system

Abstract

We provide the system. [Solution] A means of receiving input information from the user, Means for using a generative model that generates a personalized response based on the input information, A means for transmitting the generated response to the user's device and displaying it, A display means that provides an interactive learning experience in a virtual space, A tracking system to record learning progress and reflect it in future learning support, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current education system, there are problems that the burden on teachers is large and it is difficult to provide individualized learning experiences for learners. Also, with the increasing demand for online learning, a system for promoting learning flexibly and efficiently is required, but the current systems do not meet this demand sufficiently. In such a situation, a method that can meet the individual needs of each learner and reduce the burden on teachers is needed.

Means for Solving the Problems

[0005] This invention provides a system that uses a generative model to receive input information from a user and generate personalized responses based on that input information. The system quickly provides the user with appropriate learning information by transmitting and displaying the generated responses on the user's device. Furthermore, the generative model has the function of generating relevant learning materials and practice problems based on the user's selected subjects and past learning history. It also promotes a personalized learning experience by creating a learning plan according to the user's learning goals and learning period. In this way, it is possible to reduce the burden on teachers and to advance learning efficiently.

[0006] "User" refers to an individual who uses the system to receive educational services.

[0007] "Input information" refers to information that users provide to the system, including data related to learning needs and goals.

[0008] A "generative model" refers to an algorithm that includes artificial intelligence technology that automatically generates personalized responses and training materials based on input information.

[0009] "Response" refers to information and results generated by a generative model, including answers to user questions and suggestions for learning materials.

[0010] "User device" refers to devices such as terminals and computers that users use to access the system.

[0011] "Learning materials" refer to educational content provided to support users' learning, and include textbooks, workbooks, video materials, and other similar materials.

[0012] "Practice problems" refer to problems that users can use to check their understanding and improve their skills.

[0013] A "learning plan" refers to a learning schedule or progress plan created based on the user's learning goals and timeframe. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is implemented as a system that provides personalized educational support using a generative AI model. This system primarily consists of a server, terminals, and users. The respective roles are detailed below.

[0036] First, the user enters learning-related information into the terminal. This information includes, for example, the subject they want to study, their current learning status, and their goals. This information is then sent to the server via the terminal.

[0037] The server uses a generative AI model to generate responses tailored to the user based on the received input information. The generative AI model employs natural language processing techniques to analyze user requests and generate the most appropriate learning materials and answers. Furthermore, the server can also generate relevant practice problems based on the user's past learning data and selected subjects. This allows users to receive learning materials that meet their individual needs.

[0038] Next, the server sends the generated responses and learning materials to the terminal, which then displays them to the user. The user can then proceed with their learning based on the displayed information. The system can also record the user's learning progress and use this information to improve future learning support.

[0039] For example, if a user wants to efficiently learn differential equations, they input their study plan and current level of understanding using their device. The server then generates introductory materials and practice problems tailored to the user's needs and sends them to the user's device. In this way, learners can progress through their studies using materials that match their level of understanding.

[0040] Thus, in the embodiments of the present invention, a flexible and individualized learning experience that meets the needs of learners can be provided, and the burden on teachers can be reduced.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Users log in to the learning platform and enter the subjects or topics they wish to study into their device. During this process, users also provide information about their current learning status and goals.

[0044] Step 2:

[0045] The terminal sends user input information to the server. This process uses a secure and reliable communication protocol.

[0046] Step 3:

[0047] The server analyzes the received user information and passes it to the generative AI model. The generative AI model understands the user's intent and generates responses tailored to their individual learning needs.

[0048] Step 4:

[0049] The server selects or generates relevant learning materials and practice problems based on the responses created by the generation AI model. Here, content is selected according to the user's past learning history and interests.

[0050] Step 5:

[0051] The server sends the generated learning content to the terminal. The transmitted information is structured in a format that is easily understandable to the user.

[0052] Step 6:

[0053] The device displays received learning materials and responses to the user. The user can review the provided information and ask further questions as needed.

[0054] Step 7:

[0055] As the user progresses through their learning, the device records their progress and periodically sends it to the server. This data is stored on the server to help support future learning sessions.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] In educational settings, there is a need to provide individualized learning support tailored to each learner's level and goals, and to create an efficient learning environment. However, existing systems fail to adequately address the diverse needs of learners, making it difficult to reduce the burden on teachers. Therefore, there is a need for a flexible system that automatically generates and presents appropriate learning materials and practice problems based on learner input.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for receiving information from users, means for transmitting said information to a computing device via a communication device, and means for using a generative model to generate optimal answers and learning materials based on said information using natural language processing technology. This makes it possible to provide learning materials that meet the individual needs of each learner.

[0061] "Means of receiving information from users" refers to a function that collects data on subjects, understanding levels, and learning objectives entered by learners through their devices.

[0062] "Means of transmitting to a computing device via a communication device" refers to the technology of using network communication to transfer information from a terminal to a server.

[0063] "Natural language processing technology" is a computer technology that analyzes and understands human language and generates appropriate information and responses.

[0064] "Methods using generative models" refer to methods for generating appropriate training materials and answers using AI based on input information.

[0065] "Optimal answers and learning materials" refer to knowledge and practice exercises that are provided in a format best suited to the learner's needs and level of understanding.

[0066] "Educational materials tailored to individual needs" refer to educational materials provided in a format that is adapted to each learner's learning goals and level.

[0067] This invention is an individualized learning support system using a generative AI model. The user inputs information about the subject they wish to learn, their goals, and their current level of understanding via a terminal. This input is registered on the terminal via a keyboard or touch panel. This information is then transmitted to a server via a communication device.

[0068] The server analyzes this information and uses a generative AI model to generate the most suitable learning materials and responses for the user. Natural language processing technology is used in this analysis process to understand the user's input and generate appropriate responses. The server can also generate exercises and learning materials tailored to the user's individual needs based on their past learning history and selected subjects.

[0069] The generated materials and responses are sent from the server to the terminal and displayed to the user. The user can then efficiently proceed with their learning based on the presented materials. Furthermore, the user's learning progress is recorded by the system and used to support future learning sessions.

[0070] As a concrete example, if a user wants to learn differential equations, they would enter a prompt message on their terminal such as, "I want to learn the basics of differential equations. My current understanding is at a beginner level, and I would like specific practice problems and explanations." Based on this information, the system uses a generative AI model on the server to generate basic materials and practice problems, which are then provided to the user. In this way, the user can continue learning at their own pace and according to their level of understanding.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The user operates the device and inputs learning-related information. This input includes, for example, the subjects they want to study, their current learning status, and their goals. This information is received through forms or applications on the device and stored as digital data in the device's memory.

[0074] Step 2:

[0075] The terminal initializes network communication to send the entered information to the server. At this time, the entered information is encoded in an appropriate data format, such as JSON or XML. The terminal sends this to the server via the internet. Once the transmitted data reaches the server, it is ready for analysis.

[0076] Step 3:

[0077] The server analyzes the received user information. Specifically, it uses natural language processing techniques to decode the information and build context for the generative AI model. In this process, the server analyzes the content of the received data and identifies the learning content requested by the user. For example, if the user is looking for resources on differential equations, that information is extracted as context.

[0078] Step 4:

[0079] The server utilizes a generative AI model to generate learning materials and responses tailored to the user. In this process, the AI ​​model receives contextual information as input and outputs numerical or documentary educational content. The generated output includes specific practice problems and links to reference materials.

[0080] Step 5:

[0081] The server sends the generated data and responses back to the terminal. During transmission, the data is encoded and sent in the appropriate format. The server verifies the integrity of the information to ensure the user terminal can receive it.

[0082] Step 6:

[0083] The device displays the received information to the user. In doing so, the device decodes the received data and formats it to fit the user interface. The user can then begin learning based on the displayed materials and progress at their own pace.

[0084] Step 7:

[0085] Users can re-enter their progress and results as they learn into the device. The device collects this data and records it as learning history data. The learning data is sent to the server as needed to help support future learning.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] In today's educational environment, providing learners with individualized learning experiences is challenging. Furthermore, educational content is often uniform, making it difficult to accommodate diverse learning styles and progress. Additionally, online education offers limited means for efficiently tracking learning outcomes, requiring adjustments to maximize learning effectiveness.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for receiving input information from a user, means for using a generative model that generates personalized responses based on the input information, means for transmitting and displaying the generated responses on the user's device, display means for providing an interactive learning experience in a virtual space, and tracking means for recording learning progress and reflecting it in future learning support. This enables the provision of appropriate learning content to each learner, realization of a personalized learning experience, and effective improvement of learning outcomes.

[0091] A "user" is an individual or organization that provides input information for learning using this system.

[0092] "Input information" refers to data provided by the user regarding their learning, including information such as the field they wish to study, their goals, and their current learning status.

[0093] A "generative model" is a model that uses AI technology to create the optimal response for the learner based on the input information.

[0094] A "user device" refers to a terminal device used by a user to display the generated response or content.

[0095] An "interactive learning experience" is a form of learning in which users can engage with educational content in a virtual space in a two-way manner.

[0096] "Display means" refers to technologies that present generated responses or virtual spaces to users.

[0097] A "tracking mechanism to record progress and reflect it in future learning support" refers to a function that saves the user's learning progress and appropriately adjusts the content of the next learning session based on that progress.

[0098] This invention describes a method for implementing a system that provides a personalized learning experience using a generative AI model.

[0099] The server has a means of receiving input information and collects data on learning subjects, goals, and progress provided by the user. Based on this information, the server uses a generative AI model to generate optimal learning content. This generative AI model applies widely used natural language processing techniques and is used to create materials and questions that are suitable for the user's needs.

[0100] The generated content is sent to the user's device, a terminal, and displayed. Through this terminal, the user enjoys an interactive learning experience in a virtual space. Specific hardware such as smart glasses and head-mounted displays are used. Furthermore, general generative model APIs can be used as the generative AI model.

[0101] Furthermore, the server has a means of tracking learning progress and recording the user's learning data. This can then be used to improve future learning support, thereby enhancing the effectiveness of the learning process.

[0102] As a concrete example, if a user expresses a desire to learn "mechanics in physics" and inputs their current level of understanding and learning goals, the server will generate a prompt message such as "Generate interactive VR learning materials to teach the fundamental concepts of mechanics in physics that the user wishes to learn," and will use a generation AI model to generate relevant learning materials. Providing a flexible and personalized learning experience tailored to the user is the essence of this invention.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The user uses a device to input information about the topic they want to study, their current learning status, and their goals. This input may include, for example, "Physics" or "Understanding Basic Concepts." This information is then sent from the device to the server.

[0106] Step 2:

[0107] The server analyzes the received input information and creates a prompt based on its content. This prompt serves as a command to the generating AI model, specifically something like, "Generate interactive learning materials to teach the fundamental physics concepts the user wants to learn." In this step, the input information is converted into data in the form of a prompt.

[0108] Step 3:

[0109] The server inputs the generated prompt text into the generation AI model, which then generates training content. The generation AI model uses natural language processing techniques to create appropriate training materials and practice problems in response to the prompt. In this process, the input is the prompt text, and the output is the training material.

[0110] Step 4:

[0111] The server receives the generated learning materials and sends them to the user's terminal. This output may include specific text, images, or interactions within a virtual space.

[0112] Step 5:

[0113] Users progress through their learning using learning materials displayed on their devices. The devices implement interactive elements, allowing users to experience learning in a virtual space.

[0114] Step 6:

[0115] The server tracks the user's learning progress and records it in a database. It evaluates the user's behavior and understanding, and uses this information to improve future learning support. The input for this process is user behavior data, and the output is an updated learning profile.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention is implemented as an educational support system combining a generative AI model and an emotion engine. This system consists primarily of a server, terminals, and users. The specific roles of each are detailed below.

[0118] First, the user accesses the learning platform and enters information into their device, including their learning goals, selected subjects, and past learning history. The device then sends this information to the server for integration with the emotion engine.

[0119] The server processes the received data and uses an emotion engine to recognize the user's emotional state from their text. The emotion engine utilizes natural language processing techniques to analyze the emotions hidden in the user's input and identify emotional states such as positive, negative, or neutral.

[0120] The recognized emotional state is used within the server and utilized in the process by which the generative AI model generates responses to the user. Specifically, if the user is feeling anxious or stressed about learning, the server adjusts the generative model to provide responses and learning materials that alleviate the situation. Conversely, if the user is motivated, the server can respond flexibly by suggesting more challenging exercises.

[0121] The server sends generated, personalized responses and tailored learning materials to the terminal, which then displays them to the user. The user can progress through their learning based on the presented information, and the terminal continuously records their learning progress and new emotional data, feeding it back to the server. This cycle enables real-time learning support that responds to the user's emotional changes.

[0122] As a concrete example, imagine a situation where a user is beginning to learn a new mathematical concept and is having difficulty understanding it. If the emotion engine detects that the user is feeling frustrated based on their facial expressions and word choices in their input via the device, the server uses a generative model to generate easy-to-understand learning materials, including detailed explanations and basic examples, to support the user, and sends them to the device.

[0123] Thus, in the embodiments of the present invention, by using a generative AI model and an emotion engine in combination, it is possible to provide a dynamic and adaptive learning environment and realize an educational experience that is tailored to the individual needs and emotions of the user.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] Users log in to the learning platform using their device and enter the subjects or topics they want to study, as well as their learning goals. Their learning history data is also stored on their device.

[0127] Step 2:

[0128] The device sends user input information to the server. This information includes information about the user's learning and emotional information obtained during the interaction process.

[0129] Step 3:

[0130] The server processes the received data and uses an emotion engine to analyze the user's emotional state from the input information. This analysis identifies the type of emotion the user is currently experiencing (e.g., satisfaction, anxiety, stress).

[0131] Step 4:

[0132] Based on the emotional state recognized by the emotion engine, the server uses a generative AI model to generate personalized responses for the user. Specifically, it creates responses that offer further challenges for positive emotions and provide enhanced support for negative emotions.

[0133] Step 5:

[0134] The server sends the generated responses and adjusted learning materials to the terminal. This is designed to include content that reflects the user's emotional state.

[0135] Step 6:

[0136] The terminal displays personalized responses and learning materials received from the server to the user. Based on this, the user progresses through the learning process and, if necessary, enters new questions or feedback.

[0137] Step 7:

[0138] The device continuously records new interaction data resulting from the user's learning activities, along with emotional data, and sends it to the server in real time. This allows the server to track the user's emotional changes in real time and reflect them in subsequent responses.

[0139] (Example 2)

[0140] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0141] Conventional educational support systems struggle to provide dynamic responses and educational content tailored to the individual emotional states of users, resulting in a lack of support that responds to changes in users' emotions and their individual needs. In particular, in learning, users' emotions have a significant impact on learning efficiency and motivation, making appropriate support based on their emotional state essential.

[0142] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0143] In this invention, the server includes means for receiving input information from a user, means for using a computing device that analyzes the emotional state based on the input information, and means for using a generative model that generates an individualized response according to the analyzed emotional state. This makes it possible to provide individualized responses and tailored educational materials in real time according to the user's emotional state, thereby improving the quality of learning.

[0144] A "user" is an individual or group that uses the system to engage in learning activities.

[0145] "Input information" refers to data that users provide to the system via the server, such as learning objectives, selected knowledge areas, and past history information.

[0146] "Emotional state" refers to information indicating a psychological state, such as positive, negative, or neutral, which is analyzed using natural language processing technology based on the user's input information.

[0147] A "computational device" refers to a computer system or related equipment used to process input information and analyze emotional states.

[0148] A "generative model" is a model that implements machine learning algorithms to automatically generate personalized responses and educational resources based on emotional states and input information.

[0149] "Educational resources" refer to educational content such as learning materials and practice exercises that are created using generative models and provided to users.

[0150] A "learning plan" is a step-by-step plan designed to help users progress in their learning, based on their learning goals and timeframe.

[0151] "Real-time" refers to the characteristic of quickly responding to the user's emotional state and learning progress, and providing appropriate information almost instantly.

[0152] This educational support system consists of users, terminals, and a server. Users access the learning platform and input their learning goals, elective subjects, and past history information into the terminal. After receiving this input information, the terminal transmits it to the server using a secure communication method.

[0153] On the server, the processing unit uses an emotion engine to analyze the user's emotional state based on the received input information. The emotion engine uses natural language processing (NLP) techniques to identify emotions such as positive, negative, or neutral from the input text.

[0154] The analyzed emotional state is used by the server to generate responses to the user using a generative AI model. Based on the user's emotional state and selected knowledge areas, the generative AI model provides personalized and appropriate educational resources, such as learning materials and practice exercises. Furthermore, the generative model also constructs a learning plan according to the user's learning goals and timeframe.

[0155] The server prepares and sends generated, personalized responses and tailored educational materials to the terminal. The terminal displays these to the user, assisting them in their learning. The terminal also continuously records the user's learning progress and new sentiment data, and feeds this back to the server.

[0156] As a concrete example, consider a scenario where a user is struggling to understand a new mathematical concept. If the emotion engine recognizes the user's frustration through facial expressions and text input via the device, the server uses a generative AI model to generate easy-to-understand learning materials, including detailed explanations and basic examples, and sends them to the device.

[0157] An example of a prompt used in this system is, "What support do you need to understand a new mathematical concept?" Such prompts allow the generative AI model to generate responses tailored to the user's needs.

[0158] In this way, the educational support system utilizes generative AI models and an emotion engine to provide a dynamic and adaptive learning experience tailored to the user's emotional state.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The user accesses the learning platform and enters learning objectives, elective subjects, and past history information into the terminal. The input is sent to the terminal as text and selection items. The terminal processes the received data and prepares it to send to the server. At this point, the input is the user's learning-related information, and the output is formatted data ready to be sent to the server.

[0162] Step 2:

[0163] The server sends data to the emotion engine based on the formatted data received from the terminal. The emotion engine uses natural language processing techniques to analyze the input text data to determine emotional states such as positive, negative, and neutral. Specifically, it performs emotion scoring based on keywords in the text and their context. The input for this step is the user's text data, and the output is the result of the emotional state determination.

[0164] Step 3:

[0165] The server, based on the output (emotional state) from the emotion engine, invokes a generative AI model to generate personalized responses for the user. The generative AI model creates appropriate learning materials and exercises based on the user's emotional state and selected subjects. In operation, it generates prompt sentences according to the emotional state and creates appropriate responses based on those prompts. The inputs for this step are the emotional state and prompt sentences, and the outputs are personalized responses and learning materials.

[0166] Step 4:

[0167] The server sends personalized responses and learning materials created by the generative model to the terminal. The terminal receives these and displays them to the user. Specifically, the terminal displays text and learning materials on the screen, providing an easily accessible interface for the user. The input is the response data from the server, and the output is the information displayed to the user.

[0168] Step 5:

[0169] The user progresses through the learning process based on the information displayed on the device. The device records the learning progress and responses, and collects new emotional state data. The device then feeds this new data back to the server. In this process, the input is the user's learning activity and emotional responses, and the output is the learning progress and emotional data based on that activity.

[0170] This entire process allows users to receive real-time, emotion-responsive learning support.

[0171] (Application Example 2)

[0172] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0173] In today's learning environment, uniform teaching methods fail to adequately address the diverse needs and emotions of learners, resulting in challenges that impact learning efficiency and motivation. In particular, providing customized learning support tailored to individual emotional states is difficult, making real-time, appropriate educational assistance essential.

[0174] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0175] In this invention, the server includes means for receiving input information from a user, means for using a natural language processing engine to analyze the input information and the user's emotions, and means for using a generative model to generate personalized responses according to the emotional state based on the analysis results. This enables dynamic learning support that responds to the user's emotional state.

[0176] "User" refers to an individual who uses the system to learn.

[0177] "Input information" refers to information that users provide to the system, including learning objectives, courses taken, and past learning history.

[0178] A "natural language processing engine" is software designed to understand and analyze human language, and in particular, it has the ability to analyze emotions from user input.

[0179] "Emotion" refers to the user's emotional state during learning, and includes positive, negative, and neutral emotional states.

[0180] "Personalized responses" refer to appropriately tailored feedback and learning materials that are generated based on the user's specific learning situation and emotional state.

[0181] A "generative model" is an algorithm or program that automatically generates personalized responses based on input information and analyzed emotions.

[0182] "Dynamic learning support" refers to flexible educational support that is immediately adapted to the user's real-time emotional state and learning progress.

[0183] The system that implements this application example processes user input in real time to support learning. Users access the learning platform using devices such as smartphones and tablets and input information such as learning goals, courses taken, and past learning history.

[0184] The device sends this information to the server. The server uses a natural language processing engine to analyze the user's emotions from this information. Natural language processing libraries such as SpaCy are used for this analysis. Based on the analyzed emotional data, a generative AI model generates a personalized response. AI model libraries such as Transformers are used for the generative model's algorithm.

[0185] The generated responses may include learning materials and feedback tailored to the user's emotional state. For example, if the user's motivation to learn is low, explanations in a gentle tone to reduce stress may be included. Conversely, if motivation is high, challenging exercises may be provided.

[0186] For example, if the emotion engine detects user frustration when a user is facing a difficult mathematical concept, the system will generate educational materials that include a detailed explanation along with an encouraging message. By inputting a prompt such as, "A 3-year-old child is feeling frustrated while learning numbers. Please suggest a way to play counting games in a gentle tone," into the generative model and adjusting the content, appropriate learning support can be provided.

[0187] In this way, the system can dynamically respond to the user's real-time needs, enabling it to provide a personalized learning experience.

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] Users access the learning platform using devices such as smartphones and tablets, and input their learning goals, courses, and past learning history. This information is collected on the device as user input data.

[0191] Step 2:

[0192] The terminal sends the aggregated input data to the server. The server receives the input data and begins analysis using a natural language processing engine. The input in this process is the user's input information, and the output is the analyzed emotional data. Specifically, the input text is classified into positive, negative, and neutral states using tools such as SpaCy.

[0193] Step 3:

[0194] The server provides prompts to the generative AI model based on the analyzed emotional data. These prompts include detailed instructions tailored to the user's emotional state. The generative AI model uses Transformers to generate personalized responses based on these prompts. The input is a prompt containing the analyzed emotional data, and the output is a customized response.

[0195] Step 4:

[0196] The server sends the personalized response generated by the generative AI model to the user's device. The user can then receive and view this response on their device. The input is the generated response, and the output is the display state on the device.

[0197] Step 5:

[0198] The user progresses through the learning process based on the displayed responses. The device receives new inputs and feedback from the user and sends them back to the server. This new input information becomes the input information for the next step (Step 1), and the process is repeated. Here, the new input information is sent back to the system again, and the process loops, enabling real-time learning support.

[0199] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0200] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0201] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0202] [Second Embodiment]

[0203] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0204] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0205] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0206] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0207] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0208] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0209] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0210] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0211] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0212] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0213] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0214] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0215] This invention is implemented as a system that provides personalized educational support using a generative AI model. This system primarily consists of a server, terminals, and users. The respective roles are detailed below.

[0216] First, the user enters learning-related information into the terminal. This information includes, for example, the subject they want to study, their current learning status, and their goals. This information is then sent to the server via the terminal.

[0217] The server uses a generative AI model to generate responses tailored to the user based on the received input information. The generative AI model employs natural language processing techniques to analyze user requests and generate the most appropriate learning materials and answers. Furthermore, the server can also generate relevant practice problems based on the user's past learning data and selected subjects. This allows users to receive learning materials that meet their individual needs.

[0218] Next, the server sends the generated responses and learning materials to the terminal, which then displays them to the user. The user can then proceed with their learning based on the displayed information. The system can also record the user's learning progress and use this information to improve future learning support.

[0219] For example, if a user wants to efficiently learn differential equations, they input their study plan and current level of understanding using their device. The server then generates introductory materials and practice problems tailored to the user's needs and sends them to the user's device. In this way, learners can progress through their studies using materials that match their level of understanding.

[0220] Thus, in the embodiments of the present invention, a flexible and individualized learning experience that meets the needs of learners can be provided, and the burden on teachers can be reduced.

[0221] The following describes the processing flow.

[0222] Step 1:

[0223] Users log in to the learning platform and enter the subjects or topics they wish to study into their device. During this process, users also provide information about their current learning status and goals.

[0224] Step 2:

[0225] The terminal sends user input information to the server. This process uses a secure and reliable communication protocol.

[0226] Step 3:

[0227] The server analyzes the received user information and passes it to the generative AI model. The generative AI model understands the user's intent and generates responses tailored to their individual learning needs.

[0228] Step 4:

[0229] The server selects or generates relevant learning materials and practice problems based on the responses created by the generation AI model. Here, content is selected according to the user's past learning history and interests.

[0230] Step 5:

[0231] The server sends the generated learning content to the terminal. The transmitted information is structured in a format that is easily understandable to the user.

[0232] Step 6:

[0233] The device displays received learning materials and responses to the user. The user can review the provided information and ask further questions as needed.

[0234] Step 7:

[0235] The device records the user's progress as they learn and periodically sends this information to the server. This data is stored on the server to help support future learning sessions.

[0236] (Example 1)

[0237] Next, we will describe Example 1. 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."

[0238] In educational settings, there is a need to provide individualized learning support tailored to each learner's level and goals, and to create an efficient learning environment. However, existing systems fail to adequately address the diverse needs of learners, making it difficult to reduce the burden on teachers. Therefore, there is a need for a flexible system that automatically generates and presents appropriate learning materials and practice problems based on learner input.

[0239] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0240] In this invention, the server includes means for receiving information from users, means for transmitting said information to a computing device via a communication device, and means for using a generative model to generate optimal answers and learning materials based on said information using natural language processing technology. This makes it possible to provide learning materials that meet the individual needs of each learner.

[0241] "Means of receiving information from users" refers to a function that collects data on subjects, understanding levels, and learning objectives entered by learners through their devices.

[0242] "Means of transmitting to a computing device via a communication device" refers to the technology of using network communication to transfer information from a terminal to a server.

[0243] "Natural language processing technology" is a computer technology that analyzes and understands human language and generates appropriate information and responses.

[0244] "Methods using generative models" refer to methods for generating appropriate training materials and answers using AI based on input information.

[0245] "Optimal answers and learning materials" refer to knowledge and practice exercises that are provided in a format best suited to the learner's needs and level of understanding.

[0246] "Educational materials tailored to individual needs" refer to educational materials provided in a format that is adapted to each learner's learning goals and level.

[0247] This invention is an individualized learning support system using a generative AI model. The user inputs information about the subject they wish to learn, their goals, and their current level of understanding via a terminal. This input is registered on the terminal via a keyboard or touch panel. This information is then transmitted to a server via a communication device.

[0248] The server analyzes this information and uses a generative AI model to generate the most suitable learning materials and responses for the user. Natural language processing technology is used in this analysis process to understand the user's input and generate appropriate responses. The server can also generate exercises and learning materials tailored to the user's individual needs based on their past learning history and selected subjects.

[0249] The generated materials and responses are sent from the server to the terminal and displayed to the user. The user can then efficiently proceed with their learning based on the presented materials. Furthermore, the user's learning progress is recorded by the system and used to support future learning sessions.

[0250] As a concrete example, if a user wants to learn differential equations, they would enter a prompt message on their terminal such as, "I want to learn the basics of differential equations. My current understanding is at a beginner level, and I would like specific practice problems and explanations." Based on this information, the system uses a generative AI model on the server to generate basic materials and practice problems, which are then provided to the user. In this way, the user can continue learning at their own pace and according to their level of understanding.

[0251] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0252] Step 1:

[0253] The user operates the device and inputs learning-related information. This input includes, for example, the subjects they want to study, their current learning status, and their goals. This information is received through forms or applications on the device and stored as digital data in the device's memory.

[0254] Step 2:

[0255] The terminal initializes network communication to send the entered information to the server. At this time, the entered information is encoded in an appropriate data format, such as JSON or XML. The terminal sends this to the server via the internet. Once the transmitted data reaches the server, it is ready for analysis.

[0256] Step 3:

[0257] The server analyzes the received user information. Specifically, it uses natural language processing techniques to decode the information and build context for the generative AI model. In this process, the server analyzes the content of the received data and identifies the learning content requested by the user. For example, if the user is looking for resources on differential equations, that information is extracted as context.

[0258] Step 4:

[0259] The server utilizes a generative AI model to generate learning materials and responses tailored to the user. In this process, the AI ​​model receives contextual information as input and outputs numerical or documentary educational content. The generated output includes specific practice problems and links to reference materials.

[0260] Step 5:

[0261] The server sends the generated data and responses back to the terminal. During transmission, the data is encoded and sent in the appropriate format. The server verifies the integrity of the information to ensure the user terminal can receive it.

[0262] Step 6:

[0263] The device displays the received information to the user. In doing so, the device decodes the received data and formats it to fit the user interface. The user can then begin learning based on the displayed materials and progress at their own pace.

[0264] Step 7:

[0265] Users can re-enter their progress and results as they learn into the device. The device collects this data and records it as learning history data. The learning data is sent to the server as needed to help support future learning.

[0266] (Application Example 1)

[0267] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0268] In today's educational environment, providing learners with individualized learning experiences is challenging. Furthermore, educational content is often uniform, making it difficult to accommodate diverse learning styles and progress. Additionally, online education offers limited means for efficiently tracking learning outcomes, requiring adjustments to maximize learning effectiveness.

[0269] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0270] In this invention, the server includes means for receiving input information from a user, means for using a generative model that generates personalized responses based on the input information, means for transmitting and displaying the generated responses on the user's device, display means for providing an interactive learning experience in a virtual space, and tracking means for recording learning progress and reflecting it in future learning support. This enables the provision of appropriate learning content to each learner, realization of a personalized learning experience, and effective improvement of learning outcomes.

[0271] A "user" is an individual or organization that provides input information for learning using this system.

[0272] "Input information" refers to data provided by the user regarding their learning, including information such as the field they wish to study, their goals, and their current learning status.

[0273] A "generative model" is a model that uses AI technology to create the optimal response for the learner based on the input information.

[0274] A "user device" refers to a terminal device used by a user to display the generated response or content.

[0275] An "interactive learning experience" is a form of learning in which users can engage with educational content in a virtual space in a two-way manner.

[0276] "Display means" refers to technologies that present generated responses or virtual spaces to users.

[0277] "A tracking mechanism that records progress and reflects it in future learning support" refers to a function that saves the user's learning progress and appropriately adjusts the content of the next learning session based on that progress.

[0278] This invention describes a method for implementing a system that provides a personalized learning experience using a generative AI model.

[0279] The server has means for receiving input information and collects data on the learning target, goal, and progress status provided by the user. Based on this information, the server utilizes a generative AI model to generate optimal learning content. This generative AI model applies widely used natural language processing techniques and is used to create materials and questions suitable for the user's requests.

[0280] The generated content is transmitted to and displayed on the terminal, which is the utilization device. Through this terminal, the user enjoys an interactive learning experience within the virtual space. As specific hardware, smart glasses, head-mounted displays, etc. are utilized. Also, as the generative AI model, a general generative model API can be used.

[0281] Furthermore, the server is equipped with means for tracking the progress of learning and records the user's learning data. Thereby, it can be reflected in the next learning support, and it is possible to improve the learning effect.

[0282] As a specific example, when the user wishes to learn "mechanics in physics" and inputs the current understanding level and learning goal, the server creates a prompt sentence such as "Please generate an interactive VR teaching material for teaching the basic concepts related to the mechanics of physics that the user wants to learn." and uses the generative AI model to generate related teaching materials. Providing a flexible and individualized learning experience suitable for the user is the essence of this invention.

[0283] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0284] Step 1:

[0285] The user uses the terminal to input information regarding the theme to be learned, the current learning status, and the goal. The input information includes, for example, "physics", "understanding of basic concepts", etc. This information is transmitted from the terminal to the server.

[0286] Step 2:

[0287] The server analyzes the received input information and creates a prompt sentence based on its content. This prompt sentence serves as a command for the generative AI model. Specifically, it could be something like "Please generate an interactive teaching material to teach the basic concepts of physics that the user wants to learn." In this step, the input information is converted into the form of a prompt sentence through data transformation.

[0288] Step 3:

[0289] The server inputs the generated prompt sentence into the generative AI model to generate learning content. The generative AI model uses natural language processing technology to create appropriate learning materials and practice questions according to the prompt. At this time, the input is the prompt sentence, and the output is the learning materials.

[0290] Step 4:

[0291] The server receives the generated learning materials and transmits them to the terminal, which is the device for use. This output may include specific text, images, or interactions within a virtual space.

[0292] Step 5:

[0293] The user proceeds with learning using the learning materials displayed through the terminal. The terminal implements interactive elements to enable the user to experience learning within a virtual space.

[0294] Step 6:

[0295] The server tracks the progress of the user's learning and records it in the database. It evaluates the user's actions and understanding level and reflects them in the next learning support. The input in this process is the user's action data, and the output is the updated learning profile.

[0296] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0297] This invention is implemented as an educational support system combining a generative AI model and an emotion engine. This system consists primarily of a server, terminals, and users. The specific roles of each are detailed below.

[0298] First, the user accesses the learning platform and enters information into their device, including their learning goals, selected subjects, and past learning history. The device then sends this information to the server for integration with the emotion engine.

[0299] The server processes the received data and uses an emotion engine to recognize the user's emotional state from their text. The emotion engine utilizes natural language processing techniques to analyze the emotions hidden in the user's input and identify emotional states such as positive, negative, or neutral.

[0300] The recognized emotional state is used within the server and utilized in the process by which the generative AI model generates responses to the user. Specifically, if the user is feeling anxious or stressed about learning, the server adjusts the generative model to provide responses and learning materials that alleviate the situation. Conversely, if the user is motivated, the server can respond flexibly by suggesting more challenging exercises.

[0301] The server sends generated, personalized responses and tailored learning materials to the terminal, which then displays them to the user. The user can progress through their learning based on the presented information, and the terminal continuously records their learning progress and new emotional data, feeding it back to the server. This cycle enables real-time learning support that responds to the user's emotional changes.

[0302] As a specific example, assume a situation where a user starts learning a new mathematical concept and is having difficulty understanding it. When the emotion engine recognizes from the user's expression and the choice of words in the input content through the terminal that the user is feeling frustrated, the server uses the generation model to generate educational materials with gentle content including detailed explanations and basic examples to support the user, and sends them to the terminal.

[0303] Thus, in the embodiment of the present invention, by using the generation AI model and the emotion engine in combination, it is possible to provide a dynamic and adaptive learning environment and realize an educational experience that conforms to the individualized needs and emotions of the user.

[0304] The following describes the processing flow.

[0305] Step 1:

[0306] The user uses the terminal to log in to the learning platform and enters the subject or topic to be learned and their own learning goals. Also, the previous learning history data is retained on the terminal.

[0307] Step 2:

[0308] The terminal sends the input information from the user to the server. This information includes information related to the user's learning content and emotion information obtained in the process of interaction.

[0309] Step 3:

[0310] The server processes the received data and analyzes the emotional state from the user's input information using the emotion engine. Through this analysis, the type of emotion the user is currently experiencing (e.g., satisfaction, anxiety, stress, etc.) is identified.

[0311] Step 4:

[0312] Based on the emotional state recognized by the emotion engine, the server uses a generative AI model to generate personalized responses for the user. Specifically, it creates responses that offer further challenges for positive emotions and provide enhanced support for negative emotions.

[0313] Step 5:

[0314] The server sends the generated responses and adjusted learning materials to the terminal. This is designed to include content that reflects the user's emotional state.

[0315] Step 6:

[0316] The terminal displays personalized responses and learning materials received from the server to the user. Based on this, the user progresses through the learning process and, if necessary, enters new questions or feedback.

[0317] Step 7:

[0318] The device continuously records new interaction data resulting from the user's learning activities, along with emotional data, and sends it to the server in real time. This allows the server to track the user's emotional changes in real time and reflect them in subsequent responses.

[0319] (Example 2)

[0320] Next, we will describe Example 2. 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".

[0321] Conventional educational support systems struggle to provide dynamic responses and educational content tailored to the individual emotional states of users, resulting in a lack of support that responds to changes in users' emotions and their individual needs. In particular, in learning, users' emotions have a significant impact on learning efficiency and motivation, making appropriate support based on their emotional state essential.

[0322] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0323] In this invention, the server includes means for receiving input information from a user, means for using a computing device that analyzes the emotional state based on the input information, and means for using a generative model that generates an individualized response according to the analyzed emotional state. This makes it possible to provide individualized responses and tailored educational materials in real time according to the user's emotional state, thereby improving the quality of learning.

[0324] A "user" is an individual or group that uses the system to engage in learning activities.

[0325] "Input information" refers to data that users provide to the system via the server, such as learning objectives, selected knowledge areas, and past history information.

[0326] "Emotional state" refers to information indicating a psychological state, such as positive, negative, or neutral, which is analyzed using natural language processing technology based on the user's input information.

[0327] A "computational device" refers to a computer system or related equipment used to process input information and analyze emotional states.

[0328] A "generative model" is a model that implements machine learning algorithms to automatically generate personalized responses and educational resources based on emotional states and input information.

[0329] "Educational resources" refer to educational content such as learning materials and practice exercises that are created using generative models and provided to users.

[0330] A "learning plan" is a step-by-step plan designed to help users progress in their learning, based on their learning goals and timeframe.

[0331] "Real-time" refers to the characteristic of quickly responding to the user's emotional state and learning progress, and providing appropriate information almost instantly.

[0332] This educational support system consists of users, terminals, and a server. Users access the learning platform and input their learning goals, elective subjects, and past history information into the terminal. After receiving this input information, the terminal transmits it to the server using a secure communication method.

[0333] On the server, the processing unit uses an emotion engine to analyze the user's emotional state based on the received input information. The emotion engine uses natural language processing (NLP) techniques to identify emotions such as positive, negative, or neutral from the input text.

[0334] The analyzed emotional state is used by the server to generate responses to the user using a generative AI model. Based on the user's emotional state and selected knowledge areas, the generative AI model provides personalized and appropriate educational resources, such as learning materials and practice exercises. Furthermore, the generative model also constructs a learning plan according to the user's learning goals and timeframe.

[0335] The server prepares and sends generated, personalized responses and tailored educational materials to the terminal. The terminal displays these to the user, assisting them in their learning. The terminal also continuously records the user's learning progress and new sentiment data, and feeds this back to the server.

[0336] As a concrete example, consider a scenario where a user is struggling to understand a new mathematical concept. If the emotion engine recognizes the user's frustration through facial expressions and text input via the device, the server uses a generative AI model to generate easy-to-understand learning materials, including detailed explanations and basic examples, and sends them to the device.

[0337] An example of a prompt used in this system is, "What support do you need to understand a new mathematical concept?" Such prompts allow the generative AI model to generate responses tailored to the user's needs.

[0338] In this way, the educational support system utilizes generative AI models and an emotion engine to provide a dynamic and adaptive learning experience tailored to the user's emotional state.

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The user accesses the learning platform and enters learning objectives, elective subjects, and past history information into the terminal. The input is sent to the terminal as text and selection items. The terminal processes the received data and prepares it to send to the server. At this point, the input is the user's learning-related information, and the output is formatted data ready to be sent to the server.

[0342] Step 2:

[0343] The server sends data to the emotion engine based on the formatted data received from the terminal. The emotion engine uses natural language processing techniques to analyze the input text data to determine emotional states such as positive, negative, and neutral. Specifically, it performs emotion scoring based on keywords in the text and their context. The input for this step is the user's text data, and the output is the result of the emotional state determination.

[0344] Step 3:

[0345] The server, based on the output (emotional state) from the emotion engine, invokes a generative AI model to generate personalized responses for the user. The generative AI model creates appropriate learning materials and exercises based on the user's emotional state and selected subjects. In operation, it generates prompt sentences according to the emotional state and creates appropriate responses based on those prompts. The inputs for this step are the emotional state and prompt sentences, and the outputs are personalized responses and learning materials.

[0346] Step 4:

[0347] The server sends personalized responses and learning materials created by the generative model to the terminal. The terminal receives these and displays them to the user. Specifically, the terminal displays text and learning materials on the screen, providing an easily accessible interface for the user. The input is the response data from the server, and the output is the information displayed to the user.

[0348] Step 5:

[0349] The user progresses through the learning process based on the information displayed on the device. The device records the learning progress and responses, and collects new emotional state data. The device then feeds this new data back to the server. In this process, the input is the user's learning activity and emotional responses, and the output is the learning progress and emotional data based on that activity.

[0350] This entire process allows users to receive real-time, emotion-responsive learning support.

[0351] (Application Example 2)

[0352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0353] In today's learning environment, uniform teaching methods fail to adequately address the diverse needs and emotions of learners, resulting in challenges that impact learning efficiency and motivation. In particular, providing customized learning support tailored to individual emotional states is difficult, making real-time, appropriate educational assistance essential.

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

[0355] In this invention, the server includes means for receiving input information from a user, means for using a natural language processing engine to analyze the input information and the user's emotions, and means for using a generative model to generate personalized responses according to the emotional state based on the analysis results. This enables dynamic learning support that responds to the user's emotional state.

[0356] "User" refers to an individual who uses the system to learn.

[0357] "Input information" refers to information that users provide to the system, including learning objectives, courses taken, and past learning history.

[0358] A "natural language processing engine" is software designed to understand and analyze human language, and in particular, it has the ability to analyze emotions from user input.

[0359] "Emotion" refers to the user's emotional state during learning, and includes positive, negative, and neutral emotional states.

[0360] "Personalized responses" refer to appropriately tailored feedback and learning materials that are generated based on the user's specific learning situation and emotional state.

[0361] A "generative model" is an algorithm or program that automatically generates personalized responses based on input information and analyzed emotions.

[0362] "Dynamic learning support" refers to flexible educational support that is immediately adapted to the user's real-time emotional state and learning progress.

[0363] The system that implements this application example processes user input in real time to support learning. Users access the learning platform using devices such as smartphones and tablets and input information such as learning goals, courses taken, and past learning history.

[0364] The device sends this information to the server. The server uses a natural language processing engine to analyze the user's emotions from this information. Natural language processing libraries such as SpaCy are used for this analysis. Based on the analyzed emotional data, a generative AI model generates a personalized response. AI model libraries such as Transformers are used for the generative model's algorithm.

[0365] The generated responses may include learning materials and feedback tailored to the user's emotional state. For example, if the user's motivation to learn is low, explanations in a gentle tone to reduce stress may be included. Conversely, if motivation is high, challenging exercises may be provided.

[0366] For example, if the emotion engine detects user frustration when a user is facing a difficult mathematical concept, the system will generate educational materials that include a detailed explanation along with an encouraging message. By inputting a prompt such as, "A 3-year-old child is feeling frustrated while learning numbers. Please suggest a way to play counting games in a gentle tone," into the generative model and adjusting the content, appropriate learning support can be provided.

[0367] In this way, the system can dynamically respond to the user's real-time needs, enabling it to provide a personalized learning experience.

[0368] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0369] Step 1:

[0370] Users access the learning platform using devices such as smartphones and tablets, and input their learning goals, courses, and past learning history. This information is collected on the device as user input data.

[0371] Step 2:

[0372] The terminal sends the aggregated input data to the server. The server receives the input data and begins analysis using a natural language processing engine. The input in this process is the user's input information, and the output is the analyzed emotional data. Specifically, the input text is classified into positive, negative, and neutral states using tools such as SpaCy.

[0373] Step 3:

[0374] The server provides prompts to the generative AI model based on the analyzed emotional data. These prompts include detailed instructions tailored to the user's emotional state. The generative AI model uses Transformers to generate personalized responses based on these prompts. The input is a prompt containing the analyzed emotional data, and the output is a customized response.

[0375] Step 4:

[0376] The server sends the personalized response generated by the generative AI model to the user's device. The user can then receive and view this response on their device. The input is the generated response, and the output is the display state on the device.

[0377] Step 5:

[0378] The user progresses through the learning process based on the displayed responses. The device receives new inputs and feedback from the user and sends them back to the server. This new input information becomes the input information for the next step (Step 1), and the process is repeated. Here, the new input information is sent back to the system again, and the process loops, enabling real-time learning support.

[0379] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0380] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0381] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0382] [Third Embodiment]

[0383] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0384] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0385] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0386] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0387] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0388] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0389] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0390] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0391] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0392] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0393] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0394] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0395] This invention is implemented as a system that provides personalized educational support using a generative AI model. This system primarily consists of a server, terminals, and users. The respective roles are detailed below.

[0396] First, the user enters learning-related information into the terminal. This information includes, for example, the subject they want to study, their current learning status, and their goals. This information is then sent to the server via the terminal.

[0397] The server uses a generative AI model to generate responses tailored to the user based on the received input information. The generative AI model employs natural language processing techniques to analyze user requests and generate the most appropriate learning materials and answers. Furthermore, the server can also generate relevant practice problems based on the user's past learning data and selected subjects. This allows users to receive learning materials that meet their individual needs.

[0398] Next, the server sends the generated responses and learning materials to the terminal, which then displays them to the user. The user can then proceed with their learning based on the displayed information. The system can also record the user's learning progress and use this information to improve future learning support.

[0399] For example, if a user wants to efficiently learn differential equations, they input their study plan and current level of understanding using their device. The server then generates introductory materials and practice problems tailored to the user's needs and sends them to the user's device. In this way, learners can progress through their studies using materials that match their level of understanding.

[0400] Thus, in the embodiments of the present invention, a flexible and individualized learning experience that meets the needs of learners can be provided, and the burden on teachers can be reduced.

[0401] The following describes the processing flow.

[0402] Step 1:

[0403] Users log in to the learning platform and enter the subjects or topics they wish to study into their device. During this process, users also provide information about their current learning status and goals.

[0404] Step 2:

[0405] The terminal sends user input information to the server. This process uses a secure and reliable communication protocol.

[0406] Step 3:

[0407] The server analyzes the received user information and passes it to the generative AI model. The generative AI model understands the user's intent and generates responses tailored to their individual learning needs.

[0408] Step 4:

[0409] The server selects or generates relevant learning materials and practice problems based on the responses created by the generation AI model. Here, content is selected according to the user's past learning history and interests.

[0410] Step 5:

[0411] The server sends the generated learning content to the terminal. The transmitted information is structured in a format that is easily understandable to the user.

[0412] Step 6:

[0413] The device displays received learning materials and responses to the user. The user can review the provided information and ask further questions as needed.

[0414] Step 7:

[0415] The device records the user's progress as they learn and periodically sends this information to the server. This data is stored on the server to help support future learning sessions.

[0416] (Example 1)

[0417] Next, we will describe Example 1. 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."

[0418] In educational settings, there is a need to provide individualized learning support tailored to each learner's level and goals, and to create an efficient learning environment. However, existing systems fail to adequately address the diverse needs of learners, making it difficult to reduce the burden on teachers. Therefore, there is a need for a flexible system that automatically generates and presents appropriate learning materials and practice problems based on learner input.

[0419] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0420] In this invention, the server includes means for receiving information from users, means for transmitting said information to a computing device via a communication device, and means for using a generative model to generate optimal answers and learning materials based on said information using natural language processing technology. This makes it possible to provide learning materials that meet the individual needs of each learner.

[0421] "Means of receiving information from users" refers to a function that collects data on subjects, understanding levels, and learning objectives entered by learners through their devices.

[0422] "Means of transmitting to a computing device via a communication device" refers to the technology of using network communication to transfer information from a terminal to a server.

[0423] "Natural language processing technology" is a computer technology that analyzes and understands human language and generates appropriate information and responses.

[0424] "Methods using generative models" refer to methods for generating appropriate training materials and answers using AI based on input information.

[0425] "Optimal answers and learning materials" refer to knowledge and practice exercises that are provided in a format best suited to the learner's needs and level of understanding.

[0426] "Educational materials tailored to individual needs" refer to educational materials provided in a format that is adapted to each learner's learning goals and level.

[0427] This invention is an individualized learning support system using a generative AI model. The user inputs information about the subject they wish to learn, their goals, and their current level of understanding via a terminal. This input is registered on the terminal via a keyboard or touch panel. This information is then transmitted to a server via a communication device.

[0428] The server analyzes this information and uses a generative AI model to generate the most suitable learning materials and responses for the user. Natural language processing technology is used in this analysis process to understand the user's input and generate appropriate responses. The server can also generate exercises and learning materials tailored to the user's individual needs based on their past learning history and selected subjects.

[0429] The generated materials and responses are sent from the server to the terminal and displayed to the user. The user can then efficiently proceed with their learning based on the presented materials. Furthermore, the user's learning progress is recorded by the system and used to support future learning sessions.

[0430] As a concrete example, if a user wants to learn differential equations, they would enter a prompt message on their terminal such as, "I want to learn the basics of differential equations. My current understanding is at a beginner level, and I would like specific practice problems and explanations." Based on this information, the system uses a generative AI model on the server to generate basic materials and practice problems, which are then provided to the user. In this way, the user can continue learning at their own pace and according to their level of understanding.

[0431] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0432] Step 1:

[0433] The user operates the device and inputs learning-related information. This input includes, for example, the subjects they want to study, their current learning status, and their goals. This information is received through forms or applications on the device and stored as digital data in the device's memory.

[0434] Step 2:

[0435] The terminal initializes network communication to send the entered information to the server. At this time, the entered information is encoded in an appropriate data format, such as JSON or XML. The terminal sends this to the server via the internet. Once the transmitted data reaches the server, it is ready for analysis.

[0436] Step 3:

[0437] The server analyzes the received user information. Specifically, it uses natural language processing techniques to decode the information and build context for the generative AI model. In this process, the server analyzes the content of the received data and identifies the learning content requested by the user. For example, if the user is looking for resources on differential equations, that information is extracted as context.

[0438] Step 4:

[0439] The server utilizes a generative AI model to generate learning materials and responses tailored to the user. In this process, the AI ​​model receives contextual information as input and outputs numerical or documentary educational content. The generated output includes specific practice problems and links to reference materials.

[0440] Step 5:

[0441] The server sends the generated data and responses back to the terminal. During transmission, the data is encoded and sent in the appropriate format. The server verifies the integrity of the information to ensure the user terminal can receive it.

[0442] Step 6:

[0443] The device displays the received information to the user. In doing so, the device decodes the received data and formats it to fit the user interface. The user can then begin learning based on the displayed materials and progress at their own pace.

[0444] Step 7:

[0445] Users can re-enter their progress and results as they learn into the device. The device collects this data and records it as learning history data. The learning data is sent to the server as needed to help support future learning.

[0446] (Application Example 1)

[0447] Next, we will explain Application Example 1. In the following explanation, 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."

[0448] In today's educational environment, providing learners with individualized learning experiences is challenging. Furthermore, educational content is often uniform, making it difficult to accommodate diverse learning styles and progress. Additionally, online education offers limited means for efficiently tracking learning outcomes, requiring adjustments to maximize learning effectiveness.

[0449] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0450] In this invention, the server includes means for receiving input information from a user, means for using a generative model that generates personalized responses based on the input information, means for transmitting and displaying the generated responses on the user's device, display means for providing an interactive learning experience in a virtual space, and tracking means for recording learning progress and reflecting it in future learning support. This enables the provision of appropriate learning content to each learner, realization of a personalized learning experience, and effective improvement of learning outcomes.

[0451] A "user" is an individual or organization that provides input information for learning using this system.

[0452] "Input information" refers to data provided by the user regarding their learning, including information such as the field they wish to study, their goals, and their current learning status.

[0453] A "generative model" is a model that uses AI technology to create the optimal response for the learner based on the input information.

[0454] A "user device" refers to a terminal device used by a user to display the generated response or content.

[0455] An "interactive learning experience" is a form of learning in which users can engage with educational content in a virtual space in a two-way manner.

[0456] "Display means" refers to technologies that present generated responses or virtual spaces to users.

[0457] "A tracking mechanism that records progress and reflects it in future learning support" refers to a function that saves the user's learning progress and appropriately adjusts the content of the next learning session based on that progress.

[0458] This invention describes a method for implementing a system that provides a personalized learning experience using a generative AI model.

[0459] The server has a means of receiving input information and collects data on learning subjects, goals, and progress provided by the user. Based on this information, the server uses a generative AI model to generate optimal learning content. This generative AI model applies widely used natural language processing techniques and is used to create materials and questions that are suitable for the user's needs.

[0460] The generated content is sent to the user's device, a terminal, and displayed. Through this terminal, the user enjoys an interactive learning experience in a virtual space. Specific hardware such as smart glasses and head-mounted displays are used. Furthermore, general generative model APIs can be used as the generative AI model.

[0461] Furthermore, the server has a means of tracking learning progress and recording the user's learning data. This can then be used to improve future learning support, thereby enhancing the effectiveness of the learning process.

[0462] As a concrete example, if a user expresses a desire to learn "mechanics in physics" and inputs their current level of understanding and learning goals, the server will generate a prompt message such as "Generate interactive VR learning materials to teach the fundamental concepts of mechanics in physics that the user wishes to learn," and will use a generation AI model to generate relevant learning materials. Providing a flexible and personalized learning experience tailored to the user is the essence of this invention.

[0463] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0464] Step 1:

[0465] The user uses a device to input information about the topic they want to study, their current learning status, and their goals. This input may include, for example, "Physics" or "Understanding Basic Concepts." This information is then sent from the device to the server.

[0466] Step 2:

[0467] The server analyzes the received input information and creates a prompt based on its content. This prompt serves as a command to the generating AI model, specifically something like, "Generate interactive learning materials to teach the fundamental physics concepts the user wants to learn." In this step, the input information is converted into data in the form of a prompt.

[0468] Step 3:

[0469] The server inputs the generated prompt text into the generation AI model, which then generates training content. The generation AI model uses natural language processing techniques to create appropriate training materials and practice problems in response to the prompt. In this process, the input is the prompt text, and the output is the training material.

[0470] Step 4:

[0471] The server receives the generated learning materials and sends them to the user's terminal. This output may include specific text, images, or interactions within a virtual space.

[0472] Step 5:

[0473] Users progress through their learning using learning materials displayed on their devices. The devices implement interactive elements, allowing users to experience learning in a virtual space.

[0474] Step 6:

[0475] The server tracks the user's learning progress and records it in a database. It evaluates the user's behavior and understanding, and uses this information to improve future learning support. The input for this process is user behavior data, and the output is an updated learning profile.

[0476] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0477] This invention is implemented as an educational support system combining a generative AI model and an emotion engine. This system consists primarily of a server, terminals, and users. The specific roles of each are detailed below.

[0478] First, the user accesses the learning platform and enters information into their device, including their learning goals, selected subjects, and past learning history. The device then sends this information to the server for integration with the emotion engine.

[0479] The server processes the received data and uses an emotion engine to recognize the user's emotional state from their text. The emotion engine utilizes natural language processing techniques to analyze the emotions hidden in the user's input and identify emotional states such as positive, negative, or neutral.

[0480] The recognized emotional state is used within the server and utilized in the process by which the generative AI model generates responses to the user. Specifically, if the user is feeling anxious or stressed about learning, the server adjusts the generative model to provide responses and learning materials that alleviate the situation. Conversely, if the user is motivated, the server can respond flexibly by suggesting more challenging exercises.

[0481] The server sends generated, personalized responses and tailored learning materials to the terminal, which then displays them to the user. The user can progress through their learning based on the presented information, and the terminal continuously records their learning progress and new emotional data, feeding it back to the server. This cycle enables real-time learning support that responds to the user's emotional changes.

[0482] As a concrete example, imagine a situation where a user is beginning to learn a new mathematical concept and is having difficulty understanding it. If the emotion engine detects that the user is feeling frustrated based on their facial expressions and word choices in their input via the device, the server uses a generative model to generate easy-to-understand learning materials, including detailed explanations and basic examples, to support the user, and sends them to the device.

[0483] Thus, in the embodiments of the present invention, by using a generative AI model and an emotion engine in combination, it is possible to provide a dynamic and adaptive learning environment and realize an educational experience that is tailored to the individual needs and emotions of the user.

[0484] The following describes the processing flow.

[0485] Step 1:

[0486] Users log in to the learning platform using their device and enter the subjects or topics they want to study, as well as their learning goals. Their learning history data is also stored on their device.

[0487] Step 2:

[0488] The device sends user input information to the server. This information includes information about the user's learning content and emotional information obtained during the interaction process.

[0489] Step 3:

[0490] The server processes the received data and uses an emotion engine to analyze the user's emotional state from the input information. This analysis identifies the type of emotion the user is currently experiencing (e.g., satisfaction, anxiety, stress).

[0491] Step 4:

[0492] Based on the emotional state recognized by the emotion engine, the server uses a generative AI model to generate personalized responses for the user. Specifically, it creates responses that offer further challenges for positive emotions and provide enhanced support for negative emotions.

[0493] Step 5:

[0494] The server sends the generated responses and adjusted learning materials to the terminal. This is designed to include content that reflects the user's emotional state.

[0495] Step 6:

[0496] The terminal displays personalized responses and learning materials received from the server to the user. Based on this, the user progresses through the learning process and, if necessary, enters new questions or feedback.

[0497] Step 7:

[0498] The device continuously records new interaction data resulting from the user's learning activities, along with emotional data, and sends it to the server in real time. This allows the server to track the user's emotional changes in real time and reflect them in subsequent responses.

[0499] (Example 2)

[0500] Next, we will describe Example 2. 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."

[0501] Conventional educational support systems struggle to provide dynamic responses and educational content tailored to the individual emotional states of users, resulting in a lack of support that responds to changes in users' emotions and their individual needs. In particular, in learning, users' emotions have a significant impact on learning efficiency and motivation, making appropriate support based on their emotional state essential.

[0502] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0503] In this invention, the server includes means for receiving input information from a user, means for using a computing device that analyzes the emotional state based on the input information, and means for using a generative model that generates an individualized response according to the analyzed emotional state. This makes it possible to provide individualized responses and tailored educational materials in real time according to the user's emotional state, thereby improving the quality of learning.

[0504] A "user" is an individual or group that uses the system to engage in learning activities.

[0505] "Input information" refers to data that users provide to the system via the server, such as learning objectives, selected knowledge areas, and past history information.

[0506] "Emotional state" refers to information indicating a psychological state, such as positive, negative, or neutral, which is analyzed using natural language processing technology based on the user's input information.

[0507] A "computational device" refers to a computer system or related equipment used to process input information and analyze emotional states.

[0508] A "generative model" is a model that implements machine learning algorithms to automatically generate personalized responses and educational resources based on emotional states and input information.

[0509] "Educational resources" refer to educational content such as learning materials and practice exercises that are created using generative models and provided to users.

[0510] A "learning plan" is a step-by-step plan designed to help users progress in their learning, based on their learning goals and timeframe.

[0511] "Real-time" refers to the characteristic of quickly responding to the user's emotional state and learning progress, and providing appropriate information almost instantly.

[0512] This educational support system consists of users, terminals, and a server. Users access the learning platform and input their learning goals, elective subjects, and past history information into the terminal. After receiving this input information, the terminal transmits it to the server using a secure communication method.

[0513] On the server, the processing unit uses an emotion engine to analyze the user's emotional state based on the received input information. The emotion engine uses natural language processing (NLP) techniques to identify emotions such as positive, negative, or neutral from the input text.

[0514] The analyzed emotional state is used by the server to generate responses to the user using a generative AI model. Based on the user's emotional state and selected knowledge areas, the generative AI model provides personalized and appropriate educational resources, such as learning materials and practice exercises. Furthermore, the generative model also constructs a learning plan according to the user's learning goals and timeframe.

[0515] The server prepares and sends generated, personalized responses and tailored educational materials to the terminal. The terminal displays these to the user, assisting them in their learning. The terminal also continuously records the user's learning progress and new sentiment data, and feeds this back to the server.

[0516] As a concrete example, consider a scenario where a user is struggling to understand a new mathematical concept. If the emotion engine recognizes the user's frustration through facial expressions and text input via the device, the server uses a generative AI model to generate easy-to-understand learning materials, including detailed explanations and basic examples, and sends them to the device.

[0517] An example of a prompt used in this system is, "What support do you need to understand a new mathematical concept?" Such prompts allow the generative AI model to generate responses tailored to the user's needs.

[0518] In this way, the educational support system utilizes generative AI models and an emotion engine to provide a dynamic and adaptive learning experience tailored to the user's emotional state.

[0519] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0520] Step 1:

[0521] The user accesses the learning platform and enters learning objectives, elective subjects, and past history information into the terminal. The input is sent to the terminal as text and selection items. The terminal processes the received data and prepares it to send to the server. At this point, the input is the user's learning-related information, and the output is formatted data ready to be sent to the server.

[0522] Step 2:

[0523] The server sends data to the emotion engine based on the formatted data received from the terminal. The emotion engine uses natural language processing techniques to analyze the input text data to determine emotional states such as positive, negative, and neutral. Specifically, it performs emotion scoring based on keywords in the text and their context. The input for this step is the user's text data, and the output is the result of the emotional state determination.

[0524] Step 3:

[0525] The server, based on the output (emotional state) from the emotion engine, invokes a generative AI model to generate personalized responses for the user. The generative AI model creates appropriate learning materials and exercises based on the user's emotional state and selected subjects. In operation, it generates prompt sentences according to the emotional state and creates appropriate responses based on those prompts. The inputs for this step are the emotional state and prompt sentences, and the outputs are personalized responses and learning materials.

[0526] Step 4:

[0527] The server sends personalized responses and learning materials created by the generative model to the terminal. The terminal receives these and displays them to the user. Specifically, the terminal displays text and learning materials on the screen, providing an easily accessible interface for the user. The input is the response data from the server, and the output is the information displayed to the user.

[0528] Step 5:

[0529] The user progresses through the learning process based on the information displayed on the device. The device records the learning progress and responses, and collects new emotional state data. The device then feeds this new data back to the server. In this process, the input is the user's learning activity and emotional responses, and the output is the learning progress and emotional data based on that activity.

[0530] This entire process allows users to receive real-time, emotion-responsive learning support.

[0531] (Application Example 2)

[0532] Next, we will explain application example 2. In the following explanation, 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."

[0533] In today's learning environment, uniform teaching methods fail to adequately address the diverse needs and emotions of learners, resulting in challenges that impact learning efficiency and motivation. In particular, providing customized learning support tailored to individual emotional states is difficult, making real-time, appropriate educational assistance essential.

[0534] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0535] In this invention, the server includes means for receiving input information from a user, means for using a natural language processing engine to analyze the input information and the user's emotions, and means for using a generative model to generate personalized responses according to the emotional state based on the analysis results. This enables dynamic learning support that responds to the user's emotional state.

[0536] "User" refers to an individual who uses the system to learn.

[0537] "Input information" refers to information that users provide to the system, including learning objectives, courses taken, and past learning history.

[0538] A "natural language processing engine" is software designed to understand and analyze human language, and in particular, it has the ability to analyze emotions from user input.

[0539] "Emotion" refers to the user's emotional state during learning, and includes positive, negative, and neutral emotional states.

[0540] "Personalized responses" refer to appropriately tailored feedback and learning materials that are generated based on the user's specific learning situation and emotional state.

[0541] A "generative model" is an algorithm or program that automatically generates personalized responses based on input information and analyzed emotions.

[0542] "Dynamic learning support" refers to flexible educational support that is immediately adapted to the user's real-time emotional state and learning progress.

[0543] The system that implements this application example processes user input in real time to support learning. Users access the learning platform using devices such as smartphones and tablets and input information such as learning goals, courses taken, and past learning history.

[0544] The device sends this information to the server. The server uses a natural language processing engine to analyze the user's emotions from this information. Natural language processing libraries such as SpaCy are used for this analysis. Based on the analyzed emotional data, a generative AI model generates a personalized response. AI model libraries such as Transformers are used for the generative model's algorithm.

[0545] The generated responses may include learning materials and feedback tailored to the user's emotional state. For example, if the user's motivation to learn is low, explanations in a gentle tone to reduce stress may be included. Conversely, if motivation is high, challenging exercises may be provided.

[0546] For example, if the emotion engine detects user frustration when a user is facing a difficult mathematical concept, the system will generate educational materials that include a detailed explanation along with an encouraging message. By inputting a prompt such as, "A 3-year-old child is feeling frustrated while learning numbers. Please suggest a way to play counting games in a gentle tone," into the generative model and adjusting the content, appropriate learning support can be provided.

[0547] In this way, the system can dynamically respond to the user's real-time needs, enabling it to provide a personalized learning experience.

[0548] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0549] Step 1:

[0550] Users access the learning platform using devices such as smartphones and tablets, and input their learning goals, courses, and past learning history. This information is collected on the device as user input data.

[0551] Step 2:

[0552] The terminal sends the aggregated input data to the server. The server receives the input data and begins analysis using a natural language processing engine. The input in this process is the user's input information, and the output is the analyzed emotional data. Specifically, the input text is classified into positive, negative, and neutral states using tools such as SpaCy.

[0553] Step 3:

[0554] The server provides prompts to the generative AI model based on the analyzed emotional data. These prompts include detailed instructions tailored to the user's emotional state. The generative AI model uses Transformers to generate personalized responses based on these prompts. The input is a prompt containing the analyzed emotional data, and the output is a customized response.

[0555] Step 4:

[0556] The server sends the personalized response generated by the generative AI model to the user's device. The user can then receive and view this response on their device. The input is the generated response, and the output is the display state on the device.

[0557] Step 5:

[0558] The user progresses through the learning process based on the displayed responses. The device receives new inputs and feedback from the user and sends them back to the server. This new input information becomes the input information for the next step (Step 1), and the process is repeated. Here, the new input information is sent back to the system again, and the process loops, enabling real-time learning support.

[0559] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0560] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0561] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0562] [Fourth Embodiment]

[0563] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0564] As shown in Figure 7, the 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.

[0565] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0566] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0567] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0568] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0569] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0570] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0571] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0572] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0573] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0574] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0575] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0576] This invention is implemented as a system that provides personalized educational support using a generative AI model. This system primarily consists of a server, terminals, and users. The respective roles are detailed below.

[0577] First, the user enters learning-related information into the terminal. This information includes, for example, the subject they want to study, their current learning status, and their goals. This information is then sent to the server via the terminal.

[0578] The server uses a generative AI model to generate responses tailored to the user based on the received input information. The generative AI model employs natural language processing techniques to analyze user requests and generate the most appropriate learning materials and answers. Furthermore, the server can also generate relevant practice problems based on the user's past learning data and selected subjects. This allows users to receive learning materials that meet their individual needs.

[0579] Next, the server sends the generated responses and learning materials to the terminal, which then displays them to the user. The user can then proceed with their learning based on the displayed information. The system can also record the user's learning progress and use this information to improve future learning support.

[0580] For example, if a user wants to efficiently learn differential equations, they input their study plan and current level of understanding using their device. The server then generates introductory materials and practice problems tailored to the user's needs and sends them to the user's device. In this way, learners can progress through their studies using materials that match their level of understanding.

[0581] Thus, in the embodiments of the present invention, a flexible and individualized learning experience that meets the needs of learners can be provided, and the burden on teachers can be reduced.

[0582] The following describes the processing flow.

[0583] Step 1:

[0584] Users log in to the learning platform and enter the subjects or topics they wish to study into their device. During this process, users also provide information about their current learning status and goals.

[0585] Step 2:

[0586] The terminal sends user input information to the server. This process uses a secure and reliable communication protocol.

[0587] Step 3:

[0588] The server analyzes the received user information and passes it to the generative AI model. The generative AI model understands the user's intent and generates responses tailored to their individual learning needs.

[0589] Step 4:

[0590] The server selects or generates relevant learning materials and practice problems based on the responses created by the generation AI model. Here, content is selected according to the user's past learning history and interests.

[0591] Step 5:

[0592] The server sends the generated learning content to the terminal. The transmitted information is structured in a format that is easily understandable to the user.

[0593] Step 6:

[0594] The device displays received learning materials and responses to the user. The user can review the provided information and ask further questions as needed.

[0595] Step 7:

[0596] The device records the user's progress as they learn and periodically sends this information to the server. This data is stored on the server to help support future learning sessions.

[0597] (Example 1)

[0598] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0599] In educational settings, there is a need to provide individualized learning support tailored to each learner's level and goals, and to create an efficient learning environment. However, existing systems fail to adequately address the diverse needs of learners, making it difficult to reduce the burden on teachers. Therefore, there is a need for a flexible system that automatically generates and presents appropriate learning materials and practice problems based on learner input.

[0600] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0601] In this invention, the server includes means for receiving information from users, means for transmitting said information to a computing device via a communication device, and means for using a generative model to generate optimal answers and learning materials based on said information using natural language processing technology. This makes it possible to provide learning materials that meet the individual needs of each learner.

[0602] "Means of receiving information from users" refers to a function that collects data on subjects, understanding levels, and learning objectives entered by learners through their devices.

[0603] "Means of transmitting to a computing device via a communication device" refers to the technology of using network communication to transfer information from a terminal to a server.

[0604] "Natural language processing technology" is a computer technology that analyzes and understands human language and generates appropriate information and responses.

[0605] "Methods using generative models" refer to methods for generating appropriate training materials and answers using AI based on input information.

[0606] "Optimal answers and learning materials" refer to knowledge and practice exercises that are provided in a format best suited to the learner's needs and level of understanding.

[0607] "Educational materials tailored to individual needs" refer to educational materials provided in a format that is adapted to each learner's learning goals and level.

[0608] This invention is an individualized learning support system using a generative AI model. The user inputs information about the subject they wish to learn, their goals, and their current level of understanding via a terminal. This input is registered on the terminal via a keyboard or touch panel. This information is then transmitted to a server via a communication device.

[0609] The server analyzes this information and uses a generative AI model to generate the most suitable learning materials and responses for the user. Natural language processing technology is used in this analysis process to understand the user's input and generate appropriate responses. The server can also generate exercises and learning materials tailored to the user's individual needs based on their past learning history and selected subjects.

[0610] The generated materials and responses are sent from the server to the terminal and displayed to the user. The user can then efficiently proceed with their learning based on the presented materials. Furthermore, the user's learning progress is recorded by the system and used to support future learning sessions.

[0611] As a concrete example, if a user wants to learn differential equations, they would enter a prompt message on their terminal such as, "I want to learn the basics of differential equations. My current understanding is at a beginner level, and I would like specific practice problems and explanations." Based on this information, the system uses a generative AI model on the server to generate basic materials and practice problems, which are then provided to the user. In this way, the user can continue learning at their own pace and according to their level of understanding.

[0612] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0613] Step 1:

[0614] The user operates the device and inputs learning-related information. This input includes, for example, the subjects they want to study, their current learning status, and their goals. This information is received through forms or applications on the device and stored as digital data in the device's memory.

[0615] Step 2:

[0616] The terminal initializes network communication to send the entered information to the server. At this time, the entered information is encoded in an appropriate data format, such as JSON or XML. The terminal sends this to the server via the internet. Once the transmitted data reaches the server, it is ready for analysis.

[0617] Step 3:

[0618] The server analyzes the received user information. Specifically, it uses natural language processing techniques to decode the information and build context for the generative AI model. In this process, the server analyzes the content of the received data and identifies the learning content requested by the user. For example, if the user is looking for resources on differential equations, that information is extracted as context.

[0619] Step 4:

[0620] The server utilizes a generative AI model to generate learning materials and responses tailored to the user. In this process, the AI ​​model receives contextual information as input and outputs numerical or documentary educational content. The generated output includes specific practice problems and links to reference materials.

[0621] Step 5:

[0622] The server sends the generated data and responses back to the terminal. During transmission, the data is encoded and sent in the appropriate format. The server verifies the integrity of the information to ensure the user terminal can receive it.

[0623] Step 6:

[0624] The device displays the received information to the user. In doing so, the device decodes the received data and formats it to fit the user interface. The user can then begin learning based on the displayed materials and progress at their own pace.

[0625] Step 7:

[0626] Users can re-enter their progress and results as they learn into the device. The device collects this data and records it as learning history data. The learning data is sent to the server as needed to help support future learning.

[0627] (Application Example 1)

[0628] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] In today's educational environment, providing learners with individualized learning experiences is challenging. Furthermore, educational content is often uniform, making it difficult to accommodate diverse learning styles and progress. Additionally, online education offers limited means for efficiently tracking learning outcomes, requiring adjustments to maximize learning effectiveness.

[0630] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0631] In this invention, the server includes means for receiving input information from a user, means for using a generative model that generates personalized responses based on the input information, means for transmitting and displaying the generated responses on the user's device, display means for providing an interactive learning experience in a virtual space, and tracking means for recording learning progress and reflecting it in future learning support. This enables the provision of appropriate learning content to each learner, realization of a personalized learning experience, and effective improvement of learning outcomes.

[0632] A "user" is an individual or organization that provides input information for learning using this system.

[0633] "Input information" refers to data provided by the user regarding their learning, including information such as the field they wish to study, their goals, and their current learning status.

[0634] A "generative model" is a model that uses AI technology to create the optimal response for the learner based on the input information.

[0635] A "user device" refers to a terminal device used by a user to display the generated response or content.

[0636] An "interactive learning experience" is a form of learning in which users can engage with educational content in a virtual space in a two-way manner.

[0637] "Display means" refers to technologies that present generated responses or virtual spaces to users.

[0638] "A tracking mechanism that records progress and reflects it in future learning support" refers to a function that saves the user's learning progress and appropriately adjusts the content of the next learning session based on that progress.

[0639] This invention describes a method for implementing a system that provides a personalized learning experience using a generative AI model.

[0640] The server has a means of receiving input information and collects data on learning subjects, goals, and progress provided by the user. Based on this information, the server uses a generative AI model to generate optimal learning content. This generative AI model applies widely used natural language processing techniques and is used to create materials and questions that are suitable for the user's needs.

[0641] The generated content is sent to the user's device, a terminal, and displayed. Through this terminal, the user enjoys an interactive learning experience in a virtual space. Specific hardware such as smart glasses and head-mounted displays are used. Furthermore, general generative model APIs can be used as the generative AI model.

[0642] Furthermore, the server has a means of tracking learning progress and recording the user's learning data. This can then be used to improve future learning support, thereby enhancing the effectiveness of the learning process.

[0643] As a concrete example, if a user expresses a desire to learn "mechanics in physics" and inputs their current level of understanding and learning goals, the server will generate a prompt message such as "Generate interactive VR learning materials to teach the fundamental concepts of mechanics in physics that the user wishes to learn," and will use a generation AI model to generate relevant learning materials. Providing a flexible and personalized learning experience tailored to the user is the essence of this invention.

[0644] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0645] Step 1:

[0646] The user uses a device to input information about the topic they want to study, their current learning status, and their goals. This input may include, for example, "Physics" or "Understanding Basic Concepts." This information is then sent from the device to the server.

[0647] Step 2:

[0648] The server analyzes the received input information and creates a prompt based on its content. This prompt serves as a command to the generating AI model, specifically something like, "Generate interactive learning materials to teach the fundamental physics concepts the user wants to learn." In this step, the input information is converted into data in the form of a prompt.

[0649] Step 3:

[0650] The server inputs the generated prompt text into the generation AI model, which then generates training content. The generation AI model uses natural language processing techniques to create appropriate training materials and practice problems in response to the prompt. In this process, the input is the prompt text, and the output is the training material.

[0651] Step 4:

[0652] The server receives the generated learning materials and sends them to the user's terminal. This output may include specific text, images, or interactions within a virtual space.

[0653] Step 5:

[0654] Users progress through their learning using learning materials displayed on their devices. The devices implement interactive elements, allowing users to experience learning in a virtual space.

[0655] Step 6:

[0656] The server tracks the user's learning progress and records it in a database. It evaluates the user's behavior and understanding, and uses this information to improve future learning support. The input for this process is user behavior data, and the output is an updated learning profile.

[0657] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0658] This invention is implemented as an educational support system combining a generative AI model and an emotion engine. This system consists primarily of a server, terminals, and users. The specific roles of each are detailed below.

[0659] First, the user accesses the learning platform and enters information into their device, including their learning goals, selected subjects, and past learning history. The device then sends this information to the server for integration with the emotion engine.

[0660] The server processes the received data and uses an emotion engine to recognize the user's emotional state from their text. The emotion engine utilizes natural language processing techniques to analyze the emotions hidden in the user's input and identify emotional states such as positive, negative, or neutral.

[0661] The recognized emotional state is used within the server and utilized in the process by which the generative AI model generates responses to the user. Specifically, if the user is feeling anxious or stressed about learning, the server adjusts the generative model to provide responses and learning materials that alleviate the situation. Conversely, if the user is motivated, the server can respond flexibly by suggesting more challenging exercises.

[0662] The server sends generated, personalized responses and tailored learning materials to the terminal, which then displays them to the user. The user can progress through their learning based on the presented information, and the terminal continuously records their learning progress and new emotional data, feeding it back to the server. This cycle enables real-time learning support that responds to the user's emotional changes.

[0663] As a concrete example, imagine a situation where a user is beginning to learn a new mathematical concept and is having difficulty understanding it. If the emotion engine detects that the user is feeling frustrated based on their facial expressions and word choices in their input via the device, the server uses a generative model to generate easy-to-understand learning materials, including detailed explanations and basic examples, to support the user, and sends them to the device.

[0664] Thus, in the embodiments of the present invention, by using a generative AI model and an emotion engine in combination, it is possible to provide a dynamic and adaptive learning environment and realize an educational experience that is tailored to the individual needs and emotions of the user.

[0665] The following describes the processing flow.

[0666] Step 1:

[0667] Users log in to the learning platform using their device and enter the subjects or topics they want to study, as well as their learning goals. Their learning history data is also stored on their device.

[0668] Step 2:

[0669] The device sends user input information to the server. This information includes information about the user's learning content and emotional information obtained during the interaction process.

[0670] Step 3:

[0671] The server processes the received data and uses an emotion engine to analyze the user's emotional state from the input information. This analysis identifies the type of emotion the user is currently experiencing (e.g., satisfaction, anxiety, stress).

[0672] Step 4:

[0673] Based on the emotional state recognized by the emotion engine, the server uses a generative AI model to generate personalized responses for the user. Specifically, it creates responses that offer further challenges for positive emotions and provide enhanced support for negative emotions.

[0674] Step 5:

[0675] The server sends the generated responses and adjusted learning materials to the terminal. This is designed to include content that reflects the user's emotional state.

[0676] Step 6:

[0677] The terminal displays personalized responses and learning materials received from the server to the user. Based on this, the user progresses through the learning process and, if necessary, enters new questions or feedback.

[0678] Step 7:

[0679] The device continuously records new interaction data resulting from the user's learning activities, along with emotional data, and sends it to the server in real time. This allows the server to track the user's emotional changes in real time and reflect them in subsequent responses.

[0680] (Example 2)

[0681] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0682] Conventional educational support systems struggle to provide dynamic responses and educational content tailored to the individual emotional states of users, resulting in a lack of support that responds to changes in users' emotions and their individual needs. In particular, in learning, users' emotions have a significant impact on learning efficiency and motivation, making appropriate support based on their emotional state essential.

[0683] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0684] In this invention, the server includes means for receiving input information from a user, means for using a computing device that analyzes the emotional state based on the input information, and means for using a generative model that generates an individualized response according to the analyzed emotional state. This makes it possible to provide individualized responses and tailored educational materials in real time according to the user's emotional state, thereby improving the quality of learning.

[0685] A "user" is an individual or group that uses the system to engage in learning activities.

[0686] "Input information" refers to data that users provide to the system via the server, such as learning objectives, selected knowledge areas, and past history information.

[0687] "Emotional state" refers to information indicating a psychological state, such as positive, negative, or neutral, which is analyzed using natural language processing technology based on the user's input information.

[0688] A "computational device" refers to a computer system or related equipment used to process input information and analyze emotional states.

[0689] A "generative model" is a model that implements machine learning algorithms to automatically generate personalized responses and educational resources based on emotional states and input information.

[0690] "Educational resources" refer to educational content such as learning materials and practice exercises that are created using generative models and provided to users.

[0691] A "learning plan" is a step-by-step plan designed to help users progress in their learning, based on their learning goals and timeframe.

[0692] "Real-time" refers to the characteristic of quickly responding to the user's emotional state and learning progress, and providing appropriate information almost instantly.

[0693] This educational support system consists of users, terminals, and a server. Users access the learning platform and input their learning goals, elective subjects, and past history information into the terminal. After receiving this input information, the terminal transmits it to the server using a secure communication method.

[0694] On the server, the processing unit uses an emotion engine to analyze the user's emotional state based on the received input information. The emotion engine uses natural language processing (NLP) techniques to identify emotions such as positive, negative, or neutral from the input text.

[0695] The analyzed emotional state is used by the server to generate responses to the user using a generative AI model. Based on the user's emotional state and selected knowledge areas, the generative AI model provides personalized and appropriate educational resources, such as learning materials and practice exercises. Furthermore, the generative model also constructs a learning plan according to the user's learning goals and timeframe.

[0696] The server prepares and sends generated, personalized responses and tailored educational materials to the terminal. The terminal displays these to the user, assisting them in their learning. The terminal also continuously records the user's learning progress and new sentiment data, and feeds this back to the server.

[0697] As a concrete example, consider a scenario where a user is struggling to understand a new mathematical concept. If the emotion engine recognizes the user's frustration through facial expressions and text input via the device, the server uses a generative AI model to generate easy-to-understand learning materials, including detailed explanations and basic examples, and sends them to the device.

[0698] An example of a prompt used in this system is, "What support do you need to understand a new mathematical concept?" Such prompts allow the generative AI model to generate responses tailored to the user's needs.

[0699] In this way, the educational support system utilizes generative AI models and an emotion engine to provide a dynamic and adaptive learning experience tailored to the user's emotional state.

[0700] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0701] Step 1:

[0702] The user accesses the learning platform and enters learning objectives, elective subjects, and past history information into the terminal. The input is sent to the terminal as text and selection items. The terminal processes the received data and prepares it to send to the server. At this point, the input is the user's learning-related information, and the output is formatted data ready to be sent to the server.

[0703] Step 2:

[0704] The server sends data to the emotion engine based on the formatted data received from the terminal. The emotion engine uses natural language processing techniques to analyze the input text data to determine emotional states such as positive, negative, and neutral. Specifically, it performs emotion scoring based on keywords in the text and their context. The input for this step is the user's text data, and the output is the result of the emotional state determination.

[0705] Step 3:

[0706] The server, based on the output (emotional state) from the emotion engine, invokes a generative AI model to generate personalized responses for the user. The generative AI model creates appropriate learning materials and exercises based on the user's emotional state and selected subjects. In operation, it generates prompt sentences according to the emotional state and creates appropriate responses based on those prompts. The inputs for this step are the emotional state and prompt sentences, and the outputs are personalized responses and learning materials.

[0707] Step 4:

[0708] The server sends personalized responses and learning materials created by the generative model to the terminal. The terminal receives these and displays them to the user. Specifically, the terminal displays text and learning materials on the screen, providing an easily accessible interface for the user. The input is the response data from the server, and the output is the information displayed to the user.

[0709] Step 5:

[0710] The user progresses through the learning process based on the information displayed on the device. The device records the learning progress and responses, and collects new emotional state data. The device then feeds this new data back to the server. In this process, the input is the user's learning activity and emotional responses, and the output is the learning progress and emotional data based on that activity.

[0711] This entire process allows users to receive real-time, emotion-responsive learning support.

[0712] (Application Example 2)

[0713] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0714] In today's learning environment, uniform teaching methods fail to adequately address the diverse needs and emotions of learners, resulting in challenges that impact learning efficiency and motivation. In particular, providing customized learning support tailored to individual emotional states is difficult, making real-time, appropriate educational assistance essential.

[0715] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0716] In this invention, the server includes means for receiving input information from a user, means for using a natural language processing engine to analyze the input information and the user's emotions, and means for using a generative model to generate personalized responses according to the emotional state based on the analysis results. This enables dynamic learning support that responds to the user's emotional state.

[0717] "User" refers to an individual who uses the system to learn.

[0718] "Input information" refers to information that users provide to the system, including learning objectives, courses taken, and past learning history.

[0719] A "natural language processing engine" is software designed to understand and analyze human language, and in particular, it has the ability to analyze emotions from user input.

[0720] "Emotion" refers to the user's emotional state during learning, and includes positive, negative, and neutral emotional states.

[0721] "Personalized responses" refer to appropriately tailored feedback and learning materials that are generated based on the user's specific learning situation and emotional state.

[0722] A "generative model" is an algorithm or program that automatically generates personalized responses based on input information and analyzed emotions.

[0723] "Dynamic learning support" refers to flexible educational support that is immediately adapted to the user's real-time emotional state and learning progress.

[0724] The system that implements this application example processes user input in real time to support learning. Users access the learning platform using devices such as smartphones and tablets and input information such as learning goals, courses taken, and past learning history.

[0725] The device sends this information to the server. The server uses a natural language processing engine to analyze the user's emotions from this information. Natural language processing libraries such as SpaCy are used for this analysis. Based on the analyzed emotional data, a generative AI model generates a personalized response. AI model libraries such as Transformers are used for the generative model's algorithm.

[0726] The generated responses may include learning materials and feedback tailored to the user's emotional state. For example, if the user's motivation to learn is low, explanations in a gentle tone to reduce stress may be included. Conversely, if motivation is high, challenging exercises may be provided.

[0727] For example, if the emotion engine detects user frustration when a user is facing a difficult mathematical concept, the system will generate educational materials that include a detailed explanation along with an encouraging message. By inputting a prompt such as, "A 3-year-old child is feeling frustrated while learning numbers. Please suggest a way to play counting games in a gentle tone," into the generative model and adjusting the content, appropriate learning support can be provided.

[0728] In this way, the system can dynamically respond to the user's real-time needs, enabling it to provide a personalized learning experience.

[0729] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0730] Step 1:

[0731] Users access the learning platform using devices such as smartphones and tablets, and input their learning goals, courses, and past learning history. This information is collected on the device as user input data.

[0732] Step 2:

[0733] The terminal sends the aggregated input data to the server. The server receives the input data and begins analysis using a natural language processing engine. The input in this process is the user's input information, and the output is the analyzed emotional data. Specifically, the input text is classified into positive, negative, and neutral states using tools such as SpaCy.

[0734] Step 3:

[0735] The server provides prompts to the generative AI model based on the analyzed emotional data. These prompts include detailed instructions tailored to the user's emotional state. The generative AI model uses Transformers to generate personalized responses based on these prompts. The input is a prompt containing the analyzed emotional data, and the output is a customized response.

[0736] Step 4:

[0737] The server sends the personalized response generated by the generative AI model to the user's device. The user can then receive and view this response on their device. The input is the generated response, and the output is the display state on the device.

[0738] Step 5:

[0739] The user progresses through the learning process based on the displayed responses. The device receives new inputs and feedback from the user and sends them back to the server. This new input information becomes the input information for the next step (Step 1), and the process is repeated. Here, the new input information is sent back to the system again, and the process loops, enabling real-time learning support.

[0740] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0741] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0742] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0743] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0744] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0745] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0746] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0747] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0748] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0749] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0750] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0751] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0752] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0753] 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.

[0754] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0755] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0756] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0757] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0758] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0759] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0760] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0761] The following is further disclosed regarding the embodiments described above.

[0762] (Claim 1)

[0763] A means of receiving input information from the user,

[0764] Means for using a generative model that generates a personalized response based on the input information,

[0765] A means for transmitting the generated response to the user's device and displaying it,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, characterized in that the generation model generates relevant learning materials and practice problems based on the user's selected subjects and past learning history.

[0769] (Claim 3)

[0770] The system according to claim 1, characterized in that the generative model creates a learning plan according to the user's learning goals and learning period.

[0771] "Example 1"

[0772] (Claim 1)

[0773] Means of receiving information from users,

[0774] Means for transmitting the information to a computer via a communication device,

[0775] A means for using a generative model to generate optimal answers and learning materials using natural language processing technology based on the said information,

[0776] A means for transmitting and displaying the generated answers and learning materials on the user's communication device,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, characterized in that the generation model generates relevant exercises based on the user's past learning history and selected learning subjects, and provides learning materials suitable for individual needs.

[0780] (Claim 3)

[0781] The system according to claim 1, characterized in that the generation model constructs a learning plan according to the user's learning goals and set learning deadline, and presents an achievable learning path.

[0782] "Application Example 1"

[0783] (Claim 1)

[0784] A means of receiving input information from the user,

[0785] Means for using a generative model that generates a personalized response based on the input information,

[0786] A means for transmitting the generated response to the user's device and displaying it,

[0787] A display means that provides an interactive learning experience in a virtual space,

[0788] A tracking system to record learning progress and reflect it in future learning support,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, characterized in that the generation model generates relevant learning materials and practice problems based on the user's selected field and past learning history.

[0792] (Claim 3)

[0793] The system according to claim 1, characterized in that the generative model creates a learning plan according to the user's learning goals and learning period.

[0794] "Example 2 of combining an emotion engine"

[0795] (Claim 1)

[0796] A means of receiving input information from the user,

[0797] A means for using a computing device that analyzes emotional state based on the input information,

[0798] Means for using a generative model that generates individualized responses according to the analyzed emotional state,

[0799] A means for transmitting and displaying the generated response and adjusted educational materials on the user's device,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, characterized in that the generation model generates relevant educational resources and practice tasks based on the user's selected knowledge area and historical information.

[0803] (Claim 3)

[0804] The system according to claim 1, characterized in that the generation model constructs a learning plan based on the user's learning achievement goals and timeframe.

[0805] "Application example 2 when combining with an emotional engine"

[0806] (Claim 1)

[0807] A means of receiving input information from the user,

[0808] A means for using a natural language processing engine to analyze the input information and the user's emotions,

[0809] Means for using a generative model that generates individualized responses according to emotional states based on the analysis results,

[0810] If the generated response includes dynamically adjusted learning resources, means for transmitting and displaying its contents on the user's device,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, characterized in that the generation model generates relevant learning materials and practice problems based on the user's selected courses and past learning records, and further adjusts the information according to changes in the user's emotions.

[0814] (Claim 3)

[0815] The system according to claim 1, characterized in that the generative model creates a learning plan according to the user's learning goals and planned learning period, and adjusts the learning approach according to the user's emotional state. [Explanation of Symbols]

[0816] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving input information from the user, Means for using a generative model that generates a personalized response based on the input information, A means for transmitting the generated response to the user's device and displaying it, A display means that provides an interactive learning experience in a virtual space, A tracking system to record learning progress and reflect it in future learning support, A system that includes this.

2. The system according to claim 1, characterized in that the generation model generates relevant learning materials and practice problems based on the user's selected field and past learning history.

3. The system according to claim 1, characterized in that the generation model creates a learning plan according to the user's learning goals and learning period.

Images