System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting a learner profile; means for generating learning content based on the collected learner profile; means for monitoring a learning progress of the learner; means for identifying weaknesses of the learner based on the learning progress and suggesting reinforcement learning; and means for analyzing answers and reactions of the learner to assess comprehension and provide additional explanation as needed.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] Today's learners are seeking to study effectively and efficiently within a limited time frame. However, many learners are unaware of the optimal study method for them, and they have difficulty improving their academic ability due to insufficient retention and review of what they have learned. To solve this problem, a system is needed that provides learning content and questions customized for each learner, and realizes efficient and effective learning support. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] The present invention provides a system including means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, and means for analyzing the learner's answers and responses to evaluate the learner's understanding and providing additional explanations as necessary. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[0007] A "learner profile" is a data set that includes information such as a learner's grade, interests, and past learning history.

[0008] "Learning content" refers to the learning materials and questions provided to support learners' learning.

[0009] "Natural language generation AI" is artificial intelligence that uses natural language processing technology to generate text and create content.

[0010] "Study progress" is data that refers to how far a learner has progressed in their studies, the time it takes to solve problems, and information on whether the answers were correct or incorrect.

[0011] "Monitoring" refers to the process of observing learners' learning status in real time and collecting data.

[0012] "Weaknesses" refer to areas or topics where a learner has particular difficulty understanding or answering questions.

[0013] "Reinforcement learning" refers to additional learning content or questions provided to overcome specific weaknesses.

[0014] "Level of understanding" is an indicator that shows how well a learner understands a particular learning content. [Brief explanation of the drawings]

[0015] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[0037] (Collecting learner profiles)

[0038] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[0039] (learning content generation)

[0040] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[0041] (Monitoring learning progress)

[0042] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0043] (Identifying weaknesses and suggesting reinforcement learning)

[0044] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[0045] (Evaluation of understanding and additional explanation)

[0046] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[0047] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[0051] Step 2:

[0052] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[0053] Step 3:

[0054] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[0055] Step 4:

[0056] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[0057] Step 5:

[0058] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[0059] Step 6:

[0060] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[0061] Step 7:

[0062] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[0063] Step 8:

[0064] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[0065] Step 9:

[0066] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[0067] Step 10:

[0068] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[0069] Step 11:

[0070] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[0071] Step 12:

[0072] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[0073] Step 13:

[0074] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[0075] Step 14:

[0076] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[0077] Step 15:

[0078] The device records the user's answers. The device records the user's answers and sends them to the server.

[0079] Step 16:

[0080] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[0081] Step 17:

[0082] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[0083] Step 18:

[0084] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[0085] Step 19:

[0086] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] Conventional learning support systems have difficulty providing optimal learning content based on each learner's individual characteristics and progress. They also lack a mechanism for identifying learners' weaknesses in real time and quickly suggesting appropriate reinforcement learning. This makes it difficult to improve a learner's understanding and maximize learning efficiency. Furthermore, they are also inadequate in assessing a learner's understanding based on their answers and providing corresponding additional explanations, limiting the effectiveness of learning.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes: means for collecting a learner profile by a user inputting profile information such as grade level, interests, and past learning history and transmitting it to the server via a terminal; means for generating optimal learning content based on generated prompts using a natural language generation AI model based on the collected learner profile; means for the terminal to record the user's learning status in real time and transmit learning progress data to the server, which analyzes the data to monitor the learner's learning progress; means for analyzing the learning progress data and generating additional content for reinforcement learning using a natural language generation AI model to identify the learner's weaknesses and suggest reinforcement learning; and means for the terminal to record the user's answers, the server to evaluate the user's level of understanding based on the data, and providing additional explanations using the natural language generation AI model as needed. This allows for learning support optimized for each learner, enabling efficient and effective learning.

[0092] A "learner profile" refers to a set of information about an individual learner, such as the user's grade level, interests, and past learning history.

[0093] "Terminal" refers to an electronic device with communication capabilities operated by a user, which is used to input a learning profile and access learning content.

[0094] "Server" refers to a computer system that collects, stores, and analyzes information, generates learning content, and monitors progress.

[0095] "Natural language generation AI model" refers to an artificial intelligence model that automatically generates text appropriate for a specific task based on input prompts.

[0096] A "prompt" refers to input text that provides specific instructions or questions to a natural language generation AI model.

[0097] "Learning content" refers to a series of educational materials, such as teaching materials, workbooks, and explanations, created for use by learners.

[0098] "Learning progress" refers to data that shows the progress and results of the learning content that a learner has engaged in.

[0099] "Monitoring" refers to the process of recording learning progress data in real time and tracking and managing learner progress.

[0100] "Reinforcement learning" refers to additional learning content or materials provided to identify learners' weaknesses and help them overcome them.

[0101] "Answer" refers to the answer or response that a learner submits to a question in the learning content.

[0102] "Understanding" refers to measurable indicators or assessment results that show how well a learner has understood the learning content.

[0103] "Additional explanation" refers to explanations or explanations provided in addition to existing learning content to improve a learner's understanding.

[0104] The present invention relates to a system for collecting learner profiles, generating learning content, monitoring learning progress, identifying weaknesses and suggesting supplementary learning, and evaluating comprehension and providing additional explanations. The following describes in detail the modes for implementing the present invention.

[0105] First, the user enters profile information such as grade level, interests, and past learning history. The user enters this information using an input form on the device and presses the submit button. The device encrypts this information using the HTTPS protocol and securely sends it to the server. The server then inserts the received information into the database using an SQL query to store it.

[0106] Next, the server generates optimal learning content for the user based on the saved learner profile using the natural language generation AI model "OpenAI GPT-4." The server analyzes the profile information and sends a prompt to the AI ​​model. An example of a specific prompt is, "Please generate an assignment for a high school sophomore who is weak in algebra." The AI ​​model receives this prompt, generates appropriate learning content, and sends it back to the server. The server parses the generated content in JSON format and sends it to the user's device.

[0107] Users use the learning content received on their device to progress with their studies. They solve problems and enter their answers into the device. At this time, the device records the user's learning status in real time, specifically data such as the time it takes to solve the problems and whether the answers were correct or incorrect, and periodically sends this data to the server. The server analyzes this data and monitors the user's learning progress. Machine learning algorithms are used for accurate data analysis.

[0108] By analyzing the learning progress data, the server identifies the user's weaknesses. For example, if the user repeatedly makes a specific mistake when solving algebraic equations, the server uses that information to send another prompt to the AI ​​model. A specific prompt such as "Please generate reinforcement problems for users who make many mistakes when solving algebraic equations" is used. The AI ​​model generates additional reinforcement learning content and sends it back to the server. The server then sends the generated content to the user's device.

[0109] Finally, when the user works through the reinforcement learning content and enters the answers into the device, the device sends the answer data to the server. The server uses this data to evaluate the user's level of understanding. If the user's level of understanding is determined to be low, the server again uses the AI ​​model to generate additional explanations or explanations from a different approach and sends them to the device. For example, the server could send a prompt such as, "For users who repeatedly have trouble solving a particular algebra problem, please provide a step-by-step explanation of the answer."

[0110] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] The user enters profile information such as grade level, interests, and past learning history.

[0114] Specifically, the user enters the necessary information into the input form on the terminal and clicks the send button.

[0115] Input: Grade, interests, past learning history

[0116] Output: Profile information entered into the terminal

[0117] Step 2:

[0118] The device sends the profile information to the server.

[0119] The device uses the HTTPS protocol to encrypt data and send it securely to the server.

[0120] Input: Profile information entered on the device

[0121] Output: Profile information sent to the server

[0122] Step 3:

[0123] The server stores the profile information in a database.

[0124] Specifically, the server inserts the received profile information into a database using an SQL query.

[0125] Input: Profile information sent to the server

[0126] Output: Profile information stored in the database

[0127] Step 4:

[0128] The server calls the AI ​​model based on the profile information and generates learning content.

[0129] The server analyzes the stored profile information and sends prompts to the generative AI model, such as "Please generate an assignment for a high school sophomore who is weak in algebra."

[0130] Input: Profile information stored in the database

[0131] Output: Prompts to send to the generative AI model and generated learning content

[0132] Step 5:

[0133] The server transmits the generated learning content to the user's terminal.

[0134] The server parses the generated content in JSON format and sends it to the user's device.

[0135] Input: Generated learning content

[0136] Output: Learning content sent to the user's device

[0137] Step 6:

[0138] Users can use the learning content on their devices to progress with their studies.

[0139] Specifically, the user solves the problem displayed on the terminal and inputs the answer.

[0140] Input: Learning content sent to your device

[0141] Output: User's answer

[0142] Step 7:

[0143] The terminal records the user's learning status and sends it to the server.

[0144] The device records data such as the time it takes to solve the questions and whether the answers were correct or incorrect in real time, and periodically transmits this data to the server.

[0145] Input: User answers, learning status data

[0146] Output: Learning status data sent to the server

[0147] Step 8:

[0148] The server analyzes the learning progress data and monitors the learner's progress.

[0149] Specifically, the server analyzes the received data and uses machine learning algorithms to evaluate the learner's performance and trends.

[0150] Input: Learning status data sent to the server

[0151] Output: Parsed learning progress data, learner progress

[0152] Step 9:

[0153] The server identifies weaknesses based on learning progress data and generates additional content for reinforcement learning.

[0154] The server then prompts the AI ​​model again based on the identified weaknesses, using a specific prompt such as "Generate reinforcement problems for users who make a lot of mistakes solving algebra equations."

[0155] Input: Parsed learning progress data, generated prompts

[0156] Output: Generated reinforcement learning content

[0157] Step 10:

[0158] The server transmits the generated augmented content to the terminal.

[0159] The server parses the additional content in JSON format and sends it to the user's device.

[0160] Input: Generated reinforcement learning content

[0161] Output: Reinforcement learning content sent to the user's device

[0162] Step 11:

[0163] The user uses the reinforcement learning content and inputs the answers into the terminal.

[0164] In concrete terms, the user solves the additional problem and inputs the answer into the terminal.

[0165] Input: Reinforcement learning content sent to the device

[0166] Output: Additional answers provided by the user

[0167] Step 12:

[0168] The terminal records the user's answers and sends them to the server.

[0169] The device records the answer data in real time and transmits it to the server.

[0170] Input: Additional answers provided by the user

[0171] Output: Additional answer data sent to the server

[0172] Step 13:

[0173] The server evaluates the level of understanding based on the answer data and provides additional explanations if necessary.

[0174] The server analyzes the answer data and, if it determines that the level of understanding is low, sends another prompt to the AI ​​model, specifically, using the prompt sentence, "Please provide a step-by-step explanation of the solution for users who have been unable to solve a particular algebra problem multiple times."

[0175] Input: Additional answer data sent to the server, generated prompt text

[0176] Output: Generated additional description

[0177] Step 14:

[0178] The server sends the generated additional description to the terminal.

[0179] The server parses the additional explanation in JSON format and sends it to the user's device.

[0180] Input: Generated additional description

[0181] Output: Additional instructions sent to the user's terminal

[0182] In this way, by explaining the process steps, the specific operation of the system and its flow can be clarified.

[0183] (Application example 1)

[0184] 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."

[0185] Today's learners have diverse learning needs and progress levels, making it difficult to select optimal learning materials and manage their progress. In particular, when receiving learning support in a brick-and-mortar store, it is difficult to receive appropriate advice and learning material recommendations in real time. There is a need to solve this problem and provide learning support optimized for each user's learning needs.

[0186] 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.

[0187] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting supplementary learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for a user to input their own learning profile in a physical store and be provided with advice and materials for purchasing on the spot, means for recording the user's progress in learning using the learning materials and reference books they have purchased, and means for recommending supplementary learning materials available for purchase in the store based on the user's learning progress. This makes it possible to select optimal learning materials for individual learners and provide learning support in real time, even in a store environment.

[0188] "Learner profile" refers to the learner's individual attribute information, such as the user's grade, interests, and past learning history.

[0189] "Means of collection" refers to the methods and technologies used to obtain information provided by users and send it to a server.

[0190] "Learning content" refers to problem sets, teaching materials, explanatory materials, etc. provided for learning.

[0191] "Means of generation" refers to the technology and methods for creating optimal learning content based on collected learner profiles.

[0192] "Monitoring means" refers to methods and technologies that track and record learners' learning progress in real time.

[0193] A "weakness" refers to an area where a learner has insufficient understanding or answers correctly in a particular learning item.

[0194] "Reinforcement learning" refers to additional learning content or training provided to learners to overcome weaknesses.

[0195] "Suggestion methods" refer to techniques and methods for presenting appropriate reinforcement learning based on the learner's weaknesses.

[0196] "Answers and responses" refers to the answers given by learners to the learning content and the evaluation results.

[0197] "Comprehension" refers to the degree to which a learner understands the learning content provided.

[0198] "Means for providing additional explanations" refers to techniques and methods for generating and providing additional explanations when a learner's level of comprehension is low.

[0199] "Brick and mortar store" refers to an educational equipment store, bookstore, or other store that operates from a physical location.

[0200] "Advice" refers to advice that recommends optimal learning materials and methods based on the learner's profile.

[0201] "Materials for considering a purchase" refers to information and recommendations that learners can refer to when considering a purchase in a store.

[0202] "Means for recording the situation" refers to techniques and methods for recording how learners progress with the purchased learning materials.

[0203] "Supplementary materials" refers to additional materials provided at the store to reinforce a learner's weak areas.

[0204] "Recommendation means" refers to the technology or method for selecting and presenting the most appropriate supplementary learning materials based on learning progress data.

[0205] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. Using this system, it is possible to provide learning support optimized for each learner, even in physical stores.

[0206] Collecting learner profiles

[0207] Users use a smartphone app to enter their learner profile. The profile includes the learner's grade, interests, past learning history, etc. This information is sent from the device to the server and stored in a database. For example, a user may enter that they are a "second-year high school student" and are interested in "math" and "English."

[0208] Generating learning content

[0209] The server uses a generative AI model to generate optimal learning content for the user based on the saved learner profile. For example, if the user is weak in algebra, the server generates a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[0210] Monitoring learning progress

[0211] Users study using purchased learning materials and reference books. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0212] Identifying weaknesses and suggesting reinforcement learning

[0213] The server analyzes the learning progress data to identify the user's weaknesses. Based on the identified weaknesses, the server uses a generative AI model to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes in solving algebraic equations, the server can generate a set of problems specific to that topic and send it to the device.

[0214] Assessment of understanding and further explanation

[0215] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the generative AI model is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the server will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[0216] Use in physical stores

[0217] Users visit a physical store and enter their learning profile through a smartphone app. The app then recommends optimal learning materials and reference books based on the profile information entered. The app also records how the user progresses with the materials they have purchased and sends this information to the server. This allows the app to recommend supplementary materials that can be purchased at the store.

[0218] Specific examples

[0219] For example, suppose a user is a second-year high school student and has an interest in mathematics and English, and has purchased a book on basic algebra. In this case, the generative AI model receives the following prompt and generates learning content:

[0220] Example prompt sentence:

[0221] "Generate the best Mathematics Algebra learning content based on user learning profile ID: 12345."

[0222] In this way, optimal learning support that meets the user's learning needs in real time can be realized.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] Users use a smartphone app to enter their learner profile. This information, such as their grade, interests, and past learning history, is sent to the server via the device. The server then stores the received profile information in a database. This saves information, such as the user being a "second-year high school student" and having interests in "math" and "English," which is then used to generate subsequent learning content.

[0226] Step 2:

[0227] The server sends a prompt to the generative AI model based on the saved learner profile to generate optimal learning content for the user. The prompt will be in the form of "Please generate optimal learning content for math algebra based on the user's learning profile ID: {ID}." The generative AI model generates learning content based on this input and returns the results to the server. The server then sends the generated content to the user's device.

[0228] Step 3:

[0229] The user uses the provided learning content to progress through their studies. The device records the user's learning progress (e.g., time to solve problems, correct / incorrect answers) in real time and sends the data to the server. The server aggregates this data and monitors the learner's progress.

[0230] Step 4:

[0231] The server analyzes the collected learning progress data. For example, it identifies that the user makes many mistakes on a particular algebra problem. The server then invokes the generative AI model again and sends a prompt saying, "Based on the user's learning progress data, please generate learning content that reinforces specific weaknesses." The model generates reinforcement learning content specific to the weaknesses and sends it to the server. The server then sends this content to the user's device.

[0232] Step 5:

[0233] The device records the results (answer data) of the user's learning as they follow the reinforcement learning content and sends that data back to the server. The server analyzes this data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends a new prompt to the generative AI model, asking it to generate more detailed additional explanations or explanations from a different approach. The generated additional explanations and explanations are sent from the server to the user's device.

[0234] Step 6:

[0235] When a user visits a physical store, they enter their learning profile through a smartphone app. Based on the profile information entered, the app recommends the most suitable study materials and reference books to purchase at the store. Based on the ID, the app retrieves recommendation information and study progress data from the server. This allows the user to select the most suitable study materials and reference books in the store.

[0236] Step 7:

[0237] The smartphone app records how the user progresses with the study materials and reference books they have purchased (e.g., study time, percentage of correct answers, etc.) and sends this data to the server. Based on this data, the server recommends supplementary materials suitable for the user. Information on the recommended supplementary materials is used the next time the user considers purchasing them in a physical store or online.

[0238] 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.

[0239] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and also combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[0240] (Collecting learner profiles)

[0241] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[0242] (learning content generation)

[0243] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[0244] (Monitoring learning progress)

[0245] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0246] (Identifying weaknesses and suggesting reinforcement learning)

[0247] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[0248] (Evaluation of understanding and additional explanation)

[0249] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[0250] (Emotion recognition)

[0251] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.). The recognized emotion data is sent to the server in real time.

[0252] (Adjusting Emotion-Based Learning Support)

[0253] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, it can lower the difficulty of the content or add more detailed explanations. If the user is tired, it can also send a notification to the device suggesting a break.

[0254] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[0255] The processing flow will be explained below.

[0256] Step 1:

[0257] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[0258] Step 2:

[0259] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[0260] Step 3:

[0261] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[0262] Step 4:

[0263] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[0264] Step 5:

[0265] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[0266] Step 6:

[0267] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[0268] Step 7:

[0269] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[0270] Step 8:

[0271] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[0272] Step 9:

[0273] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[0274] Step 10:

[0275] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[0276] Step 11:

[0277] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[0278] Step 12:

[0279] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[0280] Step 13:

[0281] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[0282] Step 14:

[0283] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[0284] Step 15:

[0285] The device records the user's answers. The device records the user's answers and sends them to the server.

[0286] Step 16:

[0287] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[0288] Step 17:

[0289] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[0290] Step 18:

[0291] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[0292] Step 19:

[0293] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[0294] Step 20:

[0295] The device recognizes the user's emotions. The device analyzes the user's facial expressions and voice, and the emotion engine identifies the user's emotional state. For example, the device recognizes emotions such as confusion, excitement, or fatigue.

[0296] Step 21:

[0297] The device sends emotion data to the server. The device sends the emotion data recognized by the emotion engine to the server in real time.

[0298] Step 22:

[0299] The server analyzes the emotional data and evaluates the user's current emotional state based on the received emotional data.

[0300] Step 23:

[0301] The server adjusts the learning content. The server adjusts the difficulty and content of the learning content based on the emotional data. For example, if the user is confused, the server may lower the difficulty of the content or provide additional hints.

[0302] Step 24:

[0303] The server adjusts the learning progress based on the emotion data. For example, if the user is tired, it sends a notification to the device suggesting a break.

[0304] Step 25:

[0305] The terminal displays the adjusted content. The terminal displays the adjusted learning content and break suggestions sent from the server to the user.

[0306] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[0307] Example 2

[0308] 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."

[0309] Conventional learning systems have difficulty providing optimal learning content for each learner, monitoring progress, and providing feedback based on their level of understanding. Furthermore, they are unable to recognize the learner's emotional state and adjust learning support accordingly, preventing the maximization of learning effectiveness.

[0310] 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.

[0311] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing the learner's emotional state, and means for adjusting learning support based on the recognized emotional state. This allows for an optimal learning experience for each learner, enabling efficient and effective learning.

[0312] A "learner profile" is data that includes personal information such as a learner's grade, interests, and past learning history.

[0313] "Learning content" refers to educational materials and exercises that are generated based on the learner's profile and learning progress.

[0314] "Progress monitoring" is the process of tracking and recording data (such as time to solve a problem, correct / incorrect answers, etc.) as a learner progresses through their studies.

[0315] "Identifying weaknesses" refers to analyzing a learner's learning data to identify areas where they lack understanding or make repeated mistakes.

[0316] "Reinforcement learning suggestions" refers to suggestions to provide additional learning content to complement or reinforce identified weaknesses of learners.

[0317] "Assessing comprehension" involves analyzing the problems solved by learners and their responses to determine how much they have understood.

[0318] "Additional explanation" means providing a more detailed explanation or an explanation from a different approach when the learner's understanding is insufficient.

[0319] "Recognizing emotional states" refers to detecting the learner's emotions (confusion, excitement, fatigue, etc.) from their facial expressions and voice.

[0320] "Adjusting learning support" refers to changing or adjusting learning content or learning progression methods based on the recognized emotional state of the learner.

[0321] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system provides optimal learning support for each learner, enabling efficient and effective learning.

[0322] Collecting learner profiles

[0323] Users enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, if a user enters that they are a second-year high school student and are interested in math and English, this information is recorded as their profile information.

[0324] Generating learning content

[0325] The server calls a natural language generation AI (e.g., GPT-4) based on the saved learner profile and generates optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it sends a prompt such as "Please generate a problem set that will teach me algebra from the basics" to the AI, which then generates a problem set. The generated content is then sent from the server to the device.

[0326] Monitoring learning progress

[0327] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0328] Identifying weaknesses and suggesting reinforcement learning

[0329] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI (e.g., BERT) to generate additional content for reinforcement learning. For example, it sends a prompt such as "Please create a problem set to help improve my weakness in solving algebraic equations" to the AI, and the problem set is created. The generated reinforcement content is sent from the server to the device.

[0330] Assessment of understanding and further explanation

[0331] The device records the user's answer data and sends it to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the server uses natural language generation AI to generate additional explanations or explanations from a different approach. For example, the server sends a prompt such as "Please explain the process of solving this algebra problem step by step" to the AI ​​to generate an explanation. These additional explanations are sent from the server to the device.

[0332] Emotion recognition

[0333] The device is equipped with an emotion engine (e.g., a general emotion recognition API) that recognizes the user's emotional state from their facial expressions and voice. The emotion engine recognizes the user's emotional state during learning and sends the data to the server in real time.

[0334] Emotion-based learning support coordination

[0335] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, the server sends a prompt to the AI ​​such as, "Please provide easy algebra problems and detailed explanations for the struggling user," and generates easy problems and detailed explanations. If the user is tired, the server sends a notification to the device suggesting a break.

[0336] In this way, the system provides an optimized learning experience based on the learner's learning situation and emotional state, thereby realizing efficient and effective learning.

[0337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0338] Step 1:

[0339] Collecting learner profiles

[0340] Input: Information such as the user's grade, interests, and past learning history

[0341] Specific behavior: Users fill out a registration form with their grade level, interests, and past learning history.

[0342] Data processing: The device receives this information and assembles it into data packets.

[0343] Output: The device sends data packets to the server, which stores the profile information in a database.

[0344] Step 2:

[0345] Generating learning content

[0346] Input: Learner profile stored in the database

[0347] Specific operation: The server analyzes the learner profile and sends a prompt to the natural language generation AI saying, "Please generate a problem set that will teach the basics of algebra in mathematics."

[0348] Data processing: Natural language generation AI (e.g., GPT-4) generates optimal learning content based on profile information.

[0349] Output: The generated learning content is sent from the server to the device.

[0350] Step 3:

[0351] Monitoring learning progress

[0352] Input: User's learning status (time to solve the problem, correct / incorrect answers, etc.)

[0353] Specific operation: The user uses the learning content received on the device to proceed with their learning. The device records their learning progress in real time.

[0354] Data processing: The device organizes the recorded data and sends it to the server.

[0355] Output: The server monitors the learning progress based on the received data and stores it in a database.

[0356] Step 4:

[0357] Identifying weaknesses and suggesting reinforcement learning

[0358] Input: Learning progress data

[0359] Specific operation: The server analyzes the learning progress data and identifies the user's weaknesses, such as "Many mistakes in solving algebraic equations." The server then sends a prompt to the natural language generation AI, saying, "Please create a problem set to help overcome the weaknesses in solving algebraic equations."

[0360] Data processing: Natural language generation AI generates content for reinforcement learning based on identified weaknesses.

[0361] Output: The generated augmentation content is sent from the server to the device.

[0362] Step 5:

[0363] Assessment of understanding and further explanation

[0364] Input: User's answer data

[0365] How it works: The device records the user's answers and sends them to the server. The server analyzes the answer data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends the AI ​​a prompt saying, "Please explain the process of solving this algebra problem step by step."

[0366] Data processing: Natural language generation AI generates detailed explanations based on prompts.

[0367] Output: The additional instructions are sent from the server to the terminal and provided to the user.

[0368] Step 6:

[0369] Emotion recognition

[0370] Input: User facial and voice data

[0371] How it works: The device's camera and microphone capture the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotional state (confusion, excitement, fatigue, etc.).

[0372] Data processing: The emotion engine analyzes and classifies emotion data.

[0373] Output: The recognized emotion data is sent to the server in real time.

[0374] Step 7:

[0375] Emotion-based learning support coordination

[0376] Input: Emotion data

[0377] Specific behavior: The server receives the emotion data and sends a prompt to the AI ​​saying, "Please provide an easy algebra problem and detailed explanation to the struggling user." If the server determines that the user is tired, it also generates a notification saying, "Take a break."

[0378] Data processing: Natural language generation AI generates optimal content based on prompts.

[0379] Output: The adjusted learning content and notifications are sent to the device and provided to the user.

[0380] These steps enable the system to provide learners with an optimal learning experience and maximize learning effectiveness.

[0381] (Application example 2)

[0382] 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."

[0383] Conventional learning support systems are unable to take into account the learner's emotional state, which can lead to reduced learning efficiency and effectiveness. It is also difficult to provide optimal content to each individual learner in real time. Furthermore, because emotional data cannot be referenced when closely monitoring learning progress or proposing effective reinforcement learning to address individual weaknesses, they are unable to respond adequately to learners. To solve these issues, a highly customized learning support system is needed.

[0384] 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 means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing emotions, and means for adjusting the learning content and learning progress method based on the recognized emotions. This makes it possible to grasp the learner's learning situation and emotional state in real time and provide individually optimized learning support.

[0385] A "learner profile" is data about an individual learner, including basic information about the learner, their interests, and past learning history.

[0386] "Learning content" refers to content such as study materials, question sets, and explanations that are generated based on the learner's profile.

[0387] "Learning progress" refers to data that shows the progress and results of a learner's learning as they use learning content.

[0388] "Reinforcement learning" refers to additional learning content or educational activities that complement learners' weaknesses and strengthen their abilities.

[0389] "Means for recognizing emotions" refers to technology that analyzes data such as the learner's facial expressions and voice to identify their emotional state at that time (for example, confusion, excitement, fatigue, etc.).

[0390] "Means for adjusting learning content and learning methods based on emotions" refers to technology that provides optimal learning content and learning methods based on the learner's emotional state based on recognized emotional data.

[0391] This invention is a system that collects learner profiles, generates learning content, monitors learning progress, identifies weaknesses and suggests supplementary learning, evaluates comprehension and provides additional explanations, and uses an emotion engine to recognize the user's emotions and provide learning support based on these. This enables optimal learning support for each learner, resulting in efficient and effective learning.

[0392] The system mainly includes the following components:

[0393] 1. Collecting learner profiles

[0394] When a user registers with the system, the terminal inputs profile information such as the user's grade, interests, and past learning history.

[0395] The collected information is sent to a server and stored in a database.

[0396] 2. Generating learning content

[0397] Based on the saved learner profile, the server calls up a natural language generation AI to generate optimal learning content for the user.

[0398] For example, if it turns out that the user is weak in algebra, a series of problem sets starting from the basics of algebra can be generated. The generated content is sent from the server to the user's terminal.

[0399] 3. Monitoring your learning progress

[0400] The user uses the learning content received on the terminal to advance their learning.

[0401] The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends the data to the server.

[0402] The server uses this data to monitor the learner's progress.

[0403] 4. Identifying weaknesses and suggesting reinforcement learning

[0404] The server analyzes the learning progress data and identifies the user's weaknesses.

[0405] Based on the identified weaknesses, natural language generation AI is again used to generate additional content for reinforcement learning.

[0406] For example, if a user makes particularly many mistakes when solving algebraic equations, a collection of exercises specific to that topic can be generated. The generated reinforcement content is then sent from the server to the device.

[0407] 5. Assessment of understanding and further explanation

[0408] The terminal records the user's answers and sends them to the server.

[0409] The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, it uses natural language generation AI to generate additional explanations or explanations from different approaches.

[0410] For example, if a user repeatedly has trouble solving a particular algebra problem, the server will provide step-by-step instructions on the process of solving the problem, including alternative solutions. Additional instructions are sent from the server to the device.

[0411] 6. Emotional Recognition

[0412] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice.

[0413] The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.) and transmits the recognized emotion data to the server in real time.

[0414] 7. Adjusting emotion-based learning support

[0415] The server adjusts the learning content and learning progress method based on the emotional data received from the emotion engine.

[0416] For example, if the user is confused, the difficulty level of the content can be reduced or more detailed explanations can be added. Also, if the user is tired, a notification can be sent to the device suggesting that they take a break.

[0417] As a specific example, consider the case where a user incorrectly answers the same algebra problem multiple times while studying it. At this time, the device recognizes the user's state of confusion and sends it to the server in real time. The server uses this information to adjust the difficulty of the content or add step-by-step explanations. The AI ​​generator then inputs a prompt such as, "If the user repeatedly fails to solve a particular algebra problem, please generate content that provides a step-by-step explanation of the solution process and suggests different solutions. The theme of the problem is 'Solution to Quadratic Equations.'" This allows the learner to progress through their studies in a more understandable way.

[0418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0419] Step 1:

[0420] When a user registers with the system, the device inputs profile information such as grade level, interests, and past learning history. This information is sent to the server to be stored in the database. Input is done by the user entering information into an input form and pressing the submit button. The input information is converted to JSON format and sent to the server as data processing. The server analyzes the received data and stores it in the database.

[0421] Step 2:

[0422] The server calls a natural language generation AI based on the saved learner profile and generates optimal learning content for the user. Profile data (e.g., algebra problems as a weak point) is input, and optimized learning content is generated based on that. Data processing involves converting the profile data into prompt sentences and inputting them into the generative AI model. The output learning content is sent to the user's device.

[0423] Step 3:

[0424] The user uses the learning content received on their device to progress through their studies. Their progress during the study (time to solve the problem, correct / incorrect answers, etc.) is recorded in real time on the device and sent to the server. The input is the result of the user's answers, and the answer data is converted to JSON format and sent to the server as data processing. The server analyzes the received data and saves the progress status in a database.

[0425] Step 4:

[0426] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses (e.g., solving algebraic equations), it again uses natural language generation AI to generate additional content for reinforcement learning. The progress data is used as input, and the results of identifying the weaknesses are converted into prompt sentences, which are then input into the generative AI model. The output reinforcement learning content is then sent to the user's device.

[0427] Step 5:

[0428] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data and generates additional explanations or explanations from different approaches as needed. The answer data is used as input, and the understanding is evaluated as a data calculation. The generative AI model is used again to generate additional explanations, and the output is sent to the user's device. As a specific example, if a user makes multiple mistakes on a specific quadratic equation problem, a step-by-step explanation is generated.

[0429] Step 6:

[0430] The device uses an emotion engine to recognize emotions from the user's facial expressions and voice. The collected emotion data is sent to the server in real time. The input is the user's facial expressions and voice data, and the emotion engine processes the data to determine the emotional state and send the resulting data to the server. Specifically, the device uses a camera to capture facial expressions and voice recognition software to analyze the voice.

[0431] Step 7:

[0432] The server adjusts the learning content and learning progress methods based on the emotional data received from the emotion engine. The emotional data is used as input, and the data is calculated to adjust optimal learning support based on the emotional state. The output is the adjusted learning content and methods, which are sent to the user's device. For example, if a state of confusion is recognized, the difficulty level of the content may be lowered or additional explanations may be provided.

[0433] In this way, the data collected at each step and the content generated are transmitted and received bidirectionally between the server and the device, providing optimized support to the learner in real time.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] [Second embodiment]

[0438] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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."

[0450] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[0451] (Collecting learner profiles)

[0452] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[0453] (learning content generation)

[0454] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[0455] (Monitoring learning progress)

[0456] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0457] (Identifying weaknesses and suggesting reinforcement learning)

[0458] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[0459] (Evaluation of understanding and additional explanation)

[0460] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[0461] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[0462] The processing flow will be explained below.

[0463] Step 1:

[0464] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[0465] Step 2:

[0466] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[0467] Step 3:

[0468] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[0469] Step 4:

[0470] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[0471] Step 5:

[0472] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[0473] Step 6:

[0474] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[0475] Step 7:

[0476] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[0477] Step 8:

[0478] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[0479] Step 9:

[0480] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[0481] Step 10:

[0482] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[0483] Step 11:

[0484] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[0485] Step 12:

[0486] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[0487] Step 13:

[0488] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[0489] Step 14:

[0490] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[0491] Step 15:

[0492] The device records the user's answers. The device records the user's answers and sends them to the server.

[0493] Step 16:

[0494] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[0495] Step 17:

[0496] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[0497] Step 18:

[0498] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[0499] Step 19:

[0500] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[0501] Example 1

[0502] 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."

[0503] Conventional learning support systems have difficulty providing optimal learning content based on each learner's individual characteristics and progress. They also lack a mechanism for identifying learners' weaknesses in real time and quickly suggesting appropriate reinforcement learning. This makes it difficult to improve a learner's understanding and maximize learning efficiency. Furthermore, they are also inadequate in assessing a learner's understanding based on their answers and providing corresponding additional explanations, limiting the effectiveness of learning.

[0504] 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.

[0505] In this invention, the server includes: means for collecting a learner profile by a user inputting profile information such as grade level, interests, and past learning history and transmitting it to the server via a terminal; means for generating optimal learning content based on generated prompts using a natural language generation AI model based on the collected learner profile; means for the terminal to record the user's learning status in real time and transmit learning progress data to the server, which analyzes the data to monitor the learner's learning progress; means for analyzing the learning progress data and generating additional content for reinforcement learning using a natural language generation AI model to identify the learner's weaknesses and suggest reinforcement learning; and means for the terminal to record the user's answers, the server to evaluate the user's level of understanding based on the data, and providing additional explanations using the natural language generation AI model as needed. This allows for learning support optimized for each learner, enabling efficient and effective learning.

[0506] A "learner profile" refers to a set of information about an individual learner, such as the user's grade level, interests, and past learning history.

[0507] "Terminal" refers to an electronic device with communication capabilities operated by a user, which is used to input a learning profile and access learning content.

[0508] "Server" refers to a computer system that collects, stores, and analyzes information, generates learning content, and monitors progress.

[0509] "Natural language generation AI model" refers to an artificial intelligence model that automatically generates text appropriate for a specific task based on input prompts.

[0510] A "prompt" refers to input text that provides specific instructions or questions to a natural language generation AI model.

[0511] "Learning content" refers to a series of educational materials, such as teaching materials, workbooks, and explanations, created for use by learners.

[0512] "Learning progress" refers to data that shows the progress and results of the learning content that a learner has engaged in.

[0513] "Monitoring" refers to the process of recording learning progress data in real time and tracking and managing learner progress.

[0514] "Reinforcement learning" refers to additional learning content or materials provided to identify learners' weaknesses and help them overcome them.

[0515] "Answer" refers to the answer or response that a learner submits to a question in the learning content.

[0516] "Understanding" refers to measurable indicators or assessment results that show how well a learner has understood the learning content.

[0517] "Additional explanation" refers to explanations or explanations provided in addition to existing learning content to improve a learner's understanding.

[0518] The present invention relates to a system for collecting learner profiles, generating learning content, monitoring learning progress, identifying weaknesses and suggesting supplementary learning, and evaluating comprehension and providing additional explanations. The following describes in detail the modes for implementing the present invention.

[0519] First, the user enters profile information such as grade level, interests, and past learning history. The user enters this information using an input form on the device and presses the submit button. The device encrypts this information using the HTTPS protocol and securely sends it to the server. The server then inserts the received information into the database using an SQL query to store it.

[0520] Next, the server generates optimal learning content for the user based on the saved learner profile using the natural language generation AI model "OpenAI GPT-4." The server analyzes the profile information and sends a prompt to the AI ​​model. An example of a specific prompt is, "Please generate an assignment for a high school sophomore who is weak in algebra." The AI ​​model receives this prompt, generates appropriate learning content, and sends it back to the server. The server parses the generated content in JSON format and sends it to the user's device.

[0521] Users use the learning content received on their device to progress with their studies. They solve problems and enter their answers into the device. At this time, the device records the user's learning status in real time, specifically data such as the time it takes to solve the problems and whether the answers were correct or incorrect, and periodically sends this data to the server. The server analyzes this data and monitors the user's learning progress. Machine learning algorithms are used for accurate data analysis.

[0522] By analyzing the learning progress data, the server identifies the user's weaknesses. For example, if the user repeatedly makes a specific mistake when solving algebraic equations, the server uses that information to send another prompt to the AI ​​model. A specific prompt such as "Please generate reinforcement problems for users who make many mistakes when solving algebraic equations" is used. The AI ​​model generates additional reinforcement learning content and sends it back to the server. The server then sends the generated content to the user's device.

[0523] Finally, when the user works through the reinforcement learning content and enters the answers into the device, the device sends the answer data to the server. The server uses this data to evaluate the user's level of understanding. If the user's level of understanding is determined to be low, the server again uses the AI ​​model to generate additional explanations or explanations from a different approach and sends them to the device. For example, the server could send a prompt such as, "For users who repeatedly have trouble solving a particular algebra problem, please provide a step-by-step explanation of the answer."

[0524] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[0525] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0526] Step 1:

[0527] The user enters profile information such as grade level, interests, and past learning history.

[0528] Specifically, the user enters the necessary information into the input form on the terminal and clicks the send button.

[0529] Input: Grade, interests, past learning history

[0530] Output: Profile information entered into the terminal

[0531] Step 2:

[0532] The device sends the profile information to the server.

[0533] The device uses the HTTPS protocol to encrypt data and send it securely to the server.

[0534] Input: Profile information entered on the device

[0535] Output: Profile information sent to the server

[0536] Step 3:

[0537] The server stores the profile information in a database.

[0538] Specifically, the server inserts the received profile information into a database using an SQL query.

[0539] Input: Profile information sent to the server

[0540] Output: Profile information stored in the database

[0541] Step 4:

[0542] The server calls the AI ​​model based on the profile information and generates learning content.

[0543] The server analyzes the stored profile information and sends prompts to the generative AI model, such as "Please generate an assignment for a high school sophomore who is weak in algebra."

[0544] Input: Profile information stored in the database

[0545] Output: Prompts to send to the generative AI model and generated learning content

[0546] Step 5:

[0547] The server transmits the generated learning content to the user's terminal.

[0548] The server parses the generated content in JSON format and sends it to the user's device.

[0549] Input: Generated learning content

[0550] Output: Learning content sent to the user's device

[0551] Step 6:

[0552] Users can use the learning content on their devices to progress with their studies.

[0553] Specifically, the user solves the problem displayed on the terminal and inputs the answer.

[0554] Input: Learning content sent to your device

[0555] Output: User's answer

[0556] Step 7:

[0557] The terminal records the user's learning status and sends it to the server.

[0558] The device records data such as the time it takes to solve the questions and whether the answers were correct or incorrect in real time, and periodically transmits this data to the server.

[0559] Input: User answers, learning status data

[0560] Output: Learning status data sent to the server

[0561] Step 8:

[0562] The server analyzes the learning progress data and monitors the learner's progress.

[0563] Specifically, the server analyzes the received data and uses machine learning algorithms to evaluate the learner's performance and trends.

[0564] Input: Learning status data sent to the server

[0565] Output: Parsed learning progress data, learner progress

[0566] Step 9:

[0567] The server identifies weaknesses based on learning progress data and generates additional content for reinforcement learning.

[0568] The server then prompts the AI ​​model again based on the identified weaknesses, using a specific prompt such as "Generate reinforcement problems for users who make a lot of mistakes solving algebra equations."

[0569] Input: Parsed learning progress data, generated prompts

[0570] Output: Generated reinforcement learning content

[0571] Step 10:

[0572] The server transmits the generated augmented content to the terminal.

[0573] The server parses the additional content in JSON format and sends it to the user's device.

[0574] Input: Generated reinforcement learning content

[0575] Output: Reinforcement learning content sent to the user's device

[0576] Step 11:

[0577] The user uses the reinforcement learning content and inputs the answers into the terminal.

[0578] In concrete terms, the user solves the additional problem and inputs the answer into the terminal.

[0579] Input: Reinforcement learning content sent to the device

[0580] Output: Additional answers provided by the user

[0581] Step 12:

[0582] The terminal records the user's answers and sends them to the server.

[0583] The device records the answer data in real time and transmits it to the server.

[0584] Input: Additional answers provided by the user

[0585] Output: Additional answer data sent to the server

[0586] Step 13:

[0587] The server evaluates the level of understanding based on the answer data and provides additional explanations if necessary.

[0588] The server analyzes the answer data and, if it determines that the level of understanding is low, sends another prompt to the AI ​​model, specifically, using the prompt sentence, "Please provide a step-by-step explanation of the solution for users who have been unable to solve a particular algebra problem multiple times."

[0589] Input: Additional answer data sent to the server, generated prompt text

[0590] Output: Generated additional description

[0591] Step 14:

[0592] The server sends the generated additional description to the terminal.

[0593] The server parses the additional explanation in JSON format and sends it to the user's device.

[0594] Input: Generated additional description

[0595] Output: Additional instructions sent to the user's terminal

[0596] In this way, by explaining the process steps, the specific operation of the system and its flow can be clarified.

[0597] (Application example 1)

[0598] 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."

[0599] Today's learners have diverse learning needs and progress levels, making it difficult to select optimal learning materials and manage their progress. In particular, when receiving learning support in a brick-and-mortar store, it is difficult to receive appropriate advice and learning material recommendations in real time. There is a need to solve this problem and provide learning support optimized for each user's learning needs.

[0600] 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.

[0601] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting supplementary learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for a user to input their own learning profile in a physical store and be provided with advice and materials for purchasing on the spot, means for recording the user's progress in learning using the learning materials and reference books they have purchased, and means for recommending supplementary learning materials available for purchase in the store based on the user's learning progress. This makes it possible to select optimal learning materials for individual learners and provide learning support in real time, even in a store environment.

[0602] "Learner profile" refers to the learner's individual attribute information, such as the user's grade, interests, and past learning history.

[0603] "Means of collection" refers to the methods and technologies used to obtain information provided by users and send it to a server.

[0604] "Learning content" refers to problem sets, teaching materials, explanatory materials, etc. provided for learning.

[0605] "Means of generation" refers to the technology and methods for creating optimal learning content based on collected learner profiles.

[0606] "Monitoring means" refers to methods and technologies that track and record learners' learning progress in real time.

[0607] A "weakness" refers to an area where a learner has insufficient understanding or answers correctly in a particular learning item.

[0608] "Reinforcement learning" refers to additional learning content or training provided to learners to overcome weaknesses.

[0609] "Suggestion methods" refer to techniques and methods for presenting appropriate reinforcement learning based on the learner's weaknesses.

[0610] "Answers and responses" refers to the answers given by learners to the learning content and the evaluation results.

[0611] "Comprehension" refers to the degree to which a learner understands the learning content provided.

[0612] "Means for providing additional explanations" refers to techniques and methods for generating and providing additional explanations when a learner's level of comprehension is low.

[0613] "Brick and mortar store" refers to an educational equipment store, bookstore, or other store that operates from a physical location.

[0614] "Advice" refers to advice that recommends optimal learning materials and methods based on the learner's profile.

[0615] "Materials for considering a purchase" refers to information and recommendations that learners can refer to when considering a purchase in a store.

[0616] "Means for recording the situation" refers to techniques and methods for recording how learners progress with the purchased learning materials.

[0617] "Supplementary materials" refers to additional materials provided at the store to reinforce a learner's weak areas.

[0618] "Recommendation means" refers to the technology or method for selecting and presenting the most appropriate supplementary learning materials based on learning progress data.

[0619] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. Using this system, it is possible to provide learning support optimized for each learner, even in physical stores.

[0620] Collecting learner profiles

[0621] Users use a smartphone app to enter their learner profile. The profile includes the learner's grade, interests, past learning history, etc. This information is sent from the device to the server and stored in a database. For example, a user may enter that they are a "second-year high school student" and are interested in "math" and "English."

[0622] Generating learning content

[0623] The server uses a generative AI model to generate optimal learning content for the user based on the saved learner profile. For example, if the user is weak in algebra, the server generates a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[0624] Monitoring learning progress

[0625] Users study using purchased learning materials and reference books. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0626] Identifying weaknesses and suggesting reinforcement learning

[0627] The server analyzes the learning progress data to identify the user's weaknesses. Based on the identified weaknesses, the server uses a generative AI model to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes in solving algebraic equations, the server can generate a set of problems specific to that topic and send it to the device.

[0628] Assessment of understanding and further explanation

[0629] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the generative AI model is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the server will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[0630] Use in physical stores

[0631] Users visit a physical store and enter their learning profile through a smartphone app. The app then recommends optimal learning materials and reference books based on the profile information entered. The app also records how the user progresses with the materials they have purchased and sends this information to the server. This allows the app to recommend supplementary materials that can be purchased at the store.

[0632] Specific examples

[0633] For example, suppose a user is a second-year high school student and has an interest in mathematics and English, and has purchased a book on basic algebra. In this case, the generative AI model receives the following prompt and generates learning content:

[0634] Example prompt sentence:

[0635] "Generate the best Mathematics Algebra learning content based on user learning profile ID: 12345."

[0636] In this way, optimal learning support that meets the user's learning needs in real time can be realized.

[0637] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0638] Step 1:

[0639] Users use a smartphone app to enter their learner profile. This information, such as their grade, interests, and past learning history, is sent to the server via the device. The server then stores the received profile information in a database. This saves information, such as the user being a "second-year high school student" and having interests in "math" and "English," which is then used to generate subsequent learning content.

[0640] Step 2:

[0641] The server sends a prompt to the generative AI model based on the saved learner profile to generate optimal learning content for the user. The prompt will be in the form of "Please generate optimal learning content for math algebra based on the user's learning profile ID: {ID}." The generative AI model generates learning content based on this input and returns the results to the server. The server then sends the generated content to the user's device.

[0642] Step 3:

[0643] The user uses the provided learning content to progress through their studies. The device records the user's learning progress (e.g., time to solve problems, correct / incorrect answers) in real time and sends the data to the server. The server aggregates this data and monitors the learner's progress.

[0644] Step 4:

[0645] The server analyzes the collected learning progress data. For example, it identifies that the user makes many mistakes on a particular algebra problem. The server then invokes the generative AI model again and sends a prompt saying, "Based on the user's learning progress data, please generate learning content that reinforces specific weaknesses." The model generates reinforcement learning content specific to the weaknesses and sends it to the server. The server then sends this content to the user's device.

[0646] Step 5:

[0647] The device records the results (answer data) of the user's learning as they follow the reinforcement learning content and sends that data back to the server. The server analyzes this data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends a new prompt to the generative AI model, asking it to generate more detailed additional explanations or explanations from a different approach. The generated additional explanations and explanations are sent from the server to the user's device.

[0648] Step 6:

[0649] When a user visits a physical store, they enter their learning profile through a smartphone app. Based on the profile information entered, the app recommends the most suitable study materials and reference books to purchase at the store. Based on the ID, the app retrieves recommendation information and study progress data from the server. This allows the user to select the most suitable study materials and reference books in the store.

[0650] Step 7:

[0651] The smartphone app records how the user progresses with the study materials and reference books they have purchased (e.g., study time, percentage of correct answers, etc.) and sends this data to the server. Based on this data, the server recommends supplementary materials suitable for the user. Information on the recommended supplementary materials is used the next time the user considers purchasing them in a physical store or online.

[0652] 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.

[0653] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and also combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[0654] (Collecting learner profiles)

[0655] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[0656] (learning content generation)

[0657] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[0658] (Monitoring learning progress)

[0659] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0660] (Identifying weaknesses and suggesting reinforcement learning)

[0661] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[0662] (Evaluation of understanding and additional explanation)

[0663] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[0664] (Emotion recognition)

[0665] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.). The recognized emotion data is sent to the server in real time.

[0666] (Adjusting Emotion-Based Learning Support)

[0667] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, it can lower the difficulty of the content or add more detailed explanations. If the user is tired, it can also send a notification to the device suggesting a break.

[0668] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[0669] The processing flow will be explained below.

[0670] Step 1:

[0671] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[0672] Step 2:

[0673] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[0674] Step 3:

[0675] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[0676] Step 4:

[0677] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[0678] Step 5:

[0679] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[0680] Step 6:

[0681] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[0682] Step 7:

[0683] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[0684] Step 8:

[0685] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[0686] Step 9:

[0687] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[0688] Step 10:

[0689] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[0690] Step 11:

[0691] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[0692] Step 12:

[0693] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[0694] Step 13:

[0695] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[0696] Step 14:

[0697] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[0698] Step 15:

[0699] The device records the user's answers. The device records the user's answers and sends them to the server.

[0700] Step 16:

[0701] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[0702] Step 17:

[0703] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[0704] Step 18:

[0705] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[0706] Step 19:

[0707] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[0708] Step 20:

[0709] The device recognizes the user's emotions. The device analyzes the user's facial expressions and voice, and the emotion engine identifies the user's emotional state. For example, the device recognizes emotions such as confusion, excitement, or fatigue.

[0710] Step 21:

[0711] The device sends emotion data to the server. The device sends the emotion data recognized by the emotion engine to the server in real time.

[0712] Step 22:

[0713] The server analyzes the emotional data and evaluates the user's current emotional state based on the received emotional data.

[0714] Step 23:

[0715] The server adjusts the learning content. The server adjusts the difficulty and content of the learning content based on the emotional data. For example, if the user is confused, the server may lower the difficulty of the content or provide additional hints.

[0716] Step 24:

[0717] The server adjusts the learning progress based on the emotion data. For example, if the user is tired, it sends a notification to the device suggesting a break.

[0718] Step 25:

[0719] The terminal displays the adjusted content. The terminal displays the adjusted learning content and break suggestions sent from the server to the user.

[0720] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[0721] Example 2

[0722] 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."

[0723] Conventional learning systems have difficulty providing optimal learning content for each learner, monitoring progress, and providing feedback based on their level of understanding. Furthermore, they are unable to recognize the learner's emotional state and adjust learning support accordingly, preventing the maximization of learning effectiveness.

[0724] 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.

[0725] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing the learner's emotional state, and means for adjusting learning support based on the recognized emotional state. This allows for an optimal learning experience for each learner, enabling efficient and effective learning.

[0726] A "learner profile" is data that includes personal information such as a learner's grade, interests, and past learning history.

[0727] "Learning content" refers to educational materials and exercises that are generated based on the learner's profile and learning progress.

[0728] "Progress monitoring" is the process of tracking and recording data (such as time to solve a problem, correct / incorrect answers, etc.) as a learner progresses through their studies.

[0729] "Identifying weaknesses" refers to analyzing a learner's learning data to identify areas where they lack understanding or make repeated mistakes.

[0730] "Reinforcement learning suggestions" refers to suggestions to provide additional learning content to complement or reinforce identified weaknesses of learners.

[0731] "Assessing comprehension" involves analyzing the problems solved by learners and their responses to determine how much they have understood.

[0732] "Additional explanation" means providing a more detailed explanation or an explanation from a different approach when the learner's understanding is insufficient.

[0733] "Recognizing emotional states" refers to detecting the learner's emotions (confusion, excitement, fatigue, etc.) from their facial expressions and voice.

[0734] "Adjusting learning support" refers to changing or adjusting learning content or learning progression methods based on the recognized emotional state of the learner.

[0735] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system provides optimal learning support for each learner, enabling efficient and effective learning.

[0736] Collecting learner profiles

[0737] Users enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, if a user enters that they are a second-year high school student and are interested in math and English, this information is recorded as their profile information.

[0738] Generating learning content

[0739] The server calls a natural language generation AI (e.g., GPT-4) based on the saved learner profile and generates optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it sends a prompt such as "Please generate a problem set that will teach me algebra from the basics" to the AI, which then generates a problem set. The generated content is then sent from the server to the device.

[0740] Monitoring learning progress

[0741] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0742] Identifying weaknesses and suggesting reinforcement learning

[0743] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI (e.g., BERT) to generate additional content for reinforcement learning. For example, it sends a prompt such as "Please create a problem set to help improve my weakness in solving algebraic equations" to the AI, and the problem set is created. The generated reinforcement content is sent from the server to the device.

[0744] Assessment of understanding and further explanation

[0745] The device records the user's answer data and sends it to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the server uses natural language generation AI to generate additional explanations or explanations from a different approach. For example, the server sends a prompt such as "Please explain the process of solving this algebra problem step by step" to the AI ​​to generate an explanation. These additional explanations are sent from the server to the device.

[0746] Emotion recognition

[0747] The device is equipped with an emotion engine (e.g., a general emotion recognition API) that recognizes the user's emotional state from their facial expressions and voice. The emotion engine recognizes the user's emotional state during learning and sends the data to the server in real time.

[0748] Emotion-based learning support coordination

[0749] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, the server sends a prompt to the AI ​​such as, "Please provide easy algebra problems and detailed explanations for the struggling user," and generates easy problems and detailed explanations. If the user is tired, the server sends a notification to the device suggesting a break.

[0750] In this way, the system provides an optimized learning experience based on the learner's learning situation and emotional state, thereby realizing efficient and effective learning.

[0751] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0752] Step 1:

[0753] Collecting learner profiles

[0754] Input: Information such as the user's grade, interests, and past learning history

[0755] Specific behavior: Users fill out a registration form with their grade level, interests, and past learning history.

[0756] Data processing: The device receives this information and assembles it into data packets.

[0757] Output: The device sends data packets to the server, which stores the profile information in a database.

[0758] Step 2:

[0759] Generating learning content

[0760] Input: Learner profile stored in the database

[0761] Specific operation: The server analyzes the learner profile and sends a prompt to the natural language generation AI saying, "Please generate a problem set that will teach the basics of algebra in mathematics."

[0762] Data processing: Natural language generation AI (e.g., GPT-4) generates optimal learning content based on profile information.

[0763] Output: The generated learning content is sent from the server to the device.

[0764] Step 3:

[0765] Monitoring learning progress

[0766] Input: User's learning status (time to solve the problem, correct / incorrect answers, etc.)

[0767] Specific operation: The user uses the learning content received on the device to proceed with their learning. The device records their learning progress in real time.

[0768] Data processing: The device organizes the recorded data and sends it to the server.

[0769] Output: The server monitors the learning progress based on the received data and stores it in a database.

[0770] Step 4:

[0771] Identifying weaknesses and suggesting reinforcement learning

[0772] Input: Learning progress data

[0773] Specific operation: The server analyzes the learning progress data and identifies the user's weaknesses, such as "Many mistakes in solving algebraic equations." The server then sends a prompt to the natural language generation AI, saying, "Please create a problem set to help overcome the weaknesses in solving algebraic equations."

[0774] Data processing: Natural language generation AI generates content for reinforcement learning based on identified weaknesses.

[0775] Output: The generated augmentation content is sent from the server to the device.

[0776] Step 5:

[0777] Assessment of understanding and further explanation

[0778] Input: User's answer data

[0779] How it works: The device records the user's answers and sends them to the server. The server analyzes the answer data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends the AI ​​a prompt saying, "Please explain the process of solving this algebra problem step by step."

[0780] Data processing: Natural language generation AI generates detailed explanations based on prompts.

[0781] Output: The additional instructions are sent from the server to the terminal and provided to the user.

[0782] Step 6:

[0783] Emotion recognition

[0784] Input: User facial and voice data

[0785] How it works: The device's camera and microphone capture the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotional state (confusion, excitement, fatigue, etc.).

[0786] Data processing: The emotion engine analyzes and classifies emotion data.

[0787] Output: The recognized emotion data is sent to the server in real time.

[0788] Step 7:

[0789] Emotion-based learning support coordination

[0790] Input: Emotion data

[0791] Specific behavior: The server receives the emotion data and sends a prompt to the AI ​​saying, "Please provide an easy algebra problem and detailed explanation to the struggling user." If the server determines that the user is tired, it also generates a notification saying, "Take a break."

[0792] Data processing: Natural language generation AI generates optimal content based on prompts.

[0793] Output: The adjusted learning content and notifications are sent to the device and provided to the user.

[0794] These steps enable the system to provide learners with an optimal learning experience and maximize learning effectiveness.

[0795] (Application example 2)

[0796] 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."

[0797] Conventional learning support systems are unable to take into account the learner's emotional state, which can lead to reduced learning efficiency and effectiveness. It is also difficult to provide optimal content to each individual learner in real time. Furthermore, because emotional data cannot be referenced when closely monitoring learning progress or proposing effective reinforcement learning to address individual weaknesses, they are unable to respond adequately to learners. To solve these issues, a highly customized learning support system is needed.

[0798] 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 means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing emotions, and means for adjusting the learning content and learning progress method based on the recognized emotions. This makes it possible to grasp the learner's learning situation and emotional state in real time and provide individually optimized learning support.

[0799] A "learner profile" is data about an individual learner, including basic information about the learner, their interests, and past learning history.

[0800] "Learning content" refers to content such as study materials, question sets, and explanations that are generated based on the learner's profile.

[0801] "Learning progress" refers to data that shows the progress and results of a learner's learning as they use learning content.

[0802] "Reinforcement learning" refers to additional learning content or educational activities that complement learners' weaknesses and strengthen their abilities.

[0803] "Means for recognizing emotions" refers to technology that analyzes data such as the learner's facial expressions and voice to identify their emotional state at that time (for example, confusion, excitement, fatigue, etc.).

[0804] "Means for adjusting learning content and learning methods based on emotions" refers to technology that provides optimal learning content and learning methods based on the learner's emotional state based on recognized emotional data.

[0805] This invention is a system that collects learner profiles, generates learning content, monitors learning progress, identifies weaknesses and suggests supplementary learning, evaluates comprehension and provides additional explanations, and uses an emotion engine to recognize the user's emotions and provide learning support based on these. This enables optimal learning support for each learner, resulting in efficient and effective learning.

[0806] The system mainly includes the following components:

[0807] 1. Collecting learner profiles

[0808] When a user registers with the system, the terminal inputs profile information such as the user's grade, interests, and past learning history.

[0809] The collected information is sent to a server and stored in a database.

[0810] 2. Generating learning content

[0811] Based on the saved learner profile, the server calls up a natural language generation AI to generate optimal learning content for the user.

[0812] For example, if it turns out that the user is weak in algebra, a series of problem sets starting from the basics of algebra can be generated. The generated content is sent from the server to the user's terminal.

[0813] 3. Monitoring your learning progress

[0814] The user uses the learning content received on the terminal to advance their learning.

[0815] The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends the data to the server.

[0816] The server uses this data to monitor the learner's progress.

[0817] 4. Identifying weaknesses and suggesting reinforcement learning

[0818] The server analyzes the learning progress data and identifies the user's weaknesses.

[0819] Based on the identified weaknesses, natural language generation AI is again used to generate additional content for reinforcement learning.

[0820] For example, if a user makes particularly many mistakes when solving algebraic equations, a collection of exercises specific to that topic can be generated. The generated reinforcement content is then sent from the server to the device.

[0821] 5. Assessment of understanding and further explanation

[0822] The terminal records the user's answers and sends them to the server.

[0823] The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, it uses natural language generation AI to generate additional explanations or explanations from different approaches.

[0824] For example, if a user repeatedly has trouble solving a particular algebra problem, the server will provide step-by-step instructions on the process of solving the problem, including alternative solutions. Additional instructions are sent from the server to the device.

[0825] 6. Emotional Recognition

[0826] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice.

[0827] The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.) and transmits the recognized emotion data to the server in real time.

[0828] 7. Adjusting emotion-based learning support

[0829] The server adjusts the learning content and learning progress method based on the emotional data received from the emotion engine.

[0830] For example, if the user is confused, the difficulty level of the content can be reduced or more detailed explanations can be added. Also, if the user is tired, a notification can be sent to the device suggesting that they take a break.

[0831] As a specific example, consider the case where a user incorrectly answers the same algebra problem multiple times while studying it. At this time, the device recognizes the user's state of confusion and sends it to the server in real time. The server uses this information to adjust the difficulty of the content or add step-by-step explanations. The AI ​​generator then inputs a prompt such as, "If the user repeatedly fails to solve a particular algebra problem, please generate content that provides a step-by-step explanation of the solution process and suggests different solutions. The theme of the problem is 'Solution to Quadratic Equations.'" This allows the learner to progress through their studies in a more understandable way.

[0832] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0833] Step 1:

[0834] When a user registers with the system, the device inputs profile information such as grade level, interests, and past learning history. This information is sent to the server to be stored in the database. Input is done by the user entering information into an input form and pressing the submit button. The input information is converted to JSON format and sent to the server as data processing. The server analyzes the received data and stores it in the database.

[0835] Step 2:

[0836] The server calls a natural language generation AI based on the saved learner profile and generates optimal learning content for the user. Profile data (e.g., algebra problems as a weak point) is input, and optimized learning content is generated based on that. Data processing involves converting the profile data into prompt sentences and inputting them into the generative AI model. The output learning content is sent to the user's device.

[0837] Step 3:

[0838] The user uses the learning content received on their device to progress through their studies. Their progress during the study (time to solve the problem, correct / incorrect answers, etc.) is recorded in real time on the device and sent to the server. The input is the result of the user's answers, and the answer data is converted to JSON format and sent to the server as data processing. The server analyzes the received data and saves the progress status in a database.

[0839] Step 4:

[0840] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses (e.g., solving algebraic equations), it again uses natural language generation AI to generate additional content for reinforcement learning. The progress data is used as input, and the results of identifying the weaknesses are converted into prompt sentences, which are then input into the generative AI model. The output reinforcement learning content is then sent to the user's device.

[0841] Step 5:

[0842] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data and generates additional explanations or explanations from different approaches as needed. The answer data is used as input, and the understanding is evaluated as a data calculation. The generative AI model is used again to generate additional explanations, and the output is sent to the user's device. As a specific example, if a user makes multiple mistakes on a specific quadratic equation problem, a step-by-step explanation is generated.

[0843] Step 6:

[0844] The device uses an emotion engine to recognize emotions from the user's facial expressions and voice. The collected emotion data is sent to the server in real time. The input is the user's facial expressions and voice data, and the emotion engine processes the data to determine the emotional state and send the resulting data to the server. Specifically, the device uses a camera to capture facial expressions and voice recognition software to analyze the voice.

[0845] Step 7:

[0846] The server adjusts the learning content and learning progress methods based on the emotional data received from the emotion engine. The emotional data is used as input, and the data is calculated to adjust optimal learning support based on the emotional state. The output is the adjusted learning content and methods, which are sent to the user's device. For example, if a state of confusion is recognized, the difficulty level of the content may be lowered or additional explanations may be provided.

[0847] In this way, the data collected at each step and the content generated are transmitted and received bidirectionally between the server and the device, providing optimized support to the learner in real time.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] [Third embodiment]

[0852] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0853] 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.

[0854] 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).

[0855] 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.

[0856] 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.

[0857] 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).

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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."

[0864] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[0865] (Collecting learner profiles)

[0866] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[0867] (learning content generation)

[0868] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[0869] (Monitoring learning progress)

[0870] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[0871] (Identifying weaknesses and suggesting reinforcement learning)

[0872] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[0873] (Evaluation of understanding and additional explanation)

[0874] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[0875] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[0876] The processing flow will be explained below.

[0877] Step 1:

[0878] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[0879] Step 2:

[0880] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[0881] Step 3:

[0882] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[0883] Step 4:

[0884] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[0885] Step 5:

[0886] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[0887] Step 6:

[0888] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[0889] Step 7:

[0890] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[0891] Step 8:

[0892] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[0893] Step 9:

[0894] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[0895] Step 10:

[0896] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[0897] Step 11:

[0898] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[0899] Step 12:

[0900] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[0901] Step 13:

[0902] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[0903] Step 14:

[0904] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[0905] Step 15:

[0906] The device records the user's answers. The device records the user's answers and sends them to the server.

[0907] Step 16:

[0908] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[0909] Step 17:

[0910] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[0911] Step 18:

[0912] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[0913] Step 19:

[0914] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[0915] Example 1

[0916] 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."

[0917] Conventional learning support systems have difficulty providing optimal learning content based on each learner's individual characteristics and progress. They also lack a mechanism for identifying learners' weaknesses in real time and quickly suggesting appropriate reinforcement learning. This makes it difficult to improve a learner's understanding and maximize learning efficiency. Furthermore, they are also inadequate in assessing a learner's understanding based on their answers and providing corresponding additional explanations, limiting the effectiveness of learning.

[0918] 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.

[0919] In this invention, the server includes: means for collecting a learner profile by a user inputting profile information such as grade level, interests, and past learning history and transmitting it to the server via a terminal; means for generating optimal learning content based on generated prompts using a natural language generation AI model based on the collected learner profile; means for the terminal to record the user's learning status in real time and transmit learning progress data to the server, which analyzes the data to monitor the learner's learning progress; means for analyzing the learning progress data and generating additional content for reinforcement learning using a natural language generation AI model to identify the learner's weaknesses and suggest reinforcement learning; and means for the terminal to record the user's answers, the server to evaluate the user's level of understanding based on the data, and providing additional explanations using the natural language generation AI model as needed. This allows for learning support optimized for each learner, enabling efficient and effective learning.

[0920] A "learner profile" refers to a set of information about an individual learner, such as the user's grade level, interests, and past learning history.

[0921] "Terminal" refers to an electronic device with communication capabilities operated by a user, which is used to input a learning profile and access learning content.

[0922] "Server" refers to a computer system that collects, stores, and analyzes information, generates learning content, and monitors progress.

[0923] "Natural language generation AI model" refers to an artificial intelligence model that automatically generates text appropriate for a specific task based on input prompts.

[0924] A "prompt" refers to input text that provides specific instructions or questions to a natural language generation AI model.

[0925] "Learning content" refers to a series of educational materials, such as teaching materials, workbooks, and explanations, created for use by learners.

[0926] "Learning progress" refers to data that shows the progress and results of the learning content that a learner has engaged in.

[0927] "Monitoring" refers to the process of recording learning progress data in real time and tracking and managing learner progress.

[0928] "Reinforcement learning" refers to additional learning content or materials provided to identify learners' weaknesses and help them overcome them.

[0929] "Answer" refers to the answer or response that a learner submits to a question in the learning content.

[0930] "Understanding" refers to measurable indicators or assessment results that show how well a learner has understood the learning content.

[0931] "Additional explanation" refers to explanations or explanations provided in addition to existing learning content to improve a learner's understanding.

[0932] The present invention relates to a system for collecting learner profiles, generating learning content, monitoring learning progress, identifying weaknesses and suggesting supplementary learning, and evaluating comprehension and providing additional explanations. The following describes in detail the modes for implementing the present invention.

[0933] First, the user enters profile information such as grade level, interests, and past learning history. The user enters this information using an input form on the device and presses the submit button. The device encrypts this information using the HTTPS protocol and securely sends it to the server. The server then inserts the received information into the database using an SQL query to store it.

[0934] Next, the server generates optimal learning content for the user based on the saved learner profile using the natural language generation AI model "OpenAI GPT-4." The server analyzes the profile information and sends a prompt to the AI ​​model. An example of a specific prompt is, "Please generate an assignment for a high school sophomore who is weak in algebra." The AI ​​model receives this prompt, generates appropriate learning content, and sends it back to the server. The server parses the generated content in JSON format and sends it to the user's device.

[0935] Users use the learning content received on their device to progress with their studies. They solve problems and enter their answers into the device. At this time, the device records the user's learning status in real time, specifically data such as the time it takes to solve the problems and whether the answers were correct or incorrect, and periodically sends this data to the server. The server analyzes this data and monitors the user's learning progress. Machine learning algorithms are used for accurate data analysis.

[0936] By analyzing the learning progress data, the server identifies the user's weaknesses. For example, if the user repeatedly makes a specific mistake when solving algebraic equations, the server uses that information to send another prompt to the AI ​​model. A specific prompt such as "Please generate reinforcement problems for users who make many mistakes when solving algebraic equations" is used. The AI ​​model generates additional reinforcement learning content and sends it back to the server. The server then sends the generated content to the user's device.

[0937] Finally, when the user works through the reinforcement learning content and enters the answers into the device, the device sends the answer data to the server. The server uses this data to evaluate the user's level of understanding. If the user's level of understanding is determined to be low, the server again uses the AI ​​model to generate additional explanations or explanations from a different approach and sends them to the device. For example, the server could send a prompt such as, "For users who repeatedly have trouble solving a particular algebra problem, please provide a step-by-step explanation of the answer."

[0938] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[0939] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0940] Step 1:

[0941] The user enters profile information such as grade level, interests, and past learning history.

[0942] Specifically, the user enters the necessary information into the input form on the terminal and clicks the send button.

[0943] Input: Grade, interests, past learning history

[0944] Output: Profile information entered into the terminal

[0945] Step 2:

[0946] The device sends the profile information to the server.

[0947] The device uses the HTTPS protocol to encrypt data and send it securely to the server.

[0948] Input: Profile information entered on the device

[0949] Output: Profile information sent to the server

[0950] Step 3:

[0951] The server stores the profile information in a database.

[0952] Specifically, the server inserts the received profile information into a database using an SQL query.

[0953] Input: Profile information sent to the server

[0954] Output: Profile information stored in the database

[0955] Step 4:

[0956] The server calls the AI ​​model based on the profile information and generates learning content.

[0957] The server analyzes the stored profile information and sends prompts to the generative AI model, such as "Please generate an assignment for a high school sophomore who is weak in algebra."

[0958] Input: Profile information stored in the database

[0959] Output: Prompts to send to the generative AI model and generated learning content

[0960] Step 5:

[0961] The server transmits the generated learning content to the user's terminal.

[0962] The server parses the generated content in JSON format and sends it to the user's device.

[0963] Input: Generated learning content

[0964] Output: Learning content sent to the user's device

[0965] Step 6:

[0966] Users can use the learning content on their devices to progress with their studies.

[0967] Specifically, the user solves the problem displayed on the terminal and inputs the answer.

[0968] Input: Learning content sent to your device

[0969] Output: User's answer

[0970] Step 7:

[0971] The terminal records the user's learning status and sends it to the server.

[0972] The device records data such as the time it takes to solve the questions and whether the answers were correct or incorrect in real time, and periodically transmits this data to the server.

[0973] Input: User answers, learning status data

[0974] Output: Learning status data sent to the server

[0975] Step 8:

[0976] The server analyzes the learning progress data and monitors the learner's progress.

[0977] Specifically, the server analyzes the received data and uses machine learning algorithms to evaluate the learner's performance and trends.

[0978] Input: Learning status data sent to the server

[0979] Output: Parsed learning progress data, learner progress

[0980] Step 9:

[0981] The server identifies weaknesses based on learning progress data and generates additional content for reinforcement learning.

[0982] The server then prompts the AI ​​model again based on the identified weaknesses, using a specific prompt such as "Generate reinforcement problems for users who make a lot of mistakes solving algebra equations."

[0983] Input: Parsed learning progress data, generated prompts

[0984] Output: Generated reinforcement learning content

[0985] Step 10:

[0986] The server transmits the generated augmented content to the terminal.

[0987] The server parses the additional content in JSON format and sends it to the user's device.

[0988] Input: Generated reinforcement learning content

[0989] Output: Reinforcement learning content sent to the user's device

[0990] Step 11:

[0991] The user uses the reinforcement learning content and inputs the answers into the terminal.

[0992] In concrete terms, the user solves the additional problem and inputs the answer into the terminal.

[0993] Input: Reinforcement learning content sent to the device

[0994] Output: Additional answers provided by the user

[0995] Step 12:

[0996] The terminal records the user's answers and sends them to the server.

[0997] The device records the answer data in real time and transmits it to the server.

[0998] Input: Additional answers provided by the user

[0999] Output: Additional answer data sent to the server

[1000] Step 13:

[1001] The server evaluates the level of understanding based on the answer data and provides additional explanations if necessary.

[1002] The server analyzes the answer data and, if it determines that the level of understanding is low, sends another prompt to the AI ​​model, specifically, using the prompt sentence, "Please provide a step-by-step explanation of the solution for users who have been unable to solve a particular algebra problem multiple times."

[1003] Input: Additional answer data sent to the server, generated prompt text

[1004] Output: Generated additional description

[1005] Step 14:

[1006] The server sends the generated additional description to the terminal.

[1007] The server parses the additional explanation in JSON format and sends it to the user's device.

[1008] Input: Generated additional description

[1009] Output: Additional instructions sent to the user's terminal

[1010] In this way, by explaining the process steps, the specific operation of the system and its flow can be clarified.

[1011] (Application example 1)

[1012] 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."

[1013] Today's learners have diverse learning needs and progress levels, making it difficult to select optimal learning materials and manage their progress. In particular, when receiving learning support in a brick-and-mortar store, it is difficult to receive appropriate advice and learning material recommendations in real time. There is a need to solve this problem and provide learning support optimized for each user's learning needs.

[1014] 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.

[1015] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting supplementary learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for a user to input their own learning profile in a physical store and be provided with advice and materials for purchasing on the spot, means for recording the user's progress in learning using the learning materials and reference books they have purchased, and means for recommending supplementary learning materials available for purchase in the store based on the user's learning progress. This makes it possible to select optimal learning materials for individual learners and provide learning support in real time, even in a store environment.

[1016] "Learner profile" refers to the learner's individual attribute information, such as the user's grade, interests, and past learning history.

[1017] "Means of collection" refers to the methods and technologies used to obtain information provided by users and send it to a server.

[1018] "Learning content" refers to problem sets, teaching materials, explanatory materials, etc. provided for learning.

[1019] "Means of generation" refers to the technology and methods for creating optimal learning content based on collected learner profiles.

[1020] "Monitoring means" refers to methods and technologies that track and record learners' learning progress in real time.

[1021] A "weakness" refers to an area where a learner has insufficient understanding or answers correctly in a particular learning item.

[1022] "Reinforcement learning" refers to additional learning content or training provided to learners to overcome weaknesses.

[1023] "Suggestion methods" refer to techniques and methods for presenting appropriate reinforcement learning based on the learner's weaknesses.

[1024] "Answers and responses" refers to the answers given by learners to the learning content and the evaluation results.

[1025] "Comprehension" refers to the degree to which a learner understands the learning content provided.

[1026] "Means for providing additional explanations" refers to techniques and methods for generating and providing additional explanations when a learner's level of comprehension is low.

[1027] "Brick and mortar store" refers to an educational equipment store, bookstore, or other store that operates from a physical location.

[1028] "Advice" refers to advice that recommends optimal learning materials and methods based on the learner's profile.

[1029] "Materials for considering a purchase" refers to information and recommendations that learners can refer to when considering a purchase in a store.

[1030] "Means for recording the situation" refers to techniques and methods for recording how learners progress with the purchased learning materials.

[1031] "Supplementary materials" refers to additional materials provided at the store to reinforce a learner's weak areas.

[1032] "Recommendation means" refers to the technology or method for selecting and presenting the most appropriate supplementary learning materials based on learning progress data.

[1033] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. Using this system, it is possible to provide learning support optimized for each learner, even in physical stores.

[1034] Collecting learner profiles

[1035] Users use a smartphone app to enter their learner profile. The profile includes the learner's grade, interests, past learning history, etc. This information is sent from the device to the server and stored in a database. For example, a user may enter that they are a "second-year high school student" and are interested in "math" and "English."

[1036] Generating learning content

[1037] The server uses a generative AI model to generate optimal learning content for the user based on the saved learner profile. For example, if the user is weak in algebra, the server generates a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[1038] Monitoring learning progress

[1039] Users study using purchased learning materials and reference books. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[1040] Identifying weaknesses and suggesting reinforcement learning

[1041] The server analyzes the learning progress data to identify the user's weaknesses. Based on the identified weaknesses, the server uses a generative AI model to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes in solving algebraic equations, the server can generate a set of problems specific to that topic and send it to the device.

[1042] Assessment of understanding and further explanation

[1043] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the generative AI model is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the server will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[1044] Use in physical stores

[1045] Users visit a physical store and enter their learning profile through a smartphone app. The app then recommends optimal learning materials and reference books based on the profile information entered. The app also records how the user progresses with the materials they have purchased and sends this information to the server. This allows the app to recommend supplementary materials that can be purchased at the store.

[1046] Specific examples

[1047] For example, suppose a user is a second-year high school student and has an interest in mathematics and English, and has purchased a book on basic algebra. In this case, the generative AI model receives the following prompt and generates learning content:

[1048] Example prompt sentence:

[1049] "Generate the best Mathematics Algebra learning content based on user learning profile ID: 12345."

[1050] In this way, optimal learning support that meets the user's learning needs in real time can be realized.

[1051] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1052] Step 1:

[1053] Users use a smartphone app to enter their learner profile. This information, such as their grade, interests, and past learning history, is sent to the server via the device. The server then stores the received profile information in a database. This saves information, such as the user being a "second-year high school student" and having interests in "math" and "English," which is then used to generate subsequent learning content.

[1054] Step 2:

[1055] The server sends a prompt to the generative AI model based on the saved learner profile to generate optimal learning content for the user. The prompt will be in the form of "Please generate optimal learning content for math algebra based on the user's learning profile ID: {ID}." The generative AI model generates learning content based on this input and returns the results to the server. The server then sends the generated content to the user's device.

[1056] Step 3:

[1057] The user uses the provided learning content to progress through their studies. The device records the user's learning progress (e.g., time to solve problems, correct / incorrect answers) in real time and sends the data to the server. The server aggregates this data and monitors the learner's progress.

[1058] Step 4:

[1059] The server analyzes the collected learning progress data. For example, it identifies that the user makes many mistakes on a particular algebra problem. The server then invokes the generative AI model again and sends a prompt saying, "Based on the user's learning progress data, please generate learning content that reinforces specific weaknesses." The model generates reinforcement learning content specific to the weaknesses and sends it to the server. The server then sends this content to the user's device.

[1060] Step 5:

[1061] The device records the results (answer data) of the user's learning as they follow the reinforcement learning content and sends that data back to the server. The server analyzes this data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends a new prompt to the generative AI model, asking it to generate more detailed additional explanations or explanations from a different approach. The generated additional explanations and explanations are sent from the server to the user's device.

[1062] Step 6:

[1063] When a user visits a physical store, they enter their learning profile through a smartphone app. Based on the profile information entered, the app recommends the most suitable study materials and reference books to purchase at the store. Based on the ID, the app retrieves recommendation information and study progress data from the server. This allows the user to select the most suitable study materials and reference books in the store.

[1064] Step 7:

[1065] The smartphone app records how the user progresses with the study materials and reference books they have purchased (e.g., study time, percentage of correct answers, etc.) and sends this data to the server. Based on this data, the server recommends supplementary materials suitable for the user. Information on the recommended supplementary materials is used the next time the user considers purchasing them in a physical store or online.

[1066] 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.

[1067] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and also combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[1068] (Collecting learner profiles)

[1069] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[1070] (learning content generation)

[1071] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[1072] (Monitoring learning progress)

[1073] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[1074] (Identifying weaknesses and suggesting reinforcement learning)

[1075] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[1076] (Evaluation of understanding and additional explanation)

[1077] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[1078] (Emotion recognition)

[1079] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.). The recognized emotion data is sent to the server in real time.

[1080] (Adjusting Emotion-Based Learning Support)

[1081] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, it can lower the difficulty of the content or add more detailed explanations. If the user is tired, it can also send a notification to the device suggesting a break.

[1082] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[1086] Step 2:

[1087] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[1088] Step 3:

[1089] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[1090] Step 4:

[1091] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[1092] Step 5:

[1093] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[1094] Step 6:

[1095] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[1096] Step 7:

[1097] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[1098] Step 8:

[1099] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[1100] Step 9:

[1101] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[1102] Step 10:

[1103] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[1104] Step 11:

[1105] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[1106] Step 12:

[1107] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[1108] Step 13:

[1109] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[1110] Step 14:

[1111] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[1112] Step 15:

[1113] The device records the user's answers. The device records the user's answers and sends them to the server.

[1114] Step 16:

[1115] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[1116] Step 17:

[1117] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[1118] Step 18:

[1119] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[1120] Step 19:

[1121] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[1122] Step 20:

[1123] The device recognizes the user's emotions. The device analyzes the user's facial expressions and voice, and the emotion engine identifies the user's emotional state. For example, the device recognizes emotions such as confusion, excitement, or fatigue.

[1124] Step 21:

[1125] The device sends emotion data to the server. The device sends the emotion data recognized by the emotion engine to the server in real time.

[1126] Step 22:

[1127] The server analyzes the emotional data and evaluates the user's current emotional state based on the received emotional data.

[1128] Step 23:

[1129] The server adjusts the learning content. The server adjusts the difficulty and content of the learning content based on the emotional data. For example, if the user is confused, the server may lower the difficulty of the content or provide additional hints.

[1130] Step 24:

[1131] The server adjusts the learning progress based on the emotion data. For example, if the user is tired, it sends a notification to the device suggesting a break.

[1132] Step 25:

[1133] The terminal displays the adjusted content. The terminal displays the adjusted learning content and break suggestions sent from the server to the user.

[1134] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[1135] Example 2

[1136] 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."

[1137] Conventional learning systems have difficulty providing optimal learning content for each learner, monitoring progress, and providing feedback based on their level of understanding. Furthermore, they are unable to recognize the learner's emotional state and adjust learning support accordingly, preventing the maximization of learning effectiveness.

[1138] 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.

[1139] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing the learner's emotional state, and means for adjusting learning support based on the recognized emotional state. This allows for an optimal learning experience for each learner, enabling efficient and effective learning.

[1140] A "learner profile" is data that includes personal information such as a learner's grade, interests, and past learning history.

[1141] "Learning content" refers to educational materials and exercises that are generated based on the learner's profile and learning progress.

[1142] "Progress monitoring" is the process of tracking and recording data (such as time to solve a problem, correct / incorrect answers, etc.) as a learner progresses through their studies.

[1143] "Identifying weaknesses" refers to analyzing a learner's learning data to identify areas where they lack understanding or make repeated mistakes.

[1144] "Reinforcement learning suggestions" refers to suggestions to provide additional learning content to complement or reinforce identified weaknesses of learners.

[1145] "Assessing comprehension" involves analyzing the problems solved by learners and their responses to determine how much they have understood.

[1146] "Additional explanation" means providing a more detailed explanation or an explanation from a different approach when the learner's understanding is insufficient.

[1147] "Recognizing emotional states" refers to detecting the learner's emotions (confusion, excitement, fatigue, etc.) from their facial expressions and voice.

[1148] "Adjusting learning support" refers to changing or adjusting learning content or learning progression methods based on the recognized emotional state of the learner.

[1149] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system provides optimal learning support for each learner, enabling efficient and effective learning.

[1150] Collecting learner profiles

[1151] Users enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, if a user enters that they are a second-year high school student and are interested in math and English, this information is recorded as their profile information.

[1152] Generating learning content

[1153] The server calls a natural language generation AI (e.g., GPT-4) based on the saved learner profile and generates optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it sends a prompt such as "Please generate a problem set that will teach me algebra from the basics" to the AI, which then generates a problem set. The generated content is then sent from the server to the device.

[1154] Monitoring learning progress

[1155] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[1156] Identifying weaknesses and suggesting reinforcement learning

[1157] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI (e.g., BERT) to generate additional content for reinforcement learning. For example, it sends a prompt such as "Please create a problem set to help improve my weakness in solving algebraic equations" to the AI, and the problem set is created. The generated reinforcement content is sent from the server to the device.

[1158] Assessment of understanding and further explanation

[1159] The device records the user's answer data and sends it to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the server uses natural language generation AI to generate additional explanations or explanations from a different approach. For example, the server sends a prompt such as "Please explain the process of solving this algebra problem step by step" to the AI ​​to generate an explanation. These additional explanations are sent from the server to the device.

[1160] Emotion recognition

[1161] The device is equipped with an emotion engine (e.g., a general emotion recognition API) that recognizes the user's emotional state from their facial expressions and voice. The emotion engine recognizes the user's emotional state during learning and sends the data to the server in real time.

[1162] Emotion-based learning support coordination

[1163] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, the server sends a prompt to the AI ​​such as, "Please provide easy algebra problems and detailed explanations for the struggling user," and generates easy problems and detailed explanations. If the user is tired, the server sends a notification to the device suggesting a break.

[1164] In this way, the system provides an optimized learning experience based on the learner's learning situation and emotional state, thereby realizing efficient and effective learning.

[1165] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1166] Step 1:

[1167] Collecting learner profiles

[1168] Input: Information such as the user's grade, interests, and past learning history

[1169] Specific behavior: Users fill out a registration form with their grade level, interests, and past learning history.

[1170] Data processing: The device receives this information and assembles it into data packets.

[1171] Output: The device sends data packets to the server, which stores the profile information in a database.

[1172] Step 2:

[1173] Generating learning content

[1174] Input: Learner profile stored in the database

[1175] Specific operation: The server analyzes the learner profile and sends a prompt to the natural language generation AI saying, "Please generate a problem set that will teach the basics of algebra in mathematics."

[1176] Data processing: Natural language generation AI (e.g., GPT-4) generates optimal learning content based on profile information.

[1177] Output: The generated learning content is sent from the server to the device.

[1178] Step 3:

[1179] Monitoring learning progress

[1180] Input: User's learning status (time to solve the problem, correct / incorrect answers, etc.)

[1181] Specific operation: The user uses the learning content received on the device to proceed with their learning. The device records their learning progress in real time.

[1182] Data processing: The device organizes the recorded data and sends it to the server.

[1183] Output: The server monitors the learning progress based on the received data and stores it in a database.

[1184] Step 4:

[1185] Identifying weaknesses and suggesting reinforcement learning

[1186] Input: Learning progress data

[1187] Specific operation: The server analyzes the learning progress data and identifies the user's weaknesses, such as "Many mistakes in solving algebraic equations." The server then sends a prompt to the natural language generation AI, saying, "Please create a problem set to help overcome the weaknesses in solving algebraic equations."

[1188] Data processing: Natural language generation AI generates content for reinforcement learning based on identified weaknesses.

[1189] Output: The generated augmentation content is sent from the server to the device.

[1190] Step 5:

[1191] Assessment of understanding and further explanation

[1192] Input: User's answer data

[1193] How it works: The device records the user's answers and sends them to the server. The server analyzes the answer data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends the AI ​​a prompt saying, "Please explain the process of solving this algebra problem step by step."

[1194] Data processing: Natural language generation AI generates detailed explanations based on prompts.

[1195] Output: The additional instructions are sent from the server to the terminal and provided to the user.

[1196] Step 6:

[1197] Emotion recognition

[1198] Input: User facial and voice data

[1199] How it works: The device's camera and microphone capture the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotional state (confusion, excitement, fatigue, etc.).

[1200] Data processing: The emotion engine analyzes and classifies emotion data.

[1201] Output: The recognized emotion data is sent to the server in real time.

[1202] Step 7:

[1203] Emotion-based learning support coordination

[1204] Input: Emotion data

[1205] Specific behavior: The server receives the emotion data and sends a prompt to the AI ​​saying, "Please provide an easy algebra problem and detailed explanation to the struggling user." If the server determines that the user is tired, it also generates a notification saying, "Take a break."

[1206] Data processing: Natural language generation AI generates optimal content based on prompts.

[1207] Output: The adjusted learning content and notifications are sent to the device and provided to the user.

[1208] These steps enable the system to provide learners with an optimal learning experience and maximize learning effectiveness.

[1209] (Application example 2)

[1210] 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."

[1211] Conventional learning support systems are unable to take into account the learner's emotional state, which can lead to reduced learning efficiency and effectiveness. It is also difficult to provide optimal content to each individual learner in real time. Furthermore, because emotional data cannot be referenced when closely monitoring learning progress or proposing effective reinforcement learning to address individual weaknesses, they are unable to respond adequately to learners. To solve these issues, a highly customized learning support system is needed.

[1212] 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 means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing emotions, and means for adjusting the learning content and learning progress method based on the recognized emotions. This makes it possible to grasp the learner's learning situation and emotional state in real time and provide individually optimized learning support.

[1213] A "learner profile" is data about an individual learner, including basic information about the learner, their interests, and past learning history.

[1214] "Learning content" refers to content such as study materials, question sets, and explanations that are generated based on the learner's profile.

[1215] "Learning progress" refers to data that shows the progress and results of a learner's learning as they use learning content.

[1216] "Reinforcement learning" refers to additional learning content or educational activities that complement learners' weaknesses and strengthen their abilities.

[1217] "Means for recognizing emotions" refers to technology that analyzes data such as the learner's facial expressions and voice to identify their emotional state at that time (for example, confusion, excitement, fatigue, etc.).

[1218] "Means for adjusting learning content and learning methods based on emotions" refers to technology that provides optimal learning content and learning methods based on the learner's emotional state based on recognized emotional data.

[1219] This invention is a system that collects learner profiles, generates learning content, monitors learning progress, identifies weaknesses and suggests supplementary learning, evaluates comprehension and provides additional explanations, and uses an emotion engine to recognize the user's emotions and provide learning support based on these. This enables optimal learning support for each learner, resulting in efficient and effective learning.

[1220] The system mainly includes the following components:

[1221] 1. Collecting learner profiles

[1222] When a user registers with the system, the terminal inputs profile information such as the user's grade, interests, and past learning history.

[1223] The collected information is sent to a server and stored in a database.

[1224] 2. Generating learning content

[1225] Based on the saved learner profile, the server calls up a natural language generation AI to generate optimal learning content for the user.

[1226] For example, if it turns out that the user is weak in algebra, a series of problem sets starting from the basics of algebra can be generated. The generated content is sent from the server to the user's terminal.

[1227] 3. Monitoring your learning progress

[1228] The user uses the learning content received on the terminal to advance their learning.

[1229] The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends the data to the server.

[1230] The server uses this data to monitor the learner's progress.

[1231] 4. Identifying weaknesses and suggesting reinforcement learning

[1232] The server analyzes the learning progress data and identifies the user's weaknesses.

[1233] Based on the identified weaknesses, natural language generation AI is again used to generate additional content for reinforcement learning.

[1234] For example, if a user makes particularly many mistakes when solving algebraic equations, a collection of exercises specific to that topic can be generated. The generated reinforcement content is then sent from the server to the device.

[1235] 5. Assessment of understanding and further explanation

[1236] The terminal records the user's answers and sends them to the server.

[1237] The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, it uses natural language generation AI to generate additional explanations or explanations from different approaches.

[1238] For example, if a user repeatedly has trouble solving a particular algebra problem, the server will provide step-by-step instructions on the process of solving the problem, including alternative solutions. Additional instructions are sent from the server to the device.

[1239] 6. Emotional Recognition

[1240] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice.

[1241] The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.) and transmits the recognized emotion data to the server in real time.

[1242] 7. Adjusting emotion-based learning support

[1243] The server adjusts the learning content and learning progress method based on the emotional data received from the emotion engine.

[1244] For example, if the user is confused, the difficulty level of the content can be reduced or more detailed explanations can be added. Also, if the user is tired, a notification can be sent to the device suggesting that they take a break.

[1245] As a specific example, consider the case where a user incorrectly answers the same algebra problem multiple times while studying it. At this time, the device recognizes the user's state of confusion and sends it to the server in real time. The server uses this information to adjust the difficulty of the content or add step-by-step explanations. The AI ​​generator then inputs a prompt such as, "If the user repeatedly fails to solve a particular algebra problem, please generate content that provides a step-by-step explanation of the solution process and suggests different solutions. The theme of the problem is 'Solution to Quadratic Equations.'" This allows the learner to progress through their studies in a more understandable way.

[1246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1247] Step 1:

[1248] When a user registers with the system, the device inputs profile information such as grade level, interests, and past learning history. This information is sent to the server to be stored in the database. Input is done by the user entering information into an input form and pressing the submit button. The input information is converted to JSON format and sent to the server as data processing. The server analyzes the received data and stores it in the database.

[1249] Step 2:

[1250] The server calls a natural language generation AI based on the saved learner profile and generates optimal learning content for the user. Profile data (e.g., algebra problems as a weak point) is input, and optimized learning content is generated based on that. Data processing involves converting the profile data into prompt sentences and inputting them into the generative AI model. The output learning content is sent to the user's device.

[1251] Step 3:

[1252] The user uses the learning content received on their device to progress through their studies. Their progress during the study (time to solve the problem, correct / incorrect answers, etc.) is recorded in real time on the device and sent to the server. The input is the result of the user's answers, and the answer data is converted to JSON format and sent to the server as data processing. The server analyzes the received data and saves the progress status in a database.

[1253] Step 4:

[1254] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses (e.g., solving algebraic equations), it again uses natural language generation AI to generate additional content for reinforcement learning. The progress data is used as input, and the results of identifying the weaknesses are converted into prompt sentences, which are then input into the generative AI model. The output reinforcement learning content is then sent to the user's device.

[1255] Step 5:

[1256] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data and generates additional explanations or explanations from different approaches as needed. The answer data is used as input, and the understanding is evaluated as a data calculation. The generative AI model is used again to generate additional explanations, and the output is sent to the user's device. As a specific example, if a user makes multiple mistakes on a specific quadratic equation problem, a step-by-step explanation is generated.

[1257] Step 6:

[1258] The device uses an emotion engine to recognize emotions from the user's facial expressions and voice. The collected emotion data is sent to the server in real time. The input is the user's facial expressions and voice data, and the emotion engine processes the data to determine the emotional state and send the resulting data to the server. Specifically, the device uses a camera to capture facial expressions and voice recognition software to analyze the voice.

[1259] Step 7:

[1260] The server adjusts the learning content and learning progress methods based on the emotional data received from the emotion engine. The emotional data is used as input, and the data is calculated to adjust optimal learning support based on the emotional state. The output is the adjusted learning content and methods, which are sent to the user's device. For example, if a state of confusion is recognized, the difficulty level of the content may be lowered or additional explanations may be provided.

[1261] In this way, the data collected at each step and the content generated are transmitted and received bidirectionally between the server and the device, providing optimized support to the learner in real time.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] [Fourth embodiment]

[1266] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1267] 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.

[1268] 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).

[1269] 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.

[1270] 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.

[1271] 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).

[1272] 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.

[1273] 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.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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."

[1279] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[1280] (Collecting learner profiles)

[1281] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[1282] (learning content generation)

[1283] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[1284] (Monitoring learning progress)

[1285] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[1286] (Identifying weaknesses and suggesting reinforcement learning)

[1287] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[1288] (Evaluation of understanding and additional explanation)

[1289] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[1290] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[1291] The processing flow will be explained below.

[1292] Step 1:

[1293] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[1294] Step 2:

[1295] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[1296] Step 3:

[1297] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[1298] Step 4:

[1299] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[1300] Step 5:

[1301] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[1302] Step 6:

[1303] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[1304] Step 7:

[1305] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[1306] Step 8:

[1307] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[1308] Step 9:

[1309] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[1310] Step 10:

[1311] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[1312] Step 11:

[1313] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[1314] Step 12:

[1315] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[1316] Step 13:

[1317] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[1318] Step 14:

[1319] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[1320] Step 15:

[1321] The device records the user's answers. The device records the user's answers and sends them to the server.

[1322] Step 16:

[1323] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[1324] Step 17:

[1325] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[1326] Step 18:

[1327] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[1328] Step 19:

[1329] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[1330] Example 1

[1331] 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."

[1332] Conventional learning support systems have difficulty providing optimal learning content based on each learner's individual characteristics and progress. They also lack a mechanism for identifying learners' weaknesses in real time and quickly suggesting appropriate reinforcement learning. This makes it difficult to improve a learner's understanding and maximize learning efficiency. Furthermore, they are also inadequate in assessing a learner's understanding based on their answers and providing corresponding additional explanations, limiting the effectiveness of learning.

[1333] 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.

[1334] In this invention, the server includes: means for collecting a learner profile by a user inputting profile information such as grade level, interests, and past learning history and transmitting it to the server via a terminal; means for generating optimal learning content based on generated prompts using a natural language generation AI model based on the collected learner profile; means for the terminal to record the user's learning status in real time and transmit learning progress data to the server, which analyzes the data to monitor the learner's learning progress; means for analyzing the learning progress data and generating additional content for reinforcement learning using a natural language generation AI model to identify the learner's weaknesses and suggest reinforcement learning; and means for the terminal to record the user's answers, the server to evaluate the user's level of understanding based on the data, and providing additional explanations using the natural language generation AI model as needed. This allows for learning support optimized for each learner, enabling efficient and effective learning.

[1335] A "learner profile" refers to a set of information about an individual learner, such as the user's grade level, interests, and past learning history.

[1336] "Terminal" refers to an electronic device with communication capabilities operated by a user, which is used to input a learning profile and access learning content.

[1337] "Server" refers to a computer system that collects, stores, and analyzes information, generates learning content, and monitors progress.

[1338] "Natural language generation AI model" refers to an artificial intelligence model that automatically generates text appropriate for a specific task based on input prompts.

[1339] A "prompt" refers to input text that provides specific instructions or questions to a natural language generation AI model.

[1340] "Learning content" refers to a series of educational materials, such as teaching materials, workbooks, and explanations, created for use by learners.

[1341] "Learning progress" refers to data that shows the progress and results of the learning content that a learner has engaged in.

[1342] "Monitoring" refers to the process of recording learning progress data in real time and tracking and managing learner progress.

[1343] "Reinforcement learning" refers to additional learning content or materials provided to identify learners' weaknesses and help them overcome them.

[1344] "Answer" refers to the answer or response that a learner submits to a question in the learning content.

[1345] "Understanding" refers to measurable indicators or assessment results that show how well a learner has understood the learning content.

[1346] "Additional explanation" refers to explanations or explanations provided in addition to existing learning content to improve a learner's understanding.

[1347] The present invention relates to a system for collecting learner profiles, generating learning content, monitoring learning progress, identifying weaknesses and suggesting supplementary learning, and evaluating comprehension and providing additional explanations. The following describes in detail the modes for implementing the present invention.

[1348] First, the user enters profile information such as grade level, interests, and past learning history. The user enters this information using an input form on the device and presses the submit button. The device encrypts this information using the HTTPS protocol and securely sends it to the server. The server then inserts the received information into the database using an SQL query to store it.

[1349] Next, the server generates optimal learning content for the user based on the saved learner profile using the natural language generation AI model "OpenAI GPT-4." The server analyzes the profile information and sends a prompt to the AI ​​model. An example of a specific prompt is, "Please generate an assignment for a high school sophomore who is weak in algebra." The AI ​​model receives this prompt, generates appropriate learning content, and sends it back to the server. The server parses the generated content in JSON format and sends it to the user's device.

[1350] Users use the learning content received on their device to progress with their studies. They solve problems and enter their answers into the device. At this time, the device records the user's learning status in real time, specifically data such as the time it takes to solve the problems and whether the answers were correct or incorrect, and periodically sends this data to the server. The server analyzes this data and monitors the user's learning progress. Machine learning algorithms are used for accurate data analysis.

[1351] By analyzing the learning progress data, the server identifies the user's weaknesses. For example, if the user repeatedly makes a specific mistake when solving algebraic equations, the server uses that information to send another prompt to the AI ​​model. A specific prompt such as "Please generate reinforcement problems for users who make many mistakes when solving algebraic equations" is used. The AI ​​model generates additional reinforcement learning content and sends it back to the server. The server then sends the generated content to the user's device.

[1352] Finally, when the user works through the reinforcement learning content and enters the answers into the device, the device sends the answer data to the server. The server uses this data to evaluate the user's level of understanding. If the user's level of understanding is determined to be low, the server again uses the AI ​​model to generate additional explanations or explanations from a different approach and sends them to the device. For example, the server could send a prompt such as, "For users who repeatedly have trouble solving a particular algebra problem, please provide a step-by-step explanation of the answer."

[1353] In this way, a learning experience optimized for each learner is provided, resulting in efficient and effective learning.

[1354] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1355] Step 1:

[1356] The user enters profile information such as grade level, interests, and past learning history.

[1357] Specifically, the user enters the necessary information into the input form on the terminal and clicks the send button.

[1358] Input: Grade, interests, past learning history

[1359] Output: Profile information entered into the terminal

[1360] Step 2:

[1361] The device sends the profile information to the server.

[1362] The device uses the HTTPS protocol to encrypt data and send it securely to the server.

[1363] Input: Profile information entered on the device

[1364] Output: Profile information sent to the server

[1365] Step 3:

[1366] The server stores the profile information in a database.

[1367] Specifically, the server inserts the received profile information into a database using an SQL query.

[1368] Input: Profile information sent to the server

[1369] Output: Profile information stored in the database

[1370] Step 4:

[1371] The server calls the AI ​​model based on the profile information and generates learning content.

[1372] The server analyzes the stored profile information and sends prompts to the generative AI model, such as "Please generate an assignment for a high school sophomore who is weak in algebra."

[1373] Input: Profile information stored in the database

[1374] Output: Prompts to send to the generative AI model and generated learning content

[1375] Step 5:

[1376] The server transmits the generated learning content to the user's terminal.

[1377] The server parses the generated content in JSON format and sends it to the user's device.

[1378] Input: Generated learning content

[1379] Output: Learning content sent to the user's device

[1380] Step 6:

[1381] Users can use the learning content on their devices to progress with their studies.

[1382] Specifically, the user solves the problem displayed on the terminal and inputs the answer.

[1383] Input: Learning content sent to your device

[1384] Output: User's answer

[1385] Step 7:

[1386] The terminal records the user's learning status and sends it to the server.

[1387] The device records data such as the time it takes to solve the questions and whether the answers were correct or incorrect in real time, and periodically transmits this data to the server.

[1388] Input: User answers, learning status data

[1389] Output: Learning status data sent to the server

[1390] Step 8:

[1391] The server analyzes the learning progress data and monitors the learner's progress.

[1392] Specifically, the server analyzes the received data and uses machine learning algorithms to evaluate the learner's performance and trends.

[1393] Input: Learning status data sent to the server

[1394] Output: Parsed learning progress data, learner progress

[1395] Step 9:

[1396] The server identifies weaknesses based on learning progress data and generates additional content for reinforcement learning.

[1397] The server then prompts the AI ​​model again based on the identified weaknesses, using a specific prompt such as "Generate reinforcement problems for users who make a lot of mistakes solving algebra equations."

[1398] Input: Parsed learning progress data, generated prompts

[1399] Output: Generated reinforcement learning content

[1400] Step 10:

[1401] The server transmits the generated augmented content to the terminal.

[1402] The server parses the additional content in JSON format and sends it to the user's device.

[1403] Input: Generated reinforcement learning content

[1404] Output: Reinforcement learning content sent to the user's device

[1405] Step 11:

[1406] The user uses the reinforcement learning content and inputs the answers into the terminal.

[1407] In concrete terms, the user solves the additional problem and inputs the answer into the terminal.

[1408] Input: Reinforcement learning content sent to the device

[1409] Output: Additional answers provided by the user

[1410] Step 12:

[1411] The terminal records the user's answers and sends them to the server.

[1412] The device records the answer data in real time and transmits it to the server.

[1413] Input: Additional answers provided by the user

[1414] Output: Additional answer data sent to the server

[1415] Step 13:

[1416] The server evaluates the level of understanding based on the answer data and provides additional explanations if necessary.

[1417] The server analyzes the answer data and, if it determines that the level of understanding is low, sends another prompt to the AI ​​model, specifically, using the prompt sentence, "Please provide a step-by-step explanation of the solution for users who have been unable to solve a particular algebra problem multiple times."

[1418] Input: Additional answer data sent to the server, generated prompt text

[1419] Output: Generated additional description

[1420] Step 14:

[1421] The server sends the generated additional description to the terminal.

[1422] The server parses the additional explanation in JSON format and sends it to the user's device.

[1423] Input: Generated additional description

[1424] Output: Additional instructions sent to the user's terminal

[1425] In this way, by explaining the process steps, the specific operation of the system and its flow can be clarified.

[1426] (Application example 1)

[1427] 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."

[1428] Today's learners have diverse learning needs and progress levels, making it difficult to select optimal learning materials and manage their progress. In particular, when receiving learning support in a brick-and-mortar store, it is difficult to receive appropriate advice and learning material recommendations in real time. There is a need to solve this problem and provide learning support optimized for each user's learning needs.

[1429] 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.

[1430] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting supplementary learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for a user to input their own learning profile in a physical store and be provided with advice and materials for purchasing on the spot, means for recording the user's progress in learning using the learning materials and reference books they have purchased, and means for recommending supplementary learning materials available for purchase in the store based on the user's learning progress. This makes it possible to select optimal learning materials for individual learners and provide learning support in real time, even in a store environment.

[1431] "Learner profile" refers to the learner's individual attribute information, such as the user's grade, interests, and past learning history.

[1432] "Means of collection" refers to the methods and technologies used to obtain information provided by users and send it to a server.

[1433] "Learning content" refers to problem sets, teaching materials, explanatory materials, etc. provided for learning.

[1434] "Means of generation" refers to the technology and methods for creating optimal learning content based on collected learner profiles.

[1435] "Monitoring means" refers to methods and technologies that track and record learners' learning progress in real time.

[1436] A "weakness" refers to an area where a learner has insufficient understanding or answers correctly in a particular learning item.

[1437] "Reinforcement learning" refers to additional learning content or training provided to learners to overcome weaknesses.

[1438] "Suggestion methods" refer to techniques and methods for presenting appropriate reinforcement learning based on the learner's weaknesses.

[1439] "Answers and responses" refers to the answers given by learners to the learning content and the evaluation results.

[1440] "Comprehension" refers to the degree to which a learner understands the learning content provided.

[1441] "Means for providing additional explanations" refers to techniques and methods for generating and providing additional explanations when a learner's level of comprehension is low.

[1442] "Brick and mortar store" refers to an educational equipment store, bookstore, or other store that operates from a physical location.

[1443] "Advice" refers to advice that recommends optimal learning materials and methods based on the learner's profile.

[1444] "Materials for considering a purchase" refers to information and recommendations that learners can refer to when considering a purchase in a store.

[1445] "Means for recording the situation" refers to techniques and methods for recording how learners progress with the purchased learning materials.

[1446] "Supplementary materials" refers to additional materials provided at the store to reinforce a learner's weak areas.

[1447] "Recommendation means" refers to the technology or method for selecting and presenting the most appropriate supplementary learning materials based on learning progress data.

[1448] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, and evaluates comprehension and provides additional explanations. Using this system, it is possible to provide learning support optimized for each learner, even in physical stores.

[1449] Collecting learner profiles

[1450] Users use a smartphone app to enter their learner profile. The profile includes the learner's grade, interests, past learning history, etc. This information is sent from the device to the server and stored in a database. For example, a user may enter that they are a "second-year high school student" and are interested in "math" and "English."

[1451] Generating learning content

[1452] The server uses a generative AI model to generate optimal learning content for the user based on the saved learner profile. For example, if the user is weak in algebra, the server generates a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[1453] Monitoring learning progress

[1454] Users study using purchased learning materials and reference books. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[1455] Identifying weaknesses and suggesting reinforcement learning

[1456] The server analyzes the learning progress data to identify the user's weaknesses. Based on the identified weaknesses, the server uses a generative AI model to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes in solving algebraic equations, the server can generate a set of problems specific to that topic and send it to the device.

[1457] Assessment of understanding and further explanation

[1458] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the generative AI model is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the server will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[1459] Use in physical stores

[1460] Users visit a physical store and enter their learning profile through a smartphone app. The app then recommends optimal learning materials and reference books based on the profile information entered. The app also records how the user progresses with the materials they have purchased and sends this information to the server. This allows the app to recommend supplementary materials that can be purchased at the store.

[1461] Specific examples

[1462] For example, suppose a user is a second-year high school student and has an interest in mathematics and English, and has purchased a book on basic algebra. In this case, the generative AI model receives the following prompt and generates learning content:

[1463] Example prompt sentence:

[1464] "Generate the best Mathematics Algebra learning content based on user learning profile ID: 12345."

[1465] In this way, optimal learning support that meets the user's learning needs in real time can be realized.

[1466] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1467] Step 1:

[1468] Users use a smartphone app to enter their learner profile. This information, such as their grade, interests, and past learning history, is sent to the server via the device. The server then stores the received profile information in a database. This saves information, such as the user being a "second-year high school student" and having interests in "math" and "English," which is then used to generate subsequent learning content.

[1469] Step 2:

[1470] The server sends a prompt to the generative AI model based on the saved learner profile to generate optimal learning content for the user. The prompt will be in the form of "Please generate optimal learning content for math algebra based on the user's learning profile ID: {ID}." The generative AI model generates learning content based on this input and returns the results to the server. The server then sends the generated content to the user's device.

[1471] Step 3:

[1472] The user uses the provided learning content to progress through their studies. The device records the user's learning progress (e.g., time to solve problems, correct / incorrect answers) in real time and sends the data to the server. The server aggregates this data and monitors the learner's progress.

[1473] Step 4:

[1474] The server analyzes the collected learning progress data. For example, it identifies that the user makes many mistakes on a particular algebra problem. The server then invokes the generative AI model again and sends a prompt saying, "Based on the user's learning progress data, please generate learning content that reinforces specific weaknesses." The model generates reinforcement learning content specific to the weaknesses and sends it to the server. The server then sends this content to the user's device.

[1475] Step 5:

[1476] The device records the results (answer data) of the user's learning as they follow the reinforcement learning content and sends that data back to the server. The server analyzes this data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends a new prompt to the generative AI model, asking it to generate more detailed additional explanations or explanations from a different approach. The generated additional explanations and explanations are sent from the server to the user's device.

[1477] Step 6:

[1478] When a user visits a physical store, they enter their learning profile through a smartphone app. Based on the profile information entered, the app recommends the most suitable study materials and reference books to purchase at the store. Based on the ID, the app retrieves recommendation information and study progress data from the server. This allows the user to select the most suitable study materials and reference books in the store.

[1479] Step 7:

[1480] The smartphone app records how the user progresses with the study materials and reference books they have purchased (e.g., study time, percentage of correct answers, etc.) and sends this data to the server. Based on this data, the server recommends supplementary materials suitable for the user. Information on the recommended supplementary materials is used the next time the user considers purchasing them in a physical store or online.

[1481] 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.

[1482] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and also combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system enables optimal learning support for each learner, resulting in efficient and effective learning.

[1483] (Collecting learner profiles)

[1484] When a user registers with the system, they enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, a user may enter that they are a second-year high school student and are interested in mathematics and English.

[1485] (learning content generation)

[1486] The server then calls up a natural language generation AI based on the saved learner profile to generate optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it will generate a series of problem sets starting from the basics of algebra. The generated content is then sent from the server to the user's device.

[1487] (Monitoring learning progress)

[1488] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[1489] (Identifying weaknesses and suggesting reinforcement learning)

[1490] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI to generate additional content for reinforcement learning. For example, if the user makes particularly many mistakes when solving algebraic equations, it will generate a problem set specific to that topic. The generated reinforcement content is sent from the server to the device.

[1491] (Evaluation of understanding and additional explanation)

[1492] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, natural language generation AI is used to generate additional explanations or explanations from different approaches. For example, if a user repeatedly fails to solve a particular algebra problem, the system will explain the solution process step by step and introduce different solutions. The additional explanations are sent from the server to the device.

[1493] (Emotion recognition)

[1494] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.). The recognized emotion data is sent to the server in real time.

[1495] (Adjusting Emotion-Based Learning Support)

[1496] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, it can lower the difficulty of the content or add more detailed explanations. If the user is tired, it can also send a notification to the device suggesting a break.

[1497] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[1498] The processing flow will be explained below.

[1499] Step 1:

[1500] The user registers for study. The user logs in to the system and enters their study profile (grade, interests, past study history, etc.). For example, the user registers that they are a second-year high school student and are interested in mathematics and English.

[1501] Step 2:

[1502] The terminal transmits the data to the server. The terminal transmits the profile data entered by the user to the server.

[1503] Step 3:

[1504] The server stores the profile. The server stores the user's profile in a database and makes it available for future learning content generation.

[1505] Step 4:

[1506] The server analyzes the learning data. Based on the user's profile data, the server analyzes which areas and topics to focus on. For example, it may reveal that the user is weak in algebra.

[1507] Step 5:

[1508] The server calls the natural language generation AI, which then sends a request to generate optimal learning content for the user.

[1509] Step 6:

[1510] Natural language generation AI generates content. Based on the user's request, the AI ​​generates learning materials and problems that match the user's level of understanding. For example, it generates a series of problem sets starting from the basics of algebra.

[1511] Step 7:

[1512] The server transmits the generated content to the terminal. The server transmits the generated learning content to the user's terminal.

[1513] Step 8:

[1514] The user uses the learning content. The user uses the learning content received on the device to progress with their studies.

[1515] Step 9:

[1516] The device records the user's learning progress. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time.

[1517] Step 10:

[1518] The device transmits the progress data to the server. The device periodically transmits the learning progress data to the server.

[1519] Step 11:

[1520] The server analyzes the progress data received, particularly identifying the user's weaknesses and areas of difficulty.

[1521] Step 12:

[1522] The server plans reinforcement learning and sends requests to the natural language generation AI to generate additional questions and explanations based on the identified weaknesses.

[1523] Step 13:

[1524] Natural language generation AI generates supplementary content. Natural language generation AI generates content for reinforcement learning. For example, if a user makes particularly many mistakes when solving algebraic equations, it will generate a set of problems specific to that topic.

[1525] Step 14:

[1526] The server transmits the augmented content to the terminal. The server transmits the generated augmented content to the user's terminal.

[1527] Step 15:

[1528] The device records the user's answers. The device records the user's answers and sends them to the server.

[1529] Step 16:

[1530] The server evaluates the user's level of understanding. The server evaluates the user's level of understanding based on the received answer data.

[1531] Step 17:

[1532] The server plans additional explanations. If the level of understanding is low, the AI ​​sends a request to generate additional explanations or explanations from different perspectives.

[1533] Step 18:

[1534] Natural language generation AI generates additional explanations. Natural language generation AI generates explanations that provide detailed explanations or alternative approaches. For example, if a user repeatedly fails to solve a particular algebra problem, it will explain the process of solving the problem step by step and suggest alternative solutions.

[1535] Step 19:

[1536] The server transmits the additional explanation to the terminal. The server transmits the generated additional explanation to the user's terminal.

[1537] Step 20:

[1538] The device recognizes the user's emotions. The device analyzes the user's facial expressions and voice, and the emotion engine identifies the user's emotional state. For example, the device recognizes emotions such as confusion, excitement, or fatigue.

[1539] Step 21:

[1540] The device sends emotion data to the server. The device sends the emotion data recognized by the emotion engine to the server in real time.

[1541] Step 22:

[1542] The server analyzes the emotional data and evaluates the user's current emotional state based on the received emotional data.

[1543] Step 23:

[1544] The server adjusts the learning content. The server adjusts the difficulty and content of the learning content based on the emotional data. For example, if the user is confused, the server may lower the difficulty of the content or provide additional hints.

[1545] Step 24:

[1546] The server adjusts the learning progress based on the emotion data. For example, if the user is tired, it sends a notification to the device suggesting a break.

[1547] Step 25:

[1548] The terminal displays the adjusted content. The terminal displays the adjusted learning content and break suggestions sent from the server to the user.

[1549] In this way, a learning experience optimized based on the learner's learning situation and emotional state is provided, resulting in efficient and effective learning.

[1550] Example 2

[1551] 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."

[1552] Conventional learning systems have difficulty providing optimal learning content for each learner, monitoring progress, and providing feedback based on their level of understanding. Furthermore, they are unable to recognize the learner's emotional state and adjust learning support accordingly, preventing the maximization of learning effectiveness.

[1553] 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.

[1554] In this invention, the server includes means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing the learner's emotional state, and means for adjusting learning support based on the recognized emotional state. This allows for an optimal learning experience for each learner, enabling efficient and effective learning.

[1555] A "learner profile" is data that includes personal information such as a learner's grade, interests, and past learning history.

[1556] "Learning content" refers to educational materials and exercises that are generated based on the learner's profile and learning progress.

[1557] "Progress monitoring" is the process of tracking and recording data (such as time to solve a problem, correct / incorrect answers, etc.) as a learner progresses through their studies.

[1558] "Identifying weaknesses" refers to analyzing a learner's learning data to identify areas where they lack understanding or make repeated mistakes.

[1559] "Reinforcement learning suggestions" refers to suggestions to provide additional learning content to complement or reinforce identified weaknesses of learners.

[1560] "Assessing comprehension" involves analyzing the problems solved by learners and their responses to determine how much they have understood.

[1561] "Additional explanation" means providing a more detailed explanation or an explanation from a different approach when the learner's understanding is insufficient.

[1562] "Recognizing emotional states" refers to detecting the learner's emotions (confusion, excitement, fatigue, etc.) from their facial expressions and voice.

[1563] "Adjusting learning support" refers to changing or adjusting learning content or learning progression methods based on the recognized emotional state of the learner.

[1564] This invention relates to a system that collects learner profiles, generates learning content, monitors learning progress, identifies weak points and suggests supplementary learning, evaluates comprehension and provides additional explanations, and combines an emotion engine to recognize the user's emotions and provide learning support based on those emotions. This system provides optimal learning support for each learner, enabling efficient and effective learning.

[1565] Collecting learner profiles

[1566] Users enter profile information such as their grade, interests, and past learning history. The device sends this information to the server, which stores it in a database. For example, if a user enters that they are a second-year high school student and are interested in math and English, this information is recorded as their profile information.

[1567] Generating learning content

[1568] The server calls a natural language generation AI (e.g., GPT-4) based on the saved learner profile and generates optimal learning content for the user. For example, if it is determined that the user is weak in algebra, it sends a prompt such as "Please generate a problem set that will teach me algebra from the basics" to the AI, which then generates a problem set. The generated content is then sent from the server to the device.

[1569] Monitoring learning progress

[1570] The user uses the learning content received on the device to progress with their studies. The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends this data to the server. The server uses this data to monitor the learner's progress.

[1571] Identifying weaknesses and suggesting reinforcement learning

[1572] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses, it again uses natural language generation AI (e.g., BERT) to generate additional content for reinforcement learning. For example, it sends a prompt such as "Please create a problem set to help improve my weakness in solving algebraic equations" to the AI, and the problem set is created. The generated reinforcement content is sent from the server to the device.

[1573] Assessment of understanding and further explanation

[1574] The device records the user's answer data and sends it to the server. The server evaluates the user's level of understanding based on the answer data. If the user's level of understanding is determined to be low, the server uses natural language generation AI to generate additional explanations or explanations from a different approach. For example, the server sends a prompt such as "Please explain the process of solving this algebra problem step by step" to the AI ​​to generate an explanation. These additional explanations are sent from the server to the device.

[1575] Emotion recognition

[1576] The device is equipped with an emotion engine (e.g., a general emotion recognition API) that recognizes the user's emotional state from their facial expressions and voice. The emotion engine recognizes the user's emotional state during learning and sends the data to the server in real time.

[1577] Emotion-based learning support coordination

[1578] The server adjusts the learning content and learning progress based on the emotional data received from the emotion engine. For example, if the user is confused, the server sends a prompt to the AI ​​such as, "Please provide easy algebra problems and detailed explanations for the struggling user," and generates easy problems and detailed explanations. If the user is tired, the server sends a notification to the device suggesting a break.

[1579] In this way, the system provides an optimized learning experience based on the learner's learning situation and emotional state, thereby realizing efficient and effective learning.

[1580] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1581] Step 1:

[1582] Collecting learner profiles

[1583] Input: Information such as the user's grade, interests, and past learning history

[1584] Specific behavior: Users fill out a registration form with their grade level, interests, and past learning history.

[1585] Data processing: The device receives this information and assembles it into data packets.

[1586] Output: The device sends data packets to the server, which stores the profile information in a database.

[1587] Step 2:

[1588] Generating learning content

[1589] Input: Learner profile stored in the database

[1590] Specific operation: The server analyzes the learner profile and sends a prompt to the natural language generation AI saying, "Please generate a problem set that will teach the basics of algebra in mathematics."

[1591] Data processing: Natural language generation AI (e.g., GPT-4) generates optimal learning content based on profile information.

[1592] Output: The generated learning content is sent from the server to the device.

[1593] Step 3:

[1594] Monitoring learning progress

[1595] Input: User's learning status (time to solve the problem, correct / incorrect answers, etc.)

[1596] Specific operation: The user uses the learning content received on the device to proceed with their learning. The device records their learning progress in real time.

[1597] Data processing: The device organizes the recorded data and sends it to the server.

[1598] Output: The server monitors the learning progress based on the received data and stores it in a database.

[1599] Step 4:

[1600] Identifying weaknesses and suggesting reinforcement learning

[1601] Input: Learning progress data

[1602] Specific operation: The server analyzes the learning progress data and identifies the user's weaknesses, such as "Many mistakes in solving algebraic equations." The server then sends a prompt to the natural language generation AI, saying, "Please create a problem set to help overcome the weaknesses in solving algebraic equations."

[1603] Data processing: Natural language generation AI generates content for reinforcement learning based on identified weaknesses.

[1604] Output: The generated augmentation content is sent from the server to the device.

[1605] Step 5:

[1606] Assessment of understanding and further explanation

[1607] Input: User's answer data

[1608] How it works: The device records the user's answers and sends them to the server. The server analyzes the answer data and evaluates the user's level of understanding. If the level of understanding is determined to be low, the server sends the AI ​​a prompt saying, "Please explain the process of solving this algebra problem step by step."

[1609] Data processing: Natural language generation AI generates detailed explanations based on prompts.

[1610] Output: The additional instructions are sent from the server to the terminal and provided to the user.

[1611] Step 6:

[1612] Emotion recognition

[1613] Input: User facial and voice data

[1614] How it works: The device's camera and microphone capture the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotional state (confusion, excitement, fatigue, etc.).

[1615] Data processing: The emotion engine analyzes and classifies emotion data.

[1616] Output: The recognized emotion data is sent to the server in real time.

[1617] Step 7:

[1618] Emotion-based learning support coordination

[1619] Input: Emotion data

[1620] Specific behavior: The server receives the emotion data and sends a prompt to the AI ​​saying, "Please provide an easy algebra problem and detailed explanation to the struggling user." If the server determines that the user is tired, it also generates a notification saying, "Take a break."

[1621] Data processing: Natural language generation AI generates optimal content based on prompts.

[1622] Output: The adjusted learning content and notifications are sent to the device and provided to the user.

[1623] These steps enable the system to provide learners with an optimal learning experience and maximize learning effectiveness.

[1624] (Application example 2)

[1625] 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."

[1626] Conventional learning support systems are unable to take into account the learner's emotional state, which can lead to reduced learning efficiency and effectiveness. It is also difficult to provide optimal content to each individual learner in real time. Furthermore, because emotional data cannot be referenced when closely monitoring learning progress or proposing effective reinforcement learning to address individual weaknesses, they are unable to respond adequately to learners. To solve these issues, a highly customized learning support system is needed.

[1627] 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 means for collecting learner profiles, means for generating learning content based on the collected learner profiles, means for monitoring the learner's learning progress, means for identifying the learner's weaknesses based on the learning progress and suggesting reinforcement learning, means for analyzing the learner's answers and responses to evaluate the learner's level of understanding and providing additional explanations as needed, means for recognizing emotions, and means for adjusting the learning content and learning progress method based on the recognized emotions. This makes it possible to grasp the learner's learning situation and emotional state in real time and provide individually optimized learning support.

[1628] A "learner profile" is data about an individual learner, including basic information about the learner, their interests, and past learning history.

[1629] "Learning content" refers to content such as study materials, question sets, and explanations that are generated based on the learner's profile.

[1630] "Learning progress" refers to data that shows the progress and results of a learner's learning as they use learning content.

[1631] "Reinforcement learning" refers to additional learning content or educational activities that complement learners' weaknesses and strengthen their abilities.

[1632] "Means for recognizing emotions" refers to technology that analyzes data such as the learner's facial expressions and voice to identify their emotional state at that time (for example, confusion, excitement, fatigue, etc.).

[1633] "Means for adjusting learning content and learning methods based on emotions" refers to technology that provides optimal learning content and learning methods based on the learner's emotional state based on recognized emotional data.

[1634] This invention is a system that collects learner profiles, generates learning content, monitors learning progress, identifies weaknesses and suggests supplementary learning, evaluates comprehension and provides additional explanations, and uses an emotion engine to recognize the user's emotions and provide learning support based on these. This enables optimal learning support for each learner, resulting in efficient and effective learning.

[1635] The system mainly includes the following components:

[1636] 1. Collecting learner profiles

[1637] When a user registers with the system, the terminal inputs profile information such as the user's grade, interests, and past learning history.

[1638] The collected information is sent to a server and stored in a database.

[1639] 2. Generating learning content

[1640] Based on the saved learner profile, the server calls up a natural language generation AI to generate optimal learning content for the user.

[1641] For example, if it turns out that the user is weak in algebra, a series of problem sets starting from the basics of algebra can be generated. The generated content is sent from the server to the user's terminal.

[1642] 3. Monitoring your learning progress

[1643] The user uses the learning content received on the terminal to advance their learning.

[1644] The device records the user's learning status (time to solve problems, correct / incorrect answers, etc.) in real time and sends the data to the server.

[1645] The server uses this data to monitor the learner's progress.

[1646] 4. Identifying weaknesses and suggesting reinforcement learning

[1647] The server analyzes the learning progress data and identifies the user's weaknesses.

[1648] Based on the identified weaknesses, natural language generation AI is again used to generate additional content for reinforcement learning.

[1649] For example, if a user makes particularly many mistakes when solving algebraic equations, a collection of exercises specific to that topic can be generated. The generated reinforcement content is then sent from the server to the device.

[1650] 5. Assessment of understanding and further explanation

[1651] The terminal records the user's answers and sends them to the server.

[1652] The server evaluates the user's level of understanding based on the answer data. If the level of understanding is determined to be low, it uses natural language generation AI to generate additional explanations or explanations from different approaches.

[1653] For example, if a user repeatedly has trouble solving a particular algebra problem, the server will provide step-by-step instructions on the process of solving the problem, including alternative solutions. Additional instructions are sent from the server to the device.

[1654] 6. Emotional Recognition

[1655] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice.

[1656] The emotion engine recognizes the user's emotional state during learning (e.g., confusion, excitement, fatigue, etc.) and transmits the recognized emotion data to the server in real time.

[1657] 7. Adjusting emotion-based learning support

[1658] The server adjusts the learning content and learning progress method based on the emotional data received from the emotion engine.

[1659] For example, if the user is confused, the difficulty level of the content can be reduced or more detailed explanations can be added. Also, if the user is tired, a notification can be sent to the device suggesting that they take a break.

[1660] As a specific example, consider the case where a user incorrectly answers the same algebra problem multiple times while studying it. At this time, the device recognizes the user's state of confusion and sends it to the server in real time. The server uses this information to adjust the difficulty of the content or add step-by-step explanations. The AI ​​generator then inputs a prompt such as, "If the user repeatedly fails to solve a particular algebra problem, please generate content that provides a step-by-step explanation of the solution process and suggests different solutions. The theme of the problem is 'Solution to Quadratic Equations.'" This allows the learner to progress through their studies in a more understandable way.

[1661] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1662] Step 1:

[1663] When a user registers with the system, the device inputs profile information such as grade level, interests, and past learning history. This information is sent to the server to be stored in the database. Input is done by the user entering information into an input form and pressing the submit button. The input information is converted to JSON format and sent to the server as data processing. The server analyzes the received data and stores it in the database.

[1664] Step 2:

[1665] The server calls a natural language generation AI based on the saved learner profile and generates optimal learning content for the user. Profile data (e.g., algebra problems as a weak point) is input, and optimized learning content is generated based on that. Data processing involves converting the profile data into prompt sentences and inputting them into the generative AI model. The output learning content is sent to the user's device.

[1666] Step 3:

[1667] The user uses the learning content received on their device to progress through their studies. Their progress during the study (time to solve the problem, correct / incorrect answers, etc.) is recorded in real time on the device and sent to the server. The input is the result of the user's answers, and the answer data is converted to JSON format and sent to the server as data processing. The server analyzes the received data and saves the progress status in a database.

[1668] Step 4:

[1669] The server analyzes the learning progress data and identifies the user's weaknesses. Based on the identified weaknesses (e.g., solving algebraic equations), it again uses natural language generation AI to generate additional content for reinforcement learning. The progress data is used as input, and the results of identifying the weaknesses are converted into prompt sentences, which are then input into the generative AI model. The output reinforcement learning content is then sent to the user's device.

[1670] Step 5:

[1671] The device records the user's answers and sends them to the server. The server evaluates the user's level of understanding based on the answer data and generates additional explanations or explanations from different approaches as needed. The answer data is used as input, and the understanding is evaluated as a data calculation. The generative AI model is used again to generate additional explanations, and the output is sent to the user's device. As a specific example, if a user makes multiple mistakes on a specific quadratic equation problem, a step-by-step explanation is generated.

[1672] Step 6:

[1673] The device uses an emotion engine to recognize emotions from the user's facial expressions and voice. The collected emotion data is sent to the server in real time. The input is the user's facial expressions and voice data, and the emotion engine processes the data to determine the emotional state and send the resulting data to the server. Specifically, the device uses a camera to capture facial expressions and voice recognition software to analyze the voice.

[1674] Step 7:

[1675] The server adjusts the learning content and learning progress methods based on the emotional data received from the emotion engine. The emotional data is used as input, and the data is calculated to adjust optimal learning support based on the emotional state. The output is the adjusted learning content and methods, which are sent to the user's device. For example, if a state of confusion is recognized, the difficulty level of the content may be lowered or additional explanations may be provided.

[1676] In this way, the data collected at each step and the content generated are transmitted and received bidirectionally between the server and the device, providing optimized support to the learner in real time.

[1677] 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.

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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.

[1683] 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).

[1684] 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.

[1685] 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."

[1686] 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.

[1687] 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).

[1688] 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.

[1689] 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.

[1690] 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.

[1691] 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.

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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. ...

Claims

1. a means for collecting learner profiles; means for generating learning content based on the collected learner profile; a means of monitoring learners' learning progress; A means for identifying weaknesses of learners based on their learning progress and suggesting reinforcement learning; A means of analysing learners' answers and responses to assess their understanding and provide additional explanations where necessary; A system including:

2. The system of claim 1 further comprising means for analyzing a learner profile to identify learner interests.

3. The system of claim 1 further comprising means for collecting learner progress data in real time.

Images