system, including their learning progress, questions, and answers to past questions.

[1022] "AI analysis methods" refers to technology that uses artificial intelligence to analyze input data and identify a learner's learning style, level of understanding, emotional state, etc.

[1023] "Plan proposal means" refers to technology for generating and proposing optimal learning plans for learners based on the analysis results of the AI ​​analysis means.

[1024] "Schedule optimization means" refers to technology that dynamically adjusts learning plans based on a learner's progress and provides an optimal schedule.

[1025] "Messenger application" refers to application software for sending and receiving messages in real time over the Internet.

[1026] "Automatic response means" refers to technology that generates and provides instant answers to questions from learners.

[1027] "Detailed explanation means" refers to technology for generating and providing detailed explanations for answers to past questions.

[1028] "Real-time monitoring means" refers to technology that constantly monitors learners' learning progress and provides appropriate feedback in real time.

[1029] "Physical store integration means" refers to the technology and systems established to provide learning support within physical stores.

[1030] "Emotion analysis means" refers to technology for analyzing a learner's emotional state and providing emotion-based feedback.

[1031] A system for implementing this invention includes an AI analysis means for collecting and analyzing input data from learners, a plan proposal means for proposing an optimal study plan for a learner, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering learners' questions via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a physical store collaboration means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state.

[1032] The server first collects the learner's input data and analyzes it using AI analysis tools. At this time, it uses natural language processing technology to understand the content of the message entered by the learner and extract important information. It also uses emotion analysis tools (e.g., Emotion API) to identify the learner's emotional state.

[1033] Based on the analysis results obtained by the AI ​​analysis means and the emotional state obtained by the emotion analysis means, the server uses the plan suggestion means to generate and suggest an optimal learning plan for each learner. This learning plan is personalized, taking into consideration the learner's progress, level of understanding, and emotional state.

[1034] Depending on the progress, the server dynamically adjusts the learning plan using a schedule optimization means, providing the learner with a schedule that includes relaxation and appropriate breaks.

[1035] When a learner enters a question on the messenger application, the server analyzes the question using an automatic response means, generates an appropriate answer, and provides it immediately, using natural language processing means to understand the meaning of the question and retrieve the answer from a related knowledge database.

[1036] Furthermore, when a learner submits an answer to a past question, the server uses a detailed explanation means to analyze the answer and provide detailed feedback including the solution procedure and related knowledge.

[1037] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback and advice in real time as needed. It also uses emotion analysis means to provide feedback that takes into account the learner's emotional state.

[1038] To realize learning support in physical stores, a smartphone application is provided via a physical store linkage method. This application is designed to allow learners to adjust their learning plans, receive questions and receive emotional feedback in real time while studying in the store.

[1039] As a specific example, if a learner sends a message saying, "I'm a little tired today, but I'd like to review science," the server will use emotion analysis to identify the state of "tired" and suggest, "You seem tired today. Let's start with some light review questions."

[1040] An example of a prompt is:

[1041] "My child is not making progress in math, what should I do?"

[1042] The server would respond with, "It looks like you're not making much progress with math. Take your time and try this plan: easy-to-follow video tutorials and light practice problems."

[1043] In this way, by using the system of the present invention, learners can receive consistent learning support even in a physical store environment, allowing them to study effectively and efficiently.

[1044] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1045] Step 1:

[1046] A user sends input data related to their learning (e.g., learning progress, questions, emotional state) through a messenger application. Input: User's message. Output: Message data received by the server.

[1047] Step 2:

[1048] The server uses AI analysis means to analyze message data received from users. At this time, natural language processing technology (e.g., NLP model) is used to extract important information (e.g., learning content, questions, emotional expressions). Input: Message data. Output: Analyzed information (e.g., learning content, questions, emotional state).

[1049] Step 3:

[1050] Using emotion analysis tools (e.g., Emotion API), analyze the learner's emotional state contained in the message data. Input: Message data. Output: Learner's emotional state (e.g., tired, nervous).

[1051] Step 4:

[1052] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the learner based on the analysis results and emotional state. Input: Analyzed information and emotional state. Output: Individualized learning plan.

[1053] Step 5:

[1054] The server uses schedule optimization techniques to dynamically adjust the learning plan according to the user's progress. Input: Learning plan and progress data. Output: Optimized learning schedule.

[1055] Step 6:

[1056] When a user inputs a question through the messenger application, the server uses an automatic response means to analyze the question and utilizes natural language processing means to generate an appropriate answer. Input: Question message. Output: Generated answer.

[1057] Step 7:

[1058] When a user submits an answer to a past question, the server analyzes the answer using detailed explanation means and generates detailed feedback including solution steps and related knowledge. Input: Answer to past question. Output: Detailed explanation feedback.

[1059] Step 8:

[1060] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback in real time as needed. Input: Progress data. Output: Real-time feedback.

[1061] Step 9:

[1062] Through the brick-and-mortar integration method, as learners progress through their learning in-store, the smartphone application supports all of the above steps, adjusting their learning plans, answering questions, and providing emotional feedback in real time. Input: Learning data from the brick-and-mortar store. Output: Real-time support provided in-store.

[1063] 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.

[1064] 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.

[1065] 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.

[1066] [Third embodiment]

[1067] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1068] 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.

[1069] 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).

[1070] 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.

[1071] 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.

[1072] 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).

[1073] 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.

[1074] 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.

[1075] 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.

[1076] 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.

[1077] 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.

[1078] 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."

[1079] The present invention relates to a system that enables learners to easily receive learning support using a messenger application such as LINE, and specific embodiments thereof will be described below.

[1080] 1.Collection and analysis of learning data

[1081] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, and other information.

[1082] Examples:

[1083] When a user sends a message on LINE saying, "I didn't understand yesterday's math problem," the server receives the data and uses AI analysis to identify which areas the user is weak in.

[1084] 2.Suggested study plan

[1085] Based on the analysis results obtained by the AI ​​analysis means, the plan proposal means generates and proposes an optimal learning plan for the learner. The proposed content is personalized and tailored to the learner's level of understanding and learning progress.

[1086] Examples:

[1087] If the AI ​​analysis means identifies that the user has a low level of understanding of mathematics, the plan suggestion means will suggest a specific study plan such as "Focus on mathematics for one hour every day for the next week."

[1088] 3. Schedule optimization

[1089] The server uses a schedule optimization means to dynamically adjust the learning schedule based on the learner's progress and learning pace, allowing the learner to progress efficiently.

[1090] Examples:

[1091] When a user types into LINE, "There are only 10 days left until the next exam," the server recalculates the schedule based on that information and presents a specific schedule such as, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[1092] 4. Automated Question Answering

[1093] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[1094] Examples:

[1095] When a user asks a question on LINE, such as "Please tell me about the law of conservation of energy," the server analyzes the question, automatically generates an answer -- "The law of conservation of energy is the law that energy remains constant over time" -- and sends it to the device, which then displays it to the user.

[1096] 5. Detailed explanations of past exam answers

[1097] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[1098] Examples:

[1099] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[1100] 6. Real-time monitoring and feedback

[1101] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provide timely feedback, allowing the learner to always be aware of their learning situation and make corrections as needed.

[1102] Examples:

[1103] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends feedback such as "This is going well" or "Your progress in math is falling behind. Give it a little more time."

[1104] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing study plans to answering questions and managing progress, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[1105] The processing flow will be explained below.

[1106] Step 1:

[1107] Users use the LINE application to input their learning data, including progress reports, questions, and answers to past exam questions.

[1108] Step 2:

[1109] The device sends the data entered by the user to the server using LINE's API.

[1110] Step 3:

[1111] The server receives the data and stores it in a database.

[1112] Step 4:

[1113] The server analyzes the stored data using AI analytics, which are used to identify learning progress, comprehension, and specific areas of weakness.

[1114] Step 5:

[1115] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which includes prioritizing learning content and allocating learning time.

[1116] Step 6:

[1117] The server sends the generated learning plan to the device.

[1118] Step 7:

[1119] The device displays the learning plan to the user as a LINE message.

[1120] Step 8:

[1121] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[1122] Step 9:

[1123] The terminal sends a question from the user to the server.

[1124] Step 10:

[1125] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[1126] Step 11:

[1127] The server generates a response and sends it to the terminal.

[1128] Step 12:

[1129] The terminal displays the answer to the user.

[1130] Step 13:

[1131] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[1132] Step 14:

[1133] The terminal sends the answer data for past questions to the server.

[1134] Step 15:

[1135] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[1136] Step 16:

[1137] The server generates commentary and sends feedback to the device.

[1138] Step 17:

[1139] The device displays detailed instructions and feedback to the user.

[1140] Step 18:

[1141] Users report their learning progress via LINE, for example, "I studied for two hours today."

[1142] Step 19:

[1143] The device sends progress data to the server.

[1144] Step 20:

[1145] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[1146] Step 21:

[1147] Based on the analysis, the server generates progress-based feedback, including suggestions for additional study time and motivational messages.

[1148] Step 22:

[1149] The server generates feedback and sends it to the device.

[1150] Step 23:

[1151] The device displays the feedback to the user.

[1152] Step 24:

[1153] The learning plan is compared with actual progress, and the server dynamically adjusts the learning schedule as needed.

[1154] Step 25:

[1155] The server transmits the adjusted schedule to the terminal.

[1156] Step 26:

[1157] The terminal displays the new schedule to the user.

[1158] Example 1

[1159] 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."

[1160] Conventional learning support systems lack comprehensive support for learners to efficiently progress through their studies in real time. In particular, they do not propose dynamic learning plans or optimize schedules based on individual learners' progress and level of understanding, which means that learning effectiveness is not fully improved. Furthermore, they lack the ability to respond immediately to questions and provide detailed feedback.

[1161] 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.

[1162] In this invention, the server includes AI analysis means for collecting and analyzing learner input data, plan proposal means for proposing an optimal study plan for the learner based on the analysis results, schedule optimization means for dynamically adjusting the study plan based on the learner's progress, automatic response means for instantly answering questions from the learner through communication software, detailed explanation means for providing detailed explanations of answers to past exam questions, real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a terminal for transferring the learner's questions and progress to the server through communication software, and a server for transmitting answers and feedback generated based on the analysis results to the learner through communication software. This enables the learner to receive real-time and comprehensive learning support.

[1163] "AI analysis means" refers to a device or software that analyzes learner input data and identifies the learner's learning style and level of understanding.

[1164] "Plan proposal means" refers to a device or software that proposes the optimal learning plan to a learner based on the analysis results obtained by the AI ​​analysis means.

[1165] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learning plan based on a learner's progress and learning pace.

[1166] "Automatic response means" means a device or software that generates and provides immediate answers to questions posed by learners through communication software.

[1167] "Detailed explanation means" refers to a device or software for providing detailed explanations for answers to past exam questions.

[1168] "Real-time monitoring means" refers to a device or software for monitoring a learner's learning progress in real time and providing appropriate feedback.

[1169] "Terminal" refers to a device that transfers learners' questions and progress to the server via communication software.

[1170] "Server" refers to a device or system for transmitting answers and feedback generated based on the analysis results to learners via communication software.

[1171] "Communications software" refers to software that provides a means of communication, such as a messenger application.

[1172] The present invention relates to a system that allows learners to easily receive learning support using communication software (e.g., a messenger application). This system is composed of a server, a terminal, and a user, and specific embodiments thereof are described below.

[1173] Collection and analysis of training data

[1174] The user sends learning data (study progress, questions, answers to past exam questions, etc.) through communication software. The device receives the data and automatically transfers it to the server. The server stores the received data in an internal database and analyzes it using AI analysis tools. This analysis is carried out to identify the learner's learning style and level of understanding.

[1175] Examples:

[1176] When a user sends a message via communication software saying, "I didn't understand yesterday's math problem," the device forwards the message to the server, which analyzes the message and identifies the user's weak areas.

[1177] Study plan suggestions

[1178] The server generates an optimal learning plan using the plan suggestion means based on the analysis results obtained by the AI ​​analysis means. This learning plan is personalized based on the learner's level of understanding and learning progress.

[1179] Examples:

[1180] From the analysis results, the server determines that the user has a low level of understanding of mathematics, and then uses the plan suggestion means to generate a study plan such as "Focus on mathematics for one hour every day for the next week" and send it to the user.

[1181] Schedule optimization

[1182] When a user sends a specific condition (e.g., "There are only 10 days left until the next exam") via the communication software, the device forwards the information to the server, which uses a schedule optimization tool to calculate a new schedule and sends the optimized schedule to the user.

[1183] Examples:

[1184] When a user sends an email saying, "There are only 10 days left until the next exam," the server uses that information to suggest a schedule that includes "focusing on physics for the first three days, chemistry for the next three days, and reviewing all subjects for the remaining four days."

[1185] Automated Question Answering

[1186] When a user inputs a question into the communication software, the terminal transfers the question to the server, which uses an automatic response means to analyze the question and generate an appropriate answer, which is then sent to the user.

[1187] Examples:

[1188] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[1189] Detailed explanations of past exam answers

[1190] When a user sends answers to past exam questions using the communication software, the terminal transfers the answers to the server, which uses the detailed explanation means to analyze the answers and generate detailed feedback, which is then sent to the user.

[1191] Examples:

[1192] When a user submits their "answer to a past exam question," the server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[1193] Real-time monitoring and feedback

[1194] The user periodically reports their learning progress through the communication software, and the terminal forwards the report to the server, which uses real-time monitoring means to monitor the progress and generate the necessary feedback, which is then sent to the user.

[1195] Examples:

[1196] When a user types, "I solved 10 English problems today," the server sends feedback such as, "That's good enough" or "You're making slow progress on math. Give it a little more time."

[1197] Example prompt sentence:

[1198] 1. "If you find that the user has a low level of understanding of mathematics, please suggest an appropriate learning plan."

[1199] 2. "If the user reports that there are only 10 days until their next exam, generate an efficient study schedule."

[1200] 3. "Generate an answer that explains the law of conservation of energy."

[1201] 4. "Generate detailed explanations for solving past exam questions."

[1202] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1203] Step 1: Collect training data

[1204] input:

[1205] Study data (e.g., study progress, questions, answers to past exam questions) sent by users via communication software (e.g., messenger applications)

[1206] Specific behavior:

[1207] The user sends a message saying, "I didn't understand the math problem yesterday." The device receives this message and forwards it to the server.

[1208] output:

[1209] The server receives the message and stores it in a database.

[1210] Step 2: Analyze the training data

[1211] input:

[1212] Learning data stored on the server

[1213] Specific behavior:

[1214] The server uses AI analytics to analyze the data and identify the learner's learning style and level of understanding.

[1215] output:

[1216] Analysis results regarding learners' learning styles and comprehension levels

[1217] Step 3: Propose a study plan

[1218] input:

[1219] Learner analysis results obtained using AI analysis methods

[1220] Specific behavior:

[1221] The server uses the plan suggestion means to generate an optimal learning plan for the learner, and the generated learning plan is sent to the user via the communication software.

[1222] output:

[1223] Personalized learning plans suggested to users

[1224] Examples:

[1225] The server generates a study plan such as "Focus on mathematics for one hour every day for the next week" and sends it to the user.

[1226] Step 4: Optimize your schedule

[1227] input:

[1228] Specific conditions submitted by the user (e.g., "I only have 10 days left until my next exam")

[1229] Specific behavior:

[1230] When a user sends a message via the communication software saying "I only have 10 days until my next exam," the device forwards that information to the server, which uses a schedule optimization tool to calculate a new schedule.

[1231] output:

[1232] User-optimized learning schedule

[1233] Examples:

[1234] The server sends the user a schedule that reads, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[1235] Step 5: Automated Question Answering

[1236] input:

[1237] Questions entered by users in communication software

[1238] Specific behavior:

[1239] When a user submits a question, the terminal forwards the question to the server, which uses an automatic response mechanism to analyze the question and generate an appropriate answer.

[1240] output:

[1241] Instant answers sent to users

[1242] Examples:

[1243] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[1244] Step 6: Detailed explanation of past exam answers

[1245] input:

[1246] Answers to past exam questions sent by users via communication software

[1247] Specific behavior:

[1248] Once the user submits the answer, the device forwards the answer to the server, which uses the detailed explanation means to analyze the answer and generate detailed feedback.

[1249] output:

[1250] Detailed explanation sent to users

[1251] Examples:

[1252] The server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[1253] Step 7: Real-time monitoring and feedback

[1254] input:

[1255] Learning progress reports sent by users via communication software

[1256] Specific behavior:

[1257] The user periodically sends reports, which the terminal then forwards to the server, which uses real-time monitoring means to monitor the progress and generate feedback accordingly.

[1258] output:

[1259] Feedback sent to users

[1260] Examples:

[1261] When a user sends a message saying, "Today I solved 10 English problems," the server generates feedback such as, "That's good enough," or "You're not making much progress on math. Give it a little more time," and sends it to the user.

[1262] (Application example 1)

[1263] 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."

[1264] Conventional learning support systems have issues such as being unable to fully address the individual needs of learners, lacking means to properly manage learning progress, limited functionality for responding to questions in real time, and difficulty in dynamically adjusting learning plans. As a result, learners often find it difficult to progress effectively and end up with an inadequate learning experience. The present invention aims to solve these issues by utilizing content delivery and AI models to build a system that provides learning support that meets the individual needs of learners.

[1265] 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.

[1266] In this invention, the server includes: an AI analysis means for analyzing learner input data; a plan proposal means for proposing an optimal study plan for the learner based on the analysis results; a schedule optimization means for dynamically adjusting the study plan based on the learner's progress; an automatic response means for instantly answering questions from the learner via a messenger application; a detailed explanation means for providing detailed explanations of answers to past exam questions; a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback; a content delivery means that is an application installed on a smartphone and delivers content; a generative AI model means that uses a generative AI model for response generation; and a schedule proposal means that proposes an optimal study schedule by using prompt sentences. This allows learners to efficiently receive learning support that meets their individual needs and maximizes their learning effectiveness.

[1267] "Learner" refers to an individual or group of people who learn, understand, and acquire knowledge of content.

[1268] "Input data" refers to information provided by learners to the system, and includes a wide range of information such as progress, questions, and answers to past exam questions.

[1269] "Analysis" refers to the process of understanding, classifying, and evaluating the meaning and characteristics of collected input data.

[1270] "AI analysis means" refers to a part of a system or device that uses artificial intelligence technology to analyze input data.

[1271] "Plan suggestion means" refers to a device or software for generating and suggesting an optimal learning plan for a learner based on the analysis results.

[1272] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learner's learning plan based on the learner's progress and learning pace.

[1273] "Messenger application" refers to software for instant messaging and real-time communication.

[1274] "Automatic response means" refers to a function or device that provides immediate answers to questions from learners.

[1275] "Detailed explanation means" refers to a function or device for providing detailed feedback and explanations on answers to past questions.

[1276] "Real-time monitoring means" refers to a function or device for monitoring a learner's learning progress in real time and providing timely feedback.

[1277] "Content delivery means" refers to a function or device for delivering information and materials necessary for learning to learners.

[1278] "Generative AI model" refers to an artificial intelligence model that uses generative AI technology to generate answers and suggestions based on learners' questions and requests.

[1279] "Prompt sentence" refers to the input sentence that a generative AI model uses to generate appropriate answers or suggestions.

[1280] The "schedule suggestion means" refers to a function or device for suggesting an optimal learning schedule to a learner using prompt sentences.

[1281] The present invention provides a system that allows learners to receive effective learning support through a dedicated application installed on their smartphones.

[1282] The system includes the following means:

[1283] 1. Collecting and analyzing learner data

[1284] Learners use a messenger application to input their progress, questions, answers to past exam questions, etc. The server collects this data and analyzes it using AI analysis tools, such as generative AI models like OpenAI's GPT-3. This makes it possible to identify the learner's level of understanding, weaknesses, and learning progress.

[1285] 2. Study plan suggestions

[1286] Based on the analysis results, the plan suggestion tool proposes the optimal learning plan for the learner. This plan is individually generated based on the learner's level of understanding and progress. The generated plan is provided to the learner via a smartphone application.

[1287] 3. Schedule optimization

[1288] The server uses a schedule optimization method to dynamically adjust the learning schedule based on the learner's progress and learning pace, enabling the learner to progress efficiently.

[1289] 4. Automated Question Answering

[1290] When a learner enters a question through the messenger application, the data is sent to the server, which uses an automatic response tool to analyze the question and generate an appropriate answer. The automatic response tool uses natural language processing technology.

[1291] 5. Detailed explanations of past exam questions

[1292] When a learner submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution steps and related knowledge.

[1293] 6. Real-time monitoring and feedback

[1294] The server uses real-time monitoring means to constantly monitor learning progress and provide appropriate feedback. Progress is reported to the user on a regular basis.

[1295] 7. Content Delivery

[1296] Use content delivery methods to provide learners with materials and information necessary for their studies, including workbooks, instructional videos, and reference materials.

[1297] 8. Generative AI Model and Prompts

[1298] It employs a generative AI model to generate responses and suggest optimal study schedules and answers based on prompts, such as "If there are only 10 days until the next exam, please suggest the optimal study schedule."

[1299] Through these measures, learners can receive learning support tailored to their individual needs, enabling them to study effectively.

[1300] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1301] Step 1:

[1302] Using an application installed on their smartphone, users input their study progress, questions, answers to past exam questions, etc. The input data is sent to the server via a messenger application.

[1303] Step 2:

[1304] The server collects the received input data and analyzes it using AI analysis methods, specifically, passing the collected data to a generative AI model to identify the learner's level of understanding and progress.

[1305] Input: User input data (progress information, question content, past exam answers)

[1306] Output: Analysis results (student's understanding, weaknesses, progress)

[1307] Step 3:

[1308] The server generates an individualized learning plan based on the analysis results. Using the plan suggestion means, the server inputs prompt sentences into the generative AI model and proposes the optimal learning plan.

[1309] Input: Analysis results

[1310] Output: Learning plan

[1311] Step 4:

[1312] The server dynamically adjusts the generated learning plan based on the learner's progress, and uses a schedule optimization tool to recalculate the schedule according to the user's current situation.

[1313] Input: Learning plan, learner progress information

[1314] Output: Optimized study schedule

[1315] Step 5:

[1316] When a user enters a question through the messenger application, the data is sent to the server, which uses an automated response tool to analyze the question and generate an appropriate answer using natural language processing technology.

[1317] Input: Question

[1318] Output: The generated answer

[1319] Step 6:

[1320] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation method. Using a generative AI model, it generates a detailed explanation including the solution steps and related knowledge, and provides it to the user.

[1321] Input: Answers to past questions

[1322] Output:Detailed explanation

[1323] Step 7:

[1324] The server constantly monitors the learner's progress using real-time monitoring means, periodically analyzing the progress data and generating and sending appropriate feedback to the user.

[1325] Input: Progress data collected in real time

[1326] Output: Feedback

[1327] Step 8:

[1328] The server uses content distribution means to distribute materials and information necessary for learning to learners, including workbooks, explanatory videos, reference materials, and so on.

[1329] Input: Learner needs and progress information

[1330] Output: The content to be delivered

[1331] Through the above processing steps, users can receive learning support tailored to their individual needs, maximizing the effectiveness of their learning.

[1332] 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.

[1333] The present invention relates to a system that allows learners to easily receive learning support using messenger applications such as LINE, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments of the system are described below.

[1334] 1.Collection and analysis of learning data

[1335] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, etc. The server also uses an emotion engine to analyze the learner's emotional state from the input data.

[1336] Examples:

[1337] When a user sends a message on LINE saying, "I'm tired today, but I want to review math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[1338] 2.Suggested study plan

[1339] Based on the analysis results obtained by the AI ​​analysis means and the emotion analysis results by the emotion engine, the plan proposal means generates and proposes the optimal learning plan for the learner. The proposed content is tailored to the learner's level of understanding and learning progress, and is personalized taking into account their emotional state.

[1340] Examples:

[1341] If the emotion engine identifies the user as being in a "tired" state, the plan suggestion means will suggest a study plan such as "Let's focus on light review questions today."

[1342] 3. Schedule optimization

[1343] The server dynamically adjusts the learning schedule based on the learner's progress, learning pace, and emotional state using a schedule optimization means, allowing the learner to study efficiently and comfortably.

[1344] Examples:

[1345] When a user types into LINE, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to alleviate the pressure.

[1346] 4. Automated Question Answering

[1347] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[1348] Examples:

[1349] When a user asks a question on LINE such as "Please tell me about the law of conservation of energy," the server analyzes the question and searches for or generates an appropriate answer, providing the answer, "The law of conservation of energy is the law that energy remains constant over time."

[1350] 5. Detailed explanations of past exam answers

[1351] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[1352] Examples:

[1353] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[1354] 6. Real-time monitoring and feedback

[1355] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provides timely feedback, and also uses an emotion engine to provide feedback that takes into account the learner's emotional state.

[1356] Examples:

[1357] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends specific feedback such as "This is fine" or "Your progress in math is behind, but please don't rush." ​​based on the emotional state obtained from the emotion engine.

[1358] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing learning plans to answering questions, progress management, and feedback that takes into account their emotional state, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[1359] The processing flow will be explained below.

[1360] DETAILED DESCRIPTION OF THE INVENTION - PROCESS STEPS

[1361] Step 1:

[1362] Users use the LINE application to input learning data, including progress reports, questions, answers to past exam questions, and emotional messages.

[1363] Step 2:

[1364] The device sends the data entered by the user to the server using LINE's API.

[1365] Step 3:

[1366] The server receives the transmitted data and stores it in a database, allowing users' learning status and emotional data to be managed in a unified manner.

[1367] Step 4:

[1368] The server analyzes the stored data using AI analysis tools, including learning style analysis tools to identify learning progress, level of understanding, and specific areas of weakness.

[1369] Step 5:

[1370] The emotion engine analyzes the input data and identifies the learner's emotional state. For example, it extracts emotions such as "tired" or "stressed" from the input text.

[1371] Step 6:

[1372] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which is personalized based on the user's level of understanding, progress, and emotional state.

[1373] Step 7:

[1374] The server sends the generated learning plan to the device.

[1375] Step 8:

[1376] The device will display the study plan to the user as a LINE message, allowing the user to check their daily study plan.

[1377] Step 9:

[1378] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[1379] Step 10:

[1380] The terminal sends a question from the user to the server.

[1381] Step 11:

[1382] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[1383] Step 12:

[1384] The server generates a response and sends it to the terminal.

[1385] Step 13:

[1386] The terminal displays the answer to the user.

[1387] Step 14:

[1388] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[1389] Step 15:

[1390] The terminal sends the answer data for past questions to the server.

[1391] Step 16:

[1392] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[1393] Step 17:

[1394] The server generates commentary and sends feedback to the device.

[1395] Step 18:

[1396] The device displays detailed instructions and feedback to the user.

[1397] Step 19:

[1398] Users report their learning progress via LINE, for example, "I studied for two hours today."

[1399] Step 20:

[1400] The device sends progress data to the server.

[1401] Step 21:

[1402] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[1403] Step 22:

[1404] The server also takes into account the emotional state captured by the emotion engine and generates progress-based feedback, including suggestions for additional study time and motivational messages.

[1405] Step 23:

[1406] The server generates feedback and sends it to the device.

[1407] Step 24:

[1408] The device displays the feedback to the user.

[1409] Step 25:

[1410] The server compares the learning plan with actual progress and dynamically adjusts the learning schedule as needed, taking into account the results of the emotion engine.

[1411] Step 26:

[1412] The server transmits the adjusted schedule to the terminal.

[1413] Step 27:

[1414] The terminal displays the new schedule to the user.

[1415] Example 2

[1416] 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."

[1417] Conventional learning support systems lack the emotional state of learners, making it difficult to provide personalized learning plans based on individual levels of understanding and progress. They also struggle to respond quickly and accurately to learners' questions, significantly impairing learning efficiency. Furthermore, they lack the ability to monitor and provide feedback on learners' progress in real time, often hindering learners' motivation and preventing effective learning.

[1418] 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.

[1419] In this invention, the server includes a data analysis means, a plan proposal means, a schedule optimization means, an automatic response means, a detailed explanation means, a real-time monitoring means, and an emotion analysis means, which enable the server to propose a personalized study plan that takes into account the user's learning progress and emotional state, to provide quick and accurate question responses, to provide detailed explanations, and to monitor and provide feedback on progress in real time.

[1420] "Data analysis means" refers to a means of analyzing input data collected from learners and using the results to grasp the learners' level of understanding and progress.

[1421] The "plan suggestion means" is a means for generating and proposing an optimal learning plan for a learner based on information obtained from the data analysis means and the emotion analysis means.

[1422] A "schedule optimization method" is a method that dynamically adjusts a learner's learning schedule, taking into account the learner's progress and emotional state.

[1423] An "automatic response method" is a method that instantly analyzes questions from learners via a messenger application and generates and provides appropriate answers.

[1424] "Detailed explanation means" is a means of analyzing the content of past questions answered by learners and providing detailed feedback such as solution procedures and related knowledge.

[1425] "Real-time monitoring means" refers to means for constantly monitoring a learner's learning progress and providing immediate feedback as necessary.

[1426] "Emotion analysis means" is a means for analyzing the emotional state of a learner from input data and utilizing that information in other analytical means.

[1427] "Messenger application" refers to a communication platform that enables real-time communication, such as LINE, and is a means for learners to interact with the system.

[1428] "Natural language processing means" refers to means that use technology to analyze and understand questions and input data from learners in natural language.

[1429] This invention relates to a system that allows learners to easily receive learning support using a messenger application, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments are described below.

[1430] The server receives learning data sent by the user through the messenger application. This learning data includes learning progress, questions, answers to past exam questions, etc. The received data is stored in the server and analyzed using data analysis means. This analysis identifies the learner's learning style, level of understanding, and progress. In addition, the emotional state of the learner is analyzed from the input data using emotion analysis means.

[1431] Examples:

[1432] When a user sends a message in a messenger application saying, "I'm tired today, but I want to review my math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[1433] Next, the server uses the plan suggestion means to generate and propose an optimal learning plan for the user based on the information obtained from the data analysis means and emotion analysis means. This learning plan is customized according to the user's level of understanding and progress, and also takes into account their emotional state.

[1434] Examples:

[1435] If the emotion engine identifies the user as being "tired," the server will suggest a study plan such as "Focus on light review questions today."

[1436] Furthermore, the server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state, allowing the user to study efficiently and comfortably.

[1437] Examples:

[1438] When a user types into a messenger application, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to reduce the pressure.

[1439] When a user enters a question through the messenger application, the device sends the question to the server, which then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the user to instantly resolve their doubts.

[1440] Examples:

[1441] When a user asks a question in a messenger application, such as "Tell me about the law of conservation of energy," the server analyzes the question and provides the answer, "The law of conservation of energy is the law that energy remains constant over time."

[1442] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[1443] Examples:

[1444] When a user submits their answer to a past exam question, the server analyzes the answer and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the terminal. The terminal then displays it to the user.

[1445] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide appropriate feedback. Furthermore, by using emotion analysis means, the server can provide feedback that takes into account the user's emotional state.

[1446] Examples:

[1447] When a user periodically reports their learning progress via a messenger application, the server uses that information to evaluate their progress and sends specific feedback based on the emotional state obtained from the emotion engine, such as "You're doing fine" or "You're making slow progress in math, but don't rush."

[1448] As described above, this system allows users to easily receive learning support through a messenger application, and by providing a series of functions ranging from proposing study plans to answering questions, progress management, and feedback that takes into account emotional state, it is possible to reduce users' stress and maximize the effectiveness of their learning.

[1449] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1450] Step 1:

[1451] The user sends the learning data through a messenger application.

[1452] Specific behavior:

[1453] A user types, "I'm tired today but I want to review math," and sends it through a messenger application.

[1454] input:

[1455] User message data (e.g., "I'm tired today, but I want to review math")

[1456] output:

[1457] The user's message data is sent to the server.

[1458] Step 2:

[1459] The terminal transfers the message data received from the user to the server.

[1460] Specific behavior:

[1461] The terminal transmits message data received through the messenger application to the server.

[1462] input:

[1463] Message data received from the user

[1464] output:

[1465] The message data is sent to the server.

[1466] Step 3:

[1467] The server stores the received data and analyzes it using a data analysis means.

[1468] Specific behavior:

[1469] The server stores the message data in a database and analyzes the message content using AI analysis tools.

[1470] input:

[1471] Stored message data

[1472] output:

[1473] Analyzed learning progress data and comprehension data

[1474] Step 4:

[1475] The server uses emotion analysis means to analyze the user's emotional state from the data.

[1476] Specific behavior:

[1477] The server uses an AI model to perform emotion analysis and identify the user's emotional state.

[1478] input:

[1479] User message data

[1480] output:

[1481] Sentiment analysis results (e.g., "Tired")

[1482] Step 5:

[1483] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the user based on the information obtained from the data analysis means and the emotion analysis means.

[1484] Specific behavior:

[1485] Based on the analysis results, the server uses an AI model to generate an optimal study plan and suggests it through the messenger application.

[1486] input:

[1487] Analysis results (learning progress data, emotion analysis results)

[1488] output:

[1489] Generated study plans (e.g., "Focus on light review questions today")

[1490] Step 6:

[1491] The server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state.

[1492] Specific behavior:

[1493] The server uses the AI ​​model to recalculate the user's schedule and provides the adjusted schedule to the user through the messenger application.

[1494] input:

[1495] User progress data, emotional state data

[1496] output:

[1497] Coordinated study schedule

[1498] Step 7:

[1499] The user enters a question through a messenger application, and the device sends the question to the server.

[1500] Specific behavior:

[1501] The user asks a question such as "Please tell me about the law of conservation of energy," and the device sends the question to the server.

[1502] input:

[1503] User question data

[1504] output:

[1505] The query data is sent to the server.

[1506] Step 8:

[1507] The server uses an automatic response means to analyze the question and automatically generate and provide an appropriate answer.

[1508] Specific behavior:

[1509] The server uses natural language processing means to analyze the question, generate an appropriate answer, and send it back to the user through the messenger application.

[1510] input:

[1511] User question data

[1512] output:

[1513] Generated answers (e.g., "The law of conservation of energy is the law that energy remains constant over time.")

[1514] Step 9:

[1515] When a user submits an answer to a past question, the terminal transfers the answer to the server.

[1516] Specific behavior:

[1517] The user inputs the answer, and the terminal transmits the answer data to the server.

[1518] input:

[1519] User's past exam answer data

[1520] output:

[1521] The answer data is sent to the server.

[1522] Step 10:

[1523] The server uses a detailed explanation facility to analyze the answer and provide detailed feedback.

[1524] Specific behavior:

[1525] The server analyzes the answers to past exam questions, generates detailed explanations including the steps and thinking behind the solutions, and provides them to users via a messenger application.

[1526] input:

[1527] User's past exam answer data

[1528] output:

[1529] Detailed explanation (e.g., "You need to solve this problem using Newton's second law. First, consider the balance of forces...")

[1530] Step 11:

[1531] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide immediate feedback as needed.

[1532] Specific behavior:

[1533] The server uses an AI model to analyze the user's learning progress in real time and sends feedback based on the progress through a messenger application.

[1534] input:

[1535] User progress data

[1536] output:

[1537] Feedback (e.g., "You're doing well" or "You're not making much progress in math, but please keep trying")

[1538] (Application example 2)

[1539] 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."

[1540] Conventional learning support systems are primarily designed for use in online environments and lack integration with in-store learning support. Furthermore, it is difficult to provide personalized feedback and propose learning plans that take into account the learner's emotional state, making it difficult to maximize learning efficiency. Furthermore, the lack of features such as real-time learning progress monitoring and instant question-answering in the in-store environment makes it difficult for learners to effectively advance their learning in-store.

[1541] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an AI analysis means for collecting and analyzing learner input data, a plan proposal means for proposing an optimal study plan for the learner based on the analysis results, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering questions from the learner via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback, a physical store linkage means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state via a smartphone application. This enables the learner to effectively study at a physical store and receive personalized feedback and study plan proposals based on their emotional state.

[1542] "Learner" refers to an individual who participates in a learning activity to acquire knowledge or skills.

[1543] "Input data" refers to the information that learners provide to the learning system, including their learning progress, questions, and answers to past questions.

[1544] "AI analysis methods" refers to technology that uses artificial intelligence to analyze input data and identify a learner's learning style, level of understanding, emotional state, etc.

[1545] "Plan proposal means" refers to technology for generating and proposing optimal learning plans for learners based on the analysis results of the AI ​​analysis means.

[1546] "Schedule optimization means" refers to technology that dynamically adjusts learning plans based on a learner's progress and provides an optimal schedule.

[1547] "Messenger application" refers to application software for sending and receiving messages in real time over the Internet.

[1548] "Automatic response means" refers to technology that generates and provides instant answers to questions from learners.

[1549] "Detailed explanation means" refers to technology for generating and providing detailed explanations for answers to past questions.

[1550] "Real-time monitoring means" refers to technology that constantly monitors learners' learning progress and provides appropriate feedback in real time.

[1551] "Physical store integration means" refers to the technology and systems established to provide learning support within physical stores.

[1552] "Emotion analysis means" refers to technology for analyzing a learner's emotional state and providing emotion-based feedback.

[1553] A system for implementing this invention includes an AI analysis means for collecting and analyzing input data from learners, a plan proposal means for proposing an optimal study plan for a learner, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering learners' questions via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a physical store collaboration means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state.

[1554] The server first collects the learner's input data and analyzes it using AI analysis tools. At this time, it uses natural language processing technology to understand the content of the message entered by the learner and extract important information. It also uses emotion analysis tools (e.g., Emotion API) to identify the learner's emotional state.

[1555] Based on the analysis results obtained by the AI ​​analysis means and the emotional state obtained by the emotion analysis means, the server uses the plan suggestion means to generate and suggest an optimal learning plan for each learner. This learning plan is personalized, taking into consideration the learner's progress, level of understanding, and emotional state.

[1556] Depending on the progress, the server dynamically adjusts the learning plan using a schedule optimization means, providing the learner with a schedule that includes relaxation and appropriate breaks.

[1557] When a learner enters a question on the messenger application, the server analyzes the question using an automatic response means, generates an appropriate answer, and provides it immediately, using natural language processing means to understand the meaning of the question and retrieve the answer from a related knowledge database.

[1558] Furthermore, when a learner submits an answer to a past question, the server uses a detailed explanation means to analyze the answer and provide detailed feedback including the solution procedure and related knowledge.

[1559] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback and advice in real time as needed. It also uses emotion analysis means to provide feedback that takes into account the learner's emotional state.

[1560] To realize learning support in physical stores, a smartphone application is provided via a physical store linkage method. This application is designed to allow learners to adjust their learning plans, receive questions and receive emotional feedback in real time while studying in the store.

[1561] As a specific example, if a learner sends a message saying, "I'm a little tired today, but I'd like to review science," the server will use emotion analysis to identify the state of "tired" and suggest, "You seem tired today. Let's start with some light review questions."

[1562] An example of a prompt is:

[1563] "My child is not making progress in math, what should I do?"

[1564] The server would respond with, "It looks like you're not making much progress with math. Take your time and try this plan: easy-to-follow video tutorials and light practice problems."

[1565] In this way, by using the system of the present invention, learners can receive consistent learning support even in a physical store environment, allowing them to study effectively and efficiently.

[1566] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1567] Step 1:

[1568] A user sends input data related to their learning (e.g., learning progress, questions, emotional state) through a messenger application. Input: User's message. Output: Message data received by the server.

[1569] Step 2:

[1570] The server uses AI analysis means to analyze message data received from users. At this time, natural language processing technology (e.g., NLP model) is used to extract important information (e.g., learning content, questions, emotional expressions). Input: Message data. Output: Analyzed information (e.g., learning content, questions, emotional state).

[1571] Step 3:

[1572] Using emotion analysis tools (e.g., Emotion API), analyze the learner's emotional state contained in the message data. Input: Message data. Output: Learner's emotional state (e.g., tired, nervous).

[1573] Step 4:

[1574] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the learner based on the analysis results and emotional state. Input: Analyzed information and emotional state. Output: Individualized learning plan.

[1575] Step 5:

[1576] The server uses schedule optimization techniques to dynamically adjust the learning plan according to the user's progress. Input: Learning plan and progress data. Output: Optimized learning schedule.

[1577] Step 6:

[1578] When a user inputs a question through the messenger application, the server uses an automatic response means to analyze the question and utilizes natural language processing means to generate an appropriate answer. Input: Question message. Output: Generated answer.

[1579] Step 7:

[1580] When a user submits an answer to a past question, the server analyzes the answer using detailed explanation means and generates detailed feedback including solution steps and related knowledge. Input: Answer to past question. Output: Detailed explanation feedback.

[1581] Step 8:

[1582] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback in real time as needed. Input: Progress data. Output: Real-time feedback.

[1583] Step 9:

[1584] Through the brick-and-mortar integration method, as learners progress through their learning in-store, the smartphone application supports all of the above steps, adjusting their learning plans, answering questions, and providing emotional feedback in real time. Input: Learning data from the brick-and-mortar store. Output: Real-time support provided in-store.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] [Fourth embodiment]

[1589] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1590] 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.

[1591] 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).

[1592] 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.

[1593] 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.

[1594] 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).

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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."

[1602] The present invention relates to a system that enables learners to easily receive learning support using a messenger application such as LINE, and specific embodiments thereof will be described below.

[1603] 1.Collection and analysis of learning data

[1604] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, and other information.

[1605] Examples:

[1606] When a user sends a message on LINE saying, "I didn't understand yesterday's math problem," the server receives the data and uses AI analysis to identify which areas the user is weak in.

[1607] 2.Suggested study plan

[1608] Based on the analysis results obtained by the AI ​​analysis means, the plan proposal means generates and proposes an optimal learning plan for the learner. The proposed content is personalized and tailored to the learner's level of understanding and learning progress.

[1609] Examples:

[1610] If the AI ​​analysis means identifies that the user has a low level of understanding of mathematics, the plan suggestion means will suggest a specific study plan such as "Focus on mathematics for one hour every day for the next week."

[1611] 3. Schedule optimization

[1612] The server dynamically adjusts the learning schedule based on the learner's progress and learning pace using a schedule optimization means, allowing the learner to progress efficiently.

[1613] Examples:

[1614] When a user types into LINE, "There are only 10 days left until the next exam," the server recalculates the schedule based on that information and presents a specific schedule such as, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[1615] 4. Automated Question Answering

[1616] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[1617] Examples:

[1618] When a user asks a question on LINE, such as "Please tell me about the law of conservation of energy," the server analyzes the question, automatically generates an answer -- "The law of conservation of energy is the law that energy remains constant over time" -- and sends it to the device, which then displays it to the user.

[1619] 5. Detailed explanations of past exam answers

[1620] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[1621] Examples:

[1622] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[1623] 6. Real-time monitoring and feedback

[1624] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provide timely feedback, allowing the learner to always be aware of their learning situation and make corrections as needed.

[1625] Examples:

[1626] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends feedback such as "This is going well" or "Your progress in math is falling behind. Give it a little more time."

[1627] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing study plans to answering questions and managing progress, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[1628] The processing flow will be explained below.

[1629] Step 1:

[1630] Users use the LINE application to input their learning data, including progress reports, questions, and answers to past exam questions.

[1631] Step 2:

[1632] The device sends the data entered by the user to the server using LINE's API.

[1633] Step 3:

[1634] The server receives the data and stores it in a database.

[1635] Step 4:

[1636] The server analyzes the stored data using AI analytics, which are used to identify learning progress, comprehension, and specific areas of weakness.

[1637] Step 5:

[1638] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which includes prioritizing learning content and allocating learning time.

[1639] Step 6:

[1640] The server sends the generated learning plan to the device.

[1641] Step 7:

[1642] The device displays the learning plan to the user as a LINE message.

[1643] Step 8:

[1644] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[1645] Step 9:

[1646] The terminal sends a question from the user to the server.

[1647] Step 10:

[1648] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[1649] Step 11:

[1650] The server generates a response and sends it to the terminal.

[1651] Step 12:

[1652] The terminal displays the answer to the user.

[1653] Step 13:

[1654] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[1655] Step 14:

[1656] The terminal sends the answer data for past questions to the server.

[1657] Step 15:

[1658] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[1659] Step 16:

[1660] The server generates commentary and sends feedback to the device.

[1661] Step 17:

[1662] The device displays detailed instructions and feedback to the user.

[1663] Step 18:

[1664] Users report their learning progress via LINE, for example, "I studied for two hours today."

[1665] Step 19:

[1666] The device sends progress data to the server.

[1667] Step 20:

[1668] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[1669] Step 21:

[1670] Based on the analysis, the server generates progress-based feedback, including suggestions for additional study time and motivational messages.

[1671] Step 22:

[1672] The server generates feedback and sends it to the device.

[1673] Step 23:

[1674] The device displays the feedback to the user.

[1675] Step 24:

[1676] The learning plan is compared with actual progress, and the server dynamically adjusts the learning schedule as needed.

[1677] Step 25:

[1678] The server transmits the adjusted schedule to the terminal.

[1679] Step 26:

[1680] The terminal displays the new schedule to the user.

[1681] Example 1

[1682] 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."

[1683] Conventional learning support systems lack comprehensive support for learners to efficiently progress through their studies in real time. In particular, they do not propose dynamic learning plans or optimize schedules based on individual learners' progress and level of understanding, which means that learning effectiveness is not fully improved. Furthermore, they lack the ability to respond immediately to questions and provide detailed feedback.

[1684] 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.

[1685] In this invention, the server includes AI analysis means for collecting and analyzing learner input data, plan proposal means for proposing an optimal study plan for the learner based on the analysis results, schedule optimization means for dynamically adjusting the study plan based on the learner's progress, automatic response means for instantly answering questions from the learner through communication software, detailed explanation means for providing detailed explanations of answers to past exam questions, real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a terminal for transferring the learner's questions and progress to the server through communication software, and a server for transmitting answers and feedback generated based on the analysis results to the learner through communication software. This enables the learner to receive real-time and comprehensive learning support.

[1686] "AI analysis means" refers to a device or software that analyzes learner input data and identifies the learner's learning style and level of understanding.

[1687] "Plan proposal means" refers to a device or software that proposes the optimal learning plan to a learner based on the analysis results obtained by the AI ​​analysis means.

[1688] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learning plan based on a learner's progress and learning pace.

[1689] "Automatic response means" means a device or software that generates and provides immediate answers to questions posed by learners through communication software.

[1690] "Detailed explanation means" refers to a device or software for providing detailed explanations for answers to past exam questions.

[1691] "Real-time monitoring means" refers to a device or software for monitoring a learner's learning progress in real time and providing appropriate feedback.

[1692] "Terminal" refers to a device that transfers learners' questions and progress to the server via communication software.

[1693] "Server" refers to a device or system for transmitting answers and feedback generated based on the analysis results to learners via communication software.

[1694] "Communications software" refers to software that provides a means of communication, such as a messenger application.

[1695] The present invention relates to a system that allows learners to easily receive learning support using communication software (e.g., a messenger application). This system is composed of a server, a terminal, and a user, and specific embodiments thereof are described below.

[1696] Collection and analysis of training data

[1697] The user sends learning data (study progress, questions, answers to past exam questions, etc.) through communication software. The device receives the data and automatically transfers it to the server. The server stores the received data in an internal database and analyzes it using AI analysis tools. This analysis is carried out to identify the learner's learning style and level of understanding.

[1698] Examples:

[1699] When a user sends a message via communication software saying, "I didn't understand yesterday's math problem," the device forwards the message to the server, which analyzes the message and identifies the user's weak areas.

[1700] Study plan suggestions

[1701] The server generates an optimal learning plan using the plan suggestion means based on the analysis results obtained by the AI ​​analysis means. This learning plan is personalized based on the learner's level of understanding and learning progress.

[1702] Examples:

[1703] From the analysis results, the server determines that the user has a low level of understanding of mathematics, and then uses the plan suggestion means to generate a study plan such as "Focus on mathematics for one hour every day for the next week" and send it to the user.

[1704] Schedule optimization

[1705] When a user sends a specific condition (e.g., "There are only 10 days left until the next exam") via the communication software, the device forwards the information to the server, which uses a schedule optimization tool to calculate a new schedule and sends the optimized schedule to the user.

[1706] Examples:

[1707] When a user sends an email saying, "There are only 10 days left until the next exam," the server uses that information to suggest a schedule that includes "focusing on physics for the first three days, chemistry for the next three days, and reviewing all subjects for the remaining four days."

[1708] Automated Question Answering

[1709] When a user inputs a question into the communication software, the terminal transfers the question to the server, which uses an automatic response means to analyze the question and generate an appropriate answer, which is then sent to the user.

[1710] Examples:

[1711] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[1712] Detailed explanations of past exam answers

[1713] When a user sends answers to past exam questions using the communication software, the terminal transfers the answers to the server, which uses the detailed explanation means to analyze the answers and generate detailed feedback, which is then sent to the user.

[1714] Examples:

[1715] When a user submits their "answer to a past exam question," the server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[1716] Real-time monitoring and feedback

[1717] The user periodically reports their learning progress through the communication software, and the terminal forwards the report to the server, which uses real-time monitoring means to monitor the progress and generate the necessary feedback, which is then sent to the user.

[1718] Examples:

[1719] When a user types, "I solved 10 English problems today," the server sends feedback such as, "That's good enough" or "You're making slow progress on math. Give it a little more time."

[1720] Example prompt sentence:

[1721] 1. "If you find that the user has a low level of understanding of mathematics, please suggest an appropriate learning plan."

[1722] 2. "If the user reports that there are only 10 days until their next exam, generate an efficient study schedule."

[1723] 3. "Generate an answer that explains the law of conservation of energy."

[1724] 4. "Generate detailed explanations for solving past exam questions."

[1725] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1726] Step 1: Collect training data

[1727] input:

[1728] Study data (e.g., study progress, questions, answers to past exam questions) sent by users via communication software (e.g., messenger applications)

[1729] Specific behavior:

[1730] The user sends a message saying, "I didn't understand the math problem yesterday." The device receives this message and forwards it to the server.

[1731] output:

[1732] The server receives the message and stores it in a database.

[1733] Step 2: Analyze the training data

[1734] input:

[1735] Learning data stored on the server

[1736] Specific behavior:

[1737] The server uses AI analytics to analyze the data and identify the learner's learning style and level of understanding.

[1738] output:

[1739] Analysis results regarding learners' learning styles and comprehension levels

[1740] Step 3: Propose a study plan

[1741] input:

[1742] Learner analysis results obtained using AI analysis methods

[1743] Specific behavior:

[1744] The server uses the plan suggestion means to generate an optimal learning plan for the learner, and the generated learning plan is sent to the user via the communication software.

[1745] output:

[1746] Personalized learning plans suggested to users

[1747] Examples:

[1748] The server generates a study plan such as "Focus on mathematics for one hour every day for the next week" and sends it to the user.

[1749] Step 4: Optimize your schedule

[1750] input:

[1751] Specific conditions submitted by the user (e.g., "I only have 10 days left until my next exam")

[1752] Specific behavior:

[1753] When a user sends a message via the communication software saying "I only have 10 days until my next exam," the device forwards that information to the server, which uses a schedule optimization tool to calculate a new schedule.

[1754] output:

[1755] User-optimized learning schedule

[1756] Examples:

[1757] The server sends the user a schedule that reads, "Focus on physics for the first three days, chemistry for the next three days, and review all subjects for the remaining four days."

[1758] Step 5: Automated Question Answering

[1759] input:

[1760] Questions entered by users in communication software

[1761] Specific behavior:

[1762] When a user submits a question, the terminal forwards the question to the server, which uses an automatic response mechanism to analyze the question and generate an appropriate answer.

[1763] output:

[1764] Instant answers sent to users

[1765] Examples:

[1766] When a user asks, "Please tell me about the law of conservation of energy," the server generates an answer, "The law of conservation of energy is the law that energy remains constant over time," and sends it to the user.

[1767] Step 6: Detailed explanation of past exam answers

[1768] input:

[1769] Answers to past exam questions sent by users via communication software

[1770] Specific behavior:

[1771] Once the user submits the answer, the device forwards the answer to the server, which uses the detailed explanation means to analyze the answer and generate detailed feedback.

[1772] output:

[1773] Detailed explanation sent to users

[1774] Examples:

[1775] The server generates a detailed explanation such as "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the user.

[1776] Step 7: Real-time monitoring and feedback

[1777] input:

[1778] Learning progress reports sent by users via communication software

[1779] Specific behavior:

[1780] The user periodically sends reports, which the terminal then forwards to the server, which uses real-time monitoring means to monitor the progress and generate feedback accordingly.

[1781] output:

[1782] Feedback sent to users

[1783] Examples:

[1784] When a user sends a message saying, "Today I solved 10 English problems," the server generates feedback such as, "That's good enough," or "You're not making much progress on math. Give it a little more time," and sends it to the user.

[1785] (Application example 1)

[1786] 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."

[1787] Conventional learning support systems have issues such as being unable to fully address the individual needs of learners, lacking means to properly manage learning progress, limited functionality for responding to questions in real time, and difficulty in dynamically adjusting learning plans. As a result, learners often find it difficult to progress effectively and end up with an inadequate learning experience. The present invention aims to solve these issues by utilizing content delivery and AI models to build a system that provides learning support that meets the individual needs of learners.

[1788] 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.

[1789] In this invention, the server includes: an AI analysis means for analyzing learner input data; a plan proposal means for proposing an optimal study plan for the learner based on the analysis results; a schedule optimization means for dynamically adjusting the study plan based on the learner's progress; an automatic response means for instantly answering questions from the learner via a messenger application; a detailed explanation means for providing detailed explanations of answers to past exam questions; a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback; a content delivery means that is an application installed on a smartphone and delivers content; a generative AI model means that uses a generative AI model for response generation; and a schedule proposal means that proposes an optimal study schedule by using prompt sentences. This allows learners to efficiently receive learning support that meets their individual needs and maximizes their learning effectiveness.

[1790] "Learner" refers to an individual or group of people who learn, understand, and acquire knowledge of content.

[1791] "Input data" refers to information provided by learners to the system, and includes a wide range of information such as progress, questions, and answers to past exam questions.

[1792] "Analysis" refers to the process of understanding, classifying, and evaluating the meaning and characteristics of collected input data.

[1793] "AI analysis means" refers to a part of a system or device that uses artificial intelligence technology to analyze input data.

[1794] "Plan suggestion means" refers to a device or software for generating and suggesting an optimal learning plan for a learner based on the analysis results.

[1795] "Schedule optimization tool" refers to a device or software that dynamically adjusts a learner's learning plan based on the learner's progress and learning pace.

[1796] "Messenger application" refers to software for instant messaging and real-time communication.

[1797] "Automatic response means" refers to a function or device that provides immediate answers to questions from learners.

[1798] "Detailed explanation means" refers to a function or device for providing detailed feedback and explanations on answers to past questions.

[1799] "Real-time monitoring means" refers to a function or device for monitoring a learner's learning progress in real time and providing timely feedback.

[1800] "Content delivery means" refers to a function or device for delivering information and materials necessary for learning to learners.

[1801] "Generative AI model" refers to an artificial intelligence model that uses generative AI technology to generate answers and suggestions based on learners' questions and requests.

[1802] "Prompt sentence" refers to the input sentence that a generative AI model uses to generate appropriate answers or suggestions.

[1803] The "schedule suggestion means" refers to a function or device for suggesting an optimal learning schedule to a learner using prompt sentences.

[1804] The present invention provides a system that allows learners to receive effective learning support through a dedicated application installed on their smartphones.

[1805] The system includes the following means:

[1806] 1. Collecting and analyzing learner data

[1807] Learners use a messenger application to input their progress, questions, answers to past exam questions, etc. The server collects this data and analyzes it using AI analysis tools, such as generative AI models like OpenAI's GPT-3. This makes it possible to identify the learner's level of understanding, weaknesses, and learning progress.

[1808] 2. Study plan suggestions

[1809] Based on the analysis results, the plan suggestion tool proposes the optimal learning plan for the learner. This plan is individually generated based on the learner's level of understanding and progress. The generated plan is provided to the learner via a smartphone application.

[1810] 3. Schedule optimization

[1811] The server uses a schedule optimization method to dynamically adjust the learning schedule based on the learner's progress and learning pace, enabling the learner to progress efficiently.

[1812] 4. Automated Question Answering

[1813] When a learner enters a question through the messenger application, the data is sent to the server, which uses an automatic response tool to analyze the question and generate an appropriate answer. The automatic response tool uses natural language processing technology.

[1814] 5. Detailed explanations of past exam questions

[1815] When a learner submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution steps and related knowledge.

[1816] 6. Real-time monitoring and feedback

[1817] The server uses real-time monitoring means to constantly monitor learning progress and provide appropriate feedback. Progress is reported to the user on a regular basis.

[1818] 7. Content Delivery

[1819] Use content delivery methods to provide learners with materials and information necessary for their studies, including workbooks, instructional videos, and reference materials.

[1820] 8. Generative AI Model and Prompts

[1821] It employs a generative AI model to generate responses and suggest optimal study schedules and answers based on prompts, such as "If there are only 10 days until the next exam, please suggest the optimal study schedule."

[1822] Through these measures, learners can receive learning support tailored to their individual needs, enabling them to study effectively.

[1823] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1824] Step 1:

[1825] Using an application installed on their smartphone, users input their study progress, questions, answers to past exam questions, etc. The input data is sent to the server via a messenger application.

[1826] Step 2:

[1827] The server collects the received input data and analyzes it using AI analysis methods, specifically, passing the collected data to a generative AI model to identify the learner's level of understanding and progress.

[1828] Input: User input data (progress information, question content, past exam answers)

[1829] Output: Analysis results (student's understanding, weaknesses, progress)

[1830] Step 3:

[1831] The server generates an individualized learning plan based on the analysis results. Using the plan suggestion means, the server inputs prompt sentences into the generative AI model and proposes the optimal learning plan.

[1832] Input: Analysis results

[1833] Output: Learning plan

[1834] Step 4:

[1835] The server dynamically adjusts the generated learning plan based on the learner's progress, and uses a schedule optimization tool to recalculate the schedule according to the user's current situation.

[1836] Input: Learning plan, learner progress information

[1837] Output: Optimized study schedule

[1838] Step 5:

[1839] When a user enters a question through the messenger application, the data is sent to the server, which uses an automated response tool to analyze the question and generate an appropriate answer using natural language processing technology.

[1840] Input: Question

[1841] Output: The generated answer

[1842] Step 6:

[1843] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation method. Using a generative AI model, it generates a detailed explanation including the solution steps and related knowledge, and provides it to the user.

[1844] Input: Answers to past questions

[1845] Output:Detailed explanation

[1846] Step 7:

[1847] The server constantly monitors the learner's progress using real-time monitoring means, periodically analyzing the progress data and generating and sending appropriate feedback to the user.

[1848] Input: Progress data collected in real time

[1849] Output: Feedback

[1850] Step 8:

[1851] The server uses content distribution means to distribute materials and information necessary for learning to learners, including workbooks, explanatory videos, reference materials, and so on.

[1852] Input: Learner needs and progress information

[1853] Output: The content to be delivered

[1854] Through the above processing steps, users can receive learning support tailored to their individual needs, maximizing the effectiveness of their learning.

[1855] 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.

[1856] The present invention relates to a system that allows learners to easily receive learning support using messenger applications such as LINE, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments of the system are described below.

[1857] 1.Collection and analysis of learning data

[1858] The server receives learning data sent by users via LINE, such as learning progress, questions, and answers to past exam questions. The received data is stored on the server and analyzed by AI analysis tools. This analysis identifies the learner's learning style, level of understanding, learning progress, etc. The server also uses an emotion engine to analyze the learner's emotional state from the input data.

[1859] Examples:

[1860] When a user sends a message on LINE saying, "I'm tired today, but I want to review math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[1861] 2.Suggested study plan

[1862] Based on the analysis results obtained by the AI ​​analysis means and the emotion analysis results by the emotion engine, the plan proposal means generates and proposes the optimal learning plan for the learner. The proposed content is tailored to the learner's level of understanding and learning progress, and is personalized taking into account their emotional state.

[1863] Examples:

[1864] If the emotion engine identifies the user as being in a "tired" state, the plan suggestion means will suggest a study plan such as "Let's focus on light review questions today."

[1865] 3. Schedule optimization

[1866] The server dynamically adjusts the learning schedule based on the learner's progress, learning pace, and emotional state using a schedule optimization means, allowing the learner to study efficiently and comfortably.

[1867] Examples:

[1868] When a user types into LINE, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to alleviate the pressure.

[1869] 4. Automated Question Answering

[1870] When a user enters a question through LINE chat, the device sends the question to the server. The server then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the learner to instantly resolve their doubts.

[1871] Examples:

[1872] When a user asks a question on LINE such as "Please tell me about the law of conservation of energy," the server analyzes the question and searches for or generates an appropriate answer, providing the answer, "The law of conservation of energy is the law that energy remains constant over time."

[1873] 5. Detailed explanations of past exam answers

[1874] When a learner solves a past exam question and submits their answer, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[1875] Examples:

[1876] When a user sends their answers to past exam questions via LINE, the server analyzes the answers and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the device, which then displays it to the user.

[1877] 6. Real-time monitoring and feedback

[1878] The server uses real-time monitoring means to constantly monitor the learner's learning progress and provides timely feedback, and also uses an emotion engine to provide feedback that takes into account the learner's emotional state.

[1879] Examples:

[1880] When users periodically report their learning progress via LINE, the server evaluates their progress based on that information and sends specific feedback such as "This is fine" or "Your progress in math is behind, but please don't rush." ​​based on the emotional state obtained from the emotion engine.

[1881] As described above, the present invention allows learners to easily receive learning support on LINE, and by providing a series of functions ranging from proposing learning plans to answering questions, progress management, and feedback that takes into account their emotional state, it is possible to reduce learners' stress and maximize the effectiveness of their learning.

[1882] The processing flow will be explained below.

[1883] DETAILED DESCRIPTION OF THE INVENTION - PROCESS STEPS

[1884] Step 1:

[1885] Users use the LINE application to input learning data, including progress reports, questions, answers to past exam questions, and emotional messages.

[1886] Step 2:

[1887] The device sends the data entered by the user to the server using LINE's API.

[1888] Step 3:

[1889] The server receives the transmitted data and stores it in a database, allowing users' learning status and emotional data to be managed in a unified manner.

[1890] Step 4:

[1891] The server analyzes the stored data using AI analysis tools, including learning style analysis tools to identify learning progress, level of understanding, and specific areas of weakness.

[1892] Step 5:

[1893] The emotion engine analyzes the input data and identifies the learner's emotional state. For example, it extracts emotions such as "tired" or "stressed" from the input text.

[1894] Step 6:

[1895] Based on the analysis results, the plan suggestion tool generates an optimal learning plan, which is personalized based on the user's level of understanding, progress, and emotional state.

[1896] Step 7:

[1897] The server sends the generated learning plan to the device.

[1898] Step 8:

[1899] The device will display the study plan to the user as a LINE message, allowing the user to check their daily study plan.

[1900] Step 9:

[1901] The user inputs a question via LINE, such as "Tell me about Newton's laws of motion."

[1902] Step 10:

[1903] The terminal sends a question from the user to the server.

[1904] Step 11:

[1905] The server uses automated response tools to analyze the question and generate appropriate answers, either retrieved from a database or generated using natural language processing tools.

[1906] Step 12:

[1907] The server generates a response and sends it to the terminal.

[1908] Step 13:

[1909] The terminal displays the answer to the user.

[1910] Step 14:

[1911] The user sends the answers to past exam questions via LINE. For example, the message might say, "I'm sending you the answers to the mechanics questions."

[1912] Step 15:

[1913] The terminal sends the answer data for past questions to the server.

[1914] Step 16:

[1915] The server analyzes the answer with a detailed explanation tool and generates detailed feedback about the accuracy of the answer and the solution method.

[1916] Step 17:

[1917] The server generates commentary and sends feedback to the device.

[1918] Step 18:

[1919] The device displays detailed instructions and feedback to the user.

[1920] Step 19:

[1921] Users report their learning progress via LINE, for example, "I studied for two hours today."

[1922] Step 20:

[1923] The device sends progress data to the server.

[1924] Step 21:

[1925] The server uses real-time monitoring means to analyze progress and evaluate whether learning progress is behind schedule or on track.

[1926] Step 22:

[1927] The server also takes into account the emotional state captured by the emotion engine and generates progress-based feedback, including suggestions for additional study time and motivational messages.

[1928] Step 23:

[1929] The server generates feedback and sends it to the device.

[1930] Step 24:

[1931] The device displays the feedback to the user.

[1932] Step 25:

[1933] The server compares the learning plan with actual progress and dynamically adjusts the learning schedule as needed, taking into account the results of the emotion engine.

[1934] Step 26:

[1935] The server transmits the adjusted schedule to the terminal.

[1936] Step 27:

[1937] The terminal displays the new schedule to the user.

[1938] Example 2

[1939] 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."

[1940] Conventional learning support systems lack the emotional state of learners, making it difficult to provide personalized learning plans based on individual levels of understanding and progress. They also struggle to respond quickly and accurately to learners' questions, significantly impairing learning efficiency. Furthermore, they lack the ability to monitor and provide feedback on learners' progress in real time, often hindering learners' motivation and preventing effective learning.

[1941] 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.

[1942] In this invention, the server includes a data analysis means, a plan proposal means, a schedule optimization means, an automatic response means, a detailed explanation means, a real-time monitoring means, and an emotion analysis means, which enable the server to propose a personalized study plan that takes into account the user's learning progress and emotional state, to provide quick and accurate question responses, to provide detailed explanations, and to monitor and provide feedback on progress in real time.

[1943] "Data analysis means" refers to a means of analyzing input data collected from learners and using the results to grasp the learners' level of understanding and progress.

[1944] The "plan suggestion means" is a means for generating and proposing an optimal learning plan for a learner based on information obtained from the data analysis means and the emotion analysis means.

[1945] A "schedule optimization method" is a method that dynamically adjusts a learner's learning schedule, taking into account the learner's progress and emotional state.

[1946] An "automatic response method" is a method that instantly analyzes questions from learners via a messenger application and generates and provides appropriate answers.

[1947] "Detailed explanation means" is a means of analyzing the content of past questions answered by learners and providing detailed feedback such as solution procedures and related knowledge.

[1948] "Real-time monitoring means" refers to means for constantly monitoring a learner's learning progress and providing immediate feedback as necessary.

[1949] "Emotion analysis means" is a means for analyzing the emotional state of a learner from input data and utilizing that information in other analytical means.

[1950] "Messenger application" refers to a communication platform that enables real-time communication, such as LINE, and is a means for learners to interact with the system.

[1951] "Natural language processing means" refers to means that use technology to analyze and understand questions and input data from learners in natural language.

[1952] This invention relates to a system that allows learners to easily receive learning support using a messenger application, and by combining it with an emotion engine, it is possible to provide feedback and adjust learning plans based on the emotions of individual learners. Specific embodiments are described below.

[1953] The server receives learning data sent by the user through the messenger application. This learning data includes learning progress, questions, answers to past exam questions, etc. The received data is stored in the server and analyzed using data analysis means. This analysis identifies the learner's learning style, level of understanding, and progress. In addition, the emotional state of the learner is analyzed from the input data using emotion analysis means.

[1954] Examples:

[1955] When a user sends a message in a messenger application saying, "I'm tired today, but I want to review my math," the server receives this data and uses an emotion engine to identify the user's "tired" state.

[1956] Next, the server uses the plan suggestion means to generate and propose an optimal learning plan for the user based on the information obtained from the data analysis means and emotion analysis means. This learning plan is customized according to the user's level of understanding and progress, and also takes into account their emotional state.

[1957] Examples:

[1958] If the emotion engine identifies the user as being "tired," the server will suggest a study plan such as "Focus on light review questions today."

[1959] Furthermore, the server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state, allowing the user to study efficiently and comfortably.

[1960] Examples:

[1961] When a user types into a messenger application, "There are only 10 days left until my next exam, and I'm feeling the pressure," the server recalculates the schedule based on that information and presents a specific schedule that includes relaxation plans to reduce the pressure.

[1962] When a user enters a question through the messenger application, the device sends the question to the server, which then uses an automatic response tool to analyze the question and automatically generate and provide an appropriate answer, allowing the user to instantly resolve their doubts.

[1963] Examples:

[1964] When a user asks a question in a messenger application, such as "Tell me about the law of conservation of energy," the server analyzes the question and provides the answer, "The law of conservation of energy is the law that energy remains constant over time."

[1965] When a user submits their answer to a past exam question, the server analyzes the answer using a detailed explanation tool and provides detailed feedback, including the solution procedure, the thinking behind it, and related knowledge.

[1966] Examples:

[1967] When a user submits their answer to a past exam question, the server analyzes the answer and generates a detailed explanation such as, "This problem must be solved using Newton's second law. First, consider the balance of forces..." and sends it to the terminal. The terminal then displays it to the user.

[1968] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide appropriate feedback. Furthermore, by using emotion analysis means, the server can provide feedback that takes into account the user's emotional state.

[1969] Examples:

[1970] When a user periodically reports their learning progress via a messenger application, the server uses that information to evaluate their progress and sends specific feedback based on the emotional state obtained from the emotion engine, such as "You're doing fine" or "You're making slow progress in math, but don't rush."

[1971] As described above, this system allows users to easily receive learning support through a messenger application, and by providing a series of functions ranging from proposing study plans to answering questions, progress management, and feedback that takes into account emotional state, it is possible to reduce users' stress and maximize the effectiveness of their learning.

[1972] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1973] Step 1:

[1974] The user sends the learning data through a messenger application.

[1975] Specific behavior:

[1976] A user types, "I'm tired today but I want to review math," and sends it through a messenger application.

[1977] input:

[1978] User message data (e.g., "I'm tired today, but I want to review math")

[1979] output:

[1980] The user's message data is sent to the server.

[1981] Step 2:

[1982] The terminal transfers the message data received from the user to the server.

[1983] Specific behavior:

[1984] The terminal transmits message data received through the messenger application to the server.

[1985] input:

[1986] Message data received from the user

[1987] output:

[1988] The message data is sent to the server.

[1989] Step 3:

[1990] The server stores the received data and analyzes it using a data analysis means.

[1991] Specific behavior:

[1992] The server stores the message data in a database and analyzes the message content using AI analysis tools.

[1993] input:

[1994] Stored message data

[1995] output:

[1996] Analyzed learning progress data and comprehension data

[1997] Step 4:

[1998] The server uses emotion analysis means to analyze the user's emotional state from the data.

[1999] Specific behavior:

[2000] The server uses an AI model to perform emotion analysis and identify the user's emotional state.

[2001] input:

[2002] User message data

[2003] output:

[2004] Sentiment analysis results (e.g., "Tired")

[2005] Step 5:

[2006] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the user based on the information obtained from the data analysis means and the emotion analysis means.

[2007] Specific behavior:

[2008] Based on the analysis results, the server uses an AI model to generate an optimal study plan and suggests it through the messenger application.

[2009] input:

[2010] Analysis results (learning progress data, emotion analysis results)

[2011] output:

[2012] Generated study plans (e.g., "Focus on light review questions today")

[2013] Step 6:

[2014] The server uses a schedule optimization means to dynamically adjust the learning schedule based on the user's progress, learning pace, and emotional state.

[2015] Specific behavior:

[2016] The server uses the AI ​​model to recalculate the user's schedule and provides the adjusted schedule to the user through the messenger application.

[2017] input:

[2018] User progress data, emotional state data

[2019] output:

[2020] Coordinated study schedule

[2021] Step 7:

[2022] The user enters a question through a messenger application, and the device sends the question to the server.

[2023] Specific behavior:

[2024] The user asks a question such as "Please tell me about the law of conservation of energy," and the device sends the question to the server.

[2025] input:

[2026] User question data

[2027] output:

[2028] The query data is sent to the server.

[2029] Step 8:

[2030] The server uses an automatic response means to analyze the question and automatically generate and provide an appropriate answer.

[2031] Specific behavior:

[2032] The server uses natural language processing means to analyze the question, generate an appropriate answer, and send it back to the user through the messenger application.

[2033] input:

[2034] User question data

[2035] output:

[2036] Generated answers (e.g., "The law of conservation of energy is the law that energy remains constant over time.")

[2037] Step 9:

[2038] When a user submits an answer to a past question, the terminal transfers the answer to the server.

[2039] Specific behavior:

[2040] The user inputs the answer, and the terminal transmits the answer data to the server.

[2041] input:

[2042] User's past exam answer data

[2043] output:

[2044] The answer data is sent to the server.

[2045] Step 10:

[2046] The server uses a detailed explanation facility to analyze the answer and provide detailed feedback.

[2047] Specific behavior:

[2048] The server analyzes the answers to past exam questions, generates detailed explanations including the steps and thinking behind the solutions, and provides them to users via a messenger application.

[2049] input:

[2050] User's past exam answer data

[2051] output:

[2052] Detailed explanation (e.g., "You need to solve this problem using Newton's second law. First, consider the balance of forces...")

[2053] Step 11:

[2054] The server uses real-time monitoring means to constantly monitor the user's learning progress and provide immediate feedback as needed.

[2055] Specific behavior:

[2056] The server uses an AI model to analyze the user's learning progress in real time and sends feedback based on the progress through a messenger application.

[2057] input:

[2058] User progress data

[2059] output:

[2060] Feedback (e.g., "You're doing well" or "You're not making much progress in math, but please keep trying")

[2061] (Application example 2)

[2062] 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."

[2063] Conventional learning support systems are primarily designed for use in online environments and lack integration with in-store learning support. Furthermore, it is difficult to provide personalized feedback and propose learning plans that take into account the learner's emotional state, making it difficult to maximize learning efficiency. Furthermore, the lack of features such as real-time learning progress monitoring and instant question-answering in the in-store environment makes it difficult for learners to effectively advance their learning in-store.

[2064] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an AI analysis means for collecting and analyzing learner input data, a plan proposal means for proposing an optimal study plan for the learner based on the analysis results, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering questions from the learner via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's study progress in real time and providing appropriate feedback, a physical store linkage means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state via a smartphone application. This enables the learner to effectively study at a physical store and receive personalized feedback and study plan proposals based on their emotional state.

[2065] "Learner" refers to an individual who participates in a learning activity to acquire knowledge or skills.

[2066] "Input data" refers to the information that learners provide to the learning system, including their learning progress, questions, and answers to past questions.

[2067] "AI analysis methods" refers to technology that uses artificial intelligence to analyze input data and identify a learner's learning style, level of understanding, emotional state, etc.

[2068] "Plan proposal means" refers to technology for generating and proposing optimal learning plans for learners based on the analysis results of the AI ​​analysis means.

[2069] "Schedule optimization means" refers to technology that dynamically adjusts learning plans based on a learner's progress and provides an optimal schedule.

[2070] "Messenger application" refers to application software for sending and receiving messages in real time over the Internet.

[2071] "Automatic response means" refers to technology that generates and provides instant answers to questions from learners.

[2072] "Detailed explanation means" refers to technology for generating and providing detailed explanations for answers to past questions.

[2073] "Real-time monitoring means" refers to technology that constantly monitors learners' learning progress and provides appropriate feedback in real time.

[2074] "Physical store integration means" refers to the technology and systems established to provide learning support within physical stores.

[2075] "Emotion analysis means" refers to technology for analyzing a learner's emotional state and providing emotion-based feedback.

[2076] A system for implementing this invention includes an AI analysis means for collecting and analyzing input data from learners, a plan proposal means for proposing an optimal study plan for a learner, a schedule optimization means for dynamically adjusting the study plan based on the learner's progress, an automatic response means for instantly answering learners' questions via a messenger application, a detailed explanation means for providing detailed explanations of answers to past exam questions, a real-time monitoring means for monitoring the learner's learning progress in real time and providing appropriate feedback, a physical store collaboration means for providing study support within a physical store, and an emotion analysis means for providing feedback based on the learner's emotional state.

[2077] The server first collects the learner's input data and analyzes it using AI analysis tools. At this time, it uses natural language processing technology to understand the content of the message entered by the learner and extract important information. It also uses emotion analysis tools (e.g., Emotion API) to identify the learner's emotional state.

[2078] Based on the analysis results obtained by the AI ​​analysis means and the emotional state obtained by the emotion analysis means, the server uses the plan suggestion means to generate and suggest an optimal learning plan for each learner. This learning plan is personalized, taking into consideration the learner's progress, level of understanding, and emotional state.

[2079] Depending on the progress, the server dynamically adjusts the learning plan using a schedule optimization means, providing the learner with a schedule that includes relaxation and appropriate breaks.

[2080] When a learner enters a question on the messenger application, the server analyzes the question using an automatic response means, generates an appropriate answer, and provides it immediately, using natural language processing means to understand the meaning of the question and retrieve the answer from a related knowledge database.

[2081] Furthermore, when a learner submits an answer to a past question, the server uses a detailed explanation means to analyze the answer and provide detailed feedback including the solution procedure and related knowledge.

[2082] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback and advice in real time as needed. It also uses emotion analysis means to provide feedback that takes into account the learner's emotional state.

[2083] To realize learning support in physical stores, a smartphone application is provided via a physical store linkage method. This application is designed to allow learners to adjust their learning plans, receive questions and receive emotional feedback in real time while studying in the store.

[2084] As a specific example, if a learner sends a message saying, "I'm a little tired today, but I'd like to review science," the server will use emotion analysis to identify the state of "tired" and suggest, "You seem tired today. Let's start with some light review questions."

[2085] An example of a prompt is:

[2086] "My child is not making progress in math, what should I do?"

[2087] The server would respond with, "It looks like you're not making much progress with math. Take your time and try this plan: easy-to-follow video tutorials and light practice problems."

[2088] In this way, by using the system of the present invention, learners can receive consistent learning support even in a physical store environment, allowing them to study effectively and efficiently.

[2089] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2090] Step 1:

[2091] A user sends input data related to their learning (e.g., learning progress, questions, emotional state) through a messenger application. Input: User's message. Output: Message data received by the server.

[2092] Step 2:

[2093] The server uses AI analysis means to analyze message data received from users. At this time, natural language processing technology (e.g., NLP model) is used to extract important information (e.g., learning content, questions, emotional expressions). Input: Message data. Output: Analyzed information (e.g., learning content, questions, emotional state).

[2094] Step 3:

[2095] Using emotion analysis tools (e.g., Emotion API), analyze the learner's emotional state contained in the message data. Input: Message data. Output: Learner's emotional state (e.g., tired, nervous).

[2096] Step 4:

[2097] The server uses the plan suggestion means to generate and suggest an optimal learning plan for the learner based on the analysis results and emotional state. Input: Analyzed information and emotional state. Output: Individualized learning plan.

[2098] Step 5:

[2099] The server uses schedule optimization techniques to dynamically adjust the learning plan according to the user's progress. Input: Learning plan and progress data. Output: Optimized learning schedule.

[2100] Step 6:

[2101] When a user inputs a question through the messenger application, the server uses an automatic response means to analyze the question and utilizes natural language processing means to generate an appropriate answer. Input: Question message. Output: Generated answer.

[2102] Step 7:

[2103] When a user submits an answer to a past question, the server analyzes the answer using detailed explanation means and generates detailed feedback including solution steps and related knowledge. Input: Answer to past question. Output: Detailed explanation feedback.

[2104] Step 8:

[2105] Using real-time monitoring means, the server constantly monitors the learner's progress and provides appropriate feedback in real time as needed. Input: Progress data. Output: Real-time feedback.

[2106] Step 9:

[2107] Through the brick-and-mortar integration method, as learners progress through their learning in-store, the smartphone application supports all of the above steps, adjusting their learning plans, answering questions, and providing emotional feedback in real time. Input: Learning data from the brick-and-mortar store. Output: Real-time support provided in-store.

[2108] 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.

[2109] 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.

[2110] 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.

[2111] 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.

[2112] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2113] 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.

[2114] 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).

[2115] 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.

[2116] 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."

[2117] 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.

[2118] 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).

[2119] 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.

[2120] 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.

[2121] 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.

[2122] 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.

[2123] 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.

[2124] 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.

[2125] 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.

[2126] 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.

[2127] 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.

[2128] 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.

[2129] The following is further disclosed regarding the above embodiment.

[2130] (Claim 1)

[2131] To collect and analyze learner input data

[2132] AI analysis means,

[2133] Based on the analysis results, we propose the best learning plan for the learner.

[2134] A plan proposal means;

[2135] Dynamically adjusting said learning plan based on the learner's progress.

[2136] Schedule optimization means;

[2137] Instantly answer questions from learners via messenger applications such as LINE

[2138] an automatic response means;

[2139] Provides detailed explanations for past exam answers

[2140] Detailed explanation means,

[2141] Monitor learners' progress in real time and provide appropriate feedback

[2142] A system including real-time monitoring means.

[2143] (Claim 2)

[2144] Using the learner's input data and the analysis results, a learning plan is generated based on the learner's individual learning style.

[2145] 10. The system of claim 1, further comprising a learning style analysis means.

[2146] (Claim 3)

[2147] To generate answers to learners' questions through messenger applications such as LINE.

[2148] 10. The system of claim 1, further comprising natural language processing means.

[2149] "Example 1"

[2150] (Claim 1)

[2151] To collect and analyze learner input data

[2152] AI analysis means,

[2153] Based on the analysis results, we propose the best learning plan for the learner.

[2154] A plan proposal means;

[2155] Dynamically adjusting said learning plan based on the learner's progress.

[2156] Schedule optimization means;

[2157] Instantly answer learner questions through communication software

[2158] an automatic response means;

[2159] Provides detailed explanations for past exam answers

[2160] Detailed explanation means,

[2161] Monitor learners' progress in real time and provide appropriate feedback

[2162] Real-time monitoring means;

[2163] To transfer learners' questions and progress to the server via communication software

[2164] A terminal and

[2165] To send answers and feedback generated based on the analysis results to learners via communication software

[2166] A system that includes a server.

[2167] (Claim 2)

[2168] Using the learner's input data and the analysis results, a learning plan is generated based on each individual's learning style.

[2169] 10. The system of claim 1, further comprising a learning style analysis means.

[2170] (Claim 3)

[2171] To generate answers to learners' questions through communication software

[2172] 10. The system of claim 1, further comprising natural language processing means.

[2173] "Application Example 1"

[2174] (Claim 1)

[2175] To collect and analyze learner input data

[2176] AI analysis means,

[2177] Based on the analysis results, we propose the best learning plan for the learner.

[2178] A plan proposal means;

[2179] Dynamically adjusting said learning plan based on the learner's progress.

[2180] Schedule optimization means;

[2181] Instantly answer learner questions through messenger applications

[2182] an automatic response means;

[2183] Provides detailed explanations for past exam answers

[2184] Detailed explanation means,

[2185] Monitor learners' progress in real time and provide appropriate feedback

[2186] Real-time monitoring means;

[2187] An application installed on a smartphone that distributes content

[2188] a content distribution means;

[2189] Use a generative AI model to generate responses

[2190] a generative AI model means;

[2191] Prompts suggest optimal study schedules

[2192] A schedule suggestion means;

[2193] A system including:

[2194] (Claim 2)

[2195] Using the learner's input data and the analysis results, a learning plan is generated based on each individual's learning style.

[2196] 10. The system of claim 1, further comprising a learning style analysis means.

[2197] (Claim 3)

[2198] To generate answers to learners' questions through messenger applications

[2199] 10. The system of claim 1, further comprising natural language processing means.

[2200] "Example 2: Combining Emotion Engines"

[2201] (Claim 1)

[2202] To collect and analyze learner input data

[2203] data analysis means;

[2204] Based on the analysis results and the learner's emotional state, the system proposes an optimal learning plan

[2205] A plan proposal means;

[2206] Dynamically adjusting the learning plan based on the learner's progress and emotional state

[2207] Schedule optimization means;

[2208] Instantly answer learner questions through messenger applications

[2209] an automatic response means;

[2210] Provides detailed explanations for past exam answers

[2211] Detailed explanation means,

[2212] Monitor learners' progress in real time and provide appropriate feedback

[2213] Real-time monitoring means;

[2214] Analyzing learners' emotional states

[2215] A system including a means for sentiment analysis.

[2216] (Claim 2)

[2217] Using the learner's input data and the analysis results, a learning plan is generated based on the learner's individual learning style and emotional state.

[2218] 10. The system of claim 1, further comprising a learning style analysis means.

[2219] (Claim 3)

[2220] generating answers to learners' questions through said messenger application;

[2221] 10. The system of claim 1, further comprising natural language processing means.

[2222] "Application example 2 when combining emotion engines"

[2223] (Claim 1)

[2224] To collect and analyze learner input data

[2225] AI analysis means,

[2226] Based on the analysis results, we propose the best learning plan for the learner.

[2227] A plan proposal means;

[2228] Dynamically adjusting said learning plan based on the learner's progress.

[2229] Schedule optimization means;

[2230] Instantly answer learner questions through messenger applications

[2231] an automatic response means;

[2232] Provides detailed explanations for past exam answers

[2233] Detailed explanation means,

[2234] Monitor learners' progress in real time and provide appropriate feedback

[2235] Real-time monitoring mea...

Claims

1. To collect and analyze learner input data AI analysis methods and Based on the analysis results, we propose the best learning plan for the learner. A plan proposal means; Dynamically adjusting said learning plan based on the learner's progress. Schedule optimization means; Instantly answer questions from learners via messenger applications such as LINE an automatic response means; Provides detailed explanations for past exam answers Detailed explanation means, Monitor learners' progress in real time and provide appropriate feedback A system including real-time monitoring means.

2. Using the learner's input data and the analysis results, a learning plan is generated based on the learner's individual learning style.

10. The system of claim 1, further comprising a learning style analysis means.

3. To generate answers to learners' questions through messenger applications such as LINE. The system of claim 1 further comprising a natural language processing means.

Images