system

Abstract

We provide the system. [Solution] A means for generating answers to questions in real time using a generative AI algorithm that analyzes questions received from users, A means of providing learning content in the most optimal format based on the user's learning progress, A means for analyzing a user's learning history and performance data to generate an individually optimized learning plan, A means to enable collaborative learning among multiple users, A means of analyzing trends from user learning data and generating insights to improve the quality of education, A means for providing interactive information to the user's portable display device and displaying visual aids, 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 method for controlling a persona chatbot, which is 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 in 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 modern educational settings, there is a demand for an individually optimized learning experience that caters to the learning needs of each student. However, it is limited for teachers to manage the learning progress of each student and provide appropriate support. Also, the motivation for students to learn independently and continuously is insufficient. As a result, there is a problem that the learning efficiency of students decreases and they cannot achieve sufficient results.

Means for Solving the Problems

[0005] This invention provides a system that analyzes user questions in real time using a generation AI algorithm and generates answers. This system automatically generates an optimal learning plan based on the user's learning status and history, and provides learning content in multiple formats. It also enhances user motivation through a reward system. Furthermore, it addresses these challenges by supporting collaborative learning among multiple users and generating insights to improve the overall quality of education through big data analysis.

[0006] A "generative AI algorithm" is an artificial intelligence technology that analyzes user questions and generates appropriate answers in real time.

[0007] "Real-time" is a temporal concept that indicates that data processing and responses occur immediately.

[0008] "Learning content" refers to educational materials and information for users to use in their studies, including formats such as videos, text, and quizzes.

[0009] A "learning plan" is a plan that outlines the optimal learning method and schedule, customized based on the user's learning needs and progress.

[0010] A "reward system" is a mechanism that awards points or rewards to users based on their learning achievements, with the aim of increasing their motivation to learn.

[0011] "Collaborative learning" refers to learning activities conducted jointly by multiple users, with the aim of mutually deepening their knowledge and understanding.

[0012] "Big data analysis" is a technique that uses statistical methods and machine learning to analyze large amounts of data and discover useful insights and patterns. [Brief explanation of the drawing]

[0013] [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]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] 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.

[0017] 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.

[0018] 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, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a learning agent system using generative AI to improve the learning experience of individual users. This system is operated via the user's terminal, with a server playing a central role.

[0035] Question support function

[0036] The server receives questions submitted by users and analyzes them using natural language processing algorithms. It recognizes questions from text or voice input directly through an interface displayed on the user's device, allowing users to submit questions in various formats. After analysis, the server generates answers using a generative AI model and provides these answers to the user's device in real time. For example, if a user asks, "What are some important historical events?", the server provides a list of relevant historical events.

[0037] Multi-mode learning support

[0038] Users can choose a learning format that suits their learning style. Based on the user's selection, the server generates and sends learning content such as videos, text, and quizzes to the device. For example, if a user selects "video about the energy conversion process," the server selects the corresponding video material and makes it available for viewing.

[0039] Learning plan generation

[0040] The server periodically analyzes the user's learning history and performance data to automatically build an optimized learning plan. This plan is displayed on the user's device, and the user can proceed with their learning based on it. For example, if a user repeatedly struggles with a particular problem in past tests, the server will incorporate additional practice problems related to that problem into the learning plan.

[0041] Collaborative learning function

[0042] This system features functions that facilitate collaborative learning among users. Users can be paired with other users, and the server shares assigned tasks and provides feedback to support collaborative learning. For example, if two users are working together on a project for a given task, the server tracks their progress and adjusts the timeline as needed.

[0043] Big Data Analysis

[0044] The server analyzes the collected learning data and generates insights to improve the quality of education. These insights are provided to educational institutions and users to help plan the next semester and curriculum. For example, if the analysis reveals that a particular learning module is especially effective, new teaching materials can be developed based on it.

[0045] In this way, the system supports the user's learning experience in multiple ways, enabling efficient and effective learning.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] Users enter questions and learning requests on their own devices. This includes text input or voice input.

[0049] Step 2:

[0050] The device sends user input information to the server. The transmitted data includes the question content and details of the learning request.

[0051] Step 3:

[0052] The server analyzes the input data it receives. It uses a generative AI algorithm to understand the input content and classify the information for appropriate processing.

[0053] Step 4:

[0054] The server generates answers and learning content based on the input. For questions, it uses a generation AI model to generate answers in real time, and for learning requests, it selects and generates content in an appropriate format.

[0055] Step 5:

[0056] The server sends generated answers or learning content to the device. This involves real-time communication, allowing users to receive information immediately.

[0057] Step 6:

[0058] The device displays the received data to the user. This allows the user to check their answers and access learning content.

[0059] (Example 1)

[0060] 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."

[0061] There is a need to provide means to improve learning effectiveness by promoting personalized and effective learning and providing optimal content according to the user's learning needs. Conventional systems have difficulty providing appropriate feedback and content based on the user's learning status and history, and often lack functions such as collaborative learning and insight provision. This invention aims to solve these problems.

[0062] 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.

[0063] In this invention, the server includes means for generating responses to information in real time using generative AI technology that analyzes information received from the user, means for providing educational content in an optimal format based on the user's learning status, and means for analyzing the user's learning history and performance data to generate an individually optimized learning plan. This makes it possible to improve the user's learning effectiveness and provide a personalized learning experience.

[0064] "Generative AI technology" is a technology that uses artificial intelligence to analyze user input and automatically generate appropriate responses.

[0065] "Educational content" refers to learning materials and resources tailored to the user's learning needs and circumstances.

[0066] A "learning plan" is a personalized learning schedule and guideline based on the user's learning history and achievements.

[0067] "Collaborative learning" is a learning format that allows multiple users to learn by exchanging knowledge and information with each other.

[0068] "Insights" refer to knowledge and understanding that can be gained by analyzing user learning data and trends, and that can help improve the quality of education.

[0069] "Educational data" refers to a collection of information and materials generated during the learning process, which is used to support the user's learning.

[0070] A "reward structure" refers to a system that awards points or rewards to users based on their learning activities and achievements, and is designed to increase their motivation to learn.

[0071] In this invention, the user uses an interface through their own device to enrich their learning experience. The device sends the user's questions and requests to the server in digital format via text input or voice input. In the case of voice input, the device is equipped with speech recognition software that converts speech into text.

[0072] The server analyzes the received digital data using a software framework for natural language processing (e.g., SpaCy, NLTK). This identifies the intent of the question and the content of the request. Furthermore, it utilizes generative AI models (e.g., OpenAI®, GPT-3®) to generate a response in real time based on the analyzed information. This generated response is sent to the user's terminal in an easy-to-use format.

[0073] For example, if a user asks, "Please tell me more about a famous literary work," the server will gather relevant information, generate an overview and background information about the work, and display it on the terminal. A possible prompt would be, "I want to know about energy conversion. Please give specific examples." Entering such a request will then provide detailed information.

[0074] Furthermore, the server continuously collects and analyzes learning history and performance data to understand the user's learning progress. This allows it to automatically build and provide an optimized learning plan to enhance learning effectiveness. The content comes in a variety of formats, including videos, text, and quizzes, selected according to the user's preferences.

[0075] Furthermore, to facilitate collaborative learning, the server also manages schedules and provides feedback when multiple users work on a project together. This invention aims to promote cooperation among users and improve the quality of learning.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The user either types a question using a terminal or speaks the question aloud. The input data is captured on the terminal in text or audio format. The terminal uses speech recognition software to convert the audio data into text. This entered text is then sent to the server.

[0079] Step 2:

[0080] The server receives text data from the terminal. First, it uses natural language processing software to analyze the text data and interpret the intent of the question and key keywords. This process involves analyzing the grammatical structure of the text and processing the data to understand its meaning.

[0081] Step 3:

[0082] The server uses a generative AI model based on the analysis results to generate responses to questions. At this stage, the server passes a prompt to the generative AI model, requesting it to generate information in accordance with the question. The output of the generative AI model is stored on the server as detailed answers and related information to the question.

[0083] Step 4:

[0084] The server sends the generated response to the user's device. This response data is formatted in a user-friendly format and displayed on the device's interface. The device adjusts the font size and layout appropriately, and uses text-to-speech functionality as needed.

[0085] Step 5:

[0086] When a user selects a specific learning format, the server receives this information and generates corresponding learning content. The server searches an educational database and selects videos, texts, quizzes, or other materials based on the user's choice. The selected content is then sent to the device and provided to the user.

[0087] Step 6:

[0088] The server periodically analyzes the user's learning history and performance data. This analysis uses machine learning models to identify the user's weaknesses and strengths, and performs data calculations to build a learning plan. The optimized learning plan is displayed on the device, and the user can proceed with their learning based on that plan.

[0089] (Application Example 1)

[0090] 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."

[0091] In today's educational environment, providing a learning experience tailored to individual users remains challenging. Furthermore, there is a need for real-time, interactive support to enable learners to acquire knowledge efficiently and effectively. Additionally, there is a lack of means to deliver learning content visually and intuitively while enhancing learning motivation. This makes it difficult to provide optimal education based on each user's individual learning style and progress.

[0092] 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.

[0093] In this invention, the server includes means for analyzing questions received from the user and generating answers in real time, means for providing content in an optimal format based on the user's learning progress, and means for providing interactive information to the user's portable display device and displaying visual aids. As a result, the user can enjoy an individually optimized learning experience and learn more deeply and intuitively through visual aids.

[0094] A "user" is an individual who utilizes this system and is the target audience for improving their learning experience.

[0095] A "generative AI algorithm" is an algorithm that utilizes artificial intelligence to analyze questions received from users and generate appropriate answers.

[0096] "Learning status" refers to the user's current knowledge level, progress, and approach to learning.

[0097] "Learning content" refers to information and learning materials provided to support users' learning, and includes formats such as text, videos, and diagrams.

[0098] A "portable display device" is an electronic device with a display that can be carried and used by the user, enabling the display of information and interaction.

[0099] "Interactive information" refers to information provided through two-way interaction with the user, and it changes dynamically in real time in response to the user's actions and questions.

[0100] "Visual aids" refer to visual content such as diagrams, images, and videos provided to facilitate user understanding.

[0101] The system that realizes this invention functions in cooperation with a user's portable display device and a server. When a user makes a query to the portable display device using voice or text, the data is sent to the server by the device. The server can analyze the received data using a natural language processing algorithm and generate an answer immediately using a generative AI model. The answer is sent to the user's portable display device and, when displayed, is provided along with visual aids such as diagrams as needed.

[0102] The hardware used includes portable display devices, such as smart glasses or smartphones. The system utilizes software such as Google® Cloud Natural Language and OpenAI GPT to perform efficient natural language processing and response generation. It also tracks users' learning history and trends through big data analysis, providing insights to improve the quality of education.

[0103] For example, if a user asks, "I want to learn about the planets in the solar system," the server retrieves detailed information about each planet through a generating AI and displays it on a portable display device along with visual aids such as names, images, and characteristics. An example of a prompt presented to the user would be, "Please tell me how to ask a question so that the generating AI will provide accurate information when I want to learn about the planets in the solar system." This allows users to learn more deeply and intuitively.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The user inputs the question via voice or text into a portable display device. The input data is converted into text data using speech recognition technology on the device and organized as initial data. The output at this stage is parseable question data that is sent to the server.

[0107] Step 2:

[0108] The server analyzes the received question data using natural language processing algorithms. This analysis process helps the server understand the intent and content of the question and identify the information necessary to obtain an appropriate answer. The output, based on the analyzable question data as input, is information request data that is passed to the generative AI model.

[0109] Step 3:

[0110] The server uses a generative AI model to generate answers based on the information request data. The generative AI searches for relevant information and creates answers that fit the question. The generated answer data is the output of this step.

[0111] Step 4:

[0112] The generated response data is sent from the server to the portable display device. The device prepares to visually present the received responses to the user. At this time, visual aids such as diagrams and videos are also included as content, if necessary. The visualized learning content as output is the information that is ultimately displayed to the user.

[0113] Step 5:

[0114] Users can review the displayed answers on a portable display device and request further details as needed. This makes the learning process interactive, allowing users to continuously input new questions and deepen their knowledge. In this step, the visualized learning content can be reused as input material.

[0115] 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.

[0116] This invention provides a learning agent system with a generative AI and an emotion engine to improve the user experience. The system is designed to maximize the user's motivation and achievements in learning and operates through server, terminal, and user interaction.

[0117] Emotion recognition and content customization

[0118] The server uses an emotion engine to analyze the user's emotional state based on data obtained from the user's device. This analysis uses data such as the user's voice tone, facial expressions, and input patterns. The emotion engine determines whether the user is stressed or fully engaged, and customizes the learning content as needed. For example, if the user is facing a task that is too difficult for them to keep up with, the server will either lower the difficulty level of the material or suggest more inspiring content.

[0119] Dynamic learning plan adjustment

[0120] The server dynamically adjusts the learning plan based on the user's emotional data. It provides real-time emotional feedback to deliver an optimal learning experience. This feedback is achieved by updating the learning pace and content guidelines. For example, if the user's emotional state is analyzed as "interested," the server will suggest special projects or experiments that further explore that interest.

[0121] Optimizing emotion-based collaborative learning

[0122] The emotion engine also optimizes pair and group matching by taking emotional states into account during collaborative learning activities with other users. This feature ensures that each user learns with the most suitable partner. For example, if a user shows signs of anxiety, the server selects a more supportive and comfortable partner, creating a collaborative learning environment.

[0123] Thus, by incorporating emotion recognition technology, the present invention provides an environment in which users can learn most effectively and realizes customized learning that meets individual needs.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The user starts a learning session on the device, and the device collects the user's input as data for the emotion engine. This includes voice, facial expressions, input speed, and more.

[0127] Step 2:

[0128] The device sends collected emotional data to the server. The transmitted data includes information necessary to infer the user's emotional state.

[0129] Step 3:

[0130] The server uses an emotion engine to analyze the received emotion data and identify the user's current emotional state. This analysis helps determine whether the user is excited, interested, stressed, or otherwise in a state of mind.

[0131] Step 4:

[0132] The server customizes learning content based on the identified emotional state. Specifically, this may involve adjusting the difficulty level, selecting new materials, or adding relaxation content.

[0133] Step 5:

[0134] The server sends customized content to the user's device. The sent content is optimized for the user's emotional state.

[0135] Step 6:

[0136] The user continues learning using the received content, and the device collects further learning and sentiment data. This generates new data, preparing it for the next cycle.

[0137] Step 7:

[0138] Furthermore, if users wish to engage in collaborative learning, the server will select the most suitable learning partner based on sentiment data from multiple users and notify the user's device. The selection criteria include the user's support needs and willingness to cooperate.

[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] In recent years, with the widespread adoption of online learning environments, providing personalized learning experiences to maximize user motivation and results has become crucial. However, conventional systems lack the functionality to adequately consider users' emotional states and dynamically adjust learning plans. As a result, users may experience stress or lose interest, leading to challenges in achieving optimal learning efficiency.

[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 generating responses to user inquiries in real time using a generative AI method for analyzing user inquiries; means for providing educational materials in an appropriate form based on the user's learning status and emotional state; and means for analyzing the user's learning history, performance data, and emotional data to generate an individually optimized learning plan. This makes it possible to provide a dynamic learning environment that takes the user's emotional state into consideration, and realizes an optimal learning experience tailored to each individual user.

[0144] The "Generative AI Method" is an artificial intelligence algorithm that analyzes user inquiries and automatically generates appropriate responses.

[0145] "User learning status" refers to information that indicates what the user is currently learning and their progress.

[0146] "Emotional state" refers to information that indicates the user's current psychological state, including stress, interest, and concentration.

[0147] "Educational materials" refer to information and content provided to support user learning, and include formats such as text, images, and audio.

[0148] "Learning history" refers to a record of the user's past learning activities, including information such as date, time, content, and results.

[0149] "Performance data" refers to data that shows the results and achievements of a user's learning activities.

[0150] A "personally optimized learning plan" refers to a learning plan that is constructed in a way that is best suited to each individual user, taking into account their learning progress and emotional state.

[0151] "Collaborative learning" refers to learning activities conducted jointly by multiple users, and it is necessary to build mutually complementary relationships in order to maximize its effectiveness.

[0152] "Mutual matching means" refers to methods and processes for selecting the most suitable partner, taking into account the emotional state of the users.

[0153] "Analyzing trends" refers to the process of identifying long-term changes and patterns based on user learning data, and gaining insights from them to improve education.

[0154] This invention provides a learning agent system that utilizes generative AI technology and an emotion engine to improve the user's learning experience. The entire system consists of a server, a terminal, and user interaction.

[0155] The server analyzes data collected from the user's device in real time and uses an emotion engine to evaluate the user's emotional state. Specifically, it processes data such as voice input, camera footage, and text input to determine whether the user is feeling stressed, interested, or otherwise. Machine learning algorithms are used for this analysis.

[0156] After the server acquires sentiment data, it uses a generative AI model to individually optimize learning content. For example, if the sentiment engine determines that a user is facing a difficult task, the server can recommend materials with a lower difficulty level or content that increases motivation.

[0157] Furthermore, the server optimizes collaborative learning with other users by taking into account the user's emotional state. Based on the user's emotional data, it selects the most suitable partner, increasing the efficiency of mutual learning. This makes the learning environment more cooperative and effective.

[0158] For example, if a user starts learning a new language, the server can use an emotion engine to detect at what point the user is confused and use generative AI to suggest appropriate learning materials.

[0159] Examples of specific prompts could include instructions such as, "If the user is feeling stressed, suggest a simple exercise," or "If the user shows interest, suggest a new project," which could be input into the AI ​​generation model.

[0160] The system, configured in this way, aims to provide a dynamic learning experience that takes user emotions into account, thereby improving the quality and efficiency of learning.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The user begins learning and sends data such as voice input, camera footage, and text input through their device.

[0164] The input data includes the user's learning progress and emotional state.

[0165] Following this, the data is sent to the server.

[0166] Step 2:

[0167] The server operates the emotion engine based on the received user data.

[0168] In this process, voice tone and facial expression data are analyzed using machine learning algorithms to determine the user's emotional state. For example, indicators such as stress and interest can be obtained as analysis results.

[0169] The analysis results are stored within the system and used for content adaptation in the next step.

[0170] Step 3:

[0171] The server uses the results of the emotion engine as input and optimizes the learning content using a generative AI model.

[0172] If your emotional state is determined to be "stressed," the system will automatically generate learning materials with a lower difficulty level. Conversely, if you are "interested," materials designed to deepen your knowledge will be selected.

[0173] In this way, the server utilizes a generative AI model to create appropriate prompts and prepare optimized learning materials.

[0174] Step 4:

[0175] The server sends the generated learning content to the user's device.

[0176] The device receives this information and presents it to the user in a way that they can understand visually or aurally. For example, video materials or audio guides may be played.

[0177] This allows users to progress with their learning based on feedback.

[0178] Step 5:

[0179] The server considers user sentiment data to select partners for collaborative learning.

[0180] Based on emotional states, it forms optimal pairings and promotes cooperative relationships between users.

[0181] The pairing results are sent to the device, and the users begin to connect with each other.

[0182] Step 6:

[0183] The server collects user feedback and additional data, which are then used to inform the next learning cycle.

[0184] Based on new sentiment data and learning outcomes, we will update the criteria for content optimization and pairing in the next iteration.

[0185] In this way, the user's learning experience is continuously improved.

[0186] (Application Example 2)

[0187] 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".

[0188] The widespread adoption of online education in the modern era has increased the importance of personalized support for individual learners. However, traditional education systems often fail to consider learners' emotional states, leading to decreased motivation and stress. Furthermore, the lack of dynamic content adjustments and project suggestions based on learners' emotions and interests limits the quality of learning.

[0189] 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.

[0190] In this invention, the server includes means for analyzing the user's emotional state and dynamically adjusting the learning content based on the emotional state; means for recommending highly relevant content based on the user's emotional state; and means for suggesting special projects or discussions based on the user's interests and emotions. This enables effective learning support for individual learners.

[0191] "User emotional state" refers to the psychological and emotional state that the user exhibits through the interface, and it is the element that the system uses to adapt the learning content in real time based on this state.

[0192] "Means of dynamic adjustment" refers to functions that allow the system to modify and optimize learning content and difficulty level based on data analyzed in real time and user feedback.

[0193] A "means of recommending highly relevant content" is a system that automatically selects and provides learning materials and information that match the user's current emotional state and interests.

[0194] "Means of proposing special projects and discussions" refers to a function that creates new challenges and discussion opportunities based on the user's current learning content and emotional state, in order to delve deeper into their interests.

[0195] A "personally optimized learning plan" refers to an educational plan that is customized to the individual learner's characteristics, based on the user's learning history and performance data.

[0196] The system based on this invention provides a personalized learning experience by monitoring the user's emotional state and dynamically adjusting the learning content based on it. The system consists of the following main components:

[0197] The server uses software such as OpenCV and TENSORFLOW® to analyze the user's voice tone and facial expressions in order to process data acquired from the user's terminal. This allows the server to evaluate the user's psychological state in real time and adjust the difficulty level and format of the learning content based on the results. For example, if the user is feeling stressed, the server will simplify the learning content and provide inspiring content.

[0198] The user's device captures data using its camera and microphone and sends it to the server. This allows the system to provide more accurate emotional information and suggest the most suitable learning plan for the user. Furthermore, by integrating notification functions such as Twilio, it is possible to directly communicate feedback and suggestions to the user based on their emotional state.

[0199] For example, if the emotion engine determines that a user is bored during an online history lecture, the server will re-engage the user by suggesting history-related entertainment content or discussion forums. In this way, the system personalizes and improves the learning experience.

[0200] An example of a prompt message is: "If the user's emotional state is determined to be 'lack of interest,' recommend a relevant historical documentary and trigger the creation of a new discussion forum." This can further enhance the user's learning experience.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The device uses the user's camera and microphone to capture the user's facial expression and voice data. The input is real-time acquired voice tone and facial image data, and the output is sent to the server.

[0204] Step 2:

[0205] Based on facial expression and audio data received by the server, the user's emotional state is analyzed using OpenCV and TensorFlow. The input is audio and facial expression data sent from the terminal, and the output is a classification of the user's emotional state into categories such as "interested" and "bored."

[0206] Step 3:

[0207] The server uses the generated AI model to adjust the necessary learning content based on the analyzed emotional state. The input is the emotional state obtained in step 2, and the output is learning content customized for the user.

[0208] Step 4:

[0209] The server sends information about the adjusted learning content to the device via a notification service such as Twilio. The input is the learning content created in step 3, and the output is the content displayed and notified on the user's device.

[0210] Step 5:

[0211] The user reviews the learning content and suggestions received through their device and proceeds with their learning. They also send new sentiment data as feedback. The input is the displayed learning content, and the output is the user's reactions and feedback information.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] This invention provides a learning agent system using generative AI to improve the learning experience of individual users. This system is operated via the user's terminal, with a server playing a central role.

[0229] Question support function

[0230] The server receives questions submitted by users and analyzes them using natural language processing algorithms. It recognizes questions from text or voice input directly through an interface displayed on the user's device, allowing users to submit questions in various formats. After analysis, the server generates answers using a generative AI model and provides these answers to the user's device in real time. For example, if a user asks, "What are some important historical events?", the server provides a list of relevant historical events.

[0231] Multi-mode learning support

[0232] Users can choose a learning format that suits their learning style. Based on the user's selection, the server generates and sends learning content such as videos, text, and quizzes to the device. For example, if a user selects "video about the energy conversion process," the server selects the corresponding video material and makes it available for viewing.

[0233] Learning plan generation

[0234] The server periodically analyzes the user's learning history and performance data to automatically build an optimized learning plan. This plan is displayed on the user's device, and the user can proceed with their learning based on it. For example, if a user repeatedly struggles with a particular problem in past tests, the server will incorporate additional practice problems related to that problem into the learning plan.

[0235] Collaborative learning function

[0236] This system features functions that facilitate collaborative learning among users. Users can be paired with other users, and the server shares assigned tasks and provides feedback to support collaborative learning. For example, if two users are working together on a project for a given task, the server tracks their progress and adjusts the timeline as needed.

[0237] Big Data Analysis

[0238] The server analyzes the collected learning data and generates insights to improve the quality of education. These insights are provided to educational institutions and users to help plan the next semester and curriculum. For example, if the analysis reveals that a particular learning module is especially effective, new teaching materials can be developed based on it.

[0239] In this way, the system supports the user's learning experience in multiple ways, enabling efficient and effective learning.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] Users enter questions and learning requests on their own devices. This includes text input or voice input.

[0243] Step 2:

[0244] The device sends user input information to the server. The transmitted data includes the question content and details of the learning request.

[0245] Step 3:

[0246] The server analyzes the input data it receives. It uses a generative AI algorithm to understand the input content and classify the information for appropriate processing.

[0247] Step 4:

[0248] The server generates answers and learning content based on the input. For questions, it uses a generation AI model to generate answers in real time, and for learning requests, it selects and generates content in an appropriate format.

[0249] Step 5:

[0250] The server sends generated answers or learning content to the device. This involves real-time communication, allowing users to receive information immediately.

[0251] Step 6:

[0252] The device displays the received data to the user. This allows the user to check their answers and access learning content.

[0253] (Example 1)

[0254] 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".

[0255] There is a need to provide means to improve learning effectiveness by promoting personalized and effective learning and providing optimal content according to the user's learning needs. Conventional systems have difficulty providing appropriate feedback and content based on the user's learning status and history, and often lack functions such as collaborative learning and insight provision. This invention aims to solve these problems.

[0256] 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.

[0257] In this invention, the server includes means for generating responses to information in real time using generative AI technology that analyzes information received from the user, means for providing educational content in an optimal format based on the user's learning status, and means for analyzing the user's learning history and performance data to generate an individually optimized learning plan. This makes it possible to improve the user's learning effectiveness and provide a personalized learning experience.

[0258] "Generative AI technology" is a technology that uses artificial intelligence to analyze user input and automatically generate appropriate responses.

[0259] "Educational content" refers to learning materials and resources tailored to the user's learning needs and circumstances.

[0260] A "learning plan" is a personalized learning schedule and guideline based on the user's learning history and achievements.

[0261] "Collaborative learning" is a learning format that allows multiple users to learn by exchanging knowledge and information with each other.

[0262] "Insights" refer to knowledge and understanding that can be gained by analyzing user learning data and trends, and that can help improve the quality of education.

[0263] "Educational data" refers to a collection of information and materials generated during the learning process, which is used to support the user's learning.

[0264] A "reward structure" refers to a system that awards points or rewards to users based on their learning activities and achievements, and is designed to increase their motivation to learn.

[0265] In this invention, the user uses an interface through their own device to enrich their learning experience. The device sends the user's questions and requests to the server in digital format via text input or voice input. In the case of voice input, the device is equipped with speech recognition software that converts speech into text.

[0266] The server analyzes the received digital data using a software framework for natural language processing (e.g., SpaCy, NLTK). This identifies the intent of the question and the content of the request. Furthermore, it utilizes a generative AI model (e.g., OpenAI GPT-3) to generate a response in real time based on the analyzed information. This generated response is sent to the user's terminal in an easy-to-use format.

[0267] For example, if a user asks, "Please tell me more about a famous literary work," the server will gather relevant information, generate an overview and background information about the work, and display it on the terminal. A possible prompt would be, "I want to know about energy conversion. Please give specific examples." Entering such a request will then provide detailed information.

[0268] Furthermore, the server continuously collects and analyzes learning history and performance data to understand the user's learning progress. This allows it to automatically build and provide an optimized learning plan to enhance learning effectiveness. The content comes in a variety of formats, including videos, text, and quizzes, selected according to the user's preferences.

[0269] Furthermore, to facilitate collaborative learning, the server also manages schedules and provides feedback when multiple users work on a project together. This invention aims to promote cooperation among users and improve the quality of learning.

[0270] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0271] Step 1:

[0272] The user either types a question using a terminal or speaks the question aloud. The input data is captured on the terminal in text or audio format. The terminal uses speech recognition software to convert the audio data into text. This entered text is then sent to the server.

[0273] Step 2:

[0274] The server receives text data from the terminal. First, it uses natural language processing software to analyze the text data and interpret the intent of the question and key keywords. This process involves analyzing the grammatical structure of the text and processing the data to understand its meaning.

[0275] Step 3:

[0276] The server uses a generative AI model based on the analysis results to generate responses to questions. At this stage, the server passes a prompt to the generative AI model, requesting it to generate information in accordance with the question. The output of the generative AI model is stored on the server as a detailed answer to the question and related information.

[0277] Step 4:

[0278] The server sends the generated response to the user's device. This response data is formatted in a user-friendly format and displayed on the device's interface. The device adjusts the font size and layout appropriately, and uses text-to-speech functionality as needed.

[0279] Step 5:

[0280] When a user selects a specific learning format, the server receives this information and generates corresponding learning content. The server searches an educational database and selects videos, texts, quizzes, or other materials based on the user's choice. The selected content is then sent to the device and provided to the user.

[0281] Step 6:

[0282] The server periodically analyzes the user's learning history and performance data. In this analysis, a machine learning model is used to identify the user's weaknesses and areas of strength, and data operations are performed to construct a learning plan. The optimized learning plan is displayed on the terminal, and the user can proceed with learning based on that plan.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In the modern educational environment, it is still difficult to provide a learning experience suitable for individual users. Also, real-time interactive support for learners to obtain knowledge efficiently and effectively is required. Furthermore, there is a lack of means to provide learning content visually and intuitively while improving learning motivation. As a result, it is difficult to provide optimal education based on the individual learning styles and progress of users.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0287] In this invention, the server includes means for analyzing a question received from a user and generating an answer in real time, means for providing content in an optimal format based on the user's learning situation, and means for providing interactive information to the user's portable display device and displaying visual assistance information. As a result, the user can enjoy an individually optimized learning experience and can learn more deeply and intuitively through visual assistance.

[0288] The "user" is an individual who uses this system and is the target person aiming to improve the learning experience.

[0289] A "generative AI algorithm" is an algorithm that utilizes artificial intelligence to analyze questions received from users and generate appropriate answers.

[0290] "Learning status" refers to the user's current knowledge level, progress, and approach to learning.

[0291] "Learning content" refers to information and learning materials provided to support users' learning, and includes formats such as text, videos, and diagrams.

[0292] A "portable display device" is an electronic device with a display that can be carried and used by the user, enabling the display of information and interaction.

[0293] "Interactive information" refers to information provided through two-way interaction with the user, and it changes dynamically in real time in response to the user's actions and questions.

[0294] "Visual aids" refer to visual content such as diagrams, images, and videos provided to facilitate user understanding.

[0295] The system that realizes this invention functions in cooperation with a user's portable display device and a server. When a user makes a query to the portable display device using voice or text, the data is sent to the server by the device. The server can analyze the received data using a natural language processing algorithm and generate an answer immediately using a generative AI model. The answer is sent to the user's portable display device and, when displayed, is provided along with visual aids such as diagrams as needed.

[0296] The hardware used includes portable display devices, such as smart glasses or smartphones. The system utilizes software like Google Cloud Natural Language and OpenAI GPT to perform efficient natural language processing and response generation. It also tracks users' learning history and trends through big data analysis, providing insights to improve the quality of education.

[0297] For example, if a user asks, "I want to learn about the planets in the solar system," the server retrieves detailed information about each planet through a generating AI and displays it on a portable display device along with visual aids such as names, images, and characteristics. An example of a prompt presented to the user would be, "Please tell me how to ask a question so that the generating AI will provide accurate information when I want to learn about the planets in the solar system." This allows users to learn more deeply and intuitively.

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The user inputs the question via voice or text into a portable display device. The input data is converted into text data using speech recognition technology on the device and organized as initial data. The output at this stage is parseable question data that is sent to the server.

[0301] Step 2:

[0302] The server analyzes the received question data using natural language processing algorithms. This analysis process helps the server understand the intent and content of the question and identify the information necessary to obtain an appropriate answer. The output, based on the analyzable question data as input, is information request data that is passed to the generative AI model.

[0303] Step 3:

[0304] The server uses a generative AI model to generate an answer based on the information request data. The generative AI searches for relevant information and creates an answer that matches the question content. The generated answer data becomes the output of this step.

[0305] Step 4:

[0306] The generated answer data is sent from the server to the portable display device. The terminal prepares to visually present the received answer to the user. At this time, visual auxiliary information such as illustrations and videos may also be included as content. The visualized learning content as the output is the information finally displayed to the user.

[0307] Step 5:

[0308] The user can check the displayed answer on the portable display device and request more detailed information if necessary. As a result, the learning process proceeds in a two-way manner, and the user can continuously input new questions and deepen their knowledge. In this step, the visualized learning content can be utilized again as input material.

[0309] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0310] The present invention provides a learning agent system having a generative AI and an emotion engine to improve the user experience. The system is designed to maximize the user's learning motivation and achievements and operates through the interaction of the server, the terminal, and the user.

[0311] Emotion Recognition and Content Customization

[0312] The server uses an emotion engine to analyze the user's emotional state based on data obtained from the user's device. This analysis uses data such as the user's voice tone, facial expressions, and input patterns. The emotion engine determines whether the user is stressed or fully engaged, and customizes the learning content as needed. For example, if the user is facing a task that is too difficult for them to keep up with, the server will either lower the difficulty level of the material or suggest more inspiring content.

[0313] Dynamic learning plan adjustment

[0314] The server dynamically adjusts the learning plan based on the user's emotional data. It provides real-time emotional feedback to deliver an optimal learning experience. This feedback is achieved by updating the learning pace and content guidelines. For example, if the user's emotional state is analyzed as "interested," the server will suggest special projects or experiments that further explore that interest.

[0315] Optimizing emotion-based collaborative learning

[0316] The emotion engine also optimizes pair and group matching by taking emotional states into account during collaborative learning activities with other users. This feature ensures that each user learns with the most suitable partner. For example, if a user shows signs of anxiety, the server selects a more supportive and comfortable partner, creating a collaborative learning environment.

[0317] Thus, by incorporating emotion recognition technology, the present invention provides an environment in which users can learn most effectively and realizes customized learning that meets individual needs.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The user starts a learning session on the device, and the device collects the user's input as data for the emotion engine. This includes voice, facial expressions, input speed, and more.

[0321] Step 2:

[0322] The device sends collected emotional data to the server. The transmitted data includes information necessary to infer the user's emotional state.

[0323] Step 3:

[0324] The server uses an emotion engine to analyze the received emotion data and identify the user's current emotional state. This analysis helps determine whether the user is excited, interested, stressed, or otherwise in a state of mind.

[0325] Step 4:

[0326] The server customizes learning content based on the identified emotional state. Specifically, this may involve adjusting the difficulty level, selecting new materials, or adding relaxation content.

[0327] Step 5:

[0328] The server sends customized content to the user's device. The sent content is optimized for the user's emotional state.

[0329] Step 6:

[0330] The user continues learning using the received content, and the device collects further learning and sentiment data. This generates new data, preparing it for the next cycle.

[0331] Step 7:

[0332] Furthermore, if users wish to engage in collaborative learning, the server will select the most suitable learning partner based on sentiment data from multiple users and notify the user's device. The selection criteria include the user's support needs and willingness to cooperate.

[0333] (Example 2)

[0334] 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".

[0335] In recent years, with the widespread adoption of online learning environments, providing personalized learning experiences to maximize user motivation and results has become crucial. However, conventional systems lack the functionality to adequately consider users' emotional states and dynamically adjust learning plans. As a result, users may experience stress or lose interest, leading to challenges in achieving optimal learning efficiency.

[0336] 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.

[0337] In this invention, the server includes means for generating responses to user inquiries in real time using a generative AI method for analyzing user inquiries; means for providing educational materials in an appropriate form based on the user's learning status and emotional state; and means for analyzing the user's learning history, performance data, and emotional data to generate an individually optimized learning plan. This makes it possible to provide a dynamic learning environment that takes the user's emotional state into consideration, and realizes an optimal learning experience tailored to each individual user.

[0338] The "Generative AI Method" is an artificial intelligence algorithm that analyzes user inquiries and automatically generates appropriate responses.

[0339] "User learning status" refers to information that indicates what the user is currently learning and their progress.

[0340] "Emotional state" refers to information that indicates the user's current psychological state, including stress, interest, and concentration.

[0341] "Educational materials" refer to information and content provided to support user learning, and include formats such as text, images, and audio.

[0342] "Learning history" refers to a record of the user's past learning activities, including information such as date, time, content, and results.

[0343] "Performance data" refers to data that shows the results and achievements of a user's learning activities.

[0344] A "personally optimized learning plan" refers to a learning plan that is constructed in a way that is best suited to each individual user, taking into account their learning progress and emotional state.

[0345] "Collaborative learning" refers to learning activities conducted jointly by multiple users, and it is necessary to build mutually complementary relationships in order to maximize its effectiveness.

[0346] "Mutual matching means" refers to methods and processes for selecting the most suitable partner, taking into account the emotional state of the users.

[0347] "Analyzing trends" refers to the process of identifying long-term changes and patterns based on user learning data, and gaining insights from them to improve education.

[0348] This invention provides a learning agent system that utilizes generative AI technology and an emotion engine to improve the user's learning experience. The entire system consists of a server, a terminal, and user interaction.

[0349] The server analyzes data collected from the user's device in real time and uses an emotion engine to evaluate the user's emotional state. Specifically, it processes data such as voice input, camera footage, and text input to determine whether the user is feeling stressed, interested, or otherwise. Machine learning algorithms are used for this analysis.

[0350] After the server acquires sentiment data, it uses a generative AI model to individually optimize learning content. For example, if the sentiment engine determines that a user is facing a difficult task, the server can recommend materials with a lower difficulty level or content that increases motivation.

[0351] Furthermore, the server optimizes collaborative learning with other users by taking into account the user's emotional state. Based on the user's emotional data, it selects the most suitable partner, increasing the efficiency of mutual learning. This makes the learning environment more cooperative and effective.

[0352] For example, if a user starts learning a new language, the server can use an emotion engine to detect at what point the user is confused and use generative AI to suggest appropriate learning materials.

[0353] Examples of specific prompts could include instructions such as, "If the user is feeling stressed, suggest a simple exercise," or "If the user shows interest, suggest a new project," which could be input into the AI ​​generation model.

[0354] The system, configured in this way, aims to provide a dynamic learning experience that takes user emotions into account, thereby improving the quality and efficiency of learning.

[0355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0356] Step 1:

[0357] The user begins learning and sends data such as voice input, camera footage, and text input through their device.

[0358] The input data includes the user's learning progress and emotional state.

[0359] Following this, the data is sent to the server.

[0360] Step 2:

[0361] The server operates the emotion engine based on the received user data.

[0362] In this process, voice tone and facial expression data are analyzed using machine learning algorithms to determine the user's emotional state. For example, indicators such as stress and interest can be obtained as analysis results.

[0363] The analysis results are stored within the system and used for content adaptation in the next step.

[0364] Step 3:

[0365] The server uses the results of the emotion engine as input and optimizes the learning content using a generative AI model.

[0366] If your emotional state is determined to be "stressed," the system will automatically generate learning materials with a lower difficulty level. Conversely, if you are "interested," materials designed to deepen your knowledge will be selected.

[0367] In this way, the server utilizes a generative AI model to create appropriate prompts and prepare optimized learning materials.

[0368] Step 4:

[0369] The server sends the generated learning content to the user's device.

[0370] The device receives this information and presents it to the user in a way that they can understand visually or aurally. For example, video materials or audio guides may be played.

[0371] This allows users to progress with their learning based on feedback.

[0372] Step 5:

[0373] The server considers user sentiment data to select partners for collaborative learning.

[0374] Based on emotional states, it forms optimal pairings and promotes cooperative relationships between users.

[0375] The pairing results are sent to the device, and the users begin to connect with each other.

[0376] Step 6:

[0377] The server collects user feedback and additional data, which are then used to inform the next learning cycle.

[0378] Based on new sentiment data and learning outcomes, we will update the criteria for content optimization and pairing in the next iteration.

[0379] In this way, the user's learning experience is continuously improved.

[0380] (Application Example 2)

[0381] 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 as the "terminal".

[0382] The widespread adoption of online education in the modern era has increased the importance of personalized support for individual learners. However, traditional education systems often fail to consider learners' emotional states, leading to decreased motivation and stress. Furthermore, the lack of dynamic content adjustments and project suggestions based on learners' emotions and interests limits the quality of learning.

[0383] 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.

[0384] In this invention, the server includes means for analyzing the user's emotional state and dynamically adjusting the learning content based on the emotional state; means for recommending highly relevant content based on the user's emotional state; and means for suggesting special projects or discussions based on the user's interests and emotions. This enables effective learning support for individual learners.

[0385] "User emotional state" refers to the psychological and emotional state that the user exhibits through the interface, and it is the element that the system uses to adapt the learning content in real time based on this state.

[0386] "Means of dynamic adjustment" refers to functions that allow the system to modify and optimize learning content and difficulty level based on data analyzed in real time and user feedback.

[0387] A "means of recommending highly relevant content" is a system that automatically selects and provides learning materials and information that match the user's current emotional state and interests.

[0388] "Means of proposing special projects and discussions" refers to a function that creates new challenges and discussion opportunities based on the user's current learning content and emotional state, in order to delve deeper into their interests.

[0389] A "personally optimized learning plan" refers to an educational plan that is customized to the individual learner's characteristics, based on the user's learning history and performance data.

[0390] The system based on this invention provides a personalized learning experience by monitoring the user's emotional state and dynamically adjusting the learning content based on it. The system consists of the following main components:

[0391] The server uses software such as OpenCV and TensorFlow to analyze the user's voice tone and facial expressions in order to process data acquired from the user's terminal. This allows the server to evaluate the user's psychological state in real time and adjust the difficulty level and format of the learning content based on the results. For example, if the user is feeling stressed, the server will simplify the learning content and provide inspiring material.

[0392] The user's device captures data using its camera and microphone and sends it to the server. This allows the system to provide more accurate emotional information and suggest the most suitable learning plan for the user. Furthermore, by integrating notification functions such as Twilio, it is possible to directly communicate feedback and suggestions to the user based on their emotional state.

[0393] For example, if the emotion engine determines that a user is bored during an online history lecture, the server will re-engage the user by suggesting history-related entertainment content or discussion forums. In this way, the system personalizes and improves the learning experience.

[0394] An example of a prompt message is: "If the user's emotional state is determined to be 'lack of interest,' recommend a relevant historical documentary and trigger the creation of a new discussion forum." This can further enhance the user's learning experience.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] The device uses the user's camera and microphone to capture the user's facial expression and voice data. The input is real-time acquired voice tone and facial image data, and the output is sent to the server.

[0398] Step 2:

[0399] Based on facial expression and audio data received by the server, the user's emotional state is analyzed using OpenCV and TensorFlow. The input is audio and facial expression data sent from the terminal, and the output is a classification of the user's emotional state into categories such as "interested" and "bored."

[0400] Step 3:

[0401] The server uses the generated AI model to adjust the necessary learning content based on the analyzed emotional state. The input is the emotional state obtained in step 2, and the output is learning content customized for the user.

[0402] Step 4:

[0403] The server sends information about the adjusted learning content to the device via a notification service such as Twilio. The input is the learning content created in step 3, and the output is the content displayed and notified on the user's device.

[0404] Step 5:

[0405] The user reviews the learning content and suggestions received through their device and proceeds with their learning. They also send new sentiment data as feedback. The input is the displayed learning content, and the output is the user's reactions and feedback information.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] [Third Embodiment]

[0410] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0411] 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.

[0412] 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).

[0413] 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.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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".

[0422] This invention provides a learning agent system using generative AI to improve the learning experience of individual users. This system is operated via the user's terminal, with a server playing a central role.

[0423] Question support function

[0424] The server receives questions submitted by users and analyzes them using natural language processing algorithms. It recognizes questions from text or voice input directly through an interface displayed on the user's device, allowing users to submit questions in various formats. After analysis, the server generates answers using a generative AI model and provides these answers to the user's device in real time. For example, if a user asks, "What are some important historical events?", the server provides a list of relevant historical events.

[0425] Multi-mode learning support

[0426] Users can choose a learning format that suits their learning style. Based on the user's selection, the server generates and sends learning content such as videos, text, and quizzes to the device. For example, if a user selects "video about the energy conversion process," the server selects the corresponding video material and makes it available for viewing.

[0427] Learning plan generation

[0428] The server periodically analyzes the user's learning history and performance data to automatically build an optimized learning plan. This plan is displayed on the user's device, and the user can proceed with their learning based on it. For example, if a user repeatedly struggles with a particular problem in past tests, the server will incorporate additional practice problems related to that problem into the learning plan.

[0429] Collaborative learning function

[0430] This system features functions that facilitate collaborative learning among users. Users can be paired with other users, and the server shares assigned tasks and provides feedback to support collaborative learning. For example, if two users are working together on a project for a given task, the server tracks their progress and adjusts the timeline as needed.

[0431] Big Data Analysis

[0432] The server analyzes the collected learning data and generates insights to improve the quality of education. These insights are provided to educational institutions and users to help plan the next semester and curriculum. For example, if the analysis reveals that a particular learning module is especially effective, new teaching materials can be developed based on it.

[0433] In this way, the system supports the user's learning experience in multiple ways, enabling efficient and effective learning.

[0434] The following describes the processing flow.

[0435] Step 1:

[0436] Users enter questions and learning requests on their own devices. This includes text input or voice input.

[0437] Step 2:

[0438] The device sends user input information to the server. The transmitted data includes the question content and details of the learning request.

[0439] Step 3:

[0440] The server analyzes the input data it receives. It uses a generative AI algorithm to understand the input content and classify the information for appropriate processing.

[0441] Step 4:

[0442] The server generates answers and learning content based on the input. For questions, it uses a generation AI model to generate answers in real time, and for learning requests, it selects and generates content in an appropriate format.

[0443] Step 5:

[0444] The server sends generated answers or learning content to the device. This involves real-time communication, allowing users to receive information immediately.

[0445] Step 6:

[0446] The device displays the received data to the user. This allows the user to check their answers and access learning content.

[0447] (Example 1)

[0448] 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."

[0449] There is a need to provide means to improve learning effectiveness by promoting personalized and effective learning and providing optimal content according to the user's learning needs. Conventional systems have difficulty providing appropriate feedback and content based on the user's learning status and history, and often lack functions such as collaborative learning and insight provision. This invention aims to solve these problems.

[0450] 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.

[0451] In this invention, the server includes means for generating responses to information in real time using generative AI technology that analyzes information received from the user, means for providing educational content in an optimal format based on the user's learning status, and means for analyzing the user's learning history and performance data to generate an individually optimized learning plan. This makes it possible to improve the user's learning effectiveness and provide a personalized learning experience.

[0452] "Generative AI technology" is a technology that uses artificial intelligence to analyze user input and automatically generate appropriate responses.

[0453] "Educational content" refers to learning materials and resources tailored to the user's learning needs and circumstances.

[0454] A "learning plan" is a personalized learning schedule and guideline based on the user's learning history and achievements.

[0455] "Collaborative learning" is a learning format that allows multiple users to learn by exchanging knowledge and information with each other.

[0456] "Insights" refer to knowledge and understanding that can be gained by analyzing user learning data and trends, and that can help improve the quality of education.

[0457] "Educational data" refers to a collection of information and materials generated during the learning process, which is used to support the user's learning.

[0458] A "reward structure" refers to a system that awards points or rewards to users based on their learning activities and achievements, and is designed to increase their motivation to learn.

[0459] In this invention, the user uses an interface through their own device to enrich their learning experience. The device sends the user's questions and requests to the server in digital format via text input or voice input. In the case of voice input, the device is equipped with speech recognition software that converts speech into text.

[0460] The server analyzes the received digital data using a software framework for natural language processing (e.g., SpaCy, NLTK). This identifies the intent of the question and the content of the request. Furthermore, it utilizes a generative AI model (e.g., OpenAI GPT-3) to generate a response in real time based on the analyzed information. This generated response is sent to the user's terminal in an easy-to-use format.

[0461] For example, if a user asks, "Please tell me more about a famous literary work," the server will gather relevant information, generate an overview and background information about the work, and display it on the terminal. A possible prompt would be, "I want to know about energy conversion. Please give specific examples." Entering such a request will then provide detailed information.

[0462] Furthermore, the server continuously collects and analyzes learning history and performance data to understand the user's learning progress. This allows it to automatically build and provide an optimized learning plan to enhance learning effectiveness. The content comes in a variety of formats, including videos, text, and quizzes, selected according to the user's preferences.

[0463] Furthermore, to facilitate collaborative learning, the server also manages schedules and provides feedback when multiple users work on a project together. This invention aims to promote cooperation among users and improve the quality of learning.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The user either types a question using a terminal or speaks the question aloud. The input data is captured on the terminal in text or audio format. The terminal uses speech recognition software to convert the audio data into text. This entered text is then sent to the server.

[0467] Step 2:

[0468] The server receives text data from the terminal. First, it uses natural language processing software to analyze the text data and interpret the intent of the question and key keywords. This process involves analyzing the grammatical structure of the text and processing the data to understand its meaning.

[0469] Step 3:

[0470] The server uses a generative AI model based on the analysis results to generate responses to questions. At this stage, the server passes a prompt to the generative AI model, requesting it to generate information in accordance with the question. The output of the generative AI model is stored on the server as a detailed answer to the question and related information.

[0471] Step 4:

[0472] The server sends the generated response to the user's device. This response data is formatted in a user-friendly format and displayed on the device's interface. The device adjusts the font size and layout appropriately, and uses text-to-speech functionality as needed.

[0473] Step 5:

[0474] When a user selects a specific learning format, the server receives this information and generates corresponding learning content. The server searches an educational database and selects videos, texts, quizzes, or other materials based on the user's choice. The selected content is then sent to the device and provided to the user.

[0475] Step 6:

[0476] The server periodically analyzes the user's learning history and performance data. This analysis uses machine learning models to identify the user's weaknesses and strengths, and performs data calculations to build a learning plan. The optimized learning plan is displayed on the device, and the user can proceed with their learning based on that plan.

[0477] (Application Example 1)

[0478] 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."

[0479] In today's educational environment, providing a learning experience tailored to individual users remains challenging. Furthermore, there is a need for real-time, interactive support to enable learners to acquire knowledge efficiently and effectively. Additionally, there is a lack of means to deliver learning content visually and intuitively while enhancing learning motivation. This makes it difficult to provide optimal education based on each user's individual learning style and progress.

[0480] 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.

[0481] In this invention, the server includes means for analyzing questions received from the user and generating answers in real time, means for providing content in an optimal format based on the user's learning progress, and means for providing interactive information to the user's portable display device and displaying visual aids. As a result, the user can enjoy an individually optimized learning experience and learn more deeply and intuitively through visual aids.

[0482] A "user" is an individual who utilizes this system and is the target audience for improving their learning experience.

[0483] A "generative AI algorithm" is an algorithm that utilizes artificial intelligence to analyze questions received from users and generate appropriate answers.

[0484] "Learning status" refers to the user's current knowledge level, progress, and approach to learning.

[0485] "Learning content" refers to information and learning materials provided to support users' learning, and includes formats such as text, videos, and diagrams.

[0486] A "portable display device" is an electronic device with a display that can be carried and used by the user, enabling the display of information and interaction.

[0487] "Interactive information" refers to information provided through two-way interaction with the user, and it changes dynamically in real time in response to the user's actions and questions.

[0488] "Visual aids" refer to visual content such as diagrams, images, and videos provided to facilitate user understanding.

[0489] The system that realizes this invention functions in cooperation with a user's portable display device and a server. When a user makes a query to the portable display device using voice or text, the data is sent to the server by the device. The server can analyze the received data using a natural language processing algorithm and generate an answer immediately using a generative AI model. The answer is sent to the user's portable display device and, when displayed, is provided along with visual aids such as diagrams as needed.

[0490] The hardware used includes portable display devices, such as smart glasses or smartphones. The system utilizes software like Google Cloud Natural Language and OpenAI GPT to perform efficient natural language processing and response generation. It also tracks users' learning history and trends through big data analysis, providing insights to improve the quality of education.

[0491] For example, if a user asks, "I want to learn about the planets in the solar system," the server retrieves detailed information about each planet through a generating AI and displays it on a portable display device along with visual aids such as names, images, and characteristics. An example of a prompt presented to the user would be, "Please tell me how to ask a question so that the generating AI will provide accurate information when I want to learn about the planets in the solar system." This allows users to learn more deeply and intuitively.

[0492] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0493] Step 1:

[0494] The user inputs the question via voice or text into a portable display device. The input data is converted into text data using speech recognition technology on the device and organized as initial data. The output at this stage is parseable question data that is sent to the server.

[0495] Step 2:

[0496] The server analyzes the received question data using natural language processing algorithms. This analysis process helps the server understand the intent and content of the question and identify the information necessary to obtain an appropriate answer. The output, based on the analyzable question data as input, is information request data that is passed to the generative AI model.

[0497] Step 3:

[0498] The server uses a generative AI model to generate answers based on the information request data. The generative AI searches for relevant information and creates answers that fit the question. The generated answer data is the output of this step.

[0499] Step 4:

[0500] The generated response data is sent from the server to the portable display device. The device prepares to visually present the received responses to the user. At this time, visual aids such as diagrams and videos are also included as content, if necessary. The visualized learning content as output is the information that is ultimately displayed to the user.

[0501] Step 5:

[0502] Users can review the displayed answers on a portable display device and request further details as needed. This makes the learning process interactive, allowing users to continuously input new questions and deepen their knowledge. In this step, the visualized learning content can be reused as input material.

[0503] 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.

[0504] This invention provides a learning agent system with a generative AI and an emotion engine to improve the user experience. The system is designed to maximize the user's motivation and achievements and operates through server, terminal, and user interaction.

[0505] Emotion recognition and content customization

[0506] The server uses an emotion engine to analyze the user's emotional state based on data obtained from the user's device. This analysis uses data such as the user's voice tone, facial expressions, and input patterns. The emotion engine determines whether the user is stressed or fully engaged, and customizes the learning content as needed. For example, if the user is facing a task that is too difficult for them to keep up with, the server will either lower the difficulty level of the material or suggest more inspiring content.

[0507] Dynamic learning plan adjustment

[0508] The server dynamically adjusts the learning plan based on the user's emotional data. It provides real-time emotional feedback to deliver an optimal learning experience. This feedback is achieved by updating the learning pace and content guidelines. For example, if the user's emotional state is analyzed as "interested," the server will suggest special projects or experiments that further explore that interest.

[0509] Optimizing emotion-based collaborative learning

[0510] The emotion engine also optimizes pair and group matching by taking emotional states into account during collaborative learning activities with other users. This feature ensures that each user learns with the most suitable partner. For example, if a user shows signs of anxiety, the server selects a more supportive and comfortable partner, creating a collaborative learning environment.

[0511] Thus, by incorporating emotion recognition technology, the present invention provides an environment in which users can learn most effectively and realizes customized learning that meets individual needs.

[0512] The following describes the processing flow.

[0513] Step 1:

[0514] The user starts a learning session on the device, and the device collects the user's input as data for the emotion engine. This includes voice, facial expressions, input speed, and more.

[0515] Step 2:

[0516] The device sends collected emotional data to the server. The transmitted data includes information necessary to infer the user's emotional state.

[0517] Step 3:

[0518] The server uses an emotion engine to analyze the received emotion data and identify the user's current emotional state. This analysis helps determine whether the user is excited, interested, stressed, or otherwise in a state of mind.

[0519] Step 4:

[0520] The server customizes learning content based on the identified emotional state. Specifically, this may involve adjusting the difficulty level, selecting new learning materials, or adding relaxation content.

[0521] Step 5:

[0522] The server sends customized content to the user's device. The sent content is optimized for the user's emotional state.

[0523] Step 6:

[0524] The user continues learning using the received content, and the device collects further learning and sentiment data. This generates new data, preparing it for the next cycle.

[0525] Step 7:

[0526] Furthermore, if users wish to engage in collaborative learning, the server will select the most suitable learning partner based on sentiment data from multiple users and notify the user's device. The selection criteria include the user's support needs and willingness to cooperate.

[0527] (Example 2)

[0528] 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."

[0529] In recent years, with the widespread adoption of online learning environments, providing personalized learning experiences to maximize user motivation and results has become crucial. However, conventional systems lack the functionality to adequately consider users' emotional states and dynamically adjust learning plans. As a result, users may experience stress or lose interest, leading to challenges in achieving optimal learning efficiency.

[0530] 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.

[0531] In this invention, the server includes means for generating responses to user inquiries in real time using a generative AI method for analyzing user inquiries; means for providing educational materials in an appropriate form based on the user's learning status and emotional state; and means for analyzing the user's learning history, performance data, and emotional data to generate an individually optimized learning plan. This makes it possible to provide a dynamic learning environment that takes the user's emotional state into consideration, and realizes an optimal learning experience tailored to each individual user.

[0532] The "Generative AI Method" is an artificial intelligence algorithm that analyzes user inquiries and automatically generates appropriate responses.

[0533] "User learning status" refers to information that indicates what the user is currently learning and their progress.

[0534] "Emotional state" refers to information that indicates the user's current psychological state, including stress, interest, and concentration.

[0535] "Educational materials" refer to information and content provided to support user learning, and include formats such as text, images, and audio.

[0536] "Learning history" refers to a record of the user's past learning activities, including information such as date, time, content, and results.

[0537] "Performance data" refers to data that shows the results and achievements of a user's learning activities.

[0538] A "personally optimized learning plan" refers to a learning plan that is constructed in a way that is best suited to each individual user, taking into account their learning progress and emotional state.

[0539] "Collaborative learning" refers to learning activities conducted jointly by multiple users, and it is necessary to build mutually complementary relationships in order to maximize its effectiveness.

[0540] "Mutual matching means" refers to methods and processes for selecting the most suitable partner, taking into account the emotional state of the users.

[0541] "Analyzing trends" refers to the process of identifying long-term changes and patterns based on user learning data, and gaining insights from them to improve education.

[0542] This invention provides a learning agent system that utilizes generative AI technology and an emotion engine to improve the user's learning experience. The entire system consists of a server, a terminal, and user interaction.

[0543] The server analyzes data collected from the user's device in real time and uses an emotion engine to evaluate the user's emotional state. Specifically, it processes data such as voice input, camera footage, and text input to determine whether the user is feeling stressed, interested, or otherwise. Machine learning algorithms are used for this analysis.

[0544] After the server acquires sentiment data, it uses a generative AI model to individually optimize learning content. For example, if the sentiment engine determines that a user is facing a difficult task, the server can recommend materials with a lower difficulty level or content that increases motivation.

[0545] Furthermore, the server optimizes collaborative learning with other users by taking into account the user's emotional state. Based on the user's emotional data, it selects the most suitable partner, increasing the efficiency of mutual learning. This makes the learning environment more cooperative and effective.

[0546] For example, if a user starts learning a new language, the server can use an emotion engine to detect at what point the user is confused and use generative AI to suggest appropriate learning materials.

[0547] Examples of specific prompt messages could be input into the AI ​​generation model such as, "If the user is feeling stressed, suggest a simple exercise," or "If the user shows interest, suggest a new project."

[0548] The system, configured in this way, aims to provide a dynamic learning experience that takes user emotions into account, thereby improving the quality and efficiency of learning.

[0549] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0550] Step 1:

[0551] The user begins learning and sends data such as voice input, camera footage, and text input through their device.

[0552] The input data includes the user's learning progress and emotional state.

[0553] Following this, the data is sent to the server.

[0554] Step 2:

[0555] The server operates the emotion engine based on the received user data.

[0556] In this process, voice tone and facial expression data are analyzed using machine learning algorithms to determine the user's emotional state. For example, indicators such as stress and interest can be obtained as analysis results.

[0557] The analysis results are stored within the system and used for content adaptation in the next step.

[0558] Step 3:

[0559] The server uses the results of the emotion engine as input and optimizes the learning content using a generative AI model.

[0560] If your emotional state is determined to be "stressed," the system will automatically generate learning materials with a lower difficulty level. Conversely, if you are "interested," materials designed to deepen your knowledge will be selected.

[0561] In this way, the server utilizes a generative AI model to create appropriate prompts and prepare optimized learning materials.

[0562] Step 4:

[0563] The server sends the generated learning content to the user's device.

[0564] The device receives this information and presents it to the user in a way that they can understand visually or aurally. For example, video materials or audio guides may be played.

[0565] This allows users to progress with their learning based on feedback.

[0566] Step 5:

[0567] The server considers user sentiment data to select partners for collaborative learning.

[0568] Based on emotional states, it forms optimal pairings and promotes cooperative relationships between users.

[0569] The pairing results are sent to the device, and the users begin to connect with each other.

[0570] Step 6:

[0571] The server collects user feedback and additional data, which are then used to inform the next learning cycle.

[0572] Based on new sentiment data and learning outcomes, we will update the criteria for content optimization and pairing in the next iteration.

[0573] In this way, the user's learning experience is continuously improved.

[0574] (Application Example 2)

[0575] 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."

[0576] The widespread adoption of online education in the modern era has increased the importance of personalized support for individual learners. However, traditional education systems often fail to consider learners' emotional states, leading to decreased motivation and stress. Furthermore, the lack of dynamic content adjustments and project suggestions based on learners' emotions and interests limits the quality of learning.

[0577] 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.

[0578] In this invention, the server includes means for analyzing the user's emotional state and dynamically adjusting the learning content based on the emotional state; means for recommending highly relevant content based on the user's emotional state; and means for suggesting special projects or discussions based on the user's interests and emotions. This enables effective learning support for individual learners.

[0579] "User emotional state" refers to the psychological and emotional state that the user exhibits through the interface, and it is the element that the system uses to adapt the learning content in real time based on this state.

[0580] "Means of dynamic adjustment" refers to functions that allow the system to change and optimize learning content and difficulty level based on data analyzed in real time and user feedback.

[0581] A "means of recommending highly relevant content" is a system that automatically selects and provides learning materials and information that match the user's current emotional state and interests.

[0582] "Means of proposing special projects and discussions" refers to a function that creates new challenges and discussion opportunities based on the user's current learning content and emotional state, in order to delve deeper into their interests.

[0583] A "personally optimized learning plan" refers to an educational plan that is customized to the individual learner's characteristics, based on the user's learning history and performance data.

[0584] The system based on this invention provides a personalized learning experience by monitoring the user's emotional state and dynamically adjusting the learning content based on it. The system consists of the following main components:

[0585] The server uses software such as OpenCV and TensorFlow to analyze the user's voice tone and facial expressions in order to process data acquired from the user's terminal. This allows the server to evaluate the user's psychological state in real time and adjust the difficulty level and format of the learning content based on the results. For example, if the user is feeling stressed, the server will simplify the learning content and provide inspiring material.

[0586] The user's device captures data using its camera and microphone and sends it to the server. This allows the system to provide more accurate emotional information and suggest the most suitable learning plan for the user. Furthermore, by integrating notification functions such as Twilio, it is possible to directly communicate feedback and suggestions to the user based on their emotional state.

[0587] For example, if the emotion engine determines that a user is bored during an online history lecture, the server will re-engage the user by suggesting history-related entertainment content or discussion forums. In this way, the system personalizes and improves the learning experience.

[0588] An example of a prompt message is: "If the user's emotional state is determined to be 'lack of interest,' recommend a relevant historical documentary and trigger the creation of a new discussion forum." This can further enhance the user's learning experience.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The device uses the user's camera and microphone to capture the user's facial expression and voice data. The input is real-time acquired voice tone and facial image data, and the output is sent to the server.

[0592] Step 2:

[0593] Based on facial expression and audio data received by the server, the user's emotional state is analyzed using OpenCV and TensorFlow. The input is audio and facial expression data sent from the terminal, and the output is a classification of the user's emotional state into categories such as "interested" and "bored."

[0594] Step 3:

[0595] The server uses the generated AI model to adjust the necessary learning content based on the analyzed emotional state. The input is the emotional state obtained in step 2, and the output is learning content customized for the user.

[0596] Step 4:

[0597] The server sends information about the adjusted learning content to the device via a notification service such as Twilio. The input is the learning content created in step 3, and the output is the content displayed and notified on the user's device.

[0598] Step 5:

[0599] The user reviews the learning content and suggestions received through their device and proceeds with their learning. They also send new sentiment data as feedback. The input is the displayed learning content, and the output is the user's reactions and feedback information.

[0600] 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.

[0601] 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.

[0602] 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.

[0603] [Fourth Embodiment]

[0604] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0605] 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.

[0606] 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).

[0607] 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.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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".

[0617] This invention provides a learning agent system using generative AI to improve the learning experience of individual users. This system is operated via the user's terminal, with a server playing a central role.

[0618] Question support function

[0619] The server receives questions submitted by users and analyzes them using natural language processing algorithms. It recognizes questions from text or voice input directly through an interface displayed on the user's device, allowing users to submit questions in various formats. After analysis, the server generates answers using a generative AI model and provides these answers to the user's device in real time. For example, if a user asks, "What are some important historical events?", the server provides a list of relevant historical events.

[0620] Multi-mode learning support

[0621] Users can choose a learning format that suits their learning style. Based on the user's selection, the server generates and sends learning content such as videos, text, and quizzes to the device. For example, if a user selects "video about the energy conversion process," the server selects the corresponding video material and makes it available for viewing.

[0622] Learning plan generation

[0623] The server periodically analyzes the user's learning history and performance data to automatically build an optimized learning plan. This plan is displayed on the user's device, and the user can proceed with their learning based on it. For example, if a user repeatedly struggles with a particular problem in past tests, the server will incorporate additional practice problems related to that problem into the learning plan.

[0624] Collaborative learning function

[0625] This system features functions that facilitate collaborative learning among users. Users can be paired with other users, and the server shares assigned tasks and provides feedback to support collaborative learning. For example, if two users are working together on a project for a given task, the server tracks their progress and adjusts the timeline as needed.

[0626] Big Data Analysis

[0627] The server analyzes the collected learning data and generates insights to improve the quality of education. These insights are provided to educational institutions and users to help plan the next semester and curriculum. For example, if the analysis reveals that a particular learning module is especially effective, new teaching materials can be developed based on it.

[0628] In this way, the system supports the user's learning experience in multiple ways, enabling efficient and effective learning.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] Users enter questions and learning requests on their own devices. This includes text input or voice input.

[0632] Step 2:

[0633] The device sends user input information to the server. The transmitted data includes the question content and details of the learning request.

[0634] Step 3:

[0635] The server analyzes the input data it receives. It uses a generative AI algorithm to understand the input content and classify the information for appropriate processing.

[0636] Step 4:

[0637] The server generates answers and learning content based on the input. For questions, it uses a generation AI model to generate answers in real time, and for learning requests, it selects and generates content in an appropriate format.

[0638] Step 5:

[0639] The server sends generated answers or learning content to the device. This involves real-time communication, allowing users to receive information immediately.

[0640] Step 6:

[0641] The device displays the received data to the user. This allows the user to check their answers and access learning content.

[0642] (Example 1)

[0643] 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".

[0644] There is a need to provide means to improve learning effectiveness by promoting personalized and effective learning and providing optimal content according to the user's learning needs. Conventional systems have difficulty providing appropriate feedback and content based on the user's learning status and history, and often lack functions such as collaborative learning and insight provision. This invention aims to solve these problems.

[0645] 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.

[0646] In this invention, the server includes means for generating responses to information in real time using generative AI technology that analyzes information received from the user, means for providing educational content in an optimal format based on the user's learning status, and means for analyzing the user's learning history and performance data to generate an individually optimized learning plan. This makes it possible to improve the user's learning effectiveness and provide a personalized learning experience.

[0647] "Generative AI technology" is a technology that uses artificial intelligence to analyze user input and automatically generate appropriate responses.

[0648] "Educational content" refers to learning materials and resources tailored to the user's learning needs and circumstances.

[0649] A "learning plan" is a personalized learning schedule and guideline based on the user's learning history and achievements.

[0650] "Collaborative learning" is a learning format that allows multiple users to learn by exchanging knowledge and information with each other.

[0651] "Insights" refer to knowledge and understanding that can be gained by analyzing user learning data and trends, and that can help improve the quality of education.

[0652] "Educational data" refers to a collection of information and materials generated during the learning process, which is used to support the user's learning.

[0653] A "reward structure" refers to a system that awards points or rewards to users based on their learning activities and achievements, and is designed to increase their motivation to learn.

[0654] In this invention, the user uses an interface through their own device to enrich their learning experience. The device sends the user's questions and requests to the server in digital format via text input or voice input. In the case of voice input, the device is equipped with speech recognition software that converts speech into text.

[0655] The server analyzes the received digital data using a software framework for natural language processing (e.g., SpaCy, NLTK). This identifies the intent of the question and the content of the request. Furthermore, it utilizes a generative AI model (e.g., OpenAI GPT-3) to generate a response in real time based on the analyzed information. This generated response is sent to the user's terminal in an easy-to-use format.

[0656] For example, if a user asks, "Please tell me more about a famous literary work," the server will gather relevant information, generate an overview and background information about the work, and display it on the terminal. A possible prompt would be, "I want to know about energy conversion. Please give specific examples." Entering such a request will then provide detailed information.

[0657] Furthermore, the server continuously collects and analyzes learning history and performance data to understand the user's learning progress. This allows it to automatically build and provide an optimized learning plan to enhance learning effectiveness. The content comes in a variety of formats, including videos, text, and quizzes, selected according to the user's preferences.

[0658] Furthermore, to facilitate collaborative learning, the server also manages schedules and provides feedback when multiple users work on a project together. This invention aims to promote cooperation among users and improve the quality of learning.

[0659] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0660] Step 1:

[0661] The user either types a question using a terminal or speaks the question aloud. The input data is captured on the terminal in text or audio format. The terminal uses speech recognition software to convert the audio data into text. This entered text is then sent to the server.

[0662] Step 2:

[0663] The server receives text data from the terminal. First, it uses natural language processing software to analyze the text data and interpret the intent of the question and key keywords. This process involves analyzing the grammatical structure of the text and processing the data to understand its meaning.

[0664] Step 3:

[0665] The server uses a generative AI model based on the analysis results to generate responses to questions. At this stage, the server passes a prompt to the generative AI model, requesting it to generate information in accordance with the question. The output of the generative AI model is stored on the server as a detailed answer to the question and related information.

[0666] Step 4:

[0667] The server sends the generated response to the user's device. This response data is formatted in a user-friendly format and displayed on the device's interface. The device adjusts the font size and layout appropriately, and uses text-to-speech functionality as needed.

[0668] Step 5:

[0669] When a user selects a specific learning format, the server receives this information and generates corresponding learning content. The server searches an educational database and selects videos, texts, quizzes, or other materials based on the user's choice. The selected content is then sent to the device and provided to the user.

[0670] Step 6:

[0671] The server periodically analyzes the user's learning history and performance data. This analysis uses machine learning models to identify the user's weaknesses and strengths, and performs data calculations to build a learning plan. The optimized learning plan is displayed on the device, and the user can proceed with their learning based on that plan.

[0672] (Application Example 1)

[0673] 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".

[0674] In today's educational environment, providing a learning experience tailored to individual users remains challenging. Furthermore, there is a need for real-time, interactive support to enable learners to acquire knowledge efficiently and effectively. Additionally, there is a lack of means to deliver learning content visually and intuitively while enhancing learning motivation. This makes it difficult to provide optimal education based on each user's individual learning style and progress.

[0675] 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.

[0676] In this invention, the server includes means for analyzing questions received from the user and generating answers in real time, means for providing content in an optimal format based on the user's learning progress, and means for providing interactive information to the user's portable display device and displaying visual aids. As a result, the user can enjoy an individually optimized learning experience and learn more deeply and intuitively through visual aids.

[0677] A "user" is an individual who utilizes this system and is the target audience for improving their learning experience.

[0678] A "generative AI algorithm" is an algorithm that utilizes artificial intelligence to analyze questions received from users and generate appropriate answers.

[0679] "Learning status" refers to the user's current knowledge level, progress, and approach to learning.

[0680] "Learning content" refers to information and learning materials provided to support users' learning, and includes formats such as text, videos, and diagrams.

[0681] A "portable display device" is an electronic device with a display that can be carried and used by the user, enabling the display of information and interaction.

[0682] "Interactive information" refers to information provided through two-way interaction with the user, and it changes dynamically in real time in response to the user's actions and questions.

[0683] "Visual aids" refer to visual content such as diagrams, images, and videos provided to facilitate user understanding.

[0684] The system that realizes this invention functions in cooperation with a user's portable display device and a server. When a user makes a query to the portable display device using voice or text, the data is sent to the server by the device. The server can analyze the received data using a natural language processing algorithm and generate an answer immediately using a generative AI model. The answer is sent to the user's portable display device and, when displayed, is provided along with visual aids such as diagrams as needed.

[0685] The hardware used includes portable display devices, such as smart glasses or smartphones. The system utilizes software like Google Cloud Natural Language and OpenAI GPT to perform efficient natural language processing and response generation. It also tracks users' learning history and trends through big data analysis, providing insights to improve the quality of education.

[0686] For example, if a user asks, "I want to learn about the planets in the solar system," the server retrieves detailed information about each planet through a generating AI and displays it on a portable display device along with visual aids such as names, images, and characteristics. An example of a prompt presented to the user would be, "Please tell me how to ask a question so that the generating AI will provide accurate information when I want to learn about the planets in the solar system." This allows users to learn more deeply and intuitively.

[0687] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0688] Step 1:

[0689] The user inputs the question via voice or text into a portable display device. The input data is converted into text data using speech recognition technology on the device and organized as initial data. The output at this stage is parseable question data that is sent to the server.

[0690] Step 2:

[0691] The server analyzes the received question data using natural language processing algorithms. This analysis process helps the server understand the intent and content of the question and identify the information necessary to obtain an appropriate answer. The output, based on the analyzable question data as input, is information request data that is passed to the generative AI model.

[0692] Step 3:

[0693] The server uses a generative AI model to generate answers based on the information request data. The generative AI searches for relevant information and creates answers that fit the question. The generated answer data is the output of this step.

[0694] Step 4:

[0695] The generated response data is sent from the server to the portable display device. The device prepares to visually present the received responses to the user. At this time, visual aids such as diagrams and videos are also included as content, if necessary. The visualized learning content as output is the information that is ultimately displayed to the user.

[0696] Step 5:

[0697] Users can review the displayed answers on a portable display device and request further details as needed. This makes the learning process interactive, allowing users to continuously input new questions and deepen their knowledge. In this step, the visualized learning content can be reused as input material.

[0698] 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.

[0699] This invention provides a learning agent system with a generative AI and an emotion engine to improve the user experience. The system is designed to maximize the user's motivation and achievements and operates through server, terminal, and user interaction.

[0700] Emotion recognition and content customization

[0701] The server uses an emotion engine to analyze the user's emotional state based on data obtained from the user's device. This analysis uses data such as the user's voice tone, facial expressions, and input patterns. The emotion engine determines whether the user is stressed or fully engaged, and customizes the learning content as needed. For example, if the user is facing a task that is too difficult for them to keep up with, the server will either lower the difficulty level of the material or suggest more inspiring content.

[0702] Dynamic learning plan adjustment

[0703] The server dynamically adjusts the learning plan based on the user's emotional data. It provides real-time emotional feedback to deliver an optimal learning experience. This feedback is achieved by updating the learning pace and content guidelines. For example, if the user's emotional state is analyzed as "interested," the server will suggest special projects or experiments that further explore that interest.

[0704] Optimizing emotion-based collaborative learning

[0705] The emotion engine also optimizes pair and group matching by taking emotional states into account during collaborative learning activities with other users. This feature ensures that each user learns with the most suitable partner. For example, if a user shows signs of anxiety, the server selects a more supportive and comfortable partner, creating a collaborative learning environment.

[0706] Thus, by incorporating emotion recognition technology, the present invention provides an environment in which users can learn most effectively and realizes customized learning that meets individual needs.

[0707] The following describes the processing flow.

[0708] Step 1:

[0709] The user starts a learning session on the device, and the device collects the user's input as data for the emotion engine. This includes voice, facial expressions, input speed, and more.

[0710] Step 2:

[0711] The device sends collected emotional data to the server. The transmitted data includes information necessary to infer the user's emotional state.

[0712] Step 3:

[0713] The server uses an emotion engine to analyze the received emotion data and identify the user's current emotional state. This analysis helps determine whether the user is excited, interested, stressed, or otherwise in a state of mind.

[0714] Step 4:

[0715] The server customizes learning content based on the identified emotional state. Specifically, this may involve adjusting the difficulty level, selecting new learning materials, or adding relaxation content.

[0716] Step 5:

[0717] The server sends customized content to the user's device. The sent content is optimized for the user's emotional state.

[0718] Step 6:

[0719] The user continues learning using the received content, and the device collects further learning and sentiment data. This generates new data, preparing it for the next cycle.

[0720] Step 7:

[0721] Furthermore, if users wish to engage in collaborative learning, the server will select the most suitable learning partner based on sentiment data from multiple users and notify the user's device. The selection criteria include the user's support needs and willingness to cooperate.

[0722] (Example 2)

[0723] 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".

[0724] In recent years, with the widespread adoption of online learning environments, providing personalized learning experiences to maximize user motivation and results has become crucial. However, conventional systems lack the functionality to adequately consider users' emotional states and dynamically adjust learning plans. As a result, users may experience stress or lose interest, leading to challenges in achieving optimal learning efficiency.

[0725] 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.

[0726] In this invention, the server includes means for generating responses to user inquiries in real time using a generative AI method for analyzing user inquiries; means for providing educational materials in an appropriate form based on the user's learning status and emotional state; and means for analyzing the user's learning history, performance data, and emotional data to generate an individually optimized learning plan. This makes it possible to provide a dynamic learning environment that takes the user's emotional state into consideration, and realizes an optimal learning experience tailored to each individual user.

[0727] The "Generative AI Method" is an artificial intelligence algorithm that analyzes user inquiries and automatically generates appropriate responses.

[0728] "User learning status" refers to information that indicates what the user is currently learning and their progress.

[0729] "Emotional state" refers to information that indicates the user's current psychological state, including stress, interest, and concentration.

[0730] "Educational materials" refer to information and content provided to support user learning, and include formats such as text, images, and audio.

[0731] "Learning history" refers to a record of the user's past learning activities, including information such as date, time, content, and results.

[0732] "Performance data" refers to data that shows the results and achievements of a user's learning activities.

[0733] A "personally optimized learning plan" refers to a learning plan that is constructed in a way that is best suited to each individual user, taking into account their learning progress and emotional state.

[0734] "Collaborative learning" refers to learning activities conducted jointly by multiple users, and it is necessary to build mutually complementary relationships in order to maximize its effectiveness.

[0735] "Mutual matching means" refers to methods and processes for selecting the most suitable partner, taking into account the emotional state of the users.

[0736] "Analyzing trends" refers to the process of identifying long-term changes and patterns based on user learning data, and gaining insights from them to improve education.

[0737] This invention provides a learning agent system that utilizes generative AI technology and an emotion engine to improve the user's learning experience. The entire system consists of a server, a terminal, and user interaction.

[0738] The server analyzes data collected from the user's device in real time and uses an emotion engine to evaluate the user's emotional state. Specifically, it processes data such as voice input, camera footage, and text input to determine whether the user is feeling stressed, interested, or otherwise. Machine learning algorithms are used for this analysis.

[0739] After the server acquires sentiment data, it uses a generative AI model to individually optimize learning content. For example, if the sentiment engine determines that a user is facing a difficult task, the server can recommend materials with a lower difficulty level or content that increases motivation.

[0740] Furthermore, the server optimizes collaborative learning with other users by taking into account the user's emotional state. Based on the user's emotional data, it selects the most suitable partner, increasing the efficiency of mutual learning. This makes the learning environment more cooperative and effective.

[0741] For example, if a user starts learning a new language, the server can use an emotion engine to detect at what point the user is confused and use generative AI to suggest appropriate learning materials.

[0742] Examples of specific prompt messages could be input into the AI ​​generation model such as, "If the user is feeling stressed, suggest a simple exercise," or "If the user shows interest, suggest a new project."

[0743] The system, configured in this way, aims to provide a dynamic learning experience that takes user emotions into account, thereby improving the quality and efficiency of learning.

[0744] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0745] Step 1:

[0746] The user begins learning and sends data such as voice input, camera footage, and text input through their device.

[0747] The input data includes the user's learning progress and emotional state.

[0748] Following this, the data is sent to the server.

[0749] Step 2:

[0750] The server operates the emotion engine based on the received user data.

[0751] In this process, voice tone and facial expression data are analyzed using machine learning algorithms to determine the user's emotional state. For example, indicators such as stress and interest can be obtained as analysis results.

[0752] The analysis results are stored within the system and used for content adaptation in the next step.

[0753] Step 3:

[0754] The server uses the results of the emotion engine as input and optimizes the learning content using a generative AI model.

[0755] If your emotional state is determined to be "stressed," the system will automatically generate learning materials with a lower difficulty level. Conversely, if you are "interested," materials designed to deepen your knowledge will be selected.

[0756] In this way, the server utilizes a generative AI model to create appropriate prompts and prepare optimized learning materials.

[0757] Step 4:

[0758] The server sends the generated learning content to the user's device.

[0759] The device receives this information and presents it to the user in a way that they can understand visually or aurally. For example, video materials or audio guides may be played.

[0760] This allows users to progress with their learning based on feedback.

[0761] Step 5:

[0762] The server considers user sentiment data to select partners for collaborative learning.

[0763] Based on emotional states, it forms optimal pairings and promotes cooperative relationships between users.

[0764] The pairing results are sent to the device, and the users begin to connect with each other.

[0765] Step 6:

[0766] The server collects user feedback and additional data, which are then used to inform the next learning cycle.

[0767] Based on new sentiment data and learning outcomes, we will update the criteria for content optimization and pairing in the next iteration.

[0768] In this way, the user's learning experience is continuously improved.

[0769] (Application Example 2)

[0770] 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".

[0771] The widespread adoption of online education in the modern era has increased the importance of personalized support for individual learners. However, traditional education systems often fail to consider learners' emotional states, leading to decreased motivation and stress. Furthermore, the lack of dynamic content adjustments and project suggestions based on learners' emotions and interests limits the quality of learning.

[0772] 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.

[0773] In this invention, the server includes means for analyzing the user's emotional state and dynamically adjusting the learning content based on the emotional state; means for recommending highly relevant content based on the user's emotional state; and means for suggesting special projects or discussions based on the user's interests and emotions. This enables effective learning support for individual learners.

[0774] "User emotional state" refers to the psychological and emotional state that the user exhibits through the interface, and it is the element that the system uses to adapt the learning content in real time based on this state.

[0775] "Means of dynamic adjustment" refers to functions that allow the system to change and optimize learning content and difficulty level based on data analyzed in real time and user feedback.

[0776] A "means of recommending highly relevant content" is a system that automatically selects and provides learning materials and information that match the user's current emotional state and interests.

[0777] "Means of proposing special projects and discussions" refers to a function that creates new challenges and discussion opportunities based on the user's current learning content and emotional state, in order to delve deeper into their interests.

[0778] A "personally optimized learning plan" refers to an educational plan that is customized to the individual learner's characteristics, based on the user's learning history and performance data.

[0779] The system based on this invention provides a personalized learning experience by monitoring the user's emotional state and dynamically adjusting the learning content based on it. The system consists of the following main components:

[0780] The server uses software such as OpenCV and TensorFlow to analyze the user's voice tone and facial expressions in order to process data acquired from the user's terminal. This allows the server to evaluate the user's psychological state in real time and adjust the difficulty level and format of the learning content based on the results. For example, if the user is feeling stressed, the server will simplify the learning content and provide inspiring material.

[0781] The user's device captures data using its camera and microphone and sends it to the server. This allows the system to provide more accurate emotional information and suggest the most suitable learning plan for the user. Furthermore, by integrating notification functions such as Twilio, it is possible to directly communicate feedback and suggestions to the user based on their emotional state.

[0782] For example, if the emotion engine determines that a user is bored during an online history lecture, the server will re-engage the user by suggesting history-related entertainment content or discussion forums. In this way, the system personalizes and improves the learning experience.

[0783] An example of a prompt message is: "If the user's emotional state is determined to be 'lack of interest,' recommend a relevant historical documentary and trigger the creation of a new discussion forum." This can further enhance the user's learning experience.

[0784] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0785] Step 1:

[0786] The device uses the user's camera and microphone to capture the user's facial expression and voice data. The input is real-time acquired voice tone and facial image data, and the output is sent to the server.

[0787] Step 2:

[0788] Based on facial expression and audio data received by the server, the user's emotional state is analyzed using OpenCV and TensorFlow. The input is audio and facial expression data sent from the terminal, and the output is a classification of the user's emotional state into categories such as "interested" and "bored."

[0789] Step 3:

[0790] The server uses the generated AI model to adjust the necessary learning content based on the analyzed emotional state. The input is the emotional state obtained in step 2, and the output is learning content customized for the user.

[0791] Step 4:

[0792] The server sends information about the adjusted learning content to the device via a notification service such as Twilio. The input is the learning content created in step 3, and the output is the content displayed and notified on the user's device.

[0793] Step 5:

[0794] The user reviews the learning content and suggestions received through their device and proceeds with their learning. They also send new sentiment data as feedback. The input is the displayed learning content, and the output is the user's reactions and feedback information.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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."

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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 to be incorporated by reference.

[0816] The following is further disclosed regarding the embodiments described above.

[0817] (Claim 1)

[0818] A means for generating answers to questions in real time using a generative AI algorithm that analyzes questions received from users,

[0819] A means of providing learning content in the most optimal format based on the user's learning progress,

[0820] A means for analyzing a user's learning history and performance data to generate an individually optimized learning plan,

[0821] A means to enable collaborative learning among multiple users,

[0822] A means of analyzing trends from user learning data and generating insights to improve the quality of education,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, further comprising means for sending the generated response to the user's terminal and displaying it in a format easily understandable to the user.

[0826] (Claim 3)

[0827] The system according to claim 1, comprising a reward system that evaluates the user's learning achievements and awards points or benefits, and includes means for improving the user's motivation to learn.

[0828] "Example 1"

[0829] (Claim 1)

[0830] A means for generating a response to information in real time using generative AI technology that analyzes information received from a user,

[0831] A means of providing educational content in the most optimal format based on the user's learning progress,

[0832] A means for analyzing a user's learning history and performance data to generate an individually optimized learning plan,

[0833] A means to enable collaborative learning among multiple users,

[0834] A means of analyzing trends from user learning information and generating insights to improve the quality of education,

[0835] A processing means for converting input audio into text and recognizing the question,

[0836] Means of understanding information using natural language processing technology,

[0837] A search method for selecting relevant content from educational data,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, further comprising means for sending the generated response to the user's terminal and displaying it in a format easily understandable to the user.

[0841] (Claim 3)

[0842] The system according to claim 1, comprising a reward structure that evaluates the user's learning achievements and awards points or benefits, and includes means for improving the user's motivation to learn.

[0843] "Application Example 1"

[0844] (Claim 1)

[0845] A means for generating answers to questions in real time using a generative AI algorithm that analyzes questions received from users,

[0846] A means of providing learning content in the most optimal format based on the user's learning progress,

[0847] A means for analyzing a user's learning history and performance data to generate an individually optimized learning plan,

[0848] A means to enable collaborative learning among multiple users,

[0849] A means of analyzing trends from user learning data and generating insights to improve the quality of education,

[0850] A means for providing interactive information to the user's portable display device and displaying visual aids,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, further comprising means for transmitting the generated response to the user's portable display device and displaying it in a format easily understandable to the user.

[0854] (Claim 3)

[0855] The system according to claim 1, comprising a reward system that evaluates the user's learning achievements and awards points or benefits, and includes means for improving the user's motivation to learn.

[0856] "Example 2 of combining an emotion engine"

[0857] (Claim 1)

[0858] A means for generating replies to user inquiries in real time using a generation AI method that analyzes user inquiries,

[0859] A means of providing educational materials in an appropriate form based on the user's learning progress and emotional state,

[0860] A means for analyzing a user's learning history, performance data, and sentiment data to generate an individually optimized learning plan,

[0861] To enable collaborative learning among multiple users, a mutual matching method that takes emotional states into consideration is provided,

[0862] A means of analyzing trends from user learning information and generating insights to improve the quality of education,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, further comprising means for sending the generated reply to the user's terminal and displaying it in a format easily understandable to the user.

[0866] (Claim 3)

[0867] The system according to claim 1, comprising an incentive system that evaluates the user's learning achievements and provides reward points or benefits, and includes means for improving the user's motivation to learn.

[0868] "Application example 2 when combining with an emotional engine"

[0869] (Claim 1)

[0870] A means for generating answers to questions in real time using a generative AI algorithm that analyzes questions received from users,

[0871] A means of providing learning content in the most optimal format based on the user's learning progress,

[0872] A means for analyzing a user's learning history and performance data to generate an individually optimized learning plan,

[0873] A means to enable collaborative learning among multiple users,

[0874] A means of analyzing trends from user learning data and generating insights to improve the quality of education,

[0875] A means for analyzing the user's emotional state and dynamically adjusting the learning content based on the said emotional state,

[0876] A means of recommending highly relevant content based on the user's emotional state,

[0877] A means of proposing special projects and discussions based on users' interests and emotions,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, comprising means for sending the generated response to the user's terminal and displaying it in a format easily understandable to the user, and adjusting the display format of the content according to the user's emotional state.

[0881] (Claim 3)

[0882] The system according to claim 1, comprising a reward system that evaluates the user's learning achievements and awards points or benefits, and means of improving the user's motivation to learn by providing emotion-based feedback. [Explanation of Symbols]

[0883] 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 for generating answers to questions in real time using a generative AI algorithm that analyzes questions received from users, A means of providing learning content in the most optimal format based on the user's learning progress, A means for analyzing a user's learning history and performance data to generate an individually optimized learning plan, A means to enable collaborative learning among multiple users, A means of analyzing trends from user learning data and generating insights to improve the quality of education, A means for providing interactive information to the user's portable display device and displaying visual aids, A system that includes this.

2. The system according to claim 1, further comprising means for transmitting the generated response to the user's portable display device and displaying it in a format easily understandable to the user.

3. The system according to claim 1, comprising a reward system that evaluates the user's learning achievements and awards points or benefits, and includes means for improving the user's motivation to learn.

Images